informatica-python 1.9.0__tar.gz → 1.9.2__tar.gz

{informatica_python-1.9.0 → informatica_python-1.9.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.9.0
+Version: 1.9.2
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT
@@ -307,6 +307,12 @@ Converts Informatica expressions to Python equivalents:
 ### v1.9.x (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`)
 - Workflow imports automatically match the named mapping files
+- **Expression converter rewrite**: Recursive parenthesis-aware parser replacing simple regex; fixes nested IIF/INSTR/LTRIM/RTRIM/REPLACECHR/REPLACESTR/SUBSTR/TO_CHAR/CHR/MAKE_DATE_TIME
+- **`:LKP.` references** now properly converted to `lookup_func()` calls in vectorized mode
+- **String literal safety**: `||` concatenation no longer applies `.astype(str)` to string literals
+- **NULL/TRUE/FALSE**: Correctly resolved as `None`/`True`/`False` before field-name substitution
+- **`import pandas as pd`** and `from datetime import datetime` now included in generated mapping files
+- **MSSQL connection fallbacks**: `pymssql` and `sqlalchemy` tried when `pyodbc` unavailable
 
 ### v1.8.x (Phase 7)
 - Row-count logging at every pipeline step (source reads, transforms, target writes)

{informatica_python-1.9.0 → informatica_python-1.9.2}/README.md

@@ -280,6 +280,12 @@ Converts Informatica expressions to Python equivalents:
 ### v1.9.x (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`)
 - Workflow imports automatically match the named mapping files
+- **Expression converter rewrite**: Recursive parenthesis-aware parser replacing simple regex; fixes nested IIF/INSTR/LTRIM/RTRIM/REPLACECHR/REPLACESTR/SUBSTR/TO_CHAR/CHR/MAKE_DATE_TIME
+- **`:LKP.` references** now properly converted to `lookup_func()` calls in vectorized mode
+- **String literal safety**: `||` concatenation no longer applies `.astype(str)` to string literals
+- **NULL/TRUE/FALSE**: Correctly resolved as `None`/`True`/`False` before field-name substitution
+- **`import pandas as pd`** and `from datetime import datetime` now included in generated mapping files
+- **MSSQL connection fallbacks**: `pymssql` and `sqlalchemy` tried when `pyodbc` unavailable
 
 ### v1.8.x (Phase 7)
 - Row-count logging at every pipeline step (source reads, transforms, target writes)

{informatica_python-1.9.0 → informatica_python-1.9.2}/informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.9.0"
+__version__ = "1.9.2"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

{informatica_python-1.9.0 → informatica_python-1.9.2}/informatica_python/generators/helper_gen.py

@@ -151,6 +151,17 @@ def _add_db_functions(lines, data_lib):
     lines.append("            return pyodbc.connect(conn_str)")
     lines.append("        except ImportError:")
     lines.append("            pass")
+    lines.append("        try:")
+    lines.append("            import pymssql")
+    lines.append("            return pymssql.connect(server=host, port=int(port), database=database, user=username, password=password)")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
+    lines.append("        try:")
+    lines.append("            from sqlalchemy import create_engine")
+    lines.append("            engine = create_engine(f'mssql+pymssql://{username}:{password}@{host}:{port}/{database}')")
+    lines.append("            return engine.connect()")
+    lines.append("        except ImportError:")
+    lines.append("            pass")
     lines.append("")
     lines.append("    if db_type == 'postgresql':")
     lines.append("        try:")

{informatica_python-1.9.0 → informatica_python-1.9.2}/informatica_python/generators/mapping_gen.py

@@ -227,6 +227,8 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
     lines.append("")
     lines.append("import logging")
     lines.append("import numpy as np")
+    lines.append("import pandas as pd")
+    lines.append("from datetime import datetime")
     lines.append("from helper_functions import *")
     lines.append("")
     lines.append("logger = logging.getLogger(__name__)")
@@ -601,8 +603,19 @@ def _generate_source_qualifier(lines, sq, source_map, source_dfs, connector_grap
         lines.append(f"    execute_sql(config, '''{pre_sql}''')")
         lines.append("")
 
-    if sql_override:
-        src_name = next(iter(connected_sources)) if connected_sources else "source"
+    if not connected_sources:
+        sq_src_name = sq.name[3:] if sq.name.upper().startswith("SQ_") else sq.name
+        if sql_override:
+            lines.append(f"    sql_{sq_safe} = '''")
+            for sql_line in sql_override.strip().split("\n"):
+                lines.append(f"    {sql_line}")
+            lines.append(f"    '''")
+            lines.append(f"    df_{sq_safe} = read_from_db(config, sql_{sq_safe}, 'default')")
+        else:
+            lines.append(f"    df_{sq_safe} = read_file(config.get('sources', {{}}).get('{sq_src_name}', {{}}).get('file_path', '{sq_src_name}'),")
+            lines.append(f"                              config.get('sources', {{}}).get('{sq_src_name}', {{}}))")
+    elif sql_override:
+        src_name = next(iter(connected_sources))
         src_def = source_map.get(src_name, SourceDef(name=src_name))
         sq_override = (session_overrides or {}).get(sq.name, {}) or (session_overrides or {}).get(src_name, {})
         conn_name = sq_override.get("connection_name") or (_safe_name(src_def.db_name) if src_def.db_name else "default")
@@ -612,36 +625,35 @@ def _generate_source_qualifier(lines, sq, source_map, source_dfs, connector_grap
             lines.append(f"    {sql_line}")
         lines.append(f"    '''")
         lines.append(f"    df_{sq_safe} = read_from_db(config, sql_{sq_safe}, '{conn_name}')")
+    elif len(connected_sources) == 1:
+        src_name = next(iter(connected_sources))
+        src_def = source_map.get(src_name, SourceDef(name=src_name))
+        safe_src = _safe_name(src_name)
+        src_override = (session_overrides or {}).get(sq.name, {}) or (session_overrides or {}).get(src_name, {})
+        if src_def.database_type and src_def.database_type != "Flat File":
+            conn_name = src_override.get("connection_name") or (_safe_name(src_def.db_name) if src_def.db_name else "default")
+            schema = src_def.owner_name or "dbo"
+            cols = ", ".join(f.name for f in src_def.fields) if src_def.fields else "*"
+            lines.append(f"    df_{sq_safe} = read_from_db(config, 'SELECT {cols} FROM {schema}.{src_def.name}', '{conn_name}')")
+        elif src_def.flatfile:
+            _emit_flatfile_read(lines, sq_safe, src_def)
+        else:
+            lines.append(f"    df_{sq_safe} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
+            lines.append(f"                              config.get('sources', {{}}).get('{src_def.name}', {{}}))")
     else:
-        if len(connected_sources) == 1:
-            src_name = next(iter(connected_sources))
+        for src_name in connected_sources:
             src_def = source_map.get(src_name, SourceDef(name=src_name))
             safe_src = _safe_name(src_name)
-            src_override = (session_overrides or {}).get(sq.name, {}) or (session_overrides or {}).get(src_name, {})
             if src_def.database_type and src_def.database_type != "Flat File":
-                conn_name = src_override.get("connection_name") or (_safe_name(src_def.db_name) if src_def.db_name else "default")
+                conn_name = _safe_name(src_def.db_name) if src_def.db_name else "default"
                 schema = src_def.owner_name or "dbo"
-                cols = ", ".join(f.name for f in src_def.fields) if src_def.fields else "*"
-                lines.append(f"    df_{sq_safe} = read_from_db(config, 'SELECT {cols} FROM {schema}.{src_def.name}', '{conn_name}')")
+                lines.append(f"    df_{safe_src} = read_from_db(config, 'SELECT * FROM {schema}.{src_def.name}', '{conn_name}')")
             elif src_def.flatfile:
-                _emit_flatfile_read(lines, sq_safe, src_def)
+                _emit_flatfile_read(lines, safe_src, src_def)
             else:
-                lines.append(f"    df_{sq_safe} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
+                lines.append(f"    df_{safe_src} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
                 lines.append(f"                              config.get('sources', {{}}).get('{src_def.name}', {{}}))")
-        else:
-            for src_name in connected_sources:
-                src_def = source_map.get(src_name, SourceDef(name=src_name))
-                safe_src = _safe_name(src_name)
-                if src_def.database_type and src_def.database_type != "Flat File":
-                    conn_name = _safe_name(src_def.db_name) if src_def.db_name else "default"
-                    schema = src_def.owner_name or "dbo"
-                    lines.append(f"    df_{safe_src} = read_from_db(config, 'SELECT * FROM {schema}.{src_def.name}', '{conn_name}')")
-                elif src_def.flatfile:
-                    _emit_flatfile_read(lines, safe_src, src_def)
-                else:
-                    lines.append(f"    df_{safe_src} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
-                    lines.append(f"                              config.get('sources', {{}}).get('{src_def.name}', {{}}))")
-            lines.append(f"    df_{sq_safe} = df_{_safe_name(next(iter(connected_sources)))}")
+        lines.append(f"    df_{sq_safe} = df_{_safe_name(next(iter(connected_sources)))}")
 
     source_dfs[sq.name] = f"df_{sq_safe}"
     lines.append(f"    try:")