Test and release pipeline

.github/workflows/ci.yml

@@ -0,0 +1,40 @@
+name: CI
+
+on: 
+  push:
+    branches: 
+      - "main"
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Test
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: true
+      matrix:
+        python: [3.12, 3.13]
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 1
+
+    - name: Install the latest version of uv and set the python version
+      uses: astral-sh/setup-uv@v6.7.0
+      with:
+        enable-cache: true
+        python-version: ${{ matrix.python }}
+
+    - name: Pull dependencies
+      run: uv sync --all-extras --all-groups
+
+    - name: Execute tests
+      run: uv run pytest

.github/workflows/lint.yml

@@ -0,0 +1,35 @@
+name: Lint
+
+on:
+  push:
+    paths:
+      - '**.py'
+      - '.github/workflows/lint.yml'
+
+permissions:
+  contents: write
+
+jobs:
+  lint:
+    name: Lint Shell scripts
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 1
+
+    - uses: astral-sh/setup-uv@v6.7.0
+
+    - name: Ruff lint
+      run: uv run ruff check --exit-zero .
+
+    - name: Ruff format
+      run: uv run ruff format .
+
+    - name: Commit changes
+      uses: stefanzweifel/git-auto-commit-action@v5
+      with:
+        commit_message: Fix styling
+
+

.github/workflows/release.yml

@@ -0,0 +1,69 @@
+name: Publish on PyPI
+
+on: 
+  push:
+    branches: 
+      - "main"
+  release:
+    types: [created]
+
+permissions:
+  contents: read
+
+jobs:
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 1
+
+    - name: Install the latest version of uv and set the python version
+      uses: astral-sh/setup-uv@v6.7.0
+      with:
+        python-version: "3.12"
+
+    - name: Build wheel
+      run: |
+        uv build
+
+    # Smoke test the build for packaging errors
+    - name: Smoke test (wheel)
+      run: uv run --isolated --no-project --with dist/*.whl tests/smoke_test.py
+    - name: Smoke test (source distribution)
+      run: uv run --isolated --no-project --with dist/*.tar.gz tests/smoke_test.py
+
+    - name: Upload build for publishing
+      uses: actions/upload-artifact@v4
+      with:
+        name: parxy_release
+        if-no-files-found: error
+        retention-days: 1
+        path: dist/*
+
+  pypi:
+    name: Upload release to PyPI
+    runs-on: ubuntu-latest
+    needs: build
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Install the latest version of uv and set the python version
+        uses: astral-sh/setup-uv@v6.7.0
+        if: github.event_name == 'release'
+        with:
+          enable-cache: false
+          ignore-empty-workdir: true
+          python-version: "3.12"
+
+      - name: Download build
+        uses: actions/download-artifact@v4
+        with:
+          name: parxy_release
+          path: dist
+
+      - name: Publish package distributions to PyPI
+        if: github.event_name == 'release'
+        run: uv publish

README.md

@@ -1,5 +1,5 @@
-[![CI](https://github.com/OneOffTech/parxy/actions/workflows/ci.yml/badge.svg)](https://github.com/OneOffTech/parxy/actions/workflows/ci.yml) [![Build Docker Image](https://github.com/OneOffTech/parxy/actions/workflows/docker.yml/badge.svg)](https://github.com/OneOffTech/parxy/actions/workflows/docker.yml)
- [![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+![pypi](https://img.shields.io/pypi/v/parxy.svg)
+[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://docs.pydantic.dev/latest/contributing/#badges) [![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv) [![CI](https://github.com/OneOffTech/parxy/actions/workflows/ci.yml/badge.svg)](https://github.com/OneOffTech/parxy/actions/workflows/ci.yml)
 
 # OneOffTech Parxy
 
@@ -36,13 +36,13 @@ Parxy is available as a standalone command line and a library. The quickest way
 Use with minimal footprint (fewer drivers supported):
 
 ```bash
-uvx --from "git+https://github.com/oneofftech/parxy.git" parxy --help
+uvx parxy --help
 ```
 
 Use all supported drivers:
 
 ```bash
-uvx --from "git+https://github.com/oneofftech/parxy.git[all]" parxy --help
+uvx parxy[all] --help
 ```
 
 See [Supported services](#supported-services) for the list of included drivers and their extras for the installation.

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "parxy-core"
+name = "parxy"
 version = "0.1.0"
 description = "Parxy document processing gateway"
 readme = "README.md"

src/__main__.py

@@ -1,4 +1,4 @@
 from parxy_cli import cli
 
-if __name__ == "__main__":
-    cli()
+if __name__ == '__main__':
+    cli()

src/parxy_cli/cli.py

@@ -8,7 +8,6 @@
 import typer
 from rich import print
 from rich.console import Console
-from rich.table import Table
 
 from parxy_core.facade import Parxy
 
@@ -93,7 +92,7 @@ def parse(
         # Process each file
         for file_path in files:
             try:
-                console.print(f'----')
+                console.print('----')
 
                 # Parse the document
                 doc = Parxy.parse(

src/parxy_core/drivers/abstract_driver.py

@@ -121,7 +121,7 @@ def parse(
 
         except Exception as ex:
             self._logger.error(
-                f'Error while parsing file',
+                'Error while parsing file',
                 file,
                 self.__class__.__name__,
                 exc_info=True,

src/parxy_core/drivers/llamaparse.py

@@ -1,6 +1,5 @@
 import io
-from typing import TYPE_CHECKING, Dict, Any, Optional, Union
-from logging import Logger
+from typing import TYPE_CHECKING
 
 # Type hints that will be available at runtime when llama_cloud_services is installed
 if TYPE_CHECKING:
@@ -51,7 +50,7 @@ def _initialize_driver(self):
         except ImportError as e:
             raise ImportError(
                 'LlamaParse dependencies not installed. '
-                "Install with 'pip install parxy-core[llama]'"
+                "Install with 'pip install parxy[llama]'"
             ) from e
 
         self.__client = LlamaParse(**self._config)
@@ -123,7 +122,7 @@ def _handle(
             # For all other errors, raise as parsing exception
             raise ParsingException(str(ex), self.__class__) from ex
 
-        if not res.error is None:
+        if res.error is not None:
             raise ParsingException(
                 res.error, self.__class__, res.model_dump(exclude={'file_name'})
             )

src/parxy_core/drivers/llmwhisperer.py

@@ -2,9 +2,7 @@
 
 import validators
 
-from typing import TYPE_CHECKING, Dict, Any
-
-from logging import Logger
+from typing import TYPE_CHECKING
 
 
 # Type hints that will be available at runtime when llm whisperer is installed
@@ -50,7 +48,7 @@ def _initialize_driver(self):
         except ImportError as e:
             raise ImportError(
                 'LlmWhisperer dependencies not installed. '
-                "Install with 'pip install parxy-core[llmwhisperer]'"
+                "Install with 'pip install parxy[llmwhisperer]'"
             ) from e
 
         self.__client = LLMWhispererClientV2(**self._config)

src/parxy_core/drivers/pdfact.py

@@ -1,11 +1,10 @@
 import io
-from typing import Optional, Dict, Any
+from typing import Optional
 
 import requests
 import validators
 
 from urllib.parse import urljoin
-from logging import Logger
 
 from parxy_core.drivers import Driver
 from parxy_core.models import (

src/parxy_core/drivers/unstructured_local.py

@@ -43,7 +43,7 @@ def _initialize_driver(self):
         except ImportError as e:
             raise ImportError(
                 'Unstructured dependencies not installed. '
-                "Install with 'pip install parxy-core[unstructured_local]'"
+                "Install with 'pip install parxy[unstructured_local]'"
             ) from e
 
     def _handle(

src/parxy_core/exceptions/__init__.py

@@ -1,4 +1,10 @@
-from parxy_core.exceptions.authentication_exception import AuthenticationException as AuthenticationException
+from parxy_core.exceptions.authentication_exception import (
+    AuthenticationException as AuthenticationException,
+)
 from parxy_core.exceptions.parsing_exception import ParsingException as ParsingException
-from parxy_core.exceptions.file_not_found_exception import FileNotFoundException as FileNotFoundException
-from parxy_core.exceptions.unsupported_format_exception import UnsupportedFormatException as UnsupportedFormatException
+from parxy_core.exceptions.file_not_found_exception import (
+    FileNotFoundException as FileNotFoundException,
+)
+from parxy_core.exceptions.unsupported_format_exception import (
+    UnsupportedFormatException as UnsupportedFormatException,
+)

src/parxy_core/exceptions/authentication_exception.py

@@ -1,6 +1,6 @@
 class AuthenticationException(Exception):
     """Exception raised for authentication errors.
-    
+
     This exception should be raised when authentication fails with external services
     or APIs, such as invalid API keys, expired tokens, or insufficient permissions.
 
@@ -51,7 +51,7 @@ def __str__(self) -> str:
         str
             Formatted error message including service name and details
         """
-        base_message = f"Authentication failed for {self.service}: {self.message}"
+        base_message = f'Authentication failed for {self.service}: {self.message}'
         if self.details:
-            return f"{base_message}\nDetails: {self.details}"
-        return base_message
+            return f'{base_message}\nDetails: {self.details}'
+        return base_message

src/parxy_core/exceptions/file_not_found_exception.py

@@ -1,6 +1,6 @@
 class FileNotFoundException(FileNotFoundError):
     """Exception raised for file not found errors.
-    
+
     This exception is raised when a file cannot be accessed for parsing.
 
     Attributes
@@ -50,7 +50,7 @@ def __str__(self) -> str:
         str
             Formatted error message including service name and details
         """
-        base_message = f"Parsing failed for {self.service}: {self.message}"
+        base_message = f'Parsing failed for {self.service}: {self.message}'
         if self.details:
-            return f"{base_message}\nDetails: {self.details}"
-        return base_message
+            return f'{base_message}\nDetails: {self.details}'
+        return base_message

src/parxy_core/exceptions/parsing_exception.py

@@ -1,6 +1,6 @@
 class ParsingException(Exception):
     """Exception raised for parsing errors.
-    
+
     This exception is raised when parsing document fails.
 
     Attributes
@@ -50,7 +50,7 @@ def __str__(self) -> str:
         str
             Formatted error message including service name and details
         """
-        base_message = f"Parsing failed for {self.service}: {self.message}"
+        base_message = f'Parsing failed for {self.service}: {self.message}'
         if self.details:
-            return f"{base_message}\nDetails: {self.details}"
-        return base_message
+            return f'{base_message}\nDetails: {self.details}'
+        return base_message

src/parxy_core/exceptions/unsupported_format_exception.py

@@ -1,6 +1,6 @@
 class UnsupportedFormatException(Exception):
     """Exception raised for file format not supported.
-    
+
     This exception is raised when a file is of a format not supported by the parsing service.
 
     Attributes
@@ -50,7 +50,7 @@ def __str__(self) -> str:
         str
             Formatted error message including service name and details
         """
-        base_message = f"Unsupported format for {self.service}: {self.message}"
+        base_message = f'Unsupported format for {self.service}: {self.message}'
         if self.details:
-            return f"{base_message}\nDetails: {self.details}"
-        return base_message
+            return f'{base_message}\nDetails: {self.details}'
+        return base_message