fix: Add async/await, PDF metadata, and type safety fixes
This commit addresses multiple issues with async operations, PDF metadata extraction, and type safety in document processing and search. ## Async/Await Fixes - processor.py:259 - Added await for chunker.chunk_text(content) - processor.py:270 - Added await for bm25_service.encode_batch(chunk_texts) - tests/unit/test_document_chunker.py - Converted all 12 test methods to async ## PDF Metadata Enhancement - pymupdf.py:143 - Added file_size metadata extraction - pymupdf.py:145-206 - Refactored to extract text page-by-page - Manually loop through pages instead of using page_chunks=True - Generate page_boundaries metadata for precise page tracking - Works around pymupdf.layout.activate() breaking page_chunks=True - processor.py:32-66 - Added assign_page_numbers() helper function - Assigns page numbers to chunks based on overlap with page boundaries - Handles chunks spanning multiple pages - processor.py:298-300 - Call assign_page_numbers() for PDF files ## Type Safety Fixes - bm25_hybrid.py:184 - Removed int() conversion of doc_id - semantic.py:131 - Removed int() conversion of doc_id - viz_routes.py:275 - Removed int() conversion of doc_id - Added comments documenting that doc_id can be int (notes) or str (file paths) ## Testing - All 18 tests passing (12 unit + 6 integration) - No type errors in modified files - Container logs show successful processing - Vector viz searches working correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -130,6 +130,62 @@ class NextcloudClient:
|
||||
all_notes = self.notes.get_all_notes()
|
||||
return await self._notes_search.search_notes(all_notes, query)
|
||||
|
||||
async def find_files_by_tag(
|
||||
self, tag_name: str, mime_type_filter: str | None = None
|
||||
) -> list[dict]:
|
||||
"""Find files by system tag name, optionally filtered by MIME type.
|
||||
|
||||
This method coordinates tag lookup and file retrieval via WebDAV:
|
||||
1. Look up the tag ID by name
|
||||
2. Get all files with that tag (via REPORT with full metadata)
|
||||
3. Optionally filter by MIME type
|
||||
|
||||
Args:
|
||||
tag_name: Name of the system tag to search for (e.g., "vector-index")
|
||||
mime_type_filter: Optional MIME type filter (e.g., "application/pdf")
|
||||
|
||||
Returns:
|
||||
List of file dictionaries with WebDAV properties (path, size, content_type, etc.)
|
||||
|
||||
Raises:
|
||||
RuntimeError: If tag lookup or file query fails
|
||||
|
||||
Examples:
|
||||
# Find all files with "vector-index" tag
|
||||
files = await nc_client.find_files_by_tag("vector-index")
|
||||
|
||||
# Find only PDFs with the tag
|
||||
pdfs = await nc_client.find_files_by_tag("vector-index", "application/pdf")
|
||||
"""
|
||||
# Look up tag by name using WebDAV
|
||||
tag = await self.webdav.get_tag_by_name(tag_name)
|
||||
if not tag:
|
||||
logger.debug(f"Tag '{tag_name}' not found, returning empty list")
|
||||
return []
|
||||
|
||||
# Get files with this tag (returns full file info from REPORT)
|
||||
files = await self.webdav.get_files_by_tag(tag["id"])
|
||||
if not files:
|
||||
logger.debug(f"No files found with tag '{tag_name}'")
|
||||
return []
|
||||
|
||||
logger.debug(f"Found {len(files)} files with tag '{tag_name}'")
|
||||
|
||||
# Apply MIME type filter if specified
|
||||
if mime_type_filter:
|
||||
filtered_files = [
|
||||
f
|
||||
for f in files
|
||||
if f.get("content_type", "").startswith(mime_type_filter)
|
||||
]
|
||||
logger.info(
|
||||
f"Returning {len(filtered_files)} files with tag '{tag_name}' (filtered by {mime_type_filter})"
|
||||
)
|
||||
return filtered_files
|
||||
|
||||
logger.info(f"Returning {len(files)} files with tag '{tag_name}'")
|
||||
return files
|
||||
|
||||
def _get_webdav_base_path(self) -> str:
|
||||
"""Helper to get the base WebDAV path for the authenticated user."""
|
||||
return f"/remote.php/dav/files/{self.username}"
|
||||
|
||||
Reference in New Issue
Block a user