Add more keywords as identifier in PPL (#1319) (#1323)

opensearch-trigger-bot[bot] · penghuo · web-flow · commit 0b101363bdc1 · 2023-02-03T17:17:45.000-08:00
Signed-off-by: Peng Huo <penghuo@gmail.com> (cherry picked from commit 79c7922) Co-authored-by: Peng Huo <penghuo@gmail.com>
diff --git a/ppl/src/main/antlr/OpenSearchPPLParser.g4 b/ppl/src/main/antlr/OpenSearchPPLParser.g4
@@ -610,12 +610,26 @@ wildcard
 
 keywordsCanBeId
     : D // OD SQL and ODBC special
-    | statsFunctionName
-    | TIMESTAMP | DATE | TIME
-    | FIRST | LAST
     | timespanUnit | SPAN
-    | dateAndTimeFunctionBase
-    | textFunctionBase
-    | mathematicalFunctionBase
-    | positionFunctionName
+    | evalFunctionName
+    | relevanceArgName
+    | intervalUnit
+    // commands
+    | SEARCH | DESCRIBE | SHOW | FROM | WHERE | FIELDS | RENAME | STATS | DEDUP | SORT | EVAL | HEAD | TOP | RARE
+    | PARSE | METHOD | REGEX | PUNCT | GROK | PATTERN | PATTERNS | NEW_FIELD | KMEANS | AD | ML
+    // commands assist keywords
+    | SOURCE | INDEX | DESC | DATASOURCES
+    // CLAUSEKEYWORDS
+    | SORTBY
+    // FIELDKEYWORDSAUTO
+    | STR | IP | NUM
+    // ARGUMENT KEYWORDS
+    | KEEPEMPTY | CONSECUTIVE | DEDUP_SPLITVALUES | PARTITIONS | ALLNUM | DELIM | CENTROIDS | ITERATIONS | DISTANCE_TYPE
+    | NUMBER_OF_TREES | SHINGLE_SIZE | SAMPLE_SIZE | OUTPUT_AFTER | TIME_DECAY | ANOMALY_RATE | CATEGORY_FIELD
+    | TIME_FIELD | TIME_ZONE | TRAINING_DATA_SIZE | ANOMALY_SCORE_THRESHOLD
+    // AGGREGATIONS
+    | AVG | COUNT | DISTINCT_COUNT | ESTDC | ESTDC_ERROR | MAX | MEAN | MEDIAN | MIN | MODE | RANGE | STDEV | STDEVP
+    | SUM | SUMSQ | VAR_SAMP | VAR_POP | STDDEV_SAMP | STDDEV_POP | PERCENTILE | TAKE | FIRST | LAST | LIST | VALUES
+    | EARLIEST | EARLIEST_TIME | LATEST | LATEST_TIME | PER_DAY | PER_HOUR | PER_MINUTE | PER_SECOND | RATE | SPARKLINE
+    | C | DC
     ;
diff --git a/ppl/src/test/java/org/opensearch/sql/ppl/parser/AstExpressionBuilderTest.java b/ppl/src/test/java/org/opensearch/sql/ppl/parser/AstExpressionBuilderTest.java
@@ -813,6 +813,11 @@ public void functionNameCanBeUsedAsIdentifier() {
         "ABS | CEIL | CEILING | CONV | CRC32 | E | EXP | FLOOR | LN | LOG"
         + " | LOG10 | LOG2 | MOD | PI |POW | POWER | RAND | ROUND | SIGN | SQRT | TRUNCATE "
             + "| ACOS | ASIN | ATAN | ATAN2 | COS | COT | DEGREES | RADIANS | SIN | TAN");
+    assertFunctionNameCouldBeId(
+        "SEARCH | DESCRIBE | SHOW | FROM | WHERE | FIELDS | RENAME | STATS "
+            + "| DEDUP | SORT | EVAL | HEAD | TOP | RARE | PARSE | METHOD | REGEX | PUNCT | GROK "
+            + "| PATTERN | PATTERNS | NEW_FIELD | KMEANS | AD | ML | SOURCE | INDEX | D | DESC "
+            + "| DATASOURCES");
   }
 
   void assertFunctionNameCouldBeId(String antlrFunctionName) {
@@ -833,4 +838,26 @@ void assertFunctionNameCouldBeId(String antlrFunctionName) {
           ));
     }
   }
+
+  // https://github.com/opensearch-project/sql/issues/1318
+  @Test
+  public void indexCanBeId() {
+    assertEqual("source = index | stats count() by index",
+        agg(
+            relation("index"),
+            exprList(
+                alias(
+                    "count()",
+                    aggregate("count", AllFields.of())
+                )
+            ),
+            emptyList(),
+            exprList(
+                alias(
+                    "index",
+                    field("index")
+                )),
+            defaultStatsArgs()
+        ));
+  }
 }
