informatica-python 1.4.0__tar.gz → 1.4.2__tar.gz

informatica_python-1.4.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Nick
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

informatica_python-1.4.2/PKG-INFO

@@ -0,0 +1,228 @@
+Metadata-Version: 2.4
+Name: informatica-python
+Version: 1.4.2
+Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
+Author: Nick
+License: MIT
+Keywords: informatica,powercenter,etl,code-generator,pandas,pyspark,data-engineering
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Code Generators
+Classifier: Topic :: Database :: Database Engines/Servers
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lxml>=4.9.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Dynamic: license-file
+
+# informatica-python
+
+Convert Informatica PowerCenter workflow XML exports into clean, runnable Python/PySpark code.
+
+**Author:** Nick
+**License:** MIT
+**PyPI:** [informatica-python](https://pypi.org/project/informatica-python/)
+
+---
+
+## Overview
+
+`informatica-python` parses Informatica PowerCenter XML export files and generates equivalent Python code using your choice of data library. It handles all 72 DTD tags from the PowerCenter XML schema and produces a complete, ready-to-run Python project.
+
+## Installation
+
+```bash
+pip install informatica-python
+```
+
+## Quick Start
+
+### Command Line
+
+```bash
+# Generate Python files to a directory
+informatica-python workflow_export.xml -o output_dir
+
+# Generate as a zip archive
+informatica-python workflow_export.xml -z output.zip
+
+# Use a different data library
+informatica-python workflow_export.xml -o output_dir --data-lib polars
+
+# Parse to JSON only (no code generation)
+informatica-python workflow_export.xml --json
+
+# Save parsed JSON to file
+informatica-python workflow_export.xml --json-file parsed.json
+```
+
+### Python API
+
+```python
+from informatica_python import InformaticaConverter
+
+converter = InformaticaConverter()
+
+# Parse and generate files
+converter.convert_to_files("workflow_export.xml", "output_dir")
+
+# Parse and generate zip
+converter.convert_to_zip("workflow_export.xml", "output.zip")
+
+# Parse to structured dict
+result = converter.parse_file("workflow_export.xml")
+
+# Use a different data library
+converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars")
+```
+
+## Generated Output Files
+
+| File | Description |
+|------|-------------|
+| `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions) |
+| `mapping_N.py` | One per mapping — transformation logic, source reads, target writes |
+| `workflow.py` | Task orchestration with topological ordering 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 |
+| `error_log.txt` | Conversion summary, warnings, and unsupported feature notes |
+
+## Supported Data Libraries
+
+Select via `--data-lib` CLI flag or `data_lib` parameter:
+
+| Library | Flag | Best For |
+|---------|------|----------|
+| **pandas** | `pandas` (default) | General-purpose, most compatible |
+| **dask** | `dask` | Large datasets, parallel processing |
+| **polars** | `polars` | High performance, Rust-backed |
+| **vaex** | `vaex` | Out-of-core, billion-row datasets |
+| **modin** | `modin` | Drop-in pandas replacement, multi-core |
+
+## Supported Transformations
+
+The code generator produces real, runnable Python for these transformation types:
+
+- **Source Qualifier** — SQL override, pre/post SQL, column selection
+- **Expression** — Field-level expressions converted to pandas operations
+- **Filter** — Row filtering with converted conditions
+- **Joiner** — `pd.merge()` with join type and condition parsing
+- **Lookup** — `pd.merge()` lookups with connection-aware DB/file reads
+- **Aggregator** — `groupby().agg()` with SUM/COUNT/AVG/MIN/MAX/FIRST/LAST
+- **Sorter** — `sort_values()` with multi-key ascending/descending
+- **Router** — Multi-group conditional routing with if/elif/else
+- **Union** — `pd.concat()` across multiple input groups
+- **Update Strategy** — Insert/Update/Delete/Reject flag generation
+- **Sequence Generator** — Auto-incrementing ID columns
+- **Normalizer** — `pd.melt()` with auto-detected id/value vars
+- **Rank** — `groupby().rank()` with Top-N filtering
+- **Stored Procedure** — Stub generation with SP name and parameters
+- **Transaction Control** — Commit/rollback logic stubs
+- **Custom / Java** — Placeholder stubs with TODO markers
+- **SQL Transform** — Direct SQL execution pass-through
+
+## Supported XML Tags (72 Tags)
+
+**Top-level:** POWERMART, REPOSITORY, FOLDER, FOLDERVERSION
+
+**Source/Target:** SOURCE, SOURCEFIELD, TARGET, TARGETFIELD, TARGETINDEX, TARGETINDEXFIELD, FLATFILE, XMLINFO, XMLTEXT, GROUP, TABLEATTRIBUTE, FIELDATTRIBUTE, METADATAEXTENSION, KEYWORD, ERPSRCINFO
+
+**Mapping/Mapplet:** MAPPING, MAPPLET, TRANSFORMATION, TRANSFORMFIELD, TRANSFORMFIELDATTR, TRANSFORMFIELDATTRDEF, INSTANCE, ASSOCIATED_SOURCE_INSTANCE, CONNECTOR, MAPDEPENDENCY, TARGETLOADORDER, MAPPINGVARIABLE, FIELDDEPENDENCY, INITPROP, ERPINFO
+
+**Task/Session/Workflow:** TASK, TIMER, VALUEPAIR, SCHEDULER, SCHEDULEINFO, STARTOPTIONS, ENDOPTIONS, SCHEDULEOPTIONS, RECURRING, CUSTOM, DAILYFREQUENCY, REPEAT, FILTER, SESSION, CONFIGREFERENCE, SESSTRANSFORMATIONINST, SESSTRANSFORMATIONGROUP, PARTITION, HASHKEY, KEYRANGE, CONFIG, SESSIONCOMPONENT, CONNECTIONREFERENCE, TASKINSTANCE, WORKFLOWLINK, WORKFLOWVARIABLE, WORKFLOWEVENT, WORKLET, WORKFLOW, ATTRIBUTE
+
+**Shortcut:** SHORTCUT
+
+**SAP:** SAPFUNCTION, SAPSTRUCTURE, SAPPROGRAM, SAPOUTPUTPORT, SAPVARIABLE, SAPPROGRAMFLOWOBJECT, SAPTABLEPARAM
+
+## Key Features
+
+### Session Connection Overrides (v1.4+)
+When sessions define per-transform connection overrides (different database, file directory, or filename), the generated code uses those overrides instead of source/target defaults.
+
+### Worklet Support (v1.4+)
+Worklet workflows are detected and generate separate `run_worklet_NAME(config)` functions. The main workflow calls these automatically for Worklet task types.
+
+### Type Casting at Target Writes (v1.4+)
+Target field datatypes are mapped to pandas types and generate proper casting code:
+- Integers: nullable `Int64`/`Int32` or `fillna(0).astype(int)` for NOT NULL
+- Dates: `pd.to_datetime(errors='coerce')`
+- Decimals/Floats: `pd.to_numeric(errors='coerce')`
+- Booleans: `.astype('boolean')`
+
+### Flat File Handling (v1.3+)
+Parses FLATFILE metadata for delimiter, fixed-width, header lines, skip rows, quote/escape chars. Generates `pd.read_fwf()` for fixed-width or enriched `read_file()` for delimited.
+
+### Mapplet Inlining (v1.3+)
+Expands Mapplet instances into prefixed transforms, rewires connectors, and eliminates duplication.
+
+### Decision Tasks (v1.3+)
+Converts Informatica decision conditions to Python if/else branches with proper variable substitution.
+
+### Expression Converter (80+ Functions)
+
+Converts Informatica expressions to Python equivalents:
+
+- **String:** SUBSTR, LTRIM, RTRIM, UPPER, LOWER, LPAD, RPAD, INSTR, LENGTH, CONCAT, REPLACE, REG_EXTRACT, REG_REPLACE, REVERSE, INITCAP, CHR, ASCII
+- **Date:** ADD_TO_DATE, DATE_DIFF, GET_DATE_PART, SYSDATE, SYSTIMESTAMP, TO_DATE, TO_CHAR, TRUNC (date)
+- **Numeric:** ROUND, TRUNC, MOD, ABS, CEIL, FLOOR, POWER, SQRT, LOG, EXP, SIGN
+- **Conversion:** TO_INTEGER, TO_BIGINT, TO_FLOAT, TO_DECIMAL, TO_CHAR, TO_DATE
+- **Null handling:** IIF, DECODE, NVL, NVL2, ISNULL, IS_SPACES, IS_NUMBER
+- **Aggregate:** SUM, AVG, COUNT, MIN, MAX, FIRST, LAST, MEDIAN, STDDEV, VARIANCE
+- **Lookup:** :LKP expressions with dynamic lookup references
+- **Variable:** SETVARIABLE / mapping variable assignment
+
+## Requirements
+
+- Python >= 3.8
+- lxml >= 4.9.0
+- PyYAML >= 6.0
+
+## Changelog
+
+### v1.4.x (Phase 3)
+- Session connection overrides for sources and targets
+- Worklet function generation with safe invocation
+- Type casting at target writes based on TARGETFIELD datatypes
+- Flat-file session path overrides properly wired
+
+### v1.3.x (Phase 2)
+- FLATFILE metadata in source reads and target writes
+- Normalizer with `pd.melt()`
+- Rank with group-by and Top-N filtering
+- Decision tasks with real if/else branches
+- Mapplet instance inlining
+
+### v1.2.x (Phase 1)
+- Core parser for all 72 XML tags
+- Expression converter with 80+ functions
+- Aggregator, Joiner, Lookup code generation
+- Workflow orchestration with topological task ordering
+- Multi-library support (pandas, dask, polars, vaex, modin)
+
+## Development
+
+```bash
+# Clone and install in development mode
+cd informatica_python
+pip install -e ".[dev]"
+
+# Run tests (25 tests)
+pytest tests/test_converter.py -v
+```
+
+## License
+
+MIT License - Copyright (c) 2025 Nick
+
+See [LICENSE](LICENSE) for details.

informatica_python-1.4.2/README.md

@@ -0,0 +1,201 @@
+# informatica-python
+
+Convert Informatica PowerCenter workflow XML exports into clean, runnable Python/PySpark code.
+
+**Author:** Nick
+**License:** MIT
+**PyPI:** [informatica-python](https://pypi.org/project/informatica-python/)
+
+---
+
+## Overview
+
+`informatica-python` parses Informatica PowerCenter XML export files and generates equivalent Python code using your choice of data library. It handles all 72 DTD tags from the PowerCenter XML schema and produces a complete, ready-to-run Python project.
+
+## Installation
+
+```bash
+pip install informatica-python
+```
+
+## Quick Start
+
+### Command Line
+
+```bash
+# Generate Python files to a directory
+informatica-python workflow_export.xml -o output_dir
+
+# Generate as a zip archive
+informatica-python workflow_export.xml -z output.zip
+
+# Use a different data library
+informatica-python workflow_export.xml -o output_dir --data-lib polars
+
+# Parse to JSON only (no code generation)
+informatica-python workflow_export.xml --json
+
+# Save parsed JSON to file
+informatica-python workflow_export.xml --json-file parsed.json
+```
+
+### Python API
+
+```python
+from informatica_python import InformaticaConverter
+
+converter = InformaticaConverter()
+
+# Parse and generate files
+converter.convert_to_files("workflow_export.xml", "output_dir")
+
+# Parse and generate zip
+converter.convert_to_zip("workflow_export.xml", "output.zip")
+
+# Parse to structured dict
+result = converter.parse_file("workflow_export.xml")
+
+# Use a different data library
+converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars")
+```
+
+## Generated Output Files
+
+| File | Description |
+|------|-------------|
+| `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions) |
+| `mapping_N.py` | One per mapping — transformation logic, source reads, target writes |
+| `workflow.py` | Task orchestration with topological ordering 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 |
+| `error_log.txt` | Conversion summary, warnings, and unsupported feature notes |
+
+## Supported Data Libraries
+
+Select via `--data-lib` CLI flag or `data_lib` parameter:
+
+| Library | Flag | Best For |
+|---------|------|----------|
+| **pandas** | `pandas` (default) | General-purpose, most compatible |
+| **dask** | `dask` | Large datasets, parallel processing |
+| **polars** | `polars` | High performance, Rust-backed |
+| **vaex** | `vaex` | Out-of-core, billion-row datasets |
+| **modin** | `modin` | Drop-in pandas replacement, multi-core |
+
+## Supported Transformations
+
+The code generator produces real, runnable Python for these transformation types:
+
+- **Source Qualifier** — SQL override, pre/post SQL, column selection
+- **Expression** — Field-level expressions converted to pandas operations
+- **Filter** — Row filtering with converted conditions
+- **Joiner** — `pd.merge()` with join type and condition parsing
+- **Lookup** — `pd.merge()` lookups with connection-aware DB/file reads
+- **Aggregator** — `groupby().agg()` with SUM/COUNT/AVG/MIN/MAX/FIRST/LAST
+- **Sorter** — `sort_values()` with multi-key ascending/descending
+- **Router** — Multi-group conditional routing with if/elif/else
+- **Union** — `pd.concat()` across multiple input groups
+- **Update Strategy** — Insert/Update/Delete/Reject flag generation
+- **Sequence Generator** — Auto-incrementing ID columns
+- **Normalizer** — `pd.melt()` with auto-detected id/value vars
+- **Rank** — `groupby().rank()` with Top-N filtering
+- **Stored Procedure** — Stub generation with SP name and parameters
+- **Transaction Control** — Commit/rollback logic stubs
+- **Custom / Java** — Placeholder stubs with TODO markers
+- **SQL Transform** — Direct SQL execution pass-through
+
+## Supported XML Tags (72 Tags)
+
+**Top-level:** POWERMART, REPOSITORY, FOLDER, FOLDERVERSION
+
+**Source/Target:** SOURCE, SOURCEFIELD, TARGET, TARGETFIELD, TARGETINDEX, TARGETINDEXFIELD, FLATFILE, XMLINFO, XMLTEXT, GROUP, TABLEATTRIBUTE, FIELDATTRIBUTE, METADATAEXTENSION, KEYWORD, ERPSRCINFO
+
+**Mapping/Mapplet:** MAPPING, MAPPLET, TRANSFORMATION, TRANSFORMFIELD, TRANSFORMFIELDATTR, TRANSFORMFIELDATTRDEF, INSTANCE, ASSOCIATED_SOURCE_INSTANCE, CONNECTOR, MAPDEPENDENCY, TARGETLOADORDER, MAPPINGVARIABLE, FIELDDEPENDENCY, INITPROP, ERPINFO
+
+**Task/Session/Workflow:** TASK, TIMER, VALUEPAIR, SCHEDULER, SCHEDULEINFO, STARTOPTIONS, ENDOPTIONS, SCHEDULEOPTIONS, RECURRING, CUSTOM, DAILYFREQUENCY, REPEAT, FILTER, SESSION, CONFIGREFERENCE, SESSTRANSFORMATIONINST, SESSTRANSFORMATIONGROUP, PARTITION, HASHKEY, KEYRANGE, CONFIG, SESSIONCOMPONENT, CONNECTIONREFERENCE, TASKINSTANCE, WORKFLOWLINK, WORKFLOWVARIABLE, WORKFLOWEVENT, WORKLET, WORKFLOW, ATTRIBUTE
+
+**Shortcut:** SHORTCUT
+
+**SAP:** SAPFUNCTION, SAPSTRUCTURE, SAPPROGRAM, SAPOUTPUTPORT, SAPVARIABLE, SAPPROGRAMFLOWOBJECT, SAPTABLEPARAM
+
+## Key Features
+
+### Session Connection Overrides (v1.4+)
+When sessions define per-transform connection overrides (different database, file directory, or filename), the generated code uses those overrides instead of source/target defaults.
+
+### Worklet Support (v1.4+)
+Worklet workflows are detected and generate separate `run_worklet_NAME(config)` functions. The main workflow calls these automatically for Worklet task types.
+
+### Type Casting at Target Writes (v1.4+)
+Target field datatypes are mapped to pandas types and generate proper casting code:
+- Integers: nullable `Int64`/`Int32` or `fillna(0).astype(int)` for NOT NULL
+- Dates: `pd.to_datetime(errors='coerce')`
+- Decimals/Floats: `pd.to_numeric(errors='coerce')`
+- Booleans: `.astype('boolean')`
+
+### Flat File Handling (v1.3+)
+Parses FLATFILE metadata for delimiter, fixed-width, header lines, skip rows, quote/escape chars. Generates `pd.read_fwf()` for fixed-width or enriched `read_file()` for delimited.
+
+### Mapplet Inlining (v1.3+)
+Expands Mapplet instances into prefixed transforms, rewires connectors, and eliminates duplication.
+
+### Decision Tasks (v1.3+)
+Converts Informatica decision conditions to Python if/else branches with proper variable substitution.
+
+### Expression Converter (80+ Functions)
+
+Converts Informatica expressions to Python equivalents:
+
+- **String:** SUBSTR, LTRIM, RTRIM, UPPER, LOWER, LPAD, RPAD, INSTR, LENGTH, CONCAT, REPLACE, REG_EXTRACT, REG_REPLACE, REVERSE, INITCAP, CHR, ASCII
+- **Date:** ADD_TO_DATE, DATE_DIFF, GET_DATE_PART, SYSDATE, SYSTIMESTAMP, TO_DATE, TO_CHAR, TRUNC (date)
+- **Numeric:** ROUND, TRUNC, MOD, ABS, CEIL, FLOOR, POWER, SQRT, LOG, EXP, SIGN
+- **Conversion:** TO_INTEGER, TO_BIGINT, TO_FLOAT, TO_DECIMAL, TO_CHAR, TO_DATE
+- **Null handling:** IIF, DECODE, NVL, NVL2, ISNULL, IS_SPACES, IS_NUMBER
+- **Aggregate:** SUM, AVG, COUNT, MIN, MAX, FIRST, LAST, MEDIAN, STDDEV, VARIANCE
+- **Lookup:** :LKP expressions with dynamic lookup references
+- **Variable:** SETVARIABLE / mapping variable assignment
+
+## Requirements
+
+- Python >= 3.8
+- lxml >= 4.9.0
+- PyYAML >= 6.0
+
+## Changelog
+
+### v1.4.x (Phase 3)
+- Session connection overrides for sources and targets
+- Worklet function generation with safe invocation
+- Type casting at target writes based on TARGETFIELD datatypes
+- Flat-file session path overrides properly wired
+
+### v1.3.x (Phase 2)
+- FLATFILE metadata in source reads and target writes
+- Normalizer with `pd.melt()`
+- Rank with group-by and Top-N filtering
+- Decision tasks with real if/else branches
+- Mapplet instance inlining
+
+### v1.2.x (Phase 1)
+- Core parser for all 72 XML tags
+- Expression converter with 80+ functions
+- Aggregator, Joiner, Lookup code generation
+- Workflow orchestration with topological task ordering
+- Multi-library support (pandas, dask, polars, vaex, modin)
+
+## Development
+
+```bash
+# Clone and install in development mode
+cd informatica_python
+pip install -e ".[dev]"
+
+# Run tests (25 tests)
+pytest tests/test_converter.py -v
+```
+
+## License
+
+MIT License - Copyright (c) 2025 Nick
+
+See [LICENSE](LICENSE) for details.

informatica_python-1.4.2/informatica_python/__init__.py

@@ -0,0 +1,13 @@
+"""
+informatica-python: Convert Informatica PowerCenter workflow XML to Python/PySpark code.
+
+Copyright (c) 2025 Nick. All rights reserved.
+Licensed under the MIT License.
+"""
+
+from informatica_python.converter import InformaticaConverter
+
+__version__ = "1.4.2"
+__author__ = "Nick"
+__license__ = "MIT"
+__all__ = ["InformaticaConverter"]

{informatica_python-1.4.0 → informatica_python-1.4.2}/informatica_python/generators/mapping_gen.py

@@ -247,7 +247,7 @@ def generate_mapping_code(mapping: MappingDef, folder: FolderDef,
                 lines.append(f"    _src_path_{safe} = config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path',")
                 lines.append(f"        os.path.join('{src_dir}', '{src_file}'))")
                 if src_def.flatfile:
-                    _emit_flatfile_read(lines, safe, src_def)
+                    _emit_flatfile_read(lines, safe, src_def, file_path_override=True)
                 else:
                     lines.append(f"    df_{safe} = read_file(_src_path_{safe}, config.get('sources', {{}}).get('{src_def.name}', {{}}))")
             elif src_def.database_type and src_def.database_type != "Flat File":
@@ -323,15 +323,16 @@ def _flatfile_config_dict(ff):
     return cfg
 
 
-def _emit_flatfile_read(lines, var_name, src_def, indent="    "):
+def _emit_flatfile_read(lines, var_name, src_def, indent="    ", file_path_override=None):
     ff = src_def.flatfile
     fc = _flatfile_config_dict(ff)
+    default_path = f"_src_path_{var_name}" if file_path_override else f"config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}')"
     if fc.get("fixed_width"):
         widths = []
         for fld in src_def.fields:
             widths.append(fld.precision if fld.precision else 10)
         lines.append(f"{indent}df_{var_name} = pd.read_fwf(")
-        lines.append(f"{indent}    config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
+        lines.append(f"{indent}    {default_path},")
         lines.append(f"{indent}    widths={widths},")
         hdr = fc.get("header_lines", 0)
         if hdr:
@@ -367,15 +368,22 @@ def _emit_flatfile_read(lines, var_name, src_def, indent="    "):
     if file_cfg:
         lines.append(f"{indent}ff_cfg_{var_name} = {repr(file_cfg)}")
         lines.append(f"{indent}ff_cfg_{var_name}.update(config.get('sources', {{}}).get('{src_def.name}', {{}}))")
-        lines.append(f"{indent}df_{var_name} = read_file(ff_cfg_{var_name}.get('file_path', '{src_def.name}'), ff_cfg_{var_name})")
+        if file_path_override:
+            lines.append(f"{indent}df_{var_name} = read_file({default_path}, ff_cfg_{var_name})")
+        else:
+            lines.append(f"{indent}df_{var_name} = read_file(ff_cfg_{var_name}.get('file_path', '{src_def.name}'), ff_cfg_{var_name})")
     else:
-        lines.append(f"{indent}df_{var_name} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
-        lines.append(f"{indent}                          config.get('sources', {{}}).get('{src_def.name}', {{}}))")
+        if file_path_override:
+            lines.append(f"{indent}df_{var_name} = read_file({default_path}, config.get('sources', {{}}).get('{src_def.name}', {{}}))")
+        else:
+            lines.append(f"{indent}df_{var_name} = read_file(config.get('sources', {{}}).get('{src_def.name}', {{}}).get('file_path', '{src_def.name}'),")
+            lines.append(f"{indent}                          config.get('sources', {{}}).get('{src_def.name}', {{}}))")
 
 
-def _emit_flatfile_write(lines, var_name, tgt_def, indent="    "):
+def _emit_flatfile_write(lines, var_name, tgt_def, indent="    ", file_path_override=None):
     ff = tgt_def.flatfile
     fc = _flatfile_config_dict(ff)
+    default_path = f"_tgt_path_{var_name}" if file_path_override else f"config.get('targets', {{}}).get('{tgt_def.name}', {{}}).get('file_path', '{tgt_def.name}')"
     file_cfg = {}
     if "delimiter" in fc:
         file_cfg["delimiter"] = fc["delimiter"]
@@ -387,10 +395,16 @@ def _emit_flatfile_write(lines, var_name, tgt_def, indent="    "):
     if file_cfg:
         lines.append(f"{indent}ff_cfg_{var_name} = {repr(file_cfg)}")
         lines.append(f"{indent}ff_cfg_{var_name}.update(config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
-        lines.append(f"{indent}write_file(df_target_{var_name}, ff_cfg_{var_name}.get('file_path', '{tgt_def.name}'), ff_cfg_{var_name})")
+        if file_path_override:
+            lines.append(f"{indent}write_file(df_target_{var_name}, {default_path}, ff_cfg_{var_name})")
+        else:
+            lines.append(f"{indent}write_file(df_target_{var_name}, ff_cfg_{var_name}.get('file_path', '{tgt_def.name}'), ff_cfg_{var_name})")
     else:
-        lines.append(f"{indent}write_file(df_target_{var_name}, config.get('targets', {{}}).get('{tgt_def.name}', {{}}).get('file_path', '{tgt_def.name}'),")
-        lines.append(f"{indent}          config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
+        if file_path_override:
+            lines.append(f"{indent}write_file(df_target_{var_name}, {default_path}, config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
+        else:
+            lines.append(f"{indent}write_file(df_target_{var_name}, config.get('targets', {{}}).get('{tgt_def.name}', {{}}).get('file_path', '{tgt_def.name}'),")
+            lines.append(f"{indent}          config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
 
 
 def _build_source_map(mapping, folder):
@@ -1202,7 +1216,7 @@ def _generate_target_write(lines, tgt_name, tgt_def, connector_graph, source_dfs
         lines.append(f"    _tgt_path_{tgt_safe} = config.get('targets', {{}}).get('{tgt_def.name}', {{}}).get('file_path',")
         lines.append(f"        os.path.join('{out_dir}', '{out_file}'))")
         if tgt_def.flatfile:
-            _emit_flatfile_write(lines, tgt_safe, tgt_def)
+            _emit_flatfile_write(lines, tgt_safe, tgt_def, file_path_override=True)
         else:
             lines.append(f"    write_file(df_target_{tgt_safe}, _tgt_path_{tgt_safe}, config.get('targets', {{}}).get('{tgt_def.name}', {{}}))")
     elif tgt_def.database_type and tgt_def.database_type != "Flat File":

{informatica_python-1.4.0 → informatica_python-1.4.2}/informatica_python/generators/workflow_gen.py

@@ -195,10 +195,11 @@ def _emit_task_code(lines, task, mapping_name_map, session_to_mapping, wf, workl
         lines.append(f"        logger.info('Executing worklet: {task.name}')")
         if matched_worklet:
             lines.append(f"        worklet_result_{task_safe} = run_worklet_{worklet_safe}(config)")
+            lines.append(f"        if not worklet_result_{task_safe}:")
+            lines.append(f"            raise RuntimeError('Worklet {worklet_name} returned failure')")
         else:
-            lines.append(f"        worklet_result_{task_safe} = run_worklet_{worklet_safe}(config)")
-        lines.append(f"        if not worklet_result_{task_safe}:")
-        lines.append(f"            raise RuntimeError('Worklet {worklet_name} returned failure')")
+            lines.append(f"        # WARNING: Worklet '{worklet_name}' definition not found in folder")
+            lines.append(f"        logger.warning('Worklet {worklet_name} not found — skipping')")
         lines.append(f"    except Exception as e:")
         lines.append(f"        logger.error(f'Worklet {task.name} failed: {{e}}')")
         if task.fail_parent_if_instance_fails == "YES":

informatica_python-1.4.2/informatica_python.egg-info/PKG-INFO

@@ -0,0 +1,228 @@
+Metadata-Version: 2.4
+Name: informatica-python
+Version: 1.4.2
+Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
+Author: Nick
+License: MIT
+Keywords: informatica,powercenter,etl,code-generator,pandas,pyspark,data-engineering
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Code Generators
+Classifier: Topic :: Database :: Database Engines/Servers
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lxml>=4.9.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Dynamic: license-file
+
+# informatica-python
+
+Convert Informatica PowerCenter workflow XML exports into clean, runnable Python/PySpark code.
+
+**Author:** Nick
+**License:** MIT
+**PyPI:** [informatica-python](https://pypi.org/project/informatica-python/)
+
+---
+
+## Overview
+
+`informatica-python` parses Informatica PowerCenter XML export files and generates equivalent Python code using your choice of data library. It handles all 72 DTD tags from the PowerCenter XML schema and produces a complete, ready-to-run Python project.
+
+## Installation
+
+```bash
+pip install informatica-python
+```
+
+## Quick Start
+
+### Command Line
+
+```bash
+# Generate Python files to a directory
+informatica-python workflow_export.xml -o output_dir
+
+# Generate as a zip archive
+informatica-python workflow_export.xml -z output.zip
+
+# Use a different data library
+informatica-python workflow_export.xml -o output_dir --data-lib polars
+
+# Parse to JSON only (no code generation)
+informatica-python workflow_export.xml --json
+
+# Save parsed JSON to file
+informatica-python workflow_export.xml --json-file parsed.json
+```
+
+### Python API
+
+```python
+from informatica_python import InformaticaConverter
+
+converter = InformaticaConverter()
+
+# Parse and generate files
+converter.convert_to_files("workflow_export.xml", "output_dir")
+
+# Parse and generate zip
+converter.convert_to_zip("workflow_export.xml", "output.zip")
+
+# Parse to structured dict
+result = converter.parse_file("workflow_export.xml")
+
+# Use a different data library
+converter.convert_to_files("workflow_export.xml", "output_dir", data_lib="polars")
+```
+
+## Generated Output Files
+
+| File | Description |
+|------|-------------|
+| `helper_functions.py` | Database/file I/O helpers, Informatica expression equivalents (80+ functions) |
+| `mapping_N.py` | One per mapping — transformation logic, source reads, target writes |
+| `workflow.py` | Task orchestration with topological ordering 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 |
+| `error_log.txt` | Conversion summary, warnings, and unsupported feature notes |
+
+## Supported Data Libraries
+
+Select via `--data-lib` CLI flag or `data_lib` parameter:
+
+| Library | Flag | Best For |
+|---------|------|----------|
+| **pandas** | `pandas` (default) | General-purpose, most compatible |
+| **dask** | `dask` | Large datasets, parallel processing |
+| **polars** | `polars` | High performance, Rust-backed |
+| **vaex** | `vaex` | Out-of-core, billion-row datasets |
+| **modin** | `modin` | Drop-in pandas replacement, multi-core |
+
+## Supported Transformations
+
+The code generator produces real, runnable Python for these transformation types:
+
+- **Source Qualifier** — SQL override, pre/post SQL, column selection
+- **Expression** — Field-level expressions converted to pandas operations
+- **Filter** — Row filtering with converted conditions
+- **Joiner** — `pd.merge()` with join type and condition parsing
+- **Lookup** — `pd.merge()` lookups with connection-aware DB/file reads
+- **Aggregator** — `groupby().agg()` with SUM/COUNT/AVG/MIN/MAX/FIRST/LAST
+- **Sorter** — `sort_values()` with multi-key ascending/descending
+- **Router** — Multi-group conditional routing with if/elif/else
+- **Union** — `pd.concat()` across multiple input groups
+- **Update Strategy** — Insert/Update/Delete/Reject flag generation
+- **Sequence Generator** — Auto-incrementing ID columns
+- **Normalizer** — `pd.melt()` with auto-detected id/value vars
+- **Rank** — `groupby().rank()` with Top-N filtering
+- **Stored Procedure** — Stub generation with SP name and parameters
+- **Transaction Control** — Commit/rollback logic stubs
+- **Custom / Java** — Placeholder stubs with TODO markers
+- **SQL Transform** — Direct SQL execution pass-through
+
+## Supported XML Tags (72 Tags)
+
+**Top-level:** POWERMART, REPOSITORY, FOLDER, FOLDERVERSION
+
+**Source/Target:** SOURCE, SOURCEFIELD, TARGET, TARGETFIELD, TARGETINDEX, TARGETINDEXFIELD, FLATFILE, XMLINFO, XMLTEXT, GROUP, TABLEATTRIBUTE, FIELDATTRIBUTE, METADATAEXTENSION, KEYWORD, ERPSRCINFO
+
+**Mapping/Mapplet:** MAPPING, MAPPLET, TRANSFORMATION, TRANSFORMFIELD, TRANSFORMFIELDATTR, TRANSFORMFIELDATTRDEF, INSTANCE, ASSOCIATED_SOURCE_INSTANCE, CONNECTOR, MAPDEPENDENCY, TARGETLOADORDER, MAPPINGVARIABLE, FIELDDEPENDENCY, INITPROP, ERPINFO
+
+**Task/Session/Workflow:** TASK, TIMER, VALUEPAIR, SCHEDULER, SCHEDULEINFO, STARTOPTIONS, ENDOPTIONS, SCHEDULEOPTIONS, RECURRING, CUSTOM, DAILYFREQUENCY, REPEAT, FILTER, SESSION, CONFIGREFERENCE, SESSTRANSFORMATIONINST, SESSTRANSFORMATIONGROUP, PARTITION, HASHKEY, KEYRANGE, CONFIG, SESSIONCOMPONENT, CONNECTIONREFERENCE, TASKINSTANCE, WORKFLOWLINK, WORKFLOWVARIABLE, WORKFLOWEVENT, WORKLET, WORKFLOW, ATTRIBUTE
+
+**Shortcut:** SHORTCUT
+
+**SAP:** SAPFUNCTION, SAPSTRUCTURE, SAPPROGRAM, SAPOUTPUTPORT, SAPVARIABLE, SAPPROGRAMFLOWOBJECT, SAPTABLEPARAM
+
+## Key Features
+
+### Session Connection Overrides (v1.4+)
+When sessions define per-transform connection overrides (different database, file directory, or filename), the generated code uses those overrides instead of source/target defaults.
+
+### Worklet Support (v1.4+)
+Worklet workflows are detected and generate separate `run_worklet_NAME(config)` functions. The main workflow calls these automatically for Worklet task types.
+
+### Type Casting at Target Writes (v1.4+)
+Target field datatypes are mapped to pandas types and generate proper casting code:
+- Integers: nullable `Int64`/`Int32` or `fillna(0).astype(int)` for NOT NULL
+- Dates: `pd.to_datetime(errors='coerce')`
+- Decimals/Floats: `pd.to_numeric(errors='coerce')`
+- Booleans: `.astype('boolean')`
+
+### Flat File Handling (v1.3+)
+Parses FLATFILE metadata for delimiter, fixed-width, header lines, skip rows, quote/escape chars. Generates `pd.read_fwf()` for fixed-width or enriched `read_file()` for delimited.
+
+### Mapplet Inlining (v1.3+)
+Expands Mapplet instances into prefixed transforms, rewires connectors, and eliminates duplication.
+
+### Decision Tasks (v1.3+)
+Converts Informatica decision conditions to Python if/else branches with proper variable substitution.
+
+### Expression Converter (80+ Functions)
+
+Converts Informatica expressions to Python equivalents:
+
+- **String:** SUBSTR, LTRIM, RTRIM, UPPER, LOWER, LPAD, RPAD, INSTR, LENGTH, CONCAT, REPLACE, REG_EXTRACT, REG_REPLACE, REVERSE, INITCAP, CHR, ASCII
+- **Date:** ADD_TO_DATE, DATE_DIFF, GET_DATE_PART, SYSDATE, SYSTIMESTAMP, TO_DATE, TO_CHAR, TRUNC (date)
+- **Numeric:** ROUND, TRUNC, MOD, ABS, CEIL, FLOOR, POWER, SQRT, LOG, EXP, SIGN
+- **Conversion:** TO_INTEGER, TO_BIGINT, TO_FLOAT, TO_DECIMAL, TO_CHAR, TO_DATE
+- **Null handling:** IIF, DECODE, NVL, NVL2, ISNULL, IS_SPACES, IS_NUMBER
+- **Aggregate:** SUM, AVG, COUNT, MIN, MAX, FIRST, LAST, MEDIAN, STDDEV, VARIANCE
+- **Lookup:** :LKP expressions with dynamic lookup references
+- **Variable:** SETVARIABLE / mapping variable assignment
+
+## Requirements
+
+- Python >= 3.8
+- lxml >= 4.9.0
+- PyYAML >= 6.0
+
+## Changelog
+
+### v1.4.x (Phase 3)
+- Session connection overrides for sources and targets
+- Worklet function generation with safe invocation
+- Type casting at target writes based on TARGETFIELD datatypes
+- Flat-file session path overrides properly wired
+
+### v1.3.x (Phase 2)
+- FLATFILE metadata in source reads and target writes
+- Normalizer with `pd.melt()`
+- Rank with group-by and Top-N filtering
+- Decision tasks with real if/else branches
+- Mapplet instance inlining
+
+### v1.2.x (Phase 1)
+- Core parser for all 72 XML tags
+- Expression converter with 80+ functions
+- Aggregator, Joiner, Lookup code generation
+- Workflow orchestration with topological task ordering
+- Multi-library support (pandas, dask, polars, vaex, modin)
+
+## Development
+
+```bash
+# Clone and install in development mode
+cd informatica_python
+pip install -e ".[dev]"
+
+# Run tests (25 tests)
+pytest tests/test_converter.py -v
+```
+
+## License
+
+MIT License - Copyright (c) 2025 Nick
+
+See [LICENSE](LICENSE) for details.

{informatica_python-1.4.0 → informatica_python-1.4.2}/informatica_python.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+LICENSE
 README.md
 pyproject.toml
 informatica_python/__init__.py

informatica_python-1.4.2/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["setuptools>=68.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "informatica-python"
+version = "1.4.2"
+description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.8"
+authors = [
+    { name = "Nick" },
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Code Generators",
+    "Topic :: Database :: Database Engines/Servers",
+]
+keywords = ["informatica", "powercenter", "etl", "code-generator", "pandas", "pyspark", "data-engineering"]
+dependencies = [
+    "lxml>=4.9.0",
+    "pyyaml>=6.0",
+]
+
+[project.scripts]
+informatica-python = "informatica_python.cli:main"
+
+[project.optional-dependencies]
+dev = ["pytest>=7.0"]
+
+[tool.setuptools.packages.find]
+include = ["informatica_python*"]

informatica_python-1.4.0/PKG-INFO

@@ -1,118 +0,0 @@
-Metadata-Version: 2.4
-Name: informatica-python
-Version: 1.4.0
-Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
-License-Expression: MIT
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: lxml>=4.9.0
-Requires-Dist: pyyaml>=6.0
-Provides-Extra: dev
-Requires-Dist: pytest>=7.0; extra == "dev"
-
-# informatica-python
-
-Convert Informatica PowerCenter workflow XML files to Python/PySpark code.
-
-## Installation
-
-```bash
-pip install informatica-python
-```
-
-## Quick Start
-
-### Command Line
-
-```bash
-# Convert XML to Python files in a directory
-informatica-python workflow.xml -o output_dir
-
-# Convert XML to a zip file
-informatica-python workflow.xml -z output.zip
-
-# Use a different data library (pandas, dask, polars, vaex, modin)
-informatica-python workflow.xml -o output_dir --data-lib polars
-
-# Parse XML to JSON (no code generation)
-informatica-python workflow.xml --json
-
-# Save parsed JSON to file
-informatica-python workflow.xml --json-file parsed.json
-```
-
-### Python API
-
-```python
-from informatica_python import InformaticaConverter
-
-# Convert XML to Python files
-converter = InformaticaConverter(data_lib="pandas")
-converter.convert("workflow.xml", output_dir="output")
-
-# Convert to zip
-converter.convert("workflow.xml", output_zip="output.zip")
-
-# Parse XML to JSON dict
-result = converter.parse_file("workflow.xml")
-
-# Parse XML string
-result = converter.parse_string(xml_string)
-```
-
-## Generated Output Files
-
-| File | Description |
-|------|-------------|
-| `helper_functions.py` | Database/file I/O functions plus Python equivalents for 50+ Informatica expression functions |
-| `mapping_N.py` | One file per mapping with full transformation logic |
-| `workflow.py` | Task orchestration with topological ordering |
-| `config.yml` | Connection configs, source/target metadata, variables |
-| `all_sql_queries.sql` | All extracted SQL queries (source qualifiers, lookups, pre/post SQL) |
-| `error_log.txt` | Conversion summary, warnings, and coverage statistics |
-
-## Supported Transformation Types
-
-- Source Qualifier / Application Source Qualifier
-- Expression
-- Filter
-- Aggregator
-- Sorter
-- Joiner
-- Lookup Procedure
-- Router
-- Union
-- Update Strategy
-- Sequence Generator
-- Normalizer
-- Rank
-- Stored Procedure (placeholder)
-- Custom Transformation (placeholder)
-- Java Transformation (placeholder)
-- SQL Transformation
-
-## Supported Data Libraries
-
-Choose your preferred data manipulation library with `--data-lib`:
-
-- **pandas** (default) — Standard Python data analysis
-- **dask** — Parallel computing with pandas-like API
-- **polars** — Fast DataFrame library written in Rust
-- **vaex** — Out-of-core DataFrames for large datasets
-- **modin** — Drop-in pandas replacement with parallel execution
-
-## Informatica Expression Functions
-
-The generated `helper_functions.py` includes Python equivalents for:
-
-`IIF`, `DECODE`, `NVL`, `NVL2`, `ISNULL`, `LTRIM`, `RTRIM`, `UPPER`, `LOWER`, `SUBSTR`, `LPAD`, `RPAD`, `TO_CHAR`, `TO_DATE`, `TO_INTEGER`, `TO_BIGINT`, `TO_FLOAT`, `TO_DECIMAL`, `REPLACECHR`, `REPLACESTR`, `INSTR`, `LENGTH`, `CONCAT`, `REG_EXTRACT`, `REG_MATCH`, `REG_REPLACE`, `GET_DATE_PART`, `ADD_TO_DATE`, `IS_DATE`, `IS_NUMBER`, `IS_SPACES`, `SYSDATE`, `ERROR`, `ABORT`, and more.
-
-## Requirements
-
-- Python >= 3.8
-- lxml >= 4.9.0
-- PyYAML >= 6.0
-
-## License
-
-MIT

informatica_python-1.4.0/README.md

@@ -1,106 +0,0 @@
-# informatica-python
-
-Convert Informatica PowerCenter workflow XML files to Python/PySpark code.
-
-## Installation
-
-```bash
-pip install informatica-python
-```
-
-## Quick Start
-
-### Command Line
-
-```bash
-# Convert XML to Python files in a directory
-informatica-python workflow.xml -o output_dir
-
-# Convert XML to a zip file
-informatica-python workflow.xml -z output.zip
-
-# Use a different data library (pandas, dask, polars, vaex, modin)
-informatica-python workflow.xml -o output_dir --data-lib polars
-
-# Parse XML to JSON (no code generation)
-informatica-python workflow.xml --json
-
-# Save parsed JSON to file
-informatica-python workflow.xml --json-file parsed.json
-```
-
-### Python API
-
-```python
-from informatica_python import InformaticaConverter
-
-# Convert XML to Python files
-converter = InformaticaConverter(data_lib="pandas")
-converter.convert("workflow.xml", output_dir="output")
-
-# Convert to zip
-converter.convert("workflow.xml", output_zip="output.zip")
-
-# Parse XML to JSON dict
-result = converter.parse_file("workflow.xml")
-
-# Parse XML string
-result = converter.parse_string(xml_string)
-```
-
-## Generated Output Files
-
-| File | Description |
-|------|-------------|
-| `helper_functions.py` | Database/file I/O functions plus Python equivalents for 50+ Informatica expression functions |
-| `mapping_N.py` | One file per mapping with full transformation logic |
-| `workflow.py` | Task orchestration with topological ordering |
-| `config.yml` | Connection configs, source/target metadata, variables |
-| `all_sql_queries.sql` | All extracted SQL queries (source qualifiers, lookups, pre/post SQL) |
-| `error_log.txt` | Conversion summary, warnings, and coverage statistics |
-
-## Supported Transformation Types
-
-- Source Qualifier / Application Source Qualifier
-- Expression
-- Filter
-- Aggregator
-- Sorter
-- Joiner
-- Lookup Procedure
-- Router
-- Union
-- Update Strategy
-- Sequence Generator
-- Normalizer
-- Rank
-- Stored Procedure (placeholder)
-- Custom Transformation (placeholder)
-- Java Transformation (placeholder)
-- SQL Transformation
-
-## Supported Data Libraries
-
-Choose your preferred data manipulation library with `--data-lib`:
-
-- **pandas** (default) — Standard Python data analysis
-- **dask** — Parallel computing with pandas-like API
-- **polars** — Fast DataFrame library written in Rust
-- **vaex** — Out-of-core DataFrames for large datasets
-- **modin** — Drop-in pandas replacement with parallel execution
-
-## Informatica Expression Functions
-
-The generated `helper_functions.py` includes Python equivalents for:
-
-`IIF`, `DECODE`, `NVL`, `NVL2`, `ISNULL`, `LTRIM`, `RTRIM`, `UPPER`, `LOWER`, `SUBSTR`, `LPAD`, `RPAD`, `TO_CHAR`, `TO_DATE`, `TO_INTEGER`, `TO_BIGINT`, `TO_FLOAT`, `TO_DECIMAL`, `REPLACECHR`, `REPLACESTR`, `INSTR`, `LENGTH`, `CONCAT`, `REG_EXTRACT`, `REG_MATCH`, `REG_REPLACE`, `GET_DATE_PART`, `ADD_TO_DATE`, `IS_DATE`, `IS_NUMBER`, `IS_SPACES`, `SYSDATE`, `ERROR`, `ABORT`, and more.
-
-## Requirements
-
-- Python >= 3.8
-- lxml >= 4.9.0
-- PyYAML >= 6.0
-
-## License
-
-MIT

informatica_python-1.4.0/informatica_python/__init__.py

@@ -1,4 +0,0 @@
-from informatica_python.converter import InformaticaConverter
-
-__version__ = "1.0.0"
-__all__ = ["InformaticaConverter"]

informatica_python-1.4.0/informatica_python.egg-info/PKG-INFO

@@ -1,118 +0,0 @@
-Metadata-Version: 2.4
-Name: informatica-python
-Version: 1.4.0
-Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
-License-Expression: MIT
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: lxml>=4.9.0
-Requires-Dist: pyyaml>=6.0
-Provides-Extra: dev
-Requires-Dist: pytest>=7.0; extra == "dev"
-
-# informatica-python
-
-Convert Informatica PowerCenter workflow XML files to Python/PySpark code.
-
-## Installation
-
-```bash
-pip install informatica-python
-```
-
-## Quick Start
-
-### Command Line
-
-```bash
-# Convert XML to Python files in a directory
-informatica-python workflow.xml -o output_dir
-
-# Convert XML to a zip file
-informatica-python workflow.xml -z output.zip
-
-# Use a different data library (pandas, dask, polars, vaex, modin)
-informatica-python workflow.xml -o output_dir --data-lib polars
-
-# Parse XML to JSON (no code generation)
-informatica-python workflow.xml --json
-
-# Save parsed JSON to file
-informatica-python workflow.xml --json-file parsed.json
-```
-
-### Python API
-
-```python
-from informatica_python import InformaticaConverter
-
-# Convert XML to Python files
-converter = InformaticaConverter(data_lib="pandas")
-converter.convert("workflow.xml", output_dir="output")
-
-# Convert to zip
-converter.convert("workflow.xml", output_zip="output.zip")
-
-# Parse XML to JSON dict
-result = converter.parse_file("workflow.xml")
-
-# Parse XML string
-result = converter.parse_string(xml_string)
-```
-
-## Generated Output Files
-
-| File | Description |
-|------|-------------|
-| `helper_functions.py` | Database/file I/O functions plus Python equivalents for 50+ Informatica expression functions |
-| `mapping_N.py` | One file per mapping with full transformation logic |
-| `workflow.py` | Task orchestration with topological ordering |
-| `config.yml` | Connection configs, source/target metadata, variables |
-| `all_sql_queries.sql` | All extracted SQL queries (source qualifiers, lookups, pre/post SQL) |
-| `error_log.txt` | Conversion summary, warnings, and coverage statistics |
-
-## Supported Transformation Types
-
-- Source Qualifier / Application Source Qualifier
-- Expression
-- Filter
-- Aggregator
-- Sorter
-- Joiner
-- Lookup Procedure
-- Router
-- Union
-- Update Strategy
-- Sequence Generator
-- Normalizer
-- Rank
-- Stored Procedure (placeholder)
-- Custom Transformation (placeholder)
-- Java Transformation (placeholder)
-- SQL Transformation
-
-## Supported Data Libraries
-
-Choose your preferred data manipulation library with `--data-lib`:
-
-- **pandas** (default) — Standard Python data analysis
-- **dask** — Parallel computing with pandas-like API
-- **polars** — Fast DataFrame library written in Rust
-- **vaex** — Out-of-core DataFrames for large datasets
-- **modin** — Drop-in pandas replacement with parallel execution
-
-## Informatica Expression Functions
-
-The generated `helper_functions.py` includes Python equivalents for:
-
-`IIF`, `DECODE`, `NVL`, `NVL2`, `ISNULL`, `LTRIM`, `RTRIM`, `UPPER`, `LOWER`, `SUBSTR`, `LPAD`, `RPAD`, `TO_CHAR`, `TO_DATE`, `TO_INTEGER`, `TO_BIGINT`, `TO_FLOAT`, `TO_DECIMAL`, `REPLACECHR`, `REPLACESTR`, `INSTR`, `LENGTH`, `CONCAT`, `REG_EXTRACT`, `REG_MATCH`, `REG_REPLACE`, `GET_DATE_PART`, `ADD_TO_DATE`, `IS_DATE`, `IS_NUMBER`, `IS_SPACES`, `SYSDATE`, `ERROR`, `ABORT`, and more.
-
-## Requirements
-
-- Python >= 3.8
-- lxml >= 4.9.0
-- PyYAML >= 6.0
-
-## License
-
-MIT

informatica_python-1.4.0/pyproject.toml

@@ -1,24 +0,0 @@
-[build-system]
-requires = ["setuptools>=68.0", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "informatica-python"
-version = "1.4.0"
-description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
-readme = "README.md"
-license = "MIT"
-requires-python = ">=3.8"
-dependencies = [
-    "lxml>=4.9.0",
-    "pyyaml>=6.0",
-]
-
-[project.scripts]
-informatica-python = "informatica_python.cli:main"
-
-[project.optional-dependencies]
-dev = ["pytest>=7.0"]
-
-[tool.setuptools.packages.find]
-include = ["informatica_python*"]