[PPL] Create ANTLR parser and implement basic syntax - Phase0

common/build.gradle

@@ -9,6 +9,7 @@ repositories {
 
 dependencies {
     compile "org.antlr:antlr4-runtime:4.7.1"
+    compile group: 'com.google.guava', name: 'guava', version:'15.0'
 
     testCompile group: 'junit', name: 'junit', version: '4.12'
 }

common/src/main/java/com/amazon/opendistroforelasticsearch/sql/common/utils/StringUtils.java

@@ -0,0 +1,44 @@
+/*
+ *   Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ *   Licensed under the Apache License, Version 2.0 (the "License").
+ *   You may not use this file except in compliance with the License.
+ *   A copy of the License is located at
+ *
+ *       http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *   or in the "license" file accompanying this file. This file is distributed
+ *   on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+ *   express or implied. See the License for the specific language governing
+ *   permissions and limitations under the License.
+ */
+
+package com.amazon.opendistroforelasticsearch.sql.common.utils;
+
+import com.google.common.base.Strings;
+
+public class StringUtils {
+    /**
+     * @param text string
+     * @param mark quotation mark
+     * @return An unquoted string whose outer pair of (single/double/back-tick) quotes have been removed
+     */
+    public static String unquoteIdentifier(String text, String mark) {
+        if (isQuoted(text, mark)) {
+            return text.substring(mark.length(), text.length() - mark.length());
+        }
+        return text;
+    }
+
+    public static String unquoteIdentifier(String text) {
+        if (isQuoted(text, "\"") || isQuoted(text, "'") || isQuoted(text, "`")) {
+            return text.substring(1, text.length() - 1);
+        } else {
+            return text;
+        }
+    }
+
+    private static boolean isQuoted(String text, String mark) {
+        return !Strings.isNullOrEmpty(text) && text.startsWith(mark) && text.endsWith(mark);
+    }
+}

ppl/build.gradle

@@ -25,6 +25,8 @@ dependencies {
     antlr "org.antlr:antlr4:4.7.1"
 
     compile "org.antlr:antlr4-runtime:4.7.1"
+    compile group: 'com.google.guava', name: 'guava', version:'15.0'
+    compile group: 'org.elasticsearch', name: 'elasticsearch-x-content', version:"${es_version}"
     compile group: 'org.json', name: 'json', version:'20180813'
     compile group: 'org.springframework', name: 'spring-context', version: '5.2.5.RELEASE'
     compile group: 'org.springframework', name: 'spring-beans', version: '5.2.5.RELEASE'

ppl/src/main/antlr/OpenDistroPPLLexer.g4

@@ -90,6 +90,11 @@ EXCLAMATION_SYMBOL:                 '!';
 COLON:                              ':';
 LT_PRTHS:                           '(';
 RT_PRTHS:                           ')';
+LT_SQR_PRTHS:                       '[';
+RT_SQR_PRTHS:                       ']';
+SINGLE_QUOTE:                       '\'';
+DOUBLE_QUOTE:                       '"';
+BACKTICK:                           '`';
 
 // AGGREGATIONS
 AVG:                                'AVG';
@@ -240,16 +245,15 @@ WILDCARDQUERY:                      'WILDCARDQUERY';
 WILDCARD_QUERY:                     'WILDCARD_QUERY';
 
 // LITERALS AND VALUES
-STRING_LITERAL:                     DQUOTA_STRING | SQUOTA_STRING | BQUOTA_STRING;
+//STRING_LITERAL:                     DQUOTA_STRING | SQUOTA_STRING | BQUOTA_STRING;
 ID:                                 ID_LITERAL;
-DOT_ID:                             '.' ID;
-DECIMAL_LITERAL:                    DEC_DIGIT+;
-// TODO: define WCFIELD
+INTEGER_LITERAL:                    DEC_DIGIT+;
+DECIMAL_LITERAL:                    (DEC_DIGIT+)? '.' DEC_DIGIT+;
 
 fragment ID_LITERAL:                [A-Z_$0-9@]*?[A-Z_$\-]+?[A-Z_$\-0-9]*;
-fragment DQUOTA_STRING:             '"' ( '\\'. | '""' | ~('"'| '\\') )* '"';
-fragment SQUOTA_STRING:             '\'' ('\\'. | '\'\'' | ~('\'' | '\\'))* '\'';
-fragment BQUOTA_STRING:             '`' ( '\\'. | '``' | ~('`'|'\\'))* '`';
+DQUOTA_STRING:             '"' ( '\\'. | '""' | ~('"'| '\\') )* '"';
+SQUOTA_STRING:             '\'' ('\\'. | '\'\'' | ~('\'' | '\\'))* '\'';
+BQUOTA_STRING:             '`' ( '\\'. | '``' | ~('`'|'\\'))* '`';
 fragment DEC_DIGIT:                 [0-9];
 
 

ppl/src/main/antlr/OpenDistroPPLParser.g4

@@ -26,32 +26,31 @@ pplStatement
     : searchCommand (PIPE commands)*
     ;
 
-
 /** commands */
 commands
     : whereCommand | fieldsCommand | renameCommand | statsCommand | dedupCommand | sortCommand | evalCommand
     ;
 
 searchCommand
-    : (SEARCH)? fromClause                                          #searchWithoutFilter
-    | (SEARCH)? fromClause logicalExpression                        #searchFromClauseLogicExpr
-    | (SEARCH)? logicalExpression fromClause                        #searchLogicExprFromClause
+    : (SEARCH)? fromClause                                          #searchFrom
+    | (SEARCH)? fromClause logicalExpression                        #searchFromFilter
+    | (SEARCH)? logicalExpression fromClause                        #searchFilterFrom
     ;
 
 whereCommand
-    : WHERE evalExpression
+    : WHERE logicalExpression
     ;
 
 fieldsCommand
-    : FIELDS fieldList
+    : FIELDS (PLUS | MINUS)? wcFieldList
     ;
 
 renameCommand
-    : RENAME wcField AS wcField
+    : RENAME orignalField=wcFieldExpression AS renamedField=wcFieldExpression
     ;
 
 statsCommand
-    : STATS (statsArgument)* (statsAggTerm | sparklineAggTerm) (byClause)? (dedupSplitValues)?
+    : STATS (statsArgument)* statsAggTerm (byClause)? (dedupSplitValues)?
     ;
 
 dedupCommand
@@ -63,7 +62,7 @@ sortCommand
     ;
 
 evalCommand
-    : EVAL fieldExpression EQUAL evalExpression (COMMA fieldExpression EQUAL evalExpression)
+    : EVAL evalExpression (COMMA evalExpression)*
     ;
 
 /** arguments */
@@ -94,16 +93,12 @@ byClause
     ;
 
 sortbyClause
-    : (PLUS | MINUS) sortField (COMMA (PLUS | MINUS) sortField)*
+    : (PLUS | MINUS)? sortField (COMMA (PLUS | MINUS)? sortField)*
     ;
 
 /** aggregation terms */
-aggregationTerm
-    : statsAggTerm | sparklineAggTerm
-    ;
-
 statsAggTerm
-    : statsFunction LT_PRTHS (fieldExpression)? RT_PRTHS
+    : statsFunction
     ;
 
 sparklineAggTerm
@@ -116,8 +111,8 @@ statsFunction
     ;
 
 aggregationFunction
-    : aggFunctionName LT_PRTHS fieldExpression RT_PRTHS
-    | percentileAggFunction
+    : aggFunctionName LT_PRTHS fieldExpression RT_PRTHS             #aggFunctionCall
+    | percentileAggFunction                                         #percentileAggFunctionCall
     ;
 
 aggFunctionName
@@ -126,7 +121,7 @@ aggFunctionName
     ;
 
 percentileAggFunction
-    : PERCENTILE LESS fieldExpression GREATER LT_PRTHS fieldExpression RT_PRTHS
+    : PERCENTILE LESS value=decimalLiteral GREATER LT_PRTHS aggField=fieldExpression RT_PRTHS
     ;
 
 eventOrderFunction
@@ -148,16 +143,17 @@ timeFunctionName
     ;
 
 sparklineAggregation
-    : SPARKLINE LT_PRTHS COUNT LT_PRTHS wcField RT_PRTHS COMMA spanLength=decimalLiteral RT_PRTHS
-    | SPARKLINE RT_PRTHS sparklineFunction LT_PRTHS wcField RT_PRTHS COMMA spanLength=decimalLiteral RT_PRTHS
+    : SPARKLINE LT_PRTHS COUNT LT_PRTHS wcFieldExpression RT_PRTHS COMMA spanLength=decimalLiteral RT_PRTHS
+    | SPARKLINE RT_PRTHS sparklineFunction LT_PRTHS wcFieldExpression RT_PRTHS COMMA spanLength=decimalLiteral RT_PRTHS
     ;
 
 sparklineFunction
     : sparklineFunctionName LT_PRTHS fieldExpression RT_PRTHS
     ;
 
 sparklineFunctionName
-    : C | COUNT | DC | MEAN | AVG | STDEV | STDEVP | VAR | VARP | SUM | SUMSQ | MIN | MAX | RANGE
+    :
+//    | C | COUNT | DC | MEAN | AVG | STDEV | STDEVP | VAR | VARP | SUM | SUMSQ | MIN | MAX | RANGE
     ;
 
 /** expressions */
@@ -173,35 +169,39 @@ logicalExpression
     | comparisonExpression                                          #comparsion
     | evalExpression                                                #eval
     | NOT logicalExpression                                         #logicalNot
-    | left=logicalExpression OR right=logicalExpression             #logicalOrBinary
-    | left=logicalExpression (AND)? right=logicalExpression         #logicalAndBinary
+    | left=logicalExpression OR right=logicalExpression             #logicalOr
+    | left=logicalExpression (AND)? right=logicalExpression         #logicalAnd
     ;
 
 evalExpression
-    : literalValue EQUAL literalValue
-    | evalFunctionCall
+    : fieldExpression EQUAL evalFunctionCall
     ;
 
 comparisonExpression
-    : left=fieldExpression comparisonOperator right=literalValue
-    | fieldExpression IN valueList
+    : left=fieldExpression comparisonOperator right=literalValue    #compareExpr
+    | fieldExpression IN valueList                                  #inExpr
     ;
 
 booleanExpression
-    : LT_PRTHS booleanExpression RT_PRTHS
+    : LT_PRTHS booleanLiteral RT_PRTHS
     | booleanLiteral
     ;
 
 /** tables */
 tableSource
     : ident
+    | stringLiteral
     ;
 
 /** fields */
 fieldList
     : fieldExpression (COMMA fieldExpression)*
     ;
 
+wcFieldList
+    : wcFieldExpression (COMMA wcFieldExpression)*
+    ;
+
 sortField
     : fieldExpression                                               #defaultSort
     | AUTO LT_PRTHS fieldExpression RT_PRTHS                        #autoSort
@@ -210,14 +210,18 @@ sortField
     | NUM LT_PRTHS fieldExpression RT_PRTHS                         #numSort
     ;
 
-wcField
-    : WCFIELD
-    ;
-
 fieldExpression
     : ident
+    | SINGLE_QUOTE ident SINGLE_QUOTE
+    | DOUBLE_QUOTE ident DOUBLE_QUOTE
+    | BACKTICK ident BACKTICK
+    ;
+
+wcFieldExpression
+    : wildcard
     ;
 
+
 /** functions */
 evalFunctionCall
     : evalFunctionName LT_PRTHS functionArgs RT_PRTHS
@@ -253,7 +257,7 @@ functionArgs
     ;
 
 functionArg
-    : constant | fullColumnName | expression | evalFunctionCall
+    : expression | fieldExpression | literalValue
     ;
 
 /** operators */
@@ -264,11 +268,17 @@ comparisonOperator
 /** literals and values*/
 literalValue
     : stringLiteral
-    | decimalLiteral
+    | (PLUS | MINUS)? integerLiteral
+    | (PLUS | MINUS)? decimalLiteral
+    | booleanLiteral
     ;
 
 stringLiteral
-    : STRING_LITERAL
+    : DQUOTA_STRING | SQUOTA_STRING | BQUOTA_STRING
+    ;
+
+integerLiteral
+    : INTEGER_LITERAL
     ;
 
 decimalLiteral
@@ -283,32 +293,10 @@ valueList
     : LT_PRTHS literalValue (COMMA literalValue)* RT_PRTHS
     ;
 
-fullColumnName
-    : simpleId DOT_ID*
-    ;
-
-constant
-    : stringLiteral | decimalLiteral
-    | MINUS decimalLiteral
-    | booleanLiteral
-    ;
-
-simpleId
-    : ID
-    | DOT_ID
-    | STRING_LITERAL
-    ;
-
 ident
-    : ID
-    | DOT_ID
+    : (DOT)? ID
     ;
 
-/** dataset */
-datasetType
-    : DATAMODEL | LOOKUP | SAVEDSEARCH
-    ;
-
-datasetName
-    :
+wildcard
+    : (MODULE | ident)+
     ;

ppl/src/main/java/com/amazon/opendistroforelasticsearch/sql/ppl/antlr/PPLSyntaxParser.java

@@ -27,8 +27,8 @@
  * PPL Syntax Parser
  */
 public class PPLSyntaxParser {
-    public ParseTree analyzeSyntax(String sql) {
-        OpenDistroPPLParser parser = createParser(createLexer(sql));
+    public ParseTree analyzeSyntax(String query) {
+        OpenDistroPPLParser parser = createParser(createLexer(query));
         parser.addErrorListener(new SyntaxAnalysisErrorListener());
         return parser.root();
     }
@@ -38,8 +38,8 @@ private OpenDistroPPLParser createParser(Lexer lexer) {
                 new CommonTokenStream(lexer));
     }
 
-    private OpenDistroPPLLexer createLexer(String sql) {
+    private OpenDistroPPLLexer createLexer(String query) {
         return new OpenDistroPPLLexer(
-                new CaseInsensitiveCharStream(sql));
+                new CaseInsensitiveCharStream(query));
     }
 }