SparkSQL: added support for : (colon sign) operator (Databricks SQL) (sqlfluff#3956)

Author: karabulute

src/sqlfluff/dialects/dialect_ansi.py

@@ -656,6 +656,24 @@ class CompositeComparisonOperatorSegment(BaseSegment):
     ),
     TrimParametersGrammar=OneOf("BOTH", "LEADING", "TRAILING"),
     DefaultValuesGrammar=Sequence("DEFAULT", "VALUES"),
+    ObjectReferenceDelimiterGrammar=OneOf(
+        Ref("DotSegment"),
+        Sequence(Ref("DotSegment"), Ref("DotSegment")),
+    ),
+    ObjectReferenceTerminatorGrammar=OneOf(
+        "ON",
+        "AS",
+        "USING",
+        Ref("CommaSegment"),
+        Ref("CastOperatorSegment"),
+        Ref("StartSquareBracketSegment"),
+        Ref("StartBracketSegment"),
+        Ref("BinaryOperatorGrammar"),
+        Ref("ColonSegment"),
+        Ref("DelimiterGrammar"),
+        Ref("JoinLikeClauseGrammar"),
+        BracketedSegment,
+    ),
 )
 
 
@@ -806,23 +824,8 @@ class ObjectReferenceSegment(BaseSegment):
     # match grammar (don't allow whitespace)
     match_grammar: Matchable = Delimited(
         Ref("SingleIdentifierGrammar"),
-        delimiter=OneOf(
-            Ref("DotSegment"), Sequence(Ref("DotSegment"), Ref("DotSegment"))
-        ),
-        terminator=OneOf(
-            "ON",
-            "AS",
-            "USING",
-            Ref("CommaSegment"),
-            Ref("CastOperatorSegment"),
-            Ref("StartSquareBracketSegment"),
-            Ref("StartBracketSegment"),
-            Ref("BinaryOperatorGrammar"),
-            Ref("ColonSegment"),
-            Ref("DelimiterGrammar"),
-            Ref("JoinLikeClauseGrammar"),
-            BracketedSegment,
-        ),
+        delimiter=Ref("ObjectReferenceDelimiterGrammar"),
+        terminator=Ref("ObjectReferenceTerminatorGrammar"),
         allow_gaps=False,
     )
 

src/sqlfluff/dialects/dialect_sparksql.py

@@ -346,6 +346,26 @@
         # Add arrow operators for lambdas (e.g. aggregate)
         Ref("RightArrowOperator"),
     ),
+    # Support for colon sign operator (Databricks SQL)
+    ObjectReferenceDelimiterGrammar=OneOf(
+        Ref("DotSegment"),
+        Sequence(Ref("DotSegment"), Ref("DotSegment")),
+        Ref("ColonSegment"),
+    ),
+    # Support for colon sign operator (Databricks SQL)
+    ObjectReferenceTerminatorGrammar=OneOf(
+        "ON",
+        "AS",
+        "USING",
+        Ref("CommaSegment"),
+        Ref("CastOperatorSegment"),
+        Ref("StartSquareBracketSegment"),
+        Ref("StartBracketSegment"),
+        Ref("BinaryOperatorGrammar"),
+        Ref("DelimiterGrammar"),
+        Ref("JoinLikeClauseGrammar"),
+        ansi.BracketedSegment,
+    ),
 )
 
 sparksql_dialect.add(

test/fixtures/dialects/sparksql/databricks_operator_colon_sign.sql

@@ -0,0 +1,5 @@
+SELECT c1:price
+FROM VALUES('{ "price": 5 }') AS T(c1);
+
+SELECT c1:['price']::DECIMAL(5, 2)
+FROM VALUES('{ "price": 5 }') AS T(c1);

test/fixtures/dialects/sparksql/databricks_operator_colon_sign.yml

@@ -0,0 +1,83 @@
+# YML test files are auto-generated from SQL files and should not be edited by
+# hand. To help enforce this, the "hash" field in the file must match a hash
+# computed by SQLFluff when running the tests. Please run
+# `python test/generate_parse_fixture_yml.py`  to generate them after adding or
+# altering SQL files.
+_hash: 55cdb3f3a236b72c83d31e4f9dc44c8edd428bd66484847b6fde17cfd6b809cb
+file:
+- statement:
+    select_statement:
+      select_clause:
+        keyword: SELECT
+        select_clause_element:
+          column_reference:
+          - naked_identifier: c1
+          - colon: ':'
+          - naked_identifier: price
+      from_clause:
+        keyword: FROM
+        from_expression:
+          from_expression_element:
+            table_expression:
+              values_clause:
+                keyword: VALUES
+                bracketed:
+                  start_bracket: (
+                  expression:
+                    quoted_literal: "'{ \"price\": 5 }'"
+                  end_bracket: )
+                alias_expression:
+                  keyword: AS
+                  naked_identifier: T
+                  bracketed:
+                    start_bracket: (
+                    identifier_list:
+                      naked_identifier: c1
+                    end_bracket: )
+- statement_terminator: ;
+- statement:
+    select_statement:
+      select_clause:
+        keyword: SELECT
+        select_clause_element:
+          expression:
+            column_reference:
+              naked_identifier: c1
+              colon: ':'
+            array_accessor:
+              start_square_bracket: '['
+              expression:
+                quoted_literal: "'price'"
+              end_square_bracket: ']'
+            cast_expression:
+              casting_operator: '::'
+              data_type:
+                primitive_type:
+                  keyword: DECIMAL
+                  bracketed:
+                  - start_bracket: (
+                  - numeric_literal: '5'
+                  - comma: ','
+                  - numeric_literal: '2'
+                  - end_bracket: )
+      from_clause:
+        keyword: FROM
+        from_expression:
+          from_expression_element:
+            table_expression:
+              values_clause:
+                keyword: VALUES
+                bracketed:
+                  start_bracket: (
+                  expression:
+                    quoted_literal: "'{ \"price\": 5 }'"
+                  end_bracket: )
+                alias_expression:
+                  keyword: AS
+                  naked_identifier: T
+                  bracketed:
+                    start_bracket: (
+                    identifier_list:
+                      naked_identifier: c1
+                    end_bracket: )
+- statement_terminator: ;