sql-glider 0.1.12__py3-none-any.whl → 0.1.13__py3-none-any.whl

{sql_glider-0.1.12.dist-info → sql_glider-0.1.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.12
+Version: 0.1.13
 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-0.1.12.dist-info → sql_glider-0.1.13.dist-info}/RECORD

@@ -1,6 +1,6 @@
 sqlglider/__init__.py,sha256=gDf7s52dMcX7JuCZ1SLawcB1vb3U0yJCohu9RQAATBY,125
-sqlglider/_version.py,sha256=cEPXLUpTV7EzqolnyXW8nf8Hr6IVyBji9CzB6Cq_Ar0,706
-sqlglider/cli.py,sha256=qEDLZ1a6yr-BzrtkBsJEHPByMmRERsGKZsYFTn9kaMY,55624
+sqlglider/_version.py,sha256=Xz5RLbyPcCHHXte393JYfUy4Dt7uaeWyrGVw9SmJ0eg,706
+sqlglider/cli.py,sha256=FDTjRmor_cQlcwfiD_uHTrQao2sMf3ev21IUyUSt7Qs,56401
 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
@@ -11,14 +11,14 @@ 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=o0SnH5eWUUPpzRSdsdCXEva3QTlhLDagJulJ2hRFQqA,19895
+sqlglider/graph/builder.py,sha256=suxc_hymHvHnkgltgXqwwIoxlay7zhy1Enbs6HNC3m8,20107
 sqlglider/graph/formatters.py,sha256=EGgdxTr9Mctz9tTN54XIjoX0KGNcpiSKsW3o27dhMxo,2549
 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=-LUeVNEsjfEWoKAJ2qVIiJO1noqwae4jQkwkkkVbAT8,75950
+sqlglider/lineage/analyzer.py,sha256=08pFR5aGFFPhSbRW6EqiX2d3mp91v-orcs6dm_T1FJg,76484
 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
@@ -29,8 +29,8 @@ sqlglider/utils/__init__.py,sha256=KGp9-UzKz_OFBOTFoSy-g-NXDZsvyWXG_9-1zcC6ePE,2
 sqlglider/utils/config.py,sha256=qx5zE9pjLCCzHQDFVPLVd7LgJ-lghxUa2x-aZOAHByY,4962
 sqlglider/utils/file_utils.py,sha256=5_ff28E0r1R7emZzsOnRuHd-7zIX6873eyr1SuPEr4E,1093
 sqlglider/utils/schema.py,sha256=-0Vd1A3EggBH3reXTiabO0zFeTENROgmDg861X1D7Qs,1867
-sql_glider-0.1.12.dist-info/METADATA,sha256=73yuoWaAE5DKE9wobDXxbERSP2Pq-WpdqCnaswAa9fQ,28446
-sql_glider-0.1.12.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-sql_glider-0.1.12.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
-sql_glider-0.1.12.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sql_glider-0.1.12.dist-info/RECORD,,
+sql_glider-0.1.13.dist-info/METADATA,sha256=z-utivkULH1BBhygNpLcWN9UdU1DbwfF3EzUhGtWXes,28446
+sql_glider-0.1.13.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+sql_glider-0.1.13.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
+sql_glider-0.1.13.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sql_glider-0.1.13.dist-info/RECORD,,

sqlglider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.12'
-__version_tuple__ = version_tuple = (0, 1, 12)
+__version__ = version = '0.1.13'
+__version_tuple__ = version_tuple = (0, 1, 13)
 
 __commit_id__ = commit_id = None

sqlglider/cli.py

@@ -1166,36 +1166,57 @@ def graph_build(
             strict_schema=strict_schema,
         )
 
-        # Process manifest if provided
-        if manifest:
-            builder.add_manifest(manifest, dialect=dialect)
-
-        # Process paths - collect all files first for progress tracking
+        # Collect file paths for schema extraction
+        path_files: list[Path] = []
         if paths:
-            all_files: list[Path] = []
             for path in paths:
                 if path.is_dir():
                     pattern = f"**/{glob_pattern}" if recursive else glob_pattern
-                    all_files.extend(
+                    path_files.extend(
                         f for f in sorted(path.glob(pattern)) if f.is_file()
                     )
                 elif path.is_file():
-                    all_files.append(path)
+                    path_files.append(path)
                 else:
                     err_console.print(f"[red]Error:[/red] Path not found: {path}")
                     raise typer.Exit(1)
-            builder.add_files(all_files, dialect=dialect)
 
-        # Dump resolved schema if requested
-        if dump_schema:
-            from sqlglider.graph.formatters import format_schema
+        manifest_files: list[Path] = []
+        if manifest:
+            from sqlglider.graph.models import Manifest
+
+            manifest_data = Manifest.from_csv(manifest)
+            base_dir = manifest.parent
+            for entry in manifest_data.entries:
+                file_path = Path(entry.file_path)
+                if not file_path.is_absolute():
+                    file_path = (base_dir / entry.file_path).resolve()
+                manifest_files.append(file_path)
+
+        # Extract schema upfront if requested, then dump before graph building
+        all_files = manifest_files + path_files
+        if resolve_schema and all_files:
+            builder.extract_schemas(all_files, dialect=dialect)
+
+            if dump_schema:
+                from sqlglider.graph.formatters import format_schema
+
+                schema_content = format_schema(
+                    builder.resolved_schema, dump_schema_format
+                )
+                dump_schema.write_text(schema_content, encoding="utf-8")
+                console.print(
+                    f"[green]Schema dumped to {dump_schema} "
+                    f"({len(builder.resolved_schema)} table(s))[/green]"
+                )
+
+        # Process manifest if provided
+        if manifest:
+            builder.add_manifest(manifest, dialect=dialect)
 
-            schema_content = format_schema(builder.resolved_schema, dump_schema_format)
-            dump_schema.write_text(schema_content, encoding="utf-8")
-            console.print(
-                f"[green]Schema dumped to {dump_schema} "
-                f"({len(builder.resolved_schema)} table(s))[/green]"
-            )
+        # Process path-based files
+        if path_files:
+            builder.add_files(path_files, dialect=dialect)
 
         # Build and save graph
         graph = builder.build()

sqlglider/graph/builder.py

@@ -235,19 +235,10 @@ class GraphBuilder:
         if not files_with_dialects:
             return self
 
-        # Two-pass schema resolution
-        if self.resolve_schema:
-            console.print("[blue]Pass 1: Extracting schema from files[/blue]")
+        # Two-pass schema resolution (skip if already resolved)
+        if self.resolve_schema and not self._resolved_schema:
             file_paths_only = [fp for fp, _ in files_with_dialects]
-            self._resolved_schema = self._extract_schemas(file_paths_only, dialect)
-            if self.catalog_type:
-                self._resolved_schema = self._fill_schema_from_catalog(
-                    self._resolved_schema, file_paths_only, dialect
-                )
-            console.print(
-                f"[blue]Schema resolved for "
-                f"{len(self._resolved_schema)} table(s)[/blue]"
-            )
+            self.extract_schemas(file_paths_only, dialect)
 
         total = len(files_with_dialects)
         description = "Pass 2: Analyzing lineage" if self.resolve_schema else "Parsing"
@@ -286,18 +277,9 @@ class GraphBuilder:
         if not file_paths:
             return self
 
-        # Two-pass schema resolution: extract schema from all files first
-        if self.resolve_schema:
-            console.print("[blue]Pass 1: Extracting schema from files[/blue]")
-            self._resolved_schema = self._extract_schemas(file_paths, dialect)
-            if self.catalog_type:
-                self._resolved_schema = self._fill_schema_from_catalog(
-                    self._resolved_schema, file_paths, dialect
-                )
-            console.print(
-                f"[blue]Schema resolved for "
-                f"{len(self._resolved_schema)} table(s)[/blue]"
-            )
+        # Two-pass schema resolution (skip if already resolved)
+        if self.resolve_schema and not self._resolved_schema:
+            self.extract_schemas(file_paths, dialect)
 
         if show_progress:
             total = len(file_paths)
@@ -321,6 +303,34 @@ class GraphBuilder:
                 self.add_file(file_path, dialect)
         return self
 
+    def extract_schemas(
+        self,
+        file_paths: List[Path],
+        dialect: Optional[str] = None,
+    ) -> Dict[str, Dict[str, str]]:
+        """Run schema extraction pass and optionally fill from catalog.
+
+        Call this before add_files/add_manifest to resolve schema upfront.
+        The resolved schema is stored internally and also returned.
+
+        Args:
+            file_paths: SQL files to extract schema from
+            dialect: SQL dialect override
+
+        Returns:
+            Resolved schema dict
+        """
+        console.print("[blue]Pass 1: Extracting schema from files[/blue]")
+        self._resolved_schema = self._extract_schemas(file_paths, dialect)
+        if self.catalog_type:
+            self._resolved_schema = self._fill_schema_from_catalog(
+                self._resolved_schema, file_paths, dialect
+            )
+        console.print(
+            f"[blue]Schema resolved for {len(self._resolved_schema)} table(s)[/blue]"
+        )
+        return self._resolved_schema.copy()
+
     def _extract_schemas(
         self,
         file_paths: List[Path],

sqlglider/lineage/analyzer.py

@@ -859,18 +859,31 @@ class LineageAnalyzer:
         else:
             current_query_sql = self.expr.sql(dialect=self.dialect)
 
+        # Prune schema to only tables referenced in this query to avoid
+        # sqlglot.lineage() performance degradation with large schema dicts
+        pruned_schema: Optional[Dict[str, Dict[str, str]]] = None
+        if self._file_schema:
+            referenced = {t.lower() for t in self._get_query_tables()}
+            pruned_schema = {
+                table: cols
+                for table, cols in self._file_schema.items()
+                if table.lower() in referenced
+            }
+            if not pruned_schema:
+                pruned_schema = None
+
         for col in columns_to_analyze:
             try:
                 # Get the column name that lineage expects
                 lineage_col = self._column_mapping.get(col, col)
 
                 # Get lineage tree for this column using current query SQL only
-                # Pass file schema to enable SELECT * expansion for known tables/views
+                # Pass pruned schema to enable SELECT * expansion for known tables/views
                 node = lineage(
                     lineage_col,
                     current_query_sql,
                     dialect=self.dialect,
-                    schema=self._file_schema if self._file_schema else None,
+                    schema=pruned_schema,
                 )
 
                 # Collect all source columns