openadapt-privacy 0.1.0__tar.gz

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

@@ -0,0 +1,29 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # Required for trusted publishing
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        run: uv python install 3.12
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

openadapt_privacy-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,54 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+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
+
+      - name: Run tests (without Presidio)
+        run: uv run pytest tests/ -v --ignore=tests/test_presidio.py
+
+  test-presidio:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        run: uv python install 3.12
+
+      - name: Install dependencies with Presidio
+        run: |
+          uv sync --extra dev --extra presidio
+          uv pip install pip
+          uv run python -m spacy download en_core_web_trf
+
+      - name: Run all tests
+        run: uv run pytest tests/ -v

openadapt_privacy-0.1.0/.gitignore

@@ -0,0 +1,47 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# uv
+uv.lock

openadapt_privacy-0.1.0/PKG-INFO

@@ -0,0 +1,276 @@
+Metadata-Version: 2.4
+Name: openadapt-privacy
+Version: 0.1.0
+Summary: Privacy scrubbing for GUI automation data - PII/PHI detection and redaction
+Project-URL: Homepage, https://github.com/OpenAdaptAI/openadapt-privacy
+Project-URL: Repository, https://github.com/OpenAdaptAI/openadapt-privacy
+Author-email: "MLDSAI Inc." <richard@mldsai.com>
+License-Expression: MIT
+Keywords: automation,gui,phi,pii,privacy,redaction,scrubbing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+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 :: Security
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pip>=25.3
+Requires-Dist: pydantic>=2.0.0
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
+Requires-Dist: pytest>=7.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: presidio
+Requires-Dist: presidio-analyzer>=2.2.0; extra == 'presidio'
+Requires-Dist: presidio-anonymizer>=2.2.0; extra == 'presidio'
+Requires-Dist: presidio-image-redactor>=0.0.50; extra == 'presidio'
+Requires-Dist: spacy-transformers>=1.3.0; extra == 'presidio'
+Requires-Dist: spacy>=3.7.0; extra == 'presidio'
+Description-Content-Type: text/markdown
+
+# openadapt-privacy
+
+Privacy scrubbing for GUI automation data - PII/PHI detection and redaction.
+
+## Installation
+
+```bash
+pip install openadapt-privacy
+```
+
+For Presidio-based scrubbing (recommended):
+
+```bash
+pip install openadapt-privacy[presidio]
+python -m spacy download en_core_web_trf
+```
+
+## Quick Start
+
+### Text Scrubbing
+
+```python
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+
+text = "Contact John Smith at john.smith@example.com or 555-123-4567"
+scrubbed = scrubber.scrub_text(text)
+```
+
+**Input:**
+```
+Contact John Smith at john.smith@example.com or 555-123-4567
+```
+
+**Output:**
+```
+Contact <PERSON> at <EMAIL_ADDRESS> or <PHONE_NUMBER>
+```
+
+### Example Inputs & Outputs
+
+| Input | Output |
+|-------|--------|
+| `My email is john@example.com` | `My email is <EMAIL_ADDRESS>` |
+| `SSN: 923-45-6789` | `SSN: <US_SSN>` |
+| `Card: 4532-1234-5678-9012` | `Card: <CREDIT_CARD>` |
+| `Call me at 555-123-4567` | `Call me at <PHONE_NUMBER>` |
+| `DOB: 01/15/1985` | `DOB: <DATE_TIME>` |
+| `Contact John Smith` | `Contact <PERSON>` |
+
+## Dict Scrubbing
+
+Scrub PII from nested dictionaries (e.g., GUI element trees):
+
+```python
+from openadapt_privacy import scrub_dict
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+action = {
+    "text": "Email: john@example.com",
+    "metadata": {
+        "title": "User Profile - John Smith",
+        "tooltip": "Click to contact john@example.com",
+    },
+    "coordinates": {"x": 100, "y": 200},
+}
+scrubbed = scrub_dict(action, scrubber)
+```
+
+**Input:**
+```json
+{
+    "text": "Email: john@example.com",
+    "metadata": {
+        "title": "User Profile - John Smith",
+        "tooltip": "Click to contact john@example.com"
+    },
+    "coordinates": {"x": 100, "y": 200}
+}
+```
+
+**Output:**
+```json
+{
+    "text": "Email: <EMAIL_ADDRESS>",
+    "metadata": {
+        "title": "User Profile - <PERSON>",
+        "tooltip": "Click to contact <EMAIL_ADDRESS>"
+    },
+    "coordinates": {"x": 100, "y": 200}
+}
+```
+
+## Recording Pipeline
+
+Process complete GUI automation recordings:
+
+```python
+from openadapt_privacy import DictRecordingLoader
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+loader = DictRecordingLoader()
+
+recording = loader.load_from_dict({
+    "task_description": "Send email to John Smith at john@example.com",
+    "actions": [
+        {"id": 1, "action_type": "click", "text": "Compose", "timestamp": 1000},
+        {"id": 2, "action_type": "type", "text": "john@example.com", "timestamp": 2000},
+        {"id": 3, "action_type": "click", "text": "Send", "window_title": "Email to john@example.com", "timestamp": 3000},
+    ],
+})
+
+scrubbed = recording.scrub(scrubber)
+```
+
+**Input Recording:**
+```
+task_description: "Send email to John Smith at john@example.com"
+
+actions:
+  [1] click: "Compose"
+  [2] type:  "john@example.com"
+  [3] click: "Send" (window: "Email to john@example.com")
+```
+
+**Output Recording:**
+```
+task_description: "Send email to <PERSON> at <EMAIL_ADDRESS>"
+
+actions:
+  [1] click: "Compose"
+  [2] type:  "<EMAIL_ADDRESS>"
+  [3] click: "Send" (window: "Email to <EMAIL_ADDRESS>")
+```
+
+## Image Scrubbing
+
+Redact PII from screenshots using OCR + NER:
+
+```python
+from PIL import Image
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+
+image = Image.open("screenshot.png")
+scrubbed_image = scrubber.scrub_image(image)
+scrubbed_image.save("screenshot_scrubbed.png")
+```
+
+**Input Screenshot:**
+
+![Original screenshot with PII](assets/screenshot_original.png)
+
+**Output Screenshot:**
+
+![Scrubbed screenshot with PII redacted](assets/screenshot_scrubbed.png)
+
+The image redactor:
+1. Runs OCR to detect text regions
+2. Analyzes text for PII entities (email, phone, SSN, etc.)
+3. Fills detected PII regions with solid color (configurable, default: red)
+
+## Custom Data Loader
+
+Implement your own loader for custom storage formats:
+
+```python
+from openadapt_privacy import RecordingLoader, Recording
+
+class SQLiteRecordingLoader(RecordingLoader):
+    def __init__(self, db_path: str):
+        self.db_path = db_path
+
+    def load(self, recording_id: str) -> Recording:
+        # Load from SQLite database
+        ...
+
+    def save(self, recording: Recording, recording_id: str) -> None:
+        # Save to SQLite database
+        ...
+
+# Usage
+loader = SQLiteRecordingLoader("recordings.db")
+scrubber = PresidioScrubbingProvider()
+
+# Load, scrub, and save
+scrubbed = loader.load_and_scrub("recording_001", scrubber)
+loader.save(scrubbed, "recording_001_scrubbed")
+```
+
+## Configuration
+
+```python
+from openadapt_privacy.config import PrivacyConfig
+
+custom_config = PrivacyConfig(
+    SCRUB_CHAR="X",                    # Character for scrub_text_all
+    SCRUB_FILL_COLOR=0xFF0000,         # Red for image redaction (BGR)
+    SCRUB_KEYS_HTML=[                  # Keys to scrub in dicts
+        "text", "value", "title", "tooltip", "custom_field"
+    ],
+    SCRUB_PRESIDIO_IGNORE_ENTITIES=[   # Entity types to skip
+        "DATE_TIME",
+    ],
+)
+```
+
+## Supported Entity Types
+
+| Entity | Example Input | Example Output |
+|--------|---------------|----------------|
+| `PERSON` | `John Smith` | `<PERSON>` |
+| `EMAIL_ADDRESS` | `john@example.com` | `<EMAIL_ADDRESS>` |
+| `PHONE_NUMBER` | `555-123-4567` | `<PHONE_NUMBER>` |
+| `US_SSN` | `923-45-6789` | `<US_SSN>` |
+| `CREDIT_CARD` | `4532-1234-5678-9012` | `<CREDIT_CARD>` |
+| `US_BANK_NUMBER` | `635526789012` | `<US_BANK_NUMBER>` |
+| `US_DRIVER_LICENSE` | `A123-456-789-012` | `<US_DRIVER_LICENSE>` |
+| `DATE_TIME` | `01/15/1985` | `<DATE_TIME>` |
+| `LOCATION` | `Toronto, ON` | `<LOCATION>` |
+
+## Architecture
+
+```
+openadapt_privacy/
+├── base.py           # ScrubbingProvider, TextScrubbingMixin
+├── config.py         # PrivacyConfig dataclass
+├── loaders.py        # Recording, Action, Screenshot, RecordingLoader
+├── providers/
+│   ├── __init__.py   # ScrubProvider registry
+│   └── presidio.py   # PresidioScrubbingProvider
+└── pipelines/
+    └── dicts.py      # scrub_dict, scrub_list_dicts
+```
+
+## License
+
+MIT

openadapt_privacy-0.1.0/README.md

@@ -0,0 +1,242 @@
+# openadapt-privacy
+
+Privacy scrubbing for GUI automation data - PII/PHI detection and redaction.
+
+## Installation
+
+```bash
+pip install openadapt-privacy
+```
+
+For Presidio-based scrubbing (recommended):
+
+```bash
+pip install openadapt-privacy[presidio]
+python -m spacy download en_core_web_trf
+```
+
+## Quick Start
+
+### Text Scrubbing
+
+```python
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+
+text = "Contact John Smith at john.smith@example.com or 555-123-4567"
+scrubbed = scrubber.scrub_text(text)
+```
+
+**Input:**
+```
+Contact John Smith at john.smith@example.com or 555-123-4567
+```
+
+**Output:**
+```
+Contact <PERSON> at <EMAIL_ADDRESS> or <PHONE_NUMBER>
+```
+
+### Example Inputs & Outputs
+
+| Input | Output |
+|-------|--------|
+| `My email is john@example.com` | `My email is <EMAIL_ADDRESS>` |
+| `SSN: 923-45-6789` | `SSN: <US_SSN>` |
+| `Card: 4532-1234-5678-9012` | `Card: <CREDIT_CARD>` |
+| `Call me at 555-123-4567` | `Call me at <PHONE_NUMBER>` |
+| `DOB: 01/15/1985` | `DOB: <DATE_TIME>` |
+| `Contact John Smith` | `Contact <PERSON>` |
+
+## Dict Scrubbing
+
+Scrub PII from nested dictionaries (e.g., GUI element trees):
+
+```python
+from openadapt_privacy import scrub_dict
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+action = {
+    "text": "Email: john@example.com",
+    "metadata": {
+        "title": "User Profile - John Smith",
+        "tooltip": "Click to contact john@example.com",
+    },
+    "coordinates": {"x": 100, "y": 200},
+}
+scrubbed = scrub_dict(action, scrubber)
+```
+
+**Input:**
+```json
+{
+    "text": "Email: john@example.com",
+    "metadata": {
+        "title": "User Profile - John Smith",
+        "tooltip": "Click to contact john@example.com"
+    },
+    "coordinates": {"x": 100, "y": 200}
+}
+```
+
+**Output:**
+```json
+{
+    "text": "Email: <EMAIL_ADDRESS>",
+    "metadata": {
+        "title": "User Profile - <PERSON>",
+        "tooltip": "Click to contact <EMAIL_ADDRESS>"
+    },
+    "coordinates": {"x": 100, "y": 200}
+}
+```
+
+## Recording Pipeline
+
+Process complete GUI automation recordings:
+
+```python
+from openadapt_privacy import DictRecordingLoader
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+loader = DictRecordingLoader()
+
+recording = loader.load_from_dict({
+    "task_description": "Send email to John Smith at john@example.com",
+    "actions": [
+        {"id": 1, "action_type": "click", "text": "Compose", "timestamp": 1000},
+        {"id": 2, "action_type": "type", "text": "john@example.com", "timestamp": 2000},
+        {"id": 3, "action_type": "click", "text": "Send", "window_title": "Email to john@example.com", "timestamp": 3000},
+    ],
+})
+
+scrubbed = recording.scrub(scrubber)
+```
+
+**Input Recording:**
+```
+task_description: "Send email to John Smith at john@example.com"
+
+actions:
+  [1] click: "Compose"
+  [2] type:  "john@example.com"
+  [3] click: "Send" (window: "Email to john@example.com")
+```
+
+**Output Recording:**
+```
+task_description: "Send email to <PERSON> at <EMAIL_ADDRESS>"
+
+actions:
+  [1] click: "Compose"
+  [2] type:  "<EMAIL_ADDRESS>"
+  [3] click: "Send" (window: "Email to <EMAIL_ADDRESS>")
+```
+
+## Image Scrubbing
+
+Redact PII from screenshots using OCR + NER:
+
+```python
+from PIL import Image
+from openadapt_privacy.providers.presidio import PresidioScrubbingProvider
+
+scrubber = PresidioScrubbingProvider()
+
+image = Image.open("screenshot.png")
+scrubbed_image = scrubber.scrub_image(image)
+scrubbed_image.save("screenshot_scrubbed.png")
+```
+
+**Input Screenshot:**
+
+![Original screenshot with PII](assets/screenshot_original.png)
+
+**Output Screenshot:**
+
+![Scrubbed screenshot with PII redacted](assets/screenshot_scrubbed.png)
+
+The image redactor:
+1. Runs OCR to detect text regions
+2. Analyzes text for PII entities (email, phone, SSN, etc.)
+3. Fills detected PII regions with solid color (configurable, default: red)
+
+## Custom Data Loader
+
+Implement your own loader for custom storage formats:
+
+```python
+from openadapt_privacy import RecordingLoader, Recording
+
+class SQLiteRecordingLoader(RecordingLoader):
+    def __init__(self, db_path: str):
+        self.db_path = db_path
+
+    def load(self, recording_id: str) -> Recording:
+        # Load from SQLite database
+        ...
+
+    def save(self, recording: Recording, recording_id: str) -> None:
+        # Save to SQLite database
+        ...
+
+# Usage
+loader = SQLiteRecordingLoader("recordings.db")
+scrubber = PresidioScrubbingProvider()
+
+# Load, scrub, and save
+scrubbed = loader.load_and_scrub("recording_001", scrubber)
+loader.save(scrubbed, "recording_001_scrubbed")
+```
+
+## Configuration
+
+```python
+from openadapt_privacy.config import PrivacyConfig
+
+custom_config = PrivacyConfig(
+    SCRUB_CHAR="X",                    # Character for scrub_text_all
+    SCRUB_FILL_COLOR=0xFF0000,         # Red for image redaction (BGR)
+    SCRUB_KEYS_HTML=[                  # Keys to scrub in dicts
+        "text", "value", "title", "tooltip", "custom_field"
+    ],
+    SCRUB_PRESIDIO_IGNORE_ENTITIES=[   # Entity types to skip
+        "DATE_TIME",
+    ],
+)
+```
+
+## Supported Entity Types
+
+| Entity | Example Input | Example Output |
+|--------|---------------|----------------|
+| `PERSON` | `John Smith` | `<PERSON>` |
+| `EMAIL_ADDRESS` | `john@example.com` | `<EMAIL_ADDRESS>` |
+| `PHONE_NUMBER` | `555-123-4567` | `<PHONE_NUMBER>` |
+| `US_SSN` | `923-45-6789` | `<US_SSN>` |
+| `CREDIT_CARD` | `4532-1234-5678-9012` | `<CREDIT_CARD>` |
+| `US_BANK_NUMBER` | `635526789012` | `<US_BANK_NUMBER>` |
+| `US_DRIVER_LICENSE` | `A123-456-789-012` | `<US_DRIVER_LICENSE>` |
+| `DATE_TIME` | `01/15/1985` | `<DATE_TIME>` |
+| `LOCATION` | `Toronto, ON` | `<LOCATION>` |
+
+## Architecture
+
+```
+openadapt_privacy/
+├── base.py           # ScrubbingProvider, TextScrubbingMixin
+├── config.py         # PrivacyConfig dataclass
+├── loaders.py        # Recording, Action, Screenshot, RecordingLoader
+├── providers/
+│   ├── __init__.py   # ScrubProvider registry
+│   └── presidio.py   # PresidioScrubbingProvider
+└── pipelines/
+    └── dicts.py      # scrub_dict, scrub_list_dicts
+```
+
+## License
+
+MIT

openadapt_privacy-0.1.0/openadapt_privacy/__init__.py

@@ -0,0 +1,43 @@
+"""OpenAdapt Privacy - PII/PHI detection and redaction for GUI automation data."""
+
+from openadapt_privacy.base import (
+    Modality,
+    ScrubbingProvider,
+    ScrubbingProviderFactory,
+    TextScrubbingMixin,
+)
+from openadapt_privacy.config import PrivacyConfig, config
+from openadapt_privacy.loaders import (
+    Action,
+    DictRecordingLoader,
+    Recording,
+    RecordingLoader,
+    Screenshot,
+)
+from openadapt_privacy.pipelines.dicts import DictScrubber, scrub_dict, scrub_list_dicts
+from openadapt_privacy.providers import ScrubProvider
+
+__version__ = "0.1.0"
+
+__all__ = [
+    # Base classes
+    "Modality",
+    "ScrubbingProvider",
+    "ScrubbingProviderFactory",
+    "TextScrubbingMixin",
+    # Config
+    "PrivacyConfig",
+    "config",
+    # Providers
+    "ScrubProvider",
+    # Pipelines
+    "DictScrubber",
+    "scrub_dict",
+    "scrub_list_dicts",
+    # Data loaders
+    "Action",
+    "Screenshot",
+    "Recording",
+    "RecordingLoader",
+    "DictRecordingLoader",
+]