Merge branch 'main' into postgres_load_statement

src/sqlfluff/dialects/dialect_ansi.py

@@ -58,7 +58,10 @@
 
 ansi_dialect.set_lexer_matchers(
     [
-        RegexLexer("whitespace", r"[\t ]+", WhitespaceSegment),
+        # Match all forms of whitespace except newlines and carriage returns:
+        # https://stackoverflow.com/questions/3469080/match-whitespace-but-not-newlines
+        # This pattern allows us to also match non-breaking spaces (#2189).
+        RegexLexer("whitespace", r"[^\S\r\n]+", WhitespaceSegment),
         RegexLexer(
             "inline_comment",
             r"(--|#)[^\n]*",
@@ -76,7 +79,7 @@
             ),
             trim_post_subdivide=RegexLexer(
                 "whitespace",
-                r"[\t ]+",
+                r"[^\S\r\n]+",
                 WhitespaceSegment,
             ),
         ),

src/sqlfluff/dialects/dialect_postgres.py

@@ -2765,6 +2765,8 @@ class StatementSegment(BaseSegment):
             Ref("AlterFunctionStatementSegment"),
             Ref("AlterViewStatementSegment"),
             Ref("LoadStatementSegment"),
+            Ref("ResetStatementSegment"),
+            Ref("DiscardStatementSegment"),
         ],
     )
 
@@ -3069,3 +3071,37 @@ class LoadStatementSegment(BaseSegment):
         "LOAD",
         Ref("QuotedLiteralSegment"),
     )
+
+
+@postgres_dialect.segment()
+class ResetStatementSegment(BaseSegment):
+    """A `RESET` statement.
+
+    As Specified in https://www.postgresql.org/docs/14/sql-reset.html
+    """
+
+    type = "reset_statement"
+    match_grammar = Sequence(
+        "RESET",
+        OneOf("ALL", Ref("ParameterNameSegment")),
+    )
+
+
+@postgres_dialect.segment()
+class DiscardStatementSegment(BaseSegment):
+    """A `DISCARD` statement.
+
+    As Specified in https://www.postgresql.org/docs/14/sql-discard.html
+    """
+
+    type = "discard_statement"
+    match_grammar = Sequence(
+        "DISCARD",
+        OneOf(
+            "ALL",
+            "PLANS",
+            "SEQUENCES",
+            "TEMPORARY",
+            "TEMP",
+        ),
+    )

src/sqlfluff/dialects/dialect_redshift.py

@@ -486,13 +486,13 @@ class AlterGroupSegment(BaseSegment):
                 OneOf("ADD", "DROP"),
                 "USER",
                 Delimited(
-                    Ref("NakedIdentifierSegment"),
+                    Ref("ObjectReferenceSegment"),
                 ),
             ),
             Sequence(
                 "RENAME",
                 "TO",
-                Ref("NakedIdentifierSegment"),
+                Ref("ObjectReferenceSegment"),
             ),
         ),
     )

src/sqlfluff/dialects/dialect_snowflake.py

@@ -561,6 +561,9 @@ class StatementSegment(ansi_dialect.get_segment("StatementSegment")):  # type: i
             Ref("AlterFunctionStatementSegment"),
             Ref("CreateStageSegment"),
             Ref("AlterStageSegment"),
+            Ref("UnsetStatementSegment"),
+            Ref("UndropStatementSegment"),
+            Ref("CommentStatementSegment"),
         ],
         remove=[
             Ref("CreateTypeStatementSegment"),
@@ -3342,3 +3345,134 @@ class DescribeStatementSegment(BaseSegment):
             ),
         ),
     )
+
+
+@snowflake_dialect.segment()
+class UnsetStatementSegment(BaseSegment):
+    """An `UNSET` statement.
+
+    https://docs.snowflake.com/en/sql-reference/sql/unset.html
+    """
+
+    type = "unset_statement"
+
+    match_grammar = Sequence(
+        "UNSET",
+        OneOf(
+            Ref("LocalVariableNameSegment"),
+            Bracketed(
+                Delimited(
+                    Ref("LocalVariableNameSegment"),
+                )
+            ),
+        ),
+    )
+
+
+@snowflake_dialect.segment()
+class UndropStatementSegment(BaseSegment):
+    """`UNDROP` statement.
+
+    DATABASE: https://docs.snowflake.com/en/sql-reference/sql/undrop-database.html
+    SCHEMA: https://docs.snowflake.com/en/sql-reference/sql/undrop-schema.html
+    TABLE: https://docs.snowflake.com/en/sql-reference/sql/undrop-table.html
+    """
+
+    type = "undrop_statement"
+    match_grammar = Sequence(
+        "UNDROP",
+        OneOf(
+            Sequence(
+                "DATABASE",
+                Ref("DatabaseReferenceSegment"),
+            ),
+            Sequence(
+                "SCHEMA",
+                Ref("SchemaReferenceSegment"),
+            ),
+            Sequence(
+                "TABLE",
+                Ref("TableReferenceSegment"),
+            ),
+        ),
+    )
+
+
+@snowflake_dialect.segment()
+class CommentStatementSegment(BaseSegment):
+    """`COMMENT` statement grammar.
+
+    https://docs.snowflake.com/en/sql-reference/sql/comment.html
+
+    N.B. this applies to all objects, so there may be some I've missed
+    here so add any others to the OneOf grammar below.
+    """
+
+    type = "comment_statement"
+    match_grammar = Sequence(
+        "COMMENT",
+        Sequence(
+            "IF",
+            "EXISTS",
+            optional=True,
+        ),
+        "ON",
+        OneOf(
+            "COLUMN",
+            "TABLE",
+            "VIEW",
+            "SCHEMA",
+            "DATABASE",
+            "WAREHOUSE",
+            "USER",
+            "STAGE",
+            "FUNCTION",
+            "PROCEDURE",
+            "SEQUENCE",
+            "SHARE",
+            "PIPE",
+            "STREAM",
+            "TASK",
+            Sequence(
+                "NETWORK",
+                "POLICY",
+            ),
+            Sequence(
+                OneOf(
+                    "API",
+                    "NOTIFICATION",
+                    "SECURITY",
+                    "STORAGE",
+                ),
+                "INTEGRATION",
+            ),
+            Sequence(
+                "SESSION",
+                "POLICY",
+            ),
+            Sequence(
+                "EXTERNAL",
+                "TABLE",
+            ),
+            Sequence(
+                "MATERIALIZED",
+                "VIEW",
+            ),
+            Sequence(
+                "MASKING",
+                "POLICY",
+            ),
+            Sequence(
+                "ROW",
+                "ACCESS",
+                "POLICY",
+            ),
+            Sequence(
+                "FILE",
+                "FORMAT",
+            ),
+        ),
+        Ref("ObjectReferenceSegment"),
+        "IS",
+        Ref("QuotedLiteralSegment"),
+    )

src/sqlfluff/dialects/dialect_snowflake_keywords.py

@@ -384,6 +384,7 @@
 TRUNCATECOLUMNS
 TYPE
 UNBOUNDED
+UNDROP
 UNSET
 UNSIGNED
 URL

src/sqlfluff/dialects/dialect_tsql.py

@@ -120,7 +120,7 @@
             ),
             trim_post_subdivide=RegexLexer(
                 "whitespace",
-                r"[\t ]+",
+                r"[^\S\r\n]+",
                 WhitespaceSegment,
             ),
         ),

src/sqlfluff/rules/L010.py

@@ -44,6 +44,7 @@ class Rule_L010(BaseRule):
     _target_elems: List[Tuple[str, str]] = [
         ("type", "keyword"),
         ("type", "binary_operator"),
+        ("type", "date_part"),
     ]
     config_keywords = ["capitalisation_policy"]
     # Human readable target elem for description

src/sqlfluff/rules/L041.py

@@ -1,4 +1,4 @@
-"""Implementation of Rule L040."""
+"""Implementation of Rule L041."""
 from typing import Optional
 
 from sqlfluff.core.parser import NewlineSegment, WhitespaceSegment

test/core/parser/lexer_test.py

@@ -83,9 +83,9 @@ def test__parser__lexer_string(raw, res):
         ("fsaljk", r"f", "f"),
         ("fsaljk", r"[fas]*", "fsa"),
         # Matching whitespace segments
-        ("   \t   fsaljk", r"[\t ]*", "   \t   "),
+        ("   \t   fsaljk", r"[^\S\r\n]*", "   \t   "),
         # Matching whitespace segments (with a newline)
-        ("   \t \n  fsaljk", r"[\t ]*", "   \t "),
+        ("   \t \n  fsaljk", r"[^\S\r\n]*", "   \t "),
         # Matching quotes containing stuff
         ("'something boring'   \t \n  fsaljk", r"'[^']*'", "'something boring'"),
         (

test/fixtures/dialects/ansi/non_breaking_space.sql

@@ -0,0 +1,2 @@
+#space before from is non-breaking space
+SELECT a,b, c  from sch."blah"

test/fixtures/dialects/ansi/non_breaking_space.yml

@@ -0,0 +1,31 @@
+# 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: bd4e28c926e3d5460408d9f53857a363b44ddaaba8da61153c9969cd9e37062a
+file:
+  statement:
+    select_statement:
+      select_clause:
+      - keyword: SELECT
+      - select_clause_element:
+          column_reference:
+            identifier: a
+      - comma: ','
+      - select_clause_element:
+          column_reference:
+            identifier: b
+      - comma: ','
+      - select_clause_element:
+          column_reference:
+            identifier: c
+      from_clause:
+        keyword: from
+        from_expression:
+          from_expression_element:
+            table_expression:
+              table_reference:
+              - identifier: sch
+              - dot: .
+              - identifier: '"blah"'

test/fixtures/dialects/postgres/postgres_discard.sql

@@ -0,0 +1,5 @@
+DISCARD ALL;
+DISCARD PLANS;
+DISCARD SEQUENCES;
+DISCARD TEMPORARY;
+DISCARD TEMP;

test/fixtures/dialects/postgres/postgres_discard.yml

@@ -0,0 +1,32 @@
+# 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: 00eaafbc98c8ec708bf86bddd93c306cd4f60e77c39d8b9d01d8e7aa70b90d7f
+file:
+- statement:
+    discard_statement:
+    - keyword: DISCARD
+    - keyword: ALL
+- statement_terminator: ;
+- statement:
+    discard_statement:
+    - keyword: DISCARD
+    - keyword: PLANS
+- statement_terminator: ;
+- statement:
+    discard_statement:
+    - keyword: DISCARD
+    - keyword: SEQUENCES
+- statement_terminator: ;
+- statement:
+    discard_statement:
+    - keyword: DISCARD
+    - keyword: TEMPORARY
+- statement_terminator: ;
+- statement:
+    discard_statement:
+    - keyword: DISCARD
+    - keyword: TEMP
+- statement_terminator: ;

test/fixtures/dialects/postgres/postgres_reset.sql

@@ -0,0 +1,2 @@
+RESET timezone;
+RESET ALL;

test/fixtures/dialects/postgres/postgres_reset.yml

@@ -0,0 +1,17 @@
+# 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: e9e279911916c47d20deb5cce0ef040ce5e573f71b5044dc43b3a1f3b64bbc23
+file:
+- statement:
+    reset_statement:
+      keyword: RESET
+      parameter: timezone
+- statement_terminator: ;
+- statement:
+    reset_statement:
+    - keyword: RESET
+    - keyword: ALL
+- statement_terminator: ;

test/fixtures/dialects/redshift/redshift_alter_group.sql

@@ -10,3 +10,6 @@ drop user dwuser1, dwuser2;
 
 alter group admin_group
 rename to administrators;
+
+alter group admin_group
+add user "test.user";