Skip to content

feat(optimizer)!: parse and annotate type for bigquery SOUNDEX #5576

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 14, 2025
+47 −0
Merged

feat(optimizer)!: parse and annotate type for bigquery SOUNDEX #5576

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
024aaee
feat(optimizer)!: parse and annotate type for bigquery SOUNDEX
geooo109 Aug 14, 2025
e02e263
fix tests and annotation
geooo109 Aug 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions sqlglot/dialects/bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -509,6 +509,7 @@ class BigQuery(Dialect):
exp.RegexpExtractAll: lambda self, e: self._annotate_by_args(e, "this", array=True),
exp.Replace: lambda self, e: self._annotate_by_args(e, "this"),
exp.Reverse: lambda self, e: self._annotate_by_args(e, "this"),
exp.Soundex: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
exp.SHA: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BINARY),
exp.SHA2: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BINARY),
exp.Sign: lambda self, e: self._annotate_by_args(e, "this"),
Expand Down
4 changes: 4 additions & 0 deletions sqlglot/expressions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6845,6 +6845,10 @@ class SortArray(Func):
arg_types = {"this": True, "asc": False}


class Soundex(Func):
pass


class Split(Func):
arg_types = {"this": True, "expression": True, "limit": False}

Expand Down
38 changes: 38 additions & 0 deletions tests/dialects/test_dialect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3930,3 +3930,41 @@ def test_translate(self):
"oracle": "TRANSLATE(x, y, z)",
},
)

def test_soundex(self):
self.validate_all(
"SOUNDEX(x)",
read={
"": "SOUNDEX(x)",
"bigquery": "SOUNDEX(x)",
"hive": "SOUNDEX(x)",
"spark2": "SOUNDEX(x)",
"spark": "SOUNDEX(x)",
"databricks": "SOUNDEX(x)",
"mysql": "SOUNDEX(x)",
"postgres": "SOUNDEX(x)",
"tsql": "SOUNDEX(x)",
"snowflake": "SOUNDEX(x)",
"dremio": "SOUNDEX(x)",
"trino": "SOUNDEX(x)",
"clickhouse": "SOUNDEX(x)",
"redshift": "SOUNDEX(x)",
"oracle": "SOUNDEX(x)",
},
write={
"bigquery": "SOUNDEX(x)",
"hive": "SOUNDEX(x)",
"spark2": "SOUNDEX(x)",
"spark": "SOUNDEX(x)",
"databricks": "SOUNDEX(x)",
"mysql": "SOUNDEX(x)",
"postgres": "SOUNDEX(x)",
"tsql": "SOUNDEX(x)",
"snowflake": "SOUNDEX(x)",
"dremio": "SOUNDEX(x)",
"trino": "SOUNDEX(x)",
"clickhouse": "SOUNDEX(x)",
"redshift": "SOUNDEX(x)",
"oracle": "SOUNDEX(x)",
},
)
4 changes: 4 additions & 0 deletions tests/fixtures/optimizer/annotate_functions.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -761,6 +761,10 @@ STRING;
TRANSLATE(b'AaBbCc', b'abc', b'123');
BINARY;

# dialect: bigquery
SOUNDEX('foo');
STRING;

--------------------------------------
-- Snowflake
--------------------------------------
Expand Down