informatica-python 1.3.0__tar.gz → 1.3.1__tar.gz

{informatica_python-1.3.0 → informatica_python-1.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.3.0
+Version: 1.3.1
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 License-Expression: MIT
 Requires-Python: >=3.8

{informatica_python-1.3.0 → informatica_python-1.3.1}/informatica_python/generators/helper_gen.py

@@ -208,7 +208,11 @@ def _add_file_functions(lines, data_lib):
     lines.append("    delimiter = file_config.get('delimiter', ',')")
     lines.append("    header = file_config.get('header', True)")
     lines.append("    encoding = file_config.get('encoding', 'utf-8')")
-    lines.append("    header_row = 0 if header else None")
+    lines.append("    header_row = file_config.get('header_row', 0 if header else None)")
+    lines.append("    skip_rows = file_config.get('skip_rows', 0)")
+    lines.append("    quotechar = file_config.get('quotechar', '\"')")
+    lines.append("    escapechar = file_config.get('escapechar', None)")
+    lines.append("    lineterminator = file_config.get('lineterminator', None)")
     lines.append("")
     lines.append("    logger.info(f'Reading file: {file_path} (ext={ext})')")
     lines.append("")
@@ -245,7 +249,17 @@ def _add_file_functions(lines, data_lib):
         lines.append("            return dd.read_csv(file_path, sep=delimiter, header=header_row)")
     else:
         lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
-        lines.append("            return pd.read_csv(file_path, sep=delimiter, header=header_row, encoding=encoding)")
+        lines.append("            csv_kwargs = dict(sep=delimiter, header=header_row, encoding=encoding,")
+        lines.append("                              quotechar=quotechar, escapechar=escapechar)")
+        lines.append("            if skip_rows:")
+        lines.append("                csv_kwargs['skiprows'] = skip_rows")
+        lines.append("            if lineterminator:")
+        lines.append("                csv_kwargs['lineterminator'] = lineterminator")
+        lines.append("            df = pd.read_csv(file_path, **csv_kwargs)")
+        lines.append("            if file_config.get('strip_trailing_blanks'):")
+        lines.append("                str_cols = df.select_dtypes(include=['object']).columns")
+        lines.append("                df[str_cols] = df[str_cols].apply(lambda c: c.str.rstrip())")
+        lines.append("            return df")
         lines.append("        elif ext in ('.xlsx', '.xls'):")
         lines.append("            return pd.read_excel(file_path, header=header_row)")
         lines.append("        elif ext == '.xml':")
@@ -271,6 +285,7 @@ def _add_file_functions(lines, data_lib):
     lines.append("    delimiter = file_config.get('delimiter', ',')")
     lines.append("    header = file_config.get('header', True)")
     lines.append("    encoding = file_config.get('encoding', 'utf-8')")
+    lines.append("    quotechar = file_config.get('quotechar', '\"')")
     lines.append("")
     lines.append("    os.makedirs(os.path.dirname(file_path) or '.', exist_ok=True)")
     lines.append("    logger.info(f'Writing file: {file_path}')")
@@ -290,7 +305,7 @@ def _add_file_functions(lines, data_lib):
         lines.append("            df.write_csv(file_path, separator=delimiter, has_header=header)")
     elif data_lib == "dask":
         lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
-        lines.append("            df.compute().to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding)")
+        lines.append("            df.compute().to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding, quotechar=quotechar)")
         lines.append("        elif ext in ('.xlsx', '.xls'):")
         lines.append("            df.compute().to_excel(file_path, header=header, index=False)")
         lines.append("        elif ext == '.json':")
@@ -301,7 +316,7 @@ def _add_file_functions(lines, data_lib):
         lines.append("            df.compute().to_csv(file_path, sep=delimiter, header=header, index=False)")
     else:
         lines.append("        if ext in ('.csv', '.dat', '.txt', ''):")
-        lines.append("            df.to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding)")
+        lines.append("            df.to_csv(file_path, sep=delimiter, header=header, index=False, encoding=encoding, quotechar=quotechar)")
         lines.append("        elif ext in ('.xlsx', '.xls'):")
         lines.append("            df.to_excel(file_path, header=header, index=False)")
         lines.append("        elif ext == '.json':")

{informatica_python-1.3.0 → informatica_python-1.3.1}/informatica_python/generators/mapping_gen.py

@@ -151,9 +151,13 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
     inlined_transforms, inlined_connectors, mapplet_instance_names = _inline_mapplets(mapping, folder)
 
     all_transforms = list(mapping.transformations) + inlined_transforms
-    all_connectors = [c for c in mapping.connectors
-                      if c.from_instance not in mapplet_instance_names
-                      and c.to_instance not in mapplet_instance_names] + inlined_connectors
+    if mapplet_instance_names:
+        kept_originals = [c for c in mapping.connectors
+                          if c.from_instance not in mapplet_instance_names
+                          and c.to_instance not in mapplet_instance_names]
+        all_connectors = kept_originals + inlined_connectors
+    else:
+        all_connectors = list(mapping.connectors)
 
     source_map = _build_source_map(mapping, folder)
     target_map = _build_target_map(mapping, folder)
@@ -996,21 +1000,31 @@ def _gen_rank_transform(lines, tx, tx_safe, input_df, source_dfs):
 
     ascending = top_bottom.upper() != "TOP"
 
+    rank_out_field = "RANKINDEX"
+    for fld in tx.fields:
+        if fld.name.upper() == "RANKINDEX" or "RANK" in fld.name.upper():
+            pt = (fld.porttype or "").upper()
+            if "OUTPUT" in pt and "INPUT" not in pt:
+                rank_out_field = fld.name
+                break
+
     lines.append(f"    df_{tx_safe} = {input_df}.copy()")
     if rank_port and group_by_ports:
         lines.append(f"    # Rank by '{rank_port}' within groups {group_by_ports}")
-        lines.append(f"    df_{tx_safe}['RANKINDEX'] = df_{tx_safe}.groupby({group_by_ports})['{rank_port}'].rank(")
+        lines.append(f"    _rank_vals = df_{tx_safe}.groupby({group_by_ports})['{rank_port}'].rank(")
         lines.append(f"        method='min', ascending={ascending}")
-        lines.append(f"    ).astype(int)")
+        lines.append(f"    )")
+        lines.append(f"    df_{tx_safe}['{rank_out_field}'] = _rank_vals.fillna(0).astype(int)")
         if top_n:
-            lines.append(f"    df_{tx_safe} = df_{tx_safe}[df_{tx_safe}['RANKINDEX'] <= {top_n}].reset_index(drop=True)")
+            lines.append(f"    df_{tx_safe} = df_{tx_safe}[df_{tx_safe}['{rank_out_field}'] <= {top_n}].reset_index(drop=True)")
     elif rank_port:
         lines.append(f"    # Rank by '{rank_port}' (no group-by)")
-        lines.append(f"    df_{tx_safe}['RANKINDEX'] = df_{tx_safe}['{rank_port}'].rank(method='min', ascending={ascending}).astype(int)")
+        lines.append(f"    _rank_vals = df_{tx_safe}['{rank_port}'].rank(method='min', ascending={ascending})")
+        lines.append(f"    df_{tx_safe}['{rank_out_field}'] = _rank_vals.fillna(0).astype(int)")
         if top_n:
-            lines.append(f"    df_{tx_safe} = df_{tx_safe}[df_{tx_safe}['RANKINDEX'] <= {top_n}].reset_index(drop=True)")
+            lines.append(f"    df_{tx_safe} = df_{tx_safe}[df_{tx_safe}['{rank_out_field}'] <= {top_n}].reset_index(drop=True)")
     else:
-        lines.append(f"    df_{tx_safe}['RANKINDEX'] = range(1, len(df_{tx_safe}) + 1)")
+        lines.append(f"    df_{tx_safe}['{rank_out_field}'] = range(1, len(df_{tx_safe}) + 1)")
     source_dfs[tx.name] = f"df_{tx_safe}"
 
 

{informatica_python-1.3.0 → informatica_python-1.3.1}/informatica_python/generators/workflow_gen.py

@@ -147,13 +147,11 @@ def _generate_workflow_function(lines, wf: WorkflowDef, folder: FolderDef):
                 fail_targets = []
                 for link in wf.links:
                     if link.from_instance == task.name:
-                        cond_text = (link.condition or "").strip()
-                        if cond_text and ("$" in cond_text or "SUCCEEDED" in cond_text.upper()
-                                          or "TRUE" in cond_text.upper()):
-                            succ_targets.append(link.to_instance)
-                        elif cond_text and ("FAILED" in cond_text.upper()
-                                            or "FALSE" in cond_text.upper()):
+                        cond_text = (link.condition or "").strip().upper()
+                        if "FAILED" in cond_text or "FALSE" in cond_text:
                             fail_targets.append(link.to_instance)
+                        elif "SUCCEEDED" in cond_text or "TRUE" in cond_text or cond_text:
+                            succ_targets.append(link.to_instance)
                         else:
                             succ_targets.append(link.to_instance)
 

{informatica_python-1.3.0 → informatica_python-1.3.1}/informatica_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.3.0
+Version: 1.3.1
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 License-Expression: MIT
 Requires-Python: >=3.8

{informatica_python-1.3.0 → informatica_python-1.3.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "informatica-python"
-version = "1.3.0"
+version = "1.3.1"
 description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
 readme = "README.md"
 license = "MIT"