sql-glider 0.1.9__py3-none-any.whl → 0.1.11__py3-none-any.whl

{sql_glider-0.1.9.dist-info → sql_glider-0.1.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.9
+Version: 0.1.11
 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-0.1.9.dist-info → sql_glider-0.1.11.dist-info}/RECORD

@@ -1,6 +1,6 @@
 sqlglider/__init__.py,sha256=gDf7s52dMcX7JuCZ1SLawcB1vb3U0yJCohu9RQAATBY,125
-sqlglider/_version.py,sha256=ib8ckvf-NNDfacXd8unW0p5cf-gl57XyQvjoEMc_pvc,704
-sqlglider/cli.py,sha256=9sweHRVLk2iBSzCzT2Gcj8y1g1XKzq26iApQsMaFbx4,51786
+sqlglider/_version.py,sha256=0-Ruc52ECccw_8Ef0d7jMkzrb8fkobUkZLqGGvcm1ik,706
+sqlglider/cli.py,sha256=DMCMw5dxDHB2MuxBXuJMNeDSlIGAfKDz1Renp0YwGGM,52224
 sqlglider/global_models.py,sha256=2vyJXAuXOsXQpE-D3F0ejj7eR9z0nDWFjTkielhzM8k,356
 sqlglider/catalog/__init__.py,sha256=2PqFPyzFXJ14FpSUcBmVK2L-a_ypWQHAbHFHxLDk_LE,814
 sqlglider/catalog/base.py,sha256=R7htHC43InpH4uRjYk33dMYYji6oylHns7Ye_mgfjJE,3116
@@ -11,13 +11,13 @@ sqlglider/dissection/analyzer.py,sha256=-GD3-lTbfBthq1BW6HiDjvJx2y4LDmnUVHIVIb0H
 sqlglider/dissection/formatters.py,sha256=M7gsmTNljRIeLIRv4D0vHvqJVrTqWSpsg7vem83zSzY,7302
 sqlglider/dissection/models.py,sha256=RRD3RIteqbUBY6e-74skKDvMH3qeAUaqA2sFcrjP5GQ,3618
 sqlglider/graph/__init__.py,sha256=4DDdrPM75CmeQWt7wHdBsjCm1s70BHGLYdijIbaUEKY,871
-sqlglider/graph/builder.py,sha256=0ASA749b_FkcKMEVWiijAJP1QKt54ICY7VXxUuo3-y0,11953
+sqlglider/graph/builder.py,sha256=HdkMcuZkxdEFO0CXMAaqGQSyhvzuaIQTaFscQdO2GSI,12146
 sqlglider/graph/merge.py,sha256=uUZlm4BN3S9gRL66Cc2mzhbtuh4SVAv2n4cN4eUEQBU,4077
 sqlglider/graph/models.py,sha256=EYmjv_WzDSNp_WfhJ6H-qBIOkAcoNKS7GRUryfKrHuY,9330
 sqlglider/graph/query.py,sha256=LHU8Cvn7ZPPSEnqdDn2pF8f1_LQjIvNIrZqs8cFlb6U,9433
 sqlglider/graph/serialization.py,sha256=vMXn7s35jA499e7l90vNVaJE_3QR_VHf3rEfQ9ZlgTQ,2781
 sqlglider/lineage/__init__.py,sha256=llXMeI5_PIZaiBo8tKk3-wOubF4m_6QBHbn1FtWxT7k,256
-sqlglider/lineage/analyzer.py,sha256=4VoJAsNRpz8T4sifF9VW4_SkSSU-8GtcBdDORCfPV_0,65581
+sqlglider/lineage/analyzer.py,sha256=gjJtJU-sxFokoSVxcHpcIdbP3H8GD_KQaubbbcG0UCM,68982
 sqlglider/lineage/formatters.py,sha256=_Y9wcTX4JXn1vVnZ1xI656g1FF2rMjcAVc-GHjbd9QA,10389
 sqlglider/templating/__init__.py,sha256=g3_wb6rSDI0usq2UUMDpn-J5kVwlAw3NtLdwbxL6UHs,1435
 sqlglider/templating/base.py,sha256=y5bWAW7qXl_4pPyo5KycfHwNVvt1-7slZ63DAsvTE1s,2902
@@ -25,10 +25,10 @@ sqlglider/templating/jinja.py,sha256=o01UG72N4G1-tOT5LKK1Wkccv4nJH2VN4VFaMi5c1-g
 sqlglider/templating/registry.py,sha256=BJU3N2qNVMTUtkgbibyqo8Wme_acXQRw5XI-6ZVgyac,3476
 sqlglider/templating/variables.py,sha256=5593PtLBcOxsnMCSRm2pGAD5I0Y9f__VV3_J_HfXVlQ,8010
 sqlglider/utils/__init__.py,sha256=KGp9-UzKz_OFBOTFoSy-g-NXDZsvyWXG_9-1zcC6ePE,276
-sqlglider/utils/config.py,sha256=iNJgSXFw3pmL2MCdvW3SJp4X2T3AQP2QyQuXIXT-6H0,4761
+sqlglider/utils/config.py,sha256=rbbiDCWA_h29vgWJZ1z3zQmGcei0KcxhTPcymSCYeFo,4796
 sqlglider/utils/file_utils.py,sha256=5_ff28E0r1R7emZzsOnRuHd-7zIX6873eyr1SuPEr4E,1093
-sql_glider-0.1.9.dist-info/METADATA,sha256=LOSe-vTRzfkFsnas1cHSFgnRJZL3bO34ujqLcUWMN1Q,28445
-sql_glider-0.1.9.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-sql_glider-0.1.9.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
-sql_glider-0.1.9.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sql_glider-0.1.9.dist-info/RECORD,,
+sql_glider-0.1.11.dist-info/METADATA,sha256=JxQakiYUUzvldsEzjdXQLV63ud07Gw_bcZ2BIi29nuQ,28446
+sql_glider-0.1.11.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+sql_glider-0.1.11.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
+sql_glider-0.1.11.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sql_glider-0.1.11.dist-info/RECORD,,

sqlglider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.9'
-__version_tuple__ = version_tuple = (0, 1, 9)
+__version__ = version = '0.1.11'
+__version_tuple__ = version_tuple = (0, 1, 11)
 
 __commit_id__ = commit_id = None

sqlglider/cli.py

@@ -166,6 +166,11 @@ def lineage(
         exists=True,
         help="Path to variables file (JSON or YAML)",
     ),
+    no_star: bool = typer.Option(
+        False,
+        "--no-star",
+        help="Fail if SELECT * cannot be resolved to actual columns",
+    ),
 ) -> None:
     """
     Analyze column or table lineage for a SQL file.
@@ -207,6 +212,7 @@ def lineage(
     level_str = level or config.level or "column"
     output_format = output_format or config.output_format or "text"
     templater = templater or config.templater  # None means no templating
+    no_star = no_star or config.no_star or False
     # Validate and convert level to enum
     try:
         analysis_level = AnalysisLevel(level_str)
@@ -261,7 +267,7 @@ def lineage(
         )
 
         # Create analyzer
-        analyzer = LineageAnalyzer(sql, dialect=dialect)
+        analyzer = LineageAnalyzer(sql, dialect=dialect, no_star=no_star)
 
         # Unified lineage analysis (handles both single and multi-query files)
         results = analyzer.analyze_queries(
@@ -990,6 +996,11 @@ def graph_build(
         exists=True,
         help="Path to variables file (JSON or YAML)",
     ),
+    no_star: bool = typer.Option(
+        False,
+        "--no-star",
+        help="Fail if SELECT * cannot be resolved to actual columns",
+    ),
 ) -> None:
     """
     Build a lineage graph from SQL files.
@@ -1024,6 +1035,7 @@ def graph_build(
     config = load_config()
     dialect = dialect or config.dialect or "spark"
     templater = templater or config.templater  # None means no templating
+    no_star = no_star or config.no_star or False
 
     # Validate and convert node format to enum
     try:
@@ -1080,6 +1092,7 @@ def graph_build(
             node_format=node_format_enum,
             dialect=dialect,
             sql_preprocessor=sql_preprocessor,
+            no_star=no_star,
         )
 
         # Process manifest if provided

sqlglider/graph/builder.py

@@ -33,6 +33,7 @@ class GraphBuilder:
         node_format: NodeFormat = NodeFormat.QUALIFIED,
         dialect: str = "spark",
         sql_preprocessor: Optional[SqlPreprocessor] = None,
+        no_star: bool = False,
     ):
         """
         Initialize the graph builder.
@@ -43,10 +44,12 @@ class GraphBuilder:
             sql_preprocessor: Optional function to preprocess SQL before analysis.
                              Takes (sql: str, file_path: Path) and returns processed SQL.
                              Useful for templating (e.g., Jinja2 rendering).
+            no_star: If True, fail when SELECT * cannot be resolved to columns
         """
         self.node_format = node_format
         self.dialect = dialect
         self.sql_preprocessor = sql_preprocessor
+        self.no_star = no_star
         self.graph: rx.PyDiGraph = rx.PyDiGraph()
         self._node_index_map: Dict[str, int] = {}  # identifier -> rustworkx node index
         self._source_files: Set[str] = set()
@@ -82,7 +85,9 @@ class GraphBuilder:
             if self.sql_preprocessor:
                 sql_content = self.sql_preprocessor(sql_content, file_path)
 
-            analyzer = LineageAnalyzer(sql_content, dialect=file_dialect)
+            analyzer = LineageAnalyzer(
+                sql_content, dialect=file_dialect, no_star=self.no_star
+            )
             results = analyzer.analyze_queries(level=AnalysisLevel.COLUMN)
 
             # Print warnings for any skipped queries within the file

sqlglider/lineage/analyzer.py

@@ -11,6 +11,10 @@ from sqlglot.lineage import Node, lineage
 from sqlglider.global_models import AnalysisLevel
 
 
+class StarResolutionError(Exception):
+    """Raised when SELECT * cannot be resolved and no_star mode is enabled."""
+
+
 class TableUsage(str, Enum):
     """How a table is used in a query."""
 
@@ -85,19 +89,21 @@ WarningCallback = Callable[[str], None]
 class LineageAnalyzer:
     """Analyze column and table lineage for SQL queries."""
 
-    def __init__(self, sql: str, dialect: str = "spark"):
+    def __init__(self, sql: str, dialect: str = "spark", no_star: bool = False):
         """
         Initialize the lineage analyzer.
 
         Args:
             sql: SQL query string to analyze (can contain multiple statements)
             dialect: SQL dialect (default: spark)
+            no_star: If True, fail when SELECT * cannot be resolved to columns
 
         Raises:
             ParseError: If the SQL cannot be parsed
         """
         self.sql = sql
         self.dialect = dialect
+        self._no_star = no_star
         self._skipped_queries: List[SkippedQuery] = []
         # File-scoped schema context for cross-statement lineage
         # Maps table/view names to their column definitions
@@ -171,6 +177,12 @@ class LineageAnalyzer:
                             columns.append(qualified_name)
                             self._column_mapping[qualified_name] = star_col
                     if not columns:
+                        if self._no_star:
+                            raise StarResolutionError(
+                                f"SELECT * could not be resolved to columns "
+                                f"for target table '{target_table}'. "
+                                f"Provide schema context or avoid using SELECT *."
+                            )
                         # Fallback: can't resolve *, use * as column name
                         qualified_name = f"{target_table}.*"
                         columns.append(qualified_name)
@@ -200,6 +212,12 @@ class LineageAnalyzer:
                                 columns.append(qualified_name)
                                 self._column_mapping[qualified_name] = col
                         if not qualified_star_cols:
+                            if self._no_star:
+                                raise StarResolutionError(
+                                    f"SELECT {source_table}.* could not be resolved "
+                                    f"to columns for target table '{target_table}'. "
+                                    f"Provide schema context or avoid using SELECT *."
+                                )
                             # Fallback: can't resolve t.*, use * as column name
                             qualified_name = f"{target_table}.*"
                             columns.append(qualified_name)
@@ -226,6 +244,23 @@ class LineageAnalyzer:
             # Get the first SELECT for table resolution (handles UNION case)
             first_select = self._get_first_select(select_node)
             for projection in projections:
+                # Handle SELECT * in DQL context
+                if isinstance(projection, exp.Star):
+                    if first_select:
+                        star_columns = self._resolve_star_columns(first_select)
+                        for star_col in star_columns:
+                            columns.append(star_col)
+                            self._column_mapping[star_col] = star_col
+                    if not columns:
+                        if self._no_star:
+                            raise StarResolutionError(
+                                "SELECT * could not be resolved to columns. "
+                                "Provide schema context or avoid using SELECT *."
+                            )
+                        columns.append("*")
+                        self._column_mapping["*"] = "*"
+                    continue
+
                 # Get the underlying expression (unwrap alias if present)
                 if isinstance(projection, exp.Alias):
                     source_expr = projection.this
@@ -236,6 +271,30 @@ class LineageAnalyzer:
                     column_name = None
                     lineage_name = None
 
+                # Handle table-qualified star in DQL context (e.g., t.*)
+                if isinstance(source_expr, exp.Column) and isinstance(
+                    source_expr.this, exp.Star
+                ):
+                    source_table = source_expr.table
+                    dql_star_cols: List[str] = []
+                    if source_table and first_select:
+                        dql_star_cols = self._resolve_qualified_star(
+                            source_table, first_select
+                        )
+                        for col in dql_star_cols:
+                            columns.append(col)
+                            self._column_mapping[col] = col
+                    if not dql_star_cols:
+                        if self._no_star:
+                            raise StarResolutionError(
+                                f"SELECT {source_table}.* could not be resolved "
+                                f"to columns. "
+                                f"Provide schema context or avoid using SELECT *."
+                            )
+                        columns.append("*")
+                        self._column_mapping["*"] = "*"
+                    continue
+
                 # Try to extract fully qualified name
                 if isinstance(source_expr, exp.Column):
                     # Get table and column parts
@@ -407,6 +466,8 @@ class LineageAnalyzer:
                         level=level,
                     )
                 )
+            except StarResolutionError:
+                raise
             except ValueError as e:
                 # Unsupported statement type - track it and continue
                 stmt_type = self._get_statement_type(expr)
@@ -751,7 +812,12 @@ class LineageAnalyzer:
 
         lineage_items = []
         # Get SQL for current expression only (not full multi-query SQL)
-        current_query_sql = self.expr.sql(dialect=self.dialect)
+        # For CACHE TABLE, pass just the SELECT since sqlglot.lineage doesn't
+        # natively understand CACHE statements
+        if isinstance(self.expr, exp.Cache) and self.expr.expression:
+            current_query_sql = self.expr.expression.sql(dialect=self.dialect)
+        else:
+            current_query_sql = self.expr.sql(dialect=self.dialect)
 
         for col in columns_to_analyze:
             try:

sqlglider/utils/config.py

@@ -60,6 +60,7 @@ class ConfigSettings(BaseModel):
     catalog_type: Optional[str] = None
     ddl_folder: Optional[str] = None
     catalog: Optional[CatalogConfig] = None
+    no_star: Optional[bool] = None
 
 
 def find_config_file(start_path: Optional[Path] = None) -> Optional[Path]: