informatica-python 1.7.0__tar.gz → 1.8.0__tar.gz

{informatica_python-1.7.0 → informatica_python-1.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.7.0
+Version: 1.8.0
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT

{informatica_python-1.7.0 → informatica_python-1.8.0}/informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.7.0"
+__version__ = "1.8.0"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

{informatica_python-1.7.0 → informatica_python-1.8.0}/informatica_python/generators/helper_gen.py

@@ -1278,6 +1278,9 @@ def _add_update_strategy_functions(lines):
     lines.append("        key_columns = data_cols[:1]")
     lines.append("        logger.warning(f'No key columns specified for update strategy — using first column: {key_columns}')")
     lines.append("")
+    lines.append("    db_type = conn_config.get('type', 'mssql')")
+    lines.append("    ph = '?' if db_type == 'mssql' else '%s'")
+    lines.append("")
     lines.append("    try:")
     lines.append("        cursor = conn.cursor()")
     lines.append("")
@@ -1295,8 +1298,8 @@ def _add_update_strategy_functions(lines):
     lines.append("")
     lines.append("        if len(df_update) > 0:")
     lines.append("            non_key_cols = [c for c in data_cols if c not in key_columns]")
-    lines.append("            set_clause = ', '.join(f'{c} = ?' for c in non_key_cols)")
-    lines.append("            where_clause = ' AND '.join(f'{c} = ?' for c in key_columns)")
+    lines.append("            set_clause = ', '.join(f'{c} = {ph}' for c in non_key_cols)")
+    lines.append("            where_clause = ' AND '.join(f'{c} = {ph}' for c in key_columns)")
     lines.append("            update_sql = f'UPDATE {qualified_table} SET {set_clause} WHERE {where_clause}'")
     lines.append("            logger.info(f'Updating {len(df_update)} rows in {qualified_table}')")
     lines.append("            for _, row in df_update.iterrows():")
@@ -1304,7 +1307,7 @@ def _add_update_strategy_functions(lines):
     lines.append("                cursor.execute(update_sql, values)")
     lines.append("")
     lines.append("        if len(df_delete) > 0:")
-    lines.append("            where_clause = ' AND '.join(f'{c} = ?' for c in key_columns)")
+    lines.append("            where_clause = ' AND '.join(f'{c} = {ph}' for c in key_columns)")
     lines.append("            delete_sql = f'DELETE FROM {qualified_table} WHERE {where_clause}'")
     lines.append("            logger.info(f'Deleting {len(df_delete)} rows from {qualified_table}')")
     lines.append("            for _, row in df_delete.iterrows():")

{informatica_python-1.7.0 → informatica_python-1.8.0}/informatica_python/generators/mapping_gen.py

@@ -225,9 +225,12 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
     lines.append(f"Auto-generated by informatica-python")
     lines.append('"""')
     lines.append("")
+    lines.append("import logging")
     lines.append("import numpy as np")
     lines.append("from helper_functions import *")
     lines.append("")
+    lines.append("logger = logging.getLogger(__name__)")
+    lines.append("")
     lines.append("")
 
     inlined_transforms, inlined_connectors, mapplet_instance_names = _inline_mapplets(mapping, folder)
@@ -248,12 +251,41 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
     instance_map = {i.name: i for i in mapping.instances}
     session_overrides = _build_session_conn_overrides(mapping, folder)
 
+    source_names = list(source_map.keys())
+    target_names = list(target_map.keys())
+    tx_summary = []
+    for tx in all_transforms:
+        if tx.type not in ("Source Qualifier", "Application Source Qualifier"):
+            in_flds = [f.name for f in tx.fields if "INPUT" in (f.porttype or "").upper()]
+            out_flds = [f.name for f in tx.fields if "OUTPUT" in (f.porttype or "").upper()]
+            tx_summary.append((tx.name, tx.type, in_flds, out_flds))
+
     lines.append(f"def run_{_safe_name(mapping.name)}(config):")
-    lines.append(f'    """Execute mapping: {mapping.name}"""')
+    lines.append(f'    """')
+    lines.append(f"    Execute mapping: {mapping.name}")
+    if mapping.description:
+        lines.append(f"    Description: {mapping.description}")
+    lines.append(f"")
+    lines.append(f"    Sources: {', '.join(source_names) if source_names else 'None'}")
+    lines.append(f"    Targets: {', '.join(target_names) if target_names else 'None'}")
+    if tx_summary:
+        lines.append(f"")
+        lines.append(f"    Transformation pipeline:")
+        for tx_name, tx_type, in_f, out_f in tx_summary:
+            lines.append(f"      - {tx_name} ({tx_type}): {len(in_f)} input fields -> {len(out_f)} output fields")
+    lines.append(f'    """')
     lines.append(f"    start_time = log_mapping_start('{mapping.name}')")
     lines.append("")
 
-    has_persistent_vars = False
+    has_persistent_vars = any(
+        getattr(v, 'is_persistent', 'NO').upper() == 'YES'
+        for v in (mapping.variables or [])
+    )
+    if has_persistent_vars:
+        lines.append("    # Load persistent state for mapping variables")
+        lines.append("    load_persistent_state()")
+        lines.append("")
+
     if mapping.variables:
         lines.append("    # Mapping Variables")
         for var in mapping.variables:
@@ -318,6 +350,14 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
     for tgt_name, tgt_def in target_map.items():
         _generate_target_write(lines, tgt_name, tgt_def, connector_graph, source_dfs, transform_map, instance_map, session_overrides, validate_casts=validate_casts)
 
+    if has_persistent_vars:
+        lines.append("    # Save persistent mapping variables")
+        for var in mapping.variables:
+            if getattr(var, 'is_persistent', 'NO').upper() == 'YES':
+                safe_var = _safe_name(var.name.replace("$$", ""))
+                lines.append(f"    set_persistent_variable('{mapping.name}', '{safe_var}', {safe_var})")
+        lines.append("    save_persistent_state()")
+
     lines.append("")
     lines.append(f"    log_mapping_end('{mapping.name}', start_time)")
     lines.append(f"    logger.info('Mapping {mapping.name} completed successfully')")
@@ -604,6 +644,7 @@ def _generate_source_qualifier(lines, sq, source_map, source_dfs, connector_grap
             lines.append(f"    df_{sq_safe} = df_{_safe_name(next(iter(connected_sources)))}")
 
     source_dfs[sq.name] = f"df_{sq_safe}"
+    lines.append(f"    logger.info(f'Source {sq.name}: {{len(df_{sq_safe})}} rows read')")
 
     if post_sql:
         lines.append(f"    # Post-SQL")
@@ -633,7 +674,17 @@ def _generate_transformation(lines, tx, connector_graph, source_dfs, transform_m
     if not input_df:
         input_df = "df_input"
 
+    in_fields = [f.name for f in tx.fields if "INPUT" in (f.porttype or "").upper()]
+    out_fields = [f.name for f in tx.fields if "OUTPUT" in (f.porttype or "").upper()]
+    tx_desc = tx.description or ""
+    lines.append(f"    # -------------------------------------------------------------------")
     lines.append(f"    # Transformation: {tx.name} (Type: {tx.type})")
+    if tx_desc:
+        lines.append(f"    # Description: {tx_desc}")
+    lines.append(f"    # Input fields: {', '.join(in_fields[:10])}{' ...' if len(in_fields) > 10 else ''}")
+    lines.append(f"    # Output fields: {', '.join(out_fields[:10])}{' ...' if len(out_fields) > 10 else ''}")
+    lines.append(f"    # -------------------------------------------------------------------")
+    lines.append(f"    _input_rows_{tx_safe} = len({input_df}) if hasattr({input_df}, '__len__') else 0")
 
     if tx_type == "expression":
         _gen_expression_transform(lines, tx, tx_safe, input_df, source_dfs, data_lib)
@@ -673,6 +724,8 @@ def _generate_transformation(lines, tx, connector_graph, source_dfs, transform_m
         lines.append(f"    df_{tx_safe} = {copy_expr}")
         source_dfs[tx.name] = f"df_{tx_safe}"
 
+    lines.append(f"    _output_rows_{tx_safe} = len(df_{tx_safe}) if hasattr(df_{tx_safe}, '__len__') else 0")
+    lines.append(f"    logger.info(f'{tx.name} ({tx.type}): {{_input_rows_{tx_safe}}} input rows -> {{_output_rows_{tx_safe}}} output rows')")
     lines.append("")
 
 
@@ -1230,7 +1283,7 @@ def _gen_stored_proc(lines, tx, tx_safe, input_df, source_dfs):
     lines.append(f"    # Stored Procedure: {proc_name or tx.name}")
 
     if input_params:
-        param_dict_items = ", ".join(f"'{p}': {input_df}['{p}'].iloc[0] if '{p}' in {input_df}.columns else None" for p in input_params)
+        param_dict_items = ", ".join(f"'{p}': {input_df}['{p}'].iloc[0] if '{p}' in {input_df}.columns and len({input_df}) > 0 else None" for p in input_params)
         lines.append(f"    _sp_params_{tx_safe} = {{{param_dict_items}}}")
     else:
         lines.append(f"    _sp_params_{tx_safe} = {{}}")
@@ -1304,6 +1357,8 @@ def _generate_target_write(lines, tgt_name, tgt_def, connector_graph, source_dfs
         target_cols = [f.name for f in tgt_def.fields] if tgt_def.fields else None
         if target_cols:
             lines.append(f"    available_cols = [c for c in {target_cols} if c in df_target_{tgt_safe}.columns]")
+            lines.append(f"    if '_update_strategy' in df_target_{tgt_safe}.columns and '_update_strategy' not in available_cols:")
+            lines.append(f"        available_cols.append('_update_strategy')")
             lines.append(f"    df_target_{tgt_safe} = df_target_{tgt_safe}[available_cols]")
     else:
         lines.append(f"    df_target_{tgt_safe} = {input_df}")
@@ -1337,6 +1392,7 @@ def _generate_target_write(lines, tgt_name, tgt_def, connector_graph, source_dfs
     else:
         lines.append(f"    write_file(df_target_{tgt_safe}, config.get('targets', {{}}).get('{tgt_def.name}', {{}}).get('file_path', '{tgt_def.name}'),")
         lines.append(f"              config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
+    lines.append(f"    logger.info(f'Target {tgt_def.name}: {{len(df_target_{tgt_safe})}} rows written')")
 
 
 CAST_MAP = {

{informatica_python-1.7.0 → informatica_python-1.8.0}/informatica_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.7.0
+Version: 1.8.0
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT

{informatica_python-1.7.0 → informatica_python-1.8.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "informatica-python"
-version = "1.7.0"
+version = "1.8.0"
 description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
 readme = "README.md"
 license = {text = "MIT"}

{informatica_python-1.7.0 → informatica_python-1.8.0}/tests/test_integration.py

@@ -946,6 +946,31 @@ class TestUpdateStrategy:
         assert "write_to_db" in code
         assert "_update_strategy" in code
 
+    def test_update_strategy_preserved_through_projection(self):
+        from informatica_python.models import TargetDef, FieldDef
+        from informatica_python.generators.mapping_gen import _generate_target_write
+        tgt = TargetDef(name="TGT_DB", database_type="Oracle",
+                        fields=[FieldDef(name="ID", datatype="integer"),
+                                FieldDef(name="VAL", datatype="string")])
+        lines = []
+        source_dfs = {"SRC": "df_src"}
+        from informatica_python.models import ConnectorDef
+        conns = [ConnectorDef(from_instance="SRC", to_instance="TGT_DB",
+                              from_instance_type="", to_instance_type="",
+                              from_field="ID", to_field="ID")]
+        connector_graph = {"to": {"TGT_DB": conns}, "from": {"SRC": conns}}
+        _generate_target_write(lines, "TGT_DB", tgt, connector_graph, source_dfs, {}, {})
+        code = "\n".join(lines)
+        assert "_update_strategy" in code
+        assert "available_cols.append('_update_strategy')" in code
+
+    def test_update_strategy_dialect_aware_placeholders(self):
+        from informatica_python.models import FolderDef
+        from informatica_python.generators.helper_gen import generate_helper_functions
+        folder = FolderDef(name="TestFolder")
+        code = generate_helper_functions(folder)
+        assert "ph = '?' if db_type == 'mssql' else '%s'" in code
+
     def test_update_strategy_helper_generated(self):
         from informatica_python.models import FolderDef
         from informatica_python.generators.helper_gen import generate_helper_functions
@@ -1064,8 +1089,8 @@ class TestStatePersistence:
                                                      default_value="''", is_persistent="NO")])
         folder = FolderDef(name="TestFolder", workflows=[wf])
         code = generate_workflow_code(folder)
-        assert "load_persistent_state" not in code or "import" in code
-        assert "save_persistent_state" not in code or "import" in code
+        assert "load_persistent_state()" not in code
+        assert "save_persistent_state()" not in code
 
     def test_mapping_persistent_variables(self):
         from informatica_python.models import (
@@ -1091,6 +1116,9 @@ class TestStatePersistence:
         code = generate_mapping_code(mapping, folder, "pandas", 1)
         assert "get_persistent_variable('m_persist_test', 'last_id'" in code
         assert "temp = ''" in code
+        assert "load_persistent_state()" in code
+        assert "set_persistent_variable('m_persist_test', 'last_id'" in code
+        assert "save_persistent_state()" in code
 
     def test_workflow_persistent_imports(self):
         from informatica_python.models import FolderDef, WorkflowDef, WorkflowVariable
@@ -1110,3 +1138,401 @@ class TestStatePersistence:
         assert "json.load" in code
         assert "json.dump" in code
         assert "persistent_state.json" in code
+
+
+class TestLoggingEnrichment:
+
+    def test_mapping_imports_logging(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_log_test",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP_TEST", type="Expression",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_TEST", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP_TEST", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP_TEST", type="Expression", transformation_name="EXP_TEST"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "import logging" in code
+        assert "logger = logging.getLogger(__name__)" in code
+
+    def test_source_row_count_logging(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_log_src",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "logger.info(f'Source SQ_SRC1:" in code
+        assert "rows read" in code
+
+    def test_transform_row_count_logging(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_log_tx",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="FIL_ACTIVE", type="Filter",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")],
+                                  attributes=[]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="FIL_ACTIVE", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="FIL_ACTIVE", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="FIL_ACTIVE", type="Filter", transformation_name="FIL_ACTIVE"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "_input_rows_fil_active = len(" in code
+        assert "_output_rows_fil_active = len(df_fil_active)" in code
+        assert "FIL_ACTIVE (Filter):" in code
+        assert "input rows ->" in code
+        assert "output rows" in code
+
+    def test_target_row_count_logging(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_log_tgt",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "logger.info(f'Target TGT1:" in code
+        assert "rows written" in code
+
+    def test_input_output_rows_multiple_transforms(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_log_multi",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="VAL", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="VAL", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP1", type="Expression",
+                                  fields=[FieldDef(name="VAL", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="SRT1", type="Sorter",
+                                  fields=[FieldDef(name="VAL", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP1", from_field="VAL", to_field="VAL", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP1", to_instance="SRT1", from_field="VAL", to_field="VAL", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SRT1", to_instance="TGT1", from_field="VAL", to_field="VAL", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP1", type="Expression", transformation_name="EXP1"),
+                InstanceDef(name="SRT1", type="Sorter", transformation_name="SRT1"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "_input_rows_exp1" in code
+        assert "_output_rows_exp1" in code
+        assert "_input_rows_srt1" in code
+        assert "_output_rows_srt1" in code
+        assert code.count("logger.info") >= 4
+
+
+class TestGeneratedCodeDocumentation:
+
+    def test_mapping_docstring_sources_targets(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_doc_test",
+            description="Load customer data from staging to warehouse",
+            sources=[SourceDef(name="SRC_CUST", database_type="Flat File")],
+            targets=[TargetDef(name="TGT_CUST", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC_CUST", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC_CUST", to_instance="SQ_SRC_CUST", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC_CUST", to_instance="TGT_CUST", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC_CUST", type="Source Definition", transformation_name="SRC_CUST"),
+                InstanceDef(name="TGT_CUST", type="Target Definition", transformation_name="TGT_CUST"),
+                InstanceDef(name="SQ_SRC_CUST", type="Source Qualifier", transformation_name="SQ_SRC_CUST"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "Execute mapping: m_doc_test" in code
+        assert "Load customer data from staging to warehouse" in code
+        assert "Sources: SRC_CUST" in code
+        assert "Targets: TGT_CUST" in code
+
+    def test_mapping_docstring_transform_pipeline(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_doc_pipeline",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP_CALC", type="Expression",
+                                  fields=[
+                                      FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT"),
+                                      FieldDef(name="TOTAL", datatype="decimal", porttype="OUTPUT"),
+                                  ]),
+                TransformationDef(name="FIL_VALID", type="Filter",
+                                  fields=[
+                                      FieldDef(name="ID", datatype="integer", porttype="INPUT"),
+                                      FieldDef(name="TOTAL", datatype="decimal", porttype="INPUT/OUTPUT"),
+                                  ],
+                                  attributes=[]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_CALC", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP_CALC", to_instance="FIL_VALID", from_field="TOTAL", to_field="TOTAL", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="FIL_VALID", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP_CALC", type="Expression", transformation_name="EXP_CALC"),
+                InstanceDef(name="FIL_VALID", type="Filter", transformation_name="FIL_VALID"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "Transformation pipeline:" in code
+        assert "EXP_CALC (Expression):" in code
+        assert "FIL_VALID (Filter):" in code
+        assert "input fields ->" in code
+        assert "output fields" in code
+
+    def test_transform_field_documentation(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_doc_fields",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT"),
+                                          FieldDef(name="NAME", datatype="string", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP_UPPER", type="Expression",
+                                  description="Uppercase the name field",
+                                  fields=[
+                                      FieldDef(name="ID", datatype="integer", porttype="INPUT"),
+                                      FieldDef(name="NAME", datatype="string", porttype="INPUT"),
+                                      FieldDef(name="NAME_UPPER", datatype="string", porttype="OUTPUT", expression="UPPER(NAME)"),
+                                  ]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_UPPER", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_UPPER", from_field="NAME", to_field="NAME", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP_UPPER", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP_UPPER", type="Expression", transformation_name="EXP_UPPER"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "# Input fields: ID, NAME" in code
+        assert "# Output fields: NAME_UPPER" in code
+        assert "# Description: Uppercase the name field" in code
+
+    def test_transform_description_comment(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_doc_desc",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="AGG_TOTALS", type="Aggregator",
+                                  description="Calculate regional totals",
+                                  fields=[
+                                      FieldDef(name="REGION", datatype="string", porttype="INPUT/OUTPUT"),
+                                      FieldDef(name="TOTAL", datatype="decimal", porttype="OUTPUT", expression="SUM(AMOUNT)"),
+                                  ]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="AGG_TOTALS", from_field="ID", to_field="REGION", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="AGG_TOTALS", to_instance="TGT1", from_field="REGION", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="AGG_TOTALS", type="Aggregator", transformation_name="AGG_TOTALS"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "# Description: Calculate regional totals" in code
+        assert "# ---" in code
+
+    def test_no_description_no_desc_line(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        mapping = MappingDef(
+            name="m_doc_nodesc",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP_PASS", type="Expression",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_PASS", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP_PASS", to_instance="TGT1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP_PASS", type="Expression", transformation_name="EXP_PASS"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        lines = code.split('\n')
+        desc_lines = [l for l in lines if '# Description:' in l]
+        for dl in desc_lines:
+            assert dl.strip() != "# Description:"
+
+    def test_field_list_truncation(self):
+        from informatica_python.models import (
+            MappingDef, FolderDef, TransformationDef, ConnectorDef,
+            FieldDef, SourceDef, TargetDef, InstanceDef,
+        )
+        from informatica_python.generators.mapping_gen import generate_mapping_code
+        many_fields = [FieldDef(name=f"F{i}", datatype="string", porttype="INPUT/OUTPUT") for i in range(15)]
+        mapping = MappingDef(
+            name="m_doc_many",
+            sources=[SourceDef(name="SRC1", database_type="Flat File")],
+            targets=[TargetDef(name="TGT1", database_type="Flat File", fields=[FieldDef(name="ID", datatype="integer")])],
+            transformations=[
+                TransformationDef(name="SQ_SRC1", type="Source Qualifier",
+                                  fields=[FieldDef(name="ID", datatype="integer", porttype="INPUT/OUTPUT")]),
+                TransformationDef(name="EXP_MANY", type="Expression", fields=many_fields),
+            ],
+            connectors=[
+                ConnectorDef(from_instance="SRC1", to_instance="SQ_SRC1", from_field="ID", to_field="ID", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="SQ_SRC1", to_instance="EXP_MANY", from_field="ID", to_field="F0", from_instance_type="", to_instance_type=""),
+                ConnectorDef(from_instance="EXP_MANY", to_instance="TGT1", from_field="F0", to_field="ID", from_instance_type="", to_instance_type=""),
+            ],
+            instances=[
+                InstanceDef(name="SRC1", type="Source Definition", transformation_name="SRC1"),
+                InstanceDef(name="TGT1", type="Target Definition", transformation_name="TGT1"),
+                InstanceDef(name="SQ_SRC1", type="Source Qualifier", transformation_name="SQ_SRC1"),
+                InstanceDef(name="EXP_MANY", type="Expression", transformation_name="EXP_MANY"),
+            ],
+        )
+        folder = FolderDef(name="TestFolder", mappings=[mapping])
+        code = generate_mapping_code(mapping, folder, "pandas", 1)
+        assert "..." in code