sql-glider 0.1.5__tar.gz → 0.1.6__tar.gz

{sql_glider-0.1.5 → sql_glider-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.5
+Version: 0.1.6
 Summary: SQL Utility Toolkit for better understanding, use, and governance of your queries in a native environment.
 Project-URL: Homepage, https://github.com/rycowhi/sql-glider/
 Project-URL: Repository, https://github.com/rycowhi/sql-glider/

{sql_glider-0.1.5 → sql_glider-0.1.6}/plans/2026-01-26-file-scoped-schema-context.md

@@ -96,6 +96,8 @@ node = lineage(
 | LATERAL VIEW posexplode | Collects both position and element columns |
 | Multiple LATERAL VIEWs | Collects columns from all LATERAL VIEWs |
 | LATERAL VIEW OUTER | Same handling as regular LATERAL VIEW |
+| LEFT SEMI JOIN | Only includes left table columns (right table excluded) |
+| LEFT ANTI JOIN | Only includes left table columns (right table excluded) |
 
 ---
 
@@ -103,8 +105,8 @@ node = lineage(
 
 | File | Changes |
 |------|---------|
-| `src/sqlglider/lineage/analyzer.py` | Added `_file_schema` instance variable; Added 9 schema extraction methods (including `_resolve_lateral_columns`); Modified `analyze_queries()` and `_analyze_column_lineage_internal()` and `get_output_columns()` |
-| `tests/sqlglider/lineage/test_analyzer.py` | Added `TestFileSchemaExtraction` (9 tests), `TestCrossStatementLineage` (12 tests), and `TestLateralViewColumnResolution` (5 tests) |
+| `src/sqlglider/lineage/analyzer.py` | Added `_file_schema` instance variable; Added 9 schema extraction methods (including `_resolve_lateral_columns`); Modified `analyze_queries()` and `_analyze_column_lineage_internal()` and `get_output_columns()`; Added SEMI/ANTI join handling in `_resolve_star_columns()` |
+| `tests/sqlglider/lineage/test_analyzer.py` | Added `TestFileSchemaExtraction` (9 tests), `TestCrossStatementLineage` (12 tests), `TestLateralViewColumnResolution` (5 tests), and `TestSemiAntiJoinColumnResolution` (3 tests) |
 
 ---
 

{sql_glider-0.1.5 → sql_glider-0.1.6}/src/sqlglider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.5'
-__version_tuple__ = version_tuple = (0, 1, 5)
+__version__ = version = '0.1.6'
+__version_tuple__ = version_tuple = (0, 1, 6)
 
 __commit_id__ = commit_id = None

{sql_glider-0.1.5 → sql_glider-0.1.6}/src/sqlglider/lineage/analyzer.py

@@ -1412,10 +1412,16 @@ class LineageAnalyzer:
         columns.extend(self._resolve_source_columns(source, select_node))
 
         # Handle JOIN clauses - collect columns from all joined tables
+        # EXCEPT for SEMI and ANTI joins which only return left table columns
         joins = select_node.args.get("joins")
         if joins:
             for join in joins:
                 if isinstance(join, exp.Join):
+                    # SEMI and ANTI joins don't include right table columns in SELECT *
+                    join_kind = join.kind
+                    if join_kind in ("SEMI", "ANTI"):
+                        # Skip right table columns for SEMI/ANTI joins
+                        continue
                     join_source = join.this
                     columns.extend(
                         self._resolve_source_columns(join_source, select_node)

sql_glider-0.1.6/tests/fixtures/original_queries/test_cte_view_star.sql

@@ -0,0 +1,22 @@
+CREATE TEMPORARY VIEW first_view AS
+SELECT
+    v1,
+    v2,
+    v3
+FROM source_db.source_table;
+CREATE TEMPORARY VIEW second_view AS WITH cte AS (
+    SELECT
+        *,
+        row_number() OVER (ORDER BY v1) AS row_num
+    FROM first_view
+)
+
+SELECT * FROM cte
+WHERE row_num = 1;
+
+INSERT INTO target_db.target_table
+SELECT
+    v1,
+    v2,
+    v3
+FROM second_view;

{sql_glider-0.1.5 → sql_glider-0.1.6}/tests/sqlglider/lineage/test_analyzer.py

@@ -2766,3 +2766,57 @@ class TestLateralViewColumnResolution:
         # v3 schema should include columns from v1, v2, and the lateral view
         assert "v3" in analyzer._file_schema
         assert set(analyzer._file_schema["v3"].keys()) == {"id", "arr", "name", "elem"}
+
+
+class TestSemiAntiJoinColumnResolution:
+    """Tests for SEMI and ANTI JOIN column resolution in SELECT *."""
+
+    def test_left_semi_join_only_returns_left_columns(self):
+        """LEFT SEMI JOIN should only include columns from the left table."""
+        sql = """
+        CREATE VIEW v1 AS SELECT a, b FROM t1;
+        CREATE VIEW v2 AS SELECT c FROM t2;
+        CREATE VIEW v3 AS SELECT * FROM v1 LEFT SEMI JOIN v2 ON v1.a = v2.c;
+        """
+        analyzer = LineageAnalyzer(sql, dialect="spark")
+        analyzer.analyze_queries(level=AnalysisLevel.COLUMN)
+
+        # v3 schema should only include columns from v1 (a, b), not v2 (c)
+        assert "v3" in analyzer._file_schema
+        assert set(analyzer._file_schema["v3"].keys()) == {"a", "b"}
+
+    def test_left_anti_join_only_returns_left_columns(self):
+        """LEFT ANTI JOIN should only include columns from the left table."""
+        sql = """
+        CREATE VIEW v1 AS SELECT a, b FROM t1;
+        CREATE VIEW v2 AS SELECT c FROM t2;
+        CREATE VIEW v3 AS SELECT * FROM v1 LEFT ANTI JOIN v2 ON v1.a = v2.c;
+        """
+        analyzer = LineageAnalyzer(sql, dialect="spark")
+        analyzer.analyze_queries(level=AnalysisLevel.COLUMN)
+
+        # v3 schema should only include columns from v1 (a, b), not v2 (c)
+        assert "v3" in analyzer._file_schema
+        assert set(analyzer._file_schema["v3"].keys()) == {"a", "b"}
+
+    def test_semi_join_vs_inner_join(self):
+        """SEMI JOIN should behave differently from INNER JOIN for SELECT *."""
+        # INNER JOIN returns columns from both tables
+        sql_inner = """
+        CREATE VIEW v1 AS SELECT a FROM t1;
+        CREATE VIEW v2 AS SELECT b FROM t2;
+        CREATE VIEW v3 AS SELECT * FROM v1 JOIN v2 ON v1.a = v2.b;
+        """
+        analyzer_inner = LineageAnalyzer(sql_inner, dialect="spark")
+        analyzer_inner.analyze_queries(level=AnalysisLevel.COLUMN)
+        assert set(analyzer_inner._file_schema["v3"].keys()) == {"a", "b"}
+
+        # SEMI JOIN returns only left table columns
+        sql_semi = """
+        CREATE VIEW v1 AS SELECT a FROM t1;
+        CREATE VIEW v2 AS SELECT b FROM t2;
+        CREATE VIEW v3 AS SELECT * FROM v1 LEFT SEMI JOIN v2 ON v1.a = v2.b;
+        """
+        analyzer_semi = LineageAnalyzer(sql_semi, dialect="spark")
+        analyzer_semi.analyze_queries(level=AnalysisLevel.COLUMN)
+        assert set(analyzer_semi._file_schema["v3"].keys()) == {"a"}