tha-map-runner 0.1.0__tar.gz

tha_map_runner-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,36 @@
+name: CI
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --extra dev --python ${{ matrix.python-version }}
+
+      - name: Lint
+        run: uv run ruff check src/ tests/
+
+      - name: Test
+        run: uv run pytest
+
+      - name: Type check
+        run: uv run mypy src/

tha_map_runner-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,58 @@
+name: Publish
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Build
+        run: uv build
+
+      - name: Upload dist
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish-testpypi:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: testpypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Download dist
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  publish-pypi:
+    needs: publish-testpypi
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Download dist
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

tha_map_runner-0.1.0/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

tha_map_runner-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Nathan Wright
+
+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.

tha_map_runner-0.1.0/PKG-INFO

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: tha-map-runner
+Version: 0.1.0
+Summary: Join JSON responses into CSV-style rows with dotted-path projection — a Tabular Helper API.
+Project-URL: Homepage, https://github.com/tha-guy-nate/tha-map-runner
+Project-URL: Issues, https://github.com/tha-guy-nate/tha-map-runner/issues
+Author: Nate Wright
+License: MIT
+License-File: LICENSE
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# tha-map-runner
+
+[![CI](https://github.com/tha-guy-nate/tha-map-runner/actions/workflows/ci.yml/badge.svg)](https://github.com/tha-guy-nate/tha-map-runner/actions/workflows/ci.yml)
+
+A small Python library that joins a list of row dicts with a lookup source on a key, projecting values into flat row columns via a mapping config.
+
+Think "left join between rows and a lookup source, with dotted-path projection on the source side."
+
+## Install
+
+```bash
+pip install tha-map-runner
+```
+
+## Quick start
+
+```python
+from tha_map_runner import enrich_rows
+
+rows = [
+    {"Org BK": "school-001", "Start Date": "08/15"},
+    {"Org BK": "school-002", "Start Date": "08/16"},
+]
+
+api_response = [
+    {"sourcedId": "school-001", "name": "Lincoln Elementary", "parent": {"sourcedId": "dist-A"}},
+    {"sourcedId": "school-002", "name": "Roosevelt Middle",   "parent": {"sourcedId": "dist-A"}},
+]
+
+enriched = enrich_rows(
+    rows=rows,
+    source=api_response,
+    mapping={
+        "Org Name":  "name",
+        "Parent BK": "parent.sourcedId",
+    },
+    row_key="Org BK",
+    source_key="sourcedId",
+)
+```
+
+## How it works
+
+1. Builds an index of `source` on `source_key` — O(n+m), no nested loops
+2. For each row, looks up a match by `row[row_key]`
+3. Walks dotted paths (`"parent.sourcedId"`) into the matched source entry
+4. Projects resolved values into new columns on a copy of the row
+5. Returns a new list — input is never mutated
+
+Rows whose `row status` is in `skip_statuses` are passed through unchanged.
+
+## API
+
+```python
+enrich_rows(
+    rows,                              # list of row dicts
+    source,                            # list of dicts to join against
+    mapping,                           # {"output_column": "dotted.path"} — callable values planned
+    row_key,                           # column name in rows to match on
+    source_key,                        # field in source to match on
+    *,
+    on_no_match="skip",                # "skip" | "error" | "blank"
+    allow_empty_source=False,          # if True, empty source is not an error
+    skip_statuses=["error", "warning"],# rows with these statuses are passed through
+) -> list[dict]
+```
+
+### `on_no_match`
+
+| Value | Behaviour |
+|---|---|
+| `"skip"` | Row is returned unchanged — no new columns added |
+| `"error"` | `row status="error"`, `message=...`, mapping columns set to `""` |
+| `"blank"` | Mapping columns set to `""`, row status untouched |
+
+### `skip_statuses`
+
+By default, rows already marked `row status="error"` or `row status="warning"` are passed through without processing. Override with any list:
+
+```python
+enrich_rows(..., skip_statuses=["error"])        # only skip errors
+enrich_rows(..., skip_statuses=["error", "pending"])  # custom statuses
+enrich_rows(..., skip_statuses=[])               # process every row regardless
+```
+
+### Composing with `tha-csv-runner`
+
+```python
+from tha_csv_runner import ThaCSV
+from tha_map_runner import enrich_rows
+import requests
+
+runner = ThaCSV()
+runner.read("Step 1 of 2", "input.csv", ["Org BK"])
+
+api_response = requests.get(api_url).json()
+
+runner.rows = enrich_rows(
+    rows=runner.rows,
+    source=api_response,
+    mapping={"Org Name": "name", "District": "parent.sourcedId"},
+    row_key="Org BK",
+    source_key="sourcedId",
+)
+
+runner.write("Step 2 of 2", "output.csv")
+```
+
+## License
+
+MIT

tha_map_runner-0.1.0/README.md

@@ -0,0 +1,111 @@
+# tha-map-runner
+
+[![CI](https://github.com/tha-guy-nate/tha-map-runner/actions/workflows/ci.yml/badge.svg)](https://github.com/tha-guy-nate/tha-map-runner/actions/workflows/ci.yml)
+
+A small Python library that joins a list of row dicts with a lookup source on a key, projecting values into flat row columns via a mapping config.
+
+Think "left join between rows and a lookup source, with dotted-path projection on the source side."
+
+## Install
+
+```bash
+pip install tha-map-runner
+```
+
+## Quick start
+
+```python
+from tha_map_runner import enrich_rows
+
+rows = [
+    {"Org BK": "school-001", "Start Date": "08/15"},
+    {"Org BK": "school-002", "Start Date": "08/16"},
+]
+
+api_response = [
+    {"sourcedId": "school-001", "name": "Lincoln Elementary", "parent": {"sourcedId": "dist-A"}},
+    {"sourcedId": "school-002", "name": "Roosevelt Middle",   "parent": {"sourcedId": "dist-A"}},
+]
+
+enriched = enrich_rows(
+    rows=rows,
+    source=api_response,
+    mapping={
+        "Org Name":  "name",
+        "Parent BK": "parent.sourcedId",
+    },
+    row_key="Org BK",
+    source_key="sourcedId",
+)
+```
+
+## How it works
+
+1. Builds an index of `source` on `source_key` — O(n+m), no nested loops
+2. For each row, looks up a match by `row[row_key]`
+3. Walks dotted paths (`"parent.sourcedId"`) into the matched source entry
+4. Projects resolved values into new columns on a copy of the row
+5. Returns a new list — input is never mutated
+
+Rows whose `row status` is in `skip_statuses` are passed through unchanged.
+
+## API
+
+```python
+enrich_rows(
+    rows,                              # list of row dicts
+    source,                            # list of dicts to join against
+    mapping,                           # {"output_column": "dotted.path"} — callable values planned
+    row_key,                           # column name in rows to match on
+    source_key,                        # field in source to match on
+    *,
+    on_no_match="skip",                # "skip" | "error" | "blank"
+    allow_empty_source=False,          # if True, empty source is not an error
+    skip_statuses=["error", "warning"],# rows with these statuses are passed through
+) -> list[dict]
+```
+
+### `on_no_match`
+
+| Value | Behaviour |
+|---|---|
+| `"skip"` | Row is returned unchanged — no new columns added |
+| `"error"` | `row status="error"`, `message=...`, mapping columns set to `""` |
+| `"blank"` | Mapping columns set to `""`, row status untouched |
+
+### `skip_statuses`
+
+By default, rows already marked `row status="error"` or `row status="warning"` are passed through without processing. Override with any list:
+
+```python
+enrich_rows(..., skip_statuses=["error"])        # only skip errors
+enrich_rows(..., skip_statuses=["error", "pending"])  # custom statuses
+enrich_rows(..., skip_statuses=[])               # process every row regardless
+```
+
+### Composing with `tha-csv-runner`
+
+```python
+from tha_csv_runner import ThaCSV
+from tha_map_runner import enrich_rows
+import requests
+
+runner = ThaCSV()
+runner.read("Step 1 of 2", "input.csv", ["Org BK"])
+
+api_response = requests.get(api_url).json()
+
+runner.rows = enrich_rows(
+    rows=runner.rows,
+    source=api_response,
+    mapping={"Org Name": "name", "District": "parent.sourcedId"},
+    row_key="Org BK",
+    source_key="sourcedId",
+)
+
+runner.write("Step 2 of 2", "output.csv")
+```
+
+## License
+
+MIT

tha_map_runner-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "tha-map-runner"
+version = "0.1.0"
+description = "Join JSON responses into CSV-style rows with dotted-path projection — a Tabular Helper API."
+readme = "README.md"
+license = { text = "MIT" }
+authors = [{ name = "Nate Wright" }]
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Developers",
+    "Topic :: Utilities",
+]
+dependencies = []
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8",
+    "ruff>=0.5",
+    "mypy>=1.10",
+]
+
+[project.urls]
+Homepage = "https://github.com/tha-guy-nate/tha-map-runner"
+Issues = "https://github.com/tha-guy-nate/tha-map-runner/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/tha_map_runner"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "B", "UP", "RUF"]
+
+[tool.mypy]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

tha_map_runner-0.1.0/src/tha_map_runner/__init__.py

@@ -0,0 +1,7 @@
+"""tha-map-runner: join JSON responses into CSV-style rows with dotted-path projection."""
+
+from .errors import MapperError
+from .mapper import enrich_rows
+
+__version__ = "0.1.0"
+__all__ = ["MapperError", "enrich_rows"]

tha_map_runner-0.1.0/src/tha_map_runner/errors.py

@@ -0,0 +1,2 @@
+class MapperError(Exception):
+    """Raised for invalid mapper configuration."""