Fixing indices create partially (#4652) (#4714)

* index create fixes

* Update specification/_types/analysis/token_filters.ts



* addressing review

* persian stem add

* add comment

* revert making locale optional just for validation

---------


(cherry picked from commit 92bd777)

Co-authored-by: Laura Trotta <[email protected]>
Co-authored-by: Quentin Pradet <[email protected]>

Author: 3 people

specification/_types/analysis/icu-plugin.ts

@@ -52,16 +52,16 @@ export class IcuFoldingTokenFilter extends TokenFilterBase {
 export class IcuCollationTokenFilter extends TokenFilterBase {
   type: 'icu_collation'
   alternate?: IcuCollationAlternate
-  case_first?: IcuCollationCaseFirst
-  case_level?: boolean
+  caseFirst?: IcuCollationCaseFirst
+  caseLevel?: boolean
   country?: string
   decomposition?: IcuCollationDecomposition
-  hiragana_quaternary_mode?: boolean
+  hiraganaQuaternaryMode?: boolean
   language?: string
   numeric?: boolean
   rules?: string
   strength?: IcuCollationStrength
-  variable_top?: string
+  variableTop?: string
   variant?: string
 }
 

specification/_types/analysis/token_filters.ts

@@ -383,6 +383,7 @@ export class PatternReplaceTokenFilter extends TokenFilterBase {
   type: 'pattern_replace'
   /** If `true`, all substrings matching the pattern parameter’s regular expression are replaced. If `false`, the filter replaces only the first matching substring in each token. Defaults to `true`. */
   all?: boolean
+  flags?: string
   /** Regular expression, written in Java’s regular expression syntax. The filter replaces token substrings matching this pattern with the substring in the `replacement` parameter. */
   pattern: string
   /** Replacement substring. Defaults to an empty substring (`""`). */
@@ -486,6 +487,14 @@ export class FlattenGraphTokenFilter extends TokenFilterBase {
   type: 'flatten_graph'
 }
 
+export class BengaliNormalizationTokenFilter extends TokenFilterBase {
+  type: 'bengali_normalization'
+}
+
+export class BrazilianStemTokenFilter extends TokenFilterBase {
+  type: 'brazilian_stem'
+}
+
 export class GermanNormalizationTokenFilter extends TokenFilterBase {
   type: 'german_normalization'
 }
@@ -535,6 +544,34 @@ export class SoraniNormalizationTokenFilter extends TokenFilterBase {
   type: 'sorani_normalization'
 }
 
+export class ArabicStemTokenFilter extends TokenFilterBase {
+  type: 'arabic_stem'
+}
+
+export class CzechStemTokenFilter extends TokenFilterBase {
+  type: 'czech_stem'
+}
+
+export class FrenchStemTokenFilter extends TokenFilterBase {
+  type: 'french_stem'
+}
+
+export class DutchStemTokenFilter extends TokenFilterBase {
+  type: 'dutch_stem'
+}
+
+export class GermanStemTokenFilter extends TokenFilterBase {
+  type: 'german_stem'
+}
+
+export class RussianStemTokenFilter extends TokenFilterBase {
+  type: 'russian_stem'
+}
+
+export class PersianStemTokenFilter extends TokenFilterBase {
+  type: 'persian_stem'
+}
+
 /**
  * @codegen_names name, definition
  * @ext_doc_id analysis-tokenfilters
@@ -548,20 +585,27 @@ export type TokenFilter = string | TokenFilterDefinition
  */
 export type TokenFilterDefinition =
   | ApostropheTokenFilter
+  | ArabicStemTokenFilter
   | ArabicNormalizationTokenFilter
   | AsciiFoldingTokenFilter
+  | BengaliNormalizationTokenFilter
+  | BrazilianStemTokenFilter
   | CjkBigramTokenFilter
   | CjkWidthTokenFilter
   | ClassicTokenFilter
   | CommonGramsTokenFilter
   | ConditionTokenFilter
+  | CzechStemTokenFilter
   | DecimalDigitTokenFilter
   | DelimitedPayloadTokenFilter
+  | DutchStemTokenFilter
   | EdgeNGramTokenFilter
   | ElisionTokenFilter
   | FingerprintTokenFilter
   | FlattenGraphTokenFilter
+  | FrenchStemTokenFilter
   | GermanNormalizationTokenFilter
+  | GermanStemTokenFilter
   | HindiNormalizationTokenFilter
   | HunspellTokenFilter
   | HyphenationDecompounderTokenFilter
@@ -581,10 +625,12 @@ export type TokenFilterDefinition =
   | PatternCaptureTokenFilter
   | PatternReplaceTokenFilter
   | PersianNormalizationTokenFilter
+  | PersianStemTokenFilter
   | PorterStemTokenFilter
   | PredicateTokenFilter
   | RemoveDuplicatesTokenFilter
   | ReverseTokenFilter
+  | RussianStemTokenFilter
   | ScandinavianFoldingTokenFilter
   | ScandinavianNormalizationTokenFilter
   | SerbianNormalizationTokenFilter

specification/_types/analysis/tokenizers.ts

@@ -50,10 +50,7 @@ export class EdgeNGramTokenizer extends TokenizerBase {
   custom_token_chars?: string
   max_gram?: integer
   min_gram?: integer
-  /**
-   * @server_default []
-   */
-  token_chars?: TokenChar[]
+  token_chars?: string | TokenChar[]
 }
 
 export enum TokenChar {

specification/_types/mapping/Property.ts

@@ -59,6 +59,7 @@ import {
   PercolatorProperty,
   RankFeatureProperty,
   RankFeaturesProperty,
+  RankVectorProperty,
   ScaledFloatNumberProperty,
   SearchAsYouTypeProperty,
   SemanticTextProperty,
@@ -147,6 +148,7 @@ export type Property =
   | NestedProperty
   | ObjectProperty
   | PassthroughObjectProperty
+  | RankVectorProperty
   | SemanticTextProperty
   | SparseVectorProperty
 

specification/_types/mapping/complex.ts

@@ -33,6 +33,7 @@ export class FlattenedProperty extends PropertyBase {
   null_value?: string
   similarity?: string
   split_queries_on_whitespace?: boolean
+  time_series_dimensions?: string[]
   type: 'flattened'
 }
 
@@ -59,6 +60,7 @@ export class PassthroughObjectProperty extends CorePropertyBase {
 export class AggregateMetricDoubleProperty extends PropertyBase {
   type: 'aggregate_metric_double'
   default_metric: string
+  ignore_malformed?: boolean
   metrics: string[]
   time_series_metric?: TimeSeriesMetricType
 }

specification/_types/mapping/core.ts

@@ -212,7 +212,17 @@ export class RankFeaturesProperty extends PropertyBase {
   type: 'rank_features'
 }
 
+/**
+ * Technical preview
+ */
+export class RankVectorProperty extends PropertyBase {
+  type: 'rank_vectors'
+  element_type?: RankVectorElementType
+  dims?: integer
+}
+
 export class SparseVectorProperty extends PropertyBase {
+  store?: boolean
   type: 'sparse_vector'
 }
 
@@ -356,3 +366,9 @@ export class DynamicProperty extends DocValuesPropertyBase {
   precision_step?: integer
   locale?: string
 }
+
+export enum RankVectorElementType {
+  byte,
+  float,
+  bit
+}

specification/_types/mapping/geo.ts

@@ -29,6 +29,13 @@ export class GeoPointProperty extends DocValuesPropertyBase {
   on_script_error?: OnScriptError
   script?: Script
   type: 'geo_point'
+  time_series_metric?: GeoPointMetricType
+}
+
+export enum GeoPointMetricType {
+  gauge,
+  counter,
+  position
 }
 
 export enum GeoOrientation {

specification/indices/_types/IndexSettings.ts

@@ -540,6 +540,8 @@ export class Storage {
    * of memory maps so you need disable the ability to use memory-mapping.
    */
   allow_mmap?: boolean
+  /** How often store statistics are refreshed */
+  stats_refresh_interval?: Duration
 }
 
 /**