[KQL Query] Create the ANTLR parser (elastic#114927)

x-pack/plugin/kql/build.gradle

@@ -0,0 +1,113 @@
+import org.elasticsearch.gradle.internal.info.BuildParams
+
+apply plugin: 'elasticsearch.internal-es-plugin'
+apply plugin: 'elasticsearch.internal-cluster-test'
+apply plugin: 'elasticsearch.publish'
+
+esplugin {
+  name 'x-pack-kql'
+  description 'Elasticsearch Expanded Pack Plugin - KQL query'
+  classname 'org.elasticsearch.xpack.kql.KqlPlugin'
+  extendedPlugins = ['x-pack-core']
+}
+base {
+  archivesName = 'x-pack-kql'
+}
+
+dependencies {
+  compileOnly project(path: xpackModule('core'))
+  compileOnly "org.antlr:antlr4-runtime:${versions.antlr4}"
+
+  testImplementation "org.antlr:antlr4-runtime:${versions.antlr4}"
+  testImplementation project(':test:framework')
+  testImplementation(testArtifact(project(xpackModule('core'))))
+}
+
+/****************************************************************
+ *  Enable QA/rest integration tests for snapshot builds only   *
+ *  TODO: Enable for all builds upon this feature release       *
+ ****************************************************************/
+if (BuildParams.isSnapshotBuild()) {
+  addQaCheckDependencies(project)
+}
+
+/**********************************
+ * KQL parser configuration       *
+ **********************************/
+configurations {
+  regenerate
+}
+
+dependencies {
+  regenerate "org.antlr:antlr4:${versions.antlr4}"
+}
+
+String grammarPath = 'src/main/antlr'
+String outputPath = 'src/main/java/org/elasticsearch/xpack/kql/parser'
+
+pluginManager.withPlugin('com.diffplug.spotless') {
+  spotless {
+    java {
+      // for some reason "${outputPath}/KqlBaser*.java" does not match the same files...
+      targetExclude "src/main/java/org/elasticsearch/xpack/kql/parser/KqlBase*.java"
+    }
+  }
+}
+tasks.named('checkstyleMain').configure {
+  exclude { it.file.toString().contains("src/main/java/org/elasticsearch/xpack/kql/parser/KqlBase") }
+}
+
+tasks.register("cleanGenerated", Delete) {
+  delete fileTree(grammarPath) {
+    include '*.tokens'
+  }
+  delete fileTree(outputPath) {
+    include 'KqlBase*.java'
+    include 'KqlBase*.interp'
+  }
+}
+
+tasks.register("regenParser", JavaExec) {
+  dependsOn "cleanGenerated"
+  mainClass = 'org.antlr.v4.Tool'
+  classpath = configurations.regenerate
+  systemProperty 'file.encoding', 'UTF-8'
+  systemProperty 'user.language', 'en'
+  systemProperty 'user.country', 'US'
+  systemProperty 'user.variant', ''
+  args '-Werror',
+    '-package', 'org.elasticsearch.xpack.kql.parser',
+    '-listener',
+    '-visitor',
+    '-o', outputPath,
+    "${file(grammarPath)}/KqlBase.g4"
+}
+
+tasks.register("regen") {
+  dependsOn "regenParser"
+  doLast {
+    // moves token files to grammar directory for use with IDE's
+    ant.move(file: "${outputPath}/KqlBase.tokens", toDir: grammarPath)
+    ant.move(file: "${outputPath}/KqlBaseLexer.tokens", toDir: grammarPath)
+    // make the generated classes package private
+    ant.replaceregexp(match: 'public ((interface|class) \\QKqlBase\\E\\w+)',
+      replace: '\\1',
+      encoding: 'UTF-8') {
+      fileset(dir: outputPath, includes: 'KqlBase*.java')
+    }
+    // nuke timestamps/filenames in generated files
+    ant.replaceregexp(match: '\\Q// Generated from \\E.*',
+      replace: '\\/\\/ ANTLR GENERATED CODE: DO NOT EDIT',
+      encoding: 'UTF-8') {
+      fileset(dir: outputPath, includes: 'KqlBase*.java')
+    }
+    // remove tabs in antlr generated files
+    ant.replaceregexp(match: '\t', flags: 'g', replace: '    ', encoding: 'UTF-8') {
+      fileset(dir: outputPath, includes: 'KqlBase*.java')
+    }
+    // fix line endings
+    ant.fixcrlf(srcdir: outputPath, eol: 'lf') {
+      patternset(includes: 'KqlBase*.java')
+    }
+  }
+}

x-pack/plugin/kql/src/main/antlr/KqlBase.g4

@@ -0,0 +1,145 @@
+/*
+ * 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.
+ */
+
+grammar KqlBase;
+
+
+@header {
+/*
+ * 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.
+ */
+}
+
+options {
+  caseInsensitive=true;
+}
+
+topLevelQuery
+    : query? EOF
+    ;
+
+query
+    : query (AND | OR) query          #booleanQuery
+    | NOT subQuery=simpleQuery        #notQuery
+    | simpleQuery                     #defaultQuery
+    ;
+
+simpleQuery
+    : nestedQuery
+    | expression
+    | parenthesizedQuery
+    ;
+
+expression
+    : fieldTermQuery
+    | fieldRangeQuery
+    ;
+
+nestedQuery
+    : fieldName COLON LEFT_CURLY_BRACKET query RIGHT_CURLY_BRACKET
+    ;
+
+parenthesizedQuery:
+   LEFT_PARENTHESIS query RIGHT_PARENTHESIS;
+
+fieldRangeQuery
+    : fieldName operator=OP_COMPARE rangeQueryValue
+    ;
+
+fieldTermQuery
+    : (fieldName COLON)? termQueryValue
+    ;
+
+fieldName
+    : wildcardExpression
+    | unquotedLiteralExpression
+    | quotedStringExpression
+    ;
+
+rangeQueryValue
+    : unquotedLiteralExpression
+    | quotedStringExpression
+    ;
+
+termQueryValue
+    : wildcardExpression
+    | quotedStringExpression
+    | termValue=unquotedLiteralExpression
+    | groupingTermExpression;
+
+groupingTermExpression
+    : LEFT_PARENTHESIS unquotedLiteralExpression RIGHT_PARENTHESIS
+    ;
+
+unquotedLiteralExpression
+    : UNQUOTED_LITERAL+
+    ;
+
+quotedStringExpression
+    : QUOTED_STRING
+    ;
+
+wildcardExpression
+    : WILDCARD
+;
+
+
+DEFAULT_SKIP: WHITESPACE -> skip;
+
+AND: 'and';
+OR: 'or';
+NOT: 'not';
+
+COLON: ':';
+OP_COMPARE: OP_LESS | OP_MORE | OP_LESS_EQ | OP_MORE_EQ;
+
+LEFT_PARENTHESIS: '(';
+RIGHT_PARENTHESIS: ')';
+LEFT_CURLY_BRACKET: '{';
+RIGHT_CURLY_BRACKET: '}';
+
+UNQUOTED_LITERAL: WILDCARD* UNQUOTED_LITERAL_CHAR+ WILDCARD*;
+
+QUOTED_STRING: '"'QUOTED_CHAR*'"';
+
+WILDCARD: WILDCARD_CHAR+;
+
+fragment WILDCARD_CHAR: '*';
+fragment OP_LESS: '<';
+fragment OP_LESS_EQ: '<=';
+fragment OP_MORE: '>';
+fragment OP_MORE_EQ: '>=';
+
+fragment UNQUOTED_LITERAL_CHAR
+    : ESCAPED_WHITESPACE
+    | ESCAPED_SPECIAL_CHAR
+    | ESCAPE_UNICODE_SEQUENCE
+    | '\\' (AND | OR | NOT)
+    | WILDCARD_CHAR UNQUOTED_LITERAL_CHAR
+    | NON_SPECIAL_CHAR
+    ;
+
+fragment QUOTED_CHAR
+    : ESCAPED_WHITESPACE
+    | ESCAPE_UNICODE_SEQUENCE
+    | ESCAPED_QUOTE
+    | ~["]
+    ;
+
+fragment WHITESPACE: [ \t\n\r\u3000];
+fragment ESCAPED_WHITESPACE: '\\r' | '\\t' | '\\n';
+fragment NON_SPECIAL_CHAR: ~[ \\():<>"*{}];
+fragment ESCAPED_SPECIAL_CHAR: '\\'[ \\():<>"*{}];
+
+fragment ESCAPED_QUOTE: '\\"';
+
+fragment ESCAPE_UNICODE_SEQUENCE: '\\' UNICODE_SEQUENCE;
+fragment UNICODE_SEQUENCE: 'u' HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT;
+fragment HEX_DIGIT: [0-9a-f];

x-pack/plugin/kql/src/main/antlr/KqlBase.tokens

@@ -0,0 +1,21 @@
+DEFAULT_SKIP=1
+AND=2
+OR=3
+NOT=4
+COLON=5
+OP_COMPARE=6
+LEFT_PARENTHESIS=7
+RIGHT_PARENTHESIS=8
+LEFT_CURLY_BRACKET=9
+RIGHT_CURLY_BRACKET=10
+UNQUOTED_LITERAL=11
+QUOTED_STRING=12
+WILDCARD=13
+'and'=2
+'or'=3
+'not'=4
+':'=5
+'('=7
+')'=8
+'{'=9
+'}'=10

x-pack/plugin/kql/src/main/antlr/KqlBaseLexer.tokens

@@ -0,0 +1,21 @@
+DEFAULT_SKIP=1
+AND=2
+OR=3
+NOT=4
+COLON=5
+OP_COMPARE=6
+LEFT_PARENTHESIS=7
+RIGHT_PARENTHESIS=8
+LEFT_CURLY_BRACKET=9
+RIGHT_CURLY_BRACKET=10
+UNQUOTED_LITERAL=11
+QUOTED_STRING=12
+WILDCARD=13
+'and'=2
+'or'=3
+'not'=4
+':'=5
+'('=7
+')'=8
+'{'=9
+'}'=10

x-pack/plugin/kql/src/main/java/org/elasticsearch/xpack/kql/KqlPlugin.java

@@ -0,0 +1,16 @@
+/*
+ * 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.kql;
+
+import org.elasticsearch.plugins.ExtensiblePlugin;
+import org.elasticsearch.plugins.Plugin;
+import org.elasticsearch.plugins.SearchPlugin;
+
+public class KqlPlugin extends Plugin implements SearchPlugin, ExtensiblePlugin {
+
+}

x-pack/plugin/kql/src/main/java/org/elasticsearch/xpack/kql/parser/KqlAstBuilder.java

@@ -0,0 +1,29 @@
+/*
+ * 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.kql.parser;
+
+import org.antlr.v4.runtime.ParserRuleContext;
+import org.elasticsearch.index.query.MatchAllQueryBuilder;
+import org.elasticsearch.index.query.QueryBuilder;
+import org.elasticsearch.index.query.SearchExecutionContext;
+
+class KqlAstBuilder extends KqlBaseBaseVisitor<QueryBuilder> {
+    private final SearchExecutionContext searchExecutionContext;
+
+    KqlAstBuilder(SearchExecutionContext searchExecutionContext) {
+        this.searchExecutionContext = searchExecutionContext;
+    }
+
+    public QueryBuilder toQueryBuilder(ParserRuleContext ctx) {
+        if (ctx instanceof KqlBaseParser.TopLevelQueryContext topLeveQueryContext) {
+            return new MatchAllQueryBuilder();
+        }
+
+        throw new IllegalArgumentException("context should be of type TopLevelQueryContext");
+    }
+}