-
Notifications
You must be signed in to change notification settings - Fork 25.6k
Add blockloader to patterned_text to support ESQL #134093
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from 4 commits
498a43f
3f182d8
3cd7d84
3aa135f
62c0ed9
2328dc7
6ed4a6f
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -886,12 +886,10 @@ public AllReader reader(LeafReaderContext context) throws IOException { | |
} | ||
} | ||
|
||
private static class BytesRefsFromBinary extends BlockDocValuesReader { | ||
private final BinaryDocValues docValues; | ||
private final ByteArrayStreamInput in = new ByteArrayStreamInput(); | ||
private final BytesRef scratch = new BytesRef(); | ||
abstract static class AbstractBytesRefsFromBinary extends BlockDocValuesReader { | ||
protected final BinaryDocValues docValues; | ||
|
||
BytesRefsFromBinary(BinaryDocValues docValues) { | ||
AbstractBytesRefsFromBinary(BinaryDocValues docValues) { | ||
this.docValues = docValues; | ||
} | ||
|
||
|
@@ -911,7 +909,27 @@ public void read(int docId, BlockLoader.StoredFields storedFields, Builder build | |
read(docId, (BytesRefBuilder) builder); | ||
} | ||
|
||
private void read(int doc, BytesRefBuilder builder) throws IOException { | ||
@Override | ||
public int docId() { | ||
return docValues.docID(); | ||
} | ||
|
||
abstract void read(int docId, BytesRefBuilder builder) throws IOException; | ||
} | ||
|
||
/** | ||
* Read BinaryDocValues encoded by {@link BinaryFieldMapper.CustomBinaryDocValuesField} | ||
*/ | ||
static class BytesRefsFromBinary extends AbstractBytesRefsFromBinary { | ||
private final ByteArrayStreamInput in = new ByteArrayStreamInput(); | ||
private final BytesRef scratch = new BytesRef(); | ||
|
||
BytesRefsFromBinary(BinaryDocValues docValues) { | ||
super(docValues); | ||
} | ||
|
||
@Override | ||
void read(int doc, BytesRefBuilder builder) throws IOException { | ||
if (false == docValues.advanceExact(doc)) { | ||
builder.appendNull(); | ||
return; | ||
|
@@ -939,13 +957,33 @@ private void read(int doc, BytesRefBuilder builder) throws IOException { | |
} | ||
|
||
@Override | ||
public int docId() { | ||
return docValues.docID(); | ||
public String toString() { | ||
return "BlockDocValuesReader.Bytes"; | ||
} | ||
} | ||
|
||
/** | ||
* Read BinaryDocValues with no additional structure in the BytesRefs. | ||
* Each BytesRef from the doc values maps directly to a value in the block loader. | ||
*/ | ||
public static class BytesRefsFromSimpleBinary extends AbstractBytesRefsFromBinary { | ||
|
||
public BytesRefsFromSimpleBinary(BinaryDocValues docValues) { | ||
super(docValues); | ||
} | ||
|
||
@Override | ||
void read(int doc, BytesRefBuilder builder) throws IOException { | ||
if (false == docValues.advanceExact(doc)) { | ||
builder.appendNull(); | ||
return; | ||
} | ||
BytesRef bytes = docValues.binaryValue(); | ||
builder.appendBytesRef(bytes); | ||
} | ||
|
||
@Override | ||
public String toString() { | ||
return "BlockDocValuesReader.Bytes"; | ||
return "BlockDocValuesReader.BytesSimple"; | ||
} | ||
} | ||
|
||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,40 @@ | ||
/* | ||
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
* or more contributor license agreements. Licensed under the Elastic License | ||
* 2.0; you may not use this file except in compliance with the Elastic License | ||
* 2.0. | ||
*/ | ||
|
||
package org.elasticsearch.xpack.logsdb.patternedtext; | ||
|
||
import org.apache.lucene.index.LeafReaderContext; | ||
import org.elasticsearch.index.mapper.BlockDocValuesReader; | ||
|
||
import java.io.IOException; | ||
|
||
public class PatternedTextBlockLoader extends BlockDocValuesReader.DocValuesBlockLoader { | ||
|
||
private final String templateFieldName; | ||
private final String argsFieldName; | ||
private final String argsInfoFieldName; | ||
|
||
PatternedTextBlockLoader(String templateFieldName, String argsFieldName, String argsInfoFieldName) { | ||
this.templateFieldName = templateFieldName; | ||
this.argsFieldName = argsFieldName; | ||
this.argsInfoFieldName = argsInfoFieldName; | ||
} | ||
|
||
@Override | ||
public BytesRefBuilder builder(BlockFactory factory, int expectedCount) { | ||
return factory.bytesRefs(expectedCount); | ||
} | ||
|
||
@Override | ||
public AllReader reader(LeafReaderContext context) throws IOException { | ||
var docValues = PatternedTextDocValues.from(context.reader(), templateFieldName, argsFieldName, argsInfoFieldName); | ||
if (docValues == null) { | ||
return new ConstantNullsReader(); | ||
} | ||
return new BlockDocValuesReader.BytesRefsFromSimpleBinary(docValues); | ||
} | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,108 @@ | ||
--- | ||
setup: | ||
- requires: | ||
cluster_features: [ "mapper.patterned_text" ] | ||
reason: "patterned_text mappings are used in this test" | ||
|
||
- do: | ||
indices.create: | ||
index: test | ||
body: | ||
settings: | ||
index: | ||
mapping.source.mode: synthetic | ||
mappings: | ||
properties: | ||
"@timestamp": | ||
type: date | ||
message: | ||
type: patterned_text | ||
# defaults to index_options: docs | ||
|
||
- do: | ||
bulk: | ||
index: test | ||
refresh: true | ||
body: | ||
- { "index": { "_id": "1" } } | ||
- { "@timestamp": "2025-07-17T00:00:01Z" } | ||
- { "index": { "_id": "2" } } | ||
- { "message": "Found 5 errors for service [cheddar1]", "@timestamp": "2025-07-17T00:00:02Z" } | ||
# template_id: mOVsnxlxdac | ||
- { "index": { "_id": "3" } } | ||
- { "message": "[2020-08-18T00:58:56] Found 123 errors for service [cheddar1]", "@timestamp": "2025-07-17T00:00:03Z" } | ||
# template_id: 1l_PtCLQ5xY | ||
- { "index": { "_id": "4" } } | ||
- { "message": "Found some errors for cheddar data service", "@timestamp": "2025-07-17T00:00:04Z"} | ||
# template_id: k-2qtjujOCw | ||
- { "index": { "_id": "5" } } | ||
- { "message": "Found 123 errors for service [gorgonzola-24]", "@timestamp": "2025-07-17T00:00:05Z" } | ||
# template_id: mOVsnxlxdac | ||
|
||
--- | ||
teardown: | ||
- do: | ||
indices.delete: | ||
index: test | ||
|
||
--- | ||
"Simple from": | ||
- do: | ||
esql.query: | ||
body: | ||
query: 'FROM test | SORT @timestamp | KEEP message, message.template_id | LIMIT 10' | ||
|
||
- match: {columns.0.name: "message"} | ||
- match: {columns.0.type: "text"} | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Should this be updated to be |
||
- match: {columns.1.name: "message.template_id"} | ||
- match: {columns.1.type: "keyword"} | ||
|
||
- length: {values: 5} | ||
- match: {values.0.0: null } | ||
- match: {values.0.1: null } | ||
- match: {values.1.0: "Found 5 errors for service [cheddar1]" } | ||
- match: {values.1.1: "mOVsnxlxdac" } | ||
- match: {values.2.0: "[2020-08-18T00:58:56] Found 123 errors for service [cheddar1]" } | ||
- match: {values.2.1: "1l_PtCLQ5xY" } | ||
- match: {values.3.0: "Found some errors for cheddar data service" } | ||
- match: {values.3.1: "k-2qtjujOCw" } | ||
- match: {values.4.0: "Found 123 errors for service [gorgonzola-24]" } | ||
- match: {values.4.1: "mOVsnxlxdac" } | ||
|
||
--- | ||
"match query": | ||
- do: | ||
esql.query: | ||
body: | ||
query: 'FROM test | WHERE MATCH(message, "gorgonzola-24") | KEEP message | LIMIT 10' | ||
|
||
- length: {values: 1} | ||
- match: {values.0.0: "Found 123 errors for service [gorgonzola-24]" } | ||
|
||
--- | ||
"match phrase query": | ||
- do: | ||
esql.query: | ||
body: | ||
query: 'FROM test | WHERE MATCH_PHRASE(message, "123 errors") | SORT @timestamp | KEEP message | LIMIT 10' | ||
|
||
- length: {values: 2} | ||
- match: {values.0.0: "[2020-08-18T00:58:56] Found 123 errors for service [cheddar1]" } | ||
- match: {values.1.0: "Found 123 errors for service [gorgonzola-24]" } | ||
|
||
--- | ||
"template_id stats": | ||
- do: | ||
esql.query: | ||
body: | ||
query: 'FROM test | STATS count(*) BY message.template_id | SORT message.template_id | LIMIT 10' | ||
|
||
- length: {values: 4} | ||
- match: {values.0.0: 1 } | ||
- match: {values.0.1: "1l_PtCLQ5xY" } | ||
- match: {values.1.0: 1 } | ||
- match: {values.1.1: "k-2qtjujOCw" } | ||
- match: {values.2.0: 2 } | ||
- match: {values.2.1: "mOVsnxlxdac" } | ||
- match: {values.3.0: 1 } | ||
- match: {values.3.1: null } |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe rename this
BytesRefsFromBinary
toBytesRefsFromCustomBinary
? Given that it only works with bytes created by CustomBinaryDocValuesField?