datalegion-cli 1.0.0__tar.gz

datalegion_cli-1.0.0/.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+name: CI
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    steps:
+      - uses: actions/checkout@v6
+      - uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.11"
+      - run: uv sync --group dev
+      - run: uv run ruff check src/ tests/
+      - run: uv run ruff format --check src/ tests/
+
+  test:
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    steps:
+      - uses: actions/checkout@v6
+      - uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.11"
+      - run: uv sync --group dev
+      - run: uv run pytest

datalegion_cli-1.0.0/.github/workflows/release.yml

@@ -0,0 +1,145 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - "v*"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    name: Lint & Build
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    timeout-minutes: 5
+    permissions:
+      contents: read
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install dependencies
+        run: uv sync --frozen --group dev
+
+      - name: Run lint
+        run: uv run ruff check src/ tests/
+
+      - name: Check formatting
+        run: uv run ruff format --check src/ tests/
+
+      - name: Build
+        run: uv build
+
+      - name: Prune uv cache
+        if: always()
+        run: uv cache prune --ci
+
+  test:
+    name: Test (Python ${{ matrix.python-version }})
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    timeout-minutes: 10
+    permissions:
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --frozen --group dev
+
+      - name: Run tests
+        run: uv run pytest tests/ -v --tb=short
+
+      - name: Prune uv cache
+        if: always()
+        run: uv cache prune --ci
+
+  publish-pypi:
+    name: Publish to PyPI
+    needs: [lint, test]
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    timeout-minutes: 5
+    permissions:
+      contents: read
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Set version from tag
+        run: |
+          VERSION="${GITHUB_REF_NAME#v}"
+          sed -i "s/^version = .*/version = \"${VERSION}\"/" pyproject.toml
+
+      - name: Build
+        run: uv build
+
+      - name: Publish to PyPI
+        run: uv publish --trusted-publishing always
+
+  github-release:
+    name: Create GitHub Release
+    needs: [publish-pypi]
+    runs-on: blacksmith-2vcpu-ubuntu-2404
+    timeout-minutes: 5
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          ref: main
+          token: ${{ secrets.GH_PAT }}
+
+      - name: Update version in pyproject.toml
+        run: |
+          VERSION="${GITHUB_REF_NAME#v}"
+          sed -i "s/^version = .*/version = \"${VERSION}\"/" pyproject.toml
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add pyproject.toml
+          git diff --staged --quiet || git commit -m "chore: bump version to ${VERSION} [skip ci]"
+          git push
+
+      - name: Create Release
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const tag = context.ref.replace('refs/tags/', '');
+            await github.rest.repos.createRelease({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              tag_name: tag,
+              name: tag,
+              generate_release_notes: true,
+            });

datalegion_cli-1.0.0/.gitignore

@@ -0,0 +1,207 @@
+# 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
+
+# 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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

datalegion_cli-1.0.0/PKG-INFO

@@ -0,0 +1,270 @@
+Metadata-Version: 2.4
+Name: datalegion-cli
+Version: 1.0.0
+Summary: CLI for the Data Legion API — agent-friendly, fully async
+Project-URL: Homepage, https://www.datalegion.ai
+Project-URL: Documentation, https://www.datalegion.ai/docs
+Project-URL: Repository, https://github.com/datalegion-ai/datalegion-cli
+Project-URL: Issues, https://github.com/datalegion-ai/datalegion-cli/issues
+Author-email: Data Legion <engineering@datalegion.ai>
+License-Expression: MIT
+Keywords: b2b,cli,company-enrichment,contact-data,data-enrichment,datalegion,enrichment,person-enrichment
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Requires-Dist: cryptography>=44.0.0
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: loguru>=0.7.0
+Requires-Dist: packaging>=24.0
+Requires-Dist: pydantic-settings>=2.6.0
+Requires-Dist: pydantic>=2.9.0
+Requires-Dist: rich>=13.9.0
+Requires-Dist: tomli-w>=1.0.0
+Requires-Dist: tomli>=2.0.0; python_version < '3.11'
+Requires-Dist: typer>=0.15.0
+Description-Content-Type: text/markdown
+
+# datalegion-cli
+
+The official command-line interface for the [Data Legion](https://www.datalegion.ai) API. Built for both humans and AI agents.
+
+Look up people and companies by email, phone, name, domain, LinkedIn, or ticker symbol. Search across 1.5B+ contacts and 200M+ companies using SQL syntax. Clean, hash, and validate data fields before or after enrichment. Track credit usage and manage your configuration — all from the terminal.
+
+```bash
+pip install datalegion-cli
+datalegion-cli config set api_key legion_your_key_here
+datalegion-cli person enrich --email john@example.com
+```
+
+## Features
+
+- **Fully async** — async from entry point to HTTP client, powered by `asyncio` and `httpx`
+- **Agent-friendly** — all output is JSON to stdout, logs go to stderr, supports `--stdin` for piping
+- **Encrypted config** — API keys are stored encrypted at rest (Fernet + PBKDF2, machine-tied)
+- **Auto-update** — checks GitHub releases and self-updates via Homebrew, GitHub release, git pull, or pip/uv
+- **Multiple install methods** — Homebrew, GitHub release, pip/uv (with private index support), or from source
+
+## Installation
+
+### Homebrew
+
+```bash
+brew install datalegion/tap/datalegion-cli
+```
+
+### From PyPI (or private index)
+
+```bash
+uv pip install datalegion-cli
+```
+
+Or with pip:
+
+```bash
+pip install datalegion-cli
+```
+
+To install from a private index:
+
+```bash
+uv pip install datalegion-cli --extra-index-url https://your-private-index.com/simple
+```
+
+### From GitHub release
+
+Download the `.whl` from the [latest release](https://github.com/datalegion/datalegion-cli/releases/latest) and install:
+
+```bash
+uv pip install datalegion_cli-*.whl
+```
+
+### From source
+
+```bash
+git clone https://github.com/datalegion/datalegion-cli.git
+cd datalegion-cli
+uv sync
+```
+
+## Configuration
+
+Set your API key (stored encrypted on disk):
+
+```bash
+datalegion-cli config set api_key legion_your_key_here
+```
+
+Or via environment variable (takes precedence over file config):
+
+```bash
+export LEGION_API_KEY=legion_your_key_here
+```
+
+### Other config options
+
+```bash
+# Set the API base URL
+datalegion-cli config set api_base_url https://api.datalegion.ai
+
+# Set install method for auto-update (brew, github, git, or pip)
+datalegion-cli config set install_method brew
+
+# View all config
+datalegion-cli config list
+
+# Show config file path
+datalegion-cli config path
+```
+
+Config is stored at `~/.datalegion/config.toml`. Override the location with `LEGION_CONFIG_DIR`.
+
+### Install method detection
+
+The `update` command auto-detects how the CLI was installed:
+
+| Method | Detection | Update strategy |
+|--------|-----------|-----------------|
+| `brew` | `brew list` finds the formula | `brew upgrade` |
+| `github` | Set via config | Downloads `.whl` from GitHub release |
+| `git` | `.git` directory in parent tree | `git pull --ff-only` + `uv sync` |
+| `pip` | Default fallback | `uv pip install --upgrade` |
+
+You can override detection by setting `install_method` in config. For pip installs from a private index, set the `LEGION_PIP_INDEX_URL` environment variable.
+
+## Usage
+
+### Person enrichment
+
+```bash
+# By email
+datalegion-cli person enrich --email john@example.com
+
+# By name + company
+datalegion-cli person enrich --name "Jane Smith" --company "Acme Corp" --city "NYC"
+
+# By LinkedIn
+datalegion-cli person enrich --social-url "https://linkedin.com/in/johndoe"
+
+# Multiple results with minimum confidence
+datalegion-cli person enrich --email john@example.com --multiple --min-confidence high
+
+# Select specific fields
+datalegion-cli person enrich --email john@example.com --fields "full_name,emails,phones"
+```
+
+### Person search
+
+```bash
+# SQL-based search
+datalegion-cli person search "SELECT * FROM people WHERE company_name ILIKE '%google%' AND state = 'CA'" --limit 5
+```
+
+### Company enrichment
+
+```bash
+# By domain
+datalegion-cli company enrich --domain google.com
+
+# By ticker symbol
+datalegion-cli company enrich --ticker AAPL
+
+# By name with industry context
+datalegion-cli company enrich --name "Stripe" --industry "Financial Services"
+```
+
+### Company search
+
+```bash
+# SQL-based search
+datalegion-cli company search "SELECT * FROM companies WHERE industry ILIKE '%software%' AND legion_employee_count > 100"
+```
+
+### Utility commands
+
+```bash
+# Clean and normalize fields
+datalegion-cli utility clean '{"email": "John.Doe+tag@gmail.com", "phone": "(555) 123-4567"}'
+
+# Hash an email for privacy-preserving lookups
+datalegion-cli utility hash john@example.com
+
+# Validate fields before enrichment
+datalegion-cli utility validate --email "test@example.com" --phone "+15551234567"
+```
+
+### Credits
+
+```bash
+# Check balance
+datalegion-cli credits balance
+
+# View usage history
+datalegion-cli credits usage --from 2026-01-01 --to 2026-03-01
+```
+
+### Other commands
+
+```bash
+# Check for updates
+datalegion-cli update --check
+
+# Self-update
+datalegion-cli update
+
+# Show version
+datalegion-cli version
+```
+
+## Agent / automation usage
+
+The CLI is designed to be called by AI agents and scripts. Key patterns:
+
+```bash
+# All output is JSON to stdout — parse it directly
+datalegion-cli person enrich --email john@example.com | jq '.matches[0].full_name'
+
+# Pipe JSON payloads via stdin
+echo '{"email":"john@example.com","company":"Acme"}' | datalegion-cli person enrich --stdin
+
+# Suppress logs with --quiet (only JSON on stdout)
+datalegion-cli --quiet person enrich --email john@example.com
+
+# Errors are also JSON
+datalegion-cli person enrich --email bad 2>/dev/null
+# {"ok": false, "error": "bad_request", "message": "..."}
+```
+
+## Global flags
+
+| Flag | Description |
+|------|-------------|
+| `--verbose` / `-v` | Enable debug logging to stderr |
+| `--quiet` / `-q` | Suppress all log output |
+| `--help` | Show help for any command |
+
+## Development
+
+```bash
+# Install dev dependencies
+uv sync
+
+# Run tests
+uv run pytest
+
+# Lint
+uv run ruff check src/ tests/
+
+# Build wheel
+uv build
+```
+
+## License
+
+MIT