sql-glider 0.1.11__py3-none-any.whl → 0.1.13__py3-none-any.whl

{sql_glider-0.1.11.dist-info → sql_glider-0.1.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.11
+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-0.1.11.dist-info → sql_glider-0.1.13.dist-info}/RECORD

@@ -1,6 +1,6 @@
 sqlglider/__init__.py,sha256=gDf7s52dMcX7JuCZ1SLawcB1vb3U0yJCohu9RQAATBY,125
-sqlglider/_version.py,sha256=0-Ruc52ECccw_8Ef0d7jMkzrb8fkobUkZLqGGvcm1ik,706
-sqlglider/cli.py,sha256=DMCMw5dxDHB2MuxBXuJMNeDSlIGAfKDz1Renp0YwGGM,52224
+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
@@ -11,13 +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=HdkMcuZkxdEFO0CXMAaqGQSyhvzuaIQTaFscQdO2GSI,12146
+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=gjJtJU-sxFokoSVxcHpcIdbP3H8GD_KQaubbbcG0UCM,68982
+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
@@ -25,10 +26,11 @@ 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=rbbiDCWA_h29vgWJZ1z3zQmGcei0KcxhTPcymSCYeFo,4796
+sqlglider/utils/config.py,sha256=qx5zE9pjLCCzHQDFVPLVd7LgJ-lghxUa2x-aZOAHByY,4962
 sqlglider/utils/file_utils.py,sha256=5_ff28E0r1R7emZzsOnRuHd-7zIX6873eyr1SuPEr4E,1093
-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/utils/schema.py,sha256=-0Vd1A3EggBH3reXTiabO0zFeTENROgmDg861X1D7Qs,1867
+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 = '0.1.11'
-__version_tuple__ = version_tuple = (0, 1, 11)
+__version__ = version = '0.1.13'
+__version_tuple__ = version_tuple = (0, 1, 13)
 
 __commit_id__ = commit_id = None

sqlglider/cli.py

@@ -12,7 +12,7 @@ from sqlglot.errors import ParseError
 from typing_extensions import Annotated
 
 from sqlglider.global_models import AnalysisLevel, NodeFormat
-from sqlglider.lineage.analyzer import LineageAnalyzer
+from sqlglider.lineage.analyzer import LineageAnalyzer, SchemaResolutionError
 from sqlglider.lineage.formatters import (
     CsvFormatter,
     JsonFormatter,
@@ -1001,6 +1001,35 @@ def graph_build(
         "--no-star",
         help="Fail if SELECT * cannot be resolved to actual columns",
     ),
+    resolve_schema: bool = typer.Option(
+        False,
+        "--resolve-schema",
+        help="Extract schema from all files before lineage analysis, "
+        "enabling cross-file star resolution",
+    ),
+    catalog_type: Optional[str] = typer.Option(
+        None,
+        "--catalog-type",
+        "-c",
+        help="Catalog provider for pulling DDL of tables not found in files "
+        "(requires --resolve-schema). E.g. 'databricks'",
+    ),
+    dump_schema: Optional[Path] = typer.Option(
+        None,
+        "--dump-schema",
+        help="Dump resolved schema to file (requires --resolve-schema)",
+    ),
+    dump_schema_format: Optional[str] = typer.Option(
+        None,
+        "--dump-schema-format",
+        help="Format for dumped schema: 'text' (default), 'json', or 'csv'",
+    ),
+    strict_schema: bool = typer.Option(
+        False,
+        "--strict-schema",
+        help="Fail if any column's table cannot be identified during schema extraction "
+        "(requires --resolve-schema)",
+    ),
 ) -> None:
     """
     Build a lineage graph from SQL files.
@@ -1036,6 +1065,37 @@ def graph_build(
     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
+    resolve_schema = resolve_schema or config.resolve_schema or False
+    strict_schema = strict_schema or config.strict_schema or False
+
+    if strict_schema and not resolve_schema:
+        err_console.print("[red]Error:[/red] --strict-schema requires --resolve-schema")
+        raise typer.Exit(1)
+
+    if catalog_type and not resolve_schema:
+        err_console.print("[red]Error:[/red] --catalog-type requires --resolve-schema")
+        raise typer.Exit(1)
+
+    # Resolve dump_schema options from config
+    dump_schema = dump_schema or (
+        Path(config.dump_schema) if config.dump_schema else None
+    )
+    dump_schema_format = dump_schema_format or config.dump_schema_format or "text"
+
+    if dump_schema and not resolve_schema:
+        err_console.print("[red]Error:[/red] --dump-schema requires --resolve-schema")
+        raise typer.Exit(1)
+
+    if dump_schema_format not in ("text", "json", "csv"):
+        err_console.print(
+            f"[red]Error:[/red] Invalid --dump-schema-format '{dump_schema_format}'. "
+            "Use 'text', 'json', or 'csv'."
+        )
+        raise typer.Exit(1)
+
+    # Only inherit catalog_type from config when resolve_schema is active
+    if resolve_schema and not catalog_type:
+        catalog_type = config.catalog_type
 
     # Validate and convert node format to enum
     try:
@@ -1088,32 +1148,75 @@ def graph_build(
         sql_preprocessor = _preprocess
 
     try:
+        # Build catalog config from config file if available
+        catalog_config_dict = None
+        if catalog_type and config.catalog:
+            provider_config = getattr(config.catalog, catalog_type, None)
+            if provider_config:
+                catalog_config_dict = provider_config.model_dump(exclude_none=True)
+
         builder = GraphBuilder(
             node_format=node_format_enum,
             dialect=dialect,
             sql_preprocessor=sql_preprocessor,
             no_star=no_star,
+            resolve_schema=resolve_schema,
+            catalog_type=catalog_type,
+            catalog_config=catalog_config_dict,
+            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)
+
+        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)
+
+        # Process path-based files
+        if path_files:
+            builder.add_files(path_files, dialect=dialect)
 
         # Build and save graph
         graph = builder.build()
@@ -1124,6 +1227,10 @@ def graph_build(
             f"({graph.metadata.total_nodes} nodes, {graph.metadata.total_edges} edges)"
         )
 
+    except SchemaResolutionError as e:
+        err_console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+
     except FileNotFoundError as e:
         err_console.print(f"[red]Error:[/red] {e}")
         raise typer.Exit(1)

sqlglider/graph/builder.py

@@ -16,8 +16,9 @@ from sqlglider.graph.models import (
     LineageGraph,
     Manifest,
 )
-from sqlglider.lineage.analyzer import LineageAnalyzer
+from sqlglider.lineage.analyzer import LineageAnalyzer, SchemaResolutionError
 from sqlglider.utils.file_utils import read_sql_file
+from sqlglider.utils.schema import parse_ddl_to_schema
 
 console = Console(stderr=True)
 
@@ -34,6 +35,10 @@ class GraphBuilder:
         dialect: str = "spark",
         sql_preprocessor: Optional[SqlPreprocessor] = None,
         no_star: bool = False,
+        resolve_schema: bool = False,
+        catalog_type: Optional[str] = None,
+        catalog_config: Optional[Dict[str, object]] = None,
+        strict_schema: bool = False,
     ):
         """
         Initialize the graph builder.
@@ -45,16 +50,31 @@ class GraphBuilder:
                              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
+            resolve_schema: If True, run a schema extraction pass across all
+                files before lineage analysis so that schema from any file is
+                available when analyzing every other file.
+            catalog_type: Optional catalog provider name (e.g. "databricks").
+                When set together with resolve_schema, DDL is pulled from the
+                catalog for tables whose schema could not be inferred from files.
+            catalog_config: Optional provider-specific configuration dict
+                passed to the catalog's configure() method.
+            strict_schema: If True, fail during schema extraction when an
+                unqualified column cannot be attributed to a table.
         """
         self.node_format = node_format
         self.dialect = dialect
         self.sql_preprocessor = sql_preprocessor
         self.no_star = no_star
+        self.resolve_schema = resolve_schema
+        self.catalog_type = catalog_type
+        self.catalog_config = catalog_config
+        self.strict_schema = strict_schema
         self.graph: rx.PyDiGraph = rx.PyDiGraph()
         self._node_index_map: Dict[str, int] = {}  # identifier -> rustworkx node index
         self._source_files: Set[str] = set()
         self._edge_set: Set[tuple] = set()  # (source, target) for dedup
         self._skipped_files: List[tuple[str, str]] = []  # (file_path, reason)
+        self._resolved_schema: Dict[str, Dict[str, str]] = {}  # accumulated schema
 
     def add_file(
         self,
@@ -86,7 +106,10 @@ class GraphBuilder:
                 sql_content = self.sql_preprocessor(sql_content, file_path)
 
             analyzer = LineageAnalyzer(
-                sql_content, dialect=file_dialect, no_star=self.no_star
+                sql_content,
+                dialect=file_dialect,
+                no_star=self.no_star,
+                schema=self._resolved_schema if self._resolved_schema else None,
             )
             results = analyzer.analyze_queries(level=AnalysisLevel.COLUMN)
 
@@ -209,23 +232,28 @@ class GraphBuilder:
             entry_dialect = entry.dialect or dialect or self.dialect
             files_with_dialects.append((file_path, entry_dialect))
 
-        # Process with progress
-        if files_with_dialects:
-            total = len(files_with_dialects)
-            with Progress(
-                TextColumn("[progress.description]{task.description}"),
-                BarColumn(),
-                TaskProgressColumn(),
-                console=console,
-                transient=False,
-            ) as progress:
-                task = progress.add_task("Parsing", total=total)
-                for i, (file_path, file_dialect) in enumerate(
-                    files_with_dialects, start=1
-                ):
-                    console.print(f"Parsing file {i}/{total}: {file_path.name}")
-                    self.add_file(file_path, file_dialect)
-                    progress.advance(task)
+        if not files_with_dialects:
+            return self
+
+        # 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.extract_schemas(file_paths_only, dialect)
+
+        total = len(files_with_dialects)
+        description = "Pass 2: Analyzing lineage" if self.resolve_schema else "Parsing"
+        with Progress(
+            TextColumn("[progress.description]{task.description}"),
+            BarColumn(),
+            TaskProgressColumn(),
+            console=console,
+            transient=False,
+        ) as progress:
+            task = progress.add_task(description, total=total)
+            for i, (file_path, file_dialect) in enumerate(files_with_dialects, start=1):
+                console.print(f"Parsing file {i}/{total}: {file_path.name}")
+                self.add_file(file_path, file_dialect)
+                progress.advance(task)
 
         return self
 
@@ -249,8 +277,15 @@ class GraphBuilder:
         if not file_paths:
             return self
 
+        # 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)
+            description = (
+                "Pass 2: Analyzing lineage" if self.resolve_schema else "Parsing"
+            )
             with Progress(
                 TextColumn("[progress.description]{task.description}"),
                 BarColumn(),
@@ -258,7 +293,7 @@ class GraphBuilder:
                 console=console,
                 transient=False,
             ) as progress:
-                task = progress.add_task("Parsing", total=total)
+                task = progress.add_task(description, total=total)
                 for i, file_path in enumerate(file_paths, start=1):
                     console.print(f"Parsing file {i}/{total}: {file_path.name}")
                     self.add_file(file_path, dialect)
@@ -268,6 +303,157 @@ 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],
+        dialect: Optional[str] = None,
+    ) -> Dict[str, Dict[str, str]]:
+        """Run schema extraction pass across all files.
+
+        Parses each file and extracts schema from CREATE TABLE/VIEW
+        statements without performing lineage analysis.
+
+        Args:
+            file_paths: SQL files to extract schema from
+            dialect: SQL dialect override
+
+        Returns:
+            Accumulated schema dict from all files
+        """
+        schema: Dict[str, Dict[str, str]] = {}
+        total = len(file_paths)
+        with Progress(
+            TextColumn("[progress.description]{task.description}"),
+            BarColumn(),
+            TaskProgressColumn(),
+            console=console,
+            transient=False,
+        ) as progress:
+            task = progress.add_task("Pass 1: Extracting schema", total=total)
+            for i, file_path in enumerate(file_paths, start=1):
+                console.print(f"Extracting schema {i}/{total}: {file_path.name}")
+                file_dialect = dialect or self.dialect
+                try:
+                    sql_content = read_sql_file(file_path)
+                    if self.sql_preprocessor:
+                        sql_content = self.sql_preprocessor(sql_content, file_path)
+                    analyzer = LineageAnalyzer(
+                        sql_content,
+                        dialect=file_dialect,
+                        schema=schema,
+                        strict_schema=self.strict_schema,
+                    )
+                    file_schema = analyzer.extract_schema_only()
+                    schema.update(file_schema)
+                except SchemaResolutionError:
+                    raise
+                except Exception:
+                    # Schema extraction failures are non-fatal; the file
+                    # will be reported during the lineage pass if it also fails.
+                    pass
+                progress.advance(task)
+        return schema
+
+    def _fill_schema_from_catalog(
+        self,
+        schema: Dict[str, Dict[str, str]],
+        file_paths: List[Path],
+        dialect: Optional[str] = None,
+    ) -> Dict[str, Dict[str, str]]:
+        """Pull DDL from catalog for tables not yet in schema.
+
+        Extracts all table names referenced across the files, identifies
+        those missing from the schema, and fetches their DDL from the
+        configured catalog provider.
+
+        Args:
+            schema: Schema dict already populated from file extraction
+            file_paths: SQL files to scan for table references
+            dialect: SQL dialect override
+
+        Returns:
+            Updated schema dict with catalog-sourced entries added
+        """
+        from sqlglider.catalog import get_catalog
+
+        catalog = get_catalog(self.catalog_type)  # type: ignore[arg-type]
+        if self.catalog_config:
+            catalog.configure(self.catalog_config)
+
+        # Collect all referenced table names across files
+        all_tables: Set[str] = set()
+        for file_path in file_paths:
+            file_dialect = dialect or self.dialect
+            try:
+                sql_content = read_sql_file(file_path)
+                if self.sql_preprocessor:
+                    sql_content = self.sql_preprocessor(sql_content, file_path)
+                analyzer = LineageAnalyzer(sql_content, dialect=file_dialect)
+                tables_results = analyzer.analyze_tables()
+                for result in tables_results:
+                    for table_info in result.tables:
+                        # Skip CTEs — they don't exist in catalogs
+                        from sqlglider.lineage.analyzer import ObjectType
+
+                        if table_info.object_type != ObjectType.CTE:
+                            all_tables.add(table_info.name)
+            except Exception:
+                pass
+
+        # Find tables missing from schema
+        missing = [t for t in all_tables if t not in schema]
+        if not missing:
+            return schema
+
+        console.print(
+            f"[blue]Pulling DDL from {self.catalog_type} "
+            f"for {len(missing)} table(s)...[/blue]"
+        )
+
+        ddl_results = catalog.get_ddl_batch(missing)
+        file_dialect = dialect or self.dialect
+        for table_name, ddl in ddl_results.items():
+            if ddl.startswith("ERROR:"):
+                console.print(
+                    f"[yellow]Warning:[/yellow] Could not pull DDL "
+                    f"for {table_name}: {ddl}"
+                )
+                continue
+            parsed_schema = parse_ddl_to_schema(ddl, dialect=file_dialect)
+            for name, cols in parsed_schema.items():
+                if name not in schema:
+                    schema[name] = cols
+
+        return schema
+
     def _ensure_node(
         self,
         identifier: str,
@@ -348,6 +534,11 @@ class GraphBuilder:
         """Get mapping from node identifiers to rustworkx indices."""
         return self._node_index_map.copy()
 
+    @property
+    def resolved_schema(self) -> Dict[str, Dict[str, str]]:
+        """Get the resolved schema dictionary from schema extraction pass."""
+        return self._resolved_schema.copy()
+
     @property
     def skipped_files(self) -> List[tuple[str, str]]:
         """Get list of files that were skipped during graph building."""

sqlglider/graph/formatters.py

@@ -0,0 +1,98 @@
+"""Output formatters for resolved schema data."""
+
+import csv
+import json
+from io import StringIO
+from typing import Dict
+
+SchemaDict = Dict[str, Dict[str, str]]
+
+
+def format_schema_text(schema: SchemaDict) -> str:
+    """Format resolved schema as human-readable text.
+
+    Output format:
+        customers
+          id
+          name
+
+        schema.orders
+          order_id
+          customer_id
+
+    Args:
+        schema: Resolved schema dictionary mapping table names to column dicts.
+
+    Returns:
+        Text-formatted string.
+    """
+    lines: list[str] = []
+    for table_name in sorted(schema):
+        if lines:
+            lines.append("")
+        lines.append(table_name)
+        for column_name in sorted(schema[table_name]):
+            lines.append(f"  {column_name}")
+    return "\n".join(lines) + "\n" if lines else ""
+
+
+def format_schema_json(schema: SchemaDict) -> str:
+    """Format resolved schema as JSON.
+
+    Args:
+        schema: Resolved schema dictionary mapping table names to column dicts.
+
+    Returns:
+        JSON-formatted string.
+    """
+    sorted_schema = {k: schema[k] for k in sorted(schema)}
+    return json.dumps(sorted_schema, indent=2)
+
+
+def format_schema_csv(schema: SchemaDict) -> str:
+    """Format resolved schema as CSV.
+
+    Output format:
+        table,column,type
+        customers,id,UNKNOWN
+        customers,name,UNKNOWN
+
+    Args:
+        schema: Resolved schema dictionary mapping table names to column dicts.
+
+    Returns:
+        CSV-formatted string.
+    """
+    output = StringIO()
+    writer = csv.writer(output)
+    writer.writerow(["table", "column", "type"])
+    for table_name in sorted(schema):
+        for column_name in sorted(schema[table_name]):
+            writer.writerow([table_name, column_name, schema[table_name][column_name]])
+    return output.getvalue()
+
+
+def format_schema(schema: SchemaDict, output_format: str = "text") -> str:
+    """Format resolved schema in the specified format.
+
+    Args:
+        schema: Resolved schema dictionary.
+        output_format: One of "text", "json", or "csv".
+
+    Returns:
+        Formatted string.
+
+    Raises:
+        ValueError: If output_format is not recognized.
+    """
+    formatters = {
+        "text": format_schema_text,
+        "json": format_schema_json,
+        "csv": format_schema_csv,
+    }
+    formatter = formatters.get(output_format)
+    if formatter is None:
+        raise ValueError(
+            f"Invalid schema format '{output_format}'. Use 'text', 'json', or 'csv'."
+        )
+    return formatter(schema)

sqlglider/lineage/analyzer.py

@@ -15,6 +15,10 @@ class StarResolutionError(Exception):
     """Raised when SELECT * cannot be resolved and no_star mode is enabled."""
 
 
+class SchemaResolutionError(Exception):
+    """Raised when a column's table cannot be identified and strict_schema is enabled."""
+
+
 class TableUsage(str, Enum):
     """How a table is used in a query."""
 
@@ -89,7 +93,14 @@ WarningCallback = Callable[[str], None]
 class LineageAnalyzer:
     """Analyze column and table lineage for SQL queries."""
 
-    def __init__(self, sql: str, dialect: str = "spark", no_star: bool = False):
+    def __init__(
+        self,
+        sql: str,
+        dialect: str = "spark",
+        no_star: bool = False,
+        schema: Optional[Dict[str, Dict[str, str]]] = None,
+        strict_schema: bool = False,
+    ):
         """
         Initialize the lineage analyzer.
 
@@ -97,6 +108,12 @@ class LineageAnalyzer:
             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
+            schema: Optional external schema mapping table names to column
+                definitions (e.g. {"table": {"col": "UNKNOWN"}}). File-derived
+                schema from CREATE statements will merge on top.
+            strict_schema: If True, fail during schema extraction when an
+                unqualified column cannot be attributed to a table (e.g.
+                in a multi-table SELECT without table qualifiers).
 
         Raises:
             ParseError: If the SQL cannot be parsed
@@ -104,10 +121,12 @@ class LineageAnalyzer:
         self.sql = sql
         self.dialect = dialect
         self._no_star = no_star
+        self._strict_schema = strict_schema
         self._skipped_queries: List[SkippedQuery] = []
         # File-scoped schema context for cross-statement lineage
         # Maps table/view names to their column definitions
-        self._file_schema: Dict[str, Dict[str, str]] = {}
+        self._initial_schema: Dict[str, Dict[str, str]] = dict(schema) if schema else {}
+        self._file_schema: Dict[str, Dict[str, str]] = dict(self._initial_schema)
 
         try:
             # Parse all statements in the SQL string
@@ -132,6 +151,27 @@ class LineageAnalyzer:
         """Get list of queries that were skipped during analysis."""
         return self._skipped_queries.copy()
 
+    def get_extracted_schema(self) -> Dict[str, Dict[str, str]]:
+        """Return the accumulated file schema after analysis."""
+        return dict(self._file_schema)
+
+    def extract_schema_only(self) -> Dict[str, Dict[str, str]]:
+        """Parse all statements and extract schema without running lineage.
+
+        Iterates through all expressions, extracting schema from:
+        1. CREATE TABLE/VIEW AS SELECT statements (existing behavior)
+        2. DQL statements by inferring table columns from qualified column
+           references (e.g., ``SELECT t.id FROM table t`` infers
+           ``table: {id: UNKNOWN}``)
+
+        Returns the accumulated schema dict.
+        """
+        self._file_schema = dict(self._initial_schema)
+        for expr in self.expressions:
+            self._extract_schema_from_statement(expr)
+            self._extract_schema_from_dql(expr)
+        return dict(self._file_schema)
+
     def get_output_columns(self) -> List[str]:
         """
         Extract all output column names from the query with full qualification.
@@ -426,7 +466,7 @@ class LineageAnalyzer:
         """
         results = []
         self._skipped_queries = []  # Reset skipped queries for this analysis
-        self._file_schema = {}  # Reset file schema for this analysis run
+        self._file_schema = dict(self._initial_schema)  # Reset to external schema
 
         for query_index, expr, preview in self._iterate_queries(table_filter):
             # Temporarily swap self.expr to analyze this query
@@ -819,18 +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
@@ -1427,6 +1480,119 @@ class LineageAnalyzer:
             # Store with UNKNOWN type - SQLGlot only needs column names for expansion
             self._file_schema[target_name] = {col: "UNKNOWN" for col in columns}
 
+    def _extract_schema_from_dql(self, expr: exp.Expression) -> None:
+        """Infer table schemas from column references in DQL.
+
+        Walks SELECT statements and extracts table-column mappings from:
+        1. Qualified column references (e.g., ``c.id``) — always resolved.
+        2. Unqualified column references (e.g., ``id``) — only when the
+           SELECT has exactly one real table source (no joins), making
+           attribution unambiguous.
+
+        Aliases are resolved back to actual table names.  CTEs and subquery
+        aliases are skipped since they don't represent external tables.
+
+        Args:
+            expr: The SQL expression to extract schema from.
+        """
+        # Find all SELECT nodes in the expression tree
+        selects = list(expr.find_all(exp.Select))
+        if not selects:
+            return
+
+        for select_node in selects:
+            # Build alias-to-table mapping for this SELECT scope
+            alias_map: Dict[str, str] = {}
+            cte_names: Set[str] = set()
+
+            # Collect CTE names so we can skip them
+            parent = select_node
+            while parent:
+                with_clause = parent.args.get("with")
+                if with_clause:
+                    for cte in with_clause.expressions:
+                        if isinstance(cte, exp.CTE) and cte.alias:
+                            cte_names.add(cte.alias.lower())
+                parent = parent.parent if hasattr(parent, "parent") else None
+
+            # Collect subquery aliases so we can skip them too
+            subquery_aliases: Set[str] = set()
+            from_clause = select_node.args.get("from")
+            if from_clause and isinstance(from_clause, exp.From):
+                source = from_clause.this
+                if isinstance(source, exp.Subquery) and source.alias:
+                    subquery_aliases.add(source.alias.lower())
+            for join in select_node.find_all(exp.Join):
+                if isinstance(join.this, exp.Subquery) and join.this.alias:
+                    subquery_aliases.add(join.this.alias.lower())
+
+            # Build alias map from FROM/JOIN table references
+            real_tables: list[str] = []  # track non-CTE, non-subquery tables
+            for table_ref in select_node.find_all(exp.Table):
+                # Skip tables inside nested selects — they belong to inner scope
+                if table_ref.find_ancestor(exp.Select) is not select_node:
+                    continue
+                qualified = self._get_qualified_table_name(table_ref)
+                if table_ref.alias:
+                    alias_map[table_ref.alias.lower()] = qualified
+                else:
+                    alias_map[table_ref.name.lower()] = qualified
+                # Track real tables (not CTEs or subqueries)
+                if (
+                    qualified.lower() not in cte_names
+                    and qualified.lower() not in subquery_aliases
+                ):
+                    real_tables.append(qualified)
+
+            # Determine single-table target for unqualified columns
+            # Only set when exactly one real table source exists (unambiguous)
+            single_table: Optional[str] = (
+                real_tables[0] if len(real_tables) == 1 else None
+            )
+
+            # Walk all column references in this SELECT
+            for column in select_node.find_all(exp.Column):
+                if isinstance(column.this, exp.Star):
+                    continue
+
+                table_ref_name = column.table
+                col_name = column.name
+
+                if table_ref_name:
+                    # Qualified column — resolve alias to actual table
+                    ref_lower = table_ref_name.lower()
+
+                    # Skip CTE and subquery references
+                    if ref_lower in cte_names or ref_lower in subquery_aliases:
+                        continue
+
+                    actual_table = alias_map.get(ref_lower)
+                    if not actual_table:
+                        continue
+
+                    # Skip if it resolved to a CTE or subquery
+                    if (
+                        actual_table.lower() in cte_names
+                        or actual_table.lower() in subquery_aliases
+                    ):
+                        continue
+                else:
+                    # Unqualified column — attribute to single table if unambiguous
+                    if not single_table:
+                        if self._strict_schema:
+                            preview = select_node.sql(dialect=self.dialect)[:80]
+                            raise SchemaResolutionError(
+                                f"Cannot resolve table for unqualified column "
+                                f"'{col_name}' in multi-table query: {preview}"
+                            )
+                        continue
+                    actual_table = single_table
+
+                if actual_table not in self._file_schema:
+                    self._file_schema[actual_table] = {}
+                if col_name not in self._file_schema[actual_table]:
+                    self._file_schema[actual_table][col_name] = "UNKNOWN"
+
     def _extract_columns_from_select(
         self, select_node: Union[exp.Select, exp.Union, exp.Intersect, exp.Except]
     ) -> List[str]:

sqlglider/utils/config.py

@@ -61,6 +61,10 @@ class ConfigSettings(BaseModel):
     ddl_folder: Optional[str] = None
     catalog: Optional[CatalogConfig] = None
     no_star: Optional[bool] = None
+    resolve_schema: Optional[bool] = None
+    dump_schema: Optional[str] = None
+    dump_schema_format: Optional[str] = None
+    strict_schema: Optional[bool] = None
 
 
 def find_config_file(start_path: Optional[Path] = None) -> Optional[Path]:

sqlglider/utils/schema.py

@@ -0,0 +1,62 @@
+"""Schema utilities for parsing DDL into schema dictionaries."""
+
+from typing import Dict
+
+from sqlglot import exp, parse
+
+
+def parse_ddl_to_schema(ddl: str, dialect: str = "spark") -> Dict[str, Dict[str, str]]:
+    """Extract table schemas from DDL statements.
+
+    Parses CREATE TABLE/VIEW statements and extracts column names.
+    Only column names are needed — types are stored as "UNKNOWN" since
+    SQLGlot's lineage only uses names for star expansion.
+
+    Args:
+        ddl: SQL string containing one or more CREATE TABLE/VIEW statements
+        dialect: SQL dialect for parsing
+
+    Returns:
+        Schema dict mapping table names to column definitions,
+        e.g. {"my_table": {"id": "UNKNOWN", "name": "UNKNOWN"}}
+    """
+    schema: Dict[str, Dict[str, str]] = {}
+    expressions = parse(ddl, dialect=dialect)
+
+    for expr in expressions:
+        if expr is None:
+            continue
+        if not isinstance(expr, (exp.Create,)):
+            continue
+
+        # Get target table name
+        target = expr.this
+        if isinstance(target, exp.Schema):
+            # Schema node wraps the table and column definitions
+            columns = [
+                col.name for col in target.expressions if isinstance(col, exp.ColumnDef)
+            ]
+            target = target.this
+        else:
+            columns = []
+
+        if not isinstance(target, exp.Table):
+            continue
+
+        table_name = _get_qualified_name(target)
+
+        if columns:
+            schema[table_name] = {col: "UNKNOWN" for col in columns}
+
+    return schema
+
+
+def _get_qualified_name(table: exp.Table) -> str:
+    """Build a qualified table name from a SQLGlot Table expression."""
+    parts = []
+    if table.catalog:
+        parts.append(table.catalog)
+    if table.db:
+        parts.append(table.db)
+    parts.append(table.name)
+    return ".".join(parts)