refactor: Transform document parsing into pluggable processor architecture
Refactors PR #190's hardcoded Unstructured.io integration into a flexible, extensible plugin system supporting multiple text extraction engines. - **`DocumentProcessor` ABC**: Abstract interface for all processors - **`ProcessorRegistry`**: Central registry for discovery and routing - **`ProcessingResult`**: Standardized output format across processors - **`UnstructuredProcessor`**: Refactored from `UnstructuredClient` - **`TesseractProcessor`**: Local OCR for images (lightweight alternative) - **`CustomHTTPProcessor`**: Generic wrapper for custom HTTP APIs - New `get_document_processor_config()` returns structured config - Supports enabling/disabling individual processors - Per-processor configuration via environment variables - **Breaking Change**: `ENABLE_UNSTRUCTURED_PARSING` replaced with: - `ENABLE_DOCUMENT_PROCESSING=true/false` (master switch) - `ENABLE_UNSTRUCTURED=true/false` (per-processor) - `ENABLE_TESSERACT=true/false` - `ENABLE_CUSTOM_PROCESSOR=true/false` - `parse_document()` now uses `ProcessorRegistry` - Auto-selects appropriate processor based on MIME type - Processor priority system (Unstructured=10, Tesseract=5, Custom=1) - `initialize_document_processors()` registers processors at startup - Integrated into both BasicAuth and OAuth lifespans - Graceful degradation if processors fail to initialize ```env ENABLE_DOCUMENT_PROCESSING=false ENABLE_UNSTRUCTURED=false UNSTRUCTURED_API_URL=http://unstructured:8000 UNSTRUCTURED_STRATEGY=auto # auto|fast|hi_res UNSTRUCTURED_LANGUAGES=eng,deu ENABLE_TESSERACT=false TESSERACT_LANG=eng ENABLE_CUSTOM_PROCESSOR=false CUSTOM_PROCESSOR_URL=http://localhost:9000/process CUSTOM_PROCESSOR_TYPES=application/pdf,image/jpeg ``` - **Removed**: `tests/test_unstructured_config.py` (legacy tests) - **Added**: `tests/unit/test_document_processor_config.py` - 7 unit tests for new config system - Tests individual and multi-processor configurations - **Added**: - `nextcloud_mcp_server/document_processors/__init__.py` - `nextcloud_mcp_server/document_processors/base.py` - `nextcloud_mcp_server/document_processors/registry.py` - `nextcloud_mcp_server/document_processors/unstructured.py` - `nextcloud_mcp_server/document_processors/tesseract.py` - `nextcloud_mcp_server/document_processors/custom_http.py` - `tests/unit/test_document_processor_config.py` - **Modified**: - `nextcloud_mcp_server/config.py` - New plugin config system - `nextcloud_mcp_server/app.py` - Processor initialization - `nextcloud_mcp_server/utils/document_parser.py` - Uses registry - `nextcloud_mcp_server/server/webdav.py` - Import updates - `env.sample` - New configuration format - `docker-compose.yml` - (profile changes from previous work) - **Removed**: - `nextcloud_mcp_server/client/unstructured_client.py` - Replaced by UnstructuredProcessor - `tests/test_unstructured_config.py` - Replaced with new tests ✅ **Extensible**: Add processors without modifying core code ✅ **Testable**: Mock processors for unit tests ✅ **Configurable**: Enable only needed processors ✅ **Flexible**: Choose fast (Tesseract) vs accurate (Unstructured) ✅ **Opt-in**: Disabled by default, no mandatory dependencies Users upgrading from PR #190 need to update environment variables: ```bash ENABLE_UNSTRUCTURED_PARSING=true ENABLE_DOCUMENT_PROCESSING=true ENABLE_UNSTRUCTURED=true ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
@@ -0,0 +1,146 @@
|
||||
"""Generic HTTP API processor wrapper for custom document processing services."""
|
||||
|
||||
import logging
|
||||
from typing import Any, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from .base import DocumentProcessor, ProcessingResult, ProcessorError
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class CustomHTTPProcessor(DocumentProcessor):
|
||||
"""Generic HTTP API processor wrapper.
|
||||
|
||||
Allows integration with any custom document processing API that follows
|
||||
a simple request/response pattern. This makes it easy to integrate your
|
||||
own text extraction services without writing a full processor.
|
||||
|
||||
Expected API Contract:
|
||||
- POST request with file as multipart/form-data
|
||||
- Response: {"text": "extracted text", "metadata": {...}}
|
||||
|
||||
Example:
|
||||
processor = CustomHTTPProcessor(
|
||||
name="my_ocr",
|
||||
api_url="https://my-ocr-service.com/process",
|
||||
api_key="secret",
|
||||
supported_types={"application/pdf", "image/jpeg"},
|
||||
)
|
||||
result = await processor.process(pdf_bytes, "application/pdf")
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
api_url: str,
|
||||
api_key: Optional[str] = None,
|
||||
timeout: int = 60,
|
||||
supported_types: Optional[set[str]] = None,
|
||||
name: str = "custom",
|
||||
):
|
||||
"""Initialize custom HTTP processor.
|
||||
|
||||
Args:
|
||||
api_url: Your API endpoint (should accept POST with multipart/form-data)
|
||||
api_key: Optional API key for authentication (sent as Bearer token)
|
||||
timeout: Request timeout in seconds (default: 60)
|
||||
supported_types: MIME types your API supports
|
||||
name: Unique name for this processor (default: "custom")
|
||||
"""
|
||||
self.api_url = api_url
|
||||
self.api_key = api_key
|
||||
self.timeout = timeout
|
||||
self._name = name
|
||||
self._supported_types = supported_types or set()
|
||||
|
||||
logger.info(f"Initialized CustomHTTPProcessor: {name} -> {api_url}")
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return self._name
|
||||
|
||||
@property
|
||||
def supported_mime_types(self) -> set[str]:
|
||||
return self._supported_types
|
||||
|
||||
async def process(
|
||||
self,
|
||||
content: bytes,
|
||||
content_type: str,
|
||||
filename: Optional[str] = None,
|
||||
options: Optional[dict[str, Any]] = None,
|
||||
) -> ProcessingResult:
|
||||
"""Process via custom HTTP API.
|
||||
|
||||
Args:
|
||||
content: Document bytes
|
||||
content_type: MIME type
|
||||
filename: Optional filename
|
||||
options: Custom options (passed as form data to API)
|
||||
|
||||
Returns:
|
||||
ProcessingResult with extracted text and metadata
|
||||
|
||||
Raises:
|
||||
ProcessorError: If API call fails
|
||||
"""
|
||||
options = options or {}
|
||||
|
||||
# Prepare request
|
||||
files = {"file": (filename or "document", content, content_type)}
|
||||
headers = {}
|
||||
|
||||
if self.api_key:
|
||||
headers["Authorization"] = f"Bearer {self.api_key}"
|
||||
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=self.timeout) as client:
|
||||
response = await client.post(
|
||||
self.api_url,
|
||||
files=files,
|
||||
headers=headers,
|
||||
data=options, # Pass options as form data
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
# Parse response
|
||||
result = response.json()
|
||||
text = result.get("text", "")
|
||||
metadata = result.get("metadata", {})
|
||||
|
||||
logger.debug(
|
||||
f"Custom processor '{self.name}' extracted {len(text)} characters"
|
||||
)
|
||||
|
||||
return ProcessingResult(
|
||||
text=text,
|
||||
metadata=metadata,
|
||||
processor=self.name,
|
||||
success=True,
|
||||
)
|
||||
|
||||
except httpx.HTTPError as e:
|
||||
logger.error(f"Custom processor '{self.name}' HTTP error: {e}")
|
||||
raise ProcessorError(f"API call failed: {str(e)}") from e
|
||||
except Exception as e:
|
||||
logger.error(f"Custom processor '{self.name}' failed: {e}")
|
||||
raise ProcessorError(f"Processing failed: {str(e)}") from e
|
||||
|
||||
async def health_check(self) -> bool:
|
||||
"""Check if custom API is available.
|
||||
|
||||
Returns:
|
||||
True if API responds with status < 500
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5) as client:
|
||||
# Try GET request to check availability
|
||||
response = await client.get(
|
||||
self.api_url,
|
||||
headers={"User-Agent": "nextcloud-mcp-server"},
|
||||
)
|
||||
return response.status_code < 500
|
||||
except Exception as e:
|
||||
logger.warning(f"Custom processor '{self.name}' health check failed: {e}")
|
||||
return False
|
||||
Reference in New Issue
Block a user