sql-glider 0.1.15__py3-none-any.whl → 0.1.18__py3-none-any.whl

{sql_glider-0.1.15.dist-info → sql_glider-0.1.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sql-glider
-Version: 0.1.15
+Version: 0.1.18
 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-0.1.15.dist-info → sql_glider-0.1.18.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlglider/__init__.py,sha256=gDf7s52dMcX7JuCZ1SLawcB1vb3U0yJCohu9RQAATBY,125
-sqlglider/_version.py,sha256=HPqQHR9pVxIxlFt4vovkyoe7k6UO3ag2isBN2lHFL8g,706
+sqlglider/_version.py,sha256=Nx3lULyklTDQB2p2ofjQ59zAxYunJHGjMIsvHePGZsI,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
@@ -18,10 +18,10 @@ sqlglider/graph/models.py,sha256=EYmjv_WzDSNp_WfhJ6H-qBIOkAcoNKS7GRUryfKrHuY,933
 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=08pFR5aGFFPhSbRW6EqiX2d3mp91v-orcs6dm_T1FJg,76484
+sqlglider/lineage/analyzer.py,sha256=46VjvTpC4v50dwDT_SDZWtnb3b0VdbxEOlZJZL1-cBg,78169
 sqlglider/lineage/formatters.py,sha256=_Y9wcTX4JXn1vVnZ1xI656g1FF2rMjcAVc-GHjbd9QA,10389
 sqlglider/schema/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sqlglider/schema/extractor.py,sha256=WW31wbHkL-V749pLb7EAyUOJuziZQK-5hLZVW6f970U,7234
+sqlglider/schema/extractor.py,sha256=P7sVCmBACQ55D8wHS7munbTg0dvJ3-NnUzXf9ZgCAOA,7574
 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
@@ -30,9 +30,9 @@ sqlglider/templating/variables.py,sha256=5593PtLBcOxsnMCSRm2pGAD5I0Y9f__VV3_J_Hf
 sqlglider/utils/__init__.py,sha256=KGp9-UzKz_OFBOTFoSy-g-NXDZsvyWXG_9-1zcC6ePE,276
 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-0.1.15.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/utils/schema.py,sha256=LiWrYDunXKJdoSlpKmIaIQ2hLSaIN1iQHqkXjMpGzRE,1883
+sql_glider-0.1.18.dist-info/METADATA,sha256=lPAHSo1k6J-j2wgGSJ3dAHtZBUouCRiW2L_sxuM1ewo,28446
+sql_glider-0.1.18.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+sql_glider-0.1.18.dist-info/entry_points.txt,sha256=HDuakHqHS5C0HFKsMIxMYmDU7-BLBGrnIJcYaVRu-s0,251
+sql_glider-0.1.18.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sql_glider-0.1.18.dist-info/RECORD,,

sqlglider/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.15'
-__version_tuple__ = version_tuple = (0, 1, 15)
+__version__ = version = '0.1.18'
+__version_tuple__ = version_tuple = (0, 1, 18)
 
 __commit_id__ = commit_id = None

sqlglider/lineage/analyzer.py

@@ -11,6 +11,48 @@ from sqlglot.lineage import Node, lineage
 from sqlglider.global_models import AnalysisLevel
 
 
+def _flat_schema_to_nested(
+    schema: Dict[str, Dict[str, str]],
+) -> Dict[str, object]:
+    """Convert flat dot-notation schema keys to the nested dict structure sqlglot expects.
+
+    sqlglot's MappingSchema requires consistent nesting depth across all tables.
+    Flat keys like ``"db.table"`` are split on dots and nested accordingly.
+    Shorter keys are padded with empty-string prefixes to match the max depth.
+
+    Examples::
+
+        {"users": {"id": "UNKNOWN"}}
+        → {"users": {"id": "UNKNOWN"}}  (depth 1, no change)
+
+        {"db.users": {"id": "UNKNOWN"}, "my_view": {"x": "UNKNOWN"}}
+        → {"db": {"users": {"id": "UNKNOWN"}}, "": {"my_view": {"x": "UNKNOWN"}}}
+    """
+    if not schema:
+        return {}
+
+    # Split all keys into parts
+    entries = [(key.split("."), cols) for key, cols in schema.items()]
+    max_depth = max(len(parts) for parts, _ in entries)
+
+    # If all keys are single-part (unqualified), return as-is
+    if max_depth == 1:
+        return schema  # type: ignore[return-value]
+
+    # Pad shorter keys with empty-string prefixes to match max depth
+    nested: Dict[str, object] = {}
+    for parts, cols in entries:
+        while len(parts) < max_depth:
+            parts.insert(0, "")
+        d: Dict[str, object] = nested
+        for part in parts[:-1]:
+            if part not in d:
+                d[part] = {}
+            d = d[part]  # type: ignore[assignment]
+        d[parts[-1]] = cols
+    return nested
+
+
 class StarResolutionError(Exception):
     """Raised when SELECT * cannot be resolved and no_star mode is enabled."""
 
@@ -860,8 +902,10 @@ class LineageAnalyzer:
             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
+        # sqlglot.lineage() performance degradation with large schema dicts.
+        # Then convert from flat dot-notation keys to the nested dict structure
+        # that sqlglot's MappingSchema expects.
+        lineage_schema: Optional[Dict[str, object]] = None
         if self._file_schema:
             referenced = {t.lower() for t in self._get_query_tables()}
             pruned_schema = {
@@ -869,8 +913,8 @@ class LineageAnalyzer:
                 for table, cols in self._file_schema.items()
                 if table.lower() in referenced
             }
-            if not pruned_schema:
-                pruned_schema = None
+            if pruned_schema:
+                lineage_schema = _flat_schema_to_nested(pruned_schema)
 
         for col in columns_to_analyze:
             try:
@@ -883,7 +927,7 @@ class LineageAnalyzer:
                     lineage_col,
                     current_query_sql,
                     dialect=self.dialect,
-                    schema=pruned_schema,
+                    schema=lineage_schema,
                 )
 
                 # Collect all source columns
@@ -1133,7 +1177,7 @@ class LineageAnalyzer:
         if table.db:
             parts.append(table.db)
         parts.append(table.name)
-        return ".".join(parts)
+        return ".".join(parts).lower()
 
     def _resolve_table_reference(self, ref: str, select_node: exp.Select) -> str:
         """
@@ -1478,7 +1522,7 @@ class LineageAnalyzer:
 
         if columns:
             # Store with UNKNOWN type - SQLGlot only needs column names for expansion
-            self._file_schema[target_name] = {col: "UNKNOWN" for col in columns}
+            self._file_schema[target_name] = {col.lower(): "UNKNOWN" for col in columns}
 
     def _extract_schema_from_dql(self, expr: exp.Expression) -> None:
         """Infer table schemas from column references in DQL.
@@ -1590,8 +1634,9 @@ class LineageAnalyzer:
 
                 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"
+                col_lower = col_name.lower()
+                if col_lower not in self._file_schema[actual_table]:
+                    self._file_schema[actual_table][col_lower] = "UNKNOWN"
 
     def _extract_columns_from_select(
         self, select_node: Union[exp.Select, exp.Union, exp.Intersect, exp.Except]

sqlglider/schema/extractor.py

@@ -41,7 +41,14 @@ def extract_schemas_from_files(
     if console is None:
         console = Console(stderr=True)
 
-    schema: SchemaDict = dict(initial_schema) if initial_schema else {}
+    schema: SchemaDict = (
+        {
+            k.lower(): {c.lower(): v for c, v in cols.items()}
+            for k, cols in initial_schema.items()
+        }
+        if initial_schema
+        else {}
+    )
     total = len(file_paths)
 
     with Progress(
@@ -65,7 +72,11 @@ def extract_schemas_from_files(
                     strict_schema=strict_schema,
                 )
                 file_schema = analyzer.extract_schema_only()
-                schema.update(file_schema)
+                for table_name, columns in file_schema.items():
+                    if table_name in schema:
+                        schema[table_name].update(columns)
+                    else:
+                        schema[table_name] = columns
             except SchemaResolutionError:
                 raise
             except Exception:

sqlglider/utils/schema.py

@@ -46,7 +46,7 @@ def parse_ddl_to_schema(ddl: str, dialect: str = "spark") -> Dict[str, Dict[str,
         table_name = _get_qualified_name(target)
 
         if columns:
-            schema[table_name] = {col: "UNKNOWN" for col in columns}
+            schema[table_name] = {col.lower(): "UNKNOWN" for col in columns}
 
     return schema
 
@@ -59,4 +59,4 @@ def _get_qualified_name(table: exp.Table) -> str:
     if table.db:
         parts.append(table.db)
     parts.append(table.name)
-    return ".".join(parts)
+    return ".".join(parts).lower()