informatica-python 1.9.3__py3-none-any.whl → 1.9.4__py3-none-any.whl

informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.9.3"
+__version__ = "1.9.4"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

informatica_python/generators/mapping_gen.py

@@ -757,7 +757,7 @@ def _generate_transformation(lines, tx, connector_graph, source_dfs, transform_m
     elif tx_type in ("joiner",):
         _gen_joiner_transform(lines, tx, tx_safe, input_df, input_sources, source_dfs, connector_graph, data_lib)
     elif tx_type in ("lookup procedure", "lookup"):
-        _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, data_lib)
+        _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, connector_graph, data_lib)
     elif tx_type == "router":
         _gen_router_transform(lines, tx, tx_safe, input_df, source_dfs)
     elif tx_type in ("union",):
@@ -982,7 +982,7 @@ def _gen_joiner_transform(lines, tx, tx_safe, input_df, input_sources, source_df
     source_dfs[tx.name] = f"df_{tx_safe}"
 
 
-def _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, data_lib="pandas"):
+def _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, connector_graph=None, data_lib="pandas"):
     lookup_table = ""
     lookup_sql = ""
     lookup_condition = ""
@@ -1012,6 +1012,11 @@ def _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, data_lib="pa
 
     all_output_fields = return_fields + lookup_output_fields
 
+    port_to_col = {}
+    if connector_graph and tx.name in connector_graph.get("to", {}):
+        for conn in connector_graph["to"][tx.name]:
+            port_to_col[conn.to_field.lower()] = conn.from_field
+
     lines.append(f"    # Lookup: {lookup_table or tx.name}")
     if lookup_sql:
         _emit_sql_with_params(lines, f"lkp_sql_{tx_safe}", lookup_sql)
@@ -1020,10 +1025,13 @@ def _gen_lookup_transform(lines, tx, tx_safe, input_df, source_dfs, data_lib="pa
         lines.append(f"    df_lkp_{tx_safe} = read_from_db(config, 'SELECT * FROM {lookup_table}', 'default')")
     else:
         empty_expr = lib_empty_df(data_lib)
-        lines.append(f"    df_lkp_{tx_safe} = {empty_expr}")
+        lines.append(f"    df_lkp_{tx_safe} = {empty_expr}  # WARNING: no lookup table/SQL override found")
 
     input_keys, lookup_keys = parse_lookup_condition(lookup_condition)
 
+    if input_keys and port_to_col:
+        input_keys = [port_to_col.get(k.lower(), k) for k in input_keys]
+
     if input_keys and lookup_keys:
         lines.append(f"    # Lookup condition: {lookup_condition}")
 
@@ -1078,12 +1086,23 @@ def _gen_router_transform(lines, tx, tx_safe, input_df, source_dfs):
         if "Group Filter Condition" in attr.name:
             group_conditions[attr.name] = attr.value
 
+    remaining_mask_parts = []
     if group_conditions:
         for i, (gname, cond) in enumerate(group_conditions.items()):
-            expr_py = convert_expression(cond) if cond else "True"
-            lines.append(f"    df_{tx_safe}_group{i} = {input_df}[{expr_py}].copy()  # {gname}")
+            if cond and cond.strip():
+                expr_py = convert_filter_vectorized(cond, input_df)
+            else:
+                expr_py = f"pd.Series(True, index={input_df}.index)"
+            mask_var = f"_router_mask_{tx_safe}_{i}"
+            lines.append(f"    {mask_var} = {expr_py}  # {gname}")
+            lines.append(f"    df_{tx_safe}_group{i} = {input_df}[{mask_var}].copy()")
             source_dfs[f"{tx.name}_group{i}"] = f"df_{tx_safe}_group{i}"
-    lines.append(f"    df_{tx_safe} = {input_df}.copy()  # Default group")
+            remaining_mask_parts.append(f"~{mask_var}")
+    if remaining_mask_parts:
+        lines.append(f"    _router_default_mask = {' & '.join(remaining_mask_parts)}")
+        lines.append(f"    df_{tx_safe} = {input_df}[_router_default_mask].copy()  # Default group")
+    else:
+        lines.append(f"    df_{tx_safe} = {input_df}.copy()  # Default group")
     source_dfs[tx.name] = f"df_{tx_safe}"
 
 

informatica_python/utils/expression_converter.py

@@ -248,6 +248,7 @@ def _convert_infa_date_format(fmt_str):
     fmt = fmt.replace("Mon", "%b").replace("MON", "%b")
     fmt = fmt.replace("HH24", "%H").replace("HH12", "%I").replace("HH", "%H")
     fmt = fmt.replace("MI", "%M").replace("SS", "%S")
+    fmt = fmt.replace("US", "%f").replace("NS", "%f").replace("MS", "%f")
     return fmt
 
 
@@ -548,7 +549,7 @@ def _vec_recursive(expr, df_var):
                         'RTRIM': f'.str.rstrip("{char_arg}")',
                         'TRIM': f'.str.strip("{char_arg}")',
                     }
-                return f'{inner_val}{method_map[func_name.upper()]}'
+                return f'{inner_val}.astype(str){method_map[func_name.upper()]}'
 
     upper_result = _find_func_call(cleaned, 'UPPER')
     if upper_result and upper_result[0] == 0 and upper_result[1] == len(cleaned):
@@ -584,7 +585,7 @@ def _vec_recursive(expr, df_var):
         if len(args) >= 2:
             field_val = _vec_recursive(args[0], df_var)
             try:
-                start = int(args[1].strip()) - 1
+                start = max(int(args[1].strip()) - 1, 0)
             except ValueError:
                 start_val = _vec_recursive(args[1], df_var)
                 if len(args) >= 3:
@@ -722,7 +723,11 @@ def _vec_recursive(expr, df_var):
                 field_val = _vec_recursive(args[0], df_var)
                 pattern_val = args[1].strip().strip("'\"")
                 if func_name == 'REG_EXTRACT':
-                    return f'{field_val}.str.extract(r"({pattern_val})", expand=False)'
+                    if re.search(r'(?<!\\)\((?!\?)', pattern_val):
+                        extract_pat = pattern_val
+                    else:
+                        extract_pat = f'({pattern_val})'
+                    return f'{field_val}.str.extract(r"{extract_pat}", expand=False)'
                 elif func_name == 'REG_REPLACE':
                     replace_val = args[2].strip().strip("'\"") if len(args) >= 3 else ''
                     return f'{field_val}.str.replace(r"{pattern_val}", "{replace_val}", regex=True)'
@@ -894,7 +899,8 @@ def _vec_recursive(expr, df_var):
         'True', 'False', 'None', 'and', 'or', 'not', 'np', 'pd', 'get_variable',
         'str', 'int', 'float', 'bool', 'len', 'abs', 'round',
         'fillna', 'astype', 'isna', 'notna', 'where', 'errors', 'coerce',
-        'lookup_func',
+        'lookup_func', 'expand', 'extract', 'regex', 'contains', 'replace',
+        'upper', 'lower', 'strip', 'lstrip', 'rstrip', 'dt', 'copy',
     }
     converted = _substitute_fields(converted, df_var, skip_words)
 
@@ -904,6 +910,8 @@ def _vec_recursive(expr, df_var):
     converted = re.sub(r'<>', '!=', converted)
     converted = re.sub(r'(?<![<>!=])=(?!=)', '==', converted)
     converted = re.sub(r'\berrors\s*==\s*(["\'])', r'errors=\1', converted)
+    converted = re.sub(r'\bexpand\s*==\s*', 'expand=', converted)
+    converted = re.sub(r'\bregex\s*==\s*', 'regex=', converted)
 
     converted = re.sub(r'\s+', ' ', converted).strip()
 
@@ -1044,8 +1052,14 @@ def _vectorize_simple(part, df_var):
         'True', 'False', 'None', 'and', 'or', 'not', 'np', 'pd',
         'str', 'int', 'float', 'isna', 'notna', 'fillna',
         'get_variable', 'lookup_func', 'isin', 'eq',
+        'expand', 'extract', 'astype', 'errors', 'coerce', 'regex',
+        'contains', 'replace', 'upper', 'lower', 'strip', 'lstrip', 'rstrip',
+        'dt', 'len', 'copy', 'abs', 'round', 'where', 'bool',
     }
     c = _substitute_fields(c, df_var, skip_words)
+    c = re.sub(r'\bexpand\s*==\s*', 'expand=', c)
+    c = re.sub(r'\berrors\s*==\s*', 'errors=', c)
+    c = re.sub(r'\bregex\s*==\s*', 'regex=', c)
 
     return c
 

{informatica_python-1.9.3.dist-info → informatica_python-1.9.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.9.3
+Version: 1.9.4
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT
@@ -430,7 +430,7 @@ The generated `helper_functions.py` provides a complete runtime library:
 - **Generated code formatting**: Consistent `# ---` section headers for Source Qualifiers, Transforms, and Target Writes; metadata comments (database type, field lists); column mapping and write operation comments; clean blank line handling
 - **Source/target detection**: Case-insensitive instance type matching
 - **Session→mapping inference**: Longest-suffix-match strategy for ambiguous mapping names
-- **646 tests** across unit, integration, expression, and formatting test suites
+- **663 tests** across unit, integration, expression, and formatting test suites
 
 ### v1.9.2 (Phase 8)
 - Mapping output files now use real mapping names (e.g., `mapping_m_customer_load.py`) instead of generic numeric indices (`mapping_1.py`)
@@ -495,7 +495,7 @@ The generated `helper_functions.py` provides a complete runtime library:
 cd informatica_python
 pip install -e ".[dev]"
 
-# Run tests (646 tests)
+# Run tests (663 tests)
 pytest tests/ -v
 ```
 

{informatica_python-1.9.3.dist-info → informatica_python-1.9.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-informatica_python/__init__.py,sha256=o9kEVkHnEwXAD7hhY8YbN6G8RP4Mqby_q8CpjfbiknQ,337
+informatica_python/__init__.py,sha256=UiVcrgRjgo439mxIWb1Oz1caKLcmgl0DTlz5-GrgKjs,337
 informatica_python/cli.py,sha256=gFwg0O99vKM-OLO0HoHA4emd-6qrgjMNqa9T59e4e_s,2905
 informatica_python/converter.py,sha256=xCuWrYzDji0yN72D3QqOgZCVVM2j3k2_CvlGplCWxLU,22779
 informatica_python/models.py,sha256=G_C2WfQL-ykKjNj23m8vKFtLZYrQozp99HJzrLTKG1Y,17293
@@ -7,17 +7,17 @@ informatica_python/generators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5N
 informatica_python/generators/config_gen.py,sha256=4tqcNKTB06kyGZIiM4yl0q97q_i3zeCHXTjuE1dNFKY,5726
 informatica_python/generators/error_log_gen.py,sha256=2cc0rEcblydHkb9VAMXlrH7WdSQ-CNqAXcwVk3FYZeM,21319
 informatica_python/generators/helper_gen.py,sha256=D6-UqNh09Qy2V7RimNgP-SzK_uB9YqAlsa0-cgLhf5o,72209
-informatica_python/generators/mapping_gen.py,sha256=gBVArcb8uODbgY3epdsldCbUywS-qo8CiKr7hcNjMnc,70654
+informatica_python/generators/mapping_gen.py,sha256=TPcd9tIAhOAIZMbzPslUgPvF-FY_XkI7EfvCVf-yU50,71610
 informatica_python/generators/sql_gen.py,sha256=O8Y-aJz9EyFJ0DXeuISRt5yKwC3wlp2K3B0BHrmxrXw,4872
 informatica_python/generators/workflow_gen.py,sha256=_uSlBg31ZRMhMlCYk4hWDRBPaBROrepD8_v3QGEWJxE,18089
 informatica_python/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 informatica_python/utils/datatype_map.py,sha256=iLOYg-iBKT4rMecGbrFkTpJj4yqs5S9HeBOTLUIWhX0,2809
-informatica_python/utils/expression_converter.py,sha256=CqkkTESMKxcYmVsDpNfn7VcZZe771uCIMy_0YQYq6pc,45946
+informatica_python/utils/expression_converter.py,sha256=f8sNAhE0Yo8sdcVIPDjrw_uGfd5UTD8k1SN8NYApmhI,46846
 informatica_python/utils/lib_adapters.py,sha256=1ZtuMbgDg9Ukf-OF_EG1L_BeeR-6JQk8Kx3WwMfvNRU,6516
 informatica_python/utils/sql_dialect.py,sha256=_IHJbfu8a3mT_OvHpybgSfZKqz6mwVy5ItTKDRChqnU,5461
-informatica_python-1.9.3.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
-informatica_python-1.9.3.dist-info/METADATA,sha256=VbfZWdzKE382RnkR7F2rs7PNL397g3PfglvugN4XVTw,26097
-informatica_python-1.9.3.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
-informatica_python-1.9.3.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
-informatica_python-1.9.3.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
-informatica_python-1.9.3.dist-info/RECORD,,
+informatica_python-1.9.4.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
+informatica_python-1.9.4.dist-info/METADATA,sha256=0KXrQZPNvGQB-47LSGQDZv1hm_nN6YWBlhB8WtBCV4I,26097
+informatica_python-1.9.4.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
+informatica_python-1.9.4.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
+informatica_python-1.9.4.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
+informatica_python-1.9.4.dist-info/RECORD,,