clickzetta-semantic-model-generator 1.0.13__py3-none-any.whl → 1.0.14__py3-none-any.whl

{clickzetta_semantic_model_generator-1.0.13.dist-info → clickzetta_semantic_model_generator-1.0.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: clickzetta-semantic-model-generator
-Version: 1.0.13
+Version: 1.0.14
 Summary: Curate a Semantic Model for ClickZetta Lakehouse
 License: Apache Software License; BSD License
 Author: qililiang

{clickzetta_semantic_model_generator-1.0.13.dist-info → clickzetta_semantic_model_generator-1.0.14.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=CwmO0kjQRujtDBaikjUY2h9Y28i4Ui--ojtB5Nr7XJs,36033
+semantic_model_generator/clickzetta_utils/clickzetta_connector.py,sha256=u4wLPrZAB5Um-Db388bWH2JzDX4r9lZNOR79ncNvBuc,36470
 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-1.0.13.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-clickzetta_semantic_model_generator-1.0.13.dist-info/METADATA,sha256=eWxK-U7IaduyEYAHMppEJx_DxDaTDdgQJPoed52fu-s,7817
-clickzetta_semantic_model_generator-1.0.13.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-clickzetta_semantic_model_generator-1.0.13.dist-info/RECORD,,
+clickzetta_semantic_model_generator-1.0.14.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+clickzetta_semantic_model_generator-1.0.14.dist-info/METADATA,sha256=RIO7DImIBM2Ei5AaNEumE5c3S1VBqFMh8rFRZ6UDSO0,7817
+clickzetta_semantic_model_generator-1.0.14.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+clickzetta_semantic_model_generator-1.0.14.dist-info/RECORD,,

semantic_model_generator/clickzetta_utils/clickzetta_connector.py

@@ -4,7 +4,7 @@ import concurrent.futures
 import re
 from collections import defaultdict
 from contextlib import contextmanager
-from typing import Any, Dict, Generator, List, Optional, TypeVar, Union
+from typing import Any, Dict, Generator, List, Optional, Tuple, TypeVar, Union
 
 import pandas as pd
 from clickzetta.zettapark.session import Session
@@ -491,21 +491,30 @@ def _fetch_columns_via_show(
             continue
 
         identifier_candidates: List[str] = []
-        fully_qualified = join_quoted_identifiers(
-            *(part for part in (catalog, schema_token, table_token) if part)
-        )
-        if fully_qualified:
-            identifier_candidates.append(fully_qualified)
-        schema_qualified = (
-            join_quoted_identifiers(schema_token, table_token)
-            if schema_token
-            else ""
-        )
-        if schema_qualified:
-            identifier_candidates.append(schema_qualified)
-        bare_identifier = join_quoted_identifiers(table_token)
-        if bare_identifier:
-            identifier_candidates.append(bare_identifier)
+        seen_identifiers: set[str] = set()
+
+        def _add_identifier(parts: Tuple[str, ...], *, quoted: bool) -> None:
+            tokens = [part.strip() for part in parts if part and part.strip()]
+            if not tokens:
+                return
+            if quoted:
+                identifier = ".".join(quote_identifier(token) for token in tokens)
+            else:
+                identifier = ".".join(tokens)
+            if identifier and identifier not in seen_identifiers:
+                identifier_candidates.append(identifier)
+                seen_identifiers.add(identifier)
+
+        raw_parts = (catalog, schema_token, table_token)
+        schema_parts = (schema_token, table_token)
+        table_parts = (table_token,)
+
+        _add_identifier(raw_parts, quoted=False)
+        _add_identifier(schema_parts, quoted=False)
+        _add_identifier(table_parts, quoted=False)
+        _add_identifier(raw_parts, quoted=True)
+        _add_identifier(schema_parts, quoted=True)
+        _add_identifier(table_parts, quoted=True)
 
         df = pd.DataFrame()
         df_source = ""