informatica-python 1.8.2__tar.gz → 1.9.1__tar.gz

{informatica_python-1.8.2 → informatica_python-1.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.8.2
+Version: 1.9.1
 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-1.9.1}/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-1.9.1}/informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.8.2"
+__version__ = "1.9.1"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

{informatica_python-1.8.2 → informatica_python-1.9.1}/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-1.9.1}/informatica_python/generators/mapping_gen.py

@@ -601,8 +601,19 @@ 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 +623,35 @@ 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:")

{informatica_python-1.8.2 → informatica_python-1.9.1}/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-1.9.1}/informatica_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.8.2
+Version: 1.9.1
 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-1.9.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "informatica-python"
-version = "1.8.2"
+version = "1.9.1"
 description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
 readme = "README.md"
 license = {text = "MIT"}

{informatica_python-1.8.2 → informatica_python-1.9.1}/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-1.9.1}/tests/test_integration.py

@@ -3,6 +3,7 @@ import sys
 import csv
 import tempfile
 import shutil
+import unittest
 import pytest
 from informatica_python.converter import InformaticaConverter
 from informatica_python.utils.expression_converter import (
@@ -337,7 +338,7 @@ 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 +351,7 @@ 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 +379,7 @@ 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 +399,7 @@ 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")
@@ -1536,3 +1537,77 @@ class TestGeneratedCodeDocumentation:
         folder = FolderDef(name="TestFolder", mappings=[mapping])
         code = generate_mapping_code(mapping, folder, "pandas", 1)
         assert "..." in code
+
+
+class TestSourceQualifierNoSources(unittest.TestCase):
+
+    def test_sq_with_no_connected_sources_and_empty_source_map(self):
+        from informatica_python.models import (
+            FolderDef, MappingDef, TransformationDef,
+            InstanceDef, ConnectorDef, FieldDef, TableAttribute,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_orphan_sq",
+            transformations=[
+                TransformationDef(name="SQ_ORPHAN", type="Source Qualifier", fields=[], attributes=[]),
+            ],
+            connectors=[],
+            instances=[
+                InstanceDef(name="SQ_ORPHAN", type="Source Qualifier", transformation_name="SQ_ORPHAN"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", sources=[], targets=[], mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "df_sq_orphan" in code
+        assert "read_file" in code or "read_from_db" in code
+
+    def test_sq_with_no_connectors_but_sources_exist(self):
+        from informatica_python.models import (
+            FolderDef, MappingDef, TransformationDef,
+            InstanceDef, ConnectorDef, FieldDef, TableAttribute,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_disconnect",
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier", fields=[], attributes=[]),
+            ],
+            connectors=[],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", sources=[], targets=[], mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "df_sq_src1" in code
+
+    def test_sq_with_sql_override_no_sources(self):
+        from informatica_python.models import (
+            FolderDef, MappingDef, TransformationDef,
+            InstanceDef, ConnectorDef, FieldDef, TableAttribute,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_sql_only",
+            transformations=[
+                TransformationDef(
+                    name="SQ_SQL",
+                    type="Source Qualifier",
+                    fields=[],
+                    attributes=[TableAttribute(name="Sql Query", value="SELECT * FROM my_table")],
+                ),
+            ],
+            connectors=[],
+            instances=[
+                InstanceDef(name="SQ_SQL", type="Source Qualifier", transformation_name="SQ_SQL"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", sources=[], targets=[], mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "df_sq_sql" in code
+        assert "read_from_db" in code