informatica-python 1.9.6__py3-none-any.whl → 1.9.8__py3-none-any.whl

informatica_python/generators/mapping_gen.py

@@ -481,7 +481,12 @@ def _emit_flatfile_read(lines, var_name, src_def, indent="    ", file_path_overr
     if fc.get("fixed_width"):
         widths = []
         for fld in src_def.fields:
-            widths.append(fld.precision if fld.precision else 10)
+            if fld.physical_length and fld.physical_length > 0:
+                widths.append(fld.physical_length)
+            elif fld.precision:
+                widths.append(fld.precision)
+            else:
+                widths.append(10)
         lines.append(f"{indent}df_{var_name} = pd.read_fwf(")
         lines.append(f"{indent}    {default_path},")
         lines.append(f"{indent}    widths={widths},")

informatica_python/models.py

@@ -18,6 +18,9 @@ class FieldDef:
     field_number: int = 0
     hidden: str = "NO"
     business_name: str = ""
+    offset: int = 0
+    physical_offset: int = 0
+    physical_length: int = 0
     field_attributes: List[Dict[str, str]] = field(default_factory=list)
 
 

informatica_python/parser.py

@@ -417,6 +417,9 @@ class InformaticaParser:
             hidden=self._attr(elem, "HIDDEN", "NO"),
             business_name=self._attr(elem, "BUSINESSNAME"),
             description=self._attr(elem, "DESCRIPTION"),
+            offset=self._int_attr(elem, "OFFSET"),
+            physical_offset=self._int_attr(elem, "PHYSICALOFFSET"),
+            physical_length=self._int_attr(elem, "PHYSICALLENGTH"),
         )
         for fa in elem.findall("FIELDATTRIBUTE"):
             fld.field_attributes.append({

informatica_python/utils/expression_converter.py

@@ -184,7 +184,9 @@ def convert_expression(expr):
         return cleaned
 
     if cleaned.startswith("'") and cleaned.endswith("'"):
-        return cleaned
+        close_pos = cleaned.find("'", 1)
+        if close_pos == len(cleaned) - 1:
+            return cleaned
 
     converted = cleaned
 
@@ -428,7 +430,9 @@ def _vec_recursive(expr, df_var):
         return cleaned
 
     if cleaned.startswith("'") and cleaned.endswith("'"):
-        return cleaned
+        close_pos = cleaned.find("'", 1)
+        if close_pos == len(cleaned) - 1:
+            return cleaned
 
     upper = cleaned.upper()
 
@@ -452,6 +456,17 @@ def _vec_recursive(expr, df_var):
         var_name = cleaned[2:]
         return f'get_variable("{var_name}")'
 
+    if re.match(r'^\$PM\w+$', cleaned):
+        var_name = cleaned[1:]
+        return f'resolve_builtin_variable("{var_name}")'
+
+    not_result = _find_func_call(cleaned, 'NOT')
+    if not_result and not_result[0] == 0 and not_result[1] == len(cleaned):
+        _, _, args = not_result
+        if len(args) >= 1:
+            inner = _vec_recursive(args[0], df_var)
+            return f'~({inner})'
+
     lkp_result = _find_func_call(cleaned, 'LKP')
     if lkp_result is None:
         lkp_match = re.match(r'^:LKP\.(\w+)\s*\(', cleaned, re.IGNORECASE)
@@ -666,6 +681,8 @@ def _vec_recursive(expr, df_var):
             if len(args) >= 2:
                 fmt = _convert_infa_date_format(args[1])
                 return f'{field_val}.dt.strftime("{fmt}")'
+            if any(op in field_val for op in (' + ', ' - ', ' * ', ' / ', ' % ')):
+                return f'({field_val}).astype(str)'
             return f'{field_val}.astype(str)'
 
     make_dt_result = _find_func_call(cleaned, 'MAKE_DATE_TIME')
@@ -866,8 +883,10 @@ def _vec_recursive(expr, df_var):
             v = _vec_recursive(p, df_var)
             if v.startswith("'") and v.endswith("'"):
                 vec_parts.append(v)
-            else:
+            elif v.startswith(df_var + '[') or v.startswith('pd.') or '.str.' in v:
                 vec_parts.append(f'{v}.fillna(\'\').astype(str)')
+            else:
+                vec_parts.append(f'str({v})')
         return " + ".join(vec_parts)
 
     for func_name in sorted(INFA_FUNC_MAP.keys(), key=lambda x: -len(x)):
@@ -883,6 +902,7 @@ def _vec_recursive(expr, df_var):
     converted = re.sub(r':LKP\.(\w+)\s*\(', r'lookup_func("\1", ', converted)
 
     converted = re.sub(r'\$\$(\w+)', r'get_variable("\1")', converted)
+    converted = re.sub(r'\$(PM\w+)', r'resolve_builtin_variable("\1")', converted)
 
     converted = re.sub(r'\b([A-Za-z_][A-Za-z0-9_]*)\s*IS\s+NOT\s+NULL\b',
                        lambda m: f'{df_var}["{m.group(1)}"].notna()', converted, flags=re.IGNORECASE)
@@ -895,8 +915,15 @@ def _vec_recursive(expr, df_var):
 
     converted = _convert_remaining_funcs(converted, df_var)
 
+    converted = re.sub(r'\bAND\b', ' & ', converted, flags=re.IGNORECASE)
+    converted = re.sub(r'\bOR\b', ' | ', converted, flags=re.IGNORECASE)
+    converted = re.sub(r'\bNOT\b', ' ~ ', converted, flags=re.IGNORECASE)
+    converted = re.sub(r'<>', '!=', converted)
+    converted = re.sub(r'(?<![<>!=])=(?!=)', '==', converted)
+
     skip_words = {
         'True', 'False', 'None', 'and', 'or', 'not', 'np', 'pd', 'get_variable',
+        'resolve_builtin_variable',
         'str', 'int', 'float', 'bool', 'len', 'abs', 'round',
         'fillna', 'astype', 'isna', 'notna', 'where', 'errors', 'coerce',
         'lookup_func', 'expand', 'extract', 'regex', 'contains', 'replace',
@@ -904,11 +931,6 @@ def _vec_recursive(expr, df_var):
     }
     converted = _substitute_fields(converted, df_var, skip_words)
 
-    converted = re.sub(r'\bAND\b', ' & ', converted, flags=re.IGNORECASE)
-    converted = re.sub(r'\bOR\b', ' | ', converted, flags=re.IGNORECASE)
-    converted = re.sub(r'\bNOT\b', ' ~', converted, flags=re.IGNORECASE)
-    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)
@@ -1041,6 +1063,8 @@ def _vectorize_simple(part, df_var):
     c = re.sub(r'\b([A-Za-z_]\w*)\s*IS\s+NULL\b',
                lambda m: f'{df_var}["{m.group(1)}"].isna()', c, flags=re.IGNORECASE)
 
+    c = re.sub(r'\$(PM\w+)', r'resolve_builtin_variable("\1")', c)
+
     c = re.sub(r'<>', '!=', c)
     c = re.sub(r'(?<![<>!=])=(?!=)', '==', c)
 
@@ -1048,8 +1072,13 @@ def _vectorize_simple(part, df_var):
     c = re.sub(r'\bTRUE\b', 'True', c, flags=re.IGNORECASE)
     c = re.sub(r'\bFALSE\b', 'False', c, flags=re.IGNORECASE)
 
+    c = re.sub(r'\bAND\b', ' & ', c, flags=re.IGNORECASE)
+    c = re.sub(r'\bOR\b', ' | ', c, flags=re.IGNORECASE)
+    c = re.sub(r'\bNOT\b', ' ~ ', c, flags=re.IGNORECASE)
+
     skip_words = {
         'True', 'False', 'None', 'and', 'or', 'not', 'np', 'pd',
+        'resolve_builtin_variable',
         'str', 'int', 'float', 'isna', 'notna', 'fillna',
         'get_variable', 'lookup_func', 'isin', 'eq',
         'expand', 'extract', 'astype', 'errors', 'coerce', 'regex',
@@ -1089,8 +1118,9 @@ def _split_condition_tokens(text):
             current.append(ch)
         elif depth == 0:
             rest = text[i:]
-            and_match = re.match(r'\bAND\b', rest, re.IGNORECASE)
-            or_match = re.match(r'\bOR\b', rest, re.IGNORECASE)
+            prev_is_word = i > 0 and (text[i - 1].isalnum() or text[i - 1] == '_')
+            and_match = re.match(r'\bAND\b', rest, re.IGNORECASE) if not prev_is_word else None
+            or_match = re.match(r'\bOR\b', rest, re.IGNORECASE) if not prev_is_word else None
             if and_match:
                 tokens.append(''.join(current).strip())
                 current = []
@@ -1134,9 +1164,10 @@ def _vectorize_condition(cond, df_var="df"):
     for part in parts:
         negate = False
         inner = part.strip()
-        if re.match(r'^NOT\s+', inner, flags=re.IGNORECASE):
+        not_match = re.match(r'^NOT\b\s*', inner, flags=re.IGNORECASE)
+        if not_match:
             negate = True
-            inner = re.sub(r'^NOT\s+', '', inner, flags=re.IGNORECASE).strip()
+            inner = inner[not_match.end():].strip()
 
         v = _vectorize_simple(inner, df_var)
         if negate:

{informatica_python-1.9.6.dist-info → informatica_python-1.9.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.9.6
+Version: 1.9.8
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT

{informatica_python-1.9.6.dist-info → informatica_python-1.9.8.dist-info}/RECORD

@@ -1,23 +1,23 @@
 informatica_python/__init__.py,sha256=JFO8fVMClSWe0SR-CBseX4RaPyyC3rZBdxxjy47ZT5E,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
-informatica_python/parser.py,sha256=v0qoTlAi3RZ3IHN_5g5t6f66XzRpJIjpAfpyMzZ5cuA,45223
+informatica_python/models.py,sha256=sZvVzYrEIRAfzV_HduN-qCeOAt5KZ_z7jzNTmPP3Oxs,17371
+informatica_python/parser.py,sha256=RVxoT1j6QTer2RyeG-PCEyKaoZAQhFepRcrRdsEm6OM,45410
 informatica_python/generators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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=lC30hyZn6RIkbo4e_6sbqdrCfmZHWaXdr-p0tmtfILc,82376
-informatica_python/generators/mapping_gen.py,sha256=a5UZCIoU5E5ff9Q8Nxp_m-6k8wZv2NTZL96o2hDddZo,72603
+informatica_python/generators/mapping_gen.py,sha256=5wPS9t3OLpbo89gYsHMbVqCg9Jgfzmt13IqK4diOS2g,72781
 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=SkkT2CyhIZzUms9TT4cEimZlxjOoVq96AQgGTrO_Lmc,46859
+informatica_python/utils/expression_converter.py,sha256=ynprsvZGvavML3Y8C485GyjaoqQ-k67OESXHShafeTo,48244
 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-1.9.6.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
-informatica_python-1.9.6.dist-info/METADATA,sha256=4XrzBAs63VuLy6Wf_WsgmbGLWK9iaJeHjIZiyOb2PBw,26097
-informatica_python-1.9.6.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
-informatica_python-1.9.6.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
-informatica_python-1.9.6.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
-informatica_python-1.9.6.dist-info/RECORD,,
+informatica_python-1.9.8.dist-info/licenses/LICENSE,sha256=77RaRDdXgey1D90YZAjXqEQdBxWfvUQqLQX3pC1qjUE,1061
+informatica_python-1.9.8.dist-info/METADATA,sha256=YErpXHS5T-sSTEUwENMiaCWaYhj6xiQALyyLZACrc2g,26097
+informatica_python-1.9.8.dist-info/WHEEL,sha256=PovZm1ExVWmrRefZoXCfejlbKLnQI5SVIf1SWRV4QQI,97
+informatica_python-1.9.8.dist-info/entry_points.txt,sha256=030jjTrx-1oRRQ16HZz52rdcKS8R8_llnymsTUtn_Xc,67
+informatica_python-1.9.8.dist-info/top_level.txt,sha256=Dngg-WNteYi22XAJU2XKAQS8aZ52yM2LYC0tzxrlbVQ,19
+informatica_python-1.9.8.dist-info/RECORD,,