Add position() string function to PPL (#1147)

* Add position() string function to PPL (#184)

Signed-off-by: Margarit Hakobyan <[email protected]>

Author: margarit-h

docs/user/ppl/functions/string.rst

@@ -150,6 +150,31 @@ Example::
     +---------------------+---------------------+
 
 
+POSITION
+------
+
+Description
+>>>>>>>>>>>
+
+Usage: The syntax POSITION(substr IN str) returns the position of the first occurrence of substring substr in string str. Returns 0 if substr is not in str. Returns NULL if any argument is NULL.
+
+Argument type: STRING, STRING
+
+Return type INTEGER
+
+(STRING IN STRING) -> INTEGER
+
+Example::
+
+    os> source=people | eval `POSITION('world' IN 'helloworld')` = POSITION('world' IN 'helloworld'), `POSITION('invalid' IN 'helloworld')`= POSITION('invalid' IN 'helloworld')  | fields `POSITION('world' IN 'helloworld')`, `POSITION('invalid' IN 'helloworld')`
+    fetched rows / total rows = 1/1
+    +-------------------------------------+---------------------------------------+
+    | POSITION('world' IN 'helloworld')   | POSITION('invalid' IN 'helloworld')   |
+    |-------------------------------------+---------------------------------------|
+    | 6                                   | 0                                     |
+    +-------------------------------------+---------------------------------------+
+
+
 RIGHT
 -----
 

integ-test/src/test/java/org/opensearch/sql/ppl/PositionFunctionIT.java

@@ -0,0 +1,100 @@
+/*
+ * Copyright OpenSearch Contributors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+package org.opensearch.sql.ppl;
+
+import org.junit.Test;
+
+import java.io.IOException;
+
+import static org.opensearch.sql.legacy.TestsConstants.TEST_INDEX_CALCS;
+import static org.opensearch.sql.util.MatcherUtils.rows;
+import static org.opensearch.sql.util.MatcherUtils.verifyDataRows;
+
+public class PositionFunctionIT extends PPLIntegTestCase {
+    @Override
+    public void init() throws IOException {
+        loadIndex(Index.CALCS);
+    }
+
+    @Test
+    public void test_position_function() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | eval f=position('ON', str1) | fields f";
+
+        var result = executeQuery(query);
+
+        assertEquals(17, result.getInt("total"));
+        verifyDataRows(result,
+                rows(7), rows(7),
+                rows(2), rows(0),
+                rows(0), rows(0),
+                rows(0), rows(0),
+                rows(0), rows(0),
+                rows(0), rows(0),
+                rows(0), rows(0),
+                rows(0), rows(0),
+                rows(0));
+    }
+
+    @Test
+    public void test_position_function_with_fields_only() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | eval f=position(str3 IN str2) | where str2 IN ('one', 'two', 'three')| fields f";
+
+        var result = executeQuery(query);
+
+        assertEquals(3, result.getInt("total"));
+        verifyDataRows(result, rows(3), rows(0), rows(4));
+    }
+
+    @Test
+    public void test_position_function_with_string_literals() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | eval f=position('world' IN 'hello world') | where str2='one' | fields f";
+
+        var result = executeQuery(query);
+
+        assertEquals(1, result.getInt("total"));
+        verifyDataRows(result, rows(7));
+    }
+
+    @Test
+    public void test_position_function_with_nulls() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | eval f=position('ee' IN str2) | where isnull(str2) | fields str2,f";
+
+        var result = executeQuery(query);
+
+        assertEquals(4, result.getInt("total"));
+        verifyDataRows(result,
+                rows(null, null),
+                rows(null, null),
+                rows(null, null),
+                rows(null, null));
+    }
+
+    @Test
+    public void test_position_function_with_function_as_arg() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | eval f=position(upper(str3) IN str1) | where like(str1, 'BINDING SUPPLIES') | fields f";
+
+        var result = executeQuery(query);
+
+        assertEquals(1, result.getInt("total"));
+        verifyDataRows(result, rows(15));
+    }
+
+    @Test
+    public void test_position_function_with_function_in_where_clause() throws IOException {
+        String query = "source=" + TEST_INDEX_CALCS
+                + " | where position(str3 IN str2)=1 | fields str2";
+
+        var result = executeQuery(query);
+
+        assertEquals(2, result.getInt("total"));
+        verifyDataRows(result, rows("eight"), rows("eleven"));
+    }
+}

ppl/src/main/antlr/OpenSearchPPLLexer.g4

@@ -215,6 +215,7 @@ LOG10:                              'LOG10';
 LOG2:                               'LOG2';
 MOD:                                'MOD';
 PI:                                 'PI';
+POSITION:                           'POSITION';
 POW:                                'POW';
 POWER:                              'POWER';
 RAND:                               'RAND';

ppl/src/main/antlr/OpenSearchPPLParser.g4

@@ -258,6 +258,7 @@ valueExpression
     | LT_PRTHS left=valueExpression binaryOperator
     right=valueExpression RT_PRTHS                                  #parentheticBinaryArithmetic
     | primaryExpression                                             #valueExpressionDefault
+    | positionFunction                                              #positionFunctionCall
     ;
 
 primaryExpression
@@ -267,6 +268,10 @@ primaryExpression
     | literalValue
     ;
 
+positionFunction
+    : positionFunctionName LT_PRTHS functionArg IN functionArg RT_PRTHS
+    ;
+
 booleanExpression
     : booleanFunctionCall
     ;
@@ -362,6 +367,7 @@ evalFunctionName
     | textFunctionBase
     | conditionFunctionBase
     | systemFunctionBase
+    | positionFunctionName
     ;
 
 functionArgs
@@ -484,6 +490,10 @@ textFunctionBase
     | RIGHT | LEFT | ASCII | LOCATE | REPLACE
     ;
 
+positionFunctionName
+    : POSITION
+    ;
+
 /** operators */
 comparisonOperator
     : EQUAL | NOT_EQUAL | LESS | NOT_LESS | GREATER | NOT_GREATER | REGEXP
@@ -603,4 +613,5 @@ keywordsCanBeId
     | dateAndTimeFunctionBase
     | textFunctionBase
     | mathematicalFunctionBase
+    | positionFunctionName
     ;

ppl/src/main/java/org/opensearch/sql/ppl/parser/AstExpressionBuilder.java

@@ -9,6 +9,7 @@
 import static org.opensearch.sql.ast.dsl.AstDSL.qualifiedName;
 import static org.opensearch.sql.expression.function.BuiltinFunctionName.IS_NOT_NULL;
 import static org.opensearch.sql.expression.function.BuiltinFunctionName.IS_NULL;
+import static org.opensearch.sql.expression.function.BuiltinFunctionName.POSITION;
 import static org.opensearch.sql.ppl.antlr.parser.OpenSearchPPLParser.BinaryArithmeticContext;
 import static org.opensearch.sql.ppl.antlr.parser.OpenSearchPPLParser.BooleanFunctionCallContext;
 import static org.opensearch.sql.ppl.antlr.parser.OpenSearchPPLParser.BooleanLiteralContext;
@@ -290,6 +291,15 @@ public UnresolvedExpression visitTableSource(TableSourceContext ctx) {
     }
   }
 
+  @Override
+  public UnresolvedExpression visitPositionFunction(
+          OpenSearchPPLParser.PositionFunctionContext ctx) {
+    return new Function(
+            POSITION.getName().getFunctionName(),
+            Arrays.asList(visitFunctionArg(ctx.functionArg(0)),
+                    visitFunctionArg(ctx.functionArg(1))));
+  }
+
   /**
    * Literal and value.
    */

ppl/src/test/java/org/opensearch/sql/ppl/parser/AstExpressionBuilderTest.java

@@ -181,6 +181,19 @@ public void testEvalFunctionExprNoArgs() {
         ));
   }
 
+  @Test
+  public void testPositionFunctionExpr() {
+    assertEqual("source=t | eval f=position('substr' IN 'str')",
+        eval(
+            relation("t"),
+            let(
+                field("f"),
+                function("position",
+                        stringLiteral("substr"), stringLiteral("str"))
+            )
+        ));
+  }
+
   @Test
   public void testEvalBinaryOperationExpr() {
     assertEqual("source=t | eval f=a+b",