diff --git a/docs/docset.yml b/docs/docset.yml index 6c8192e704978..9ebcf3b966f82 100644 --- a/docs/docset.yml +++ b/docs/docset.yml @@ -22,7 +22,15 @@ cross_links: - kibana - logstash toc: - - toc: reference + - toc: reference/elasticsearch + - toc: reference/community-contributed + - toc: reference/enrich-processor + - toc: reference/search-connectors + - toc: reference/elasticsearch-plugins + - toc: reference/query-languages + - toc: reference/scripting-languages + - toc: reference/text-analysis + - toc: reference/aggregations - toc: release-notes - toc: extend subs: diff --git a/docs/redirects.yml b/docs/redirects.yml index c81bb746b5bb3..88224d8bd23d9 100644 --- a/docs/redirects.yml +++ b/docs/redirects.yml @@ -41,3 +41,102 @@ redirects: 'reference/query-languages/query-dsl-function-score-query.md': 'reference/query-languages/query-dsl/query-dsl-function-score-query.md' 'reference/query-languages/query-dsl-knn-query.md': 'reference/query-languages/query-dsl/query-dsl-knn-query.md' 'reference/query-languages/query-dsl-text-expansion-query.md': 'reference/query-languages/query-dsl/query-dsl-text-expansion-query.md' + + # Related to https://github.com/elastic/elasticsearch/pull/125118 + 'reference/community-contributed.md': 'reference/community-contributed/index.md' + 'reference/data-analysis/aggregations/bucket.md': 'reference/aggregations/bucket.md' + 'reference/data-analysis/aggregations/index.md': 'reference/aggregations/index.md' + 'reference/data-analysis/aggregations/metrics.md': 'reference/aggregations/metrics.md' + 'reference/data-analysis/aggregations/pipeline.md': 'reference/aggregations/pipeline.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md': 'reference/aggregations/search-aggregations-bucket-composite-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md': 'reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md': 'reference/aggregations/search-aggregations-bucket-filter-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md': 'reference/aggregations/search-aggregations-bucket-filters-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md': 'reference/aggregations/search-aggregations-bucket-geodistance-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md': 'reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md': 'reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md': 'reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md': 'reference/aggregations/search-aggregations-bucket-histogram-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md': 'reference/aggregations/search-aggregations-bucket-multi-terms-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md': 'reference/aggregations/search-aggregations-bucket-range-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md': 'reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md': 'reference/aggregations/search-aggregations-bucket-terms-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-change-point-aggregation.md': 'reference/aggregations/search-aggregations-change-point-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md': 'reference/aggregations/search-aggregations-metrics-avg-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md': 'reference/aggregations/search-aggregations-metrics-cardinality-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-geo-line.md': 'reference/aggregations/search-aggregations-metrics-geo-line.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md': 'reference/aggregations/search-aggregations-metrics-geobounds-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-geocentroid-aggregation.md': 'reference/aggregations/search-aggregations-metrics-geocentroid-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md': 'reference/aggregations/search-aggregations-metrics-max-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md': 'reference/aggregations/search-aggregations-metrics-percentile-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md': 'reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-stats-aggregation.md': 'reference/aggregations/search-aggregations-metrics-stats-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md': 'reference/aggregations/search-aggregations-metrics-sum-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md': 'reference/aggregations/search-aggregations-metrics-top-hits-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-metrics-top-metrics.md': 'reference/aggregations/search-aggregations-metrics-top-metrics.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-derivative-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-derivative-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md' + 'reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md': 'reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md' + 'reference/data-analysis/text-analysis/analysis-asciifolding-tokenfilter.md': 'reference/text-analysis/analysis-asciifolding-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-condition-tokenfilter.md': 'reference/text-analysis/analysis-condition-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-htmlstrip-charfilter.md': 'reference/text-analysis/analysis-htmlstrip-charfilter.md' + 'reference/data-analysis/text-analysis/analysis-hunspell-tokenfilter.md': 'reference/text-analysis/analysis-hunspell-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md': 'reference/text-analysis/analysis-keyword-marker-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-kstem-tokenfilter.md': 'reference/text-analysis/analysis-kstem-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-lang-analyzer.md': 'reference/text-analysis/analysis-lang-analyzer.md' + 'reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md': 'reference/text-analysis/analysis-lowercase-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-mapping-charfilter.md': 'reference/text-analysis/analysis-mapping-charfilter.md' + 'reference/data-analysis/text-analysis/analysis-pattern-replace-charfilter.md': 'reference/text-analysis/analysis-pattern-replace-charfilter.md' + 'reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md': 'reference/text-analysis/analysis-pattern-tokenizer.md' + 'reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md': 'reference/text-analysis/analysis-porterstem-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-snowball-tokenfilter.md': 'reference/text-analysis/analysis-snowball-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-standard-analyzer.md': 'reference/text-analysis/analysis-standard-analyzer.md' + 'reference/data-analysis/text-analysis/analysis-standard-tokenizer.md': 'reference/text-analysis/analysis-standard-tokenizer.md' + 'reference/data-analysis/text-analysis/analysis-stemmer-override-tokenfilter.md': 'reference/text-analysis/analysis-stemmer-override-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md': 'reference/text-analysis/analysis-stemmer-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md': 'reference/text-analysis/analysis-stop-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md': 'reference/text-analysis/analysis-synonym-graph-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md': 'reference/text-analysis/analysis-synonym-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md': 'reference/text-analysis/analysis-whitespace-tokenizer.md' + 'reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md': 'reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md' + 'reference/data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md': 'reference/text-analysis/analysis-word-delimiter-tokenfilter.md' + 'reference/data-analysis/text-analysis/analyzer-reference.md': 'reference/text-analysis/analyzer-reference.md' + 'reference/data-analysis/text-analysis/character-filter-reference.md': 'reference/text-analysis/character-filter-reference.md' + 'reference/data-analysis/text-analysis/index.md': 'reference/text-analysis/index.md' + 'reference/data-analysis/text-analysis/normalizers.md': 'reference/text-analysis/normalizers.md' + 'reference/data-analysis/text-analysis/token-filter-reference.md': 'reference/text-analysis/token-filter-reference.md' + 'reference/data-analysis/text-analysis/tokenizer-reference.md': 'reference/text-analysis/tokenizer-reference.md' + 'reference/ingestion-tools/enrich-processor/attachment.md': 'reference/enrich-processor/attachment.md' + 'reference/ingestion-tools/enrich-processor/convert-processor.md': 'reference/enrich-processor/convert-processor.md' + 'reference/ingestion-tools/enrich-processor/csv-processor.md': 'reference/enrich-processor/csv-processor.md' + 'reference/ingestion-tools/enrich-processor/date-index-name-processor.md': 'reference/enrich-processor/date-index-name-processor.md' + 'reference/ingestion-tools/enrich-processor/date-processor.md': 'reference/enrich-processor/date-processor.md' + 'reference/ingestion-tools/enrich-processor/dissect-processor.md': 'reference/enrich-processor/dissect-processor.md' + 'reference/ingestion-tools/enrich-processor/dot-expand-processor.md': 'reference/enrich-processor/dot-expand-processor.md' + 'reference/ingestion-tools/enrich-processor/enrich-processor.md': 'reference/enrich-processor/enrich-processor.md' + 'reference/ingestion-tools/enrich-processor/fingerprint-processor.md': 'reference/enrich-processor/fingerprint-processor.md' + 'reference/ingestion-tools/enrich-processor/geoip-processor.md': 'reference/enrich-processor/geoip-processor.md' + 'reference/ingestion-tools/enrich-processor/grok-processor.md': 'reference/enrich-processor/grok-processor.md' + 'reference/ingestion-tools/enrich-processor/gsub-processor.md': 'reference/enrich-processor/gsub-processor.md' + 'reference/ingestion-tools/enrich-processor/htmlstrip-processor.md': 'reference/enrich-processor/htmlstrip-processor.md' + 'reference/ingestion-tools/enrich-processor/index.md': 'reference/enrich-processor/index.md' + 'reference/ingestion-tools/enrich-processor/inference-processor.md': 'reference/enrich-processor/inference-processor.md' + 'reference/ingestion-tools/enrich-processor/ingest-geo-grid-processor.md': 'reference/enrich-processor/ingest-geo-grid-processor.md' + 'reference/ingestion-tools/enrich-processor/ingest-node-set-security-user-processor.md': 'reference/enrich-processor/ingest-node-set-security-user-processor.md' + 'reference/ingestion-tools/enrich-processor/json-processor.md': 'reference/enrich-processor/json-processor.md' + 'reference/ingestion-tools/enrich-processor/lowercase-processor.md': 'reference/enrich-processor/lowercase-processor.md' + 'reference/ingestion-tools/enrich-processor/pipeline-processor.md': 'reference/enrich-processor/pipeline-processor.md' + 'reference/ingestion-tools/enrich-processor/remove-processor.md': 'reference/enrich-processor/remove-processor.md' + 'reference/ingestion-tools/enrich-processor/rename-processor.md': 'reference/enrich-processor/rename-processor.md' + 'reference/ingestion-tools/enrich-processor/reroute-processor.md': 'reference/enrich-processor/reroute-processor.md' + 'reference/ingestion-tools/enrich-processor/script-processor.md': 'reference/enrich-processor/script-processor.md' + 'reference/ingestion-tools/enrich-processor/set-processor.md': 'reference/enrich-processor/set-processor.md' + 'reference/ingestion-tools/enrich-processor/trim-processor.md': 'reference/enrich-processor/trim-processor.md' + 'reference/ingestion-tools/enrich-processor/user-agent-processor.md': 'reference/enrich-processor/user-agent-processor.md' + 'reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md': 'reference/search-connectors/connectors-ui-in-kibana.md' + 'reference/ingestion-tools/search-connectors/es-connectors-github.md': 'reference/search-connectors/es-connectors-github.md' + 'reference/ingestion-tools/search-connectors/index.md': 'reference/search-connectors/index.md' + 'reference/ingestion-tools/search-connectors/self-managed-connectors.md': 'reference/search-connectors/self-managed-connectors.md' \ No newline at end of file diff --git a/docs/reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md b/docs/reference/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md rename to docs/reference/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md diff --git a/docs/reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md b/docs/reference/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md similarity index 100% rename from docs/reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md rename to docs/reference/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md diff --git a/docs/reference/data-analysis/aggregations/bucket.md b/docs/reference/aggregations/bucket.md similarity index 100% rename from docs/reference/data-analysis/aggregations/bucket.md rename to docs/reference/aggregations/bucket.md diff --git a/docs/images/accuracy_0001.png b/docs/reference/aggregations/images/accuracy_0001.png similarity index 100% rename from docs/images/accuracy_0001.png rename to docs/reference/aggregations/images/accuracy_0001.png diff --git a/docs/images/accuracy_001.png b/docs/reference/aggregations/images/accuracy_001.png similarity index 100% rename from docs/images/accuracy_001.png rename to docs/reference/aggregations/images/accuracy_001.png diff --git a/docs/images/accuracy_01.png b/docs/reference/aggregations/images/accuracy_01.png similarity index 100% rename from docs/images/accuracy_01.png rename to docs/reference/aggregations/images/accuracy_01.png diff --git a/docs/images/dow.png b/docs/reference/aggregations/images/dow.png similarity index 100% rename from docs/images/dow.png rename to docs/reference/aggregations/images/dow.png diff --git a/docs/images/geo_line.png b/docs/reference/aggregations/images/geo_line.png similarity index 100% rename from docs/images/geo_line.png rename to docs/reference/aggregations/images/geo_line.png diff --git a/docs/images/geoshape_grid.png b/docs/reference/aggregations/images/geoshape_grid.png similarity index 100% rename from docs/images/geoshape_grid.png rename to docs/reference/aggregations/images/geoshape_grid.png diff --git a/docs/images/geoshape_hexgrid.png b/docs/reference/aggregations/images/geoshape_hexgrid.png similarity index 100% rename from docs/images/geoshape_hexgrid.png rename to docs/reference/aggregations/images/geoshape_hexgrid.png diff --git a/docs/images/kodiak_geo_line_simplified.png b/docs/reference/aggregations/images/kodiak_geo_line_simplified.png similarity index 100% rename from docs/images/kodiak_geo_line_simplified.png rename to docs/reference/aggregations/images/kodiak_geo_line_simplified.png diff --git a/docs/images/kodiak_geo_line_truncated.png b/docs/reference/aggregations/images/kodiak_geo_line_truncated.png similarity index 100% rename from docs/images/kodiak_geo_line_truncated.png rename to docs/reference/aggregations/images/kodiak_geo_line_truncated.png diff --git a/docs/images/lemmings.png b/docs/reference/aggregations/images/lemmings.png similarity index 100% rename from docs/images/lemmings.png rename to docs/reference/aggregations/images/lemmings.png diff --git a/docs/images/memory.png b/docs/reference/aggregations/images/memory.png similarity index 100% rename from docs/images/memory.png rename to docs/reference/aggregations/images/memory.png diff --git a/docs/images/random-sampler-agg-graph.png b/docs/reference/aggregations/images/random-sampler-agg-graph.png similarity index 100% rename from docs/images/random-sampler-agg-graph.png rename to docs/reference/aggregations/images/random-sampler-agg-graph.png diff --git a/docs/images/relative-error-vs-doc-count.png b/docs/reference/aggregations/images/relative-error-vs-doc-count.png similarity index 100% rename from docs/images/relative-error-vs-doc-count.png rename to docs/reference/aggregations/images/relative-error-vs-doc-count.png diff --git a/docs/reference/data-analysis/aggregations/index.md b/docs/reference/aggregations/index.md similarity index 100% rename from docs/reference/data-analysis/aggregations/index.md rename to docs/reference/aggregations/index.md diff --git a/docs/reference/data-analysis/aggregations/metrics.md b/docs/reference/aggregations/metrics.md similarity index 100% rename from docs/reference/data-analysis/aggregations/metrics.md rename to docs/reference/aggregations/metrics.md diff --git a/docs/reference/data-analysis/aggregations/pipeline.md b/docs/reference/aggregations/pipeline.md similarity index 98% rename from docs/reference/data-analysis/aggregations/pipeline.md rename to docs/reference/aggregations/pipeline.md index a6c16b504e5a2..86dcfc3656181 100644 --- a/docs/reference/data-analysis/aggregations/pipeline.md +++ b/docs/reference/aggregations/pipeline.md @@ -221,7 +221,7 @@ POST /sales/_search ## Dealing with dots in agg names [dots-in-agg-names] -An alternate syntax is supported to cope with aggregations or metrics which have dots in the name, such as the `99.9`th [percentile](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md). This metric may be referred to as: +An alternate syntax is supported to cope with aggregations or metrics which have dots in the name, such as the `99.9`th [percentile](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md). This metric may be referred to as: ```js "buckets_path": "my_percentile[99.9]" diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-adjacency-matrix-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-adjacency-matrix-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-adjacency-matrix-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-adjacency-matrix-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md similarity index 92% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md index 67ffd7b0d6291..4874e4057c668 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Auto-interval date histogram aggregation [search-aggregations-bucket-autodatehistogram-aggregation] -A multi-bucket aggregation similar to the [Date histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) except instead of providing an interval to use as the width of each bucket, a target number of buckets is provided indicating the number of buckets needed and the interval of the buckets is automatically chosen to best achieve that target. The number of buckets returned will always be less than or equal to this target number. +A multi-bucket aggregation similar to the [Date histogram](/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) except instead of providing an interval to use as the width of each bucket, a target number of buckets is provided indicating the number of buckets needed and the interval of the buckets is automatically chosen to best achieve that target. The number of buckets returned will always be less than or equal to this target number. The buckets field is optional, and will default to 10 buckets if not specified. @@ -55,7 +55,7 @@ POST /sales/_search?size=0 } ``` -1. Supports expressive date [format pattern](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) +1. Supports expressive date [format pattern](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) Response: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-categorize-text-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-categorize-text-aggregation.md similarity index 86% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-categorize-text-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-categorize-text-aggregation.md index 4f785a342da34..6e7dac9436932 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-categorize-text-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-categorize-text-aggregation.md @@ -10,7 +10,7 @@ mapped_pages: A multi-bucket aggregation that groups semi-structured text into buckets. Each `text` field is re-analyzed using a custom analyzer. The resulting tokens are then categorized creating buckets of similarly formatted text values. This aggregation works best with machine generated text like system logs. Only the first 100 analyzed tokens are used to categorize the text. ::::{note} -If you have considerable memory allocated to your JVM but are receiving circuit breaker exceptions from this aggregation, you may be attempting to categorize text that is poorly formatted for categorization. Consider adding `categorization_filters` or running under [sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md), [diversified sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md), or [random sampler](/reference/data-analysis/aggregations/search-aggregations-random-sampler-aggregation.md) to explore the created categories. +If you have considerable memory allocated to your JVM but are receiving circuit breaker exceptions from this aggregation, you may be attempting to categorize text that is poorly formatted for categorization. Consider adding `categorization_filters` or running under [sampler](/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md), [diversified sampler](/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md), or [random sampler](/reference/aggregations/search-aggregations-random-sampler-aggregation.md) to explore the created categories. :::: @@ -24,14 +24,14 @@ The algorithm used for categorization was completely changed in version 8.3.0. A `categorization_analyzer` : (Optional, object or string) The categorization analyzer specifies how the text is analyzed and tokenized before being categorized. The syntax is very similar to that used to define the `analyzer` in the [Analyze endpoint](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze). This property cannot be used at the same time as `categorization_filters`. - The `categorization_analyzer` field can be specified either as a string or as an object. If it is a string it must refer to a [built-in analyzer](/reference/data-analysis/text-analysis/analyzer-reference.md) or one added by another plugin. If it is an object it has the following properties: + The `categorization_analyzer` field can be specified either as a string or as an object. If it is a string it must refer to a [built-in analyzer](/reference/text-analysis/analyzer-reference.md) or one added by another plugin. If it is an object it has the following properties: :::::{dropdown} Properties of `categorization_analyzer` `char_filter` - : (array of strings or objects) One or more [character filters](/reference/data-analysis/text-analysis/character-filter-reference.md). In addition to the built-in character filters, other plugins can provide more character filters. This property is optional. If it is not specified, no character filters are applied prior to categorization. If you are customizing some other aspect of the analyzer and you need to achieve the equivalent of `categorization_filters` (which are not permitted when some other aspect of the analyzer is customized), add them here as [pattern replace character filters](/reference/data-analysis/text-analysis/analysis-pattern-replace-charfilter.md). + : (array of strings or objects) One or more [character filters](/reference/text-analysis/character-filter-reference.md). In addition to the built-in character filters, other plugins can provide more character filters. This property is optional. If it is not specified, no character filters are applied prior to categorization. If you are customizing some other aspect of the analyzer and you need to achieve the equivalent of `categorization_filters` (which are not permitted when some other aspect of the analyzer is customized), add them here as [pattern replace character filters](/reference/text-analysis/analysis-pattern-replace-charfilter.md). `tokenizer` - : (string or object) The name or definition of the [tokenizer](/reference/data-analysis/text-analysis/tokenizer-reference.md) to use after character filters are applied. This property is compulsory if `categorization_analyzer` is specified as an object. Machine learning provides a tokenizer called `ml_standard` that tokenizes in a way that has been determined to produce good categorization results on a variety of log file formats for logs in English. If you want to use that tokenizer but change the character or token filters, specify `"tokenizer": "ml_standard"` in your `categorization_analyzer`. Additionally, the `ml_classic` tokenizer is available, which tokenizes in the same way as the non-customizable tokenizer in old versions of the product (before 6.2). `ml_classic` was the default categorization tokenizer in versions 6.2 to 7.13, so if you need categorization identical to the default for jobs created in these versions, specify `"tokenizer": "ml_classic"` in your `categorization_analyzer`. + : (string or object) The name or definition of the [tokenizer](/reference/text-analysis/tokenizer-reference.md) to use after character filters are applied. This property is compulsory if `categorization_analyzer` is specified as an object. Machine learning provides a tokenizer called `ml_standard` that tokenizes in a way that has been determined to produce good categorization results on a variety of log file formats for logs in English. If you want to use that tokenizer but change the character or token filters, specify `"tokenizer": "ml_standard"` in your `categorization_analyzer`. Additionally, the `ml_classic` tokenizer is available, which tokenizes in the same way as the non-customizable tokenizer in old versions of the product (before 6.2). `ml_classic` was the default categorization tokenizer in versions 6.2 to 7.13, so if you need categorization identical to the default for jobs created in these versions, specify `"tokenizer": "ml_classic"` in your `categorization_analyzer`. ::::{note} From {{es}} 8.10.0, a new version number is used to track the configuration and state changes in the {{ml}} plugin. This new version number is decoupled from the product version and will increment independently. @@ -39,7 +39,7 @@ The algorithm used for categorization was completely changed in version 8.3.0. A `filter` - : (array of strings or objects) One or more [token filters](/reference/data-analysis/text-analysis/token-filter-reference.md). In addition to the built-in token filters, other plugins can provide more token filters. This property is optional. If it is not specified, no token filters are applied prior to categorization. + : (array of strings or objects) One or more [token filters](/reference/text-analysis/token-filter-reference.md). In addition to the built-in token filters, other plugins can provide more token filters. This property is optional. If it is not specified, no token filters are applied prior to categorization. ::::: @@ -90,7 +90,7 @@ The algorithm used for categorization was completely changed in version 8.3.0. A ## Basic use [_basic_use] ::::{warning} -Re-analyzing *large* result sets will require a lot of time and memory. This aggregation should be used in conjunction with [Async search](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-async-search-submit). Additionally, you may consider using the aggregation as a child of either the [sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md) or [diversified sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation. This will typically improve speed and memory use. +Re-analyzing *large* result sets will require a lot of time and memory. This aggregation should be used in conjunction with [Async search](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-async-search-submit). Additionally, you may consider using the aggregation as a child of either the [sampler](/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md) or [diversified sampler](/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation. This will typically improve speed and memory use. :::: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-children-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-children-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-children-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-children-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-composite-aggregation.md similarity index 99% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-composite-aggregation.md index cd477c51603c7..bca1a0dce4069 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-composite-aggregation.md @@ -237,7 +237,7 @@ GET /_search } ``` -1. Supports expressive date [format pattern](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) +1. Supports expressive date [format pattern](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) **Time Zone** diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-correlation-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-correlation-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-correlation-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-correlation-aggregation.md index 33b71364f174d..03de824f13e2a 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-correlation-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-correlation-aggregation.md @@ -12,7 +12,7 @@ A sibling pipeline aggregation which executes a correlation function on the conf ## Parameters [bucket-correlation-agg-syntax] `buckets_path` -: (Required, string) Path to the buckets that contain one set of values to correlate. For syntax, see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax). +: (Required, string) Path to the buckets that contain one set of values to correlate. For syntax, see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax). `function` : (Required, object) The correlation function to execute. @@ -76,7 +76,7 @@ A `bucket_correlation` aggregation looks like this in isolation: ## Example [bucket-correlation-agg-example] -The following snippet correlates the individual terms in the field `version` with the `latency` metric. Not shown is the pre-calculation of the `latency` indicator values, which was done utilizing the [percentiles](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. +The following snippet correlates the individual terms in the field `version` with the `latency` metric. Not shown is the pre-calculation of the `latency` indicator values, which was done utilizing the [percentiles](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. This example is only using the 10s percentiles. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md index 92f3e60dd10ae..bd9b6b0d65d18 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md @@ -12,7 +12,7 @@ A sibling pipeline aggregation which executes a two sample Kolmogorov–Smirnov ## Parameters [bucket-count-ks-test-agg-syntax] `buckets_path` -: (Required, string) Path to the buckets that contain one set of values to correlate. Must be a `_count` path For syntax, see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax). +: (Required, string) Path to the buckets that contain one set of values to correlate. Must be a `_count` path For syntax, see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax). `alternative` : (Optional, list) A list of string values indicating which K-S test alternative to calculate. The valid values are: "greater", "less", "two_sided". This parameter is key for determining the K-S statistic used when calculating the K-S test. Default value is all possible alternative hypotheses. @@ -46,7 +46,7 @@ A `bucket_count_ks_test` aggregation looks like this in isolation: ## Example [bucket-count-ks-test-agg-example] -The following snippet runs the `bucket_count_ks_test` on the individual terms in the field `version` against a uniform distribution. The uniform distribution reflects the `latency` percentile buckets. Not shown is the pre-calculation of the `latency` indicator values, which was done utilizing the [percentiles](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. +The following snippet runs the `bucket_count_ks_test` on the individual terms in the field `version` against a uniform distribution. The uniform distribution reflects the `latency` percentile buckets. Not shown is the pre-calculation of the `latency` indicator values, which was done utilizing the [percentiles](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. This example is only using the deciles of `latency`. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md similarity index 95% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md index 590502c5ce3a0..7169b1d28da1f 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Date histogram aggregation [search-aggregations-bucket-datehistogram-aggregation] -This multi-bucket aggregation is similar to the normal [histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md), but it can only be used with date or date range values. Because dates are represented internally in Elasticsearch as long values, it is possible, but not as accurate, to use the normal `histogram` on dates as well. The main difference in the two APIs is that here the interval can be specified using date/time expressions. Time-based data requires special support because time-based intervals are not always a fixed length. +This multi-bucket aggregation is similar to the normal [histogram](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md), but it can only be used with date or date range values. Because dates are represented internally in Elasticsearch as long values, it is possible, but not as accurate, to use the normal `histogram` on dates as well. The main difference in the two APIs is that here the interval can be specified using date/time expressions. Time-based data requires special support because time-based intervals are not always a fixed length. Like the histogram, values are rounded **down** into the closest bucket. For example, if the interval is a calendar day, `2020-01-03T07:00:01Z` is rounded to `2020-01-03T00:00:00Z`. Values are rounded as follows: @@ -236,7 +236,7 @@ POST /sales/_search?size=0 } ``` -1. Supports expressive date [format pattern](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) +1. Supports expressive date [format pattern](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern) Response: @@ -600,7 +600,7 @@ POST /sales/_search?size=0 ## Parameters [date-histogram-params] -You can control the order of the returned buckets using the `order` settings and filter the returned buckets based on a `min_doc_count` setting (by default all buckets between the first bucket that matches documents and the last one are returned). This histogram also supports the `extended_bounds` setting, which enables extending the bounds of the histogram beyond the data itself, and `hard_bounds` that limits the histogram to specified bounds. For more information, see [`Extended Bounds`](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-extended-bounds) and [`Hard Bounds`](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-hard-bounds). +You can control the order of the returned buckets using the `order` settings and filter the returned buckets based on a `min_doc_count` setting (by default all buckets between the first bucket that matches documents and the last one are returned). This histogram also supports the `extended_bounds` setting, which enables extending the bounds of the histogram beyond the data itself, and `hard_bounds` that limits the histogram to specified bounds. For more information, see [`Extended Bounds`](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-extended-bounds) and [`Hard Bounds`](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-hard-bounds). ### Missing value [date-histogram-missing-value] @@ -629,7 +629,7 @@ POST /sales/_search?size=0 ### Order [date-histogram-order] -By default the returned buckets are sorted by their `key` ascending, but you can control the order using the `order` setting. This setting supports the same `order` functionality as [`Terms Aggregation`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order). +By default the returned buckets are sorted by their `key` ascending, but you can control the order using the `order` setting. This setting supports the same `order` functionality as [`Terms Aggregation`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order). ### Using a script to aggregate by day of the week [date-histogram-aggregate-scripts] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md similarity index 96% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md index 82f15d7f455ec..8bfa5e76a3fd2 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Date range aggregation [search-aggregations-bucket-daterange-aggregation] -A range aggregation that is dedicated for date values. The main difference between this aggregation and the normal [range](/reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md) aggregation is that the `from` and `to` values can be expressed in [Date Math](/reference/elasticsearch/rest-apis/common-options.md#date-math) expressions, and it is also possible to specify a date format by which the `from` and `to` response fields will be returned. Note that this aggregation includes the `from` value and excludes the `to` value for each range. +A range aggregation that is dedicated for date values. The main difference between this aggregation and the normal [range](/reference/aggregations/search-aggregations-bucket-range-aggregation.md) aggregation is that the `from` and `to` values can be expressed in [Date Math](/reference/elasticsearch/rest-apis/common-options.md#date-math) expressions, and it is also possible to specify a date format by which the `from` and `to` response fields will be returned. Note that this aggregation includes the `from` value and excludes the `to` value for each range. Example: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-filter-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-filter-aggregation.md index 565f58cdba443..47f6754c78e37 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-filter-aggregation.md @@ -83,7 +83,7 @@ POST /sales/_search?size=0&filter_path=aggregations ## Use the `filters` aggregation for multiple filters [use-filters-agg-for-multiple-filters] -To group documents using multiple filters, use the [`filters` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md). This is faster than multiple `filter` aggregations. +To group documents using multiple filters, use the [`filters` aggregation](/reference/aggregations/search-aggregations-bucket-filters-aggregation.md). This is faster than multiple `filter` aggregations. For example, use this: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-filters-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-filters-aggregation.md index 03311dc5d8ac3..465361130fe80 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-filters-aggregation.md @@ -178,7 +178,7 @@ The response would be something like the following: ## Non-keyed Response [non-keyed-response] -By default, the named filters aggregation returns the buckets as an object. But in some sorting cases, such as [bucket sort](/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md), the JSON doesn’t guarantee the order of elements in the object. You can use the `keyed` parameter to specify the buckets as an array of objects. The value of this parameter can be as follows: +By default, the named filters aggregation returns the buckets as an object. But in some sorting cases, such as [bucket sort](/reference/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md), the JSON doesn’t guarantee the order of elements in the object. You can use the `keyed` parameter to specify the buckets as an array of objects. The value of this parameter can be as follows: `true` : (Default) Returns the buckets as an object diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-frequent-item-sets-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-frequent-item-sets-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-frequent-item-sets-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-frequent-item-sets-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-geodistance-aggregation.md similarity index 92% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-geodistance-aggregation.md index f34919ec75909..c4e98242a9e43 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-geodistance-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Geo-distance aggregation [search-aggregations-bucket-geodistance-aggregation] -A multi-bucket aggregation that works on `geo_point` fields and conceptually works very similar to the [range](/reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md) aggregation. The user can define a point of origin and a set of distance range buckets. The aggregation evaluates the distance of each document value from the origin point and determines the buckets it belongs to based on the ranges (a document belongs to a bucket if the distance between the document and the origin falls within the distance range of the bucket). +A multi-bucket aggregation that works on `geo_point` fields and conceptually works very similar to the [range](/reference/aggregations/search-aggregations-bucket-range-aggregation.md) aggregation. The user can define a point of origin and a set of distance range buckets. The aggregation evaluates the distance of each document value from the origin point and determines the buckets it belongs to based on the ranges (a document belongs to a bucket if the distance between the document and the origin falls within the distance range of the bucket). $$$geodistance-aggregation-example$$$ diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md similarity index 99% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md index 2c7466fd04be6..7a749c97ed8b6 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md @@ -286,7 +286,7 @@ The table below shows the metric dimensions for cells covered by various string Aggregating on [Geoshape](/reference/elasticsearch/mapping-reference/geo-shape.md) fields works just as it does for points, except that a single shape can be counted for in multiple tiles. A shape will contribute to the count of matching values if any part of its shape intersects with that tile. Below is an image that demonstrates this: -![geoshape grid](../../../images/geoshape_grid.png "") +![geoshape grid](images/geoshape_grid.png "") ## Options [_options_3] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md index 70d41496c3b9f..63064e2ab342b 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md @@ -204,9 +204,9 @@ Response: Aggregating on [Geoshape](/reference/elasticsearch/mapping-reference/geo-shape.md) fields works almost as it does for points. There are two key differences: * When aggregating over `geo_point` data, points are considered within a hexagonal tile if they lie within the edges defined by great circles. In other words the calculation is done using spherical coordinates. However, when aggregating over `geo_shape` data, the shapes are considered within a hexagon if they lie within the edges defined as straight lines on an equirectangular projection. The reason is that Elasticsearch and Lucene treat edges using the equirectangular projection at index and search time. In order to ensure that search results and aggregation results are aligned, we therefore also use equirectangular projection in aggregations. For most data, the difference is subtle or not noticed. However, for low zoom levels (low precision), especially far from the equator, this can be noticeable. For example, if the same point data is indexed as `geo_point` and `geo_shape`, it is possible to get different results when aggregating at lower resolutions. -* As is the case with [`geotile_grid`](/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md#geotilegrid-aggregating-geo-shape), a single shape can be counted for in multiple tiles. A shape will contribute to the count of matching values if any part of its shape intersects with that tile. Below is an image that demonstrates this: +* As is the case with [`geotile_grid`](/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md#geotilegrid-aggregating-geo-shape), a single shape can be counted for in multiple tiles. A shape will contribute to the count of matching values if any part of its shape intersects with that tile. Below is an image that demonstrates this: -![geoshape hexgrid](../../../images/geoshape_hexgrid.png "") +![geoshape hexgrid](images/geoshape_hexgrid.png "") ## Options [_options_4] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md similarity index 99% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md index f539d79dfe1eb..69ec49dd1a954 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md @@ -208,7 +208,7 @@ Response: Aggregating on [Geoshape](/reference/elasticsearch/mapping-reference/geo-shape.md) fields works almost as it does for points, except that a single shape can be counted for in multiple tiles. A shape will contribute to the count of matching values if any part of its shape intersects with that tile. Below is an image that demonstrates this: -![geoshape grid](../../../images/geoshape_grid.png "") +![geoshape grid](images/geoshape_grid.png "") ## Options [_options_5] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-global-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-global-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-global-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-global-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md index 198ab127e783b..31cb382baec18 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md @@ -156,7 +156,7 @@ POST /sales/_search?size=0 } ``` -When aggregating ranges, buckets are based on the values of the returned documents. This means the response may include buckets outside of a query’s range. For example, if your query looks for values greater than 100, and you have a range covering 50 to 150, and an interval of 50, that document will land in 3 buckets - 50, 100, and 150. In general, it’s best to think of the query and aggregation steps as independent - the query selects a set of documents, and then the aggregation buckets those documents without regard to how they were selected. See [note on bucketing range fields](/reference/data-analysis/aggregations/search-aggregations-bucket-range-field-note.md) for more information and an example. +When aggregating ranges, buckets are based on the values of the returned documents. This means the response may include buckets outside of a query’s range. For example, if your query looks for values greater than 100, and you have a range covering 50 to 150, and an interval of 50, that document will land in 3 buckets - 50, 100, and 150. In general, it’s best to think of the query and aggregation steps as independent - the query selects a set of documents, and then the aggregation buckets those documents without regard to how they were selected. See [note on bucketing range fields](/reference/aggregations/search-aggregations-bucket-range-field-note.md) for more information and an example. $$$search-aggregations-bucket-histogram-aggregation-hard-bounds$$$ The `hard_bounds` is a counterpart of `extended_bounds` and can limit the range of buckets in the histogram. It is particularly useful in the case of open [data ranges](/reference/elasticsearch/mapping-reference/range.md) that can result in a very large number of buckets. @@ -191,7 +191,7 @@ In this example even though the range specified in the query is up to 500, the h ## Order [_order_2] -By default the returned buckets are sorted by their `key` ascending, though the order behaviour can be controlled using the `order` setting. Supports the same `order` functionality as the [`Terms Aggregation`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order). +By default the returned buckets are sorted by their `key` ascending, though the order behaviour can be controlled using the `order` setting. Supports the same `order` functionality as the [`Terms Aggregation`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order). ## Offset [_offset] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-ipprefix-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-ipprefix-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-ipprefix-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-ipprefix-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-iprange-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-iprange-aggregation.md similarity index 93% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-iprange-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-iprange-aggregation.md index b8bbd060c117a..c385850cf481a 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-iprange-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-iprange-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # IP range aggregation [search-aggregations-bucket-iprange-aggregation] -Just like the dedicated [date](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md) range aggregation, there is also a dedicated range aggregation for IP typed fields: +Just like the dedicated [date](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md) range aggregation, there is also a dedicated range aggregation for IP typed fields: Example: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-missing-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-missing-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-missing-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-missing-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-multi-terms-aggregation.md similarity index 90% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-multi-terms-aggregation.md index 3b0e825186a66..5b16f0581f839 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-multi-terms-aggregation.md @@ -7,9 +7,9 @@ mapped_pages: # Multi Terms aggregation [search-aggregations-bucket-multi-terms-aggregation] -A multi-bucket value source based aggregation where buckets are dynamically built - one per unique set of values. The multi terms aggregation is very similar to the [`terms aggregation`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order), however in most cases it will be slower than the terms aggregation and will consume more memory. Therefore, if the same set of fields is constantly used, it would be more efficient to index a combined key for this fields as a separate field and use the terms aggregation on this field. +A multi-bucket value source based aggregation where buckets are dynamically built - one per unique set of values. The multi terms aggregation is very similar to the [`terms aggregation`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order), however in most cases it will be slower than the terms aggregation and will consume more memory. Therefore, if the same set of fields is constantly used, it would be more efficient to index a combined key for this fields as a separate field and use the terms aggregation on this field. -The multi_term aggregations are the most useful when you need to sort by a number of document or a metric aggregation on a composite key and get top N results. If sorting is not required and all values are expected to be retrieved using nested terms aggregation or [`composite aggregations`](/reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md) will be a faster and more memory efficient solution. +The multi_term aggregations are the most useful when you need to sort by a number of document or a metric aggregation on a composite key and get top N results. If sorting is not required and all values are expected to be retrieved using nested terms aggregation or [`composite aggregations`](/reference/aggregations/search-aggregations-bucket-composite-aggregation.md) will be a faster and more memory efficient solution. Example: @@ -32,7 +32,7 @@ GET /products/_search } ``` -1. `multi_terms` aggregation can work with the same field types as a [`terms aggregation`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order) and supports most of the terms aggregation parameters. +1. `multi_terms` aggregation can work with the same field types as a [`terms aggregation`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order) and supports most of the terms aggregation parameters. Response: @@ -93,7 +93,7 @@ By default, the `multi_terms` aggregation will return the buckets for the top te ## Aggregation Parameters [search-aggregations-bucket-multi-terms-aggregation-parameters] -The following parameters are supported. See [`terms aggregation`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order) for more detailed explanation of these parameters. +The following parameters are supported. See [`terms aggregation`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order) for more detailed explanation of these parameters. size : Optional. Defines how many term buckets should be returned out of the overall terms list. Defaults to 10. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-nested-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-nested-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-nested-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-nested-aggregation.md index c8407fd53e2e3..b1f03cb0bba73 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-nested-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-nested-aggregation.md @@ -104,7 +104,7 @@ Response: } ``` -You can use a [`filter`](/reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md) sub-aggregation to return results for a specific reseller. +You can use a [`filter`](/reference/aggregations/search-aggregations-bucket-filter-aggregation.md) sub-aggregation to return results for a specific reseller. ```console GET /products/_search?size=0 diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-parent-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-parent-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-parent-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-parent-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-range-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-range-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-range-field-note.md b/docs/reference/aggregations/search-aggregations-bucket-range-field-note.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-range-field-note.md rename to docs/reference/aggregations/search-aggregations-bucket-range-field-note.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-rare-terms-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-rare-terms-aggregation.md similarity index 95% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-rare-terms-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-rare-terms-aggregation.md index d001c0078394b..3c17abd2db2b7 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-rare-terms-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-rare-terms-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Rare terms aggregation [search-aggregations-bucket-rare-terms-aggregation] -A multi-bucket value source based aggregation which finds "rare" terms — terms that are at the long-tail of the distribution and are not frequent. Conceptually, this is like a `terms` aggregation that is sorted by `_count` ascending. As noted in the [terms aggregation docs](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order), actually ordering a `terms` agg by count ascending has unbounded error. Instead, you should use the `rare_terms` aggregation +A multi-bucket value source based aggregation which finds "rare" terms — terms that are at the long-tail of the distribution and are not frequent. Conceptually, this is like a `terms` aggregation that is sorted by `_count` ascending. As noted in the [terms aggregation docs](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-order), actually ordering a `terms` agg by count ascending has unbounded error. Instead, you should use the `rare_terms` aggregation ## Syntax [_syntax_3] @@ -152,21 +152,21 @@ The X-axis shows the number of distinct values the aggregation has seen, and the This first chart shows precision `0.01`: -![accuracy 01](../../../images/accuracy_01.png "") +![accuracy 01](images/accuracy_01.png "") And precision `0.001` (the default): -![accuracy 001](../../../images/accuracy_001.png "") +![accuracy 001](images/accuracy_001.png "") And finally `precision 0.0001`: -![accuracy 0001](../../../images/accuracy_0001.png "") +![accuracy 0001](images/accuracy_0001.png "") The default precision of `0.001` maintains an accuracy of < 2.5% for the tested conditions, and accuracy slowly degrades in a controlled, linear fashion as the number of distinct values increases. The default precision of `0.001` has a memory profile of `1.748⁻⁶ * n` bytes, where `n` is the number of distinct values the aggregation has seen (it can also be roughly eyeballed, e.g. 20 million unique values is about 30mb of memory). The memory usage is linear to the number of distinct values regardless of which precision is chosen, the precision only affects the slope of the memory profile as seen in this chart: -![memory](../../../images/memory.png "") +![memory](images/memory.png "") For comparison, an equivalent terms aggregation at 20 million buckets would be roughly `20m * 69b == ~1.38gb` (with 69 bytes being a very optimistic estimate of an empty bucket cost, far lower than what the circuit breaker accounts for). So although the `rare_terms` agg is relatively heavy, it is still orders of magnitude smaller than the equivalent terms aggregation diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md similarity index 99% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md index 6a6a817d94a16..62efb48323145 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md @@ -524,13 +524,13 @@ Use of background filters will slow the query as each term’s postings must be ### Filtering Values [_filtering_values_2] -It is possible (although rarely required) to filter the values for which buckets will be created. This can be done using the `include` and `exclude` parameters which are based on a regular expression string or arrays of exact terms. This functionality mirrors the features described in the [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) documentation. +It is possible (although rarely required) to filter the values for which buckets will be created. This can be done using the `include` and `exclude` parameters which are based on a regular expression string or arrays of exact terms. This functionality mirrors the features described in the [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) documentation. ## Collect mode [_collect_mode] -To avoid memory issues, the `significant_terms` aggregation always computes child aggregations in `breadth_first` mode. A description of the different collection modes can be found in the [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-collect) documentation. +To avoid memory issues, the `significant_terms` aggregation always computes child aggregations in `breadth_first` mode. A description of the different collection modes can be found in the [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-collect) documentation. ## Execution hint [_execution_hint_2] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-significanttext-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-significanttext-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-significanttext-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-significanttext-aggregation.md index 845e68d95501e..2d1b9ec6aa420 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-significanttext-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-significanttext-aggregation.md @@ -7,14 +7,14 @@ mapped_pages: # Significant text aggregation [search-aggregations-bucket-significanttext-aggregation] -An aggregation that returns interesting or unusual occurrences of free-text terms in a set. It is like the [significant terms](/reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md) aggregation but differs in that: +An aggregation that returns interesting or unusual occurrences of free-text terms in a set. It is like the [significant terms](/reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md) aggregation but differs in that: * It is specifically designed for use on type `text` fields * It does not require field data or doc-values * It re-analyzes text content on-the-fly meaning it can also filter duplicate sections of noisy text that otherwise tend to skew statistics. ::::{warning} -Re-analyzing *large* result sets will require a lot of time and memory. It is recommended that the significant_text aggregation is used as a child of either the [sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md) or [diversified sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation to limit the analysis to a *small* selection of top-matching documents e.g. 200. This will typically improve speed, memory use and quality of results. +Re-analyzing *large* result sets will require a lot of time and memory. It is recommended that the significant_text aggregation is used as a child of either the [sampler](/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md) or [diversified sampler](/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation to limit the analysis to a *small* selection of top-matching documents e.g. 200. This will typically improve speed, memory use and quality of results. :::: @@ -257,7 +257,7 @@ The results from analysing our deduplicated text are obviously of higher quality Mr Pozmantier and other one-off associations with elasticsearch no longer appear in the aggregation results as a consequence of copy-and-paste operations or other forms of mechanical repetition. -If your duplicate or near-duplicate content is identifiable via a single-value indexed field (perhaps a hash of the article’s `title` text or an `original_press_release_url` field) then it would be more efficient to use a parent [diversified sampler](/reference/data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation to eliminate these documents from the sample set based on that single key. The less duplicate content you can feed into the significant_text aggregation up front the better in terms of performance. +If your duplicate or near-duplicate content is identifiable via a single-value indexed field (perhaps a hash of the article’s `title` text or an `original_press_release_url` field) then it would be more efficient to use a parent [diversified sampler](/reference/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md) aggregation to eliminate these documents from the sample set based on that single key. The less duplicate content you can feed into the significant_text aggregation up front the better in terms of performance. ::::{admonition} How are the significance scores calculated? The numbers returned for scores are primarily intended for ranking different suggestions sensibly rather than something easily understood by end users. The scores are derived from the doc frequencies in *foreground* and *background* sets. In brief, a term is considered significant if there is a noticeable difference in the frequency in which a term appears in the subset and in the background. The way the terms are ranked can be configured, see "Parameters" section. @@ -306,7 +306,7 @@ Like most design decisions, this is the basis of a trade-off in which we have ch ### Significance heuristics [_significance_heuristics] -This aggregation supports the same scoring heuristics (JLH, mutual_information, gnd, chi_square etc) as the [significant terms](/reference/data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md) aggregation +This aggregation supports the same scoring heuristics (JLH, mutual_information, gnd, chi_square etc) as the [significant terms](/reference/aggregations/search-aggregations-bucket-significantterms-aggregation.md) aggregation ### Size & Shard Size [sig-text-shard-size] @@ -403,7 +403,7 @@ GET news/_search ### Filtering Values [_filtering_values_3] -It is possible (although rarely required) to filter the values for which buckets will be created. This can be done using the `include` and `exclude` parameters which are based on a regular expression string or arrays of exact terms. This functionality mirrors the features described in the [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) documentation. +It is possible (although rarely required) to filter the values for which buckets will be created. This can be done using the `include` and `exclude` parameters which are based on a regular expression string or arrays of exact terms. This functionality mirrors the features described in the [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) documentation. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-terms-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-terms-aggregation.md index 3bb76d937005f..f84deb2d6297c 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-terms-aggregation.md @@ -69,7 +69,7 @@ By default, you cannot run a `terms` aggregation on a `text` field. Use a `keywo By default, the `terms` aggregation returns the top ten terms with the most documents. Use the `size` parameter to return more terms, up to the [search.max_buckets](/reference/elasticsearch/configuration-reference/search-settings.md#search-settings-max-buckets) limit. -If your data contains 100 or 1000 unique terms, you can increase the `size` of the `terms` aggregation to return them all. If you have more unique terms and you need them all, use the [composite aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md) instead. +If your data contains 100 or 1000 unique terms, you can increase the `size` of the `terms` aggregation to return them all. If you have more unique terms and you need them all, use the [composite aggregation](/reference/aggregations/search-aggregations-bucket-composite-aggregation.md) instead. Larger values of `size` use more memory to compute and, push the whole aggregation close to the `max_buckets` limit. You’ll know you’ve gone too large if the request fails with a message about `max_buckets`. @@ -133,7 +133,7 @@ By default, the `terms` aggregation orders terms by descending document `_count` You can use the `order` parameter to specify a different sort order, but we don’t recommend it. It is extremely easy to create a terms ordering that will just return wrong results, and not obvious to see when you have done so. Change this only with caution. ::::{warning} -Especially avoid using `"order": { "_count": "asc" }`. If you need to find rare terms, use the [`rare_terms`](/reference/data-analysis/aggregations/search-aggregations-bucket-rare-terms-aggregation.md) aggregation instead. Due to the way the `terms` aggregation [gets terms from shards](#search-aggregations-bucket-terms-aggregation-shard-size), sorting by ascending doc count often produces inaccurate results. +Especially avoid using `"order": { "_count": "asc" }`. If you need to find rare terms, use the [`rare_terms`](/reference/aggregations/search-aggregations-bucket-rare-terms-aggregation.md) aggregation instead. Due to the way the `terms` aggregation [gets terms from shards](#search-aggregations-bucket-terms-aggregation-shard-size), sorting by ascending doc count often produces inaccurate results. :::: @@ -216,7 +216,7 @@ GET /_search ::::{admonition} Pipeline aggs cannot be used for sorting :class: note -[Pipeline aggregations](/reference/data-analysis/aggregations/pipeline.md) are run during the reduce phase after all other aggregations have already completed. For this reason, they cannot be used for ordering. +[Pipeline aggregations](/reference/aggregations/pipeline.md) are run during the reduce phase after all other aggregations have already completed. For this reason, they cannot be used for ordering. :::: @@ -548,7 +548,7 @@ There are three approaches that you can use to perform a `terms` agg across mult [`copy_to` field](/reference/elasticsearch/mapping-reference/copy-to.md) : If you know ahead of time that you want to collect the terms from two or more fields, then use `copy_to` in your mapping to create a new dedicated field at index time which contains the values from both fields. You can aggregate on this single field, which will benefit from the global ordinals optimization. -[`multi_terms` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md) +[`multi_terms` aggregation](/reference/aggregations/search-aggregations-bucket-multi-terms-aggregation.md) : Use multi_terms aggregation to combine terms from multiple fields into a compound key. This also disables the global ordinals and will be slower than collecting terms from a single field. It is faster but less flexible than using a script. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md b/docs/reference/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md similarity index 88% rename from docs/reference/data-analysis/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md rename to docs/reference/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md index ba44b9fff573a..0c6e470838882 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Variable width histogram aggregation [search-aggregations-bucket-variablewidthhistogram-aggregation] -This is a multi-bucket aggregation similar to [Histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md). However, the width of each bucket is not specified. Rather, a target number of buckets is provided and bucket intervals are dynamically determined based on the document distribution. This is done using a simple one-pass document clustering algorithm that aims to obtain low distances between bucket centroids. Unlike other multi-bucket aggregations, the intervals will not necessarily have a uniform width. +This is a multi-bucket aggregation similar to [Histogram](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md). However, the width of each bucket is not specified. Rather, a target number of buckets is provided and bucket intervals are dynamically determined based on the document distribution. This is done using a simple one-pass document clustering algorithm that aims to obtain low distances between bucket centroids. Unlike other multi-bucket aggregations, the intervals will not necessarily have a uniform width. ::::{tip} The number of buckets returned will always be less than or equal to the target number. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-change-point-aggregation.md b/docs/reference/aggregations/search-aggregations-change-point-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-change-point-aggregation.md rename to docs/reference/aggregations/search-aggregations-change-point-aggregation.md index 56960c32b5565..e5dca42a719e0 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-change-point-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-change-point-aggregation.md @@ -22,7 +22,7 @@ It is recommended to use the change point aggregation to detect changes in time- ## Parameters [change-point-agg-syntax] `buckets_path` -: (Required, string) Path to the buckets that contain one set of values in which to detect a change point. There must be at least 22 bucketed values. Fewer than 1,000 is preferred. For syntax, see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax). +: (Required, string) Path to the buckets that contain one set of values in which to detect a change point. There must be at least 22 bucketed values. Fewer than 1,000 is preferred. For syntax, see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax). ## Syntax [_syntax_11] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-matrix-stats-aggregation.md b/docs/reference/aggregations/search-aggregations-matrix-stats-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-matrix-stats-aggregation.md rename to docs/reference/aggregations/search-aggregations-matrix-stats-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-avg-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-avg-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-boxplot-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-boxplot-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-boxplot-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-boxplot-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-cardinality-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-cardinality-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md similarity index 87% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md index 832014b936d56..b3f55b5616016 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md @@ -56,7 +56,7 @@ POST /museums/_search?size=0 ::::{note} -Unlike the case with the [`geo_bounds`](/reference/data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md#geobounds-aggregation-geo-shape) aggregation, there is no option to set [`wrap_longitude`](/reference/data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md#geo-bounds-wrap-longitude). This is because the cartesian space is euclidean and does not wrap back on itself. So the bounds will always have a minimum x value less than or equal to the maximum x value. +Unlike the case with the [`geo_bounds`](/reference/aggregations/search-aggregations-metrics-geobounds-aggregation.md#geobounds-aggregation-geo-shape) aggregation, there is no option to set [`wrap_longitude`](/reference/aggregations/search-aggregations-metrics-geobounds-aggregation.md#geo-bounds-wrap-longitude). This is because the cartesian space is euclidean and does not wrap back on itself. So the bounds will always have a minimum x value less than or equal to the maximum x value. :::: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md similarity index 95% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md index cc9b820897496..aadb885f7138d 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md @@ -91,7 +91,7 @@ POST /museums/_search?size=0 } ``` -The above example uses `cartesian_centroid` as a sub-aggregation to a [terms](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) bucket aggregation for finding the central location for museums in each city. +The above example uses `cartesian_centroid` as a sub-aggregation to a [terms](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) bucket aggregation for finding the central location for museums in each city. The response for the above aggregation: @@ -145,7 +145,7 @@ The response for the above aggregation: ## Cartesian Centroid Aggregation on `shape` fields [cartesian-centroid-aggregation-geo-shape] -The centroid metric for shapes is more nuanced than for points. The centroid of a specific aggregation bucket containing shapes is the centroid of the highest-dimensionality shape type in the bucket. For example, if a bucket contains shapes consisting of polygons and lines, then the lines do not contribute to the centroid metric. Each type of shape’s centroid is calculated differently. Envelopes and circles ingested via the [Circle](/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md) are treated as polygons. +The centroid metric for shapes is more nuanced than for points. The centroid of a specific aggregation bucket containing shapes is the centroid of the highest-dimensionality shape type in the bucket. For example, if a bucket contains shapes consisting of polygons and lines, then the lines do not contribute to the centroid metric. Each type of shape’s centroid is calculated differently. Envelopes and circles ingested via the [Circle](/reference/enrich-processor/ingest-circle-processor.md) are treated as polygons. | Geometry Type | Centroid Calculation | | --- | --- | diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-extendedstats-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-extendedstats-aggregation.md similarity index 95% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-extendedstats-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-extendedstats-aggregation.md index ff573b08dd54a..99121d173581a 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-extendedstats-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-extendedstats-aggregation.md @@ -9,7 +9,7 @@ mapped_pages: A `multi-value` metrics aggregation that computes stats over numeric values extracted from the aggregated documents. -The `extended_stats` aggregations is an extended version of the [`stats`](/reference/data-analysis/aggregations/search-aggregations-metrics-stats-aggregation.md) aggregation, where additional metrics are added such as `sum_of_squares`, `variance`, `std_deviation` and `std_deviation_bounds`. +The `extended_stats` aggregations is an extended version of the [`stats`](/reference/aggregations/search-aggregations-metrics-stats-aggregation.md) aggregation, where additional metrics are added such as `sum_of_squares`, `variance`, `std_deviation` and `std_deviation_bounds`. Assuming the data consists of documents representing exams grades (between 0 and 100) of students diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-geo-line.md b/docs/reference/aggregations/search-aggregations-metrics-geo-line.md similarity index 89% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-geo-line.md rename to docs/reference/aggregations/search-aggregations-metrics-geo-line.md index ca57725ff13de..47904b3d5a699 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-geo-line.md +++ b/docs/reference/aggregations/search-aggregations-metrics-geo-line.md @@ -77,7 +77,7 @@ The resulting [GeoJSON Feature](https://tools.ietf.org/html/rfc7946#section-3.2) This result could be displayed in a map user interface: -![Kibana map with museum tour of Amsterdam](../../../images/geo_line.png "") +![Kibana map with museum tour of Amsterdam](images/geo_line.png "") ## Options [search-aggregations-metrics-geo-line-options] @@ -183,7 +183,7 @@ POST /tour/_bulk?refresh ## Grouping with terms [search-aggregations-metrics-geo-line-grouping-terms] -Using this data, for a non-time-series use case, the grouping can be done using a [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) based on city name. This would work whether or not we had defined the `tour` index as a time series index. +Using this data, for a non-time-series use case, the grouping can be done using a [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) based on city name. This would work whether or not we had defined the `tour` index as a time series index. $$$search-aggregations-metrics-geo-line-terms$$$ @@ -273,7 +273,7 @@ This functionality is in technical preview and may be changed or removed in a fu :::: -Using the same data as before, we can also perform the grouping with a [`time_series` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md). This will group by TSID, which is defined as the combinations of all fields with `time_series_dimension: true`, in this case the same `city` field used in the previous [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md). This example will only work if we defined the `tour` index as a time series index using `index.mode="time_series"`. +Using the same data as before, we can also perform the grouping with a [`time_series` aggregation](/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md). This will group by TSID, which is defined as the combinations of all fields with `time_series_dimension: true`, in this case the same `city` field used in the previous [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md). This example will only work if we defined the `tour` index as a time series index using `index.mode="time_series"`. $$$search-aggregations-metrics-geo-line-time-series$$$ @@ -296,7 +296,7 @@ POST /tour/_search?filter_path=aggregations ``` ::::{note} -The `geo_line` aggregation no longer requires the `sort` field when nested within a [`time_series` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md). This is because the sort field is set to `@timestamp`, which all time-series indexes are pre-sorted by. If you do set this parameter, and set it to something other than `@timestamp` you will get an error. +The `geo_line` aggregation no longer requires the `sort` field when nested within a [`time_series` aggregation](/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md). This is because the sort field is set to `@timestamp`, which all time-series indexes are pre-sorted by. If you do set this parameter, and set it to something other than `@timestamp` you will get an error. :::: @@ -366,7 +366,7 @@ These results are essentially the same as with the previous `terms` aggregation ## Why group with time-series? [search-aggregations-metrics-geo-line-grouping-time-series-advantages] -When reviewing these examples, you might think that there is little difference between using [`terms`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) or [`time_series`](/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md) to group the geo-lines. However, there are some important differences in behaviour between the two cases. Time series indexes are stored in a very specific order on disk. They are pre-grouped by the time-series dimension fields, and pre-sorted by the `@timestamp` field. This allows the `geo_line` aggregation to be considerably optimized: +When reviewing these examples, you might think that there is little difference between using [`terms`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) or [`time_series`](/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md) to group the geo-lines. However, there are some important differences in behaviour between the two cases. Time series indexes are stored in a very specific order on disk. They are pre-grouped by the time-series dimension fields, and pre-sorted by the `@timestamp` field. This allows the `geo_line` aggregation to be considerably optimized: * The same memory allocated for the first bucket can be re-used over and over for all subsequent buckets. This is substantially less memory than required for non-time-series cases where all buckets are collected concurrently. * No sorting needs to be done, since the data is pre-sorted by `@timestamp`. The time-series data will naturally arrive at the aggregation collector in `DESC` order. This means that if we specify `sort_order:ASC` (the default), we still collect in `DESC` order, but perform an efficient in-memory reverse order before generating the final `LineString` geometry. @@ -377,19 +377,19 @@ Note: There are other significant advantages to working with time-series data an ## Streaming line simplification [search-aggregations-metrics-geo-line-simplification] -Line simplification is a great way to reduce the size of the final results sent to the client, and displayed in a map user interface. However, normally these algorithms use a lot of memory to perform the simplification, requiring the entire geometry to be maintained in memory together with supporting data for the simplification itself. The use of a streaming line simplification algorithm allows for minimal memory usage during the simplification process by constraining memory to the bounds defined for the simplified geometry. This is only possible if no sorting is required, which is the case when grouping is done by the [`time_series` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md), running on an index with the `time_series` index mode. +Line simplification is a great way to reduce the size of the final results sent to the client, and displayed in a map user interface. However, normally these algorithms use a lot of memory to perform the simplification, requiring the entire geometry to be maintained in memory together with supporting data for the simplification itself. The use of a streaming line simplification algorithm allows for minimal memory usage during the simplification process by constraining memory to the bounds defined for the simplified geometry. This is only possible if no sorting is required, which is the case when grouping is done by the [`time_series` aggregation](/reference/aggregations/search-aggregations-bucket-time-series-aggregation.md), running on an index with the `time_series` index mode. Under these conditions the `geo_line` aggregation allocates memory to the `size` specified, and then fills that memory with the incoming documents. Once the memory is completely filled, documents from within the line are removed as new documents are added. The choice of document to remove is made to minimize the visual impact on the geometry. This process makes use of the [Visvalingam–Whyatt algorithm](https://en.wikipedia.org/wiki/Visvalingam%E2%80%93Whyatt_algorithm). Essentially this means points are removed if they have the minimum triangle area, with the triangle defined by the point under consideration and the two points before and after it in the line. In addition, we calculate the area using spherical coordinates so that no planar distortions affect the choice. In order to demonstrate how much better line simplification is to line truncation, consider this example of the north shore of Kodiak Island. The data for this is only 209 points, but if we want to set `size` to `100` we get dramatic truncation. -![North short of Kodiak Island truncated to 100 points](../../../images/kodiak_geo_line_truncated.png "") +![North short of Kodiak Island truncated to 100 points](images/kodiak_geo_line_truncated.png "") The grey line is the entire geometry of 209 points, while the blue line is the first 100 points, a very different geometry than the original. Now consider the same geometry simplified to 100 points. -![North short of Kodiak Island simplified to 100 points](../../../images/kodiak_geo_line_simplified.png "") +![North short of Kodiak Island simplified to 100 points](images/kodiak_geo_line_simplified.png "") For comparison we have shown the original in grey, the truncated in blue and the new simplified geometry in magenta. It is possible to see where the new simplified line deviates from the original, but the overall geometry appears almost identical and is still clearly recognizable as the north shore of Kodiak Island. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-geobounds-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-geobounds-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-geocentroid-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-geocentroid-aggregation.md similarity index 89% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-geocentroid-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-geocentroid-aggregation.md index eb8ad47acbeea..26b8e6770f9eb 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-geocentroid-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-geocentroid-aggregation.md @@ -91,7 +91,7 @@ POST /museums/_search?size=0 } ``` -The above example uses `geo_centroid` as a sub-aggregation to a [terms](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) bucket aggregation for finding the central location for museums in each city. +The above example uses `geo_centroid` as a sub-aggregation to a [terms](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) bucket aggregation for finding the central location for museums in each city. The response for the above aggregation: @@ -145,7 +145,7 @@ The response for the above aggregation: ## Geo Centroid Aggregation on `geo_shape` fields [geocentroid-aggregation-geo-shape] -The centroid metric for geoshapes is more nuanced than for points. The centroid of a specific aggregation bucket containing shapes is the centroid of the highest-dimensionality shape type in the bucket. For example, if a bucket contains shapes comprising of polygons and lines, then the lines do not contribute to the centroid metric. Each type of shape’s centroid is calculated differently. Envelopes and circles ingested via the [Circle](/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md) are treated as polygons. +The centroid metric for geoshapes is more nuanced than for points. The centroid of a specific aggregation bucket containing shapes is the centroid of the highest-dimensionality shape type in the bucket. For example, if a bucket contains shapes comprising of polygons and lines, then the lines do not contribute to the centroid metric. Each type of shape’s centroid is calculated differently. Envelopes and circles ingested via the [Circle](/reference/enrich-processor/ingest-circle-processor.md) are treated as polygons. | Geometry Type | Centroid Calculation | | --- | --- | @@ -204,7 +204,7 @@ POST /places/_search?size=0 ::::{admonition} Using `geo_centroid` as a sub-aggregation of `geohash_grid` :class: warning -The [`geohash_grid`](/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md) aggregation places documents, not individual geopoints, into buckets. If a document’s `geo_point` field contains [multiple values](/reference/elasticsearch/mapping-reference/array.md), the document could be assigned to multiple buckets, even if one or more of its geopoints are outside the bucket boundaries. +The [`geohash_grid`](/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md) aggregation places documents, not individual geopoints, into buckets. If a document’s `geo_point` field contains [multiple values](/reference/elasticsearch/mapping-reference/array.md), the document could be assigned to multiple buckets, even if one or more of its geopoints are outside the bucket boundaries. If a `geocentroid` sub-aggregation is also used, each centroid is calculated using all geopoints in a bucket, including those outside the bucket boundaries. This can result in centroids outside of bucket boundaries. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-max-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-max-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md similarity index 92% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md index 3926373e337cc..d39983fc31d34 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md @@ -60,9 +60,9 @@ The resulting median absolute deviation of `2` tells us that there is a fair amo ## Approximation [_approximation] -The naive implementation of calculating median absolute deviation stores the entire sample in memory, so this aggregation instead calculates an approximation. It uses the [TDigest data structure](https://github.com/tdunning/t-digest) to approximate the sample median and the median of deviations from the sample median. For more about the approximation characteristics of TDigests, see [Percentiles are (usually) approximate](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). +The naive implementation of calculating median absolute deviation stores the entire sample in memory, so this aggregation instead calculates an approximation. It uses the [TDigest data structure](https://github.com/tdunning/t-digest) to approximate the sample median and the median of deviations from the sample median. For more about the approximation characteristics of TDigests, see [Percentiles are (usually) approximate](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). -The tradeoff between resource usage and accuracy of a TDigest’s quantile approximation, and therefore the accuracy of this aggregation’s approximation of median absolute deviation, is controlled by the `compression` parameter. A higher `compression` setting provides a more accurate approximation at the cost of higher memory usage. For more about the characteristics of the TDigest `compression` parameter see [Compression](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-compression). +The tradeoff between resource usage and accuracy of a TDigest’s quantile approximation, and therefore the accuracy of this aggregation’s approximation of median absolute deviation, is controlled by the `compression` parameter. A higher `compression` setting provides a more accurate approximation at the cost of higher memory usage. For more about the characteristics of the TDigest `compression` parameter see [Compression](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-compression). ```console GET reviews/_search diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-min-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-min-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md similarity index 98% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md index 283e280a5bbe0..1d3665b572305 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md @@ -175,7 +175,7 @@ GET latency/_search ## Percentiles are (usually) approximate [search-aggregations-metrics-percentile-aggregation-approximation] -:::{include} /reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md +:::{include} /reference/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md ::: ::::{warning} diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md similarity index 89% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md index 83b8897875b01..678cd089706af 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md @@ -10,7 +10,7 @@ mapped_pages: A `multi-value` metrics aggregation that calculates one or more percentile ranks over numeric values extracted from the aggregated documents. These values can be extracted from specific numeric or [histogram fields](/reference/elasticsearch/mapping-reference/histogram.md) in the documents. ::::{note} -Please see [Percentiles are (usually) approximate](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation), [Compression](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-compression) and [Execution hint](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-execution-hint) for advice regarding approximation, performance and memory use of the percentile ranks aggregation +Please see [Percentiles are (usually) approximate](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation), [Compression](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-compression) and [Execution hint](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-execution-hint) for advice regarding approximation, performance and memory use of the percentile ranks aggregation :::: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-rate-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-rate-aggregation.md similarity index 96% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-rate-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-rate-aggregation.md index 15479da75465e..be3c46af84d65 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-rate-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-rate-aggregation.md @@ -375,7 +375,7 @@ By default `sum` mode is used. ## Relationship between bucket sizes and rate [_relationship_between_bucket_sizes_and_rate] -The `rate` aggregation supports all rate that can be used [calendar_intervals parameter](/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md#calendar_intervals) of `date_histogram` aggregation. The specified rate should compatible with the `date_histogram` aggregation interval, i.e. it should be possible to convert the bucket size into the rate. By default the interval of the `date_histogram` is used. +The `rate` aggregation supports all rate that can be used [calendar_intervals parameter](/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md#calendar_intervals) of `date_histogram` aggregation. The specified rate should compatible with the `date_histogram` aggregation interval, i.e. it should be possible to convert the bucket size into the rate. By default the interval of the `date_histogram` is used. `"rate": "second"` : compatible with all intervals diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-stats-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-stats-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-stats-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-stats-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-string-stats-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-string-stats-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-string-stats-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-string-stats-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-sum-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-sum-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-top-hits-aggregation.md similarity index 98% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-top-hits-aggregation.md index 0350eb9d8761d..05ff8160a122d 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-metrics-top-hits-aggregation.md @@ -39,7 +39,7 @@ The top_hits aggregation returns regular search hits, because of this many per h * [Include Sequence Numbers and Primary Terms](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-search) ::::{important} -If you **only** need `docvalue_fields`, `size`, and `sort` then [Top metrics](/reference/data-analysis/aggregations/search-aggregations-metrics-top-metrics.md) might be a more efficient choice than the Top Hits Aggregation. +If you **only** need `docvalue_fields`, `size`, and `sort` then [Top metrics](/reference/aggregations/search-aggregations-metrics-top-metrics.md) might be a more efficient choice than the Top Hits Aggregation. :::: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-metrics.md b/docs/reference/aggregations/search-aggregations-metrics-top-metrics.md similarity index 96% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-metrics.md rename to docs/reference/aggregations/search-aggregations-metrics-top-metrics.md index f49eebba715a5..1a93b8870cb33 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-top-metrics.md +++ b/docs/reference/aggregations/search-aggregations-metrics-top-metrics.md @@ -44,7 +44,7 @@ Which returns: } ``` -`top_metrics` is fairly similar to [`top_hits`](/reference/data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md) in spirit but because it is more limited it is able to do its job using less memory and is often faster. +`top_metrics` is fairly similar to [`top_hits`](/reference/aggregations/search-aggregations-metrics-top-hits-aggregation.md) in spirit but because it is more limited it is able to do its job using less memory and is often faster. ## `sort` [_sort] @@ -268,7 +268,7 @@ If `size` is more than `1` the `top_metrics` aggregation can’t be the **target ### Use with terms [search-aggregations-metrics-top-metrics-example-terms] -This aggregation should be quite useful inside of [`terms`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) aggregation, to, say, find the last value reported by each server. +This aggregation should be quite useful inside of [`terms`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) aggregation, to, say, find the last value reported by each server. $$$search-aggregations-metrics-top-metrics-terms$$$ diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-ttest-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-ttest-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-ttest-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-ttest-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-valuecount-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-valuecount-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-metrics-weight-avg-aggregation.md b/docs/reference/aggregations/search-aggregations-metrics-weight-avg-aggregation.md similarity index 100% rename from docs/reference/data-analysis/aggregations/search-aggregations-metrics-weight-avg-aggregation.md rename to docs/reference/aggregations/search-aggregations-metrics-weight-avg-aggregation.md diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md index 4c2f373fe33a2..16dae6d842c58 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md @@ -23,10 +23,10 @@ A sibling pipeline aggregation which calculates the mean value of a specified me ## Parameters [avg-bucket-params] `buckets_path` -: (Required, string) Path to the buckets to average. For syntax, see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax). +: (Required, string) Path to the buckets to average. For syntax, see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax). `gap_policy` -: (Optional, string) Policy to apply when gaps are found in the data. For valid values, see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy). Defaults to `skip`. +: (Optional, string) Policy to apply when gaps are found in the data. For valid values, see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy). Defaults to `skip`. `format` : (Optional, string) [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for the output value. If specified, the formatted value is returned in the aggregation’s `value_as_string` property. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md similarity index 94% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md index 2f684705d4725..f8330a2966eb3 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md @@ -33,8 +33,8 @@ $$$bucket-script-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | | `script` | The script to run for this aggregation. The script can be inline, file or indexed. (see [Scripting](docs-content://explore-analyze/scripting.md)for more details) | Required | | -| `buckets_path` | A map of script variables and their associated path to the buckets we wish to use for the variable(see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | A map of script variables and their associated path to the buckets we wish to use for the variable(see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the ratio percentage of t-shirt sales compared to total sales each month: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md similarity index 92% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md index 04e39708f048b..6d957f9da6461 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md @@ -38,8 +38,8 @@ $$$bucket-selector-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | | `script` | The script to run for this aggregation. The script can be inline, file or indexed. (see [Scripting](docs-content://explore-analyze/scripting.md)for more details) | Required | | -| `buckets_path` | A map of script variables and their associated path to the buckets we wish to use for the variable(see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | A map of script variables and their associated path to the buckets we wish to use for the variable(see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | The following snippet only retains buckets where the total sales for the month is more than 200: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md index 5d702cbc9aaab..bf0efecbd633f 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md @@ -42,7 +42,7 @@ $$$bucket-sort-params$$$ | `sort` | The list of fields to sort on. See [`sort`](/reference/elasticsearch/rest-apis/sort-search-results.md) for more details. | Optional | | | `from` | Buckets in positions prior to the set value will be truncated. | Optional | `0` | | `size` | The number of buckets to return. Defaults to all buckets of the parent aggregation. | Optional | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | The following snippet returns the buckets corresponding to the 3 months with the highest total sales in descending order: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md similarity index 98% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md index 880adfda21642..9da1d086b9561 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md @@ -27,7 +27,7 @@ $$$cumulative-cardinality-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the cardinality aggregation we wish to find the cumulative cardinality for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `buckets_path` | The path to the cardinality aggregation we wish to find the cumulative cardinality for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the cumulative cardinality of the total daily `users`: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md similarity index 95% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md index a0c08e7ffb590..8b977ec824fff 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md @@ -25,7 +25,7 @@ $$$cumulative-sum-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the cumulative sum for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `buckets_path` | The path to the buckets we wish to find the cumulative sum for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the cumulative sum of the total monthly `sales`: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-derivative-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-derivative-aggregation.md similarity index 96% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-derivative-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-derivative-aggregation.md index e04e0848d2264..f6151aecdfbb1 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-derivative-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-derivative-aggregation.md @@ -23,8 +23,8 @@ $$$derivative-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the derivative for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to find the derivative for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md similarity index 93% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md index facf92a6e82d7..40e7569eafe6b 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md @@ -27,8 +27,8 @@ $$$extended-stats-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to calculate stats for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to calculate stats for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | | `sigma` | The number of standard deviations above/below the mean to display | Optional | 2 | diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md similarity index 97% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md index 28cae9b986f58..529e2389b8f20 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md @@ -43,7 +43,7 @@ $$$inference-bucket-params$$$ | --- | --- | --- | --- | | `model_id` | The ID or alias for the trained model. | Required | - | | `inference_config` | Contains the inference type and its options. There are two types: [`regression`](#inference-agg-regression-opt) and [`classification`](#inference-agg-classification-opt) | Optional | - | -| `buckets_path` | Defines the paths to the input aggregations and maps the aggregation names to the field names expected by the model.See [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | - | +| `buckets_path` | Defines the paths to the input aggregations and maps the aggregation names to the field names expected by the model.See [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | - | ## Configuration options for {{infer}} models [_configuration_options_for_infer_models] diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md similarity index 91% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md index c78bb02de6c4b..169bb788dfba1 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md @@ -25,8 +25,8 @@ $$$max-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the maximum for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to find the maximum for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the maximum of the total monthly `sales`: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md similarity index 91% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md index 7d408cba067a9..bbee0c672507d 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md @@ -25,8 +25,8 @@ $$$min-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the minimum for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to find the minimum for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the minimum of the total monthly `sales`: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md similarity index 98% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md index a04ee179282a9..af396d32b63aa 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md @@ -27,10 +27,10 @@ $$$moving-fn-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | Path to the metric of interest (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | +| `buckets_path` | Path to the metric of interest (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | | `window` | The size of window to "slide" across the histogram. | Required | | | `script` | The script that should be executed on each window of data | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data. See [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy). | Optional | `skip` | +| `gap_policy` | The policy to apply when gaps are found in the data. See [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy). | Optional | `skip` | | `shift` | [Shift](#shift-parameter) of window position. | Optional | 0 | `moving_fn` aggregations must be embedded inside of a `histogram` or `date_histogram` aggregation. They can be embedded like any other metric aggregation: @@ -67,7 +67,7 @@ POST /_search 3. Finally, we specify a `moving_fn` aggregation which uses "the_sum" metric as its input. -Moving averages are built by first specifying a `histogram` or `date_histogram` over a field. You can then optionally add numeric metrics, such as a `sum`, inside of that histogram. Finally, the `moving_fn` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at one of the sibling metrics inside of the histogram (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`. +Moving averages are built by first specifying a `histogram` or `date_histogram` over a field. You can then optionally add numeric metrics, such as a `sum`, inside of that histogram. Finally, the `moving_fn` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at one of the sibling metrics inside of the histogram (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`. An example response from the above aggregation may look like: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md similarity index 82% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md index 1cab3ef611c66..52e10e10db591 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md @@ -7,9 +7,9 @@ mapped_pages: # Moving percentiles aggregation [search-aggregations-pipeline-moving-percentiles-aggregation] -Given an ordered series of [percentiles](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md), the Moving Percentile aggregation will slide a window across those percentiles and allow the user to compute the cumulative percentile. +Given an ordered series of [percentiles](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md), the Moving Percentile aggregation will slide a window across those percentiles and allow the user to compute the cumulative percentile. -This is conceptually very similar to the [Moving Function](/reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md) pipeline aggregation, except it works on the percentiles sketches instead of the actual buckets values. +This is conceptually very similar to the [Moving Function](/reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md) pipeline aggregation, except it works on the percentiles sketches instead of the actual buckets values. ## Syntax [_syntax_19] @@ -28,9 +28,9 @@ $$$moving-percentiles-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | Path to the percentile of interest (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | +| `buckets_path` | Path to the percentile of interest (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | | `window` | The size of window to "slide" across the histogram. | Required | | -| `shift` | [Shift](/reference/data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md#shift-parameter) of window position. | Optional | 0 | +| `shift` | [Shift](/reference/aggregations/search-aggregations-pipeline-movfn-aggregation.md#shift-parameter) of window position. | Optional | 0 | `moving_percentiles` aggregations must be embedded inside of a `histogram` or `date_histogram` aggregation. They can be embedded like any other metric aggregation: @@ -68,7 +68,7 @@ POST /_search 3. Finally, we specify a `moving_percentiles` aggregation which uses "the_percentile" sketch as its input. -Moving percentiles are built by first specifying a `histogram` or `date_histogram` over a field. You then add a percentile metric inside of that histogram. Finally, the `moving_percentiles` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at the percentiles aggregation inside of the histogram (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`). +Moving percentiles are built by first specifying a `histogram` or `date_histogram` over a field. You then add a percentile metric inside of that histogram. Finally, the `moving_percentiles` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at the percentiles aggregation inside of the histogram (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`). And the following may be the response: @@ -132,7 +132,7 @@ And the following may be the response: } ``` -The output format of the `moving_percentiles` aggregation is inherited from the format of the referenced [`percentiles`](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. +The output format of the `moving_percentiles` aggregation is inherited from the format of the referenced [`percentiles`](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation. Moving percentiles pipeline aggregations always run with `skip` gap policy. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-normalize-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-normalize-aggregation.md similarity index 96% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-normalize-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-normalize-aggregation.md index cdec3c4a59579..e275570d7b74a 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-normalize-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-normalize-aggregation.md @@ -7,7 +7,7 @@ mapped_pages: # Normalize aggregation [search-aggregations-pipeline-normalize-aggregation] -A parent pipeline aggregation which calculates the specific normalized/rescaled value for a specific bucket value. Values that cannot be normalized, will be skipped using the [skip gap policy](/reference/data-analysis/aggregations/pipeline.md#gap-policy). +A parent pipeline aggregation which calculates the specific normalized/rescaled value for a specific bucket value. Values that cannot be normalized, will be skipped using the [skip gap policy](/reference/aggregations/pipeline.md#gap-policy). ## Syntax [_syntax_20] @@ -26,7 +26,7 @@ $$$normalize_pipeline-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to normalize (see [`buckets_path` syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `buckets_path` | The path to the buckets we wish to normalize (see [`buckets_path` syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | | `method` | The specific [method](#normalize_pipeline-method) to apply | Required | | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md similarity index 93% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md index 54e6b80ab2bf2..7f3ea673505aa 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md @@ -25,8 +25,8 @@ $$$percentiles-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the percentiles for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to find the percentiles for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | | `percents` | The list of percentiles to calculate | Optional | `[ 1, 5, 25, 50, 75, 95, 99 ]` | | `keyed` | Flag which returns the range as an hash instead of an array of key-value pairs | Optional | `true` | diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md similarity index 93% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md index cd246d6217ce3..ae5de13e69ace 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md @@ -15,7 +15,7 @@ Single periods are also useful for transforming data into a stationary series. I By calculating the first-difference, we de-trend the data (e.g. remove a constant, linear trend). We can see that the data becomes a stationary series (e.g. the first difference is randomly distributed around zero, and doesn’t seem to exhibit any pattern/behavior). The transformation reveals that the dataset is following a random-walk; the value is the previous value +/- a random amount. This insight allows selection of further tools for analysis. -:::{image} ../../../images/dow.png +:::{image} images/dow.png :alt: dow :title: Dow Jones plotted and made stationary with first-differencing :name: serialdiff_dow @@ -25,7 +25,7 @@ Larger periods can be used to remove seasonal / cyclic behavior. In this example The first-difference removes the constant trend, leaving just a sine wave. The 30th-difference is then applied to the first-difference to remove the cyclic behavior, leaving a stationary series which is amenable to other analysis. -:::{image} ../../../images/lemmings.png +:::{image} images/lemmings.png :alt: lemmings :title: Lemmings data plotted made stationary with 1st and 30th difference :name: serialdiff_lemmings @@ -48,7 +48,7 @@ $$$serial-diff-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | Path to the metric of interest (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | +| `buckets_path` | Path to the metric of interest (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details | Required | | | `lag` | The historical bucket to subtract from the current value. E.g. a lag of 7 will subtract the current value from the value 7 buckets ago. Must be a positive, non-zero integer | Optional | `1` | | `gap_policy` | Determines what should happen when a gap in the data is encountered. | Optional | `insert_zeros` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | @@ -88,6 +88,6 @@ POST /_search 3. Finally, we specify a `serial_diff` aggregation which uses "the_sum" metric as its input. -Serial differences are built by first specifying a `histogram` or `date_histogram` over a field. You can then optionally add normal metrics, such as a `sum`, inside of that histogram. Finally, the `serial_diff` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at one of the sibling metrics inside of the histogram (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`. +Serial differences are built by first specifying a `histogram` or `date_histogram` over a field. You can then optionally add normal metrics, such as a `sum`, inside of that histogram. Finally, the `serial_diff` is embedded inside the histogram. The `buckets_path` parameter is then used to "point" at one of the sibling metrics inside of the histogram (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for a description of the syntax for `buckets_path`. diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md similarity index 90% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md index e816feaa1bbe0..b83d160aa185c 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md @@ -25,8 +25,8 @@ $$$stats-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to calculate stats for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to calculate stats for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property | Optional | `null` | The following snippet calculates the stats for monthly `sales`: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md b/docs/reference/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md similarity index 90% rename from docs/reference/data-analysis/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md rename to docs/reference/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md index f2c0e1597726f..47b3e32a2eb2f 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md @@ -25,8 +25,8 @@ $$$sum-bucket-params$$$ | Parameter Name | Description | Required | Default Value | | --- | --- | --- | --- | -| `buckets_path` | The path to the buckets we wish to find the sum for (see [`buckets_path` Syntax](/reference/data-analysis/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | -| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/data-analysis/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | +| `buckets_path` | The path to the buckets we wish to find the sum for (see [`buckets_path` Syntax](/reference/aggregations/pipeline.md#buckets-path-syntax) for more details) | Required | | +| `gap_policy` | The policy to apply when gaps are found in the data (see [Dealing with gaps in the data](/reference/aggregations/pipeline.md#gap-policy) for more details) | Optional | `skip` | | `format` | [DecimalFormat pattern](https://docs.oracle.com/en/java/javase/11/docs/api/java.base/java/text/DecimalFormat.html) for theoutput value. If specified, the formatted value is returned in the aggregation’s`value_as_string` property. | Optional | `null` | The following snippet calculates the sum of all the total monthly `sales` buckets: diff --git a/docs/reference/data-analysis/aggregations/search-aggregations-random-sampler-aggregation.md b/docs/reference/aggregations/search-aggregations-random-sampler-aggregation.md similarity index 82% rename from docs/reference/data-analysis/aggregations/search-aggregations-random-sampler-aggregation.md rename to docs/reference/aggregations/search-aggregations-random-sampler-aggregation.md index 0c68bb40b1ce8..96c0826b95e79 100644 --- a/docs/reference/data-analysis/aggregations/search-aggregations-random-sampler-aggregation.md +++ b/docs/reference/aggregations/search-aggregations-random-sampler-aggregation.md @@ -17,7 +17,7 @@ The `random_sampler` aggregation is a single bucket aggregation that randomly in The sampling is accomplished by providing a random subset of the entire set of documents in a shard. If a filter query is provided in the search request, that filter is applied over the sampled subset. Consequently, if a filter is restrictive, very few documents might match; therefore, the statistics might not be as accurate. ::::{note} -This aggregation is not to be confused with the [sampler aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md). The sampler aggregation is not over all documents; rather, it samples the first `n` documents matched by the query. +This aggregation is not to be confused with the [sampler aggregation](/reference/aggregations/search-aggregations-bucket-sampler-aggregation.md). The sampler aggregation is not over all documents; rather, it samples the first `n` documents matched by the query. :::: @@ -58,7 +58,7 @@ Consider the set of documents `[1, 2, 3, 4, 5]`. Your query matches `[1, 3, 5]` This type of sampling provides almost linear improvement in query latency in relation to the amount by which sampling reduces the document set size: -:::{image} ../../../images/random-sampler-agg-graph.png +:::{image} images/random-sampler-agg-graph.png :alt: Graph of the median speedup by sampling factor ::: @@ -66,7 +66,7 @@ This graph is typical of the speed up for the majority of aggregations for a tes The sample set is generated by skipping documents using a geometric distribution (`(1-p)^(k-1)*p`) with success probability being the provided `probability` (`p` in the distribution equation). The values returned from the distribution indicate how many documents to skip in the background. This is equivalent to selecting documents uniformly at random. It follows that the expected number of failures before a success is `(1-p)/p`. For example, with the `"probability": 0.01`, the expected number of failures (or average number of documents skipped) would be `99` with a variance of `9900`. Consequently, if you had only 80 documents in your index or matched by your filter, you would most likely receive no results. -:::{image} ../../../images/relative-error-vs-doc-count.png +:::{image} images/relative-error-vs-doc-count.png :alt: Graph of the relative error by sampling probability and doc count ::: @@ -91,8 +91,8 @@ The resulting statistics used from the random sampler aggregation are approximat ## Random sampling special cases [random-sampler-special-cases] -All counts returned by the random sampler aggregation are scaled to ease visualizations and calculations. For example, when randomly sampling a [date histogram aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) every `doc_count` value for every bucket is scaled by the inverse of the random_sampler `probability` value. So, if `doc_count` for a bucket is `10,000` with `probability: 0.1`, the actual number of documents aggregated is `1,000`. +All counts returned by the random sampler aggregation are scaled to ease visualizations and calculations. For example, when randomly sampling a [date histogram aggregation](/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) every `doc_count` value for every bucket is scaled by the inverse of the random_sampler `probability` value. So, if `doc_count` for a bucket is `10,000` with `probability: 0.1`, the actual number of documents aggregated is `1,000`. -An exception to this is [cardinality aggregation](/reference/data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md). Unique item counts are not suitable for automatic scaling. When interpreting the cardinality count, compare it to the number of sampled docs provided in the top level `doc_count` within the random_sampler aggregation. It gives you an idea of unique values as a percentage of total values. It may not reflect, however, the exact number of unique values for the given field. +An exception to this is [cardinality aggregation](/reference/aggregations/search-aggregations-metrics-cardinality-aggregation.md). Unique item counts are not suitable for automatic scaling. When interpreting the cardinality count, compare it to the number of sampled docs provided in the top level `doc_count` within the random_sampler aggregation. It gives you an idea of unique values as a percentage of total values. It may not reflect, however, the exact number of unique values for the given field. diff --git a/docs/reference/aggregations/toc.yml b/docs/reference/aggregations/toc.yml new file mode 100644 index 0000000000000..721b0028a2acf --- /dev/null +++ b/docs/reference/aggregations/toc.yml @@ -0,0 +1,96 @@ +toc: + - file: index.md + - file: bucket.md + children: + - file: search-aggregations-bucket-adjacency-matrix-aggregation.md + - file: search-aggregations-bucket-autodatehistogram-aggregation.md + - file: search-aggregations-bucket-categorize-text-aggregation.md + - file: search-aggregations-bucket-children-aggregation.md + - file: search-aggregations-bucket-composite-aggregation.md + - file: search-aggregations-bucket-datehistogram-aggregation.md + - file: search-aggregations-bucket-daterange-aggregation.md + - file: search-aggregations-bucket-diversified-sampler-aggregation.md + - file: search-aggregations-bucket-filter-aggregation.md + - file: search-aggregations-bucket-filters-aggregation.md + - file: search-aggregations-bucket-frequent-item-sets-aggregation.md + - file: search-aggregations-bucket-geodistance-aggregation.md + - file: search-aggregations-bucket-geohashgrid-aggregation.md + - file: search-aggregations-bucket-geohexgrid-aggregation.md + - file: search-aggregations-bucket-geotilegrid-aggregation.md + - file: search-aggregations-bucket-global-aggregation.md + - file: search-aggregations-bucket-histogram-aggregation.md + - file: search-aggregations-bucket-ipprefix-aggregation.md + - file: search-aggregations-bucket-iprange-aggregation.md + - file: search-aggregations-bucket-missing-aggregation.md + - file: search-aggregations-bucket-multi-terms-aggregation.md + - file: search-aggregations-bucket-nested-aggregation.md + - file: search-aggregations-bucket-parent-aggregation.md + - file: search-aggregations-random-sampler-aggregation.md + - file: search-aggregations-bucket-range-aggregation.md + - file: search-aggregations-bucket-rare-terms-aggregation.md + - file: search-aggregations-bucket-reverse-nested-aggregation.md + - file: search-aggregations-bucket-sampler-aggregation.md + - file: search-aggregations-bucket-significantterms-aggregation.md + - file: search-aggregations-bucket-significanttext-aggregation.md + - file: search-aggregations-bucket-terms-aggregation.md + - file: search-aggregations-bucket-time-series-aggregation.md + - file: search-aggregations-bucket-variablewidthhistogram-aggregation.md + - file: search-aggregations-bucket-range-field-note.md + - file: metrics.md + children: + - file: search-aggregations-metrics-avg-aggregation.md + - file: search-aggregations-metrics-boxplot-aggregation.md + - file: search-aggregations-metrics-cardinality-aggregation.md + - file: search-aggregations-metrics-extendedstats-aggregation.md + - file: search-aggregations-metrics-geobounds-aggregation.md + - file: search-aggregations-metrics-geocentroid-aggregation.md + - file: search-aggregations-metrics-geo-line.md + - file: search-aggregations-metrics-cartesian-bounds-aggregation.md + - file: search-aggregations-metrics-cartesian-centroid-aggregation.md + - file: search-aggregations-matrix-stats-aggregation.md + - file: search-aggregations-metrics-max-aggregation.md + - file: search-aggregations-metrics-median-absolute-deviation-aggregation.md + - file: search-aggregations-metrics-min-aggregation.md + - file: search-aggregations-metrics-percentile-rank-aggregation.md + - file: search-aggregations-metrics-percentile-aggregation.md + - file: search-aggregations-metrics-rate-aggregation.md + - file: search-aggregations-metrics-scripted-metric-aggregation.md + - file: search-aggregations-metrics-stats-aggregation.md + - file: search-aggregations-metrics-string-stats-aggregation.md + - file: search-aggregations-metrics-sum-aggregation.md + - file: search-aggregations-metrics-ttest-aggregation.md + - file: search-aggregations-metrics-top-hits-aggregation.md + - file: search-aggregations-metrics-top-metrics.md + - file: search-aggregations-metrics-valuecount-aggregation.md + - file: search-aggregations-metrics-weight-avg-aggregation.md + # TO DO: Figure out how to pull these in... separate TOCs? + # - file: data-analysis/observability/metrics-reference.md + # - file: data-analysis/serverless/metrics-reference.md + # children: + # - file: data-analysis/serverless/observability-host-metrics.md + # - file: data-analysis/serverless/observability-container-metrics.md + # - file: data-analysis/serverless/observability-kubernetes-pod-metrics.md + # - file: data-analysis/serverless/observability-aws-metrics.md + - file: pipeline.md + children: + - file: search-aggregations-pipeline-avg-bucket-aggregation.md + - file: search-aggregations-pipeline-bucket-script-aggregation.md + - file: search-aggregations-bucket-count-ks-test-aggregation.md + - file: search-aggregations-bucket-correlation-aggregation.md + - file: search-aggregations-pipeline-bucket-selector-aggregation.md + - file: search-aggregations-pipeline-bucket-sort-aggregation.md + - file: search-aggregations-change-point-aggregation.md + - file: search-aggregations-pipeline-cumulative-cardinality-aggregation.md + - file: search-aggregations-pipeline-cumulative-sum-aggregation.md + - file: search-aggregations-pipeline-derivative-aggregation.md + - file: search-aggregations-pipeline-extended-stats-bucket-aggregation.md + - file: search-aggregations-pipeline-inference-bucket-aggregation.md + - file: search-aggregations-pipeline-max-bucket-aggregation.md + - file: search-aggregations-pipeline-min-bucket-aggregation.md + - file: search-aggregations-pipeline-movfn-aggregation.md + - file: search-aggregations-pipeline-moving-percentiles-aggregation.md + - file: search-aggregations-pipeline-normalize-aggregation.md + - file: search-aggregations-pipeline-percentiles-bucket-aggregation.md + - file: search-aggregations-pipeline-serialdiff-aggregation.md + - file: search-aggregations-pipeline-stats-bucket-aggregation.md + - file: search-aggregations-pipeline-sum-bucket-aggregation.md diff --git a/docs/reference/community-contributed.md b/docs/reference/community-contributed/index.md similarity index 100% rename from docs/reference/community-contributed.md rename to docs/reference/community-contributed/index.md diff --git a/docs/reference/community-contributed/toc.yml b/docs/reference/community-contributed/toc.yml new file mode 100644 index 0000000000000..f2ab23679663c --- /dev/null +++ b/docs/reference/community-contributed/toc.yml @@ -0,0 +1,2 @@ +toc: + - file: index.md \ No newline at end of file diff --git a/docs/reference/elasticsearch-plugins/analysis-icu-folding.md b/docs/reference/elasticsearch-plugins/analysis-icu-folding.md index 4227f4902683b..057184c32a5c6 100644 --- a/docs/reference/elasticsearch-plugins/analysis-icu-folding.md +++ b/docs/reference/elasticsearch-plugins/analysis-icu-folding.md @@ -5,7 +5,7 @@ mapped_pages: # ICU folding token filter [analysis-icu-folding] -Case folding of Unicode characters based on `UTR#30`, like the [ASCII-folding token filter](/reference/data-analysis/text-analysis/analysis-asciifolding-tokenfilter.md) on steroids. It registers itself as the `icu_folding` token filter and is available to all indices: +Case folding of Unicode characters based on `UTR#30`, like the [ASCII-folding token filter](/reference/text-analysis/analysis-asciifolding-tokenfilter.md) on steroids. It registers itself as the `icu_folding` token filter and is available to all indices: ```console PUT icu_sample diff --git a/docs/reference/elasticsearch-plugins/analysis-icu-tokenizer.md b/docs/reference/elasticsearch-plugins/analysis-icu-tokenizer.md index e6d8b2379fe83..0f7ca09c23043 100644 --- a/docs/reference/elasticsearch-plugins/analysis-icu-tokenizer.md +++ b/docs/reference/elasticsearch-plugins/analysis-icu-tokenizer.md @@ -5,7 +5,7 @@ mapped_pages: # ICU tokenizer [analysis-icu-tokenizer] -Tokenizes text into words on word boundaries, as defined in [UAX #29: Unicode Text Segmentation](https://www.unicode.org/reports/tr29/). It behaves much like the [`standard` tokenizer](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md), but adds better support for some Asian languages by using a dictionary-based approach to identify words in Thai, Lao, Chinese, Japanese, and Korean, and using custom rules to break Myanmar and Khmer text into syllables. +Tokenizes text into words on word boundaries, as defined in [UAX #29: Unicode Text Segmentation](https://www.unicode.org/reports/tr29/). It behaves much like the [`standard` tokenizer](/reference/text-analysis/analysis-standard-tokenizer.md), but adds better support for some Asian languages by using a dictionary-based approach to identify words in Thai, Lao, Chinese, Japanese, and Korean, and using custom rules to break Myanmar and Khmer text into syllables. ```console PUT icu_sample diff --git a/docs/reference/elasticsearch-plugins/analysis-kuromoji-analyzer.md b/docs/reference/elasticsearch-plugins/analysis-kuromoji-analyzer.md index 8a085497d739f..6b1b96e841f66 100644 --- a/docs/reference/elasticsearch-plugins/analysis-kuromoji-analyzer.md +++ b/docs/reference/elasticsearch-plugins/analysis-kuromoji-analyzer.md @@ -13,7 +13,7 @@ The `kuromoji` analyzer uses the following analysis chain: * [`kuromoji_part_of_speech`](/reference/elasticsearch-plugins/analysis-kuromoji-speech.md) token filter * [`ja_stop`](/reference/elasticsearch-plugins/analysis-kuromoji-stop.md) token filter * [`kuromoji_stemmer`](/reference/elasticsearch-plugins/analysis-kuromoji-stemmer.md) token filter -* [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) token filter +* [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) token filter It supports the `mode` and `user_dictionary` settings from [`kuromoji_tokenizer`](/reference/elasticsearch-plugins/analysis-kuromoji-tokenizer.md). diff --git a/docs/reference/elasticsearch-plugins/analysis-kuromoji-stop.md b/docs/reference/elasticsearch-plugins/analysis-kuromoji-stop.md index 001839a8828cd..b6e29cd14e1f1 100644 --- a/docs/reference/elasticsearch-plugins/analysis-kuromoji-stop.md +++ b/docs/reference/elasticsearch-plugins/analysis-kuromoji-stop.md @@ -5,7 +5,7 @@ mapped_pages: # ja_stop token filter [analysis-kuromoji-stop] -The `ja_stop` token filter filters out Japanese stopwords (`_japanese_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_japanese_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) instead. +The `ja_stop` token filter filters out Japanese stopwords (`_japanese_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_japanese_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/text-analysis/analysis-stop-tokenfilter.md) instead. ```console PUT kuromoji_sample diff --git a/docs/reference/elasticsearch-plugins/analysis-nori-analyzer.md b/docs/reference/elasticsearch-plugins/analysis-nori-analyzer.md index 9f7f788dfe4db..c28fd994f3b58 100644 --- a/docs/reference/elasticsearch-plugins/analysis-nori-analyzer.md +++ b/docs/reference/elasticsearch-plugins/analysis-nori-analyzer.md @@ -10,7 +10,7 @@ The `nori` analyzer consists of the following tokenizer and token filters: * [`nori_tokenizer`](/reference/elasticsearch-plugins/analysis-nori-tokenizer.md) * [`nori_part_of_speech`](/reference/elasticsearch-plugins/analysis-nori-speech.md) token filter * [`nori_readingform`](/reference/elasticsearch-plugins/analysis-nori-readingform.md) token filter -* [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) token filter +* [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) token filter It supports the `decompound_mode` and `user_dictionary` settings from [`nori_tokenizer`](/reference/elasticsearch-plugins/analysis-nori-tokenizer.md) and the `stoptags` setting from [`nori_part_of_speech`](/reference/elasticsearch-plugins/analysis-nori-speech.md). diff --git a/docs/reference/elasticsearch-plugins/analysis-polish-stop.md b/docs/reference/elasticsearch-plugins/analysis-polish-stop.md index db2bac3b38585..e6c6cc9746218 100644 --- a/docs/reference/elasticsearch-plugins/analysis-polish-stop.md +++ b/docs/reference/elasticsearch-plugins/analysis-polish-stop.md @@ -5,7 +5,7 @@ mapped_pages: # polish_stop token filter [analysis-polish-stop] -The `polish_stop` token filter filters out Polish stopwords (`_polish_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_polish_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) instead. +The `polish_stop` token filter filters out Polish stopwords (`_polish_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_polish_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/text-analysis/analysis-stop-tokenfilter.md) instead. ```console PUT /polish_stop_example diff --git a/docs/reference/elasticsearch-plugins/analysis-smartcn_stop.md b/docs/reference/elasticsearch-plugins/analysis-smartcn_stop.md index b1bc52570de2b..4f2e2b2fa77ac 100644 --- a/docs/reference/elasticsearch-plugins/analysis-smartcn_stop.md +++ b/docs/reference/elasticsearch-plugins/analysis-smartcn_stop.md @@ -5,7 +5,7 @@ mapped_pages: # smartcn_stop token filter [analysis-smartcn_stop] -The `smartcn_stop` token filter filters out stopwords defined by `smartcn` analyzer (`_smartcn_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_smartcn_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) instead. +The `smartcn_stop` token filter filters out stopwords defined by `smartcn` analyzer (`_smartcn_`), and any other custom stopwords specified by the user. This filter only supports the predefined `_smartcn_` stopwords list. If you want to use a different predefined list, then use the [`stop` token filter](/reference/text-analysis/analysis-stop-tokenfilter.md) instead. ```console PUT smartcn_example diff --git a/docs/reference/elasticsearch-plugins/cloud/ec-custom-bundles.md b/docs/reference/elasticsearch-plugins/cloud/ec-custom-bundles.md index b4010c6d10e23..93275e5b868ba 100644 --- a/docs/reference/elasticsearch-plugins/cloud/ec-custom-bundles.md +++ b/docs/reference/elasticsearch-plugins/cloud/ec-custom-bundles.md @@ -84,7 +84,7 @@ Bundles The dictionary `synonyms.txt` can be used as `synonyms.txt` or using the full path `/app/config/synonyms.txt` in the `synonyms_path` of the `synonym-filter`. - To learn more about analyzing with synonyms, check [Synonym token filter](/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md) and [Formatting Synonyms](https://www.elastic.co/guide/en/elasticsearch/guide/2.x/synonym-formats.html). + To learn more about analyzing with synonyms, check [Synonym token filter](/reference/text-analysis/analysis-synonym-tokenfilter.md) and [Formatting Synonyms](https://www.elastic.co/guide/en/elasticsearch/guide/2.x/synonym-formats.html). **GeoIP database bundle** diff --git a/docs/reference/elasticsearch/configuration-reference/search-settings.md b/docs/reference/elasticsearch/configuration-reference/search-settings.md index ff20acfa5c3fa..5282743b27068 100644 --- a/docs/reference/elasticsearch/configuration-reference/search-settings.md +++ b/docs/reference/elasticsearch/configuration-reference/search-settings.md @@ -25,7 +25,7 @@ $$$indices-query-bool-max-clause-count$$$ $$$search-settings-max-buckets$$$ `search.max_buckets` -: ([Dynamic](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-put-settings), integer) Maximum number of [aggregation buckets](/reference/data-analysis/aggregations/bucket.md) allowed in a single response. Defaults to 65,536. +: ([Dynamic](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-put-settings), integer) Maximum number of [aggregation buckets](/reference/aggregations/bucket.md) allowed in a single response. Defaults to 65,536. Requests that attempt to return more than this limit will return an error. @@ -33,7 +33,7 @@ $$$search-settings-max-buckets$$$ $$$search-settings-only-allowed-scripts$$$ `search.aggs.only_allowed_metric_scripts` -: ([Dynamic](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-put-settings), boolean) Configures whether only explicitly allowed scripts can be used in [scripted metrics aggregations](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md). Defaults to `false`. +: ([Dynamic](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-put-settings), boolean) Configures whether only explicitly allowed scripts can be used in [scripted metrics aggregations](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md). Defaults to `false`. Requests using scripts not contained in either [`search.aggs.allowed_inline_metric_scripts`](/reference/elasticsearch/configuration-reference/search-settings.md#search-settings-allowed-inline-scripts) or [`search.aggs.allowed_stored_metric_scripts`](/reference/elasticsearch/configuration-reference/search-settings.md#search-settings-allowed-stored-scripts) will return an error. diff --git a/docs/reference/elasticsearch/index-settings/index-modules.md b/docs/reference/elasticsearch/index-settings/index-modules.md index b0e92eb153887..393f4d30c9392 100644 --- a/docs/reference/elasticsearch/index-settings/index-modules.md +++ b/docs/reference/elasticsearch/index-settings/index-modules.md @@ -182,7 +182,7 @@ $$$index-max-ngram-diff$$$ $$$index-max-shingle-diff$$$ `index.max_shingle_diff` -: The maximum allowed difference between max_shingle_size and min_shingle_size for the [`shingle` token filter](/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md). Defaults to `3`. +: The maximum allowed difference between max_shingle_size and min_shingle_size for the [`shingle` token filter](/reference/text-analysis/analysis-shingle-tokenfilter.md). Defaults to `3`. `index.max_refresh_listeners` : Maximum number of refresh listeners available on each shard of the index. These listeners are used to implement `refresh=wait_for`. diff --git a/docs/reference/elasticsearch/index.md b/docs/reference/elasticsearch/index.md new file mode 100644 index 0000000000000..fd75632ea62a0 --- /dev/null +++ b/docs/reference/elasticsearch/index.md @@ -0,0 +1 @@ +# Elasticsearch and index management \ No newline at end of file diff --git a/docs/reference/elasticsearch/mapping-reference/aggregate-metric-double.md b/docs/reference/elasticsearch/mapping-reference/aggregate-metric-double.md index 53dbbaf4bfdf7..bd27b239d60b6 100644 --- a/docs/reference/elasticsearch/mapping-reference/aggregate-metric-double.md +++ b/docs/reference/elasticsearch/mapping-reference/aggregate-metric-double.md @@ -7,9 +7,9 @@ mapped_pages: # Aggregate metric field type [aggregate-metric-double] -Stores pre-aggregated numeric values for [metric aggregations](/reference/data-analysis/aggregations/metrics.md). An `aggregate_metric_double` field is an object containing one or more of the following metric sub-fields: `min`, `max`, `sum`, and `value_count`. +Stores pre-aggregated numeric values for [metric aggregations](/reference/aggregations/metrics.md). An `aggregate_metric_double` field is an object containing one or more of the following metric sub-fields: `min`, `max`, `sum`, and `value_count`. -When you run certain metric aggregations on an `aggregate_metric_double` field, the aggregation uses the related sub-field’s values. For example, a [`min`](/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md) aggregation on an `aggregate_metric_double` field returns the minimum value of all `min` sub-fields. +When you run certain metric aggregations on an `aggregate_metric_double` field, the aggregation uses the related sub-field’s values. For example, a [`min`](/reference/aggregations/search-aggregations-metrics-min-aggregation.md) aggregation on an `aggregate_metric_double` field returns the minimum value of all `min` sub-fields. ::::{important} An `aggregate_metric_double` field stores a single numeric [doc value](/reference/elasticsearch/mapping-reference/doc-values.md) for each metric sub-field. Array values are not supported. `min`, `max`, and `sum` values are `double` numbers. `value_count` is a positive `long` number. @@ -34,7 +34,7 @@ PUT my-index ## Parameters for `aggregate_metric_double` fields [aggregate-metric-double-params] `metrics` -: (Required, array of strings) Array of metric sub-fields to store. Each value corresponds to a [metric aggregation](/reference/data-analysis/aggregations/metrics.md). Valid values are [`min`](/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md), [`max`](/reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md), [`sum`](/reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md), and [`value_count`](/reference/data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md). You must specify at least one value. +: (Required, array of strings) Array of metric sub-fields to store. Each value corresponds to a [metric aggregation](/reference/aggregations/metrics.md). Valid values are [`min`](/reference/aggregations/search-aggregations-metrics-min-aggregation.md), [`max`](/reference/aggregations/search-aggregations-metrics-max-aggregation.md), [`sum`](/reference/aggregations/search-aggregations-metrics-sum-aggregation.md), and [`value_count`](/reference/aggregations/search-aggregations-metrics-valuecount-aggregation.md). You must specify at least one value. `default_metric` : (Required, string) Default metric sub-field to use for queries, scripts, and aggregations that don’t use a sub-field. Must be a value from the `metrics` array. @@ -57,11 +57,11 @@ PUT my-index We designed `aggregate_metric_double` fields for use with the following aggregations: -* A [`min`](/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md) aggregation returns the minimum value of all `min` sub-fields. -* A [`max`](/reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md) aggregation returns the maximum value of all `max` sub-fields. -* A [`sum`](/reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md) aggregation returns the sum of the values of all `sum` sub-fields. -* A [`value_count`](/reference/data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md) aggregation returns the sum of the values of all `value_count` sub-fields. -* A [`avg`](/reference/data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md) aggregation. There is no `avg` sub-field; the result of the `avg` aggregation is computed using the `sum` and `value_count` metrics. To run an `avg` aggregation, the field must contain both `sum` and `value_count` metric sub-field. +* A [`min`](/reference/aggregations/search-aggregations-metrics-min-aggregation.md) aggregation returns the minimum value of all `min` sub-fields. +* A [`max`](/reference/aggregations/search-aggregations-metrics-max-aggregation.md) aggregation returns the maximum value of all `max` sub-fields. +* A [`sum`](/reference/aggregations/search-aggregations-metrics-sum-aggregation.md) aggregation returns the sum of the values of all `sum` sub-fields. +* A [`value_count`](/reference/aggregations/search-aggregations-metrics-valuecount-aggregation.md) aggregation returns the sum of the values of all `value_count` sub-fields. +* A [`avg`](/reference/aggregations/search-aggregations-metrics-avg-aggregation.md) aggregation. There is no `avg` sub-field; the result of the `avg` aggregation is computed using the `sum` and `value_count` metrics. To run an `avg` aggregation, the field must contain both `sum` and `value_count` metric sub-field. Running any other aggregation on an `aggregate_metric_double` field will fail with an "unsupported aggregation" error. diff --git a/docs/reference/elasticsearch/mapping-reference/boolean.md b/docs/reference/elasticsearch/mapping-reference/boolean.md index 3b89832213084..2896a27024d5c 100644 --- a/docs/reference/elasticsearch/mapping-reference/boolean.md +++ b/docs/reference/elasticsearch/mapping-reference/boolean.md @@ -48,7 +48,7 @@ GET my-index-000001/_search 2. Searching for documents with a JSON `true`. -Aggregations like the [`terms` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) use `1` and `0` for the `key`, and the strings `"true"` and `"false"` for the `key_as_string`. Boolean fields when used in scripts, return `true` and `false`: +Aggregations like the [`terms` aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) use `1` and `0` for the `key`, and the strings `"true"` and `"false"` for the `key_as_string`. Boolean fields when used in scripts, return `true` and `false`: ```console POST my-index-000001/_doc/1?refresh diff --git a/docs/reference/elasticsearch/mapping-reference/eager-global-ordinals.md b/docs/reference/elasticsearch/mapping-reference/eager-global-ordinals.md index 47da87c7f5719..65f46ec492509 100644 --- a/docs/reference/elasticsearch/mapping-reference/eager-global-ordinals.md +++ b/docs/reference/elasticsearch/mapping-reference/eager-global-ordinals.md @@ -64,7 +64,7 @@ Usually, global ordinals do not present a large overhead in terms of their loadi In some cases it is possible to avoid global ordinal loading altogether: -* The `terms`, `sampler`, and `significant_terms` aggregations support a parameter [`execution_hint`](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-execution-hint) that helps control how buckets are collected. It defaults to `global_ordinals`, but can be set to `map` to instead use the term values directly. +* The `terms`, `sampler`, and `significant_terms` aggregations support a parameter [`execution_hint`](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-execution-hint) that helps control how buckets are collected. It defaults to `global_ordinals`, but can be set to `map` to instead use the term values directly. * If a shard has been [force-merged](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-forcemerge) down to a single segment, then its segment ordinals are already *global* to the shard. In this case, Elasticsearch does not need to build a global ordinal mapping and there is no additional overhead from using global ordinals. Note that for performance reasons you should only force-merge an index to which you will never write to again. diff --git a/docs/reference/elasticsearch/mapping-reference/field-data-types.md b/docs/reference/elasticsearch/mapping-reference/field-data-types.md index 1dd90ba02f0f2..0265546eedbec 100644 --- a/docs/reference/elasticsearch/mapping-reference/field-data-types.md +++ b/docs/reference/elasticsearch/mapping-reference/field-data-types.md @@ -139,7 +139,7 @@ In {{es}}, arrays do not require a dedicated field data type. Any field can cont ## Multi-fields [types-multi-fields] -It is often useful to index the same field in different ways for different purposes. For instance, a `string` field could be mapped as a `text` field for full-text search, and as a `keyword` field for sorting or aggregations. Alternatively, you could index a text field with the [`standard` analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md), the [`english`](/reference/data-analysis/text-analysis/analysis-lang-analyzer.md#english-analyzer) analyzer, and the [`french` analyzer](/reference/data-analysis/text-analysis/analysis-lang-analyzer.md#french-analyzer). +It is often useful to index the same field in different ways for different purposes. For instance, a `string` field could be mapped as a `text` field for full-text search, and as a `keyword` field for sorting or aggregations. Alternatively, you could index a text field with the [`standard` analyzer](/reference/text-analysis/analysis-standard-analyzer.md), the [`english`](/reference/text-analysis/analysis-lang-analyzer.md#english-analyzer) analyzer, and the [`french` analyzer](/reference/text-analysis/analysis-lang-analyzer.md#french-analyzer). This is the purpose of *multi-fields*. Most field types support multi-fields via the [`fields`](/reference/elasticsearch/mapping-reference/multi-fields.md) parameter. diff --git a/docs/reference/elasticsearch/mapping-reference/geo-point.md b/docs/reference/elasticsearch/mapping-reference/geo-point.md index 0408eaea628ad..d69033c219695 100644 --- a/docs/reference/elasticsearch/mapping-reference/geo-point.md +++ b/docs/reference/elasticsearch/mapping-reference/geo-point.md @@ -10,9 +10,9 @@ mapped_pages: Fields of type `geo_point` accept latitude-longitude pairs, which can be used: * to find geopoints within a [bounding box](/reference/query-languages/query-dsl/query-dsl-geo-bounding-box-query.md), within a certain [distance](/reference/query-languages/query-dsl/query-dsl-geo-distance-query.md) of a central point, or within a [`geo_shape` query](/reference/query-languages/query-dsl/query-dsl-geo-shape-query.md) (for example, points in a polygon). -* to aggregate documents by [distance](/reference/data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md) from a central point. -* to aggregate documents by geographic grids: either [`geo_hash`](/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md), [`geo_tile`](/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md) or [`geo_hex`](/reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md). -* to aggregate geopoints into a track using the metrics aggregation [`geo_line`](/reference/data-analysis/aggregations/search-aggregations-metrics-geo-line.md). +* to aggregate documents by [distance](/reference/aggregations/search-aggregations-bucket-geodistance-aggregation.md) from a central point. +* to aggregate documents by geographic grids: either [`geo_hash`](/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md), [`geo_tile`](/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md) or [`geo_hex`](/reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md). +* to aggregate geopoints into a track using the metrics aggregation [`geo_line`](/reference/aggregations/search-aggregations-metrics-geo-line.md). * to integrate distance into a document’s [relevance score](/reference/query-languages/query-dsl/query-dsl-function-score-query.md). * to [sort](/reference/elasticsearch/rest-apis/sort-search-results.md#geo-sorting) documents by distance. diff --git a/docs/reference/elasticsearch/mapping-reference/geo-shape.md b/docs/reference/elasticsearch/mapping-reference/geo-shape.md index 20c55892333ff..1707db318cd4a 100644 --- a/docs/reference/elasticsearch/mapping-reference/geo-shape.md +++ b/docs/reference/elasticsearch/mapping-reference/geo-shape.md @@ -19,9 +19,9 @@ Documents using this type can be used: * to aggregate documents by geographic grids: - * either [`geo_hash`](/reference/data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md) - * or [`geo_tile`](/reference/data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md) - * or [`geo_hex`](/reference/data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md) + * either [`geo_hash`](/reference/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md) + * or [`geo_tile`](/reference/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md) + * or [`geo_hex`](/reference/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md) @@ -359,7 +359,7 @@ POST /example/_doc #### Circle [_circle] -Neither GeoJSON nor WKT supports a point-radius circle type. Instead, use a [circle ingest processor](/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md) to approximate the circle as a [`polygon`](#geo-polygon). +Neither GeoJSON nor WKT supports a point-radius circle type. Instead, use a [circle ingest processor](/reference/enrich-processor/ingest-circle-processor.md) to approximate the circle as a [`polygon`](#geo-polygon). ### Sorting and Retrieving index Shapes [_sorting_and_retrieving_index_shapes] diff --git a/docs/reference/elasticsearch/mapping-reference/histogram.md b/docs/reference/elasticsearch/mapping-reference/histogram.md index 73b30b6deac06..715e3d60ec6a4 100644 --- a/docs/reference/elasticsearch/mapping-reference/histogram.md +++ b/docs/reference/elasticsearch/mapping-reference/histogram.md @@ -27,16 +27,16 @@ Because the elements in the `values` array correspond to the elements in the sam Because the data is not indexed, you only can use `histogram` fields for the following aggregations and queries: -* [min](/reference/data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md#search-aggregations-metrics-min-aggregation-histogram-fields) aggregation -* [max](/reference/data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md#search-aggregations-metrics-max-aggregation-histogram-fields) aggregation -* [sum](/reference/data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md#search-aggregations-metrics-sum-aggregation-histogram-fields) aggregation -* [value_count](/reference/data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md#search-aggregations-metrics-valuecount-aggregation-histogram-fields) aggregation -* [avg](/reference/data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md#search-aggregations-metrics-avg-aggregation-histogram-fields) aggregation -* [percentiles](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation -* [percentile ranks](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md) aggregation -* [boxplot](/reference/data-analysis/aggregations/search-aggregations-metrics-boxplot-aggregation.md) aggregation -* [histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-histogram-fields) aggregation -* [range](/reference/data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md#search-aggregations-bucket-range-aggregation-histogram-fields) aggregation +* [min](/reference/aggregations/search-aggregations-metrics-min-aggregation.md#search-aggregations-metrics-min-aggregation-histogram-fields) aggregation +* [max](/reference/aggregations/search-aggregations-metrics-max-aggregation.md#search-aggregations-metrics-max-aggregation-histogram-fields) aggregation +* [sum](/reference/aggregations/search-aggregations-metrics-sum-aggregation.md#search-aggregations-metrics-sum-aggregation-histogram-fields) aggregation +* [value_count](/reference/aggregations/search-aggregations-metrics-valuecount-aggregation.md#search-aggregations-metrics-valuecount-aggregation-histogram-fields) aggregation +* [avg](/reference/aggregations/search-aggregations-metrics-avg-aggregation.md#search-aggregations-metrics-avg-aggregation-histogram-fields) aggregation +* [percentiles](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md) aggregation +* [percentile ranks](/reference/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md) aggregation +* [boxplot](/reference/aggregations/search-aggregations-metrics-boxplot-aggregation.md) aggregation +* [histogram](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md#search-aggregations-bucket-histogram-aggregation-histogram-fields) aggregation +* [range](/reference/aggregations/search-aggregations-bucket-range-aggregation.md#search-aggregations-bucket-range-aggregation-histogram-fields) aggregation * [exists](/reference/query-languages/query-dsl/query-dsl-exists-query.md) query @@ -44,8 +44,8 @@ Because the data is not indexed, you only can use `histogram` fields for the fol When using a histogram as part of an aggregation, the accuracy of the results will depend on how the histogram was constructed. It is important to consider the percentiles aggregation mode that will be used to build it. Some possibilities include: -* For the [T-Digest](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md) mode, the `values` array represents the mean centroid positions and the `counts` array represents the number of values that are attributed to each centroid. If the algorithm has already started to approximate the percentiles, this inaccuracy is carried over in the histogram. -* For the [High Dynamic Range (HDR)](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md#_hdr_histogram) histogram mode, the `values` array represents fixed upper limits of each bucket interval, and the `counts` array represents the number of values that are attributed to each interval. This implementation maintains a fixed worse-case percentage error (specified as a number of significant digits), therefore the value used when generating the histogram would be the maximum accuracy you can achieve at aggregation time. +* For the [T-Digest](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md) mode, the `values` array represents the mean centroid positions and the `counts` array represents the number of values that are attributed to each centroid. If the algorithm has already started to approximate the percentiles, this inaccuracy is carried over in the histogram. +* For the [High Dynamic Range (HDR)](/reference/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md#_hdr_histogram) histogram mode, the `values` array represents fixed upper limits of each bucket interval, and the `counts` array represents the number of values that are attributed to each interval. This implementation maintains a fixed worse-case percentage error (specified as a number of significant digits), therefore the value used when generating the histogram would be the maximum accuracy you can achieve at aggregation time. The histogram field is "algorithm agnostic" and does not store data specific to either T-Digest or HDRHistogram. While this means the field can technically be aggregated with either algorithm, in practice the user should chose one algorithm and index data in that manner (e.g. centroids for T-Digest or intervals for HDRHistogram) to ensure best accuracy. @@ -110,7 +110,7 @@ PUT my-index-000001/_doc/2 } ``` -1. Values for each bucket. Values in the array are treated as doubles and must be given in increasing order. For [T-Digest](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation) histograms this value represents the mean value. In case of HDR histograms this represents the value iterated to. +1. Values for each bucket. Values in the array are treated as doubles and must be given in increasing order. For [T-Digest](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation) histograms this value represents the mean value. In case of HDR histograms this represents the value iterated to. 2. Count for each bucket. Values in the arrays are treated as long integers and must be positive or zero. Negative values will be rejected. The relation between a bucket and a count is given by the position in the array. diff --git a/docs/reference/elasticsearch/mapping-reference/keyword.md b/docs/reference/elasticsearch/mapping-reference/keyword.md index a45b933861565..8cd93a7234647 100644 --- a/docs/reference/elasticsearch/mapping-reference/keyword.md +++ b/docs/reference/elasticsearch/mapping-reference/keyword.md @@ -13,7 +13,7 @@ The keyword family includes the following field types: * [`constant_keyword`](#constant-keyword-field-type) for keyword fields that always contain the same value. * [`wildcard`](#wildcard-field-type) for unstructured machine-generated content. The `wildcard` type is optimized for fields with large values or high cardinality. -Keyword fields are often used in [sorting](/reference/elasticsearch/rest-apis/sort-search-results.md), [aggregations](/reference/data-analysis/aggregations/index.md), and [term-level queries](/reference/query-languages/query-dsl/term-level-queries.md), such as [`term`](/reference/query-languages/query-dsl/query-dsl-term-query.md). +Keyword fields are often used in [sorting](/reference/elasticsearch/rest-apis/sort-search-results.md), [aggregations](/reference/aggregations/index.md), and [term-level queries](/reference/query-languages/query-dsl/term-level-queries.md), such as [`term`](/reference/query-languages/query-dsl/query-dsl-term-query.md). ::::{tip} Avoid using keyword fields for full-text search. Use the [`text`](/reference/elasticsearch/mapping-reference/text.md) field type instead. diff --git a/docs/reference/elasticsearch/mapping-reference/mapping-doc-count-field.md b/docs/reference/elasticsearch/mapping-reference/mapping-doc-count-field.md index 99896d2765783..e10cafdb3b921 100644 --- a/docs/reference/elasticsearch/mapping-reference/mapping-doc-count-field.md +++ b/docs/reference/elasticsearch/mapping-reference/mapping-doc-count-field.md @@ -70,7 +70,7 @@ PUT my_index/_doc/2 1. Field `_doc_count` must be a positive integer storing the number of documents aggregated to produce each histogram. -If we run the following [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md) on `my_index`: +If we run the following [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md) on `my_index`: ```console GET /_search diff --git a/docs/reference/elasticsearch/mapping-reference/multi-fields.md b/docs/reference/elasticsearch/mapping-reference/multi-fields.md index 1a452123df0b2..e90f733baace4 100644 --- a/docs/reference/elasticsearch/mapping-reference/multi-fields.md +++ b/docs/reference/elasticsearch/mapping-reference/multi-fields.md @@ -70,7 +70,7 @@ A multi-field mapping is completely separate from the parent field’s mapping. ## Multi-fields with multiple analyzers [_multi_fields_with_multiple_analyzers] -Another use case of multi-fields is to analyze the same field in different ways for better relevance. For instance we could index a field with the [`standard` analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md) which breaks text up into words, and again with the [`english` analyzer](/reference/data-analysis/text-analysis/analysis-lang-analyzer.md#english-analyzer) which stems words into their root form: +Another use case of multi-fields is to analyze the same field in different ways for better relevance. For instance we could index a field with the [`standard` analyzer](/reference/text-analysis/analysis-standard-analyzer.md) which breaks text up into words, and again with the [`english` analyzer](/reference/text-analysis/analysis-lang-analyzer.md#english-analyzer) which stems words into their root form: ```console PUT my-index-000001 diff --git a/docs/reference/elasticsearch/mapping-reference/nested.md b/docs/reference/elasticsearch/mapping-reference/nested.md index eb9cf59e95680..4285188f5e8ec 100644 --- a/docs/reference/elasticsearch/mapping-reference/nested.md +++ b/docs/reference/elasticsearch/mapping-reference/nested.md @@ -157,7 +157,7 @@ GET my-index-000001/_search Nested documents can be: * queried with the [`nested`](/reference/query-languages/query-dsl/query-dsl-nested-query.md) query. -* analyzed with the [`nested`](/reference/data-analysis/aggregations/search-aggregations-bucket-nested-aggregation.md) and [`reverse_nested`](/reference/data-analysis/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md) aggregations. +* analyzed with the [`nested`](/reference/aggregations/search-aggregations-bucket-nested-aggregation.md) and [`reverse_nested`](/reference/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md) aggregations. * sorted with [nested sorting](/reference/elasticsearch/rest-apis/sort-search-results.md#nested-sorting). * retrieved and highlighted with [nested inner hits](/reference/elasticsearch/rest-apis/retrieve-inner-hits.md#nested-inner-hits). diff --git a/docs/reference/elasticsearch/mapping-reference/parent-join.md b/docs/reference/elasticsearch/mapping-reference/parent-join.md index 4a555ca8b05b8..365b10b90aa60 100644 --- a/docs/reference/elasticsearch/mapping-reference/parent-join.md +++ b/docs/reference/elasticsearch/mapping-reference/parent-join.md @@ -243,7 +243,7 @@ Will return: ## Parent-join queries and aggregations [_parent_join_queries_and_aggregations] -See the [`has_child`](/reference/query-languages/query-dsl/query-dsl-has-child-query.md) and [`has_parent`](/reference/query-languages/query-dsl/query-dsl-has-parent-query.md) queries, the [`children`](/reference/data-analysis/aggregations/search-aggregations-bucket-children-aggregation.md) aggregation, and [inner hits](/reference/elasticsearch/rest-apis/retrieve-inner-hits.md#parent-child-inner-hits) for more information. +See the [`has_child`](/reference/query-languages/query-dsl/query-dsl-has-child-query.md) and [`has_parent`](/reference/query-languages/query-dsl/query-dsl-has-parent-query.md) queries, the [`children`](/reference/aggregations/search-aggregations-bucket-children-aggregation.md) aggregation, and [inner hits](/reference/elasticsearch/rest-apis/retrieve-inner-hits.md#parent-child-inner-hits) for more information. The value of the `join` field is accessible in aggregations and scripts, and may be queried with the [`parent_id` query](/reference/query-languages/query-dsl/query-dsl-parent-id-query.md): @@ -279,7 +279,7 @@ GET my-index-000001/_search ``` 1. Querying the `parent id` field (also see the [`has_parent` query](/reference/query-languages/query-dsl/query-dsl-has-parent-query.md) and the [`has_child` query](/reference/query-languages/query-dsl/query-dsl-has-child-query.md)) -2. Aggregating on the `parent id` field (also see the [`children`](/reference/data-analysis/aggregations/search-aggregations-bucket-children-aggregation.md) aggregation) +2. Aggregating on the `parent id` field (also see the [`children`](/reference/aggregations/search-aggregations-bucket-children-aggregation.md) aggregation) 3. Accessing the `parent id` field in scripts. diff --git a/docs/reference/elasticsearch/mapping-reference/range.md b/docs/reference/elasticsearch/mapping-reference/range.md index 9dae0f5a4c165..3699d7bd68ba2 100644 --- a/docs/reference/elasticsearch/mapping-reference/range.md +++ b/docs/reference/elasticsearch/mapping-reference/range.md @@ -7,7 +7,7 @@ mapped_pages: # Range field types [range] -Range field types represent a continuous range of values between an upper and lower bound. For example, a range can represent *any date in October* or *any integer from 0 to 9*. They are defined using the operators `gt` or `gte` for the lower bound, and `lt` or `lte` for the upper bound. They can be used for querying, and have limited support for aggregations. The only supported aggregations are [histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md), [cardinality](/reference/data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md). +Range field types represent a continuous range of values between an upper and lower bound. For example, a range can represent *any date in October* or *any integer from 0 to 9*. They are defined using the operators `gt` or `gte` for the lower bound, and `lt` or `lte` for the upper bound. They can be used for querying, and have limited support for aggregations. The only supported aggregations are [histogram](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md), [cardinality](/reference/aggregations/search-aggregations-metrics-cardinality-aggregation.md). The following range types are supported: diff --git a/docs/reference/elasticsearch/mapping-reference/search-analyzer.md b/docs/reference/elasticsearch/mapping-reference/search-analyzer.md index e17ebd557f1d2..0ebf7b5d7b8ba 100644 --- a/docs/reference/elasticsearch/mapping-reference/search-analyzer.md +++ b/docs/reference/elasticsearch/mapping-reference/search-analyzer.md @@ -7,7 +7,7 @@ mapped_pages: Usually, the same [analyzer](/reference/elasticsearch/mapping-reference/analyzer.md) should be applied at index time and at search time, to ensure that the terms in the query are in the same format as the terms in the inverted index. -Sometimes, though, it can make sense to use a different analyzer at search time, such as when using the [`edge_ngram`](/reference/data-analysis/text-analysis/analysis-edgengram-tokenizer.md) tokenizer for autocomplete or when using search-time synonyms. +Sometimes, though, it can make sense to use a different analyzer at search time, such as when using the [`edge_ngram`](/reference/text-analysis/analysis-edgengram-tokenizer.md) tokenizer for autocomplete or when using search-time synonyms. By default, queries will use the `analyzer` defined in the field mapping, but this can be overridden with the `search_analyzer` setting: diff --git a/docs/reference/elasticsearch/mapping-reference/search-as-you-type.md b/docs/reference/elasticsearch/mapping-reference/search-as-you-type.md index f389e3f8afb6c..1b29c48d2512d 100644 --- a/docs/reference/elasticsearch/mapping-reference/search-as-you-type.md +++ b/docs/reference/elasticsearch/mapping-reference/search-as-you-type.md @@ -146,7 +146,7 @@ More subfields enables more specific queries but increases index size. The following parameters are accepted in a mapping for the `search_as_you_type` field due to its nature as a text-like field, and behave similarly to their behavior when configuring a field of the [`text`](/reference/elasticsearch/mapping-reference/text.md) data type. Unless otherwise noted, these options configure the root fields subfields in the same way. [`analyzer`](/reference/elasticsearch/mapping-reference/analyzer.md) -: The [analyzer](docs-content://manage-data/data-store/text-analysis.md) which should be used for `text` fields, both at index-time and at search-time (unless overridden by the [`search_analyzer`](/reference/elasticsearch/mapping-reference/search-analyzer.md)). Defaults to the default index analyzer, or the [`standard` analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md). +: The [analyzer](docs-content://manage-data/data-store/text-analysis.md) which should be used for `text` fields, both at index-time and at search-time (unless overridden by the [`search_analyzer`](/reference/elasticsearch/mapping-reference/search-analyzer.md)). Defaults to the default index analyzer, or the [`standard` analyzer](/reference/text-analysis/analysis-standard-analyzer.md). [`index`](/reference/elasticsearch/mapping-reference/mapping-index.md) : Should the field be searchable? Accepts `true` (default) or `false`. diff --git a/docs/reference/elasticsearch/mapping-reference/semantic-text.md b/docs/reference/elasticsearch/mapping-reference/semantic-text.md index 8ca6a19c0d6af..91adc9de7edee 100644 --- a/docs/reference/elasticsearch/mapping-reference/semantic-text.md +++ b/docs/reference/elasticsearch/mapping-reference/semantic-text.md @@ -159,7 +159,7 @@ PUT test-index `semantic_text` uses defaults for indexing data based on the {{infer}} endpoint specified. It enables you to quickstart your semantic search by providing automatic {{infer}} and a dedicated query so you don’t need to provide further details. -In case you want to customize data indexing, use the [`sparse_vector`](/reference/elasticsearch/mapping-reference/sparse-vector.md) or [`dense_vector`](/reference/elasticsearch/mapping-reference/dense-vector.md) field types and create an ingest pipeline with an [{{infer}} processor](/reference/ingestion-tools/enrich-processor/inference-processor.md) to generate the embeddings. [This tutorial](docs-content://solutions/search/semantic-search/semantic-search-inference.md) walks you through the process. In these cases - when you use `sparse_vector` or `dense_vector` field types instead of the `semantic_text` field type to customize indexing - using the [`semantic_query`](/reference/query-languages/query-dsl/query-dsl-semantic-query.md) is not supported for querying the field data. +In case you want to customize data indexing, use the [`sparse_vector`](/reference/elasticsearch/mapping-reference/sparse-vector.md) or [`dense_vector`](/reference/elasticsearch/mapping-reference/dense-vector.md) field types and create an ingest pipeline with an [{{infer}} processor](/reference/enrich-processor/inference-processor.md) to generate the embeddings. [This tutorial](docs-content://solutions/search/semantic-search/semantic-search-inference.md) walks you through the process. In these cases - when you use `sparse_vector` or `dense_vector` field types instead of the `semantic_text` field type to customize indexing - using the [`semantic_query`](/reference/query-languages/query-dsl/query-dsl-semantic-query.md) is not supported for querying the field data. ## Updates to `semantic_text` fields [update-script] diff --git a/docs/reference/elasticsearch/mapping-reference/text.md b/docs/reference/elasticsearch/mapping-reference/text.md index f2cbca678c86c..7295f2233d777 100644 --- a/docs/reference/elasticsearch/mapping-reference/text.md +++ b/docs/reference/elasticsearch/mapping-reference/text.md @@ -15,7 +15,7 @@ The text family includes the following field types: ## Text field type [text-field-type] -A field to index full-text values, such as the body of an email or the description of a product. These fields are `analyzed`, that is they are passed through an [analyzer](docs-content://manage-data/data-store/text-analysis.md) to convert the string into a list of individual terms before being indexed. The analysis process allows Elasticsearch to search for individual words *within* each full text field. Text fields are not used for sorting and seldom used for aggregations (although the [significant text aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-significanttext-aggregation.md) is a notable exception). +A field to index full-text values, such as the body of an email or the description of a product. These fields are `analyzed`, that is they are passed through an [analyzer](docs-content://manage-data/data-store/text-analysis.md) to convert the string into a list of individual terms before being indexed. The analysis process allows Elasticsearch to search for individual words *within* each full text field. Text fields are not used for sorting and seldom used for aggregations (although the [significant text aggregation](/reference/aggregations/search-aggregations-bucket-significanttext-aggregation.md) is a notable exception). `text` fields are best suited for unstructured but human-readable content. If you need to index unstructured machine-generated content, see [Mapping unstructured content](/reference/elasticsearch/mapping-reference/keyword.md#mapping-unstructured-content). @@ -46,7 +46,7 @@ Sometimes it is useful to have both a full text (`text`) and a keyword (`keyword The following parameters are accepted by `text` fields: [`analyzer`](/reference/elasticsearch/mapping-reference/analyzer.md) -: The [analyzer](docs-content://manage-data/data-store/text-analysis.md) which should be used for the `text` field, both at index-time and at search-time (unless overridden by the [`search_analyzer`](/reference/elasticsearch/mapping-reference/search-analyzer.md)). Defaults to the default index analyzer, or the [`standard` analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md). +: The [analyzer](docs-content://manage-data/data-store/text-analysis.md) which should be used for the `text` field, both at index-time and at search-time (unless overridden by the [`search_analyzer`](/reference/elasticsearch/mapping-reference/search-analyzer.md)). Defaults to the default index analyzer, or the [`standard` analyzer](/reference/text-analysis/analysis-standard-analyzer.md). [`eager_global_ordinals`](/reference/elasticsearch/mapping-reference/eager-global-ordinals.md) : Should global ordinals be loaded eagerly on refresh? Accepts `true` or `false` (default). Enabling this is a good idea on fields that are frequently used for (significant) terms aggregations. @@ -299,7 +299,7 @@ PUT my-index-000001 A variant of [`text`](#text-field-type) that trades scoring and efficiency of positional queries for space efficiency. This field effectively stores data the same way as a `text` field that only indexes documents (`index_options: docs`) and disables norms (`norms: false`). Term queries perform as fast if not faster as on `text` fields, however queries that need positions such as the [`match_phrase` query](/reference/query-languages/query-dsl/query-dsl-match-query-phrase.md) perform slower as they need to look at the `_source` document to verify whether a phrase matches. All queries return constant scores that are equal to 1.0. -Analysis is not configurable: text is always analyzed with the [default analyzer](docs-content://manage-data/data-store/text-analysis/specify-an-analyzer.md#specify-index-time-default-analyzer) ([`standard`](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md) by default). +Analysis is not configurable: text is always analyzed with the [default analyzer](docs-content://manage-data/data-store/text-analysis/specify-an-analyzer.md#specify-index-time-default-analyzer) ([`standard`](/reference/text-analysis/analysis-standard-analyzer.md) by default). [span queries](/reference/query-languages/query-dsl/span-queries.md) are not supported with this field, use [interval queries](/reference/query-languages/query-dsl/query-dsl-intervals-query.md) instead, or the [`text`](#text-field-type) field type if you absolutely need span queries. diff --git a/docs/reference/elasticsearch/mapping-reference/token-count.md b/docs/reference/elasticsearch/mapping-reference/token-count.md index 4c0f720ca9a5d..b4c357aef2b62 100644 --- a/docs/reference/elasticsearch/mapping-reference/token-count.md +++ b/docs/reference/elasticsearch/mapping-reference/token-count.md @@ -58,7 +58,7 @@ The following parameters are accepted by `token_count` fields: : The [analyzer](docs-content://manage-data/data-store/text-analysis.md) which should be used to analyze the string value. Required. For best performance, use an analyzer without token filters. `enable_position_increments` -: Indicates if position increments should be counted. Set to `false` if you don’t want to count tokens removed by analyzer filters (like [`stop`](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md)). Defaults to `true`. +: Indicates if position increments should be counted. Set to `false` if you don’t want to count tokens removed by analyzer filters (like [`stop`](/reference/text-analysis/analysis-stop-tokenfilter.md)). Defaults to `true`. [`doc_values`](/reference/elasticsearch/mapping-reference/doc-values.md) : Should the field be stored on disk in a column-stride fashion, so that it can later be used for sorting, aggregations, or scripting? Accepts `true` (default) or `false`. diff --git a/docs/reference/elasticsearch/rest-apis/common-options.md b/docs/reference/elasticsearch/rest-apis/common-options.md index 10bf42291ea7f..b51918052fee3 100644 --- a/docs/reference/elasticsearch/rest-apis/common-options.md +++ b/docs/reference/elasticsearch/rest-apis/common-options.md @@ -23,7 +23,7 @@ Statistics are returned in a format suitable for humans (e.g. `"exists_time": "1 ## Date Math [date-math] -Most parameters which accept a formatted date value — such as `gt` and `lt` in [`range` queries](/reference/query-languages/query-dsl/query-dsl-range-query.md), or `from` and `to` in [`daterange` aggregations](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md) — understand date maths. +Most parameters which accept a formatted date value — such as `gt` and `lt` in [`range` queries](/reference/query-languages/query-dsl/query-dsl-range-query.md), or `from` and `to` in [`daterange` aggregations](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md) — understand date maths. The expression starts with an anchor date, which can either be `now`, or a date string ending with `||`. This anchor date can optionally be followed by one or more maths expressions: diff --git a/docs/reference/elasticsearch/rest-apis/filter-search-results.md b/docs/reference/elasticsearch/rest-apis/filter-search-results.md index 2d5adeb87696e..5d5f32e9ee494 100644 --- a/docs/reference/elasticsearch/rest-apis/filter-search-results.md +++ b/docs/reference/elasticsearch/rest-apis/filter-search-results.md @@ -9,7 +9,7 @@ applies_to: You can use two methods to filter search results: -* Use a boolean query with a `filter` clause. Search requests apply [boolean filters](/reference/query-languages/query-dsl/query-dsl-bool-query.md) to both search hits and [aggregations](/reference/data-analysis/aggregations/index.md). +* Use a boolean query with a `filter` clause. Search requests apply [boolean filters](/reference/query-languages/query-dsl/query-dsl-bool-query.md) to both search hits and [aggregations](/reference/aggregations/index.md). * Use the search API’s `post_filter` parameter. Search requests apply [post filters](#post-filter) only to search hits, not aggregations. You can use a post filter to calculate aggregations based on a broader result set, and then further narrow the results. You can also [rescore](#rescore) hits after the post filter to improve relevance and reorder results. @@ -62,7 +62,7 @@ GET /shirts/_search However, you would also like to use *faceted navigation* to display a list of other options that the user could click on. Perhaps you have a `model` field that would allow the user to limit their search results to red Gucci `t-shirts` or `dress-shirts`. -This can be done with a [`terms` aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md): +This can be done with a [`terms` aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md): ```console GET /shirts/_search diff --git a/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion.md b/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion.md index 034dc76616ee8..d3e4e50d53e06 100644 --- a/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion.md +++ b/docs/reference/elasticsearch/rest-apis/reciprocal-rank-fusion.md @@ -103,7 +103,7 @@ Note that if `k` from a knn search is larger than `rank_window_size`, the result The `rrf` retriever supports: -* [aggregations](/reference/data-analysis/aggregations/index.md) +* [aggregations](/reference/aggregations/index.md) * [from](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-search#search-from-param) * [suggesters](/reference/elasticsearch/rest-apis/search-suggesters.md) * [highlighting](/reference/elasticsearch/rest-apis/highlighting.md) diff --git a/docs/reference/elasticsearch/rest-apis/retrievers.md b/docs/reference/elasticsearch/rest-apis/retrievers.md index c65420a179562..6a5c27a781a4b 100644 --- a/docs/reference/elasticsearch/rest-apis/retrievers.md +++ b/docs/reference/elasticsearch/rest-apis/retrievers.md @@ -929,7 +929,7 @@ The [`from`](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operati ### Using aggregations with a retriever tree [retriever-aggregations] -[Aggregations](/reference/data-analysis/aggregations/index.md) are globally specified as part of a search request. The query used for an aggregation is the combination of all leaf retrievers as `should` clauses in a [boolean query](/reference/query-languages/query-dsl/query-dsl-bool-query.md). +[Aggregations](/reference/aggregations/index.md) are globally specified as part of a search request. The query used for an aggregation is the combination of all leaf retrievers as `should` clauses in a [boolean query](/reference/query-languages/query-dsl/query-dsl-bool-query.md). ### Restrictions on search parameters when specifying a retriever [retriever-restrictions] diff --git a/docs/reference/elasticsearch/toc.yml b/docs/reference/elasticsearch/toc.yml new file mode 100644 index 0000000000000..2dd692fca8695 --- /dev/null +++ b/docs/reference/elasticsearch/toc.yml @@ -0,0 +1,195 @@ +toc: + - file: index.md + - file: configuration-reference/index.md + children: + - file: configuration-reference/circuit-breaker-settings.md + - file: configuration-reference/auding-settings.md + - file: configuration-reference/enrich-settings.md + - file: configuration-reference/cluster-level-shard-allocation-routing-settings.md + - file: configuration-reference/miscellaneous-cluster-settings.md + - file: configuration-reference/cross-cluster-replication-settings.md + - file: configuration-reference/discovery-cluster-formation-settings.md + - file: configuration-reference/field-data-cache-settings.md + - file: configuration-reference/health-diagnostic-settings.md + - file: configuration-reference/index-lifecycle-management-settings.md + - file: configuration-reference/data-stream-lifecycle-settings.md + - file: configuration-reference/index-management-settings.md + - file: configuration-reference/index-recovery-settings.md + - file: configuration-reference/indexing-buffer-settings.md + - file: configuration-reference/license-settings.md + - file: configuration-reference/local-gateway.md + - file: configuration-reference/machine-learning-settings.md + - file: configuration-reference/inference-settings.md + - file: configuration-reference/monitoring-settings.md + - file: configuration-reference/node-settings.md + - file: configuration-reference/networking-settings.md + - file: configuration-reference/node-query-cache-settings.md + - file: configuration-reference/search-settings.md + - file: configuration-reference/security-settings.md + - file: configuration-reference/shard-request-cache-settings.md + - file: configuration-reference/snapshot-restore-settings.md + - file: configuration-reference/transforms-settings.md + - file: configuration-reference/thread-pool-settings.md + - file: configuration-reference/watcher-settings.md + - file: jvm-settings.md + - file: roles.md + - file: security-privileges.md + - file: index-settings/index.md + children: + - file: index-settings/data-tier-allocation.md + - file: index-settings/index-modules.md + - file: index-settings/history-retention.md + - file: index-settings/index-block.md + - file: index-settings/recovery-prioritization.md + - file: index-settings/pressure.md + - file: index-settings/mapping-limit.md + - file: index-settings/merge.md + - file: index-settings/path.md + - file: index-settings/shard-allocation.md + children: + - file: index-settings/total-shards-per-node.md + - file: index-settings/similarity.md + - file: index-settings/slow-log.md + - file: index-settings/sorting.md + children: + - file: index-settings/sorting-conjunctions.md + - file: index-settings/store.md + children: + - file: index-settings/preloading-data-into-file-system-cache.md + - file: index-settings/time-series.md + - file: index-settings/translog.md + - file: index-lifecycle-actions/index.md + children: + - file: index-lifecycle-actions/index.md + - file: index-lifecycle-actions/ilm-allocate.md + - file: index-lifecycle-actions/ilm-delete.md + - file: index-lifecycle-actions/ilm-forcemerge.md + - file: index-lifecycle-actions/ilm-migrate.md + - file: index-lifecycle-actions/ilm-readonly.md + - file: index-lifecycle-actions/ilm-rollover.md + - file: index-lifecycle-actions/ilm-downsample.md + - file: index-lifecycle-actions/ilm-searchable-snapshot.md + - file: index-lifecycle-actions/ilm-set-priority.md + - file: index-lifecycle-actions/ilm-shrink.md + - file: index-lifecycle-actions/ilm-unfollow.md + - file: index-lifecycle-actions/ilm-wait-for-snapshot.md + - file: rest-apis/index.md + children: + - file: rest-apis/api-conventions.md + - file: rest-apis/common-options.md + - file: rest-apis/compatibility.md + - file: rest-apis/api-examples.md + children: + - file: rest-apis/refresh-parameter.md + - file: rest-apis/optimistic-concurrency-control.md + - file: rest-apis/sort-search-results.md + - file: rest-apis/paginate-search-results.md + - file: rest-apis/retrieve-selected-fields.md + - file: rest-apis/search-multiple-data-streams-indices.md + - file: rest-apis/collapse-search-results.md + - file: rest-apis/filter-search-results.md + - file: rest-apis/highlighting.md + - file: rest-apis/retrieve-inner-hits.md + - file: rest-apis/search-shard-routing.md + - file: rest-apis/searching-with-query-rules.md + - file: rest-apis/reciprocal-rank-fusion.md + - file: rest-apis/retrievers.md + - file: rest-apis/reindex-data-stream.md + - file: rest-apis/create-index-from-source.md + - file: rest-apis/shard-request-cache.md + - file: rest-apis/search-suggesters.md + - file: mapping-reference/index.md + children: + - file: mapping-reference/document-metadata-fields.md + children: + - file: mapping-reference/mapping-doc-count-field.md + - file: mapping-reference/mapping-field-names-field.md + - file: mapping-reference/mapping-ignored-field.md + - file: mapping-reference/mapping-id-field.md + - file: mapping-reference/mapping-index-field.md + - file: mapping-reference/mapping-meta-field.md + - file: mapping-reference/mapping-routing-field.md + - file: mapping-reference/mapping-source-field.md + - file: mapping-reference/mapping-tier-field.md + - file: mapping-reference/field-data-types.md + children: + - file: mapping-reference/aggregate-metric-double.md + - file: mapping-reference/field-alias.md + - file: mapping-reference/array.md + - file: mapping-reference/binary.md + - file: mapping-reference/boolean.md + - file: mapping-reference/completion.md + - file: mapping-reference/date.md + - file: mapping-reference/date_nanos.md + - file: mapping-reference/dense-vector.md + - file: mapping-reference/flattened.md + - file: mapping-reference/geo-point.md + - file: mapping-reference/geo-shape.md + - file: mapping-reference/histogram.md + - file: mapping-reference/ip.md + - file: mapping-reference/parent-join.md + - file: mapping-reference/keyword.md + - file: mapping-reference/nested.md + - file: mapping-reference/number.md + - file: mapping-reference/object.md + - file: mapping-reference/passthrough.md + - file: mapping-reference/percolator.md + - file: mapping-reference/point.md + - file: mapping-reference/range.md + - file: mapping-reference/rank-feature.md + - file: mapping-reference/rank-features.md + - file: mapping-reference/rank-vectors.md + - file: mapping-reference/search-as-you-type.md + - file: mapping-reference/semantic-text.md + - file: mapping-reference/shape.md + - file: mapping-reference/sparse-vector.md + - file: mapping-reference/text.md + - file: mapping-reference/token-count.md + - file: mapping-reference/unsigned-long.md + - file: mapping-reference/version.md + - file: mapping-reference/mapping-parameters.md + children: + - file: mapping-reference/analyzer.md + - file: mapping-reference/coerce.md + - file: mapping-reference/copy-to.md + - file: mapping-reference/doc-values.md + - file: mapping-reference/dynamic.md + - file: mapping-reference/eager-global-ordinals.md + - file: mapping-reference/enabled.md + - file: mapping-reference/mapping-date-format.md + - file: mapping-reference/ignore-above.md + - file: mapping-reference/index-mapping-ignore-above.md + - file: mapping-reference/ignore-malformed.md + - file: mapping-reference/mapping-index.md + - file: mapping-reference/index-options.md + - file: mapping-reference/index-phrases.md + - file: mapping-reference/index-prefixes.md + - file: mapping-reference/mapping-field-meta.md + - file: mapping-reference/multi-fields.md + - file: mapping-reference/normalizer.md + - file: mapping-reference/norms.md + - file: mapping-reference/null-value.md + - file: mapping-reference/position-increment-gap.md + - file: mapping-reference/properties.md + - file: mapping-reference/search-analyzer.md + - file: mapping-reference/similarity.md + - file: mapping-reference/mapping-store.md + - file: mapping-reference/subobjects.md + - file: mapping-reference/term-vector.md + - file: elasticsearch-audit-events.md + - file: command-line-tools/index.md + children: + - file: command-line-tools/certgen.md + - file: command-line-tools/certutil.md + - file: command-line-tools/create-enrollment-token.md + - file: command-line-tools/elasticsearch-croneval.md + - file: command-line-tools/elasticsearch-keystore.md + - file: command-line-tools/node-tool.md + - file: command-line-tools/reconfigure-node.md + - file: command-line-tools/reset-password.md + - file: command-line-tools/saml-metadata.md + - file: command-line-tools/service-tokens-command.md + - file: command-line-tools/setup-passwords.md + - file: command-line-tools/shard-tool.md + - file: command-line-tools/syskeygen.md + - file: command-line-tools/users-command.md \ No newline at end of file diff --git a/docs/reference/ingestion-tools/enrich-processor/append-processor.md b/docs/reference/enrich-processor/append-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/append-processor.md rename to docs/reference/enrich-processor/append-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/attachment.md b/docs/reference/enrich-processor/attachment.md similarity index 98% rename from docs/reference/ingestion-tools/enrich-processor/attachment.md rename to docs/reference/enrich-processor/attachment.md index 9826b461f28e5..78cda99587401 100644 --- a/docs/reference/ingestion-tools/enrich-processor/attachment.md +++ b/docs/reference/enrich-processor/attachment.md @@ -329,7 +329,7 @@ Returns this: ## Using the attachment processor with arrays [attachment-with-arrays] -To use the attachment processor within an array of attachments the [foreach processor](/reference/ingestion-tools/enrich-processor/foreach-processor.md) is required. This enables the attachment processor to be run on the individual elements of the array. +To use the attachment processor within an array of attachments the [foreach processor](/reference/enrich-processor/foreach-processor.md) is required. This enables the attachment processor to be run on the individual elements of the array. For example, given the following source: diff --git a/docs/reference/ingestion-tools/enrich-processor/bytes-processor.md b/docs/reference/enrich-processor/bytes-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/bytes-processor.md rename to docs/reference/enrich-processor/bytes-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/community-id-processor.md b/docs/reference/enrich-processor/community-id-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/community-id-processor.md rename to docs/reference/enrich-processor/community-id-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/convert-processor.md b/docs/reference/enrich-processor/convert-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/convert-processor.md rename to docs/reference/enrich-processor/convert-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/csv-processor.md b/docs/reference/enrich-processor/csv-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/csv-processor.md rename to docs/reference/enrich-processor/csv-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/date-index-name-processor.md b/docs/reference/enrich-processor/date-index-name-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/date-index-name-processor.md rename to docs/reference/enrich-processor/date-index-name-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/date-processor.md b/docs/reference/enrich-processor/date-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/date-processor.md rename to docs/reference/enrich-processor/date-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/dissect-processor.md b/docs/reference/enrich-processor/dissect-processor.md similarity index 92% rename from docs/reference/ingestion-tools/enrich-processor/dissect-processor.md rename to docs/reference/enrich-processor/dissect-processor.md index 51bed2db88726..6d2c5723db1ab 100644 --- a/docs/reference/ingestion-tools/enrich-processor/dissect-processor.md +++ b/docs/reference/enrich-processor/dissect-processor.md @@ -7,7 +7,7 @@ mapped_pages: # Dissect processor [dissect-processor] -Similar to the [Grok Processor](/reference/ingestion-tools/enrich-processor/grok-processor.md), dissect also extracts structured fields out of a single text field within a document. However unlike the [Grok Processor](/reference/ingestion-tools/enrich-processor/grok-processor.md), dissect does not use [Regular Expressions](https://en.wikipedia.org/wiki/Regular_expression). This allows dissect’s syntax to be simple and for some cases faster than the [Grok Processor](/reference/ingestion-tools/enrich-processor/grok-processor.md). +Similar to the [Grok Processor](/reference/enrich-processor/grok-processor.md), dissect also extracts structured fields out of a single text field within a document. However unlike the [Grok Processor](/reference/enrich-processor/grok-processor.md), dissect does not use [Regular Expressions](https://en.wikipedia.org/wiki/Regular_expression). This allows dissect’s syntax to be simple and for some cases faster than the [Grok Processor](/reference/enrich-processor/grok-processor.md). Dissect matches a single text field against a defined pattern. @@ -46,7 +46,7 @@ and result in a document with the following fields: A dissect pattern is defined by the parts of the string that will be discarded. In the previous example, the first part to be discarded is a single space. Dissect finds this space, then assigns the value of `clientip` everything up until that space. Next, dissect matches the `[` and then `]` and then assigns `@timestamp` to everything in-between `[` and `]`. Paying special attention to the parts of the string to discard will help build successful dissect patterns. -Successful matches require all keys in a pattern to have a value. If any of the `%{{keyname}}` defined in the pattern do not have a value, then an exception is thrown and may be handled by the [`on_failure`](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#handling-pipeline-failures) directive. An empty key `%{}` or a [named skip key](#dissect-modifier-named-skip-key) can be used to match values, but exclude the value from the final document. All matched values are represented as string data types. The [convert processor](/reference/ingestion-tools/enrich-processor/convert-processor.md) may be used to convert to expected data type. +Successful matches require all keys in a pattern to have a value. If any of the `%{{keyname}}` defined in the pattern do not have a value, then an exception is thrown and may be handled by the [`on_failure`](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#handling-pipeline-failures) directive. An empty key `%{}` or a [named skip key](#dissect-modifier-named-skip-key) can be used to match values, but exclude the value from the final document. All matched values are represented as string data types. The [convert processor](/reference/enrich-processor/convert-processor.md) may be used to convert to expected data type. Dissect also supports [key modifiers](#dissect-key-modifiers) that can change dissect’s default behavior. For example you can instruct dissect to ignore certain fields, append fields, skip over padding, etc. See [below](#dissect-key-modifiers) for more information. diff --git a/docs/reference/ingestion-tools/enrich-processor/dot-expand-processor.md b/docs/reference/enrich-processor/dot-expand-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/dot-expand-processor.md rename to docs/reference/enrich-processor/dot-expand-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/drop-processor.md b/docs/reference/enrich-processor/drop-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/drop-processor.md rename to docs/reference/enrich-processor/drop-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/enrich-processor.md b/docs/reference/enrich-processor/enrich-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/enrich-processor.md rename to docs/reference/enrich-processor/enrich-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/fail-processor.md b/docs/reference/enrich-processor/fail-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/fail-processor.md rename to docs/reference/enrich-processor/fail-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/fingerprint-processor.md b/docs/reference/enrich-processor/fingerprint-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/fingerprint-processor.md rename to docs/reference/enrich-processor/fingerprint-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/foreach-processor.md b/docs/reference/enrich-processor/foreach-processor.md similarity index 98% rename from docs/reference/ingestion-tools/enrich-processor/foreach-processor.md rename to docs/reference/enrich-processor/foreach-processor.md index a1d6e0a63bc85..43bba4e4bd10f 100644 --- a/docs/reference/ingestion-tools/enrich-processor/foreach-processor.md +++ b/docs/reference/enrich-processor/foreach-processor.md @@ -134,7 +134,7 @@ After processing the result is: } ``` -For another array of objects example, refer to the [attachment processor documentation](/reference/ingestion-tools/enrich-processor/attachment.md#attachment-with-arrays). +For another array of objects example, refer to the [attachment processor documentation](/reference/enrich-processor/attachment.md#attachment-with-arrays). ### Object [foreach-object-ex] diff --git a/docs/reference/ingestion-tools/enrich-processor/geoip-processor.md b/docs/reference/enrich-processor/geoip-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/geoip-processor.md rename to docs/reference/enrich-processor/geoip-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/grok-processor.md b/docs/reference/enrich-processor/grok-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/grok-processor.md rename to docs/reference/enrich-processor/grok-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/gsub-processor.md b/docs/reference/enrich-processor/gsub-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/gsub-processor.md rename to docs/reference/enrich-processor/gsub-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/htmlstrip-processor.md b/docs/reference/enrich-processor/htmlstrip-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/htmlstrip-processor.md rename to docs/reference/enrich-processor/htmlstrip-processor.md diff --git a/docs/images/error_distance.png b/docs/reference/enrich-processor/images/error_distance.png similarity index 100% rename from docs/images/error_distance.png rename to docs/reference/enrich-processor/images/error_distance.png diff --git a/docs/images/geogrid_h3.png b/docs/reference/enrich-processor/images/geogrid_h3.png similarity index 100% rename from docs/images/geogrid_h3.png rename to docs/reference/enrich-processor/images/geogrid_h3.png diff --git a/docs/images/geogrid_h3_children.png b/docs/reference/enrich-processor/images/geogrid_h3_children.png similarity index 100% rename from docs/images/geogrid_h3_children.png rename to docs/reference/enrich-processor/images/geogrid_h3_children.png diff --git a/docs/images/geogrid_tile.png b/docs/reference/enrich-processor/images/geogrid_tile.png similarity index 100% rename from docs/images/geogrid_tile.png rename to docs/reference/enrich-processor/images/geogrid_tile.png diff --git a/docs/reference/ingestion-tools/enrich-processor/index.md b/docs/reference/enrich-processor/index.md similarity index 61% rename from docs/reference/ingestion-tools/enrich-processor/index.md rename to docs/reference/enrich-processor/index.md index 29f8b4a4f40d4..eb6ad0c09e6a7 100644 --- a/docs/reference/ingestion-tools/enrich-processor/index.md +++ b/docs/reference/enrich-processor/index.md @@ -39,13 +39,13 @@ We’ve categorized the available processors on this page and summarized their f ### General outcomes [ingest-process-category-data-enrichment-general] -[`append` processor](/reference/ingestion-tools/enrich-processor/append-processor.md) +[`append` processor](/reference/enrich-processor/append-processor.md) : Appends a value to a field. -[`date_index_name` processor](/reference/ingestion-tools/enrich-processor/date-index-name-processor.md) +[`date_index_name` processor](/reference/enrich-processor/date-index-name-processor.md) : Points documents to the right time-based index based on a date or timestamp field. -[`enrich` processor](/reference/ingestion-tools/enrich-processor/enrich-processor.md) +[`enrich` processor](/reference/enrich-processor/enrich-processor.md) : Enriches documents with data from another index. ::::{tip} @@ -54,49 +54,49 @@ Refer to [Enrich your data](docs-content://manage-data/ingest/transform-enrich/d :::: -[`inference` processor](/reference/ingestion-tools/enrich-processor/inference-processor.md) +[`inference` processor](/reference/enrich-processor/inference-processor.md) : Uses {{ml}} to classify and tag text fields. ### Specific outcomes [ingest-process-category-data-enrichment-specific] -[`attachment` processor](/reference/ingestion-tools/enrich-processor/attachment.md) +[`attachment` processor](/reference/enrich-processor/attachment.md) : Parses and indexes binary data, such as PDFs and Word documents. -[`circle` processor](/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md) +[`circle` processor](/reference/enrich-processor/ingest-circle-processor.md) : Converts a location field to a Geo-Point field. -[`community_id` processor](/reference/ingestion-tools/enrich-processor/community-id-processor.md) +[`community_id` processor](/reference/enrich-processor/community-id-processor.md) : Computes the Community ID for network flow data. -[`fingerprint` processor](/reference/ingestion-tools/enrich-processor/fingerprint-processor.md) +[`fingerprint` processor](/reference/enrich-processor/fingerprint-processor.md) : Computes a hash of the document’s content. -[`geo_grid` processor](/reference/ingestion-tools/enrich-processor/ingest-geo-grid-processor.md) +[`geo_grid` processor](/reference/enrich-processor/ingest-geo-grid-processor.md) : Converts geo-grid definitions of grid tiles or cells to regular bounding boxes or polygons which describe their shape. -[`geoip` processor](/reference/ingestion-tools/enrich-processor/geoip-processor.md) +[`geoip` processor](/reference/enrich-processor/geoip-processor.md) : Adds information about the geographical location of an IPv4 or IPv6 address from a Maxmind database. -[`ip_location` processor](/reference/ingestion-tools/enrich-processor/ip-location-processor.md) +[`ip_location` processor](/reference/enrich-processor/ip-location-processor.md) : Adds information about the geographical location of an IPv4 or IPv6 address from an ip geolocation database. -[`network_direction` processor](/reference/ingestion-tools/enrich-processor/network-direction-processor.md) +[`network_direction` processor](/reference/enrich-processor/network-direction-processor.md) : Calculates the network direction given a source IP address, destination IP address, and a list of internal networks. -[`registered_domain` processor](/reference/ingestion-tools/enrich-processor/registered-domain-processor.md) +[`registered_domain` processor](/reference/enrich-processor/registered-domain-processor.md) : Extracts the registered domain (also known as the effective top-level domain or eTLD), sub-domain, and top-level domain from a fully qualified domain name (FQDN). -[`set_security_user` processor](/reference/ingestion-tools/enrich-processor/ingest-node-set-security-user-processor.md) +[`set_security_user` processor](/reference/enrich-processor/ingest-node-set-security-user-processor.md) : Sets user-related details (such as `username`, `roles`, `email`, `full_name`,`metadata`, `api_key`, `realm` and `authentication_type`) from the current authenticated user to the current document by pre-processing the ingest. -[`uri_parts` processor](/reference/ingestion-tools/enrich-processor/uri-parts-processor.md) +[`uri_parts` processor](/reference/enrich-processor/uri-parts-processor.md) : Parses a Uniform Resource Identifier (URI) string and extracts its components as an object. -[`urldecode` processor](/reference/ingestion-tools/enrich-processor/urldecode-processor.md) +[`urldecode` processor](/reference/enrich-processor/urldecode-processor.md) : URL-decodes a string. -[`user_agent` processor](/reference/ingestion-tools/enrich-processor/user-agent-processor.md) +[`user_agent` processor](/reference/enrich-processor/user-agent-processor.md) : Parses user-agent strings to extract information about web clients. @@ -105,103 +105,103 @@ Refer to [Enrich your data](docs-content://manage-data/ingest/transform-enrich/d ### General outcomes [ingest-process-category-data-transformation-general] -[`convert` processor](/reference/ingestion-tools/enrich-processor/convert-processor.md) +[`convert` processor](/reference/enrich-processor/convert-processor.md) : Converts a field in the currently ingested document to a different type, such as converting a string to an integer. -[`dissect` processor](/reference/ingestion-tools/enrich-processor/dissect-processor.md) -: Extracts structured fields out of a single text field within a document. Unlike the [grok processor](/reference/ingestion-tools/enrich-processor/grok-processor.md), dissect does not use regular expressions. This makes the dissect’s a simpler and often faster alternative. +[`dissect` processor](/reference/enrich-processor/dissect-processor.md) +: Extracts structured fields out of a single text field within a document. Unlike the [grok processor](/reference/enrich-processor/grok-processor.md), dissect does not use regular expressions. This makes the dissect’s a simpler and often faster alternative. -[`grok` processor](/reference/ingestion-tools/enrich-processor/grok-processor.md) +[`grok` processor](/reference/enrich-processor/grok-processor.md) : Extracts structured fields out of a single text field within a document, using the [Grok](docs-content://explore-analyze/scripting/grok.md) regular expression dialect that supports reusable aliased expressions. -[`gsub` processor](/reference/ingestion-tools/enrich-processor/gsub-processor.md) +[`gsub` processor](/reference/enrich-processor/gsub-processor.md) : Converts a string field by applying a regular expression and a replacement. -[`redact` processor](/reference/ingestion-tools/enrich-processor/redact-processor.md) +[`redact` processor](/reference/enrich-processor/redact-processor.md) : Uses the [Grok](docs-content://explore-analyze/scripting/grok.md) rules engine to obscure text in the input document matching the given Grok patterns. -[`rename` processor](/reference/ingestion-tools/enrich-processor/rename-processor.md) +[`rename` processor](/reference/enrich-processor/rename-processor.md) : Renames an existing field. -[`set` processor](/reference/ingestion-tools/enrich-processor/set-processor.md) +[`set` processor](/reference/enrich-processor/set-processor.md) : Sets a value on a field. ### Specific outcomes [ingest-process-category-data-transformation-specific] -[`bytes` processor](/reference/ingestion-tools/enrich-processor/bytes-processor.md) +[`bytes` processor](/reference/enrich-processor/bytes-processor.md) : Converts a human-readable byte value to its value in bytes (for example `1kb` becomes `1024`). -[`csv` processor](/reference/ingestion-tools/enrich-processor/csv-processor.md) +[`csv` processor](/reference/enrich-processor/csv-processor.md) : Extracts a single line of CSV data from a text field. -[`date` processor](/reference/ingestion-tools/enrich-processor/date-processor.md) +[`date` processor](/reference/enrich-processor/date-processor.md) : Extracts and converts date fields. -[`dot_expand`](/reference/ingestion-tools/enrich-processor/dot-expand-processor.md) processor +[`dot_expand`](/reference/enrich-processor/dot-expand-processor.md) processor : Expands a field with dots into an object field. -[`html_strip` processor](/reference/ingestion-tools/enrich-processor/htmlstrip-processor.md) +[`html_strip` processor](/reference/enrich-processor/htmlstrip-processor.md) : Removes HTML tags from a field. -[`join` processor](/reference/ingestion-tools/enrich-processor/join-processor.md) +[`join` processor](/reference/enrich-processor/join-processor.md) : Joins each element of an array into a single string using a separator character between each element. -[`kv` processor](/reference/ingestion-tools/enrich-processor/kv-processor.md) +[`kv` processor](/reference/enrich-processor/kv-processor.md) : Parse messages (or specific event fields) containing key-value pairs. -[`lowercase` processor](/reference/ingestion-tools/enrich-processor/lowercase-processor.md) and [`uppercase` processor](/reference/ingestion-tools/enrich-processor/uppercase-processor.md) +[`lowercase` processor](/reference/enrich-processor/lowercase-processor.md) and [`uppercase` processor](/reference/enrich-processor/uppercase-processor.md) : Converts a string field to lowercase or uppercase. -[`split` processor](/reference/ingestion-tools/enrich-processor/split-processor.md) +[`split` processor](/reference/enrich-processor/split-processor.md) : Splits a field into an array of values. -[`trim` processor](/reference/ingestion-tools/enrich-processor/trim-processor.md) +[`trim` processor](/reference/enrich-processor/trim-processor.md) : Trims whitespace from field. ## Data filtering processors [ingest-process-category-data-filtering] -[`drop` processor](/reference/ingestion-tools/enrich-processor/drop-processor.md) +[`drop` processor](/reference/enrich-processor/drop-processor.md) : Drops the document without raising any errors. -[`remove` processor](/reference/ingestion-tools/enrich-processor/remove-processor.md) +[`remove` processor](/reference/enrich-processor/remove-processor.md) : Removes fields from documents. ## Pipeline handling processors [ingest-process-category-pipeline-handling] -[`fail` processor](/reference/ingestion-tools/enrich-processor/fail-processor.md) +[`fail` processor](/reference/enrich-processor/fail-processor.md) : Raises an exception. Useful for when you expect a pipeline to fail and want to relay a specific message to the requester. -[`pipeline` processor](/reference/ingestion-tools/enrich-processor/pipeline-processor.md) +[`pipeline` processor](/reference/enrich-processor/pipeline-processor.md) : Executes another pipeline. -[`reroute` processor](/reference/ingestion-tools/enrich-processor/reroute-processor.md) +[`reroute` processor](/reference/enrich-processor/reroute-processor.md) : Reroutes documents to another target index or data stream. -[`terminate` processor](/reference/ingestion-tools/enrich-processor/terminate-processor.md) +[`terminate` processor](/reference/enrich-processor/terminate-processor.md) : Terminates the current ingest pipeline, causing no further processors to be run. ## Array/JSON handling processors [ingest-process-category-array-json-handling] -[`for_each` processor](/reference/ingestion-tools/enrich-processor/foreach-processor.md) +[`for_each` processor](/reference/enrich-processor/foreach-processor.md) : Runs an ingest processor on each element of an array or object. -[`json` processor](/reference/ingestion-tools/enrich-processor/json-processor.md) +[`json` processor](/reference/enrich-processor/json-processor.md) : Converts a JSON string into a structured JSON object. -[`script` processor](/reference/ingestion-tools/enrich-processor/script-processor.md) +[`script` processor](/reference/enrich-processor/script-processor.md) : Runs an inline or stored [script](docs-content://explore-analyze/scripting.md) on incoming documents. The script runs in the [painless `ingest` context](/reference/scripting-languages/painless/painless-ingest-processor-context.md). -[`sort` processor](/reference/ingestion-tools/enrich-processor/sort-processor.md) +[`sort` processor](/reference/enrich-processor/sort-processor.md) : Sorts the elements of an array in ascending or descending order. ## Add additional processors [ingest-process-plugins] -You can install additional processors as [plugins](../../elasticsearch-plugins/index.md). +You can install additional processors as [plugins](/reference/elasticsearch-plugins/index.md). You must install any plugin processors on all nodes in your cluster. Otherwise, {{es}} will fail to create pipelines containing the processor. diff --git a/docs/reference/ingestion-tools/enrich-processor/inference-processor.md b/docs/reference/enrich-processor/inference-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/inference-processor.md rename to docs/reference/enrich-processor/inference-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md b/docs/reference/enrich-processor/ingest-circle-processor.md similarity index 98% rename from docs/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md rename to docs/reference/enrich-processor/ingest-circle-processor.md index 79a7de3100704..ef13cc822cee9 100644 --- a/docs/reference/ingestion-tools/enrich-processor/ingest-circle-processor.md +++ b/docs/reference/enrich-processor/ingest-circle-processor.md @@ -24,7 +24,7 @@ $$$circle-processor-options$$$ | `on_failure` | no | - | Handle failures for the processor. See [Handling pipeline failures](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md#handling-pipeline-failures). | | `tag` | no | - | Identifier for the processor. Useful for debugging and metrics. | -![error distance](../../../images/error_distance.png "") +![error distance](images/error_distance.png "") ```console PUT circles diff --git a/docs/reference/ingestion-tools/enrich-processor/ingest-geo-grid-processor.md b/docs/reference/enrich-processor/ingest-geo-grid-processor.md similarity index 97% rename from docs/reference/ingestion-tools/enrich-processor/ingest-geo-grid-processor.md rename to docs/reference/enrich-processor/ingest-geo-grid-processor.md index 95556f5808310..f7f8407d455a1 100644 --- a/docs/reference/ingestion-tools/enrich-processor/ingest-geo-grid-processor.md +++ b/docs/reference/enrich-processor/ingest-geo-grid-processor.md @@ -107,7 +107,7 @@ The response shows how the ingest-processor has replaced the `geocell` field wit } ``` -![Kibana map with showing the geotile at 4/8/5 and its four child cells](../../../images/geogrid_tile.png "") +![Kibana map with showing the geotile at 4/8/5 and its four child cells](images/geogrid_tile.png "") ## Example: Hexagonal geohex with polygon in WKT format [_example_hexagonal_geohex_with_polygon_in_wkt_format] @@ -139,7 +139,7 @@ The response shows how the ingest-processor has replaced the `geocell` field wit } ``` -![Kibana map with showing an H3 cell](../../../images/geogrid_h3.png "") +![Kibana map with showing an H3 cell](images/geogrid_h3.png "") ## Example: Enriched tile details [_example_enriched_tile_details] @@ -217,6 +217,6 @@ The response from this index request: This additional information will then enable, for example, creating a visualization of the H3 cell, its children and its intersecting non-children cells. -![Kibana map with three H3 layers: cell](../../../images/geogrid_h3_children.png "") +![Kibana map with three H3 layers: cell](images/geogrid_h3_children.png "") diff --git a/docs/reference/ingestion-tools/enrich-processor/ingest-node-set-security-user-processor.md b/docs/reference/enrich-processor/ingest-node-set-security-user-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/ingest-node-set-security-user-processor.md rename to docs/reference/enrich-processor/ingest-node-set-security-user-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/ip-location-processor.md b/docs/reference/enrich-processor/ip-location-processor.md similarity index 98% rename from docs/reference/ingestion-tools/enrich-processor/ip-location-processor.md rename to docs/reference/enrich-processor/ip-location-processor.md index cf9d202917c79..b85b024d795d0 100644 --- a/docs/reference/ingestion-tools/enrich-processor/ip-location-processor.md +++ b/docs/reference/enrich-processor/ip-location-processor.md @@ -17,7 +17,7 @@ By default, the processor uses the GeoLite2 City, GeoLite2 Country, and GeoLite2 {{es}} automatically downloads updates for these databases from the Elastic GeoIP endpoint: [https://geoip.elastic.co/v1/database](https://geoip.elastic.co/v1/database?elastic_geoip_service_tos=agree). To get download statistics for these updates, use the [GeoIP stats API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-ingest-geo-ip-stats). -If your cluster can’t connect to the Elastic GeoIP endpoint or you want to manage your own updates, see [Manage your own IP geolocation database updates](/reference/ingestion-tools/enrich-processor/geoip-processor.md#manage-geoip-database-updates). +If your cluster can’t connect to the Elastic GeoIP endpoint or you want to manage your own updates, see [Manage your own IP geolocation database updates](/reference/enrich-processor/geoip-processor.md#manage-geoip-database-updates). If you would like to have {{es}} download database files directly from Maxmind using your own provided license key, see [Create or update IP geolocation database configuration](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-ingest-put-ip-location-database). diff --git a/docs/reference/ingestion-tools/enrich-processor/join-processor.md b/docs/reference/enrich-processor/join-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/join-processor.md rename to docs/reference/enrich-processor/join-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/json-processor.md b/docs/reference/enrich-processor/json-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/json-processor.md rename to docs/reference/enrich-processor/json-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/kv-processor.md b/docs/reference/enrich-processor/kv-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/kv-processor.md rename to docs/reference/enrich-processor/kv-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/lowercase-processor.md b/docs/reference/enrich-processor/lowercase-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/lowercase-processor.md rename to docs/reference/enrich-processor/lowercase-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/network-direction-processor.md b/docs/reference/enrich-processor/network-direction-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/network-direction-processor.md rename to docs/reference/enrich-processor/network-direction-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/pipeline-processor.md b/docs/reference/enrich-processor/pipeline-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/pipeline-processor.md rename to docs/reference/enrich-processor/pipeline-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/redact-processor.md b/docs/reference/enrich-processor/redact-processor.md similarity index 97% rename from docs/reference/ingestion-tools/enrich-processor/redact-processor.md rename to docs/reference/enrich-processor/redact-processor.md index 92cb5fd044b6a..49b44538f3737 100644 --- a/docs/reference/ingestion-tools/enrich-processor/redact-processor.md +++ b/docs/reference/enrich-processor/redact-processor.md @@ -201,7 +201,7 @@ The username is redacted in the response. ## Grok watchdog [grok-watchdog-redact] -The watchdog interrupts expressions that take too long to execute. When interrupted, the Redact processor fails with an error. The same [settings](/reference/ingestion-tools/enrich-processor/grok-processor.md#grok-watchdog-options) that control the Grok Watchdog timeout also apply to the Redact processor. +The watchdog interrupts expressions that take too long to execute. When interrupted, the Redact processor fails with an error. The same [settings](/reference/enrich-processor/grok-processor.md#grok-watchdog-options) that control the Grok Watchdog timeout also apply to the Redact processor. ## Licensing [redact-licensing] diff --git a/docs/reference/ingestion-tools/enrich-processor/registered-domain-processor.md b/docs/reference/enrich-processor/registered-domain-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/registered-domain-processor.md rename to docs/reference/enrich-processor/registered-domain-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/remove-processor.md b/docs/reference/enrich-processor/remove-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/remove-processor.md rename to docs/reference/enrich-processor/remove-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/rename-processor.md b/docs/reference/enrich-processor/rename-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/rename-processor.md rename to docs/reference/enrich-processor/rename-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/reroute-processor.md b/docs/reference/enrich-processor/reroute-processor.md similarity index 94% rename from docs/reference/ingestion-tools/enrich-processor/reroute-processor.md rename to docs/reference/enrich-processor/reroute-processor.md index 7464f351b2d73..aad3535049697 100644 --- a/docs/reference/ingestion-tools/enrich-processor/reroute-processor.md +++ b/docs/reference/enrich-processor/reroute-processor.md @@ -22,7 +22,7 @@ It’s not possible to change the `type` of the data stream with the `reroute` p :::: -After a `reroute` processor has been executed, all the other processors of the current pipeline are skipped, including the final pipeline. If the current pipeline is executed in the context of a [Pipeline](/reference/ingestion-tools/enrich-processor/pipeline-processor.md), the calling pipeline will be skipped, too. This means that at most one `reroute` processor is ever executed within a pipeline, allowing to define mutually exclusive routing conditions, similar to a if, else-if, else-if, … condition. +After a `reroute` processor has been executed, all the other processors of the current pipeline are skipped, including the final pipeline. If the current pipeline is executed in the context of a [Pipeline](/reference/enrich-processor/pipeline-processor.md), the calling pipeline will be skipped, too. This means that at most one `reroute` processor is ever executed within a pipeline, allowing to define mutually exclusive routing conditions, similar to a if, else-if, else-if, … condition. The reroute processor ensures that the `data_stream.` fields are set according to the new target. If the document contains a `event.dataset` value, it will be updated to reflect the same value as `data_stream.dataset`. diff --git a/docs/reference/ingestion-tools/enrich-processor/script-processor.md b/docs/reference/enrich-processor/script-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/script-processor.md rename to docs/reference/enrich-processor/script-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/set-processor.md b/docs/reference/enrich-processor/set-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/set-processor.md rename to docs/reference/enrich-processor/set-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/sort-processor.md b/docs/reference/enrich-processor/sort-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/sort-processor.md rename to docs/reference/enrich-processor/sort-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/split-processor.md b/docs/reference/enrich-processor/split-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/split-processor.md rename to docs/reference/enrich-processor/split-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/terminate-processor.md b/docs/reference/enrich-processor/terminate-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/terminate-processor.md rename to docs/reference/enrich-processor/terminate-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/toc.yml b/docs/reference/enrich-processor/toc.yml similarity index 97% rename from docs/reference/ingestion-tools/enrich-processor/toc.yml rename to docs/reference/enrich-processor/toc.yml index 249d9f236fcfe..f60fe7909d70f 100644 --- a/docs/reference/ingestion-tools/enrich-processor/toc.yml +++ b/docs/reference/enrich-processor/toc.yml @@ -1,4 +1,3 @@ -project: 'Enrich processor reference' toc: - file: index.md - file: append-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/trim-processor.md b/docs/reference/enrich-processor/trim-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/trim-processor.md rename to docs/reference/enrich-processor/trim-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/uppercase-processor.md b/docs/reference/enrich-processor/uppercase-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/uppercase-processor.md rename to docs/reference/enrich-processor/uppercase-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/uri-parts-processor.md b/docs/reference/enrich-processor/uri-parts-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/uri-parts-processor.md rename to docs/reference/enrich-processor/uri-parts-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/urldecode-processor.md b/docs/reference/enrich-processor/urldecode-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/urldecode-processor.md rename to docs/reference/enrich-processor/urldecode-processor.md diff --git a/docs/reference/ingestion-tools/enrich-processor/user-agent-processor.md b/docs/reference/enrich-processor/user-agent-processor.md similarity index 100% rename from docs/reference/ingestion-tools/enrich-processor/user-agent-processor.md rename to docs/reference/enrich-processor/user-agent-processor.md diff --git a/docs/reference/index.md b/docs/reference/index.md deleted file mode 100644 index 4a938e09d06b2..0000000000000 --- a/docs/reference/index.md +++ /dev/null @@ -1 +0,0 @@ -# Reference \ No newline at end of file diff --git a/docs/reference/ingestion-tools/search-connectors/connector-reference.md b/docs/reference/ingestion-tools/search-connectors/connector-reference.md deleted file mode 100644 index d0e07a236e78c..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/connector-reference.md +++ /dev/null @@ -1,71 +0,0 @@ ---- -applies_to: - stack: ga - serverless: ga -mapped_pages: - - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-refs.html ---- - -# Connectors references [es-connectors-refs] - -The following pages contain the reference documentation for each individual connector: - -* [Azure Blob Storage](/reference/ingestion-tools/search-connectors/es-connectors-azure-blob.md) -* [Box](/reference/ingestion-tools/search-connectors/es-connectors-box.md) -* [Confluence](/reference/ingestion-tools/search-connectors/es-connectors-confluence.md) -* [Dropbox](/reference/ingestion-tools/search-connectors/es-connectors-dropbox.md) -* [GitHub](/reference/ingestion-tools/search-connectors/es-connectors-github.md) -* [Gmail](/reference/ingestion-tools/search-connectors/es-connectors-gmail.md) -* [Google Cloud Storage](/reference/ingestion-tools/search-connectors/es-connectors-google-cloud.md) -* [Google Drive](/reference/ingestion-tools/search-connectors/es-connectors-google-drive.md) -* [GraphQL](/reference/ingestion-tools/search-connectors/es-connectors-graphql.md) -* [Jira](/reference/ingestion-tools/search-connectors/es-connectors-jira.md) -* [MicrosoftSQL](/reference/ingestion-tools/search-connectors/es-connectors-ms-sql.md) -* [MongoDB](/reference/ingestion-tools/search-connectors/es-connectors-mongodb.md) -* [MySQL](/reference/ingestion-tools/search-connectors/es-connectors-mysql.md) -* [Network drive](/reference/ingestion-tools/search-connectors/es-connectors-network-drive.md) -* [Notion](/reference/ingestion-tools/search-connectors/es-connectors-notion.md) -* [OneDrive](/reference/ingestion-tools/search-connectors/es-connectors-onedrive.md) -* [OpenText Documentum](/reference/ingestion-tools/search-connectors/es-connectors-opentext.md) -* [Oracle](/reference/ingestion-tools/search-connectors/es-connectors-oracle.md) -* [Outlook](/reference/ingestion-tools/search-connectors/es-connectors-outlook.md) -* [PostgreSQL](/reference/ingestion-tools/search-connectors/es-connectors-postgresql.md) -* [Redis](/reference/ingestion-tools/search-connectors/es-connectors-redis.md) -* [S3](/reference/ingestion-tools/search-connectors/es-connectors-s3.md) -* [Salesforce](/reference/ingestion-tools/search-connectors/es-connectors-salesforce.md) -* [ServiceNow](/reference/ingestion-tools/search-connectors/es-connectors-servicenow.md) -* [SharePoint Online](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint-online.md) -* [SharePoint Server](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint.md) -* [Slack](/reference/ingestion-tools/search-connectors/es-connectors-slack.md) -* [Teams](/reference/ingestion-tools/search-connectors/es-connectors-teams.md) -* [Zoom](/reference/ingestion-tools/search-connectors/es-connectors-zoom.md) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/docs/reference/ingestion-tools/search-connectors/content-syncs.md b/docs/reference/ingestion-tools/search-connectors/content-syncs.md deleted file mode 100644 index 99c15d4309482..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/content-syncs.md +++ /dev/null @@ -1,82 +0,0 @@ ---- -mapped_pages: - - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-sync-types.html ---- - -# Content syncs [es-connectors-sync-types] - -Elastic connectors have two types of content syncs: - -* [Full syncs](#es-connectors-sync-types-full) -* [Incremental syncs](#es-connectors-sync-types-incremental) - - -## Full syncs [es-connectors-sync-types-full] - -::::{note} -We recommend running a full sync whenever [Sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md) are modified - -:::: - - -A full sync syncs all documents in the third-party data source into {{es}}. - -It also deletes any documents in {{es}}, which no longer exist in the third-party data source. - -A full sync, by definition, takes longer than an incremental sync but it ensures full data consistency. - -A full sync is available for all connectors. - -You can [schedule](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-recurring) or [manually trigger](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-manual) a full sync job. - - -## Incremental syncs [es-connectors-sync-types-incremental] - -An incremental sync only syncs data changes since the last full or incremental sync. - -Incremental syncs are only available after an initial full sync has successfully completed. Otherwise the incremental sync will fail. - -You can [schedule](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-recurring) or [manually trigger](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-manual) an incremental sync job. - - -### Incremental sync performance [es-connectors-sync-types-incremental-performance] - -During an incremental sync your connector will still *fetch* all data from the third-party data source. If data contains timestamps, the connector framework compares document ids and timestamps. If a document already exists in {{es}} with the same timestamp, then this document does not need updating and will not be sent to {{es}}. - -The determining factor in incremental sync performance is the raw volume of data ingested. For small volumes of data, the performance improvement using incremental syncs will be negligible. For large volumes of data, the performance impact can be huge. Additionally, an incremental sync is less likely to be throttled by {{es}}, making it more performant than a full sync when {{es}} is under heavy load. - -A third-party data source that has throttling and low throughput, but stores very little data in Elasticsearch, such as GitHub, Jira, or Confluence, won’t see a significant performance improvement from incremental syncs. - -However, a fast, accessible third-party data source that stores huge amounts of data in {{es}}, such as Azure Blob Storage, Google Drive, or S3, can lead to a significant performance improvement from incremental syncs. - -::::{note} -Incremental syncs for [SharePoint Online](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint-online.md) and [Google Drive](/reference/ingestion-tools/search-connectors/es-connectors-google-drive.md) connectors use specific logic. All other connectors use the same shared connector framework logic for incremental syncs. - -:::: - - - -### Incremental sync availability [es-connectors-sync-types-incremental-supported] - -Incremental syncs are available for the following connectors: - -* [Azure Blob Storage](/reference/ingestion-tools/search-connectors/es-connectors-azure-blob.md) -* [Box](/reference/ingestion-tools/search-connectors/es-connectors-box.md) -* [Confluence](/reference/ingestion-tools/search-connectors/es-connectors-confluence.md) -* [Dropbox](/reference/ingestion-tools/search-connectors/es-connectors-dropbox.md) -* [GitHub](/reference/ingestion-tools/search-connectors/es-connectors-github.md) -* [Gmail](/reference/ingestion-tools/search-connectors/es-connectors-gmail.md) -* [Google Cloud Storage](/reference/ingestion-tools/search-connectors/es-connectors-google-cloud.md) -* [Google Drive](/reference/ingestion-tools/search-connectors/es-connectors-google-drive.md) -* [Jira](/reference/ingestion-tools/search-connectors/es-connectors-jira.md) -* [Network drive](/reference/ingestion-tools/search-connectors/es-connectors-network-drive.md) -* [Notion](/reference/ingestion-tools/search-connectors/es-connectors-notion.md) -* [OneDrive](/reference/ingestion-tools/search-connectors/es-connectors-onedrive.md) -* [Outlook](/reference/ingestion-tools/search-connectors/es-connectors-outlook.md) -* [Salesforce](/reference/ingestion-tools/search-connectors/es-connectors-salesforce.md) -* [ServiceNow](/reference/ingestion-tools/search-connectors/es-connectors-servicenow.md) -* [SharePoint Online](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint-online.md) -* [SharePoint Server](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint.md) -* [Teams](/reference/ingestion-tools/search-connectors/es-connectors-teams.md) -* [Zoom](/reference/ingestion-tools/search-connectors/es-connectors-zoom.md) - diff --git a/docs/reference/ingestion-tools/search-connectors/document-level-security.md b/docs/reference/ingestion-tools/search-connectors/document-level-security.md deleted file mode 100644 index b9e99499719ca..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/document-level-security.md +++ /dev/null @@ -1,51 +0,0 @@ ---- -mapped_pages: - - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-dls.html ---- - -# Document level security [es-dls] - -Document level security (DLS) enables you to restrict access to documents in your Elasticsearch indices according to user and group permissions. This ensures search results only return authorized information for users, based on their permissions. - - -## Availability & prerequisites [es-dls-availability-prerequisites] - -Support for DLS in Elastic connectors was introduced in version **8.9.0**. - -::::{note} -This feature is in **beta** and is subject to change. The design and code is less mature than official GA features and is being provided as-is with no warranties. Beta features are not subject to the support SLA of official GA features. - -:::: - - -This feature is not available for all Elastic subscription levels. Refer to the subscriptions pages for [Elastic Cloud](https://www.elastic.co/subscriptions/cloud) and [Elastic Stack](https://www.elastic.co/subscriptions). - -DLS is available by default when using the following Elastic connectors: - -* [Confluence](/reference/ingestion-tools/search-connectors/es-connectors-confluence.md) -* [Dropbox](/reference/ingestion-tools/search-connectors/es-connectors-dropbox.md) -* [Jira](/reference/ingestion-tools/search-connectors/es-connectors-jira.md) (including Jira Data Center) -* [GitHub](/reference/ingestion-tools/search-connectors/es-connectors-github.md) -* [Gmail](/reference/ingestion-tools/search-connectors/es-connectors-gmail.md) -* [Google Drive](/reference/ingestion-tools/search-connectors/es-connectors-google-drive.md) -* [Network Drive](/reference/ingestion-tools/search-connectors/es-connectors-network-drive.md) -* [OneDrive](/reference/ingestion-tools/search-connectors/es-connectors-onedrive.md) -* [Outlook](/reference/ingestion-tools/search-connectors/es-connectors-outlook.md) -* [Salesforce](/reference/ingestion-tools/search-connectors/es-connectors-salesforce.md) -* [SharePoint Online](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint-online.md) -* [SharePoint Server](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint.md) -* [ServiceNow](/reference/ingestion-tools/search-connectors/es-connectors-servicenow.md) - -Note that our standalone products (App Search and Workplace Search) do not use this feature. Workplace Search has its own permissions management system. - - -## Learn more [es-dls-learn-more] - -DLS documentation: - -* [How DLS works](/reference/ingestion-tools/search-connectors/es-dls-overview.md) -* [DLS in Search Applications](/reference/ingestion-tools/search-connectors/es-dls-e2e-guide.md) -* [DLS for SharePoint Online connector](/reference/ingestion-tools/search-connectors/es-connectors-sharepoint-online.md#es-connectors-sharepoint-online-client-configuration) - - - diff --git a/docs/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md b/docs/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md deleted file mode 100644 index d9d736ed83af2..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md +++ /dev/null @@ -1,18 +0,0 @@ ---- -navigation_title: "Troubleshooting" -mapped_pages: - - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-troubleshooting.html ---- - -# Troubleshooting connectors [es-connectors-troubleshooting] - - -Use the following actions to help diagnose and resolve issues with [self-managed connectors](/reference/ingestion-tools/search-connectors/self-managed-connectors.md): - -* [View index health and ingestion status](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-indices). -* [View errors, document count, sync history, and sync statuses](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-index-view). -* [View synced documents and index mappings](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-documents). -* Edit your index configuration: [self-managed connector](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). - -You can also request help or support. - diff --git a/docs/reference/ingestion-tools/search-connectors/management.md b/docs/reference/ingestion-tools/search-connectors/management.md deleted file mode 100644 index d270c996f62b8..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/management.md +++ /dev/null @@ -1,18 +0,0 @@ ---- -mapped_pages: - - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-management.html ---- - -# Management topics [es-connectors-management] - -Refer to the following sections: - -* [Troubleshooting](/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md) -* [Logs](/reference/ingestion-tools/search-connectors/es-connectors-logs.md) -* [Scalability](/reference/ingestion-tools/search-connectors/es-connectors-scalability.md) -* [Security](/reference/ingestion-tools/search-connectors/es-connectors-security.md) - - - - - diff --git a/docs/reference/ingestion-tools/search-connectors/toc.yml b/docs/reference/ingestion-tools/search-connectors/toc.yml deleted file mode 100644 index 58df7af6ddccc..0000000000000 --- a/docs/reference/ingestion-tools/search-connectors/toc.yml +++ /dev/null @@ -1,65 +0,0 @@ -project: 'Search connectors reference' -toc: - - file: index.md - - file: connector-reference.md - children: - - file: es-connectors-azure-blob.md - - file: es-connectors-box.md - - file: es-connectors-confluence.md - - file: es-connectors-dropbox.md - - file: es-connectors-github.md - - file: es-connectors-gmail.md - - file: es-connectors-google-cloud.md - - file: es-connectors-google-drive.md - - file: es-connectors-graphql.md - - file: es-connectors-jira.md - - file: es-connectors-ms-sql.md - - file: es-connectors-mongodb.md - - file: es-connectors-mysql.md - - file: es-connectors-network-drive.md - - file: es-connectors-notion.md - - file: es-connectors-onedrive.md - - file: es-connectors-opentext.md - - file: es-connectors-oracle.md - - file: es-connectors-outlook.md - - file: es-connectors-postgresql.md - - file: es-connectors-redis.md - - file: es-connectors-s3.md - - file: es-connectors-salesforce.md - - file: es-connectors-servicenow.md - - file: es-connectors-sharepoint-online.md - - file: es-connectors-sharepoint.md - - file: es-connectors-slack.md - - file: es-connectors-teams.md - - file: es-connectors-zoom.md - - file: self-managed-connectors.md - children: - - file: es-connectors-run-from-docker.md - - file: es-connectors-run-from-source.md - - file: es-connectors-docker-compose-quickstart.md - - file: es-postgresql-connector-client-tutorial.md - - file: elastic-managed-connectors.md # TODO: I should be deleted - - file: build-customize-connectors.md - - file: connectors-ui-in-kibana.md - # TO DO: Do we want this page? (It's not in the inventory.) - - file: es-connectors-apis.md - children: - - file: api-tutorial.md - - file: content-syncs.md - - file: extract-transform.md - children: - - file: es-connectors-content-extraction.md - - file: es-sync-rules.md - - file: document-level-security.md - children: - - file: es-dls-overview.md - - file: es-dls-e2e-guide.md - - file: management.md - children: - - file: es-connectors-scalability.md - - file: es-connectors-security.md - - file: es-connectors-troubleshooting.md - - file: es-connectors-logs.md - - file: use-cases.md - children: - - file: es-connectors-overview-architecture.md \ No newline at end of file diff --git a/docs/reference/query-languages/eql/eql-syntax.md b/docs/reference/query-languages/eql/eql-syntax.md index bf3d2bd6f9cf4..5506f6bcdab2f 100644 --- a/docs/reference/query-languages/eql/eql-syntax.md +++ b/docs/reference/query-languages/eql/eql-syntax.md @@ -681,7 +681,7 @@ file where endsWith(file.path,".exe") or endsWith(file.path,".dll") While this works, it can be repetitive to write and can slow search speeds. To speed up search, you can do the following instead: 1. [Add a new field](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-put-mapping), `file.extension`, to the index. The `file.extension` field will contain only the file extension from the `file.path` field. -2. Use an [ingest pipeline](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md) containing the [`grok`](/reference/ingestion-tools/enrich-processor/grok-processor.md) processor or another preprocessor tool to extract the file extension from the `file.path` field before indexing. +2. Use an [ingest pipeline](docs-content://manage-data/ingest/transform-enrich/ingest-pipelines.md) containing the [`grok`](/reference/enrich-processor/grok-processor.md) processor or another preprocessor tool to extract the file extension from the `file.path` field before indexing. 3. Index the extracted file extension to the `file.extension` field. These changes may slow indexing but allow for faster searches. Users can use the `file.extension` field instead of multiple `endsWith` function calls: diff --git a/docs/reference/query-languages/esql/_snippets/functions/appendix/count_distinct.md b/docs/reference/query-languages/esql/_snippets/functions/appendix/count_distinct.md index 3218dd61c0615..ad94c66e9c6b4 100644 --- a/docs/reference/query-languages/esql/_snippets/functions/appendix/count_distinct.md +++ b/docs/reference/query-languages/esql/_snippets/functions/appendix/count_distinct.md @@ -12,7 +12,7 @@ This `COUNT_DISTINCT` function is based on the algorithm, which counts based on the hashes of the values with some interesting properties: -:::{include} /reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md +:::{include} /reference/aggregations/_snippets/search-aggregations-metrics-cardinality-aggregation-explanation.md ::: The `COUNT_DISTINCT` function takes an optional second parameter to configure diff --git a/docs/reference/query-languages/esql/_snippets/functions/appendix/percentile.md b/docs/reference/query-languages/esql/_snippets/functions/appendix/percentile.md index d163a1808403f..0d798c20021ee 100644 --- a/docs/reference/query-languages/esql/_snippets/functions/appendix/percentile.md +++ b/docs/reference/query-languages/esql/_snippets/functions/appendix/percentile.md @@ -2,7 +2,7 @@ ### `PERCENTILE` is (usually) approximate [esql-percentile-approximate] -:::{include} /reference/data-analysis/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md +:::{include} /reference/aggregations/_snippets/search-aggregations-metrics-percentile-aggregation-approximate.md ::: ::::{warning} diff --git a/docs/reference/query-languages/esql/_snippets/functions/examples/bucket.md b/docs/reference/query-languages/esql/_snippets/functions/examples/bucket.md index 817dadf0467dc..b5cbed477c2f2 100644 --- a/docs/reference/query-languages/esql/_snippets/functions/examples/bucket.md +++ b/docs/reference/query-languages/esql/_snippets/functions/examples/bucket.md @@ -208,7 +208,7 @@ FROM employees | 801.0 | 800.0 | 1052.0 | 1050.0 | Sometimes you need to change the start value of each bucket by a given duration (similar to date histogram -aggregation’s [`offset`](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md) parameter). To do so, you will need to +aggregation’s [`offset`](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md) parameter). To do so, you will need to take into account how the language handles expressions within the `STATS` command: if these contain functions or arithmetic operators, a virtual `EVAL` is inserted before and/or after the `STATS` command. Consequently, a double compensation is needed to adjust the bucketed date value before the aggregation and then again after. For instance, diff --git a/docs/reference/query-languages/esql/esql-commands.md b/docs/reference/query-languages/esql/esql-commands.md index 6689f820fe045..9acdf3c482456 100644 --- a/docs/reference/query-languages/esql/esql-commands.md +++ b/docs/reference/query-languages/esql/esql-commands.md @@ -10,7 +10,7 @@ mapped_pages: An {{esql}} source command produces a table, typically with data from {{es}}. An {{esql}} query must start with a source command. -:::{image} ../../../images/source-command.svg +:::{image} ../images/source-command.svg :alt: A source command producing a table from {{es}} ::: @@ -25,7 +25,7 @@ An {{esql}} source command produces a table, typically with data from {{es}}. An {{esql}} processing commands change an input table by adding, removing, or changing rows and columns. -:::{image} ../../../images/processing-command.svg +:::{image} ../images/processing-command.svg :alt: A processing command changing an input table ::: @@ -307,7 +307,7 @@ ENRICH policy [ON match_field] [WITH [new_name1 = ]field1, [new_name2 = ]field2, `ENRICH` enables you to add data from existing indices as new columns using an enrich policy. Refer to [Data enrichment](/reference/query-languages/esql/esql-enrich-data.md) for information about setting up a policy. -:::{image} ../../../images/esql-enrich.png +:::{image} ../images/esql-enrich.png :alt: esql enrich ::: @@ -741,7 +741,7 @@ FROM Left ```esql FROM Left | LOOKUP JOIN Right ON Key -| WHERE Language IS NOT NULL +| WHERE Language IS NOT NULL ``` ## `MV_EXPAND` [esql-mv_expand] diff --git a/docs/reference/query-languages/esql/esql-enrich-data.md b/docs/reference/query-languages/esql/esql-enrich-data.md index acc9556a0e4d8..c172aaf93d1a6 100644 --- a/docs/reference/query-languages/esql/esql-enrich-data.md +++ b/docs/reference/query-languages/esql/esql-enrich-data.md @@ -28,7 +28,7 @@ For example, you can use `ENRICH` to: The `ENRICH` command adds new columns to a table, with data from {{es}} indices. It requires a few special components: -:::{image} ../../../images/esql-enrich.png +:::{image} ../images/esql-enrich.png :alt: esql enrich ::: @@ -119,14 +119,14 @@ Once created, you can’t update or change an enrich policy. See [Update an enri Once the enrich policy is created, you need to execute it using the [execute enrich policy API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-enrich-execute-policy) or [Index Management in {{kib}}](https://www.elastic.co/guide/en/elasticsearch/reference/current/index-mgmt.html#manage-enrich-policies) to create an [enrich index](docs-content://manage-data/ingest/transform-enrich/data-enrichment.md#enrich-index). -:::{image} ../../../images/esql-enrich-policy.png +:::{image} ../images/esql-enrich-policy.png :alt: esql enrich policy ::: The *enrich index* contains documents from the policy’s source indices. Enrich indices always begin with `.enrich-*`, are read-only, and are [force merged](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-forcemerge). ::::{warning} -Enrich indices should only be used by the [enrich processor](/reference/ingestion-tools/enrich-processor/enrich-processor.md) or the [{{esql}} `ENRICH` command](/reference/query-languages/esql/esql-commands.md#esql-enrich). Avoid using enrich indices for other purposes. +Enrich indices should only be used by the [enrich processor](/reference/enrich-processor/enrich-processor.md) or the [{{esql}} `ENRICH` command](/reference/query-languages/esql/esql-commands.md#esql-enrich). Avoid using enrich indices for other purposes. :::: @@ -136,7 +136,7 @@ Enrich indices should only be used by the [enrich processor](/reference/ingestio After the policy has been executed, you can use the [`ENRICH` command](/reference/query-languages/esql/esql-commands.md#esql-enrich) to enrich your data. -:::{image} ../../../images/esql-enrich-command.png +:::{image} ../images/esql-enrich-command.png :alt: esql enrich command ::: diff --git a/docs/reference/query-languages/esql/esql-lookup-join.md b/docs/reference/query-languages/esql/esql-lookup-join.md index a3bc909be1ccc..8064f1de63b13 100644 --- a/docs/reference/query-languages/esql/esql-lookup-join.md +++ b/docs/reference/query-languages/esql/esql-lookup-join.md @@ -30,7 +30,7 @@ For example, you can use `LOOKUP JOIN` to: The `LOOKUP JOIN` command adds new columns to a table, with data from {{es}} indices. -:::{image} ../../../images/esql-lookup-join.png +:::{image} ../images/esql-lookup-join.png :alt: esql lookup join ::: diff --git a/docs/reference/query-languages/esql/esql-process-data-with-dissect-grok.md b/docs/reference/query-languages/esql/esql-process-data-with-dissect-grok.md index fcbfd43c66dbe..d5ae7fcfe4370 100644 --- a/docs/reference/query-languages/esql/esql-process-data-with-dissect-grok.md +++ b/docs/reference/query-languages/esql/esql-process-data-with-dissect-grok.md @@ -9,11 +9,11 @@ mapped_pages: Your data may contain unstructured strings that you want to structure. This makes it easier to analyze the data. For example, log messages may contain IP addresses that you want to extract so you can find the most active IP addresses. -:::{image} ../../../images/unstructured-data.png +:::{image} ../images/unstructured-data.png :alt: unstructured data ::: -{{es}} can structure your data at index time or query time. At index time, you can use the [Dissect](/reference/ingestion-tools/enrich-processor/dissect-processor.md) and [Grok](/reference/ingestion-tools/enrich-processor/grok-processor.md) ingest processors, or the {{ls}} [Dissect](logstash://reference/plugins-filters-dissect.md) and [Grok](logstash://reference/plugins-filters-grok.md) filters. At query time, you can use the {{esql}} [`DISSECT`](/reference/query-languages/esql/esql-commands.md#esql-dissect) and [`GROK`](/reference/query-languages/esql/esql-commands.md#esql-grok) commands. +{{es}} can structure your data at index time or query time. At index time, you can use the [Dissect](/reference/enrich-processor/dissect-processor.md) and [Grok](/reference/enrich-processor/grok-processor.md) ingest processors, or the {{ls}} [Dissect](logstash://reference/plugins-filters-dissect.md) and [Grok](logstash://reference/plugins-filters-grok.md) filters. At query time, you can use the {{esql}} [`DISSECT`](/reference/query-languages/esql/esql-commands.md#esql-dissect) and [`GROK`](/reference/query-languages/esql/esql-commands.md#esql-grok) commands. ## `DISSECT` or `GROK`? Or both? [esql-grok-or-dissect] @@ -267,7 +267,7 @@ The `SEMANTIC` is the identifier you give to the piece of text being matched. Fo By default, matched values are output as keyword string data types. To convert a semantic’s data type, suffix it with the target data type. For example `%{NUMBER:num:int}`, which converts the `num` semantic from a string to an integer. Currently the only supported conversions are `int` and `float`. For other types, use the [Type conversion functions](/reference/query-languages/esql/esql-functions-operators.md#esql-type-conversion-functions). -For an overview of the available patterns, refer to [GitHub](https://github.com/elastic/elasticsearch//blob/master/libs/grok/src/main/resources/patterns). You can also retrieve a list of all patterns using a [REST API](/reference/ingestion-tools/enrich-processor/grok-processor.md#grok-processor-rest-get). +For an overview of the available patterns, refer to [GitHub](https://github.com/elastic/elasticsearch//blob/master/libs/grok/src/main/resources/patterns). You can also retrieve a list of all patterns using a [REST API](/reference/enrich-processor/grok-processor.md#grok-processor-rest-get). ### Regular expressions [esql-grok-regex] @@ -351,7 +351,7 @@ To write and debug grok patterns, you can use the [Grok Debugger](docs-content:/ ### Limitations [esql-grok-limitations] -The `GROK` command does not support configuring [custom patterns](/reference/ingestion-tools/enrich-processor/grok-processor.md#custom-patterns), or [multiple patterns](/reference/ingestion-tools/enrich-processor/grok-processor.md#trace-match). The `GROK` command is not subject to [Grok watchdog settings](/reference/ingestion-tools/enrich-processor/grok-processor.md#grok-watchdog). +The `GROK` command does not support configuring [custom patterns](/reference/enrich-processor/grok-processor.md#custom-patterns), or [multiple patterns](/reference/enrich-processor/grok-processor.md#trace-match). The `GROK` command is not subject to [Grok watchdog settings](/reference/enrich-processor/grok-processor.md#grok-watchdog). diff --git a/docs/reference/query-languages/esql/limitations.md b/docs/reference/query-languages/esql/limitations.md index 6ef97d3841ba1..b030c089f2523 100644 --- a/docs/reference/query-languages/esql/limitations.md +++ b/docs/reference/query-languages/esql/limitations.md @@ -226,7 +226,7 @@ The `DISSECT` command does not support reference keys. ## Grok limitations [esql-limitations-grok] -The `GROK` command does not support configuring [custom patterns](/reference/ingestion-tools/enrich-processor/grok-processor.md#custom-patterns), or [multiple patterns](/reference/ingestion-tools/enrich-processor/grok-processor.md#trace-match). The `GROK` command is not subject to [Grok watchdog settings](/reference/ingestion-tools/enrich-processor/grok-processor.md#grok-watchdog). +The `GROK` command does not support configuring [custom patterns](/reference/enrich-processor/grok-processor.md#custom-patterns), or [multiple patterns](/reference/enrich-processor/grok-processor.md#trace-match). The `GROK` command is not subject to [Grok watchdog settings](/reference/enrich-processor/grok-processor.md#grok-watchdog). ## Multivalue limitations [esql-limitations-mv] diff --git a/docs/images/esql-enrich-command.png b/docs/reference/query-languages/images/esql-enrich-command.png similarity index 100% rename from docs/images/esql-enrich-command.png rename to docs/reference/query-languages/images/esql-enrich-command.png diff --git a/docs/images/esql-enrich-policy.png b/docs/reference/query-languages/images/esql-enrich-policy.png similarity index 100% rename from docs/images/esql-enrich-policy.png rename to docs/reference/query-languages/images/esql-enrich-policy.png diff --git a/docs/images/esql-enrich.png b/docs/reference/query-languages/images/esql-enrich.png similarity index 100% rename from docs/images/esql-enrich.png rename to docs/reference/query-languages/images/esql-enrich.png diff --git a/docs/images/esql-lookup-join.png b/docs/reference/query-languages/images/esql-lookup-join.png similarity index 100% rename from docs/images/esql-lookup-join.png rename to docs/reference/query-languages/images/esql-lookup-join.png diff --git a/docs/images/processing-command.svg b/docs/reference/query-languages/images/processing-command.svg similarity index 100% rename from docs/images/processing-command.svg rename to docs/reference/query-languages/images/processing-command.svg diff --git a/docs/images/source-command.svg b/docs/reference/query-languages/images/source-command.svg similarity index 100% rename from docs/images/source-command.svg rename to docs/reference/query-languages/images/source-command.svg diff --git a/docs/images/unstructured-data.png b/docs/reference/query-languages/images/unstructured-data.png similarity index 100% rename from docs/images/unstructured-data.png rename to docs/reference/query-languages/images/unstructured-data.png diff --git a/docs/reference/query-languages/query-dsl/query-dsl-distance-feature-query.md b/docs/reference/query-languages/query-dsl/query-dsl-distance-feature-query.md index 35a5a9ef36f21..3c047d6c96aaf 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-distance-feature-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-distance-feature-query.md @@ -143,7 +143,7 @@ GET /items/_search `origin` : (Required, string) Date or point of origin used to calculate distances. -If the `field` value is a [`date`](/reference/elasticsearch/mapping-reference/date.md) or [`date_nanos`](/reference/elasticsearch/mapping-reference/date_nanos.md) field, the `origin` value must be a [date](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern). [Date Math](/reference/elasticsearch/rest-apis/common-options.md#date-math), such as `now-1h`, is supported. +If the `field` value is a [`date`](/reference/elasticsearch/mapping-reference/date.md) or [`date_nanos`](/reference/elasticsearch/mapping-reference/date_nanos.md) field, the `origin` value must be a [date](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md#date-format-pattern). [Date Math](/reference/elasticsearch/rest-apis/common-options.md#date-math), such as `now-1h`, is supported. If the `field` value is a [`geo_point`](/reference/elasticsearch/mapping-reference/geo-point.md) field, the `origin` value must be a geopoint. diff --git a/docs/reference/query-languages/query-dsl/query-dsl-match-query.md b/docs/reference/query-languages/query-dsl/query-dsl-match-query.md index 7ccf064cac884..2baf9fbb52055 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-match-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-match-query.md @@ -199,7 +199,7 @@ GET /_search ### Synonyms [query-dsl-match-query-synonyms] -The `match` query supports multi-terms synonym expansion with the [synonym_graph](/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md) token filter. When this filter is used, the parser creates a phrase query for each multi-terms synonyms. For example, the following synonym: `"ny, new york"` would produce: +The `match` query supports multi-terms synonym expansion with the [synonym_graph](/reference/text-analysis/analysis-synonym-graph-tokenfilter.md) token filter. When this filter is used, the parser creates a phrase query for each multi-terms synonyms. For example, the following synonym: `"ny, new york"` would produce: `(ny OR ("new york"))` diff --git a/docs/reference/query-languages/query-dsl/query-dsl-query-string-query.md b/docs/reference/query-languages/query-dsl/query-dsl-query-string-query.md index d0b54024f9b3b..1292362cdf684 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-query-string-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-query-string-query.md @@ -72,7 +72,7 @@ There is a limit on the number of fields times terms that can be queried at once `analyze_wildcard` : (Optional, Boolean) If `true`, the query attempts to analyze wildcard terms in the query string. Defaults to `false`. Note that, in case of `true`, only queries that end with a `*` are fully analyzed. Queries that start with `*` or have it in the middle -are only [normalized](/reference/data-analysis/text-analysis/normalizers.md). +are only [normalized](/reference/text-analysis/normalizers.md). `analyzer` : (Optional, string) [Analyzer](docs-content://manage-data/data-store/text-analysis.md) used to convert text in the query string into tokens. Defaults to the [index-time analyzer](docs-content://manage-data/data-store/text-analysis/specify-an-analyzer.md#specify-index-time-analyzer) mapped for the `default_field`. If no analyzer is mapped, the index’s default analyzer is used. @@ -282,7 +282,7 @@ You can run [`fuzzy` queries](/reference/query-languages/query-dsl/query-dsl-fuz ``` quikc~ brwn~ foks~ ``` -For these queries, the query string is [normalized](/reference/data-analysis/text-analysis/normalizers.md). If present, only certain filters from the analyzer are applied. For a list of applicable filters, see [*Normalizers*](/reference/data-analysis/text-analysis/normalizers.md). +For these queries, the query string is [normalized](/reference/text-analysis/normalizers.md). If present, only certain filters from the analyzer are applied. For a list of applicable filters, see [*Normalizers*](/reference/text-analysis/normalizers.md). The query uses the [Damerau-Levenshtein distance](https://en.wikipedia.org/wiki/Damerau-Levenshtein_distance) to find all terms with a maximum of two changes, where a change is the insertion, deletion or substitution of a single character, or transposition of two adjacent characters. @@ -606,7 +606,7 @@ NOTE: Additional top-level `multi_match` parameters may be available based on th ### Synonyms and the `query_string` query [query-string-synonyms] -The `query_string` query supports multi-terms synonym expansion with the [synonym_graph](/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md) token filter. When this filter is used, the parser creates a phrase query for each multi-terms synonyms. For example, the following synonym: `ny, new york` would produce: +The `query_string` query supports multi-terms synonym expansion with the [synonym_graph](/reference/text-analysis/analysis-synonym-graph-tokenfilter.md) token filter. When this filter is used, the parser creates a phrase query for each multi-terms synonyms. For example, the following synonym: `ny, new york` would produce: `(ny OR ("new york"))` diff --git a/docs/reference/query-languages/query-dsl/query-dsl-range-query.md b/docs/reference/query-languages/query-dsl/query-dsl-range-query.md index d7f676109c4f3..99825e4a2cb62 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-range-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-range-query.md @@ -51,7 +51,7 @@ GET /_search `format`      (Optional, string) Date format used to convert `date` values in the query. -     By default, {{es}} uses the [date `format`](/reference/elasticsearch/mapping-reference/mapping-date-format.md) provided in the ``'s +     By default, {{es}} uses the [date `format`](/reference/elasticsearch/mapping-reference/mapping-date-format.md) provided in the ``'s      mapping. This value overrides that mapping format.      For valid syntax, see [`format`](/reference/elasticsearch/mapping-reference/mapping-date-format.md). @@ -65,7 +65,7 @@ If a format or date value is incomplete, the range query replaces any missing co $$$querying-range-fields$$$ `relation` -     (Optional, string) Indicates how the range query matches values for `range` +     (Optional, string) Indicates how the range query matches values for `range`      fields. Valid values are:      `INTERSECTS` (Default) @@ -80,10 +80,10 @@ $$$querying-range-fields$$$ `time_zone` -     (Optional, string) [Coordinated Universal Time (UTC) offset](https://en.wikipedia.org/wiki/List_of_UTC_time_offsets) or [IANA time zone](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones) +     (Optional, string) [Coordinated Universal Time (UTC) offset](https://en.wikipedia.org/wiki/List_of_UTC_time_offsets) or [IANA time zone](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones)      used to convert `date` values in the query to UTC. -     Valid values are ISO 8601 UTC offsets, such as `+01:00` or -`08:00`, and IANA +     Valid values are ISO 8601 UTC offsets, such as `+01:00` or -`08:00`, and IANA      time zone IDs, such as `America/Los_Angeles`.      For an example query using the `time_zone` parameter, see @@ -99,14 +99,14 @@ However, the `time_zone` parameter does convert dates calculated using `now` and `boost` -     (Optional, float) Floating point number used to decrease or increase the +     (Optional, float) Floating point number used to decrease or increase the      [relevance scores](/reference/query-languages/query-dsl/query-filter-context.md#relevance-scores) of a query. Defaults to `1.0`. -     You can use the `boost` parameter to adjust relevance scores for searches +     You can use the `boost` parameter to adjust relevance scores for searches      containing two or more queries. -     Boost values are relative to the default value of `1.0`. A boost value between `0` -     and `1.0` decreases the relevance score. A value greater than `1.0` +     Boost values are relative to the default value of `1.0`. A boost value between `0` +     and `1.0` decreases the relevance score. A value greater than `1.0`      increases the relevance score. @@ -145,7 +145,7 @@ GET /_search #### Missing date components [missing-date-components] -For range queries and [date range](/reference/data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md) aggregations, {{es}} replaces missing date components with the following values. Missing year components are not replaced. +For range queries and [date range](/reference/aggregations/search-aggregations-bucket-daterange-aggregation.md) aggregations, {{es}} replaces missing date components with the following values. Missing year components are not replaced. ```text MONTH_OF_YEAR: 01 @@ -171,28 +171,28 @@ When no date format is specified and the range query is targeting a date field, `gt`      Rounds up to the first millisecond not covered by the rounded date. -     For example, `2014-11-18||/M` rounds up to `2014-12-01T00:00:00.000`, +     For example, `2014-11-18||/M` rounds up to `2014-12-01T00:00:00.000`,      excluding the entire month of November. `gte`      Rounds down to the first millisecond. -     For example, `2014-11-18||/M` rounds down to `2014-11-01T00:00:00.000`, +     For example, `2014-11-18||/M` rounds down to `2014-11-01T00:00:00.000`,      including the entire month. `lt`      Rounds down to the last millisecond before the rounded value. -     For example, `2014-11-18||/M` rounds down to `2014-10-31T23:59:59.999`, +     For example, `2014-11-18||/M` rounds down to `2014-10-31T23:59:59.999`,      excluding the entire month of November. `lte`      Rounds up to the latest millisecond in the rounding interval. -     For example, `2014-11-18||/M` rounds up to `2014-11-30T23:59:59.999`, +     For example, `2014-11-18||/M` rounds up to `2014-11-30T23:59:59.999`,      including the entire month. diff --git a/docs/reference/query-languages/query-dsl/query-dsl-script-query.md b/docs/reference/query-languages/query-dsl/query-dsl-script-query.md index 7b4d54dcd6a12..604d20cd3080c 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-script-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-script-query.md @@ -8,7 +8,7 @@ mapped_pages: ::::{note} -[Runtime fields](docs-content://manage-data/data-store/mapping/runtime-fields.md) provide a very similar feature that is more flexible. You write a script to create field values and they are available everywhere, such as [`fields`](/reference/elasticsearch/rest-apis/retrieve-selected-fields.md), [all queries](/reference/query-languages/querydsl.md), and [aggregations](/reference/data-analysis/aggregations/index.md). +[Runtime fields](docs-content://manage-data/data-store/mapping/runtime-fields.md) provide a very similar feature that is more flexible. You write a script to create field values and they are available everywhere, such as [`fields`](/reference/elasticsearch/rest-apis/retrieve-selected-fields.md), [all queries](/reference/query-languages/querydsl.md), and [aggregations](/reference/aggregations/index.md). :::: diff --git a/docs/reference/query-languages/query-dsl/query-dsl-simple-query-string-query.md b/docs/reference/query-languages/query-dsl/query-dsl-simple-query-string-query.md index 1da5008a629fd..618b555166c39 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-simple-query-string-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-simple-query-string-query.md @@ -60,7 +60,7 @@ There is a limit on the number of fields that can be queried at once. It is defi `analyze_wildcard` : (Optional, Boolean) If `true`, the query attempts to analyze wildcard terms in the query string. Defaults to `false`. Note that, in case of `true`, only queries that end with a `*` are fully analyzed. Queries that start with `*` or have it in the middle -are only [normalized](/reference/data-analysis/text-analysis/normalizers.md). +are only [normalized](/reference/text-analysis/normalizers.md). `analyzer` : (Optional, string) [Analyzer](docs-content://manage-data/data-store/text-analysis.md) used to convert text in the query string into tokens. Defaults to the [index-time analyzer](docs-content://manage-data/data-store/text-analysis/specify-an-analyzer.md#specify-index-time-analyzer) mapped for the `default_field`. If no analyzer is mapped, the index’s default analyzer is used. diff --git a/docs/reference/query-languages/query-dsl/query-dsl-term-query.md b/docs/reference/query-languages/query-dsl/query-dsl-term-query.md index 633a6b7551cb4..82ff33c708311 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-term-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-term-query.md @@ -65,10 +65,10 @@ GET /_search ### Avoid using the `term` query for `text` fields [avoid-term-query-text-fields] -By default, {{es}} changes the values of `text` fields during analysis. For example, the default [standard analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md) changes `text` field values as follows: +By default, {{es}} changes the values of `text` fields during analysis. For example, the default [standard analyzer](/reference/text-analysis/analysis-standard-analyzer.md) changes `text` field values as follows: * Removes most punctuation -* Divides the remaining content into individual words, called [tokens](/reference/data-analysis/text-analysis/tokenizer-reference.md) +* Divides the remaining content into individual words, called [tokens](/reference/text-analysis/tokenizer-reference.md) * Lowercases the tokens To better search `text` fields, the `match` query also analyzes your provided search term before performing a search. This means the `match` query can search `text` fields for analyzed tokens rather than an exact term. diff --git a/docs/reference/query-languages/query-dsl/query-dsl-wildcard-query.md b/docs/reference/query-languages/query-dsl/query-dsl-wildcard-query.md index b94ca4fc2e0f7..e4066f9d70544 100644 --- a/docs/reference/query-languages/query-dsl/query-dsl-wildcard-query.md +++ b/docs/reference/query-languages/query-dsl/query-dsl-wildcard-query.md @@ -72,7 +72,7 @@ GET /_search ## Notes [wildcard-query-notes] -Wildcard queries using `*` can be resource-intensive, particularly with leading wildcards. To improve performance, minimize their use and consider alternatives like the [n-gram tokenizer](/reference/data-analysis/text-analysis/analysis-ngram-tokenizer.md). While this allows for more efficient searching, it may increase index size. For better performance and accuracy, combine wildcard queries with other query types like [`match`](/reference/query-languages/query-dsl/query-dsl-match-query.md) or [`bool`](/reference/query-languages/query-dsl/query-dsl-bool-query.md) to first narrow down results. +Wildcard queries using `*` can be resource-intensive, particularly with leading wildcards. To improve performance, minimize their use and consider alternatives like the [n-gram tokenizer](/reference/text-analysis/analysis-ngram-tokenizer.md). While this allows for more efficient searching, it may increase index size. For better performance and accuracy, combine wildcard queries with other query types like [`match`](/reference/query-languages/query-dsl/query-dsl-match-query.md) or [`bool`](/reference/query-languages/query-dsl/query-dsl-bool-query.md) to first narrow down results. ### Allow expensive queries [_allow_expensive_queries_7] diff --git a/docs/reference/query-languages/query-dsl/query-filter-context.md b/docs/reference/query-languages/query-dsl/query-filter-context.md index 67c7c0883fc2c..894a4a67c5ee6 100644 --- a/docs/reference/query-languages/query-dsl/query-filter-context.md +++ b/docs/reference/query-languages/query-dsl/query-filter-context.md @@ -51,7 +51,7 @@ Filter context applies when a query clause is passed to a `filter` parameter, su * `filter` or `must_not` parameters in [`bool`](/reference/query-languages/query-dsl/query-dsl-bool-query.md) queries * `filter` parameter in [`constant_score`](/reference/query-languages/query-dsl/query-dsl-constant-score-query.md) queries -* [`filter`](/reference/data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md) aggregations +* [`filter`](/reference/aggregations/search-aggregations-bucket-filter-aggregation.md) aggregations Filters optimize query performance and efficiency, especially for structured data queries and when combined with full-text searches. diff --git a/docs/reference/query-languages/sql/sql-functions-aggs.md b/docs/reference/query-languages/sql/sql-functions-aggs.md index b096962f6ba8c..3d21d7215354f 100644 --- a/docs/reference/query-languages/sql/sql-functions-aggs.md +++ b/docs/reference/query-languages/sql/sql-functions-aggs.md @@ -557,8 +557,8 @@ PERCENTILE( 1. a numeric field. If this field contains only `null` values, the function returns `null`. Otherwise, the function ignores `null` values in this field. 2. a numeric expression (must be a constant and not based on a field). If `null`, the function returns `null`. -3. optional string literal for the [percentile algorithm](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Possible values: `tdigest` or `hdr`. Defaults to `tdigest`. -4. optional numeric literal that configures the [percentile algorithm](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Configures `compression` for `tdigest` or `number_of_significant_value_digits` for `hdr`. The default is the same as that of the backing algorithm. +3. optional string literal for the [percentile algorithm](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Possible values: `tdigest` or `hdr`. Defaults to `tdigest`. +4. optional numeric literal that configures the [percentile algorithm](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Configures `compression` for `tdigest` or `number_of_significant_value_digits` for `hdr`. The default is the same as that of the backing algorithm. **Output**: `double` numeric value @@ -628,8 +628,8 @@ PERCENTILE_RANK( 1. a numeric field. If this field contains only `null` values, the function returns `null`. Otherwise, the function ignores `null` values in this field. 2. a numeric expression (must be a constant and not based on a field). If `null`, the function returns `null`. -3. optional string literal for the [percentile algorithm](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Possible values: `tdigest` or `hdr`. Defaults to `tdigest`. -4. optional numeric literal that configures the [percentile algorithm](/reference/data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Configures `compression` for `tdigest` or `number_of_significant_value_digits` for `hdr`. The default is the same as that of the backing algorithm. +3. optional string literal for the [percentile algorithm](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Possible values: `tdigest` or `hdr`. Defaults to `tdigest`. +4. optional numeric literal that configures the [percentile algorithm](/reference/aggregations/search-aggregations-metrics-percentile-aggregation.md#search-aggregations-metrics-percentile-aggregation-approximation). Configures `compression` for `tdigest` or `number_of_significant_value_digits` for `hdr`. The default is the same as that of the backing algorithm. **Output**: `double` numeric value diff --git a/docs/reference/query-languages/sql/sql-functions-grouping.md b/docs/reference/query-languages/sql/sql-functions-grouping.md index 4467f020dd3d2..b5a79292a6fc5 100644 --- a/docs/reference/query-languages/sql/sql-functions-grouping.md +++ b/docs/reference/query-languages/sql/sql-functions-grouping.md @@ -36,7 +36,7 @@ bucket_key = Math.floor(value / interval) * interval ``` ::::{note} -The histogram in SQL does **NOT** return empty buckets for missing intervals as the traditional [histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md) and [date histogram](/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md). Such behavior does not fit conceptually in SQL which treats all missing values as `null`; as such the histogram places all missing values in the `null` group. +The histogram in SQL does **NOT** return empty buckets for missing intervals as the traditional [histogram](/reference/aggregations/search-aggregations-bucket-histogram-aggregation.md) and [date histogram](/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md). Such behavior does not fit conceptually in SQL which treats all missing values as `null`; as such the histogram places all missing values in the `null` group. :::: @@ -134,7 +134,7 @@ When the histogram in SQL is applied on **DATE** type instead of **DATETIME**, t ::::{important} -All intervals specified for a date/time HISTOGRAM will use a [fixed interval](/reference/data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) in their `date_histogram` aggregation definition, with the notable exceptions of `INTERVAL '1' YEAR`, `INTERVAL '1' MONTH` and `INTERVAL '1' DAY` where a calendar interval is used. The choice for a calendar interval was made for having a more intuitive result for YEAR, MONTH and DAY groupings. In the case of YEAR, for example, the calendar intervals consider a one year bucket as the one starting on January 1st that specific year, whereas a fixed interval one-year-bucket considers one year as a number of milliseconds (for example, `31536000000ms` corresponding to 365 days, 24 hours per day, 60 minutes per hour etc.). With fixed intervals, the day of February 5th, 2019 for example, belongs to a bucket that starts on December 20th, 2018 and {{es}} (and implicitly Elasticsearch SQL) would have returned the year 2018 for a date that’s actually in 2019. With calendar interval this behavior is more intuitive, having the day of February 5th, 2019 actually belonging to the 2019 year bucket. +All intervals specified for a date/time HISTOGRAM will use a [fixed interval](/reference/aggregations/search-aggregations-bucket-datehistogram-aggregation.md) in their `date_histogram` aggregation definition, with the notable exceptions of `INTERVAL '1' YEAR`, `INTERVAL '1' MONTH` and `INTERVAL '1' DAY` where a calendar interval is used. The choice for a calendar interval was made for having a more intuitive result for YEAR, MONTH and DAY groupings. In the case of YEAR, for example, the calendar intervals consider a one year bucket as the one starting on January 1st that specific year, whereas a fixed interval one-year-bucket considers one year as a number of milliseconds (for example, `31536000000ms` corresponding to 365 days, 24 hours per day, 60 minutes per hour etc.). With fixed intervals, the day of February 5th, 2019 for example, belongs to a bucket that starts on December 20th, 2018 and {{es}} (and implicitly Elasticsearch SQL) would have returned the year 2018 for a date that’s actually in 2019. With calendar interval this behavior is more intuitive, having the day of February 5th, 2019 actually belonging to the 2019 year bucket. :::: diff --git a/docs/reference/query-languages/toc.yml b/docs/reference/query-languages/toc.yml index 2e19f29c2ac61..deadd649b9129 100644 --- a/docs/reference/query-languages/toc.yml +++ b/docs/reference/query-languages/toc.yml @@ -1,139 +1,139 @@ toc: - - file: query-languages/index.md - - file: query-languages/querydsl.md + - file: index.md + - file: querydsl.md children: - - file: query-languages/query-dsl/query-filter-context.md - - file: query-languages/query-dsl/compound-queries.md + - file: query-dsl/query-filter-context.md + - file: query-dsl/compound-queries.md children: - - file: query-languages/query-dsl/query-dsl-bool-query.md - - file: query-languages/query-dsl/query-dsl-boosting-query.md - - file: query-languages/query-dsl/query-dsl-constant-score-query.md - - file: query-languages/query-dsl/query-dsl-dis-max-query.md - - file: query-languages/query-dsl/query-dsl-function-score-query.md - - file: query-languages/query-dsl/full-text-queries.md + - file: query-dsl/query-dsl-bool-query.md + - file: query-dsl/query-dsl-boosting-query.md + - file: query-dsl/query-dsl-constant-score-query.md + - file: query-dsl/query-dsl-dis-max-query.md + - file: query-dsl/query-dsl-function-score-query.md + - file: query-dsl/full-text-queries.md children: - - file: query-languages/query-dsl/query-dsl-intervals-query.md - - file: query-languages/query-dsl/query-dsl-match-query.md - - file: query-languages/query-dsl/query-dsl-match-bool-prefix-query.md - - file: query-languages/query-dsl/query-dsl-match-query-phrase.md - - file: query-languages/query-dsl/query-dsl-match-query-phrase-prefix.md - - file: query-languages/query-dsl/query-dsl-combined-fields-query.md - - file: query-languages/query-dsl/query-dsl-multi-match-query.md - - file: query-languages/query-dsl/query-dsl-query-string-query.md - - file: query-languages/query-dsl/query-dsl-simple-query-string-query.md - - file: query-languages/query-dsl/geo-queries.md + - file: query-dsl/query-dsl-intervals-query.md + - file: query-dsl/query-dsl-match-query.md + - file: query-dsl/query-dsl-match-bool-prefix-query.md + - file: query-dsl/query-dsl-match-query-phrase.md + - file: query-dsl/query-dsl-match-query-phrase-prefix.md + - file: query-dsl/query-dsl-combined-fields-query.md + - file: query-dsl/query-dsl-multi-match-query.md + - file: query-dsl/query-dsl-query-string-query.md + - file: query-dsl/query-dsl-simple-query-string-query.md + - file: query-dsl/geo-queries.md children: - - file: query-languages/query-dsl/query-dsl-geo-bounding-box-query.md - - file: query-languages/query-dsl/query-dsl-geo-distance-query.md - - file: query-languages/query-dsl/query-dsl-geo-grid-query.md - - file: query-languages/query-dsl/query-dsl-geo-polygon-query.md - - file: query-languages/query-dsl/query-dsl-geo-shape-query.md - - file: query-languages/query-dsl/shape-queries.md + - file: query-dsl/query-dsl-geo-bounding-box-query.md + - file: query-dsl/query-dsl-geo-distance-query.md + - file: query-dsl/query-dsl-geo-grid-query.md + - file: query-dsl/query-dsl-geo-polygon-query.md + - file: query-dsl/query-dsl-geo-shape-query.md + - file: query-dsl/shape-queries.md children: - - file: query-languages/query-dsl/query-dsl-shape-query.md - - file: query-languages/query-dsl/joining-queries.md + - file: query-dsl/query-dsl-shape-query.md + - file: query-dsl/joining-queries.md children: - - file: query-languages/query-dsl/query-dsl-nested-query.md - - file: query-languages/query-dsl/query-dsl-has-child-query.md - - file: query-languages/query-dsl/query-dsl-has-parent-query.md - - file: query-languages/query-dsl/query-dsl-parent-id-query.md - - file: query-languages/query-dsl/query-dsl-match-all-query.md - - file: query-languages/query-dsl/span-queries.md + - file: query-dsl/query-dsl-nested-query.md + - file: query-dsl/query-dsl-has-child-query.md + - file: query-dsl/query-dsl-has-parent-query.md + - file: query-dsl/query-dsl-parent-id-query.md + - file: query-dsl/query-dsl-match-all-query.md + - file: query-dsl/span-queries.md children: - - file: query-languages/query-dsl/query-dsl-span-containing-query.md - - file: query-languages/query-dsl/query-dsl-span-field-masking-query.md - - file: query-languages/query-dsl/query-dsl-span-first-query.md - - file: query-languages/query-dsl/query-dsl-span-multi-term-query.md - - file: query-languages/query-dsl/query-dsl-span-near-query.md - - file: query-languages/query-dsl/query-dsl-span-not-query.md - - file: query-languages/query-dsl/query-dsl-span-query.md - - file: query-languages/query-dsl/query-dsl-span-term-query.md - - file: query-languages/query-dsl/query-dsl-span-within-query.md - - file: query-languages/query-dsl/vector-queries.md + - file: query-dsl/query-dsl-span-containing-query.md + - file: query-dsl/query-dsl-span-field-masking-query.md + - file: query-dsl/query-dsl-span-first-query.md + - file: query-dsl/query-dsl-span-multi-term-query.md + - file: query-dsl/query-dsl-span-near-query.md + - file: query-dsl/query-dsl-span-not-query.md + - file: query-dsl/query-dsl-span-query.md + - file: query-dsl/query-dsl-span-term-query.md + - file: query-dsl/query-dsl-span-within-query.md + - file: query-dsl/vector-queries.md children: - - file: query-languages/query-dsl/query-dsl-knn-query.md - - file: query-languages/query-dsl/query-dsl-sparse-vector-query.md - - file: query-languages/query-dsl/query-dsl-semantic-query.md - - file: query-languages/query-dsl/query-dsl-text-expansion-query.md - - file: query-languages/query-dsl/query-dsl-weighted-tokens-query.md - - file: query-languages/query-dsl/specialized-queries.md + - file: query-dsl/query-dsl-knn-query.md + - file: query-dsl/query-dsl-sparse-vector-query.md + - file: query-dsl/query-dsl-semantic-query.md + - file: query-dsl/query-dsl-text-expansion-query.md + - file: query-dsl/query-dsl-weighted-tokens-query.md + - file: query-dsl/specialized-queries.md children: - - file: query-languages/query-dsl/query-dsl-distance-feature-query.md - - file: query-languages/query-dsl/query-dsl-mlt-query.md - - file: query-languages/query-dsl/query-dsl-percolate-query.md - - file: query-languages/query-dsl/query-dsl-rank-feature-query.md - - file: query-languages/query-dsl/query-dsl-script-query.md - - file: query-languages/query-dsl/query-dsl-script-score-query.md - - file: query-languages/query-dsl/query-dsl-wrapper-query.md - - file: query-languages/query-dsl/query-dsl-pinned-query.md - - file: query-languages/query-dsl/query-dsl-rule-query.md - - file: query-languages/query-dsl/term-level-queries.md + - file: query-dsl/query-dsl-distance-feature-query.md + - file: query-dsl/query-dsl-mlt-query.md + - file: query-dsl/query-dsl-percolate-query.md + - file: query-dsl/query-dsl-rank-feature-query.md + - file: query-dsl/query-dsl-script-query.md + - file: query-dsl/query-dsl-script-score-query.md + - file: query-dsl/query-dsl-wrapper-query.md + - file: query-dsl/query-dsl-pinned-query.md + - file: query-dsl/query-dsl-rule-query.md + - file: query-dsl/term-level-queries.md children: - - file: query-languages/query-dsl/query-dsl-exists-query.md - - file: query-languages/query-dsl/query-dsl-fuzzy-query.md - - file: query-languages/query-dsl/query-dsl-ids-query.md - - file: query-languages/query-dsl/query-dsl-prefix-query.md - - file: query-languages/query-dsl/query-dsl-range-query.md - - file: query-languages/query-dsl/query-dsl-regexp-query.md - - file: query-languages/query-dsl/query-dsl-term-query.md - - file: query-languages/query-dsl/query-dsl-terms-query.md - - file: query-languages/query-dsl/query-dsl-terms-set-query.md - - file: query-languages/query-dsl/query-dsl-wildcard-query.md - - file: query-languages/query-dsl/query-dsl-minimum-should-match.md - - file: query-languages/query-dsl/query-dsl-multi-term-rewrite.md - - file: query-languages/query-dsl/regexp-syntax.md - - file: query-languages/esql.md + - file: query-dsl/query-dsl-exists-query.md + - file: query-dsl/query-dsl-fuzzy-query.md + - file: query-dsl/query-dsl-ids-query.md + - file: query-dsl/query-dsl-prefix-query.md + - file: query-dsl/query-dsl-range-query.md + - file: query-dsl/query-dsl-regexp-query.md + - file: query-dsl/query-dsl-term-query.md + - file: query-dsl/query-dsl-terms-query.md + - file: query-dsl/query-dsl-terms-set-query.md + - file: query-dsl/query-dsl-wildcard-query.md + - file: query-dsl/query-dsl-minimum-should-match.md + - file: query-dsl/query-dsl-multi-term-rewrite.md + - file: query-dsl/regexp-syntax.md + - file: esql.md children: - - file: query-languages/esql/esql-syntax.md - - file: query-languages/esql/esql-commands.md - - file: query-languages/esql/esql-functions-operators.md - - file: query-languages/esql/esql-metadata-fields.md - - file: query-languages/esql/esql-multivalued-fields.md - - file: query-languages/esql/esql-process-data-with-dissect-grok.md - - file: query-languages/esql/esql-enrich-data.md - - file: query-languages/esql/esql-lookup-join.md - - file: query-languages/esql/esql-implicit-casting.md - - file: query-languages/esql/esql-time-spans.md - - file: query-languages/esql/limitations.md - - file: query-languages/esql/esql-examples.md - - file: query-languages/sql.md + - file: esql/esql-syntax.md + - file: esql/esql-commands.md + - file: esql/esql-functions-operators.md + - file: esql/esql-metadata-fields.md + - file: esql/esql-multivalued-fields.md + - file: esql/esql-process-data-with-dissect-grok.md + - file: esql/esql-enrich-data.md + - file: esql/esql-lookup-join.md + - file: esql/esql-implicit-casting.md + - file: esql/esql-time-spans.md + - file: esql/limitations.md + - file: esql/esql-examples.md + - file: sql.md children: - - file: query-languages/sql/sql-spec.md + - file: sql/sql-spec.md children: - - file: query-languages/sql/sql-lexical-structure.md - - file: query-languages/sql/sql-commands.md - - file: query-languages/sql/sql-syntax-describe-table.md - - file: query-languages/sql/sql-syntax-select.md - - file: query-languages/sql/sql-syntax-show-catalogs.md - - file: query-languages/sql/sql-syntax-show-columns.md - - file: query-languages/sql/sql-syntax-show-functions.md - - file: query-languages/sql/sql-syntax-show-tables.md - - file: query-languages/sql/sql-data-types.md - - file: query-languages/sql/sql-index-patterns.md - - file: query-languages/sql/sql-index-frozen.md - - file: query-languages/sql/sql-functions.md + - file: sql/sql-lexical-structure.md + - file: sql/sql-commands.md + - file: sql/sql-syntax-describe-table.md + - file: sql/sql-syntax-select.md + - file: sql/sql-syntax-show-catalogs.md + - file: sql/sql-syntax-show-columns.md + - file: sql/sql-syntax-show-functions.md + - file: sql/sql-syntax-show-tables.md + - file: sql/sql-data-types.md + - file: sql/sql-index-patterns.md + - file: sql/sql-index-frozen.md + - file: sql/sql-functions.md children: - - file: query-languages/sql/sql-operators.md - - file: query-languages/sql/sql-operators-logical.md - - file: query-languages/sql/sql-operators-math.md - - file: query-languages/sql/sql-operators-cast.md - - file: query-languages/sql/sql-like-rlike-operators.md - - file: query-languages/sql/sql-functions-aggs.md - - file: query-languages/sql/sql-functions-grouping.md - - file: query-languages/sql/sql-functions-datetime.md - - file: query-languages/sql/sql-functions-search.md - - file: query-languages/sql/sql-functions-math.md - - file: query-languages/sql/sql-functions-string.md - - file: query-languages/sql/sql-functions-type-conversion.md - - file: query-languages/sql/sql-functions-geo.md - - file: query-languages/sql/sql-functions-conditional.md - - file: query-languages/sql/sql-functions-system.md - - file: query-languages/sql/sql-syntax-reserved.md - - file: query-languages/sql/sql-limitations.md - - file: query-languages/eql/eql.md + - file: sql/sql-operators.md + - file: sql/sql-operators-logical.md + - file: sql/sql-operators-math.md + - file: sql/sql-operators-cast.md + - file: sql/sql-like-rlike-operators.md + - file: sql/sql-functions-aggs.md + - file: sql/sql-functions-grouping.md + - file: sql/sql-functions-datetime.md + - file: sql/sql-functions-search.md + - file: sql/sql-functions-math.md + - file: sql/sql-functions-string.md + - file: sql/sql-functions-type-conversion.md + - file: sql/sql-functions-geo.md + - file: sql/sql-functions-conditional.md + - file: sql/sql-functions-system.md + - file: sql/sql-syntax-reserved.md + - file: sql/sql-limitations.md + - file: eql.md children: - - file: query-languages/eql/eql-syntax.md - - file: query-languages/eql/eql-function-ref.md - - file: query-languages/eql/eql-pipe-ref.md - - file: query-languages/eql/eql-ex-threat-detection.md - - file: query-languages/kql.md + - file: eql/eql-syntax.md + - file: eql/eql-function-ref.md + - file: eql/eql-pipe-ref.md + - file: eql/eql-ex-threat-detection.md + - file: kql.md diff --git a/docs/reference/scripting-languages/painless/painless-bucket-script-agg-context.md b/docs/reference/scripting-languages/painless/painless-bucket-script-agg-context.md index 069412257bdd9..2e7712aed928f 100644 --- a/docs/reference/scripting-languages/painless/painless-bucket-script-agg-context.md +++ b/docs/reference/scripting-languages/painless/painless-bucket-script-agg-context.md @@ -5,7 +5,7 @@ mapped_pages: # Bucket script aggregation context [painless-bucket-script-agg-context] -Use a Painless script in an [`bucket_script` pipeline aggregation](/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md) to calculate a value as a result in a bucket. +Use a Painless script in an [`bucket_script` pipeline aggregation](/reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md) to calculate a value as a result in a bucket. ## Variables [_variables] diff --git a/docs/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md b/docs/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md index 441be4d208832..f7b74c3811c81 100644 --- a/docs/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md +++ b/docs/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md @@ -5,7 +5,7 @@ mapped_pages: # Bucket selector aggregation context [painless-bucket-selector-agg-context] -Use a Painless script in an [`bucket_selector` aggregation](/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md) to determine if a bucket should be retained or filtered out. +Use a Painless script in an [`bucket_selector` aggregation](/reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md) to determine if a bucket should be retained or filtered out. ## Variables [_variables_2] diff --git a/docs/reference/scripting-languages/painless/painless-contexts.md b/docs/reference/scripting-languages/painless/painless-contexts.md index 4475b7bbea20c..01b61d7746621 100644 --- a/docs/reference/scripting-languages/painless/painless-contexts.md +++ b/docs/reference/scripting-languages/painless/painless-contexts.md @@ -12,7 +12,7 @@ Painless scripts typically run within one of the contexts in the following table | Name | Painless Documentation | Elasticsearch Documentation | | --- | --- | --- | | Runtime field | [Painless Documentation](/reference/scripting-languages/painless/painless-runtime-fields-context.md) | [Elasticsearch Documentation](docs-content://manage-data/data-store/mapping/runtime-fields.md) | -| Ingest processor | [Painless Documentation](/reference/scripting-languages/painless/painless-ingest-processor-context.md) | [Elasticsearch Documentation](/reference/ingestion-tools/enrich-processor/script-processor.md) | +| Ingest processor | [Painless Documentation](/reference/scripting-languages/painless/painless-ingest-processor-context.md) | [Elasticsearch Documentation](/reference/enrich-processor/script-processor.md) | | Update | [Painless Documentation](/reference/scripting-languages/painless/painless-update-context.md) | [Elasticsearch Documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-update) | | Update by query | [Painless Documentation](/reference/scripting-languages/painless/painless-update-by-query-context.md) | [Elasticsearch Documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-update-by-query) | | Reindex | [Painless Documentation](/reference/scripting-languages/painless/painless-reindex-context.md) | [Elasticsearch Documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-reindex) | @@ -23,12 +23,12 @@ Painless scripts typically run within one of the contexts in the following table | Field | [Painless Documentation](/reference/scripting-languages/painless/painless-field-context.md) | [Elasticsearch Documentation](/reference/elasticsearch/rest-apis/retrieve-selected-fields.md#script-fields) | | Filter | [Painless Documentation](/reference/scripting-languages/painless/painless-filter-context.md) | [Elasticsearch Documentation](/reference/query-languages/query-dsl/query-dsl-script-query.md) | | Minimum should match | [Painless Documentation](/reference/scripting-languages/painless/painless-min-should-match-context.md) | [Elasticsearch Documentation](/reference/query-languages/query-dsl/query-dsl-terms-set-query.md) | -| Metric aggregation initialization | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-init-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | -| Metric aggregation map | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | -| Metric aggregation combine | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-combine-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | -| Metric aggregation reduce | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | -| Bucket script aggregation | [Painless Documentation](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md) | -| Bucket selector aggregation | [Painless Documentation](/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md) | [Elasticsearch Documentation](/reference/data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md) | +| Metric aggregation initialization | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-init-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | +| Metric aggregation map | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | +| Metric aggregation combine | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-combine-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | +| Metric aggregation reduce | [Painless Documentation](/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) | +| Bucket script aggregation | [Painless Documentation](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md) | +| Bucket selector aggregation | [Painless Documentation](/reference/scripting-languages/painless/painless-bucket-selector-agg-context.md) | [Elasticsearch Documentation](/reference/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md) | | Watcher condition | [Painless Documentation](/reference/scripting-languages/painless/painless-watcher-condition-context.md) | [Elasticsearch Documentation](docs-content://explore-analyze/alerts-cases/watcher/condition-script.md) | | Watcher transform | [Painless Documentation](/reference/scripting-languages/painless/painless-watcher-transform-context.md) | [Elasticsearch Documentation](docs-content://explore-analyze/alerts-cases/watcher/transform-script.md) | diff --git a/docs/reference/scripting-languages/painless/painless-ingest-processor-context.md b/docs/reference/scripting-languages/painless/painless-ingest-processor-context.md index 57b374cbf536f..a594c8467619f 100644 --- a/docs/reference/scripting-languages/painless/painless-ingest-processor-context.md +++ b/docs/reference/scripting-languages/painless/painless-ingest-processor-context.md @@ -5,7 +5,7 @@ mapped_pages: # Ingest processor context [painless-ingest-processor-context] -Use a Painless script in an [ingest processor](/reference/ingestion-tools/enrich-processor/script-processor.md) to modify documents upon insertion. +Use a Painless script in an [ingest processor](/reference/enrich-processor/script-processor.md) to modify documents upon insertion. **Variables** diff --git a/docs/reference/scripting-languages/painless/painless-metric-agg-combine-context.md b/docs/reference/scripting-languages/painless/painless-metric-agg-combine-context.md index ee9387a6ed7e3..a6edab5dddc08 100644 --- a/docs/reference/scripting-languages/painless/painless-metric-agg-combine-context.md +++ b/docs/reference/scripting-languages/painless/painless-metric-agg-combine-context.md @@ -5,7 +5,7 @@ mapped_pages: # Metric aggregation combine context [painless-metric-agg-combine-context] -Use a Painless script to [combine](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. A combine script is run once per shard following a [map script](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) and is optional as part of a full metric aggregation. +Use a Painless script to [combine](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. A combine script is run once per shard following a [map script](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) and is optional as part of a full metric aggregation. **Variables** diff --git a/docs/reference/scripting-languages/painless/painless-metric-agg-init-context.md b/docs/reference/scripting-languages/painless/painless-metric-agg-init-context.md index fa2aa1582aab9..4c2b0007f0e27 100644 --- a/docs/reference/scripting-languages/painless/painless-metric-agg-init-context.md +++ b/docs/reference/scripting-languages/painless/painless-metric-agg-init-context.md @@ -5,7 +5,7 @@ mapped_pages: # Metric aggregation initialization context [painless-metric-agg-init-context] -Use a Painless script to [initialize](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. An initialization script is run prior to document collection once per shard and is optional as part of the full metric aggregation. +Use a Painless script to [initialize](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. An initialization script is run prior to document collection once per shard and is optional as part of the full metric aggregation. **Variables** diff --git a/docs/reference/scripting-languages/painless/painless-metric-agg-map-context.md b/docs/reference/scripting-languages/painless/painless-metric-agg-map-context.md index 7ae377db6bb9a..9c706189b88f3 100644 --- a/docs/reference/scripting-languages/painless/painless-metric-agg-map-context.md +++ b/docs/reference/scripting-languages/painless/painless-metric-agg-map-context.md @@ -5,7 +5,7 @@ mapped_pages: # Metric aggregation map context [painless-metric-agg-map-context] -Use a Painless script to [map](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. A map script is run once per collected document following an optional [initialization script](/reference/scripting-languages/painless/painless-metric-agg-init-context.md) and is required as part of a full metric aggregation. +Use a Painless script to [map](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values for use in a scripted metric aggregation. A map script is run once per collected document following an optional [initialization script](/reference/scripting-languages/painless/painless-metric-agg-init-context.md) and is required as part of a full metric aggregation. **Variables** diff --git a/docs/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md b/docs/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md index 6d2eb55efc8d0..f9148846329d1 100644 --- a/docs/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md +++ b/docs/reference/scripting-languages/painless/painless-metric-agg-reduce-context.md @@ -5,7 +5,7 @@ mapped_pages: # Metric aggregation reduce context [painless-metric-agg-reduce-context] -Use a Painless script to [reduce](/reference/data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values to produce the result of a scripted metric aggregation. A reduce script is run once on the coordinating node following a [combine script](/reference/scripting-languages/painless/painless-metric-agg-combine-context.md) (or a [map script](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) if no combine script is specified) and is optional as part of a full metric aggregation. +Use a Painless script to [reduce](/reference/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md) values to produce the result of a scripted metric aggregation. A reduce script is run once on the coordinating node following a [combine script](/reference/scripting-languages/painless/painless-metric-agg-combine-context.md) (or a [map script](/reference/scripting-languages/painless/painless-metric-agg-map-context.md) if no combine script is specified) and is optional as part of a full metric aggregation. **Variables** diff --git a/docs/reference/scripting-languages/painless/painless-runtime-fields-context.md b/docs/reference/scripting-languages/painless/painless-runtime-fields-context.md index c04320aa27d81..5f963ffe61fcd 100644 --- a/docs/reference/scripting-languages/painless/painless-runtime-fields-context.md +++ b/docs/reference/scripting-languages/painless/painless-runtime-fields-context.md @@ -51,7 +51,7 @@ $$$runtime-emit-method$$$ `grok` -: Defines a [grok pattern](/reference/ingestion-tools/enrich-processor/grok-processor.md) to extract structured fields out of a single text field within a document. A grok pattern is like a regular expression that supports aliased expressions that can be reused. See [Define a runtime field with a grok pattern](docs-content://manage-data/data-store/mapping/explore-data-with-runtime-fields.md#runtime-examples-grok). +: Defines a [grok pattern](/reference/enrich-processor/grok-processor.md) to extract structured fields out of a single text field within a document. A grok pattern is like a regular expression that supports aliased expressions that can be reused. See [Define a runtime field with a grok pattern](docs-content://manage-data/data-store/mapping/explore-data-with-runtime-fields.md#runtime-examples-grok). ::::{dropdown} Properties of `grok` `extract` @@ -61,7 +61,7 @@ $$$runtime-emit-method$$$ `dissect` -: Defines a [dissect pattern](/reference/ingestion-tools/enrich-processor/dissect-processor.md). Dissect operates much like grok, but does not accept regular expressions. See [Define a runtime field with a dissect pattern](docs-content://manage-data/data-store/mapping/explore-data-with-runtime-fields.md#runtime-examples-dissect). +: Defines a [dissect pattern](/reference/enrich-processor/dissect-processor.md). Dissect operates much like grok, but does not accept regular expressions. See [Define a runtime field with a dissect pattern](docs-content://manage-data/data-store/mapping/explore-data-with-runtime-fields.md#runtime-examples-dissect). ::::{dropdown} Properties of `dissect` `extract` diff --git a/docs/reference/scripting-languages/painless/using-datetime-in-painless.md b/docs/reference/scripting-languages/painless/using-datetime-in-painless.md index cbff86cf6dc3b..5b4e7a947f9d6 100644 --- a/docs/reference/scripting-languages/painless/using-datetime-in-painless.md +++ b/docs/reference/scripting-languages/painless/using-datetime-in-painless.md @@ -707,7 +707,7 @@ Run the following curl commands to load the data necessary for the context examp ### Day-of-the-Week Bucket Aggregation Example [_day_of_the_week_bucket_aggregation_example] -The following example uses a [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-script) as part of the [bucket script aggregation context](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) to display the number of messages from each day-of-the-week. +The following example uses a [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-script) as part of the [bucket script aggregation context](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) to display the number of messages from each day-of-the-week. ```console GET /messages/_search?pretty=true @@ -725,7 +725,7 @@ GET /messages/_search?pretty=true ### Morning/Evening Bucket Aggregation Example [_morningevening_bucket_aggregation_example] -The following example uses a [terms aggregation](/reference/data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-script) as part of the [bucket script aggregation context](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) to display the number of messages received in the morning versus the evening. +The following example uses a [terms aggregation](/reference/aggregations/search-aggregations-bucket-terms-aggregation.md#search-aggregations-bucket-terms-aggregation-script) as part of the [bucket script aggregation context](/reference/scripting-languages/painless/painless-bucket-script-agg-context.md) to display the number of messages received in the morning versus the evening. ```console GET /messages/_search?pretty=true diff --git a/docs/reference/scripting-languages/painless/using-ingest-processors-in-painless.md b/docs/reference/scripting-languages/painless/using-ingest-processors-in-painless.md index 0ebc017248c74..e82eba87b6fb4 100644 --- a/docs/reference/scripting-languages/painless/using-ingest-processors-in-painless.md +++ b/docs/reference/scripting-languages/painless/using-ingest-processors-in-painless.md @@ -5,7 +5,7 @@ mapped_pages: # Using ingest processors in Painless [painless-ingest] -Some [ingest processors](/reference/ingestion-tools/enrich-processor/index.md) expose behavior through Painless methods that can be called in Painless scripts that execute in ingest pipelines. +Some [ingest processors](/reference/enrich-processor/index.md) expose behavior through Painless methods that can be called in Painless scripts that execute in ingest pipelines. ## Method usage [_method_usage] @@ -42,7 +42,7 @@ POST /_ingest/pipeline/_simulate?verbose ### Byte conversion [_byte_conversion] -Use the [bytes processor](/reference/ingestion-tools/enrich-processor/bytes-processor.md) to return the number of bytes in the human-readable byte value supplied in the `value` parameter. +Use the [bytes processor](/reference/enrich-processor/bytes-processor.md) to return the number of bytes in the human-readable byte value supplied in the `value` parameter. ```painless long bytes(String value); @@ -51,7 +51,7 @@ long bytes(String value); ### Lowercase conversion [_lowercase_conversion] -Use the [lowercase processor](/reference/ingestion-tools/enrich-processor/lowercase-processor.md) to convert the supplied string in the `value` parameter to its lowercase equivalent. +Use the [lowercase processor](/reference/enrich-processor/lowercase-processor.md) to convert the supplied string in the `value` parameter to its lowercase equivalent. ```painless String lowercase(String value); @@ -60,7 +60,7 @@ String lowercase(String value); ### Uppercase conversion [_uppercase_conversion] -Use the [uppercase processor](/reference/ingestion-tools/enrich-processor/uppercase-processor.md) to convert the supplied string in the `value` parameter to its uppercase equivalent. +Use the [uppercase processor](/reference/enrich-processor/uppercase-processor.md) to convert the supplied string in the `value` parameter to its uppercase equivalent. ```painless String uppercase(String value); @@ -69,7 +69,7 @@ String uppercase(String value); ### JSON parsing [_json_parsing] -Use the [JSON processor](/reference/ingestion-tools/enrich-processor/json-processor.md) to convert JSON strings to structured JSON objects. The first `json` method accepts a map and a key. The processor converts the JSON string in the map as specified by the `key` parameter to structured JSON content. That content is added directly to the `map` object. +Use the [JSON processor](/reference/enrich-processor/json-processor.md) to convert JSON strings to structured JSON objects. The first `json` method accepts a map and a key. The processor converts the JSON string in the map as specified by the `key` parameter to structured JSON content. That content is added directly to the `map` object. The second `json` method accepts a JSON string in the `value` parameter and returns a structured JSON object. @@ -88,7 +88,7 @@ ctx.structuredJson = json; ### URL decoding [_url_decoding] -Use the [URL decode processor](/reference/ingestion-tools/enrich-processor/urldecode-processor.md) to URL-decode the string supplied in the `value` parameter. +Use the [URL decode processor](/reference/enrich-processor/urldecode-processor.md) to URL-decode the string supplied in the `value` parameter. ```painless String urlDecode(String value); @@ -97,7 +97,7 @@ String urlDecode(String value); ### URI decomposition [_uri_decomposition] -Use the [URI parts processor](/reference/ingestion-tools/enrich-processor/uri-parts-processor.md) to decompose the URI string supplied in the `value` parameter. Returns a map of key-value pairs in which the key is the name of the URI component such as `domain` or `path` and the value is the corresponding value for that component. +Use the [URI parts processor](/reference/enrich-processor/uri-parts-processor.md) to decompose the URI string supplied in the `value` parameter. Returns a map of key-value pairs in which the key is the name of the URI component such as `domain` or `path` and the value is the corresponding value for that component. ```painless String uriParts(String value); @@ -106,7 +106,7 @@ String uriParts(String value); ### Network community ID [_network_community_id] -Use the [community ID processor](/reference/ingestion-tools/enrich-processor/community-id-processor.md) to compute the network community ID for network flow data. +Use the [community ID processor](/reference/enrich-processor/community-id-processor.md) to compute the network community ID for network flow data. ```painless String communityId(String sourceIpAddrString, String destIpAddrString, Object ianaNumber, Object transport, Object sourcePort, Object destinationPort, Object icmpType, Object icmpCode, int seed) diff --git a/docs/reference/scripting-languages/toc.yml b/docs/reference/scripting-languages/toc.yml index c42f5e30b389e..5fa5f6e78ca66 100644 --- a/docs/reference/scripting-languages/toc.yml +++ b/docs/reference/scripting-languages/toc.yml @@ -1,56 +1,55 @@ toc: - - file: scripting-languages/index.md - # - file: scripting-languages/reference/painless.md - - file: scripting-languages/painless/painless.md + - file: index.md + - file: painless/painless.md children: - - file: scripting-languages/painless/brief-painless-walkthrough.md - - file: scripting-languages/painless/use-painless-scripts-in-runtime-fields.md - - file: scripting-languages/painless/using-datetime-in-painless.md - - file: scripting-languages/painless/how-painless-dispatches-function.md - - file: scripting-languages/painless/painless-debugging.md - - file: scripting-languages/painless/painless-api-examples.md - - file: scripting-languages/painless/using-ingest-processors-in-painless.md - - file: scripting-languages/painless/painless-language-specification.md + - file: painless/brief-painless-walkthrough.md + - file: painless/use-painless-scripts-in-runtime-fields.md + - file: painless/using-datetime-in-painless.md + - file: painless/how-painless-dispatches-function.md + - file: painless/painless-debugging.md + - file: painless/painless-api-examples.md + - file: painless/using-ingest-processors-in-painless.md + - file: painless/painless-language-specification.md children: - - file: scripting-languages/painless/painless-comments.md - - file: scripting-languages/painless/painless-keywords.md - - file: scripting-languages/painless/painless-literals.md - - file: scripting-languages/painless/painless-identifiers.md - - file: scripting-languages/painless/painless-variables.md - - file: scripting-languages/painless/painless-types.md - - file: scripting-languages/painless/painless-casting.md - - file: scripting-languages/painless/painless-operators.md - - file: scripting-languages/painless/painless-operators-general.md - - file: scripting-languages/painless/painless-operators-numeric.md - - file: scripting-languages/painless/painless-operators-boolean.md - - file: scripting-languages/painless/painless-operators-reference.md - - file: scripting-languages/painless/painless-operators-array.md - - file: scripting-languages/painless/painless-statements.md - - file: scripting-languages/painless/painless-scripts.md - - file: scripting-languages/painless/painless-functions.md - - file: scripting-languages/painless/painless-lambdas.md - - file: scripting-languages/painless/painless-regexes.md - - file: scripting-languages/painless/painless-contexts.md + - file: painless/painless-comments.md + - file: painless/painless-keywords.md + - file: painless/painless-literals.md + - file: painless/painless-identifiers.md + - file: painless/painless-variables.md + - file: painless/painless-types.md + - file: painless/painless-casting.md + - file: painless/painless-operators.md + - file: painless/painless-operators-general.md + - file: painless/painless-operators-numeric.md + - file: painless/painless-operators-boolean.md + - file: painless/painless-operators-reference.md + - file: painless/painless-operators-array.md + - file: painless/painless-statements.md + - file: painless/painless-scripts.md + - file: painless/painless-functions.md + - file: painless/painless-lambdas.md + - file: painless/painless-regexes.md + - file: painless/painless-contexts.md children: - - file: scripting-languages/painless/painless-context-examples.md - - file: scripting-languages/painless/painless-runtime-fields-context.md - - file: scripting-languages/painless/painless-ingest-processor-context.md - - file: scripting-languages/painless/painless-update-context.md - - file: scripting-languages/painless/painless-update-by-query-context.md - - file: scripting-languages/painless/painless-reindex-context.md - - file: scripting-languages/painless/painless-sort-context.md - - file: scripting-languages/painless/painless-similarity-context.md - - file: scripting-languages/painless/painless-weight-context.md - - file: scripting-languages/painless/painless-score-context.md - - file: scripting-languages/painless/painless-field-context.md - - file: scripting-languages/painless/painless-filter-context.md - - file: scripting-languages/painless/painless-min-should-match-context.md - - file: scripting-languages/painless/painless-metric-agg-init-context.md - - file: scripting-languages/painless/painless-metric-agg-map-context.md - - file: scripting-languages/painless/painless-metric-agg-combine-context.md - - file: scripting-languages/painless/painless-metric-agg-reduce-context.md - - file: scripting-languages/painless/painless-bucket-script-agg-context.md - - file: scripting-languages/painless/painless-bucket-selector-agg-context.md - - file: scripting-languages/painless/painless-analysis-predicate-context.md - - file: scripting-languages/painless/painless-watcher-condition-context.md - - file: scripting-languages/painless/painless-watcher-transform-context.md \ No newline at end of file + - file: painless/painless-context-examples.md + - file: painless/painless-runtime-fields-context.md + - file: painless/painless-ingest-processor-context.md + - file: painless/painless-update-context.md + - file: painless/painless-update-by-query-context.md + - file: painless/painless-reindex-context.md + - file: painless/painless-sort-context.md + - file: painless/painless-similarity-context.md + - file: painless/painless-weight-context.md + - file: painless/painless-score-context.md + - file: painless/painless-field-context.md + - file: painless/painless-filter-context.md + - file: painless/painless-min-should-match-context.md + - file: painless/painless-metric-agg-init-context.md + - file: painless/painless-metric-agg-map-context.md + - file: painless/painless-metric-agg-combine-context.md + - file: painless/painless-metric-agg-reduce-context.md + - file: painless/painless-bucket-script-agg-context.md + - file: painless/painless-bucket-selector-agg-context.md + - file: painless/painless-analysis-predicate-context.md + - file: painless/painless-watcher-condition-context.md + - file: painless/painless-watcher-transform-context.md \ No newline at end of file diff --git a/docs/reference/ingestion-tools/search-connectors/api-tutorial.md b/docs/reference/search-connectors/api-tutorial.md similarity index 98% rename from docs/reference/ingestion-tools/search-connectors/api-tutorial.md rename to docs/reference/search-connectors/api-tutorial.md index 2130a16404d5b..e6377435b76c6 100644 --- a/docs/reference/ingestion-tools/search-connectors/api-tutorial.md +++ b/docs/reference/search-connectors/api-tutorial.md @@ -2,7 +2,7 @@ navigation_title: "API tutorial" applies_to: stack: ga - serverless: + serverless: elasticsearch: ga mapped_pages: - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-tutorial-api.html @@ -21,7 +21,7 @@ If you’re just getting started with {{es}}, this tutorial might be a bit advan If you’re just getting started with connectors, you might want to start in the UI first. Check out this tutorial that focuses on managing connectors using the UI: -* [Self-managed connector tutorial](/reference/ingestion-tools/search-connectors/es-postgresql-connector-client-tutorial.md). Set up a self-managed PostgreSQL connector. +* [Self-managed connector tutorial](/reference/search-connectors/es-postgresql-connector-client-tutorial.md). Set up a self-managed PostgreSQL connector. :::: diff --git a/docs/reference/ingestion-tools/search-connectors/build-customize-connectors.md b/docs/reference/search-connectors/build-customize-connectors.md similarity index 95% rename from docs/reference/ingestion-tools/search-connectors/build-customize-connectors.md rename to docs/reference/search-connectors/build-customize-connectors.md index 8c199c4c5c001..d9876dfbaebdd 100644 --- a/docs/reference/ingestion-tools/search-connectors/build-customize-connectors.md +++ b/docs/reference/search-connectors/build-customize-connectors.md @@ -16,7 +16,7 @@ The framework ensures compatibility, makes it easier for our team to review PRs, The framework serves two distinct, but related use cases: -* Customizing an existing Elastic [self-managed connector](/reference/ingestion-tools/search-connectors/self-managed-connectors.md) +* Customizing an existing Elastic [self-managed connector](/reference/search-connectors/self-managed-connectors.md) * Building a new self-managed connector diff --git a/docs/reference/search-connectors/connector-reference.md b/docs/reference/search-connectors/connector-reference.md new file mode 100644 index 0000000000000..3513353e58b31 --- /dev/null +++ b/docs/reference/search-connectors/connector-reference.md @@ -0,0 +1,71 @@ +--- +applies_to: + stack: ga + serverless: ga +mapped_pages: + - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-refs.html +--- + +# Connectors references [es-connectors-refs] + +The following pages contain the reference documentation for each individual connector: + +* [Azure Blob Storage](/reference/search-connectors/es-connectors-azure-blob.md) +* [Box](/reference/search-connectors/es-connectors-box.md) +* [Confluence](/reference/search-connectors/es-connectors-confluence.md) +* [Dropbox](/reference/search-connectors/es-connectors-dropbox.md) +* [GitHub](/reference/search-connectors/es-connectors-github.md) +* [Gmail](/reference/search-connectors/es-connectors-gmail.md) +* [Google Cloud Storage](/reference/search-connectors/es-connectors-google-cloud.md) +* [Google Drive](/reference/search-connectors/es-connectors-google-drive.md) +* [GraphQL](/reference/search-connectors/es-connectors-graphql.md) +* [Jira](/reference/search-connectors/es-connectors-jira.md) +* [MicrosoftSQL](/reference/search-connectors/es-connectors-ms-sql.md) +* [MongoDB](/reference/search-connectors/es-connectors-mongodb.md) +* [MySQL](/reference/search-connectors/es-connectors-mysql.md) +* [Network drive](/reference/search-connectors/es-connectors-network-drive.md) +* [Notion](/reference/search-connectors/es-connectors-notion.md) +* [OneDrive](/reference/search-connectors/es-connectors-onedrive.md) +* [OpenText Documentum](/reference/search-connectors/es-connectors-opentext.md) +* [Oracle](/reference/search-connectors/es-connectors-oracle.md) +* [Outlook](/reference/search-connectors/es-connectors-outlook.md) +* [PostgreSQL](/reference/search-connectors/es-connectors-postgresql.md) +* [Redis](/reference/search-connectors/es-connectors-redis.md) +* [S3](/reference/search-connectors/es-connectors-s3.md) +* [Salesforce](/reference/search-connectors/es-connectors-salesforce.md) +* [ServiceNow](/reference/search-connectors/es-connectors-servicenow.md) +* [SharePoint Online](/reference/search-connectors/es-connectors-sharepoint-online.md) +* [SharePoint Server](/reference/search-connectors/es-connectors-sharepoint.md) +* [Slack](/reference/search-connectors/es-connectors-slack.md) +* [Teams](/reference/search-connectors/es-connectors-teams.md) +* [Zoom](/reference/search-connectors/es-connectors-zoom.md) + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/docs/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md b/docs/reference/search-connectors/connectors-ui-in-kibana.md similarity index 94% rename from docs/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md rename to docs/reference/search-connectors/connectors-ui-in-kibana.md index 68382f7115648..c5b4d72bad60c 100644 --- a/docs/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md +++ b/docs/reference/search-connectors/connectors-ui-in-kibana.md @@ -1,7 +1,7 @@ --- applies_to: stack: ga - serverless: + serverless: elasticsearch: ga mapped_pages: - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-usage.html @@ -24,7 +24,7 @@ In 8.12 we introduced a set of [Connector APIs](https://www.elastic.co/docs/api/ You connector writes data to an {{es}} index. -To create self-managed [**self-managed connector**](/reference/ingestion-tools/search-connectors/self-managed-connectors.md), use the buttons under **Search > Content > Connectors**. Once you’ve chosen the data source type you’d like to sync, you’ll be prompted to create an {{es}} index. +To create self-managed [**self-managed connector**](/reference/search-connectors/self-managed-connectors.md), use the buttons under **Search > Content > Connectors**. Once you’ve chosen the data source type you’d like to sync, you’ll be prompted to create an {{es}} index. ## Manage connector indices [es-connectors-usage-indices] @@ -192,16 +192,16 @@ Then choose the index to view. Choose the **Documents** tab to view the synced documents. Choose the **Index Mappings** tab to view the index mappings that were created by the connector. -When setting up a new connector, ensure you are getting the documents and fields you were expecting from the data source. If not, see [Troubleshooting](/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md) for help. +When setting up a new connector, ensure you are getting the documents and fields you were expecting from the data source. If not, see [Troubleshooting](/reference/search-connectors/es-connectors-troubleshooting.md) for help. These operations require access to Kibana and the `read` and `manage` [indices privileges^](/reference/elasticsearch/security-privileges.md) for the index containing the documents. -See [Security](/reference/ingestion-tools/search-connectors/es-connectors-security.md) for security details. +See [Security](/reference/search-connectors/es-connectors-security.md) for security details. ## Manage sync rules [es-connectors-usage-sync-rules] -Use [sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md) to limit which documents are fetched from the data source, or limit which fetched documents are stored in Elastic. +Use [sync rules](/reference/search-connectors/es-sync-rules.md) to limit which documents are fetched from the data source, or limit which fetched documents are stored in Elastic. In the {{kib}} UI, navigate to **Search > Content > Elasticsearch indices** from the main menu, or use the [global search field](docs-content://explore-analyze/query-filter/filtering.md#_finding_your_apps_and_objects). diff --git a/docs/reference/search-connectors/content-syncs.md b/docs/reference/search-connectors/content-syncs.md new file mode 100644 index 0000000000000..e3efb81186c99 --- /dev/null +++ b/docs/reference/search-connectors/content-syncs.md @@ -0,0 +1,82 @@ +--- +mapped_pages: + - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-sync-types.html +--- + +# Content syncs [es-connectors-sync-types] + +Elastic connectors have two types of content syncs: + +* [Full syncs](#es-connectors-sync-types-full) +* [Incremental syncs](#es-connectors-sync-types-incremental) + + +## Full syncs [es-connectors-sync-types-full] + +::::{note} +We recommend running a full sync whenever [Sync rules](/reference/search-connectors/es-sync-rules.md) are modified + +:::: + + +A full sync syncs all documents in the third-party data source into {{es}}. + +It also deletes any documents in {{es}}, which no longer exist in the third-party data source. + +A full sync, by definition, takes longer than an incremental sync but it ensures full data consistency. + +A full sync is available for all connectors. + +You can [schedule](/reference/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-recurring) or [manually trigger](/reference/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-manual) a full sync job. + + +## Incremental syncs [es-connectors-sync-types-incremental] + +An incremental sync only syncs data changes since the last full or incremental sync. + +Incremental syncs are only available after an initial full sync has successfully completed. Otherwise the incremental sync will fail. + +You can [schedule](/reference/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-recurring) or [manually trigger](/reference/search-connectors/connectors-ui-in-kibana.md#es-connectors-usage-syncs-manual) an incremental sync job. + + +### Incremental sync performance [es-connectors-sync-types-incremental-performance] + +During an incremental sync your connector will still *fetch* all data from the third-party data source. If data contains timestamps, the connector framework compares document ids and timestamps. If a document already exists in {{es}} with the same timestamp, then this document does not need updating and will not be sent to {{es}}. + +The determining factor in incremental sync performance is the raw volume of data ingested. For small volumes of data, the performance improvement using incremental syncs will be negligible. For large volumes of data, the performance impact can be huge. Additionally, an incremental sync is less likely to be throttled by {{es}}, making it more performant than a full sync when {{es}} is under heavy load. + +A third-party data source that has throttling and low throughput, but stores very little data in Elasticsearch, such as GitHub, Jira, or Confluence, won’t see a significant performance improvement from incremental syncs. + +However, a fast, accessible third-party data source that stores huge amounts of data in {{es}}, such as Azure Blob Storage, Google Drive, or S3, can lead to a significant performance improvement from incremental syncs. + +::::{note} +Incremental syncs for [SharePoint Online](/reference/search-connectors/es-connectors-sharepoint-online.md) and [Google Drive](/reference/search-connectors/es-connectors-google-drive.md) connectors use specific logic. All other connectors use the same shared connector framework logic for incremental syncs. + +:::: + + + +### Incremental sync availability [es-connectors-sync-types-incremental-supported] + +Incremental syncs are available for the following connectors: + +* [Azure Blob Storage](/reference/search-connectors/es-connectors-azure-blob.md) +* [Box](/reference/search-connectors/es-connectors-box.md) +* [Confluence](/reference/search-connectors/es-connectors-confluence.md) +* [Dropbox](/reference/search-connectors/es-connectors-dropbox.md) +* [GitHub](/reference/search-connectors/es-connectors-github.md) +* [Gmail](/reference/search-connectors/es-connectors-gmail.md) +* [Google Cloud Storage](/reference/search-connectors/es-connectors-google-cloud.md) +* [Google Drive](/reference/search-connectors/es-connectors-google-drive.md) +* [Jira](/reference/search-connectors/es-connectors-jira.md) +* [Network drive](/reference/search-connectors/es-connectors-network-drive.md) +* [Notion](/reference/search-connectors/es-connectors-notion.md) +* [OneDrive](/reference/search-connectors/es-connectors-onedrive.md) +* [Outlook](/reference/search-connectors/es-connectors-outlook.md) +* [Salesforce](/reference/search-connectors/es-connectors-salesforce.md) +* [ServiceNow](/reference/search-connectors/es-connectors-servicenow.md) +* [SharePoint Online](/reference/search-connectors/es-connectors-sharepoint-online.md) +* [SharePoint Server](/reference/search-connectors/es-connectors-sharepoint.md) +* [Teams](/reference/search-connectors/es-connectors-teams.md) +* [Zoom](/reference/search-connectors/es-connectors-zoom.md) + diff --git a/docs/reference/search-connectors/document-level-security.md b/docs/reference/search-connectors/document-level-security.md new file mode 100644 index 0000000000000..9962277af026e --- /dev/null +++ b/docs/reference/search-connectors/document-level-security.md @@ -0,0 +1,51 @@ +--- +mapped_pages: + - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-dls.html +--- + +# Document level security [es-dls] + +Document level security (DLS) enables you to restrict access to documents in your Elasticsearch indices according to user and group permissions. This ensures search results only return authorized information for users, based on their permissions. + + +## Availability & prerequisites [es-dls-availability-prerequisites] + +Support for DLS in Elastic connectors was introduced in version **8.9.0**. + +::::{note} +This feature is in **beta** and is subject to change. The design and code is less mature than official GA features and is being provided as-is with no warranties. Beta features are not subject to the support SLA of official GA features. + +:::: + + +This feature is not available for all Elastic subscription levels. Refer to the subscriptions pages for [Elastic Cloud](https://www.elastic.co/subscriptions/cloud) and [Elastic Stack](https://www.elastic.co/subscriptions). + +DLS is available by default when using the following Elastic connectors: + +* [Confluence](/reference/search-connectors/es-connectors-confluence.md) +* [Dropbox](/reference/search-connectors/es-connectors-dropbox.md) +* [Jira](/reference/search-connectors/es-connectors-jira.md) (including Jira Data Center) +* [GitHub](/reference/search-connectors/es-connectors-github.md) +* [Gmail](/reference/search-connectors/es-connectors-gmail.md) +* [Google Drive](/reference/search-connectors/es-connectors-google-drive.md) +* [Network Drive](/reference/search-connectors/es-connectors-network-drive.md) +* [OneDrive](/reference/search-connectors/es-connectors-onedrive.md) +* [Outlook](/reference/search-connectors/es-connectors-outlook.md) +* [Salesforce](/reference/search-connectors/es-connectors-salesforce.md) +* [SharePoint Online](/reference/search-connectors/es-connectors-sharepoint-online.md) +* [SharePoint Server](/reference/search-connectors/es-connectors-sharepoint.md) +* [ServiceNow](/reference/search-connectors/es-connectors-servicenow.md) + +Note that our standalone products (App Search and Workplace Search) do not use this feature. Workplace Search has its own permissions management system. + + +## Learn more [es-dls-learn-more] + +DLS documentation: + +* [How DLS works](/reference/search-connectors/es-dls-overview.md) +* [DLS in Search Applications](/reference/search-connectors/es-dls-e2e-guide.md) +* [DLS for SharePoint Online connector](/reference/search-connectors/es-connectors-sharepoint-online.md#es-connectors-sharepoint-online-client-configuration) + + + diff --git a/docs/reference/ingestion-tools/search-connectors/elastic-managed-connectors.md b/docs/reference/search-connectors/elastic-managed-connectors.md similarity index 88% rename from docs/reference/ingestion-tools/search-connectors/elastic-managed-connectors.md rename to docs/reference/search-connectors/elastic-managed-connectors.md index a3743ec57cc0d..005a75e17fac1 100644 --- a/docs/reference/ingestion-tools/search-connectors/elastic-managed-connectors.md +++ b/docs/reference/search-connectors/elastic-managed-connectors.md @@ -8,7 +8,7 @@ mapped_pages: # Elastic managed connectors [es-native-connectors] ::::{important} -As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/search-connectors/self-managed-connectors.md). Refer to the [8.18 documentation](https://www.elastic.co/guide/en/elasticsearch/reference/8.18/es-native-connectors.html) if you are using an older version of Elastic. :::: \ No newline at end of file diff --git a/docs/reference/ingestion-tools/search-connectors/es-connectors-apis.md b/docs/reference/search-connectors/es-connectors-apis.md similarity index 85% rename from docs/reference/ingestion-tools/search-connectors/es-connectors-apis.md rename to docs/reference/search-connectors/es-connectors-apis.md index ed85013c420c9..cbcdb58e0d540 100644 --- a/docs/reference/ingestion-tools/search-connectors/es-connectors-apis.md +++ b/docs/reference/search-connectors/es-connectors-apis.md @@ -1,7 +1,7 @@ --- applies_to: stack: ga - serverless: + serverless: elasticsearch: ga mapped_pages: - https://www.elastic.co/guide/en/elasticsearch/reference/current/es-connectors-apis.html @@ -15,7 +15,7 @@ In 8.12 we introduced a set of APIs to create and manage Elastic connectors and * [Sync job APIs](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-connector#sync-job-apis) ::::{admonition} Connector API tutorial -Check out this concrete [tutorial](/reference/ingestion-tools/search-connectors/api-tutorial.md) to get started with the Connector APIs. +Check out this concrete [tutorial](/reference/search-connectors/api-tutorial.md) to get started with the Connector APIs. :::: diff --git a/docs/reference/ingestion-tools/search-connectors/es-connectors-azure-blob.md b/docs/reference/search-connectors/es-connectors-azure-blob.md similarity index 83% rename from docs/reference/ingestion-tools/search-connectors/es-connectors-azure-blob.md rename to docs/reference/search-connectors/es-connectors-azure-blob.md index ddcb94a8e08a9..d85a32f70fdba 100644 --- a/docs/reference/ingestion-tools/search-connectors/es-connectors-azure-blob.md +++ b/docs/reference/search-connectors/es-connectors-azure-blob.md @@ -7,21 +7,21 @@ mapped_pages: # Elastic Azure Blob Storage connector reference [es-connectors-azure-blob] -The *Elastic Azure Blob Storage connector* is a [connector](/reference/ingestion-tools/search-connectors/index.md) for [Azure Blob Storage](https://azure.microsoft.com/en-us/services/storage/blobs/). +The *Elastic Azure Blob Storage connector* is a [connector](/reference/search-connectors/index.md) for [Azure Blob Storage](https://azure.microsoft.com/en-us/services/storage/blobs/). This connector is written in Python using the [Elastic connector framework](https://github.com/elastic/connectors/tree/main). View the [**source code** for this connector](https://github.com/elastic/connectors/tree/main/connectors/sources/azure_blob_storage.py) (branch *main*, compatible with Elastic *9.0*). ::::{important} -As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/search-connectors/self-managed-connectors.md). :::: ## **Self-managed connector** [es-connectors-azure-blob-connector-client-reference] ### Availability and prerequisites [es-connectors-azure-blob-client-availability-prerequisites] -This connector is available as a self-managed connector. This self-managed connector is compatible with Elastic versions **8.6.0+**. To use this connector, satisfy all [self-managed connector requirements](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +This connector is available as a self-managed connector. This self-managed connector is compatible with Elastic versions **8.6.0+**. To use this connector, satisfy all [self-managed connector requirements](/reference/search-connectors/self-managed-connectors.md). ### Compatibility [es-connectors-azure-blob-client-compatability] @@ -104,7 +104,7 @@ Refer to the [{{es}} API documentation](https://www.elastic.co/docs/api/doc/elas ### Usage [es-connectors-azure-blob-client-usage] -To use this connector as a **self-managed connector**, see [*Self-managed connectors*](/reference/ingestion-tools/search-connectors/self-managed-connectors.md) For additional usage operations, see [*Connectors UI in {{kib}}*](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md). +To use this connector as a **self-managed connector**, see [*Self-managed connectors*](/reference/search-connectors/self-managed-connectors.md) For additional usage operations, see [*Connectors UI in {{kib}}*](/reference/search-connectors/connectors-ui-in-kibana.md). ### Configuration [es-connectors-azure-blob-client-configuration] @@ -133,7 +133,7 @@ The following configuration fields are required to set up the connector: : Number of concurrent downloads for fetching content. Default value is `100`. `use_text_extraction_service` -: Requires a separate deployment of the [Elastic Text Extraction Service](/reference/ingestion-tools/search-connectors/es-connectors-content-extraction.md#es-connectors-content-extraction-local). Requires that ingest pipeline settings disable text extraction. Default value is `False`. +: Requires a separate deployment of the [Elastic Text Extraction Service](/reference/search-connectors/es-connectors-content-extraction.md#es-connectors-content-extraction-local). Requires that ingest pipeline settings disable text extraction. Default value is `False`. ### Deployment using Docker [es-connectors-azure-blob-client-docker] @@ -213,7 +213,7 @@ We also have a quickstart self-managed option using Docker Compose, so you can s The connector will fetch all data available in the container. ::::{note} -* Content from files bigger than 10 MB won’t be extracted by default. You can use the [self-managed local extraction service](/reference/ingestion-tools/search-connectors/es-connectors-content-extraction.md#es-connectors-content-extraction-local) to handle larger binary files. +* Content from files bigger than 10 MB won’t be extracted by default. You can use the [self-managed local extraction service](/reference/search-connectors/es-connectors-content-extraction.md#es-connectors-content-extraction-local) to handle larger binary files. * Permissions are not synced. **All documents** indexed to an Elastic deployment will be visible to **all users with access** to that Elastic Deployment. :::: @@ -222,26 +222,26 @@ The connector will fetch all data available in the container. #### Sync types [es-connectors-azure-blob-client-sync-types] -[Full syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. +[Full syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. -This connector also supports [incremental syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). +This connector also supports [incremental syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). ### Sync rules [es-connectors-azure-blob-client-sync-rules] -[Basic sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. +[Basic sync rules](/reference/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. Advanced sync rules are not available for this connector in the present version. Currently filtering is controlled via ingest pipelines. ### Content extraction [es-connectors-azure-blob-client-content-extraction] -See [Content extraction](/reference/ingestion-tools/search-connectors/es-connectors-content-extraction.md). +See [Content extraction](/reference/search-connectors/es-connectors-content-extraction.md). ### End-to-end testing [es-connectors-azure-blob-client-testing] -The connector framework enables operators to run functional tests against a real data source. Refer to [Connector testing](/reference/ingestion-tools/search-connectors/self-managed-connectors.md#es-build-connector-testing) for more details. +The connector framework enables operators to run functional tests against a real data source. Refer to [Connector testing](/reference/search-connectors/self-managed-connectors.md#es-build-connector-testing) for more details. To perform E2E testing for the Azure Blob Storage connector, run the following command: @@ -268,9 +268,9 @@ This connector has the following known issues: ### Troubleshooting [es-connectors-azure-blob-client-troubleshooting] -See [Troubleshooting](/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md). +See [Troubleshooting](/reference/search-connectors/es-connectors-troubleshooting.md). ### Security [es-connectors-azure-blob-client-security] -See [Security](/reference/ingestion-tools/search-connectors/es-connectors-security.md). \ No newline at end of file +See [Security](/reference/search-connectors/es-connectors-security.md). \ No newline at end of file diff --git a/docs/reference/ingestion-tools/search-connectors/es-connectors-box.md b/docs/reference/search-connectors/es-connectors-box.md similarity index 91% rename from docs/reference/ingestion-tools/search-connectors/es-connectors-box.md rename to docs/reference/search-connectors/es-connectors-box.md index bd27e45192c02..a7e8eb7d076a2 100644 --- a/docs/reference/ingestion-tools/search-connectors/es-connectors-box.md +++ b/docs/reference/search-connectors/es-connectors-box.md @@ -12,14 +12,14 @@ Th Box connector is written in Python using the [Elastic connector framework](ht View the [source code for this connector](https://github.com/elastic/connectors/tree/main/connectors/sources/box.py) (branch *main*, compatible with Elastic *9.0*). ::::{important} -As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/search-connectors/self-managed-connectors.md). :::: ## **Self-managed connector reference** [es-connectors-box-connector-client-reference] ### Availability and prerequisites [es-connectors-box-client-availability-and-prerequisites] -This connector is available as a self-managed connector. To use this connector, satisfy all [self-managed connector prerequisites](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +This connector is available as a self-managed connector. To use this connector, satisfy all [self-managed connector prerequisites](/reference/search-connectors/self-managed-connectors.md). ::::{note} This connector is in **technical preview** and is subject to change. The design and code is less mature than official GA features and is being provided as-is with no warranties. Technical preview features are not subject to the support SLA of official GA features. @@ -105,7 +105,7 @@ Refer to the [{{es}} API documentation](https://www.elastic.co/docs/api/doc/elas To use this connector as a **self-managed connector**, use the **Box** tile from the connectors list OR **Customized connector** workflow. -For additional operations, see [*Connectors UI in {{kib}}*](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md). +For additional operations, see [*Connectors UI in {{kib}}*](/reference/search-connectors/connectors-ui-in-kibana.md). ### Box API Authorization [es-connectors-box-client-api-authorization] @@ -258,7 +258,7 @@ We also have a quickstart self-managed option using Docker Compose, so you can s ### Content Extraction [es-connectors-box-client-content-extraction] -Refer to [Content extraction](/reference/ingestion-tools/search-connectors/es-connectors-content-extraction.md). +Refer to [Content extraction](/reference/search-connectors/es-connectors-content-extraction.md). ### Documents and syncs [es-connectors-box-client-documents-and-syncs] @@ -278,14 +278,14 @@ The connector syncs the following objects and entities: #### Sync types [es-connectors-box-client-sync-types] -[Full syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. +[Full syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. -This connector also supports [incremental syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). +This connector also supports [incremental syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). ### Sync rules [es-connectors-box-client-sync-rules] -[Basic sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. +[Basic sync rules](/reference/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. ### Advanced Sync Rules [es-connectors-box-client-advanced-sync-rules] @@ -295,7 +295,7 @@ Advanced sync rules are not available for this connector in the present version. ### End-to-end Testing [es-connectors-box-client-end-to-end-testing] -The connector framework enables operators to run functional tests against a real data source. Refer to [Connector testing](/reference/ingestion-tools/search-connectors/self-managed-connectors.md#es-build-connector-testing) for more details. +The connector framework enables operators to run functional tests against a real data source. Refer to [Connector testing](/reference/search-connectors/self-managed-connectors.md#es-build-connector-testing) for more details. To perform E2E testing for the Box connector, run the following command: @@ -317,10 +317,10 @@ There are no known issues for this connector. Refer to [Known issues](/release-n ### Troubleshooting [es-connectors-box-client-troubleshooting] -See [Troubleshooting](/reference/ingestion-tools/search-connectors/es-connectors-troubleshooting.md). +See [Troubleshooting](/reference/search-connectors/es-connectors-troubleshooting.md). ### Security [es-connectors-box-client-security] -See [Security](/reference/ingestion-tools/search-connectors/es-connectors-security.md). +See [Security](/reference/search-connectors/es-connectors-security.md). diff --git a/docs/reference/ingestion-tools/search-connectors/es-connectors-confluence.md b/docs/reference/search-connectors/es-connectors-confluence.md similarity index 85% rename from docs/reference/ingestion-tools/search-connectors/es-connectors-confluence.md rename to docs/reference/search-connectors/es-connectors-confluence.md index 517e2b3fc1869..cf09c43762315 100644 --- a/docs/reference/ingestion-tools/search-connectors/es-connectors-confluence.md +++ b/docs/reference/search-connectors/es-connectors-confluence.md @@ -7,12 +7,12 @@ mapped_pages: # Elastic Confluence connector reference [es-connectors-confluence] -The *Elastic Confluence connector* is a [connector](/reference/ingestion-tools/search-connectors/index.md) for [Atlassian Confluence](https://www.atlassian.com/software/confluence). This connector is written in Python using the [Elastic connector framework](https://github.com/elastic/connectors/tree/main). +The *Elastic Confluence connector* is a [connector](/reference/search-connectors/index.md) for [Atlassian Confluence](https://www.atlassian.com/software/confluence). This connector is written in Python using the [Elastic connector framework](https://github.com/elastic/connectors/tree/main). View the [**source code** for this connector](https://github.com/elastic/connectors/tree/main/connectors/sources/confluence.py) (branch *main*, compatible with Elastic *9.0*). ::::{important} -As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +As of Elastic 9.0, managed connectors on Elastic Cloud Hosted are no longer available. All connectors must be [self-managed](/reference/search-connectors/self-managed-connectors.md). :::: ## **Self-managed connector** [es-connectors-confluence-connector-client-reference] @@ -27,7 +27,7 @@ Confluence Data Center support was added in 8.13.0 in technical preview and is s :::: -To use this connector, satisfy all [self-managed connector requirements](/reference/ingestion-tools/search-connectors/self-managed-connectors.md). +To use this connector, satisfy all [self-managed connector requirements](/reference/search-connectors/self-managed-connectors.md). ### Create a Confluence connector [es-connectors-confluence-create-connector-client] @@ -105,7 +105,7 @@ Refer to the [{{es}} API documentation](https://www.elastic.co/docs/api/doc/elas ### Usage [es-connectors-confluence-client-usage] -To use this connector as a **self-managed connector**, see [*Self-managed connectors*](/reference/ingestion-tools/search-connectors/self-managed-connectors.md) For additional usage operations, see [*Connectors UI in {{kib}}*](/reference/ingestion-tools/search-connectors/connectors-ui-in-kibana.md). +To use this connector as a **self-managed connector**, see [*Self-managed connectors*](/reference/search-connectors/self-managed-connectors.md) For additional usage operations, see [*Connectors UI in {{kib}}*](/reference/search-connectors/connectors-ui-in-kibana.md). ### Compatibility [es-connectors-confluence-client-compatability] @@ -180,7 +180,7 @@ The following configuration fields are required to set up the connector: : The number of concurrent downloads for fetching the attachment content. This speeds up the content extraction of attachments. Defaults to `50`. `use_document_level_security` -: Toggle to enable [document level security (DLS)](/reference/ingestion-tools/search-connectors/document-level-security.md). +: Toggle to enable [document level security (DLS)](/reference/search-connectors/document-level-security.md). When enabled, full syncs will fetch access control lists for each document and store them in the `_allow_access_control` field. Access control syncs will fetch users' access control lists and store them in a separate index. @@ -285,16 +285,16 @@ The connector syncs the following Confluence object types: #### Sync types [es-connectors-confluence-client-sync-types] -[Full syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. +[Full syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-full) are supported by default for all connectors. -This connector also supports [incremental syncs](/reference/ingestion-tools/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). +This connector also supports [incremental syncs](/reference/search-connectors/content-syncs.md#es-connectors-sync-types-incremental). ### Sync rules [es-connectors-confluence-client-sync-rules] -[Basic sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. +[Basic sync rules](/reference/search-connectors/es-sync-rules.md#es-sync-rules-basic) are identical for all connectors and are available by default. -This connector supports [advanced sync rules](/reference/ingestion-tools/search-connectors/es-sync-rules.md#es-sync-rules-advanced) for remote filtering. These rules cover complex query-and-filter scenarios that cannot be expressed with `, ``, and ``. Simpler analyzers, like the [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md) tokenizer, only produce the `word` token type. +For example, the [`standard`](/reference/text-analysis/analysis-standard-tokenizer.md) tokenizer can produce a variety of token types, including ``, ``, and ``. Simpler analyzers, like the [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenizer.md) tokenizer, only produce the `word` token type. -Certain token filters can also add token types. For example, the [`synonym`](/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md) filter can add the `` token type. +Certain token filters can also add token types. For example, the [`synonym`](/reference/text-analysis/analysis-synonym-tokenfilter.md) filter can add the `` token type. Some tokenizers don’t support this token filter, for example keyword, simple_pattern, and simple_pattern_split tokenizers, as they don’t support setting the token type attribute. diff --git a/docs/reference/data-analysis/text-analysis/analysis-keep-words-tokenfilter.md b/docs/reference/text-analysis/analysis-keep-words-tokenfilter.md similarity index 97% rename from docs/reference/data-analysis/text-analysis/analysis-keep-words-tokenfilter.md rename to docs/reference/text-analysis/analysis-keep-words-tokenfilter.md index 999bccbabee5f..cf66e29dae2f6 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-keep-words-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-keep-words-tokenfilter.md @@ -12,7 +12,7 @@ Keeps only tokens contained in a specified word list. This filter uses Lucene’s [KeepWordFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/miscellaneous/KeepWordFilter.md). ::::{note} -To remove a list of words from a token stream, use the [`stop`](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) filter. +To remove a list of words from a token stream, use the [`stop`](/reference/text-analysis/analysis-stop-tokenfilter.md) filter. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-keyword-analyzer.md b/docs/reference/text-analysis/analysis-keyword-analyzer.md similarity index 93% rename from docs/reference/data-analysis/text-analysis/analysis-keyword-analyzer.md rename to docs/reference/text-analysis/analysis-keyword-analyzer.md index 0e674a9477282..a0fc3cd00f777 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-keyword-analyzer.md +++ b/docs/reference/text-analysis/analysis-keyword-analyzer.md @@ -37,7 +37,7 @@ The `keyword` analyzer is not configurable. The `keyword` analyzer consists of: Tokenizer -: * [Keyword Tokenizer](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) +: * [Keyword Tokenizer](/reference/text-analysis/analysis-keyword-tokenizer.md) If you need to customize the `keyword` analyzer then you need to recreate it as a `custom` analyzer and modify it, usually by adding token filters. Usually, you should prefer the [Keyword type](/reference/elasticsearch/mapping-reference/keyword.md) when you want strings that are not split into tokens, but just in case you need it, this would recreate the built-in `keyword` analyzer and you can use it as a starting point for further customization: diff --git a/docs/reference/data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md b/docs/reference/text-analysis/analysis-keyword-marker-tokenfilter.md similarity index 95% rename from docs/reference/data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md rename to docs/reference/text-analysis/analysis-keyword-marker-tokenfilter.md index 462d0d82d58eb..e5f53cb8bfdcf 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-keyword-marker-tokenfilter.md @@ -9,7 +9,7 @@ mapped_pages: Marks specified tokens as keywords, which are not stemmed. -The `keyword_marker` filter assigns specified tokens a `keyword` attribute of `true`. Stemmer token filters, such as [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) or [`porter_stem`](/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md), skip tokens with a `keyword` attribute of `true`. +The `keyword_marker` filter assigns specified tokens a `keyword` attribute of `true`. Stemmer token filters, such as [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) or [`porter_stem`](/reference/text-analysis/analysis-porterstem-tokenfilter.md), skip tokens with a `keyword` attribute of `true`. ::::{important} To work properly, the `keyword_marker` filter must be listed before any stemmer token filters in the [analyzer configuration](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md). @@ -23,7 +23,7 @@ The `keyword_marker` filter uses Lucene’s [KeywordMarkerFilter](https://lucene To see how the `keyword_marker` filter works, you first need to produce a token stream containing stemmed tokens. -The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) filter to create stemmed tokens for `fox running and jumping`. +The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) filter to create stemmed tokens for `fox running and jumping`. ```console GET /_analyze diff --git a/docs/reference/data-analysis/text-analysis/analysis-keyword-repeat-tokenfilter.md b/docs/reference/text-analysis/analysis-keyword-repeat-tokenfilter.md similarity index 96% rename from docs/reference/data-analysis/text-analysis/analysis-keyword-repeat-tokenfilter.md rename to docs/reference/text-analysis/analysis-keyword-repeat-tokenfilter.md index fd42a15a5bdff..4451ea7bd3f39 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-keyword-repeat-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-keyword-repeat-tokenfilter.md @@ -9,7 +9,7 @@ mapped_pages: Outputs a keyword version of each token in a stream. These keyword tokens are not stemmed. -The `keyword_repeat` filter assigns keyword tokens a `keyword` attribute of `true`. Stemmer token filters, such as [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) or [`porter_stem`](/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md), skip tokens with a `keyword` attribute of `true`. +The `keyword_repeat` filter assigns keyword tokens a `keyword` attribute of `true`. Stemmer token filters, such as [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) or [`porter_stem`](/reference/text-analysis/analysis-porterstem-tokenfilter.md), skip tokens with a `keyword` attribute of `true`. You can use the `keyword_repeat` filter with a stemmer token filter to output a stemmed and unstemmed version of each token in a stream. @@ -18,7 +18,7 @@ To work properly, the `keyword_repeat` filter must be listed before any stemmer Stemming does not affect all tokens. This means streams could contain duplicate tokens in the same position, even after stemming. -To remove these duplicate tokens, add the [`remove_duplicates`](/reference/data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md) filter after the stemmer filter in the analyzer configuration. +To remove these duplicate tokens, add the [`remove_duplicates`](/reference/text-analysis/analysis-remove-duplicates-tokenfilter.md) filter after the stemmer filter in the analyzer configuration. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md b/docs/reference/text-analysis/analysis-keyword-tokenizer.md similarity index 93% rename from docs/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md rename to docs/reference/text-analysis/analysis-keyword-tokenizer.md index b3458a2ced566..45ee209ee5d46 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md +++ b/docs/reference/text-analysis/analysis-keyword-tokenizer.md @@ -31,7 +31,7 @@ The above sentence would produce the following term: You can combine the `keyword` tokenizer with token filters to normalise structured data, such as product IDs or email addresses. -For example, the following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the `keyword` tokenizer and [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) filter to convert an email address to lowercase. +For example, the following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the `keyword` tokenizer and [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) filter to convert an email address to lowercase. ```console POST _analyze diff --git a/docs/reference/data-analysis/text-analysis/analysis-kstem-tokenfilter.md b/docs/reference/text-analysis/analysis-kstem-tokenfilter.md similarity index 77% rename from docs/reference/data-analysis/text-analysis/analysis-kstem-tokenfilter.md rename to docs/reference/text-analysis/analysis-kstem-tokenfilter.md index bf352093e53fa..751544b170e81 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-kstem-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-kstem-tokenfilter.md @@ -9,9 +9,9 @@ mapped_pages: Provides [KStem](https://ciir.cs.umass.edu/pubfiles/ir-35.pdf)-based stemming for the English language. The `kstem` filter combines [algorithmic stemming](docs-content://manage-data/data-store/text-analysis/stemming.md#algorithmic-stemmers) with a built-in [dictionary](docs-content://manage-data/data-store/text-analysis/stemming.md#dictionary-stemmers). -The `kstem` filter tends to stem less aggressively than other English stemmer filters, such as the [`porter_stem`](/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md) filter. +The `kstem` filter tends to stem less aggressively than other English stemmer filters, such as the [`porter_stem`](/reference/text-analysis/analysis-porterstem-tokenfilter.md) filter. -The `kstem` filter is equivalent to the [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) filter’s [`light_english`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md#analysis-stemmer-tokenfilter-language-parm) variant. +The `kstem` filter is equivalent to the [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) filter’s [`light_english`](/reference/text-analysis/analysis-stemmer-tokenfilter.md#analysis-stemmer-tokenfilter-language-parm) variant. This filter uses Lucene’s [KStemFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/en/KStemFilter.md). @@ -40,7 +40,7 @@ The filter produces the following tokens: The following [create index API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-create) request uses the `kstem` filter to configure a new [custom analyzer](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md). ::::{important} -To work properly, the `kstem` filter requires lowercase tokens. To ensure tokens are lowercased, add the [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) filter before the `kstem` filter in the analyzer configuration. +To work properly, the `kstem` filter requires lowercase tokens. To ensure tokens are lowercased, add the [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) filter before the `kstem` filter in the analyzer configuration. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-lang-analyzer.md b/docs/reference/text-analysis/analysis-lang-analyzer.md similarity index 99% rename from docs/reference/data-analysis/text-analysis/analysis-lang-analyzer.md rename to docs/reference/text-analysis/analysis-lang-analyzer.md index 3e1c651805a73..9b8ec02d9cb5f 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-lang-analyzer.md +++ b/docs/reference/text-analysis/analysis-lang-analyzer.md @@ -13,12 +13,12 @@ A set of analyzers aimed at analyzing specific language text. The following type ### Stopwords [_stopwords] -All analyzers support setting custom `stopwords` either internally in the config, or by using an external stopwords file by setting `stopwords_path`. Check [Stop Analyzer](/reference/data-analysis/text-analysis/analysis-stop-analyzer.md) for more details. +All analyzers support setting custom `stopwords` either internally in the config, or by using an external stopwords file by setting `stopwords_path`. Check [Stop Analyzer](/reference/text-analysis/analysis-stop-analyzer.md) for more details. ### Excluding words from stemming [_excluding_words_from_stemming] -The `stem_exclusion` parameter allows you to specify an array of lowercase words that should not be stemmed. Internally, this functionality is implemented by adding the [`keyword_marker` token filter](/reference/data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md) with the `keywords` set to the value of the `stem_exclusion` parameter. +The `stem_exclusion` parameter allows you to specify an array of lowercase words that should not be stemmed. Internally, this functionality is implemented by adding the [`keyword_marker` token filter](/reference/text-analysis/analysis-keyword-marker-tokenfilter.md) with the `keywords` set to the value of the `stem_exclusion` parameter. The following analyzers support setting custom `stem_exclusion` list: `arabic`, `armenian`, `basque`, `bengali`, `bulgarian`, `catalan`, `czech`, `dutch`, `english`, `finnish`, `french`, `galician`, `german`, `hindi`, `hungarian`, `indonesian`, `irish`, `italian`, `latvian`, `lithuanian`, `norwegian`, `portuguese`, `romanian`, `russian`, `serbian`, `sorani`, `spanish`, `swedish`, `turkish`. diff --git a/docs/reference/data-analysis/text-analysis/analysis-length-tokenfilter.md b/docs/reference/text-analysis/analysis-length-tokenfilter.md similarity index 97% rename from docs/reference/data-analysis/text-analysis/analysis-length-tokenfilter.md rename to docs/reference/text-analysis/analysis-length-tokenfilter.md index 40f0171de06d7..5e1ce91585cba 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-length-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-length-tokenfilter.md @@ -12,7 +12,7 @@ Removes tokens shorter or longer than specified character lengths. For example, This filter uses Lucene’s [LengthFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/miscellaneous/LengthFilter.md). ::::{tip} -The `length` filter removes entire tokens. If you’d prefer to shorten tokens to a specific length, use the [`truncate`](/reference/data-analysis/text-analysis/analysis-truncate-tokenfilter.md) filter. +The `length` filter removes entire tokens. If you’d prefer to shorten tokens to a specific length, use the [`truncate`](/reference/text-analysis/analysis-truncate-tokenfilter.md) filter. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-letter-tokenizer.md b/docs/reference/text-analysis/analysis-letter-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-letter-tokenizer.md rename to docs/reference/text-analysis/analysis-letter-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-limit-token-count-tokenfilter.md b/docs/reference/text-analysis/analysis-limit-token-count-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-limit-token-count-tokenfilter.md rename to docs/reference/text-analysis/analysis-limit-token-count-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md b/docs/reference/text-analysis/analysis-lowercase-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md rename to docs/reference/text-analysis/analysis-lowercase-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md b/docs/reference/text-analysis/analysis-lowercase-tokenizer.md similarity index 57% rename from docs/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md rename to docs/reference/text-analysis/analysis-lowercase-tokenizer.md index 6d3bb6a082c31..78496bd33768b 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md +++ b/docs/reference/text-analysis/analysis-lowercase-tokenizer.md @@ -7,7 +7,7 @@ mapped_pages: # Lowercase tokenizer [analysis-lowercase-tokenizer] -The `lowercase` tokenizer, like the [`letter` tokenizer](/reference/data-analysis/text-analysis/analysis-letter-tokenizer.md) breaks text into terms whenever it encounters a character which is not a letter, but it also lowercases all terms. It is functionally equivalent to the [`letter` tokenizer](/reference/data-analysis/text-analysis/analysis-letter-tokenizer.md) combined with the [`lowercase` token filter](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md), but is more efficient as it performs both steps in a single pass. +The `lowercase` tokenizer, like the [`letter` tokenizer](/reference/text-analysis/analysis-letter-tokenizer.md) breaks text into terms whenever it encounters a character which is not a letter, but it also lowercases all terms. It is functionally equivalent to the [`letter` tokenizer](/reference/text-analysis/analysis-letter-tokenizer.md) combined with the [`lowercase` token filter](/reference/text-analysis/analysis-lowercase-tokenfilter.md), but is more efficient as it performs both steps in a single pass. ## Example output [_example_output_12] diff --git a/docs/reference/data-analysis/text-analysis/analysis-mapping-charfilter.md b/docs/reference/text-analysis/analysis-mapping-charfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-mapping-charfilter.md rename to docs/reference/text-analysis/analysis-mapping-charfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-minhash-tokenfilter.md b/docs/reference/text-analysis/analysis-minhash-tokenfilter.md similarity index 91% rename from docs/reference/data-analysis/text-analysis/analysis-minhash-tokenfilter.md rename to docs/reference/text-analysis/analysis-minhash-tokenfilter.md index 91bd40382a091..460dd162b82aa 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-minhash-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-minhash-tokenfilter.md @@ -37,7 +37,7 @@ This filter uses Lucene’s [MinHashFilter](https://lucene.apache.org/core/10_0_ ## Tips for configuring the `min_hash` filter [analysis-minhash-tokenfilter-configuration-tips] -* `min_hash` filter input tokens should typically be k-words shingles produced from [shingle token filter](/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md). You should choose `k` large enough so that the probability of any given shingle occurring in a document is low. At the same time, as internally each shingle is hashed into to 128-bit hash, you should choose `k` small enough so that all possible different k-words shingles can be hashed to 128-bit hash with minimal collision. +* `min_hash` filter input tokens should typically be k-words shingles produced from [shingle token filter](/reference/text-analysis/analysis-shingle-tokenfilter.md). You should choose `k` large enough so that the probability of any given shingle occurring in a document is low. At the same time, as internally each shingle is hashed into to 128-bit hash, you should choose `k` small enough so that all possible different k-words shingles can be hashed to 128-bit hash with minimal collision. * We recommend you test different arguments for the `hash_count`, `bucket_count` and `hash_set_size` parameters: * To improve precision, increase the `bucket_count` or `hash_set_size` arguments. Higher `bucket_count` and `hash_set_size` values increase the likelihood that different tokens are indexed to different buckets. @@ -64,7 +64,7 @@ To customize the `min_hash` filter, duplicate it to create the basis for a new c For example, the following [create index API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-create) request uses the following custom token filters to configure a new [custom analyzer](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md): -* `my_shingle_filter`, a custom [`shingle` filter](/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md). `my_shingle_filter` only outputs five-word shingles. +* `my_shingle_filter`, a custom [`shingle` filter](/reference/text-analysis/analysis-shingle-tokenfilter.md). `my_shingle_filter` only outputs five-word shingles. * `my_minhash_filter`, a custom `min_hash` filter. `my_minhash_filter` hashes each five-word shingle once. It then assigns the hashes into 512 buckets, keeping only the smallest hash from each bucket. The request also assigns the custom analyzer to the `fingerprint` field mapping. diff --git a/docs/reference/data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md b/docs/reference/text-analysis/analysis-multiplexer-tokenfilter.md similarity index 91% rename from docs/reference/data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md rename to docs/reference/text-analysis/analysis-multiplexer-tokenfilter.md index 2a4f6c7d39608..83f083f2e3e98 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-multiplexer-tokenfilter.md @@ -21,7 +21,7 @@ filters : a list of token filters to apply to incoming tokens. These can be any token filters defined elsewhere in the index mappings. Filters can be chained using a comma-delimited string, so for example `"lowercase, porter_stem"` would apply the `lowercase` filter and then the `porter_stem` filter to a single token. ::::{warning} -[Shingle](/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md) or multi-word synonym token filters will not function normally when they are declared in the filters array because they read ahead internally which is unsupported by the multiplexer +[Shingle](/reference/text-analysis/analysis-shingle-tokenfilter.md) or multi-word synonym token filters will not function normally when they are declared in the filters array because they read ahead internally which is unsupported by the multiplexer :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-ngram-tokenfilter.md b/docs/reference/text-analysis/analysis-ngram-tokenfilter.md similarity index 94% rename from docs/reference/data-analysis/text-analysis/analysis-ngram-tokenfilter.md rename to docs/reference/text-analysis/analysis-ngram-tokenfilter.md index c2dff50cf4482..c51eb5220517a 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-ngram-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-ngram-tokenfilter.md @@ -14,7 +14,7 @@ For example, you can use the `ngram` token filter to change `fox` to `[ f, fo, o This filter uses Lucene’s [NGramTokenFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/ngram/NGramTokenFilter.md). ::::{note} -The `ngram` filter is similar to the [`edge_ngram` token filter](/reference/data-analysis/text-analysis/analysis-edgengram-tokenfilter.md). However, the `edge_ngram` only outputs n-grams that start at the beginning of a token. +The `ngram` filter is similar to the [`edge_ngram` token filter](/reference/text-analysis/analysis-edgengram-tokenfilter.md). However, the `edge_ngram` only outputs n-grams that start at the beginning of a token. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-ngram-tokenizer.md b/docs/reference/text-analysis/analysis-ngram-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-ngram-tokenizer.md rename to docs/reference/text-analysis/analysis-ngram-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-normalization-tokenfilter.md b/docs/reference/text-analysis/analysis-normalization-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-normalization-tokenfilter.md rename to docs/reference/text-analysis/analysis-normalization-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-pathhierarchy-tokenizer.md b/docs/reference/text-analysis/analysis-pathhierarchy-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-pathhierarchy-tokenizer.md rename to docs/reference/text-analysis/analysis-pathhierarchy-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-pattern-analyzer.md b/docs/reference/text-analysis/analysis-pattern-analyzer.md similarity index 91% rename from docs/reference/data-analysis/text-analysis/analysis-pattern-analyzer.md rename to docs/reference/text-analysis/analysis-pattern-analyzer.md index 3e0e6170df319..9fc6dd696939d 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-pattern-analyzer.md +++ b/docs/reference/text-analysis/analysis-pattern-analyzer.md @@ -58,7 +58,7 @@ The `pattern` analyzer accepts the following parameters: `stopwords_path` : The path to a file containing stop words. -See the [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. +See the [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. ## Example configuration [_example_configuration_3] @@ -150,12 +150,12 @@ The regex above is easier to understand as: The `pattern` analyzer consists of: Tokenizer -: * [Pattern Tokenizer](/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md) +: * [Pattern Tokenizer](/reference/text-analysis/analysis-pattern-tokenizer.md) Token Filters -: * [Lower Case Token Filter](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) -* [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) (disabled by default) +: * [Lower Case Token Filter](/reference/text-analysis/analysis-lowercase-tokenfilter.md) +* [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) (disabled by default) If you need to customize the `pattern` analyzer beyond the configuration parameters then you need to recreate it as a `custom` analyzer and modify it, usually by adding token filters. This would recreate the built-in `pattern` analyzer and you can use it as a starting point for further customization: diff --git a/docs/reference/data-analysis/text-analysis/analysis-pattern-capture-tokenfilter.md b/docs/reference/text-analysis/analysis-pattern-capture-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-pattern-capture-tokenfilter.md rename to docs/reference/text-analysis/analysis-pattern-capture-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-pattern-replace-charfilter.md b/docs/reference/text-analysis/analysis-pattern-replace-charfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-pattern-replace-charfilter.md rename to docs/reference/text-analysis/analysis-pattern-replace-charfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md b/docs/reference/text-analysis/analysis-pattern-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md rename to docs/reference/text-analysis/analysis-pattern-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-pattern_replace-tokenfilter.md b/docs/reference/text-analysis/analysis-pattern_replace-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-pattern_replace-tokenfilter.md rename to docs/reference/text-analysis/analysis-pattern_replace-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-phonetic-tokenfilter.md b/docs/reference/text-analysis/analysis-phonetic-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-phonetic-tokenfilter.md rename to docs/reference/text-analysis/analysis-phonetic-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md b/docs/reference/text-analysis/analysis-porterstem-tokenfilter.md similarity index 80% rename from docs/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md rename to docs/reference/text-analysis/analysis-porterstem-tokenfilter.md index 98040799789af..8ab65553c40ce 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-porterstem-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-porterstem-tokenfilter.md @@ -9,9 +9,9 @@ mapped_pages: Provides [algorithmic stemming](docs-content://manage-data/data-store/text-analysis/stemming.md#algorithmic-stemmers) for the English language, based on the [Porter stemming algorithm](https://snowballstem.org/algorithms/porter/stemmer.html). -This filter tends to stem more aggressively than other English stemmer filters, such as the [`kstem`](/reference/data-analysis/text-analysis/analysis-kstem-tokenfilter.md) filter. +This filter tends to stem more aggressively than other English stemmer filters, such as the [`kstem`](/reference/text-analysis/analysis-kstem-tokenfilter.md) filter. -The `porter_stem` filter is equivalent to the [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) filter’s [`english`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md#analysis-stemmer-tokenfilter-language-parm) variant. +The `porter_stem` filter is equivalent to the [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) filter’s [`english`](/reference/text-analysis/analysis-stemmer-tokenfilter.md#analysis-stemmer-tokenfilter-language-parm) variant. The `porter_stem` filter uses Lucene’s [PorterStemFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/en/PorterStemFilter.html). @@ -40,7 +40,7 @@ The filter produces the following tokens: The following [create index API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-create) request uses the `porter_stem` filter to configure a new [custom analyzer](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md). ::::{important} -To work properly, the `porter_stem` filter requires lowercase tokens. To ensure tokens are lowercased, add the [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) filter before the `porter_stem` filter in the analyzer configuration. +To work properly, the `porter_stem` filter requires lowercase tokens. To ensure tokens are lowercased, add the [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) filter before the `porter_stem` filter in the analyzer configuration. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-predicatefilter-tokenfilter.md b/docs/reference/text-analysis/analysis-predicatefilter-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-predicatefilter-tokenfilter.md rename to docs/reference/text-analysis/analysis-predicatefilter-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md b/docs/reference/text-analysis/analysis-remove-duplicates-tokenfilter.md similarity index 92% rename from docs/reference/data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md rename to docs/reference/text-analysis/analysis-remove-duplicates-tokenfilter.md index 4a4b38434679d..bf55877c683a2 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-remove-duplicates-tokenfilter.md @@ -15,7 +15,7 @@ The `remove_duplicates` filter uses Lucene’s [RemoveDuplicatesTokenFilter](htt To see how the `remove_duplicates` filter works, you first need to produce a token stream containing duplicate tokens in the same position. -The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`keyword_repeat`](/reference/data-analysis/text-analysis/analysis-keyword-repeat-tokenfilter.md) and [`stemmer`](/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md) filters to create stemmed and unstemmed tokens for `jumping dog`. +The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`keyword_repeat`](/reference/text-analysis/analysis-keyword-repeat-tokenfilter.md) and [`stemmer`](/reference/text-analysis/analysis-stemmer-tokenfilter.md) filters to create stemmed and unstemmed tokens for `jumping dog`. ```console GET _analyze diff --git a/docs/reference/data-analysis/text-analysis/analysis-reverse-tokenfilter.md b/docs/reference/text-analysis/analysis-reverse-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-reverse-tokenfilter.md rename to docs/reference/text-analysis/analysis-reverse-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md b/docs/reference/text-analysis/analysis-shingle-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-shingle-tokenfilter.md rename to docs/reference/text-analysis/analysis-shingle-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-simple-analyzer.md b/docs/reference/text-analysis/analysis-simple-analyzer.md similarity index 93% rename from docs/reference/data-analysis/text-analysis/analysis-simple-analyzer.md rename to docs/reference/text-analysis/analysis-simple-analyzer.md index e5734df6cc45d..86eb42dd90764 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-simple-analyzer.md +++ b/docs/reference/text-analysis/analysis-simple-analyzer.md @@ -31,7 +31,7 @@ The `simple` analyzer parses the sentence and produces the following tokens: The `simple` analyzer is defined by one tokenizer: Tokenizer -: * [Lowercase Tokenizer](/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md) +: * [Lowercase Tokenizer](/reference/text-analysis/analysis-lowercase-tokenizer.md) diff --git a/docs/reference/data-analysis/text-analysis/analysis-simplepattern-tokenizer.md b/docs/reference/text-analysis/analysis-simplepattern-tokenizer.md similarity index 78% rename from docs/reference/data-analysis/text-analysis/analysis-simplepattern-tokenizer.md rename to docs/reference/text-analysis/analysis-simplepattern-tokenizer.md index d68cb47724478..0856829817fbf 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-simplepattern-tokenizer.md +++ b/docs/reference/text-analysis/analysis-simplepattern-tokenizer.md @@ -7,9 +7,9 @@ mapped_pages: # Simple pattern tokenizer [analysis-simplepattern-tokenizer] -The `simple_pattern` tokenizer uses a regular expression to capture matching text as terms. The set of regular expression features it supports is more limited than the [`pattern`](/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md) tokenizer, but the tokenization is generally faster. +The `simple_pattern` tokenizer uses a regular expression to capture matching text as terms. The set of regular expression features it supports is more limited than the [`pattern`](/reference/text-analysis/analysis-pattern-tokenizer.md) tokenizer, but the tokenization is generally faster. -This tokenizer does not support splitting the input on a pattern match, unlike the [`pattern`](/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md) tokenizer. To split on pattern matches using the same restricted regular expression subset, see the [`simple_pattern_split`](/reference/data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md) tokenizer. +This tokenizer does not support splitting the input on a pattern match, unlike the [`pattern`](/reference/text-analysis/analysis-pattern-tokenizer.md) tokenizer. To split on pattern matches using the same restricted regular expression subset, see the [`simple_pattern_split`](/reference/text-analysis/analysis-simplepatternsplit-tokenizer.md) tokenizer. This tokenizer uses [Lucene regular expressions](https://lucene.apache.org/core/10_0_0/core/org/apache/lucene/util/automaton/RegExp.html). For an explanation of the supported features and syntax, see [Regular Expression Syntax](/reference/query-languages/query-dsl/regexp-syntax.md). diff --git a/docs/reference/data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md b/docs/reference/text-analysis/analysis-simplepatternsplit-tokenizer.md similarity index 90% rename from docs/reference/data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md rename to docs/reference/text-analysis/analysis-simplepatternsplit-tokenizer.md index a95fd92ceb519..dd281be18dcdf 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md +++ b/docs/reference/text-analysis/analysis-simplepatternsplit-tokenizer.md @@ -7,9 +7,9 @@ mapped_pages: # Simple pattern split tokenizer [analysis-simplepatternsplit-tokenizer] -The `simple_pattern_split` tokenizer uses a regular expression to split the input into terms at pattern matches. The set of regular expression features it supports is more limited than the [`pattern`](/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md) tokenizer, but the tokenization is generally faster. +The `simple_pattern_split` tokenizer uses a regular expression to split the input into terms at pattern matches. The set of regular expression features it supports is more limited than the [`pattern`](/reference/text-analysis/analysis-pattern-tokenizer.md) tokenizer, but the tokenization is generally faster. -This tokenizer does not produce terms from the matches themselves. To produce terms from matches using patterns in the same restricted regular expression subset, see the [`simple_pattern`](/reference/data-analysis/text-analysis/analysis-simplepattern-tokenizer.md) tokenizer. +This tokenizer does not produce terms from the matches themselves. To produce terms from matches using patterns in the same restricted regular expression subset, see the [`simple_pattern`](/reference/text-analysis/analysis-simplepattern-tokenizer.md) tokenizer. This tokenizer uses [Lucene regular expressions](https://lucene.apache.org/core/10_0_0/core/org/apache/lucene/util/automaton/RegExp.html). For an explanation of the supported features and syntax, see [Regular Expression Syntax](/reference/query-languages/query-dsl/regexp-syntax.md). diff --git a/docs/reference/data-analysis/text-analysis/analysis-snowball-tokenfilter.md b/docs/reference/text-analysis/analysis-snowball-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-snowball-tokenfilter.md rename to docs/reference/text-analysis/analysis-snowball-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-standard-analyzer.md b/docs/reference/text-analysis/analysis-standard-analyzer.md similarity index 85% rename from docs/reference/data-analysis/text-analysis/analysis-standard-analyzer.md rename to docs/reference/text-analysis/analysis-standard-analyzer.md index 1c648d55998e7..2d14d16172600 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-standard-analyzer.md +++ b/docs/reference/text-analysis/analysis-standard-analyzer.md @@ -40,7 +40,7 @@ The `standard` analyzer accepts the following parameters: `stopwords_path` : The path to a file containing stop words. -See the [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. +See the [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. ## Example configuration [_example_configuration_4] @@ -82,12 +82,12 @@ The above example produces the following terms: The `standard` analyzer consists of: Tokenizer -: * [Standard Tokenizer](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) +: * [Standard Tokenizer](/reference/text-analysis/analysis-standard-tokenizer.md) Token Filters -: * [Lower Case Token Filter](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) -* [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) (disabled by default) +: * [Lower Case Token Filter](/reference/text-analysis/analysis-lowercase-tokenfilter.md) +* [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) (disabled by default) If you need to customize the `standard` analyzer beyond the configuration parameters then you need to recreate it as a `custom` analyzer and modify it, usually by adding token filters. This would recreate the built-in `standard` analyzer and you can use it as a starting point: diff --git a/docs/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md b/docs/reference/text-analysis/analysis-standard-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md rename to docs/reference/text-analysis/analysis-standard-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-stemmer-override-tokenfilter.md b/docs/reference/text-analysis/analysis-stemmer-override-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-stemmer-override-tokenfilter.md rename to docs/reference/text-analysis/analysis-stemmer-override-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md b/docs/reference/text-analysis/analysis-stemmer-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-stemmer-tokenfilter.md rename to docs/reference/text-analysis/analysis-stemmer-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-stop-analyzer.md b/docs/reference/text-analysis/analysis-stop-analyzer.md similarity index 83% rename from docs/reference/data-analysis/text-analysis/analysis-stop-analyzer.md rename to docs/reference/text-analysis/analysis-stop-analyzer.md index bf250da6e831c..7349fe386a786 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-stop-analyzer.md +++ b/docs/reference/text-analysis/analysis-stop-analyzer.md @@ -7,7 +7,7 @@ mapped_pages: # Stop analyzer [analysis-stop-analyzer] -The `stop` analyzer is the same as the [`simple` analyzer](/reference/data-analysis/text-analysis/analysis-simple-analyzer.md) but adds support for removing stop words. It defaults to using the `_english_` stop words. +The `stop` analyzer is the same as the [`simple` analyzer](/reference/text-analysis/analysis-simple-analyzer.md) but adds support for removing stop words. It defaults to using the `_english_` stop words. ## Example output [_example_output_5] @@ -37,7 +37,7 @@ The `stop` analyzer accepts the following parameters: `stopwords_path` : The path to a file containing stop words. This path is relative to the Elasticsearch `config` directory. -See the [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. +See the [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) for more information about stop word configuration. ## Example configuration [_example_configuration_5] @@ -78,11 +78,11 @@ The above example produces the following terms: It consists of: Tokenizer -: * [Lower Case Tokenizer](/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md) +: * [Lower Case Tokenizer](/reference/text-analysis/analysis-lowercase-tokenizer.md) Token filters -: * [Stop Token Filter](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) +: * [Stop Token Filter](/reference/text-analysis/analysis-stop-tokenfilter.md) If you need to customize the `stop` analyzer beyond the configuration parameters then you need to recreate it as a `custom` analyzer and modify it, usually by adding token filters. This would recreate the built-in `stop` analyzer and you can use it as a starting point for further customization: diff --git a/docs/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md b/docs/reference/text-analysis/analysis-stop-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md rename to docs/reference/text-analysis/analysis-stop-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md b/docs/reference/text-analysis/analysis-synonym-graph-tokenfilter.md similarity index 95% rename from docs/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md rename to docs/reference/text-analysis/analysis-synonym-graph-tokenfilter.md index 238b447cd450b..273782f566881 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-synonym-graph-tokenfilter.md @@ -14,7 +14,7 @@ In order to properly handle multi-word synonyms this token filter creates a [gra ::::{note} :name: synonym-graph-index-note -This token filter is designed to be used as part of a search analyzer only. If you want to apply synonyms during indexing please use the standard [synonym token filter](/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md). +This token filter is designed to be used as part of a search analyzer only. If you want to apply synonyms during indexing please use the standard [synonym token filter](/reference/text-analysis/analysis-synonym-tokenfilter.md). :::: @@ -178,12 +178,12 @@ Order is important for your token filters. Text will be processed first through Because entries in the synonym map cannot have stacked positions, some token filters may cause issues here. Token filters that produce multiple versions of a token may choose which version of the token to emit when parsing synonyms. For example, `asciifolding` will only produce the folded version of the token. Others, like `multiplexer`, `word_delimiter_graph` or `ngram` will throw an error. -If you need to build analyzers that include both multi-token filters and synonym filters, consider using the [multiplexer](/reference/data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md) filter, with the multi-token filters in one branch and the synonym filter in the other. +If you need to build analyzers that include both multi-token filters and synonym filters, consider using the [multiplexer](/reference/text-analysis/analysis-multiplexer-tokenfilter.md) filter, with the multi-token filters in one branch and the synonym filter in the other. ### Synonyms and `stop` token filters [synonym-graph-tokenizer-stop-token-filter] -Synonyms and [stop token filters](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) interact with each other in the following ways: +Synonyms and [stop token filters](/reference/text-analysis/analysis-stop-tokenfilter.md) interact with each other in the following ways: #### Stop token filter **before** synonym token filter [_stop_token_filter_before_synonym_token_filter_2] diff --git a/docs/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md b/docs/reference/text-analysis/analysis-synonym-tokenfilter.md similarity index 96% rename from docs/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md rename to docs/reference/text-analysis/analysis-synonym-tokenfilter.md index bb293ac0c97cf..284d06099d5e7 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-synonym-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-synonym-tokenfilter.md @@ -168,12 +168,12 @@ Order is important for your token filters. Text will be processed first through Because entries in the synonym map cannot have stacked positions, some token filters may cause issues here. Token filters that produce multiple versions of a token may choose which version of the token to emit when parsing synonyms. For example, `asciifolding` will only produce the folded version of the token. Others, like `multiplexer`, `word_delimiter_graph` or `ngram` will throw an error. -If you need to build analyzers that include both multi-token filters and synonym filters, consider using the [multiplexer](/reference/data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md) filter, with the multi-token filters in one branch and the synonym filter in the other. +If you need to build analyzers that include both multi-token filters and synonym filters, consider using the [multiplexer](/reference/text-analysis/analysis-multiplexer-tokenfilter.md) filter, with the multi-token filters in one branch and the synonym filter in the other. ### Synonyms and `stop` token filters [synonym-tokenizer-stop-token-filter] -Synonyms and [stop token filters](/reference/data-analysis/text-analysis/analysis-stop-tokenfilter.md) interact with each other in the following ways: +Synonyms and [stop token filters](/reference/text-analysis/analysis-stop-tokenfilter.md) interact with each other in the following ways: #### Stop token filter **before** synonym token filter [_stop_token_filter_before_synonym_token_filter] diff --git a/docs/reference/data-analysis/text-analysis/analysis-thai-tokenizer.md b/docs/reference/text-analysis/analysis-thai-tokenizer.md similarity index 93% rename from docs/reference/data-analysis/text-analysis/analysis-thai-tokenizer.md rename to docs/reference/text-analysis/analysis-thai-tokenizer.md index 288427d6dae08..354fb67f97f88 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-thai-tokenizer.md +++ b/docs/reference/text-analysis/analysis-thai-tokenizer.md @@ -7,7 +7,7 @@ mapped_pages: # Thai tokenizer [analysis-thai-tokenizer] -The `thai` tokenizer segments Thai text into words, using the Thai segmentation algorithm included with Java. Text in other languages in general will be treated the same as the [`standard` tokenizer](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md). +The `thai` tokenizer segments Thai text into words, using the Thai segmentation algorithm included with Java. Text in other languages in general will be treated the same as the [`standard` tokenizer](/reference/text-analysis/analysis-standard-tokenizer.md). ::::{warning} This tokenizer may not be supported by all JREs. It is known to work with Sun/Oracle and OpenJDK. If your application needs to be fully portable, consider using the [ICU Tokenizer](/reference/elasticsearch-plugins/analysis-icu-tokenizer.md) instead. diff --git a/docs/reference/data-analysis/text-analysis/analysis-trim-tokenfilter.md b/docs/reference/text-analysis/analysis-trim-tokenfilter.md similarity index 85% rename from docs/reference/data-analysis/text-analysis/analysis-trim-tokenfilter.md rename to docs/reference/text-analysis/analysis-trim-tokenfilter.md index fb29e2c8741fc..1435a18e17286 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-trim-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-trim-tokenfilter.md @@ -12,7 +12,7 @@ Removes leading and trailing whitespace from each token in a stream. While this The `trim` filter uses Lucene’s [TrimFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/miscellaneous/TrimFilter.md). ::::{tip} -Many commonly used tokenizers, such as the [`standard`](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) or [`whitespace`](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) tokenizer, remove whitespace by default. When using these tokenizers, you don’t need to add a separate `trim` filter. +Many commonly used tokenizers, such as the [`standard`](/reference/text-analysis/analysis-standard-tokenizer.md) or [`whitespace`](/reference/text-analysis/analysis-whitespace-tokenizer.md) tokenizer, remove whitespace by default. When using these tokenizers, you don’t need to add a separate `trim` filter. :::: @@ -21,7 +21,7 @@ Many commonly used tokenizers, such as the [`standard`](/reference/data-analysis To see how the `trim` filter works, you first need to produce a token containing whitespace. -The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`keyword`](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) tokenizer to produce a token for `" fox "`. +The following [analyze API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-analyze) request uses the [`keyword`](/reference/text-analysis/analysis-keyword-tokenizer.md) tokenizer to produce a token for `" fox "`. ```console GET _analyze diff --git a/docs/reference/data-analysis/text-analysis/analysis-truncate-tokenfilter.md b/docs/reference/text-analysis/analysis-truncate-tokenfilter.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-truncate-tokenfilter.md rename to docs/reference/text-analysis/analysis-truncate-tokenfilter.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-uaxurlemail-tokenizer.md b/docs/reference/text-analysis/analysis-uaxurlemail-tokenizer.md similarity index 92% rename from docs/reference/data-analysis/text-analysis/analysis-uaxurlemail-tokenizer.md rename to docs/reference/text-analysis/analysis-uaxurlemail-tokenizer.md index 579738a4f39eb..a7f97c4bbf720 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-uaxurlemail-tokenizer.md +++ b/docs/reference/text-analysis/analysis-uaxurlemail-tokenizer.md @@ -7,7 +7,7 @@ mapped_pages: # UAX URL email tokenizer [analysis-uaxurlemail-tokenizer] -The `uax_url_email` tokenizer is like the [`standard` tokenizer](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) except that it recognises URLs and email addresses as single tokens. +The `uax_url_email` tokenizer is like the [`standard` tokenizer](/reference/text-analysis/analysis-standard-tokenizer.md) except that it recognises URLs and email addresses as single tokens. ## Example output [_example_output_18] diff --git a/docs/reference/data-analysis/text-analysis/analysis-unique-tokenfilter.md b/docs/reference/text-analysis/analysis-unique-tokenfilter.md similarity index 95% rename from docs/reference/data-analysis/text-analysis/analysis-unique-tokenfilter.md rename to docs/reference/text-analysis/analysis-unique-tokenfilter.md index 6d69f6c9fa992..27dea21f6b688 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-unique-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-unique-tokenfilter.md @@ -12,7 +12,7 @@ Removes duplicate tokens from a stream. For example, you can use the `unique` fi If the `only_on_same_position` parameter is set to `true`, the `unique` filter removes only duplicate tokens *in the same position*. ::::{note} -When `only_on_same_position` is `true`, the `unique` filter works the same as [`remove_duplicates`](/reference/data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md) filter. +When `only_on_same_position` is `true`, the `unique` filter works the same as [`remove_duplicates`](/reference/text-analysis/analysis-remove-duplicates-tokenfilter.md) filter. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-uppercase-tokenfilter.md b/docs/reference/text-analysis/analysis-uppercase-tokenfilter.md similarity index 94% rename from docs/reference/data-analysis/text-analysis/analysis-uppercase-tokenfilter.md rename to docs/reference/text-analysis/analysis-uppercase-tokenfilter.md index 40022c0d6d40f..b00bbe6981310 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-uppercase-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-uppercase-tokenfilter.md @@ -14,7 +14,7 @@ This filter uses Lucene’s [UpperCaseFilter](https://lucene.apache.org/core/10_ ::::{warning} Depending on the language, an uppercase character can map to multiple lowercase characters. Using the `uppercase` filter could result in the loss of lowercase character information. -To avoid this loss but still have a consistent letter case, use the [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) filter instead. +To avoid this loss but still have a consistent letter case, use the [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) filter instead. :::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-whitespace-analyzer.md b/docs/reference/text-analysis/analysis-whitespace-analyzer.md similarity index 92% rename from docs/reference/data-analysis/text-analysis/analysis-whitespace-analyzer.md rename to docs/reference/text-analysis/analysis-whitespace-analyzer.md index 361ec7ba003d4..c4f67dd2cd36e 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-whitespace-analyzer.md +++ b/docs/reference/text-analysis/analysis-whitespace-analyzer.md @@ -37,7 +37,7 @@ The `whitespace` analyzer is not configurable. It consists of: Tokenizer -: * [Whitespace Tokenizer](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) +: * [Whitespace Tokenizer](/reference/text-analysis/analysis-whitespace-tokenizer.md) If you need to customize the `whitespace` analyzer then you need to recreate it as a `custom` analyzer and modify it, usually by adding token filters. This would recreate the built-in `whitespace` analyzer and you can use it as a starting point for further customization: diff --git a/docs/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md b/docs/reference/text-analysis/analysis-whitespace-tokenizer.md similarity index 100% rename from docs/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md rename to docs/reference/text-analysis/analysis-whitespace-tokenizer.md diff --git a/docs/reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md b/docs/reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md similarity index 85% rename from docs/reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md rename to docs/reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md index a338c486a6f4e..5e4b1787542eb 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md @@ -18,9 +18,9 @@ Splits tokens at non-alphanumeric characters. The `word_delimiter_graph` filter The `word_delimiter_graph` filter uses Lucene’s [WordDelimiterGraphFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/miscellaneous/WordDelimiterGraphFilter.md). ::::{tip} -The `word_delimiter_graph` filter was designed to remove punctuation from complex identifiers, such as product IDs or part numbers. For these use cases, we recommend using the `word_delimiter_graph` filter with the [`keyword`](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) tokenizer. +The `word_delimiter_graph` filter was designed to remove punctuation from complex identifiers, such as product IDs or part numbers. For these use cases, we recommend using the `word_delimiter_graph` filter with the [`keyword`](/reference/text-analysis/analysis-keyword-tokenizer.md) tokenizer. -Avoid using the `word_delimiter_graph` filter to split hyphenated words, such as `wi-fi`. Because users often search for these words both with and without hyphens, we recommend using the [`synonym_graph`](/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md) filter instead. +Avoid using the `word_delimiter_graph` filter to split hyphenated words, such as `wi-fi`. Because users often search for these words both with and without hyphens, we recommend using the [`synonym_graph`](/reference/text-analysis/analysis-synonym-graph-tokenfilter.md) filter instead. :::: @@ -66,7 +66,7 @@ PUT /my-index-000001 ``` ::::{warning} -Avoid using the `word_delimiter_graph` filter with tokenizers that remove punctuation, such as the [`standard`](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) tokenizer. This could prevent the `word_delimiter_graph` filter from splitting tokens correctly. It can also interfere with the filter’s configurable parameters, such as [`catenate_all`](#word-delimiter-graph-tokenfilter-catenate-all) or [`preserve_original`](#word-delimiter-graph-tokenfilter-preserve-original). We recommend using the [`keyword`](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) or [`whitespace`](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) tokenizer instead. +Avoid using the `word_delimiter_graph` filter with tokenizers that remove punctuation, such as the [`standard`](/reference/text-analysis/analysis-standard-tokenizer.md) tokenizer. This could prevent the `word_delimiter_graph` filter from splitting tokens correctly. It can also interfere with the filter’s configurable parameters, such as [`catenate_all`](#word-delimiter-graph-tokenfilter-catenate-all) or [`preserve_original`](#word-delimiter-graph-tokenfilter-preserve-original). We recommend using the [`keyword`](/reference/text-analysis/analysis-keyword-tokenizer.md) or [`whitespace`](/reference/text-analysis/analysis-whitespace-tokenizer.md) tokenizer instead. :::: @@ -80,7 +80,7 @@ $$$word-delimiter-graph-tokenfilter-adjust-offsets$$$ : (Optional, Boolean) If `true`, the filter adjusts the offsets of split or catenated tokens to better reflect their actual position in the token stream. Defaults to `true`. ::::{warning} -Set `adjust_offsets` to `false` if your analyzer uses filters, such as the [`trim`](/reference/data-analysis/text-analysis/analysis-trim-tokenfilter.md) filter, that change the length of tokens without changing their offsets. Otherwise, the `word_delimiter_graph` filter could produce tokens with illegal offsets. +Set `adjust_offsets` to `false` if your analyzer uses filters, such as the [`trim`](/reference/text-analysis/analysis-trim-tokenfilter.md) filter, that change the length of tokens without changing their offsets. Otherwise, the `word_delimiter_graph` filter could produce tokens with illegal offsets. :::: @@ -94,7 +94,7 @@ $$$word-delimiter-graph-tokenfilter-catenate-all$$$ ::::{warning} Setting this parameter to `true` produces multi-position tokens, which are not supported by indexing. -If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/data-analysis/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. +If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. When used for search analysis, catenated tokens can cause problems for the [`match_phrase`](/reference/query-languages/query-dsl/query-dsl-match-query-phrase.md) query and other queries that rely on token position for matching. Avoid setting this parameter to `true` if you plan to use these queries. @@ -110,7 +110,7 @@ $$$word-delimiter-graph-tokenfilter-catenate-numbers$$$ ::::{warning} Setting this parameter to `true` produces multi-position tokens, which are not supported by indexing. -If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/data-analysis/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. +If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. When used for search analysis, catenated tokens can cause problems for the [`match_phrase`](/reference/query-languages/query-dsl/query-dsl-match-query-phrase.md) query and other queries that rely on token position for matching. Avoid setting this parameter to `true` if you plan to use these queries. @@ -126,7 +126,7 @@ $$$word-delimiter-graph-tokenfilter-catenate-words$$$ ::::{warning} Setting this parameter to `true` produces multi-position tokens, which are not supported by indexing. -If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/data-analysis/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. +If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. When used for search analysis, catenated tokens can cause problems for the [`match_phrase`](/reference/query-languages/query-dsl/query-dsl-match-query-phrase.md) query and other queries that rely on token position for matching. Avoid setting this parameter to `true` if you plan to use these queries. @@ -151,7 +151,7 @@ $$$word-delimiter-graph-tokenfilter-preserve-original$$$ ::::{warning} Setting this parameter to `true` produces multi-position tokens, which are not supported by indexing. -If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/data-analysis/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. +If this parameter is `true`, avoid using this filter in an index analyzer or use the [`flatten_graph`](/reference/text-analysis/analysis-flatten-graph-tokenfilter.md) filter after this filter to make the token stream suitable for indexing. :::: @@ -264,7 +264,7 @@ PUT /my-index-000001 ## Differences between `word_delimiter_graph` and `word_delimiter` [analysis-word-delimiter-graph-differences] -Both the `word_delimiter_graph` and [`word_delimiter`](/reference/data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md) filters produce tokens that span multiple positions when any of the following parameters are `true`: +Both the `word_delimiter_graph` and [`word_delimiter`](/reference/text-analysis/analysis-word-delimiter-tokenfilter.md) filters produce tokens that span multiple positions when any of the following parameters are `true`: * [`catenate_all`](#word-delimiter-graph-tokenfilter-catenate-all) * [`catenate_numbers`](#word-delimiter-graph-tokenfilter-catenate-numbers) @@ -292,7 +292,7 @@ Both the `word_delimiter` and `word_delimiter_graph` produce the following token This graph does not contain multi-position tokens. All tokens span only one position. -:::{image} ../../../images/token-graph-basic.svg +:::{image} images/token-graph-basic.svg :alt: token graph basic ::: @@ -303,7 +303,7 @@ The `word_delimiter_graph` filter produces the following token graph for `PowerS This graph correctly indicates the catenated `PowerShot` token spans two positions. -:::{image} ../../../images/token-graph-wdg.svg +:::{image} images/token-graph-wdg.svg :alt: token graph wdg ::: @@ -314,7 +314,7 @@ When `catenate_words` is `true`, the `word_delimiter` filter produces the follow Note that the catenated `PowerShot` token should span two positions but only spans one in the token graph, making it invalid. -:::{image} ../../../images/token-graph-wd.svg +:::{image} images/token-graph-wd.svg :alt: token graph wd ::: diff --git a/docs/reference/data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md b/docs/reference/text-analysis/analysis-word-delimiter-tokenfilter.md similarity index 89% rename from docs/reference/data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md rename to docs/reference/text-analysis/analysis-word-delimiter-tokenfilter.md index a0dde21422f8f..7ae1097371344 100644 --- a/docs/reference/data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md +++ b/docs/reference/text-analysis/analysis-word-delimiter-tokenfilter.md @@ -8,9 +8,9 @@ mapped_pages: ::::{warning} -We recommend using the [`word_delimiter_graph`](/reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md) instead of the `word_delimiter` filter. +We recommend using the [`word_delimiter_graph`](/reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md) instead of the `word_delimiter` filter. -The `word_delimiter` filter can produce invalid token graphs. See [Differences between `word_delimiter_graph` and `word_delimiter`](/reference/data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md#analysis-word-delimiter-graph-differences). +The `word_delimiter` filter can produce invalid token graphs. See [Differences between `word_delimiter_graph` and `word_delimiter`](/reference/text-analysis/analysis-word-delimiter-graph-tokenfilter.md#analysis-word-delimiter-graph-differences). The `word_delimiter` filter also uses Lucene’s [WordDelimiterFilter](https://lucene.apache.org/core/10_0_0/analysis/common/org/apache/lucene/analysis/miscellaneous/WordDelimiterFilter.md), which is marked as deprecated. @@ -26,9 +26,9 @@ Splits tokens at non-alphanumeric characters. The `word_delimiter` filter also p * Remove the English possessive (`'s`) from the end of each token. For example: `Neil's` → `Neil` ::::{tip} -The `word_delimiter` filter was designed to remove punctuation from complex identifiers, such as product IDs or part numbers. For these use cases, we recommend using the `word_delimiter` filter with the [`keyword`](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) tokenizer. +The `word_delimiter` filter was designed to remove punctuation from complex identifiers, such as product IDs or part numbers. For these use cases, we recommend using the `word_delimiter` filter with the [`keyword`](/reference/text-analysis/analysis-keyword-tokenizer.md) tokenizer. -Avoid using the `word_delimiter` filter to split hyphenated words, such as `wi-fi`. Because users often search for these words both with and without hyphens, we recommend using the [`synonym_graph`](/reference/data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md) filter instead. +Avoid using the `word_delimiter` filter to split hyphenated words, such as `wi-fi`. Because users often search for these words both with and without hyphens, we recommend using the [`synonym_graph`](/reference/text-analysis/analysis-synonym-graph-tokenfilter.md) filter instead. :::: @@ -74,7 +74,7 @@ PUT /my-index-000001 ``` ::::{warning} -Avoid using the `word_delimiter` filter with tokenizers that remove punctuation, such as the [`standard`](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) tokenizer. This could prevent the `word_delimiter` filter from splitting tokens correctly. It can also interfere with the filter’s configurable parameters, such as `catenate_all` or `preserve_original`. We recommend using the [`keyword`](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) or [`whitespace`](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) tokenizer instead. +Avoid using the `word_delimiter` filter with tokenizers that remove punctuation, such as the [`standard`](/reference/text-analysis/analysis-standard-tokenizer.md) tokenizer. This could prevent the `word_delimiter` filter from splitting tokens correctly. It can also interfere with the filter’s configurable parameters, such as `catenate_all` or `preserve_original`. We recommend using the [`keyword`](/reference/text-analysis/analysis-keyword-tokenizer.md) or [`whitespace`](/reference/text-analysis/analysis-whitespace-tokenizer.md) tokenizer instead. :::: diff --git a/docs/reference/data-analysis/text-analysis/analyzer-reference.md b/docs/reference/text-analysis/analyzer-reference.md similarity index 61% rename from docs/reference/data-analysis/text-analysis/analyzer-reference.md rename to docs/reference/text-analysis/analyzer-reference.md index c2aa76bc1c1c8..265cd3a4b492b 100644 --- a/docs/reference/data-analysis/text-analysis/analyzer-reference.md +++ b/docs/reference/text-analysis/analyzer-reference.md @@ -7,34 +7,34 @@ mapped_pages: Elasticsearch ships with a wide range of built-in analyzers, which can be used in any index without further configuration: -[Standard Analyzer](/reference/data-analysis/text-analysis/analysis-standard-analyzer.md) +[Standard Analyzer](/reference/text-analysis/analysis-standard-analyzer.md) : The `standard` analyzer divides text into terms on word boundaries, as defined by the Unicode Text Segmentation algorithm. It removes most punctuation, lowercases terms, and supports removing stop words. -[Simple Analyzer](/reference/data-analysis/text-analysis/analysis-simple-analyzer.md) +[Simple Analyzer](/reference/text-analysis/analysis-simple-analyzer.md) : The `simple` analyzer divides text into terms whenever it encounters a character which is not a letter. It lowercases all terms. -[Whitespace Analyzer](/reference/data-analysis/text-analysis/analysis-whitespace-analyzer.md) +[Whitespace Analyzer](/reference/text-analysis/analysis-whitespace-analyzer.md) : The `whitespace` analyzer divides text into terms whenever it encounters any whitespace character. It does not lowercase terms. -[Stop Analyzer](/reference/data-analysis/text-analysis/analysis-stop-analyzer.md) +[Stop Analyzer](/reference/text-analysis/analysis-stop-analyzer.md) : The `stop` analyzer is like the `simple` analyzer, but also supports removal of stop words. -[Keyword Analyzer](/reference/data-analysis/text-analysis/analysis-keyword-analyzer.md) +[Keyword Analyzer](/reference/text-analysis/analysis-keyword-analyzer.md) : The `keyword` analyzer is a noop analyzer that accepts whatever text it is given and outputs the exact same text as a single term. -[Pattern Analyzer](/reference/data-analysis/text-analysis/analysis-pattern-analyzer.md) +[Pattern Analyzer](/reference/text-analysis/analysis-pattern-analyzer.md) : The `pattern` analyzer uses a regular expression to split the text into terms. It supports lower-casing and stop words. -[Language Analyzers](/reference/data-analysis/text-analysis/analysis-lang-analyzer.md) +[Language Analyzers](/reference/text-analysis/analysis-lang-analyzer.md) : Elasticsearch provides many language-specific analyzers like `english` or `french`. -[Fingerprint Analyzer](/reference/data-analysis/text-analysis/analysis-fingerprint-analyzer.md) +[Fingerprint Analyzer](/reference/text-analysis/analysis-fingerprint-analyzer.md) : The `fingerprint` analyzer is a specialist analyzer which creates a fingerprint which can be used for duplicate detection. ## Custom analyzers [_custom_analyzers] -If you do not find an analyzer suitable for your needs, you can create a [`custom`](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md) analyzer which combines the appropriate [character filters](/reference/data-analysis/text-analysis/character-filter-reference.md), [tokenizer](/reference/data-analysis/text-analysis/tokenizer-reference.md), and [token filters](/reference/data-analysis/text-analysis/token-filter-reference.md). +If you do not find an analyzer suitable for your needs, you can create a [`custom`](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md) analyzer which combines the appropriate [character filters](/reference/text-analysis/character-filter-reference.md), [tokenizer](/reference/text-analysis/tokenizer-reference.md), and [token filters](/reference/text-analysis/token-filter-reference.md). diff --git a/docs/reference/data-analysis/text-analysis/character-filter-reference.md b/docs/reference/text-analysis/character-filter-reference.md similarity index 73% rename from docs/reference/data-analysis/text-analysis/character-filter-reference.md rename to docs/reference/text-analysis/character-filter-reference.md index e3a649844ed84..64d13b87e3fb5 100644 --- a/docs/reference/data-analysis/text-analysis/character-filter-reference.md +++ b/docs/reference/text-analysis/character-filter-reference.md @@ -5,19 +5,19 @@ mapped_pages: # Character filter reference [analysis-charfilters] -*Character filters* are used to preprocess the stream of characters before it is passed to the [tokenizer](/reference/data-analysis/text-analysis/tokenizer-reference.md). +*Character filters* are used to preprocess the stream of characters before it is passed to the [tokenizer](/reference/text-analysis/tokenizer-reference.md). A character filter receives the original text as a stream of characters and can transform the stream by adding, removing, or changing characters. For instance, a character filter could be used to convert Hindu-Arabic numerals (٠‎١٢٣٤٥٦٧٨‎٩‎) into their Arabic-Latin equivalents (0123456789), or to strip HTML elements like `` from the stream. Elasticsearch has a number of built in character filters which can be used to build [custom analyzers](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md). -[HTML Strip Character Filter](/reference/data-analysis/text-analysis/analysis-htmlstrip-charfilter.md) +[HTML Strip Character Filter](/reference/text-analysis/analysis-htmlstrip-charfilter.md) : The `html_strip` character filter strips out HTML elements like `` and decodes HTML entities like `&`. -[Mapping Character Filter](/reference/data-analysis/text-analysis/analysis-mapping-charfilter.md) +[Mapping Character Filter](/reference/text-analysis/analysis-mapping-charfilter.md) : The `mapping` character filter replaces any occurrences of the specified strings with the specified replacements. -[Pattern Replace Character Filter](/reference/data-analysis/text-analysis/analysis-pattern-replace-charfilter.md) +[Pattern Replace Character Filter](/reference/text-analysis/analysis-pattern-replace-charfilter.md) : The `pattern_replace` character filter replaces any characters matching a regular expression with the specified replacement. diff --git a/docs/images/token-graph-basic.svg b/docs/reference/text-analysis/images/token-graph-basic.svg similarity index 100% rename from docs/images/token-graph-basic.svg rename to docs/reference/text-analysis/images/token-graph-basic.svg diff --git a/docs/images/token-graph-dns-synonym-ex2.svg b/docs/reference/text-analysis/images/token-graph-dns-synonym-ex2.svg similarity index 100% rename from docs/images/token-graph-dns-synonym-ex2.svg rename to docs/reference/text-analysis/images/token-graph-dns-synonym-ex2.svg diff --git a/docs/images/token-graph-dns-synonym-flattened-ex2.svg b/docs/reference/text-analysis/images/token-graph-dns-synonym-flattened-ex2.svg similarity index 100% rename from docs/images/token-graph-dns-synonym-flattened-ex2.svg rename to docs/reference/text-analysis/images/token-graph-dns-synonym-flattened-ex2.svg diff --git a/docs/images/token-graph-wd.svg b/docs/reference/text-analysis/images/token-graph-wd.svg similarity index 100% rename from docs/images/token-graph-wd.svg rename to docs/reference/text-analysis/images/token-graph-wd.svg diff --git a/docs/images/token-graph-wdg.svg b/docs/reference/text-analysis/images/token-graph-wdg.svg similarity index 100% rename from docs/images/token-graph-wdg.svg rename to docs/reference/text-analysis/images/token-graph-wdg.svg diff --git a/docs/reference/data-analysis/text-analysis/index.md b/docs/reference/text-analysis/index.md similarity index 52% rename from docs/reference/data-analysis/text-analysis/index.md rename to docs/reference/text-analysis/index.md index b891072b4433c..5a573cd9e5761 100644 --- a/docs/reference/data-analysis/text-analysis/index.md +++ b/docs/reference/text-analysis/index.md @@ -10,8 +10,8 @@ Refer to [the text analysis overview](docs-content://manage-data/data-store/text This section contains reference information for text analysis components features, including: -* [Analyzers](/reference/data-analysis/text-analysis/analyzer-reference.md) -* [Tokenizers](/reference/data-analysis/text-analysis/tokenizer-reference.md) -* [Token filters](/reference/data-analysis/text-analysis/token-filter-reference.md) -* [Character filters](/reference/data-analysis/text-analysis/character-filter-reference.md) -* [Normalizers](/reference/data-analysis/text-analysis/normalizers.md) +* [Analyzers](/reference/text-analysis/analyzer-reference.md) +* [Tokenizers](/reference/text-analysis/tokenizer-reference.md) +* [Token filters](/reference/text-analysis/token-filter-reference.md) +* [Character filters](/reference/text-analysis/character-filter-reference.md) +* [Normalizers](/reference/text-analysis/normalizers.md) diff --git a/docs/reference/data-analysis/text-analysis/normalizers.md b/docs/reference/text-analysis/normalizers.md similarity index 91% rename from docs/reference/data-analysis/text-analysis/normalizers.md rename to docs/reference/text-analysis/normalizers.md index b9edfd9a7f5a5..09fa4743ff50c 100644 --- a/docs/reference/data-analysis/text-analysis/normalizers.md +++ b/docs/reference/text-analysis/normalizers.md @@ -12,7 +12,7 @@ Elasticsearch ships with a `lowercase` built-in normalizer. For other forms of n ## Custom normalizers [_custom_normalizers] -Custom normalizers take a list of [character filters](/reference/data-analysis/text-analysis/character-filter-reference.md) and a list of [token filters](/reference/data-analysis/text-analysis/token-filter-reference.md). +Custom normalizers take a list of [character filters](/reference/text-analysis/character-filter-reference.md) and a list of [token filters](/reference/text-analysis/token-filter-reference.md). ```console PUT index diff --git a/docs/reference/text-analysis/toc.yml b/docs/reference/text-analysis/toc.yml new file mode 100644 index 0000000000000..df90ec0b53328 --- /dev/null +++ b/docs/reference/text-analysis/toc.yml @@ -0,0 +1,85 @@ +toc: + - file: index.md + - file: analyzer-reference.md + children: + - file: analysis-fingerprint-analyzer.md + - file: analysis-keyword-analyzer.md + - file: analysis-lang-analyzer.md + - file: analysis-pattern-analyzer.md + - file: analysis-simple-analyzer.md + - file: analysis-standard-analyzer.md + - file: analysis-stop-analyzer.md + - file: analysis-whitespace-analyzer.md + - file: tokenizer-reference.md + children: + - file: analysis-chargroup-tokenizer.md + - file: analysis-classic-tokenizer.md + - file: analysis-edgengram-tokenizer.md + - file: analysis-keyword-tokenizer.md + - file: analysis-letter-tokenizer.md + - file: analysis-lowercase-tokenizer.md + - file: analysis-ngram-tokenizer.md + - file: analysis-pathhierarchy-tokenizer.md + - file: analysis-pattern-tokenizer.md + - file: analysis-simplepattern-tokenizer.md + - file: analysis-simplepatternsplit-tokenizer.md + - file: analysis-standard-tokenizer.md + - file: analysis-thai-tokenizer.md + - file: analysis-uaxurlemail-tokenizer.md + - file: analysis-whitespace-tokenizer.md + - file: token-filter-reference.md + children: + - file: analysis-apostrophe-tokenfilter.md + - file: analysis-asciifolding-tokenfilter.md + - file: analysis-cjk-bigram-tokenfilter.md + - file: analysis-cjk-width-tokenfilter.md + - file: analysis-classic-tokenfilter.md + - file: analysis-common-grams-tokenfilter.md + - file: analysis-condition-tokenfilter.md + - file: analysis-decimal-digit-tokenfilter.md + - file: analysis-delimited-payload-tokenfilter.md + - file: analysis-dict-decomp-tokenfilter.md + - file: analysis-edgengram-tokenfilter.md + - file: analysis-elision-tokenfilter.md + - file: analysis-fingerprint-tokenfilter.md + - file: analysis-flatten-graph-tokenfilter.md + - file: analysis-hunspell-tokenfilter.md + - file: analysis-hyp-decomp-tokenfilter.md + - file: analysis-keep-types-tokenfilter.md + - file: analysis-keep-words-tokenfilter.md + - file: analysis-keyword-marker-tokenfilter.md + - file: analysis-keyword-repeat-tokenfilter.md + - file: analysis-kstem-tokenfilter.md + - file: analysis-length-tokenfilter.md + - file: analysis-limit-token-count-tokenfilter.md + - file: analysis-lowercase-tokenfilter.md + - file: analysis-minhash-tokenfilter.md + - file: analysis-multiplexer-tokenfilter.md + - file: analysis-ngram-tokenfilter.md + - file: analysis-normalization-tokenfilter.md + - file: analysis-pattern-capture-tokenfilter.md + - file: analysis-pattern_replace-tokenfilter.md + - file: analysis-phonetic-tokenfilter.md + - file: analysis-porterstem-tokenfilter.md + - file: analysis-predicatefilter-tokenfilter.md + - file: analysis-remove-duplicates-tokenfilter.md + - file: analysis-reverse-tokenfilter.md + - file: analysis-shingle-tokenfilter.md + - file: analysis-snowball-tokenfilter.md + - file: analysis-stemmer-tokenfilter.md + - file: analysis-stemmer-override-tokenfilter.md + - file: analysis-stop-tokenfilter.md + - file: analysis-synonym-tokenfilter.md + - file: analysis-synonym-graph-tokenfilter.md + - file: analysis-trim-tokenfilter.md + - file: analysis-truncate-tokenfilter.md + - file: analysis-unique-tokenfilter.md + - file: analysis-uppercase-tokenfilter.md + - file: analysis-word-delimiter-tokenfilter.md + - file: analysis-word-delimiter-graph-tokenfilter.md + - file: character-filter-reference.md + children: + - file: analysis-htmlstrip-charfilter.md + - file: analysis-mapping-charfilter.md + - file: analysis-pattern-replace-charfilter.md + - file: normalizers.md \ No newline at end of file diff --git a/docs/reference/data-analysis/text-analysis/token-filter-reference.md b/docs/reference/text-analysis/token-filter-reference.md similarity index 73% rename from docs/reference/data-analysis/text-analysis/token-filter-reference.md rename to docs/reference/text-analysis/token-filter-reference.md index 6f3f094362c93..3892b56ce5f0b 100644 --- a/docs/reference/data-analysis/text-analysis/token-filter-reference.md +++ b/docs/reference/text-analysis/token-filter-reference.md @@ -5,7 +5,7 @@ mapped_pages: # Token filter reference [analysis-tokenfilters] -Token filters accept a stream of tokens from a [tokenizer](/reference/data-analysis/text-analysis/tokenizer-reference.md) and can modify tokens (eg lowercasing), delete tokens (eg remove stopwords) or add tokens (eg synonyms). +Token filters accept a stream of tokens from a [tokenizer](/reference/text-analysis/tokenizer-reference.md) and can modify tokens (eg lowercasing), delete tokens (eg remove stopwords) or add tokens (eg synonyms). {{es}} has a number of built-in token filters you can use to build [custom analyzers](docs-content://manage-data/data-store/text-analysis/create-custom-analyzer.md). diff --git a/docs/reference/data-analysis/text-analysis/tokenizer-reference.md b/docs/reference/text-analysis/tokenizer-reference.md similarity index 71% rename from docs/reference/data-analysis/text-analysis/tokenizer-reference.md rename to docs/reference/text-analysis/tokenizer-reference.md index 4ac3aaa7ea78b..6af43b253ae9a 100644 --- a/docs/reference/data-analysis/text-analysis/tokenizer-reference.md +++ b/docs/reference/text-analysis/tokenizer-reference.md @@ -13,7 +13,7 @@ mapped_pages: :::: -A *tokenizer* receives a stream of characters, breaks it up into individual *tokens* (usually individual words), and outputs a stream of *tokens*. For instance, a [`whitespace`](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) tokenizer breaks text into tokens whenever it sees any whitespace. It would convert the text `"Quick brown fox!"` into the terms `[Quick, brown, fox!]`. +A *tokenizer* receives a stream of characters, breaks it up into individual *tokens* (usually individual words), and outputs a stream of *tokens*. For instance, a [`whitespace`](/reference/text-analysis/analysis-whitespace-tokenizer.md) tokenizer breaks text into tokens whenever it sees any whitespace. It would convert the text `"Quick brown fox!"` into the terms `[Quick, brown, fox!]`. The tokenizer is also responsible for recording the following: @@ -28,25 +28,25 @@ Elasticsearch has a number of built in tokenizers which can be used to build [cu The following tokenizers are usually used for tokenizing full text into individual words: -[Standard Tokenizer](/reference/data-analysis/text-analysis/analysis-standard-tokenizer.md) +[Standard Tokenizer](/reference/text-analysis/analysis-standard-tokenizer.md) : The `standard` tokenizer divides text into terms on word boundaries, as defined by the Unicode Text Segmentation algorithm. It removes most punctuation symbols. It is the best choice for most languages. -[Letter Tokenizer](/reference/data-analysis/text-analysis/analysis-letter-tokenizer.md) +[Letter Tokenizer](/reference/text-analysis/analysis-letter-tokenizer.md) : The `letter` tokenizer divides text into terms whenever it encounters a character which is not a letter. -[Lowercase Tokenizer](/reference/data-analysis/text-analysis/analysis-lowercase-tokenizer.md) +[Lowercase Tokenizer](/reference/text-analysis/analysis-lowercase-tokenizer.md) : The `lowercase` tokenizer, like the `letter` tokenizer, divides text into terms whenever it encounters a character which is not a letter, but it also lowercases all terms. -[Whitespace Tokenizer](/reference/data-analysis/text-analysis/analysis-whitespace-tokenizer.md) +[Whitespace Tokenizer](/reference/text-analysis/analysis-whitespace-tokenizer.md) : The `whitespace` tokenizer divides text into terms whenever it encounters any whitespace character. -[UAX URL Email Tokenizer](/reference/data-analysis/text-analysis/analysis-uaxurlemail-tokenizer.md) +[UAX URL Email Tokenizer](/reference/text-analysis/analysis-uaxurlemail-tokenizer.md) : The `uax_url_email` tokenizer is like the `standard` tokenizer except that it recognises URLs and email addresses as single tokens. -[Classic Tokenizer](/reference/data-analysis/text-analysis/analysis-classic-tokenizer.md) +[Classic Tokenizer](/reference/text-analysis/analysis-classic-tokenizer.md) : The `classic` tokenizer is a grammar based tokenizer for the English Language. -[Thai Tokenizer](/reference/data-analysis/text-analysis/analysis-thai-tokenizer.md) +[Thai Tokenizer](/reference/text-analysis/analysis-thai-tokenizer.md) : The `thai` tokenizer segments Thai text into words. @@ -54,10 +54,10 @@ The following tokenizers are usually used for tokenizing full text into individu These tokenizers break up text or words into small fragments, for partial word matching: -[N-Gram Tokenizer](/reference/data-analysis/text-analysis/analysis-ngram-tokenizer.md) +[N-Gram Tokenizer](/reference/text-analysis/analysis-ngram-tokenizer.md) : The `ngram` tokenizer can break up text into words when it encounters any of a list of specified characters (e.g. whitespace or punctuation), then it returns n-grams of each word: a sliding window of continuous letters, e.g. `quick` → `[qu, ui, ic, ck]`. -[Edge N-Gram Tokenizer](/reference/data-analysis/text-analysis/analysis-edgengram-tokenizer.md) +[Edge N-Gram Tokenizer](/reference/text-analysis/analysis-edgengram-tokenizer.md) : The `edge_ngram` tokenizer can break up text into words when it encounters any of a list of specified characters (e.g. whitespace or punctuation), then it returns n-grams of each word which are anchored to the start of the word, e.g. `quick` → `[q, qu, qui, quic, quick]`. @@ -65,22 +65,22 @@ These tokenizers break up text or words into small fragments, for partial word m The following tokenizers are usually used with structured text like identifiers, email addresses, zip codes, and paths, rather than with full text: -[Keyword Tokenizer](/reference/data-analysis/text-analysis/analysis-keyword-tokenizer.md) -: The `keyword` tokenizer is a noop tokenizer that accepts whatever text it is given and outputs the exact same text as a single term. It can be combined with token filters like [`lowercase`](/reference/data-analysis/text-analysis/analysis-lowercase-tokenfilter.md) to normalise the analysed terms. +[Keyword Tokenizer](/reference/text-analysis/analysis-keyword-tokenizer.md) +: The `keyword` tokenizer is a noop tokenizer that accepts whatever text it is given and outputs the exact same text as a single term. It can be combined with token filters like [`lowercase`](/reference/text-analysis/analysis-lowercase-tokenfilter.md) to normalise the analysed terms. -[Pattern Tokenizer](/reference/data-analysis/text-analysis/analysis-pattern-tokenizer.md) +[Pattern Tokenizer](/reference/text-analysis/analysis-pattern-tokenizer.md) : The `pattern` tokenizer uses a regular expression to either split text into terms whenever it matches a word separator, or to capture matching text as terms. -[Simple Pattern Tokenizer](/reference/data-analysis/text-analysis/analysis-simplepattern-tokenizer.md) +[Simple Pattern Tokenizer](/reference/text-analysis/analysis-simplepattern-tokenizer.md) : The `simple_pattern` tokenizer uses a regular expression to capture matching text as terms. It uses a restricted subset of regular expression features and is generally faster than the `pattern` tokenizer. -[Char Group Tokenizer](/reference/data-analysis/text-analysis/analysis-chargroup-tokenizer.md) +[Char Group Tokenizer](/reference/text-analysis/analysis-chargroup-tokenizer.md) : The `char_group` tokenizer is configurable through sets of characters to split on, which is usually less expensive than running regular expressions. -[Simple Pattern Split Tokenizer](/reference/data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md) +[Simple Pattern Split Tokenizer](/reference/text-analysis/analysis-simplepatternsplit-tokenizer.md) : The `simple_pattern_split` tokenizer uses the same restricted regular expression subset as the `simple_pattern` tokenizer, but splits the input at matches rather than returning the matches as terms. -[Path Tokenizer](/reference/data-analysis/text-analysis/analysis-pathhierarchy-tokenizer.md) +[Path Tokenizer](/reference/text-analysis/analysis-pathhierarchy-tokenizer.md) : The `path_hierarchy` tokenizer takes a hierarchical value like a filesystem path, splits on the path separator, and emits a term for each component in the tree, e.g. `/foo/bar/baz` → `[/foo, /foo/bar, /foo/bar/baz ]`. diff --git a/docs/reference/toc.yml b/docs/reference/toc.yml deleted file mode 100644 index 46398e22d9e6e..0000000000000 --- a/docs/reference/toc.yml +++ /dev/null @@ -1,792 +0,0 @@ -toc: - - file: index.md - - file: elasticsearch/configuration-reference/index.md - children: - - file: elasticsearch/configuration-reference/circuit-breaker-settings.md - - file: elasticsearch/configuration-reference/auding-settings.md - - file: elasticsearch/configuration-reference/enrich-settings.md - - file: elasticsearch/configuration-reference/cluster-level-shard-allocation-routing-settings.md - - file: elasticsearch/configuration-reference/miscellaneous-cluster-settings.md - - file: elasticsearch/configuration-reference/cross-cluster-replication-settings.md - - file: elasticsearch/configuration-reference/discovery-cluster-formation-settings.md - - file: elasticsearch/configuration-reference/field-data-cache-settings.md - - file: elasticsearch/configuration-reference/health-diagnostic-settings.md - - file: elasticsearch/configuration-reference/index-lifecycle-management-settings.md - - file: elasticsearch/configuration-reference/data-stream-lifecycle-settings.md - - file: elasticsearch/configuration-reference/index-management-settings.md - - file: elasticsearch/configuration-reference/index-recovery-settings.md - - file: elasticsearch/configuration-reference/indexing-buffer-settings.md - - file: elasticsearch/configuration-reference/license-settings.md - - file: elasticsearch/configuration-reference/local-gateway.md - - file: elasticsearch/configuration-reference/machine-learning-settings.md - - file: elasticsearch/configuration-reference/inference-settings.md - - file: elasticsearch/configuration-reference/monitoring-settings.md - - file: elasticsearch/configuration-reference/node-settings.md - - file: elasticsearch/configuration-reference/networking-settings.md - - file: elasticsearch/configuration-reference/node-query-cache-settings.md - - file: elasticsearch/configuration-reference/search-settings.md - - file: elasticsearch/configuration-reference/security-settings.md - - file: elasticsearch/configuration-reference/shard-request-cache-settings.md - - file: elasticsearch/configuration-reference/snapshot-restore-settings.md - - file: elasticsearch/configuration-reference/transforms-settings.md - - file: elasticsearch/configuration-reference/thread-pool-settings.md - - file: elasticsearch/configuration-reference/watcher-settings.md - - file: elasticsearch/jvm-settings.md - - file: elasticsearch/roles.md - - file: elasticsearch/security-privileges.md - - file: elasticsearch/index-settings/index.md - children: - - file: elasticsearch/index-settings/data-tier-allocation.md - - file: elasticsearch/index-settings/index-modules.md - - file: elasticsearch/index-settings/history-retention.md - - file: elasticsearch/index-settings/index-block.md - - file: elasticsearch/index-settings/recovery-prioritization.md - - file: elasticsearch/index-settings/pressure.md - - file: elasticsearch/index-settings/mapping-limit.md - - file: elasticsearch/index-settings/merge.md - - file: elasticsearch/index-settings/path.md - - file: elasticsearch/index-settings/shard-allocation.md - children: - - file: elasticsearch/index-settings/total-shards-per-node.md - - file: elasticsearch/index-settings/similarity.md - - file: elasticsearch/index-settings/slow-log.md - - file: elasticsearch/index-settings/sorting.md - children: - - file: elasticsearch/index-settings/sorting-conjunctions.md - - file: elasticsearch/index-settings/store.md - children: - - file: elasticsearch/index-settings/preloading-data-into-file-system-cache.md - - file: elasticsearch/index-settings/time-series.md - - file: elasticsearch/index-settings/translog.md - - file: elasticsearch/index-lifecycle-actions/index.md - children: - - file: elasticsearch/index-lifecycle-actions/index.md - - file: elasticsearch/index-lifecycle-actions/ilm-allocate.md - - file: elasticsearch/index-lifecycle-actions/ilm-delete.md - - file: elasticsearch/index-lifecycle-actions/ilm-forcemerge.md - - file: elasticsearch/index-lifecycle-actions/ilm-migrate.md - - file: elasticsearch/index-lifecycle-actions/ilm-readonly.md - - file: elasticsearch/index-lifecycle-actions/ilm-rollover.md - - file: elasticsearch/index-lifecycle-actions/ilm-downsample.md - - file: elasticsearch/index-lifecycle-actions/ilm-searchable-snapshot.md - - file: elasticsearch/index-lifecycle-actions/ilm-set-priority.md - - file: elasticsearch/index-lifecycle-actions/ilm-shrink.md - - file: elasticsearch/index-lifecycle-actions/ilm-unfollow.md - - file: elasticsearch/index-lifecycle-actions/ilm-wait-for-snapshot.md - - file: elasticsearch/rest-apis/index.md - children: - - file: elasticsearch/rest-apis/api-conventions.md - - file: elasticsearch/rest-apis/common-options.md - - file: elasticsearch/rest-apis/compatibility.md - - file: elasticsearch/rest-apis/api-examples.md - children: - - file: elasticsearch/rest-apis/refresh-parameter.md - - file: elasticsearch/rest-apis/optimistic-concurrency-control.md - - file: elasticsearch/rest-apis/sort-search-results.md - - file: elasticsearch/rest-apis/paginate-search-results.md - - file: elasticsearch/rest-apis/retrieve-selected-fields.md - - file: elasticsearch/rest-apis/search-multiple-data-streams-indices.md - - file: elasticsearch/rest-apis/collapse-search-results.md - - file: elasticsearch/rest-apis/filter-search-results.md - - file: elasticsearch/rest-apis/highlighting.md - - file: elasticsearch/rest-apis/retrieve-inner-hits.md - - file: elasticsearch/rest-apis/search-shard-routing.md - - file: elasticsearch/rest-apis/searching-with-query-rules.md - - file: elasticsearch/rest-apis/reciprocal-rank-fusion.md - - file: elasticsearch/rest-apis/retrievers.md - - file: elasticsearch/rest-apis/reindex-data-stream.md - - file: elasticsearch/rest-apis/create-index-from-source.md - - file: elasticsearch/rest-apis/shard-request-cache.md - - file: elasticsearch/rest-apis/search-suggesters.md - - file: elasticsearch/mapping-reference/index.md - children: - - file: elasticsearch/mapping-reference/document-metadata-fields.md - children: - - file: elasticsearch/mapping-reference/mapping-doc-count-field.md - - file: elasticsearch/mapping-reference/mapping-field-names-field.md - - file: elasticsearch/mapping-reference/mapping-ignored-field.md - - file: elasticsearch/mapping-reference/mapping-id-field.md - - file: elasticsearch/mapping-reference/mapping-index-field.md - - file: elasticsearch/mapping-reference/mapping-meta-field.md - - file: elasticsearch/mapping-reference/mapping-routing-field.md - - file: elasticsearch/mapping-reference/mapping-source-field.md - - file: elasticsearch/mapping-reference/mapping-tier-field.md - - file: elasticsearch/mapping-reference/field-data-types.md - children: - - file: elasticsearch/mapping-reference/aggregate-metric-double.md - - file: elasticsearch/mapping-reference/field-alias.md - - file: elasticsearch/mapping-reference/array.md - - file: elasticsearch/mapping-reference/binary.md - - file: elasticsearch/mapping-reference/boolean.md - - file: elasticsearch/mapping-reference/completion.md - - file: elasticsearch/mapping-reference/date.md - - file: elasticsearch/mapping-reference/date_nanos.md - - file: elasticsearch/mapping-reference/dense-vector.md - - file: elasticsearch/mapping-reference/flattened.md - - file: elasticsearch/mapping-reference/geo-point.md - - file: elasticsearch/mapping-reference/geo-shape.md - - file: elasticsearch/mapping-reference/histogram.md - - file: elasticsearch/mapping-reference/ip.md - - file: elasticsearch/mapping-reference/parent-join.md - - file: elasticsearch/mapping-reference/keyword.md - - file: elasticsearch/mapping-reference/nested.md - - file: elasticsearch/mapping-reference/number.md - - file: elasticsearch/mapping-reference/object.md - - file: elasticsearch/mapping-reference/passthrough.md - - file: elasticsearch/mapping-reference/percolator.md - - file: elasticsearch/mapping-reference/point.md - - file: elasticsearch/mapping-reference/range.md - - file: elasticsearch/mapping-reference/rank-feature.md - - file: elasticsearch/mapping-reference/rank-features.md - - file: elasticsearch/mapping-reference/rank-vectors.md - - file: elasticsearch/mapping-reference/search-as-you-type.md - - file: elasticsearch/mapping-reference/semantic-text.md - - file: elasticsearch/mapping-reference/shape.md - - file: elasticsearch/mapping-reference/sparse-vector.md - - file: elasticsearch/mapping-reference/text.md - - file: elasticsearch/mapping-reference/token-count.md - - file: elasticsearch/mapping-reference/unsigned-long.md - - file: elasticsearch/mapping-reference/version.md - - file: elasticsearch/mapping-reference/mapping-parameters.md - children: - - file: elasticsearch/mapping-reference/analyzer.md - - file: elasticsearch/mapping-reference/coerce.md - - file: elasticsearch/mapping-reference/copy-to.md - - file: elasticsearch/mapping-reference/doc-values.md - - file: elasticsearch/mapping-reference/dynamic.md - - file: elasticsearch/mapping-reference/eager-global-ordinals.md - - file: elasticsearch/mapping-reference/enabled.md - - file: elasticsearch/mapping-reference/mapping-date-format.md - - file: elasticsearch/mapping-reference/ignore-above.md - - file: elasticsearch/mapping-reference/index-mapping-ignore-above.md - - file: elasticsearch/mapping-reference/ignore-malformed.md - - file: elasticsearch/mapping-reference/mapping-index.md - - file: elasticsearch/mapping-reference/index-options.md - - file: elasticsearch/mapping-reference/index-phrases.md - - file: elasticsearch/mapping-reference/index-prefixes.md - - file: elasticsearch/mapping-reference/mapping-field-meta.md - - file: elasticsearch/mapping-reference/multi-fields.md - - file: elasticsearch/mapping-reference/normalizer.md - - file: elasticsearch/mapping-reference/norms.md - - file: elasticsearch/mapping-reference/null-value.md - - file: elasticsearch/mapping-reference/position-increment-gap.md - - file: elasticsearch/mapping-reference/properties.md - - file: elasticsearch/mapping-reference/search-analyzer.md - - file: elasticsearch/mapping-reference/similarity.md - - file: elasticsearch/mapping-reference/mapping-store.md - - file: elasticsearch/mapping-reference/subobjects.md - - file: elasticsearch/mapping-reference/term-vector.md - - file: elasticsearch/elasticsearch-audit-events.md - - file: elasticsearch/command-line-tools/index.md - children: - - file: elasticsearch/command-line-tools/certgen.md - - file: elasticsearch/command-line-tools/certutil.md - - file: elasticsearch/command-line-tools/create-enrollment-token.md - - file: elasticsearch/command-line-tools/elasticsearch-croneval.md - - file: elasticsearch/command-line-tools/elasticsearch-keystore.md - - file: elasticsearch/command-line-tools/node-tool.md - - file: elasticsearch/command-line-tools/reconfigure-node.md - - file: elasticsearch/command-line-tools/reset-password.md - - file: elasticsearch/command-line-tools/saml-metadata.md - - file: elasticsearch/command-line-tools/service-tokens-command.md - - file: elasticsearch/command-line-tools/setup-passwords.md - - file: elasticsearch/command-line-tools/shard-tool.md - - file: elasticsearch/command-line-tools/syskeygen.md - - file: elasticsearch/command-line-tools/users-command.md - - file: community-contributed.md - - file: ingestion-tools/enrich-processor/index.md - children: - - file: ingestion-tools/enrich-processor/append-processor.md - - file: ingestion-tools/enrich-processor/attachment.md - - file: ingestion-tools/enrich-processor/bytes-processor.md - - file: ingestion-tools/enrich-processor/ingest-circle-processor.md - - file: ingestion-tools/enrich-processor/community-id-processor.md - - file: ingestion-tools/enrich-processor/convert-processor.md - - file: ingestion-tools/enrich-processor/csv-processor.md - - file: ingestion-tools/enrich-processor/date-processor.md - - file: ingestion-tools/enrich-processor/date-index-name-processor.md - - file: ingestion-tools/enrich-processor/dissect-processor.md - - file: ingestion-tools/enrich-processor/dot-expand-processor.md - - file: ingestion-tools/enrich-processor/drop-processor.md - - file: ingestion-tools/enrich-processor/enrich-processor.md - - file: ingestion-tools/enrich-processor/fail-processor.md - - file: ingestion-tools/enrich-processor/fingerprint-processor.md - - file: ingestion-tools/enrich-processor/foreach-processor.md - - file: ingestion-tools/enrich-processor/ingest-geo-grid-processor.md - - file: ingestion-tools/enrich-processor/geoip-processor.md - - file: ingestion-tools/enrich-processor/grok-processor.md - - file: ingestion-tools/enrich-processor/gsub-processor.md - - file: ingestion-tools/enrich-processor/htmlstrip-processor.md - - file: ingestion-tools/enrich-processor/inference-processor.md - - file: ingestion-tools/enrich-processor/ip-location-processor.md - - file: ingestion-tools/enrich-processor/join-processor.md - - file: ingestion-tools/enrich-processor/json-processor.md - - file: ingestion-tools/enrich-processor/kv-processor.md - - file: ingestion-tools/enrich-processor/lowercase-processor.md - - file: ingestion-tools/enrich-processor/network-direction-processor.md - - file: ingestion-tools/enrich-processor/pipeline-processor.md - - file: ingestion-tools/enrich-processor/redact-processor.md - - file: ingestion-tools/enrich-processor/registered-domain-processor.md - - file: ingestion-tools/enrich-processor/remove-processor.md - - file: ingestion-tools/enrich-processor/rename-processor.md - - file: ingestion-tools/enrich-processor/reroute-processor.md - - file: ingestion-tools/enrich-processor/script-processor.md - - file: ingestion-tools/enrich-processor/set-processor.md - - file: ingestion-tools/enrich-processor/ingest-node-set-security-user-processor.md - - file: ingestion-tools/enrich-processor/sort-processor.md - - file: ingestion-tools/enrich-processor/split-processor.md - - file: ingestion-tools/enrich-processor/terminate-processor.md - - file: ingestion-tools/enrich-processor/trim-processor.md - - file: ingestion-tools/enrich-processor/uppercase-processor.md - - file: ingestion-tools/enrich-processor/urldecode-processor.md - - file: ingestion-tools/enrich-processor/uri-parts-processor.md - - file: ingestion-tools/enrich-processor/user-agent-processor.md - - file: ingestion-tools/search-connectors/index.md - children: - - file: ingestion-tools/search-connectors/connector-reference.md - children: - - file: ingestion-tools/search-connectors/es-connectors-azure-blob.md - - file: ingestion-tools/search-connectors/es-connectors-box.md - - file: ingestion-tools/search-connectors/es-connectors-confluence.md - - file: ingestion-tools/search-connectors/es-connectors-dropbox.md - - file: ingestion-tools/search-connectors/es-connectors-github.md - - file: ingestion-tools/search-connectors/es-connectors-gmail.md - - file: ingestion-tools/search-connectors/es-connectors-google-cloud.md - - file: ingestion-tools/search-connectors/es-connectors-google-drive.md - - file: ingestion-tools/search-connectors/es-connectors-graphql.md - - file: ingestion-tools/search-connectors/es-connectors-jira.md - - file: ingestion-tools/search-connectors/es-connectors-ms-sql.md - - file: ingestion-tools/search-connectors/es-connectors-mongodb.md - - file: ingestion-tools/search-connectors/es-connectors-mysql.md - - file: ingestion-tools/search-connectors/es-connectors-network-drive.md - - file: ingestion-tools/search-connectors/es-connectors-notion.md - - file: ingestion-tools/search-connectors/es-connectors-onedrive.md - - file: ingestion-tools/search-connectors/es-connectors-opentext.md - - file: ingestion-tools/search-connectors/es-connectors-oracle.md - - file: ingestion-tools/search-connectors/es-connectors-outlook.md - - file: ingestion-tools/search-connectors/es-connectors-postgresql.md - - file: ingestion-tools/search-connectors/es-connectors-redis.md - - file: ingestion-tools/search-connectors/es-connectors-s3.md - - file: ingestion-tools/search-connectors/es-connectors-salesforce.md - - file: ingestion-tools/search-connectors/es-connectors-servicenow.md - - file: ingestion-tools/search-connectors/es-connectors-sharepoint-online.md - - file: ingestion-tools/search-connectors/es-connectors-sharepoint.md - - file: ingestion-tools/search-connectors/es-connectors-slack.md - - file: ingestion-tools/search-connectors/es-connectors-teams.md - - file: ingestion-tools/search-connectors/es-connectors-zoom.md - - file: ingestion-tools/search-connectors/self-managed-connectors.md - children: - - file: ingestion-tools/search-connectors/es-connectors-run-from-docker.md - - file: ingestion-tools/search-connectors/es-connectors-run-from-source.md - - file: ingestion-tools/search-connectors/es-connectors-docker-compose-quickstart.md - - file: ingestion-tools/search-connectors/es-postgresql-connector-client-tutorial.md - - file: ingestion-tools/search-connectors/elastic-managed-connectors.md # TODO: I should be deleted - - file: ingestion-tools/search-connectors/build-customize-connectors.md - - file: ingestion-tools/search-connectors/connectors-ui-in-kibana.md - # TO DO: Do we want this page? (It's not in the inventory.) - - file: ingestion-tools/search-connectors/es-connectors-apis.md - children: - - file: ingestion-tools/search-connectors/api-tutorial.md - - file: ingestion-tools/search-connectors/content-syncs.md - - file: ingestion-tools/search-connectors/extract-transform.md - children: - - file: ingestion-tools/search-connectors/es-connectors-content-extraction.md - - file: ingestion-tools/search-connectors/es-sync-rules.md - - file: ingestion-tools/search-connectors/document-level-security.md - children: - - file: ingestion-tools/search-connectors/es-dls-overview.md - - file: ingestion-tools/search-connectors/es-dls-e2e-guide.md - - file: ingestion-tools/search-connectors/management.md - children: - - file: ingestion-tools/search-connectors/es-connectors-scalability.md - - file: ingestion-tools/search-connectors/es-connectors-security.md - - file: ingestion-tools/search-connectors/es-connectors-troubleshooting.md - - file: ingestion-tools/search-connectors/es-connectors-logs.md - - file: ingestion-tools/search-connectors/use-cases.md - children: - - file: ingestion-tools/search-connectors/es-connectors-overview-architecture.md - - file: elasticsearch-plugins/index.md - children: - - file: elasticsearch-plugins/plugin-management.md - children: - - file: elasticsearch-plugins/installation.md - - file: elasticsearch-plugins/plugin-management-custom-url.md - - file: elasticsearch-plugins/installing-multiple-plugins.md - - file: elasticsearch-plugins/mandatory-plugins.md - - file: elasticsearch-plugins/listing-removing-updating.md - - file: elasticsearch-plugins/_other_command_line_parameters.md - - file: elasticsearch-plugins/_plugins_directory.md - - file: elasticsearch-plugins/manage-plugins-using-configuration-file.md - - file: elasticsearch-plugins/cloud/ec-custom-bundles.md - - file: elasticsearch-plugins/cloud/ec-plugins-guide.md - - file: elasticsearch-plugins/api-extension-plugins.md - - file: elasticsearch-plugins/analysis-plugins.md - children: - - file: elasticsearch-plugins/analysis-icu.md - children: - - file: elasticsearch-plugins/analysis-icu-analyzer.md - - file: elasticsearch-plugins/analysis-icu-normalization-charfilter.md - - file: elasticsearch-plugins/analysis-icu-tokenizer.md - - file: elasticsearch-plugins/analysis-icu-normalization.md - - file: elasticsearch-plugins/analysis-icu-folding.md - - file: elasticsearch-plugins/analysis-icu-collation.md - - file: elasticsearch-plugins/analysis-icu-collation-keyword-field.md - - file: elasticsearch-plugins/analysis-icu-transform.md - - file: elasticsearch-plugins/analysis-kuromoji.md - children: - - file: elasticsearch-plugins/analysis-kuromoji-analyzer.md - - file: elasticsearch-plugins/analysis-kuromoji-charfilter.md - - file: elasticsearch-plugins/analysis-kuromoji-tokenizer.md - - file: elasticsearch-plugins/analysis-kuromoji-baseform.md - - file: elasticsearch-plugins/analysis-kuromoji-speech.md - - file: elasticsearch-plugins/analysis-kuromoji-readingform.md - - file: elasticsearch-plugins/analysis-kuromoji-stemmer.md - - file: elasticsearch-plugins/analysis-kuromoji-stop.md - - file: elasticsearch-plugins/analysis-kuromoji-number.md - - file: elasticsearch-plugins/analysis-kuromoji-hiragana-uppercase.md - - file: elasticsearch-plugins/analysis-kuromoji-katakana-uppercase.md - - file: elasticsearch-plugins/analysis-kuromoji-completion.md - - file: elasticsearch-plugins/analysis-nori.md - children: - - file: elasticsearch-plugins/analysis-nori-analyzer.md - - file: elasticsearch-plugins/analysis-nori-tokenizer.md - - file: elasticsearch-plugins/analysis-nori-speech.md - - file: elasticsearch-plugins/analysis-nori-readingform.md - - file: elasticsearch-plugins/analysis-nori-number.md - - file: elasticsearch-plugins/analysis-phonetic.md - children: - - file: elasticsearch-plugins/analysis-phonetic-token-filter.md - - file: elasticsearch-plugins/analysis-smartcn.md - children: - - file: elasticsearch-plugins/_reimplementing_and_extending_the_analyzers.md - - file: elasticsearch-plugins/analysis-smartcn_stop.md - - file: elasticsearch-plugins/analysis-stempel.md - children: - - file: elasticsearch-plugins/_reimplementing_and_extending_the_analyzers_2.md - - file: elasticsearch-plugins/analysis-polish-stop.md - - file: elasticsearch-plugins/analysis-ukrainian.md - - file: elasticsearch-plugins/discovery-plugins.md - children: - - file: elasticsearch-plugins/discovery-ec2.md - children: - - file: elasticsearch-plugins/discovery-ec2-usage.md - - file: elasticsearch-plugins/cloud-aws-best-practices.md - - file: elasticsearch-plugins/discovery-azure-classic.md - children: - - file: elasticsearch-plugins/discovery-azure-classic-usage.md - - file: elasticsearch-plugins/discovery-azure-classic-long.md - - file: elasticsearch-plugins/discovery-azure-classic-scale.md - - file: elasticsearch-plugins/discovery-gce.md - children: - - file: elasticsearch-plugins/discovery-gce-usage.md - - file: elasticsearch-plugins/discovery-gce-network-host.md - - file: elasticsearch-plugins/discovery-gce-usage-long.md - - file: elasticsearch-plugins/discovery-gce-usage-cloning.md - - file: elasticsearch-plugins/discovery-gce-usage-zones.md - - file: elasticsearch-plugins/discovery-gce-usage-tags.md - - file: elasticsearch-plugins/discovery-gce-usage-port.md - - file: elasticsearch-plugins/discovery-gce-usage-tips.md - - file: elasticsearch-plugins/discovery-gce-usage-testing.md - - file: elasticsearch-plugins/mapper-plugins.md - children: - - file: elasticsearch-plugins/mapper-size.md - children: - - file: elasticsearch-plugins/mapper-size-usage.md - - file: elasticsearch-plugins/mapper-murmur3.md - children: - - file: elasticsearch-plugins/mapper-murmur3-usage.md - - file: elasticsearch-plugins/mapper-annotated-text.md - children: - - file: elasticsearch-plugins/mapper-annotated-text-usage.md - - file: elasticsearch-plugins/mapper-annotated-text-tips.md - - file: elasticsearch-plugins/mapper-annotated-text-highlighter.md - - file: elasticsearch-plugins/mapper-annotated-text-limitations.md - - file: elasticsearch-plugins/snapshotrestore-repository-plugins.md - children: - - file: elasticsearch-plugins/repository-hdfs.md - children: - - file: elasticsearch-plugins/repository-hdfs-usage.md - - file: elasticsearch-plugins/repository-hdfs-config.md - - file: elasticsearch-plugins/repository-hdfs-security.md - - file: elasticsearch-plugins/store-plugins.md - children: - - file: elasticsearch-plugins/store-smb.md - children: - - file: elasticsearch-plugins/store-smb-usage.md - - file: elasticsearch-plugins/integrations.md - - file: query-languages/index.md - children: - - file: query-languages/querydsl.md - children: - - file: query-languages/query-dsl/query-filter-context.md - - file: query-languages/query-dsl/compound-queries.md - children: - - file: query-languages/query-dsl/query-dsl-bool-query.md - - file: query-languages/query-dsl/query-dsl-boosting-query.md - - file: query-languages/query-dsl/query-dsl-constant-score-query.md - - file: query-languages/query-dsl/query-dsl-dis-max-query.md - - file: query-languages/query-dsl/query-dsl-function-score-query.md - - file: query-languages/query-dsl/full-text-queries.md - children: - - file: query-languages/query-dsl/query-dsl-intervals-query.md - - file: query-languages/query-dsl/query-dsl-match-query.md - - file: query-languages/query-dsl/query-dsl-match-bool-prefix-query.md - - file: query-languages/query-dsl/query-dsl-match-query-phrase.md - - file: query-languages/query-dsl/query-dsl-match-query-phrase-prefix.md - - file: query-languages/query-dsl/query-dsl-combined-fields-query.md - - file: query-languages/query-dsl/query-dsl-multi-match-query.md - - file: query-languages/query-dsl/query-dsl-query-string-query.md - - file: query-languages/query-dsl/query-dsl-simple-query-string-query.md - - file: query-languages/query-dsl/geo-queries.md - children: - - file: query-languages/query-dsl/query-dsl-geo-bounding-box-query.md - - file: query-languages/query-dsl/query-dsl-geo-distance-query.md - - file: query-languages/query-dsl/query-dsl-geo-grid-query.md - - file: query-languages/query-dsl/query-dsl-geo-polygon-query.md - - file: query-languages/query-dsl/query-dsl-geo-shape-query.md - - file: query-languages/query-dsl/shape-queries.md - children: - - file: query-languages/query-dsl/query-dsl-shape-query.md - - file: query-languages/query-dsl/joining-queries.md - children: - - file: query-languages/query-dsl/query-dsl-nested-query.md - - file: query-languages/query-dsl/query-dsl-has-child-query.md - - file: query-languages/query-dsl/query-dsl-has-parent-query.md - - file: query-languages/query-dsl/query-dsl-parent-id-query.md - - file: query-languages/query-dsl/query-dsl-match-all-query.md - - file: query-languages/query-dsl/span-queries.md - children: - - file: query-languages/query-dsl/query-dsl-span-containing-query.md - - file: query-languages/query-dsl/query-dsl-span-field-masking-query.md - - file: query-languages/query-dsl/query-dsl-span-first-query.md - - file: query-languages/query-dsl/query-dsl-span-multi-term-query.md - - file: query-languages/query-dsl/query-dsl-span-near-query.md - - file: query-languages/query-dsl/query-dsl-span-not-query.md - - file: query-languages/query-dsl/query-dsl-span-query.md - - file: query-languages/query-dsl/query-dsl-span-term-query.md - - file: query-languages/query-dsl/query-dsl-span-within-query.md - - file: query-languages/query-dsl/vector-queries.md - children: - - file: query-languages/query-dsl/query-dsl-knn-query.md - - file: query-languages/query-dsl/query-dsl-sparse-vector-query.md - - file: query-languages/query-dsl/query-dsl-semantic-query.md - - file: query-languages/query-dsl/query-dsl-text-expansion-query.md - - file: query-languages/query-dsl/query-dsl-weighted-tokens-query.md - - file: query-languages/query-dsl/specialized-queries.md - children: - - file: query-languages/query-dsl/query-dsl-distance-feature-query.md - - file: query-languages/query-dsl/query-dsl-mlt-query.md - - file: query-languages/query-dsl/query-dsl-percolate-query.md - - file: query-languages/query-dsl/query-dsl-rank-feature-query.md - - file: query-languages/query-dsl/query-dsl-script-query.md - - file: query-languages/query-dsl/query-dsl-script-score-query.md - - file: query-languages/query-dsl/query-dsl-wrapper-query.md - - file: query-languages/query-dsl/query-dsl-pinned-query.md - - file: query-languages/query-dsl/query-dsl-rule-query.md - - file: query-languages/query-dsl/term-level-queries.md - children: - - file: query-languages/query-dsl/query-dsl-exists-query.md - - file: query-languages/query-dsl/query-dsl-fuzzy-query.md - - file: query-languages/query-dsl/query-dsl-ids-query.md - - file: query-languages/query-dsl/query-dsl-prefix-query.md - - file: query-languages/query-dsl/query-dsl-range-query.md - - file: query-languages/query-dsl/query-dsl-regexp-query.md - - file: query-languages/query-dsl/query-dsl-term-query.md - - file: query-languages/query-dsl/query-dsl-terms-query.md - - file: query-languages/query-dsl/query-dsl-terms-set-query.md - - file: query-languages/query-dsl/query-dsl-wildcard-query.md - - file: query-languages/query-dsl/query-dsl-minimum-should-match.md - - file: query-languages/query-dsl/query-dsl-multi-term-rewrite.md - - file: query-languages/query-dsl/regexp-syntax.md - - file: query-languages/esql.md - children: - - file: query-languages/esql/esql-syntax.md - - file: query-languages/esql/esql-commands.md - - file: query-languages/esql/esql-functions-operators.md - - file: query-languages/esql/esql-metadata-fields.md - - file: query-languages/esql/esql-multivalued-fields.md - - file: query-languages/esql/esql-process-data-with-dissect-grok.md - - file: query-languages/esql/esql-enrich-data.md - - file: query-languages/esql/esql-lookup-join.md - - file: query-languages/esql/esql-implicit-casting.md - - file: query-languages/esql/esql-time-spans.md - - file: query-languages/esql/limitations.md - - file: query-languages/esql/esql-examples.md - - file: query-languages/sql.md - children: - - file: query-languages/sql/sql-spec.md - children: - - file: query-languages/sql/sql-lexical-structure.md - - file: query-languages/sql/sql-commands.md - - file: query-languages/sql/sql-syntax-describe-table.md - - file: query-languages/sql/sql-syntax-select.md - - file: query-languages/sql/sql-syntax-show-catalogs.md - - file: query-languages/sql/sql-syntax-show-columns.md - - file: query-languages/sql/sql-syntax-show-functions.md - - file: query-languages/sql/sql-syntax-show-tables.md - - file: query-languages/sql/sql-data-types.md - - file: query-languages/sql/sql-index-patterns.md - - file: query-languages/sql/sql-index-frozen.md - - file: query-languages/sql/sql-functions.md - children: - - file: query-languages/sql/sql-operators.md - - file: query-languages/sql/sql-operators-logical.md - - file: query-languages/sql/sql-operators-math.md - - file: query-languages/sql/sql-operators-cast.md - - file: query-languages/sql/sql-like-rlike-operators.md - - file: query-languages/sql/sql-functions-aggs.md - - file: query-languages/sql/sql-functions-grouping.md - - file: query-languages/sql/sql-functions-datetime.md - - file: query-languages/sql/sql-functions-search.md - - file: query-languages/sql/sql-functions-math.md - - file: query-languages/sql/sql-functions-string.md - - file: query-languages/sql/sql-functions-type-conversion.md - - file: query-languages/sql/sql-functions-geo.md - - file: query-languages/sql/sql-functions-conditional.md - - file: query-languages/sql/sql-functions-system.md - - file: query-languages/sql/sql-syntax-reserved.md - - file: query-languages/sql/sql-limitations.md - - file: query-languages/eql.md - children: - - file: query-languages/eql/eql-syntax.md - - file: query-languages/eql/eql-function-ref.md - - file: query-languages/eql/eql-pipe-ref.md - - file: query-languages/eql/eql-ex-threat-detection.md - - file: query-languages/kql.md - - file: scripting-languages/index.md - children: - # - file: scripting-languages/reference/painless.md - - file: scripting-languages/painless/painless.md - children: - - file: scripting-languages/painless/brief-painless-walkthrough.md - - file: scripting-languages/painless/use-painless-scripts-in-runtime-fields.md - - file: scripting-languages/painless/using-datetime-in-painless.md - - file: scripting-languages/painless/how-painless-dispatches-function.md - - file: scripting-languages/painless/painless-debugging.md - - file: scripting-languages/painless/painless-api-examples.md - - file: scripting-languages/painless/using-ingest-processors-in-painless.md - - file: scripting-languages/painless/painless-language-specification.md - children: - - file: scripting-languages/painless/painless-comments.md - - file: scripting-languages/painless/painless-keywords.md - - file: scripting-languages/painless/painless-literals.md - - file: scripting-languages/painless/painless-identifiers.md - - file: scripting-languages/painless/painless-variables.md - - file: scripting-languages/painless/painless-types.md - - file: scripting-languages/painless/painless-casting.md - - file: scripting-languages/painless/painless-operators.md - - file: scripting-languages/painless/painless-operators-general.md - - file: scripting-languages/painless/painless-operators-numeric.md - - file: scripting-languages/painless/painless-operators-boolean.md - - file: scripting-languages/painless/painless-operators-reference.md - - file: scripting-languages/painless/painless-operators-array.md - - file: scripting-languages/painless/painless-statements.md - - file: scripting-languages/painless/painless-scripts.md - - file: scripting-languages/painless/painless-functions.md - - file: scripting-languages/painless/painless-lambdas.md - - file: scripting-languages/painless/painless-regexes.md - - file: scripting-languages/painless/painless-contexts.md - children: - - file: scripting-languages/painless/painless-context-examples.md - - file: scripting-languages/painless/painless-runtime-fields-context.md - - file: scripting-languages/painless/painless-ingest-processor-context.md - - file: scripting-languages/painless/painless-update-context.md - - file: scripting-languages/painless/painless-update-by-query-context.md - - file: scripting-languages/painless/painless-reindex-context.md - - file: scripting-languages/painless/painless-sort-context.md - - file: scripting-languages/painless/painless-similarity-context.md - - file: scripting-languages/painless/painless-weight-context.md - - file: scripting-languages/painless/painless-score-context.md - - file: scripting-languages/painless/painless-field-context.md - - file: scripting-languages/painless/painless-filter-context.md - - file: scripting-languages/painless/painless-min-should-match-context.md - - file: scripting-languages/painless/painless-metric-agg-init-context.md - - file: scripting-languages/painless/painless-metric-agg-map-context.md - - file: scripting-languages/painless/painless-metric-agg-combine-context.md - - file: scripting-languages/painless/painless-metric-agg-reduce-context.md - - file: scripting-languages/painless/painless-bucket-script-agg-context.md - - file: scripting-languages/painless/painless-bucket-selector-agg-context.md - - file: scripting-languages/painless/painless-analysis-predicate-context.md - - file: scripting-languages/painless/painless-watcher-condition-context.md - - file: scripting-languages/painless/painless-watcher-transform-context.md - - file: data-analysis/text-analysis/index.md - children: - - file: data-analysis/text-analysis/analyzer-reference.md - children: - - file: data-analysis/text-analysis/analysis-fingerprint-analyzer.md - - file: data-analysis/text-analysis/analysis-keyword-analyzer.md - - file: data-analysis/text-analysis/analysis-lang-analyzer.md - - file: data-analysis/text-analysis/analysis-pattern-analyzer.md - - file: data-analysis/text-analysis/analysis-simple-analyzer.md - - file: data-analysis/text-analysis/analysis-standard-analyzer.md - - file: data-analysis/text-analysis/analysis-stop-analyzer.md - - file: data-analysis/text-analysis/analysis-whitespace-analyzer.md - - file: data-analysis/text-analysis/tokenizer-reference.md - children: - - file: data-analysis/text-analysis/analysis-chargroup-tokenizer.md - - file: data-analysis/text-analysis/analysis-classic-tokenizer.md - - file: data-analysis/text-analysis/analysis-edgengram-tokenizer.md - - file: data-analysis/text-analysis/analysis-keyword-tokenizer.md - - file: data-analysis/text-analysis/analysis-letter-tokenizer.md - - file: data-analysis/text-analysis/analysis-lowercase-tokenizer.md - - file: data-analysis/text-analysis/analysis-ngram-tokenizer.md - - file: data-analysis/text-analysis/analysis-pathhierarchy-tokenizer.md - - file: data-analysis/text-analysis/analysis-pattern-tokenizer.md - - file: data-analysis/text-analysis/analysis-simplepattern-tokenizer.md - - file: data-analysis/text-analysis/analysis-simplepatternsplit-tokenizer.md - - file: data-analysis/text-analysis/analysis-standard-tokenizer.md - - file: data-analysis/text-analysis/analysis-thai-tokenizer.md - - file: data-analysis/text-analysis/analysis-uaxurlemail-tokenizer.md - - file: data-analysis/text-analysis/analysis-whitespace-tokenizer.md - - file: data-analysis/text-analysis/token-filter-reference.md - children: - - file: data-analysis/text-analysis/analysis-apostrophe-tokenfilter.md - - file: data-analysis/text-analysis/analysis-asciifolding-tokenfilter.md - - file: data-analysis/text-analysis/analysis-cjk-bigram-tokenfilter.md - - file: data-analysis/text-analysis/analysis-cjk-width-tokenfilter.md - - file: data-analysis/text-analysis/analysis-classic-tokenfilter.md - - file: data-analysis/text-analysis/analysis-common-grams-tokenfilter.md - - file: data-analysis/text-analysis/analysis-condition-tokenfilter.md - - file: data-analysis/text-analysis/analysis-decimal-digit-tokenfilter.md - - file: data-analysis/text-analysis/analysis-delimited-payload-tokenfilter.md - - file: data-analysis/text-analysis/analysis-dict-decomp-tokenfilter.md - - file: data-analysis/text-analysis/analysis-edgengram-tokenfilter.md - - file: data-analysis/text-analysis/analysis-elision-tokenfilter.md - - file: data-analysis/text-analysis/analysis-fingerprint-tokenfilter.md - - file: data-analysis/text-analysis/analysis-flatten-graph-tokenfilter.md - - file: data-analysis/text-analysis/analysis-hunspell-tokenfilter.md - - file: data-analysis/text-analysis/analysis-hyp-decomp-tokenfilter.md - - file: data-analysis/text-analysis/analysis-keep-types-tokenfilter.md - - file: data-analysis/text-analysis/analysis-keep-words-tokenfilter.md - - file: data-analysis/text-analysis/analysis-keyword-marker-tokenfilter.md - - file: data-analysis/text-analysis/analysis-keyword-repeat-tokenfilter.md - - file: data-analysis/text-analysis/analysis-kstem-tokenfilter.md - - file: data-analysis/text-analysis/analysis-length-tokenfilter.md - - file: data-analysis/text-analysis/analysis-limit-token-count-tokenfilter.md - - file: data-analysis/text-analysis/analysis-lowercase-tokenfilter.md - - file: data-analysis/text-analysis/analysis-minhash-tokenfilter.md - - file: data-analysis/text-analysis/analysis-multiplexer-tokenfilter.md - - file: data-analysis/text-analysis/analysis-ngram-tokenfilter.md - - file: data-analysis/text-analysis/analysis-normalization-tokenfilter.md - - file: data-analysis/text-analysis/analysis-pattern-capture-tokenfilter.md - - file: data-analysis/text-analysis/analysis-pattern_replace-tokenfilter.md - - file: data-analysis/text-analysis/analysis-phonetic-tokenfilter.md - - file: data-analysis/text-analysis/analysis-porterstem-tokenfilter.md - - file: data-analysis/text-analysis/analysis-predicatefilter-tokenfilter.md - - file: data-analysis/text-analysis/analysis-remove-duplicates-tokenfilter.md - - file: data-analysis/text-analysis/analysis-reverse-tokenfilter.md - - file: data-analysis/text-analysis/analysis-shingle-tokenfilter.md - - file: data-analysis/text-analysis/analysis-snowball-tokenfilter.md - - file: data-analysis/text-analysis/analysis-stemmer-tokenfilter.md - - file: data-analysis/text-analysis/analysis-stemmer-override-tokenfilter.md - - file: data-analysis/text-analysis/analysis-stop-tokenfilter.md - - file: data-analysis/text-analysis/analysis-synonym-tokenfilter.md - - file: data-analysis/text-analysis/analysis-synonym-graph-tokenfilter.md - - file: data-analysis/text-analysis/analysis-trim-tokenfilter.md - - file: data-analysis/text-analysis/analysis-truncate-tokenfilter.md - - file: data-analysis/text-analysis/analysis-unique-tokenfilter.md - - file: data-analysis/text-analysis/analysis-uppercase-tokenfilter.md - - file: data-analysis/text-analysis/analysis-word-delimiter-tokenfilter.md - - file: data-analysis/text-analysis/analysis-word-delimiter-graph-tokenfilter.md - - file: data-analysis/text-analysis/character-filter-reference.md - children: - - file: data-analysis/text-analysis/analysis-htmlstrip-charfilter.md - - file: data-analysis/text-analysis/analysis-mapping-charfilter.md - - file: data-analysis/text-analysis/analysis-pattern-replace-charfilter.md - - file: data-analysis/text-analysis/normalizers.md - - file: data-analysis/aggregations/index.md - children: - - file: data-analysis/aggregations/bucket.md - children: - - file: data-analysis/aggregations/search-aggregations-bucket-adjacency-matrix-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-autodatehistogram-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-categorize-text-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-children-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-composite-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-datehistogram-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-daterange-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-diversified-sampler-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-filter-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-filters-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-frequent-item-sets-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-geodistance-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-geohashgrid-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-geohexgrid-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-geotilegrid-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-global-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-histogram-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-ipprefix-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-iprange-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-missing-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-multi-terms-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-nested-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-parent-aggregation.md - - file: data-analysis/aggregations/search-aggregations-random-sampler-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-range-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-rare-terms-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-reverse-nested-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-sampler-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-significantterms-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-significanttext-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-terms-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-time-series-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-variablewidthhistogram-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-range-field-note.md - - file: data-analysis/aggregations/metrics.md - children: - - file: data-analysis/aggregations/search-aggregations-metrics-avg-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-boxplot-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-cardinality-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-extendedstats-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-geobounds-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-geocentroid-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-geo-line.md - - file: data-analysis/aggregations/search-aggregations-metrics-cartesian-bounds-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-cartesian-centroid-aggregation.md - - file: data-analysis/aggregations/search-aggregations-matrix-stats-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-max-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-median-absolute-deviation-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-min-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-percentile-rank-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-percentile-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-rate-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-scripted-metric-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-stats-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-string-stats-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-sum-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-ttest-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-top-hits-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-top-metrics.md - - file: data-analysis/aggregations/search-aggregations-metrics-valuecount-aggregation.md - - file: data-analysis/aggregations/search-aggregations-metrics-weight-avg-aggregation.md - # TO DO: Figure out how to pull these in... separate TOCs? - # - file: data-analysis/aggregations/data-analysis/observability/metrics-reference.md - # - file: data-analysis/aggregations/data-analysis/serverless/metrics-reference.md - # children: - # - file: data-analysis/aggregations/data-analysis/serverless/observability-host-metrics.md - # - file: data-analysis/aggregations/data-analysis/serverless/observability-container-metrics.md - # - file: data-analysis/aggregations/data-analysis/serverless/observability-kubernetes-pod-metrics.md - # - file: data-analysis/aggregations/data-analysis/serverless/observability-aws-metrics.md - - file: data-analysis/aggregations/pipeline.md - children: - - file: data-analysis/aggregations/search-aggregations-pipeline-avg-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-bucket-script-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-count-ks-test-aggregation.md - - file: data-analysis/aggregations/search-aggregations-bucket-correlation-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-bucket-selector-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-bucket-sort-aggregation.md - - file: data-analysis/aggregations/search-aggregations-change-point-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-cumulative-cardinality-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-cumulative-sum-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-derivative-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-extended-stats-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-inference-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-max-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-min-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-movfn-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-moving-percentiles-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-normalize-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-percentiles-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-serialdiff-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-stats-bucket-aggregation.md - - file: data-analysis/aggregations/search-aggregations-pipeline-sum-bucket-aggregation.md diff --git a/docs/release-notes/known-issues.md b/docs/release-notes/known-issues.md index 0f930c6ca0dad..e0d4339be497f 100644 --- a/docs/release-notes/known-issues.md +++ b/docs/release-notes/known-issues.md @@ -60,7 +60,7 @@ The connector service has the following known issues: :::: - * **Optimize** [**sync rules**](/reference/ingestion-tools/search-connectors/es-sync-rules.md): + * **Optimize** [**sync rules**](/reference/search-connectors/es-sync-rules.md): * Review and optimize sync rules to filter and reduce data retrieved from the source before syncing. @@ -154,5 +154,5 @@ The connector service has the following known issues: ## Individual connector known issues [es-connectors-known-issues-specific] -Individual connectors may have additional known issues. Refer to [each connector’s reference documentation](/reference/ingestion-tools/search-connectors/index.md) for connector-specific known issues. +Individual connectors may have additional known issues. Refer to [each connector’s reference documentation](/reference/search-connectors/index.md) for connector-specific known issues.