fix(review): close doc via try/finally; don't count parse failures as indexed
Address PR #852 review: - pymupdf.py: the metadata `doc` was only closed on the PdfParseFailed and success paths, so a failure in `_extract_metadata`/`mkdir`/`get_settings` leaked it. `doc` is only needed for metadata + page_count (the heavy parse works from `content` bytes in the worker), so open it, read metadata, and close it immediately under try/finally; drop the two later doc.close() calls. - processor.py: a permanent parse failure early-returned from `_index_document`, after which `process_document` still recorded record_qdrant_operation("upsert", "success") + record_vector_sync_processing(success) -- counting an OOM/timeout bomb as astrolabe_documents_indexed_total{status="success"}. `_index_document` now returns False on that path and the caller skips the success metrics (the failure is already recorded via document_parse_failed_total + the registry's document_parse_total{error}). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
7db8d3e301
commit
7ec116a3c7
@@ -107,14 +107,19 @@ class PyMuPDFProcessor(DocumentProcessor):
|
||||
if progress_callback:
|
||||
await progress_callback(0, 100, "Opening PDF document")
|
||||
|
||||
# Open document and extract metadata in thread
|
||||
# Open document only to read metadata + page count, then close it
|
||||
# immediately (try/finally so a failure in _extract_metadata can't
|
||||
# leak it). The heavy extraction below works from ``content`` bytes
|
||||
# in the isolated worker, so ``doc`` is not needed past this point.
|
||||
doc = await anyio.to_thread.run_sync( # type: ignore[attr-defined]
|
||||
lambda: pymupdf.open("pdf", content)
|
||||
)
|
||||
|
||||
metadata = self._extract_metadata(doc, filename)
|
||||
metadata["file_size"] = len(content)
|
||||
page_count = doc.page_count
|
||||
try:
|
||||
metadata = self._extract_metadata(doc, filename)
|
||||
metadata["file_size"] = len(content)
|
||||
page_count = doc.page_count
|
||||
finally:
|
||||
doc.close()
|
||||
|
||||
if progress_callback:
|
||||
await progress_callback(10, 100, f"Extracting {page_count} pages")
|
||||
@@ -143,7 +148,6 @@ class PyMuPDFProcessor(DocumentProcessor):
|
||||
mem_limit_mb=settings.document_parse_mem_limit_mb,
|
||||
)
|
||||
except PdfParseFailed as exc:
|
||||
doc.close()
|
||||
logger.warning(
|
||||
"Isolated PDF parse failed for %s (reason=%s): %s",
|
||||
filename or "<bytes>",
|
||||
@@ -198,9 +202,6 @@ class PyMuPDFProcessor(DocumentProcessor):
|
||||
metadata["image_paths"] = image_paths
|
||||
metadata["page_boundaries"] = page_boundaries
|
||||
|
||||
# Close document
|
||||
doc.close()
|
||||
|
||||
if progress_callback:
|
||||
await progress_callback(100, 100, "Processing complete")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user