Merge branch 'main' into extra_config_path

src/sqlfluff/dialects/dialect_bigquery.py

@@ -30,7 +30,9 @@
     OptionallyBracketed,
     Indent,
     Dedent,
+    Matchable,
 )
+from sqlfluff.core.parser.segments.base import BracketedSegment
 
 from sqlfluff.core.dialects import load_raw_dialect
 
@@ -123,6 +125,18 @@
         type="literal",
         trim_chars=("@",),
     ),
+    # Add a Full equivalent which also allow keywords
+    NakedIdentifierSegmentFull=RegexParser(
+        r"[A-Z0-9_]*[A-Z][A-Z0-9_]*",
+        CodeSegment,
+        name="naked_identifier_all",
+        type="identifier",
+    ),
+    SingleIdentifierGrammarFull=OneOf(
+        Ref("NakedIdentifierSegment"),
+        Ref("QuotedIdentifierSegment"),
+        Ref("NakedIdentifierSegmentFull"),
+    ),
 )
 
 
@@ -633,9 +647,47 @@ class LiteralCoercionSegment(BaseSegment):
 
 @bigquery_dialect.segment(replace=True)
 class ColumnReferenceSegment(ObjectReferenceSegment):  # type: ignore
-    """A reference to column, field or alias."""
+    """A reference to column, field or alias.
+
+    We override this for BigQuery to allow keywords in structures
+    (using Full segments) and to properly return references for objects.
+
+    Ref: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical
+    "A reserved keyword must be a quoted identifier if it is a standalone
+    keyword or the first component of a path expression. It may be unquoted
+    as the second or later component of a path expression."
+    """
 
     type = "column_reference"
+    match_grammar: Matchable = Sequence(
+        Ref("SingleIdentifierGrammar"),
+        Sequence(
+            OneOf(Ref("DotSegment"), Sequence(Ref("DotSegment"), Ref("DotSegment"))),
+            Delimited(
+                Ref("SingleIdentifierGrammarFull"),
+                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("DelimiterSegment"),
+                    BracketedSegment,
+                ),
+                allow_gaps=False,
+            ),
+            allow_gaps=False,
+            optional=True,
+        ),
+        allow_gaps=False,
+    )
 
     def extract_possible_references(self, level):
         """Extract possible references of a given level."""

test/fixtures/dialects/bigquery/select_column_object_with_keyword.sql

@@ -0,0 +1,7 @@
+-- current is a reserved word but keywords are allowed as part of a nested object name
+SELECT
+  table1.current.column,
+  table1.object.current.column,
+  table1.object.nested.current.column,
+FROM
+  table1

test/fixtures/dialects/bigquery/select_column_object_with_keyword.yml

@@ -0,0 +1,48 @@
+# 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: e9b7b38575826b8cc463734bcc7647038a51e5b8342f3c2dd6624b233bae30d8
+file:
+  statement:
+    select_statement:
+      select_clause:
+      - keyword: SELECT
+      - select_clause_element:
+          column_reference:
+          - identifier: table1
+          - dot: .
+          - identifier: current
+          - dot: .
+          - identifier: column
+      - comma: ','
+      - select_clause_element:
+          column_reference:
+          - identifier: table1
+          - dot: .
+          - identifier: object
+          - dot: .
+          - identifier: current
+          - dot: .
+          - identifier: column
+      - comma: ','
+      - select_clause_element:
+          column_reference:
+          - identifier: table1
+          - dot: .
+          - identifier: object
+          - dot: .
+          - identifier: nested
+          - dot: .
+          - identifier: current
+          - dot: .
+          - identifier: column
+      - comma: ','
+      from_clause:
+        keyword: FROM
+        from_expression:
+          from_expression_element:
+            table_expression:
+              table_reference:
+                identifier: table1