clickzetta-semantic-model-generator 1.0.9__py3-none-any.whl → 1.0.11__py3-none-any.whl

{clickzetta_semantic_model_generator-1.0.9.dist-info → clickzetta_semantic_model_generator-1.0.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: clickzetta-semantic-model-generator
-Version: 1.0.9
+Version: 1.0.11
 Summary: Curate a Semantic Model for ClickZetta Lakehouse
 License: Apache Software License; BSD License
 Author: qililiang

{clickzetta_semantic_model_generator-1.0.9.dist-info → clickzetta_semantic_model_generator-1.0.11.dist-info}/RECORD

@@ -1,5 +1,5 @@
 semantic_model_generator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-semantic_model_generator/clickzetta_utils/clickzetta_connector.py,sha256=1XzJo6ItPRktoKKLJD1eD8EbXYRhSYJrzzHTcbN3b84,34462
+semantic_model_generator/clickzetta_utils/clickzetta_connector.py,sha256=LfudaByoNX8rBe1BYYhgXL7eFWC2H5tBhuivwCfn1iA,35428
 semantic_model_generator/clickzetta_utils/env_vars.py,sha256=8cbL6R75c1-aVQ2i1TDr9SiHCUjTrgvXbIRz4MbcmbE,7664
 semantic_model_generator/clickzetta_utils/utils.py,sha256=UBfWy9qOTyut8tL02gOHHbh6Uz8RqRz5Mm2YdKWFN54,4950
 semantic_model_generator/data_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -32,7 +32,7 @@ semantic_model_generator/validate/context_length.py,sha256=HL-GfaRXNcVji1-pAFGXG
 semantic_model_generator/validate/keywords.py,sha256=frZ5HjRXP69K6dYAU5_d86oSp40_3yoLUg1eQwU3oLM,7080
 semantic_model_generator/validate/schema.py,sha256=eL_wl5yscIeczwNBRUKhF_7QqWW2wSGimkgaOhMFsrA,5893
 semantic_model_generator/validate_model.py,sha256=Uq-V-GfPeF2Dy4l9uF5Guv104gDCDGh0Cxz1AJOu5dk,836
-clickzetta_semantic_model_generator-1.0.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-clickzetta_semantic_model_generator-1.0.9.dist-info/METADATA,sha256=8E8CIqr1H20Kx_GbAALWP0k0fQBwIRKHVBQR3lVpedk,7816
-clickzetta_semantic_model_generator-1.0.9.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-clickzetta_semantic_model_generator-1.0.9.dist-info/RECORD,,
+clickzetta_semantic_model_generator-1.0.11.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+clickzetta_semantic_model_generator-1.0.11.dist-info/METADATA,sha256=redlqh04BYGLtGTzRYRL9TFjAGEpmDRdrStQrOtwT5E,7817
+clickzetta_semantic_model_generator-1.0.11.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+clickzetta_semantic_model_generator-1.0.11.dist-info/RECORD,,

semantic_model_generator/clickzetta_utils/clickzetta_connector.py

@@ -483,37 +483,53 @@ def _fetch_columns_via_show(
     category = _catalog_category(session, workspace)
     is_shared_catalog = category == "SHARED"
     catalog = workspace if is_shared_catalog else workspace.upper()
-    schema = (
-        table_schema or ""
-    )
-    if schema and not is_shared_catalog:
-        schema = schema.upper()
+    schema_token = table_schema or ""
+    if schema_token and not is_shared_catalog:
+        schema_token = schema_token.upper()
 
     for table_name in table_names:
-        qualified_parts = [
-            part
-            for part in (
-                catalog,
-                schema,
-                table_name.upper() if not is_shared_catalog else table_name,
-            )
-            if part
-        ]
-        qualified_table = ".".join(qualified_parts)
-        if is_shared_catalog:
-            query = f"SHOW COLUMNS IN SHARE {qualified_table}"
-        else:
-            query = f"SHOW COLUMNS IN {qualified_table}"
+        table_token = str(table_name).strip()
+        if not table_token:
+            continue
+        qualified_table = join_quoted_identifiers(
+            *(part for part in (catalog, schema_token, table_token) if part)
+        )
+        query = f"SHOW COLUMNS IN {qualified_table}"
+        df_source = "SHOW COLUMNS"
         try:
             df = session.sql(query).to_pandas()
         except Exception as exc:
             logger.debug(
                 "SHOW COLUMNS fallback failed for {}: {}", qualified_table, exc
             )
-            continue
+            df = pd.DataFrame()
+        if df.empty:
+            describe_query = f"DESCRIBE TABLE {qualified_table}"
+            try:
+                describe_df = session.sql(describe_query).to_pandas()
+            except Exception as exc:
+                logger.debug(
+                    "DESCRIBE TABLE fallback failed for {}: {}", qualified_table, exc
+                )
+                describe_df = pd.DataFrame()
+            if not describe_df.empty:
+                df_source = "DESCRIBE TABLE"
+                df = describe_df
         if df.empty:
             continue
         df.columns = [str(col).upper() for col in df.columns]
+        if df_source == "DESCRIBE TABLE":
+            if "KIND" in df.columns:
+                df = df[df["KIND"].astype(str).str.upper() == "COLUMN"]
+            rename_map = {}
+            if "NAME" in df.columns:
+                rename_map["NAME"] = "COLUMN_NAME"
+            if "TYPE" in df.columns:
+                rename_map["TYPE"] = "DATA_TYPE"
+            if rename_map:
+                df = df.rename(columns=rename_map)
+            if df.empty:
+                continue
         schema_col = next(
             (col for col in ("TABLE_SCHEMA", "SCHEMA_NAME") if col in df.columns), None
         )
@@ -536,8 +552,14 @@ def _fetch_columns_via_show(
         )
 
         normalized = pd.DataFrame()
-        normalized[_TABLE_SCHEMA_COL] = df[schema_col] if schema_col else table_schema
-        normalized[_TABLE_NAME_COL] = df[table_col] if table_col else table_name
+        normalized[_TABLE_SCHEMA_COL] = (
+            df[schema_col]
+            if schema_col
+            else (schema_token or table_schema or "")
+        )
+        normalized[_TABLE_NAME_COL] = (
+            df[table_col] if table_col else table_token
+        )
         normalized[_COLUMN_NAME_COL] = (
             df[column_col] if column_col else df.index.astype(str)
         )