sql-glider 0.1.14__py3-none-any.whl → 0.1.15__py3-none-any.whl

{sql_glider-0.1.14.dist-info → sql_glider-0.1.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.14
+Version: 0.1.15
 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-0.1.14.dist-info → sql_glider-0.1.15.dist-info}/RECORD

@@ -1,6 +1,6 @@
 sqlglider/__init__.py,sha256=gDf7s52dMcX7JuCZ1SLawcB1vb3U0yJCohu9RQAATBY,125
-sqlglider/_version.py,sha256=1asLxKIxr0ym19WewGl0URtkfnEuN7mK8ZckB9dZw6Q,706
-sqlglider/cli.py,sha256=UvDaeDhQRu98M1PaUtWsIL_F_LtulOf58kWGn6SxUzE,64175
+sqlglider/_version.py,sha256=HPqQHR9pVxIxlFt4vovkyoe7k6UO3ag2isBN2lHFL8g,706
+sqlglider/cli.py,sha256=9zNMaw3rgcqb6uG05VJTYbLUXmZzdX87gAOJ4Zg3xjY,65319
 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
@@ -11,8 +11,8 @@ 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=fS6p-73zyjuYIHRzM3uXFTFZ8zyal0s7oBdyO2Fv8vQ,15224
-sqlglider/graph/formatters.py,sha256=EGgdxTr9Mctz9tTN54XIjoX0KGNcpiSKsW3o27dhMxo,2549
+sqlglider/graph/builder.py,sha256=VNBdsDlkiaId3JGvr2G4h6OIFek_9zPsGMIYL9GpJlk,15796
+sqlglider/graph/formatters.py,sha256=p85-WN9oPmEETsAtWSo1sIQELF36w85QoFEJyfBZGoM,4800
 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
@@ -21,7 +21,7 @@ sqlglider/lineage/__init__.py,sha256=llXMeI5_PIZaiBo8tKk3-wOubF4m_6QBHbn1FtWxT7k
 sqlglider/lineage/analyzer.py,sha256=08pFR5aGFFPhSbRW6EqiX2d3mp91v-orcs6dm_T1FJg,76484
 sqlglider/lineage/formatters.py,sha256=_Y9wcTX4JXn1vVnZ1xI656g1FF2rMjcAVc-GHjbd9QA,10389
 sqlglider/schema/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sqlglider/schema/extractor.py,sha256=iOi13ZStR4ngC2GkZGXjB0lsgmDqJ-OYwTRgH72hy1w,7082
+sqlglider/schema/extractor.py,sha256=WW31wbHkL-V749pLb7EAyUOJuziZQK-5hLZVW6f970U,7234
 sqlglider/templating/__init__.py,sha256=g3_wb6rSDI0usq2UUMDpn-J5kVwlAw3NtLdwbxL6UHs,1435
 sqlglider/templating/base.py,sha256=y5bWAW7qXl_4pPyo5KycfHwNVvt1-7slZ63DAsvTE1s,2902
 sqlglider/templating/jinja.py,sha256=o01UG72N4G1-tOT5LKK1Wkccv4nJH2VN4VFaMi5c1-g,5220
@@ -31,8 +31,8 @@ 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-0.1.14.dist-info/METADATA,sha256=SdedCDEPwWR2Kqrg8_mMgb0PNmNZj0OExHiapyKZ63A,28446
-sql_glider-0.1.14.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-sql_glider-0.1.14.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
-sql_glider-0.1.14.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sql_glider-0.1.14.dist-info/RECORD,,
+sql_glider-0.1.15.dist-info/METADATA,sha256=IF0dZD6rOriyausbDZhHPMfYnhHyRlxyi9v_ihTgCUo,28446
+sql_glider-0.1.15.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+sql_glider-0.1.15.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
+sql_glider-0.1.15.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sql_glider-0.1.15.dist-info/RECORD,,

sqlglider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.14'
-__version_tuple__ = version_tuple = (0, 1, 14)
+__version__ = version = '0.1.15'
+__version_tuple__ = version_tuple = (0, 1, 15)
 
 __commit_id__ = commit_id = None

sqlglider/cli.py

@@ -171,6 +171,12 @@ def lineage(
         "--no-star",
         help="Fail if SELECT * cannot be resolved to actual columns",
     ),
+    provide_schema: Optional[Path] = typer.Option(
+        None,
+        "--provide-schema",
+        exists=True,
+        help="Path to a schema file (JSON, CSV, or text) for star resolution",
+    ),
 ) -> None:
     """
     Analyze column or table lineage for a SQL file.
@@ -266,8 +272,15 @@ def lineage(
             source_path=source_path,
         )
 
+        # Load provided schema if specified
+        schema = None
+        if provide_schema:
+            from sqlglider.graph.formatters import load_schema_file
+
+            schema = load_schema_file(provide_schema)
+
         # Create analyzer
-        analyzer = LineageAnalyzer(sql, dialect=dialect, no_star=no_star)
+        analyzer = LineageAnalyzer(sql, dialect=dialect, no_star=no_star, schema=schema)
 
         # Unified lineage analysis (handles both single and multi-query files)
         results = analyzer.analyze_queries(
@@ -1292,6 +1305,13 @@ def graph_build(
         "--dump-schema-format",
         help="Format for dumped schema: 'text' (default), 'json', or 'csv'",
     ),
+    provide_schema: Optional[Path] = typer.Option(
+        None,
+        "--provide-schema",
+        exists=True,
+        help="Path to a schema file (JSON, CSV, or text) to use for star resolution. "
+        "Can be combined with --resolve-schema to merge file-extracted schema on top.",
+    ),
     strict_schema: bool = typer.Option(
         False,
         "--strict-schema",
@@ -1434,6 +1454,17 @@ def graph_build(
             strict_schema=strict_schema,
         )
 
+        # Load provided schema file if specified
+        if provide_schema:
+            from sqlglider.graph.formatters import load_schema_file
+
+            loaded_schema = load_schema_file(provide_schema)
+            builder.set_schema(loaded_schema)
+            console.print(
+                f"[green]Loaded schema from {provide_schema} "
+                f"({len(loaded_schema)} table(s))[/green]"
+            )
+
         # Collect file paths for schema extraction
         manifest_files, path_files = _collect_sql_files(
             paths, manifest, recursive, glob_pattern

sqlglider/graph/builder.py

@@ -303,6 +303,21 @@ class GraphBuilder:
                 self.add_file(file_path, dialect)
         return self
 
+    def set_schema(self, schema: Dict[str, Dict[str, str]]) -> "GraphBuilder":
+        """Pre-seed the resolved schema from an external source.
+
+        This allows skipping the schema extraction pass when the schema
+        is already known (e.g., loaded from a file).
+
+        Args:
+            schema: Schema dictionary mapping table names to column dicts.
+
+        Returns:
+            self for method chaining
+        """
+        self._resolved_schema = schema
+        return self
+
     def extract_schemas(
         self,
         file_paths: List[Path],
@@ -325,6 +340,7 @@ class GraphBuilder:
             file_paths,
             dialect=file_dialect,
             sql_preprocessor=self.sql_preprocessor,
+            initial_schema=self._resolved_schema if self._resolved_schema else None,
             strict_schema=self.strict_schema,
             catalog_type=self.catalog_type,
             catalog_config=self.catalog_config,

sqlglider/graph/formatters.py

@@ -1,8 +1,9 @@
-"""Output formatters for resolved schema data."""
+"""Output formatters and parsers for resolved schema data."""
 
 import csv
 import json
 from io import StringIO
+from pathlib import Path
 from typing import Dict
 
 SchemaDict = Dict[str, Dict[str, str]]
@@ -96,3 +97,93 @@ def format_schema(schema: SchemaDict, output_format: str = "text") -> str:
             f"Invalid schema format '{output_format}'. Use 'text', 'json', or 'csv'."
         )
     return formatter(schema)
+
+
+def parse_schema_json(content: str) -> SchemaDict:
+    """Parse schema from JSON format.
+
+    Args:
+        content: JSON string with table -> {column -> type} structure.
+
+    Returns:
+        Parsed schema dictionary.
+    """
+    return json.loads(content)  # type: ignore[no-any-return]
+
+
+def parse_schema_csv(content: str) -> SchemaDict:
+    """Parse schema from CSV format.
+
+    Expects columns: table, column, type.
+
+    Args:
+        content: CSV string with header row.
+
+    Returns:
+        Parsed schema dictionary.
+    """
+    schema: SchemaDict = {}
+    reader = csv.DictReader(StringIO(content))
+    for row in reader:
+        table = row["table"]
+        column = row["column"]
+        col_type = row.get("type", "UNKNOWN")
+        if table not in schema:
+            schema[table] = {}
+        schema[table][column] = col_type
+    return schema
+
+
+def parse_schema_text(content: str) -> SchemaDict:
+    """Parse schema from indented text format.
+
+    Expected format:
+        table_name
+          column1
+          column2
+
+        other_table
+          col_a
+
+    Args:
+        content: Text-formatted schema string.
+
+    Returns:
+        Parsed schema dictionary.
+    """
+    schema: SchemaDict = {}
+    current_table: str | None = None
+    for line in content.splitlines():
+        if not line or not line.strip():
+            continue
+        if line.startswith("  "):
+            if current_table is not None:
+                schema[current_table][line.strip()] = "UNKNOWN"
+        else:
+            current_table = line.strip()
+            schema[current_table] = {}
+    return schema
+
+
+def load_schema_file(path: Path) -> SchemaDict:
+    """Load a schema file, auto-detecting format from extension.
+
+    `.json` → JSON, `.csv` → CSV, otherwise text.
+
+    Args:
+        path: Path to schema file.
+
+    Returns:
+        Parsed schema dictionary.
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+    """
+    content = path.read_text(encoding="utf-8")
+    suffix = path.suffix.lower()
+    if suffix == ".json":
+        return parse_schema_json(content)
+    elif suffix == ".csv":
+        return parse_schema_csv(content)
+    else:
+        return parse_schema_text(content)

sqlglider/schema/extractor.py

@@ -153,6 +153,7 @@ def extract_and_resolve_schema(
     file_paths: List[Path],
     dialect: str = "spark",
     sql_preprocessor: Optional[SqlPreprocessor] = None,
+    initial_schema: Optional[SchemaDict] = None,
     strict_schema: bool = False,
     catalog_type: Optional[str] = None,
     catalog_config: Optional[Dict[str, object]] = None,
@@ -167,6 +168,7 @@ def extract_and_resolve_schema(
         file_paths: SQL files to extract schema from.
         dialect: SQL dialect.
         sql_preprocessor: Optional SQL preprocessor.
+        initial_schema: Optional starting schema to build upon.
         strict_schema: If True, fail on ambiguous column attribution.
         catalog_type: Optional catalog provider name.
         catalog_config: Optional provider-specific configuration dict.
@@ -183,6 +185,7 @@ def extract_and_resolve_schema(
         file_paths,
         dialect=dialect,
         sql_preprocessor=sql_preprocessor,
+        initial_schema=initial_schema,
         strict_schema=strict_schema,
         console=console,
     )