informatica-python 1.8.2__tar.gz → 1.9.0__tar.gz

{informatica_python-1.8.2 → informatica_python-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.8.2
+Version: 1.9.0
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT
@@ -97,7 +97,7 @@ converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars
 | File | Description |
 |------|-------------|
 | `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions), window/analytic functions, stored procedure execution, state persistence |
-| `mapping_N.py` | One per mapping — transformation logic with row-count logging, source reads, target writes, inline documentation |
+| `mapping_{name}.py` | One per mapping, named after the real Informatica mapping name — transformation logic with row-count logging, source reads, target writes, inline documentation |
 | `workflow.py` | Task orchestration with topological ordering, decision branching, worklet calls, and error handling |
 | `config.yml` | Connection configs, source/target metadata, runtime parameters |
 | `all_sql_queries.sql` | All SQL extracted from Source Qualifiers, Lookups, SQL transforms (with ANSI-translated variants) |
@@ -304,6 +304,10 @@ Converts Informatica expressions to Python equivalents:
 
 ## Changelog
 
+### 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
+
 ### v1.8.x (Phase 7)
 - Row-count logging at every pipeline step (source reads, transforms, target writes)
 - Backend-safe logging (try/except wrapped for Dask/lazy backends)

{informatica_python-1.8.2 → informatica_python-1.9.0}/README.md

@@ -70,7 +70,7 @@ converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars
 | File | Description |
 |------|-------------|
 | `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions), window/analytic functions, stored procedure execution, state persistence |
-| `mapping_N.py` | One per mapping — transformation logic with row-count logging, source reads, target writes, inline documentation |
+| `mapping_{name}.py` | One per mapping, named after the real Informatica mapping name — transformation logic with row-count logging, source reads, target writes, inline documentation |
 | `workflow.py` | Task orchestration with topological ordering, decision branching, worklet calls, and error handling |
 | `config.yml` | Connection configs, source/target metadata, runtime parameters |
 | `all_sql_queries.sql` | All SQL extracted from Source Qualifiers, Lookups, SQL transforms (with ANSI-translated variants) |
@@ -277,6 +277,10 @@ Converts Informatica expressions to Python equivalents:
 
 ## Changelog
 
+### 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
+
 ### v1.8.x (Phase 7)
 - Row-count logging at every pipeline step (source reads, transforms, target writes)
 - Backend-safe logging (try/except wrapped for Dask/lazy backends)

{informatica_python-1.8.2 → informatica_python-1.9.0}/informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.8.2"
+__version__ = "1.9.0"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

{informatica_python-1.8.2 → informatica_python-1.9.0}/informatica_python/converter.py

@@ -19,6 +19,14 @@ class InformaticaConverter:
         self.parser = InformaticaParser()
         self.powermart = None
 
+    @staticmethod
+    def _safe_name(name):
+        import re
+        safe = re.sub(r'[^a-zA-Z0-9_]', '_', name)
+        if safe and safe[0].isdigit():
+            safe = '_' + safe
+        return safe.lower()
+
     def parse_file(self, file_path: str) -> dict:
         self.powermart = self.parser.parse_file(file_path)
         return self.to_json()
@@ -102,7 +110,8 @@ class InformaticaConverter:
 
         for i, mapping in enumerate(folder.mappings, 1):
             code = generate_mapping_code(mapping, folder, self.data_lib, i, validate_casts=validate_casts)
-            files[f"mapping_{i}.py"] = code
+            safe_name = self._safe_name(mapping.name)
+            files[f"mapping_{safe_name}.py"] = code
 
         files["workflow.py"] = generate_workflow_code(folder)
 

{informatica_python-1.8.2 → informatica_python-1.9.0}/informatica_python/generators/workflow_gen.py

@@ -25,9 +25,9 @@ def generate_workflow_code(folder: FolderDef) -> str:
     lines.append("from helper_functions import load_config, logger, load_persistent_state, save_persistent_state, get_persistent_variable, set_persistent_variable")
     lines.append("")
 
-    for i, mapping in enumerate(folder.mappings, 1):
+    for mapping in folder.mappings:
         safe_name = _safe_name(mapping.name)
-        lines.append(f"from mapping_{i} import run_{safe_name}")
+        lines.append(f"from mapping_{safe_name} import run_{safe_name}")
     lines.append("")
     lines.append("")
 

{informatica_python-1.8.2 → informatica_python-1.9.0}/informatica_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.8.2
+Version: 1.9.0
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT
@@ -97,7 +97,7 @@ converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars
 | File | Description |
 |------|-------------|
 | `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions), window/analytic functions, stored procedure execution, state persistence |
-| `mapping_N.py` | One per mapping — transformation logic with row-count logging, source reads, target writes, inline documentation |
+| `mapping_{name}.py` | One per mapping, named after the real Informatica mapping name — transformation logic with row-count logging, source reads, target writes, inline documentation |
 | `workflow.py` | Task orchestration with topological ordering, decision branching, worklet calls, and error handling |
 | `config.yml` | Connection configs, source/target metadata, runtime parameters |
 | `all_sql_queries.sql` | All SQL extracted from Source Qualifiers, Lookups, SQL transforms (with ANSI-translated variants) |
@@ -304,6 +304,10 @@ Converts Informatica expressions to Python equivalents:
 
 ## Changelog
 
+### 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
+
 ### v1.8.x (Phase 7)
 - Row-count logging at every pipeline step (source reads, transforms, target writes)
 - Backend-safe logging (try/except wrapped for Dask/lazy backends)

{informatica_python-1.8.2 → informatica_python-1.9.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "informatica-python"
-version = "1.8.2"
+version = "1.9.0"
 description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
 readme = "README.md"
 license = {text = "MIT"}

{informatica_python-1.8.2 → informatica_python-1.9.0}/tests/test_converter.py

@@ -104,7 +104,6 @@ def test_convert_to_files():
 
         expected_files = [
             "helper_functions.py",
-            "mapping_1.py",
             "workflow.py",
             "config.yml",
             "all_sql_queries.sql",
@@ -118,6 +117,12 @@ def test_convert_to_files():
             assert size > 0, f"{f} should not be empty"
             print(f"  {f}: {size} bytes")
 
+        mapping_files = [f for f in os.listdir(output_dir) if f.startswith("mapping_") and f.endswith(".py")]
+        assert len(mapping_files) > 0, "At least one mapping file should exist"
+        for mf in mapping_files:
+            assert mf != "mapping_1.py", "Mapping files should use real mapping names, not numeric indices"
+            print(f"  {mf}: {os.path.getsize(os.path.join(output_dir, mf))} bytes")
+
         print(f"PASS: test_convert_to_files")
 
 

{informatica_python-1.8.2 → informatica_python-1.9.0}/tests/test_integration.py

@@ -337,7 +337,7 @@ class TestCodeGeneration:
         converter = InformaticaConverter(data_lib="pandas")
         output = converter.convert_string(MINIMAL_XML, output_dir=self.tmpdir)
 
-        mapping_path = os.path.join(output, "mapping_1.py")
+        mapping_path = os.path.join(output, "mapping_m_test_expr.py")
         assert os.path.exists(mapping_path)
 
         with open(mapping_path) as f:
@@ -350,7 +350,7 @@ class TestCodeGeneration:
         converter = InformaticaConverter(data_lib="pandas")
         output = converter.convert_string(FILTER_XML, output_dir=self.tmpdir)
 
-        mapping_path = os.path.join(output, "mapping_1.py")
+        mapping_path = os.path.join(output, "mapping_m_test_filter.py")
         with open(mapping_path) as f:
             code = f.read()
         assert 'Filter' in code
@@ -378,7 +378,7 @@ class TestCodeGeneration:
         output = converter.convert_string(MINIMAL_XML, output_dir=self.tmpdir)
 
         expected_files = [
-            "helper_functions.py", "mapping_1.py", "workflow.py",
+            "helper_functions.py", "mapping_m_test_expr.py", "workflow.py",
             "config.yml", "all_sql_queries.sql", "error_log.txt",
         ]
         for fname in expected_files:
@@ -398,7 +398,7 @@ class TestCodeGeneration:
         converter = InformaticaConverter(data_lib="pandas")
         output = converter.convert_string(MINIMAL_XML, output_dir=self.tmpdir)
 
-        mapping_path = os.path.join(output, "mapping_1.py")
+        mapping_path = os.path.join(output, "mapping_m_test_expr.py")
         with open(mapping_path) as f:
             code = f.read()
         compile(code, mapping_path, "exec")