mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-10-12 02:57:12 +00:00
jurassicparkicecreamandshamoon
62cc31fbdb
* Feature: store barcode contents, list and search them New setting PAPERLESS_CONSUMER_STORE_BARCODE_VALUES (off by default) stores all barcodes found during consumption with the document: page, type and content. They are listed on the metadata tab with a copy button, returned by the documents API and searchable with barcodes: in the advanced search. Versions keep their own barcodes, reprocessing reads them again. Refs #9898 * Tests: cover the remaining barcode branches Covers unchanged and failing barcode reads on reprocessing, unsupported files and DocumentBarcode.__str__, and uses toHaveLength in the barcode list spec as suggested by SonarCloud. * Address review: keep barcodes when they can't be read, format choices - Reprocessing and new versions keep the stored barcodes when the file can't be scanned or the scan fails, and replace them atomically. - Format is a TextChoices of the zxing-cpp formats, with a test. - Shared scan code, latest_version helper, TypedDict, serializer reuse. - Barcodes in the split manifest, export/import tests, pytest-style tests. * Barcode tests: TIFF reprocess, format check both ways, fixtures - Reprocessing a TIFF with TIFF support off keeps the stored barcodes. - The format test also fails when zxing-cpp drops a format. - Fixtures in place of the sample dir mixin, plugin-level disabled test. - Format labels aren't translated, OpenAPI enum named BarcodeFormatEnum. * Review: module-level zxing reader, shorter barcode docs - read_barcodes_zxing is a module-level function used by scan_pdf. - Drop the trivial __str__ test, mark it no cover. - Shorten the barcode docs and remove the duplicate in configuration.md. * Fix header * Use utility class * Return barcodes from the metadata endpoint only Drop the barcodes field and its prefetches from the document serializer, as agreed in the review. Also remove the now empty component stylesheet. --------- Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
105 lines
3.7 KiB
Python
105 lines
3.7 KiB
Python
import logging
|
|
|
|
from django.conf import settings
|
|
from django.db import transaction
|
|
|
|
from documents.management.commands.base import PaperlessCommand
|
|
from documents.models import Document
|
|
from documents.search import get_backend
|
|
from documents.search import needs_rebuild
|
|
from documents.search import reset_backend
|
|
from documents.search import wipe_index
|
|
|
|
logger = logging.getLogger("paperless.management.document_index")
|
|
|
|
|
|
class Command(PaperlessCommand):
|
|
"""
|
|
Django management command for search index operations.
|
|
|
|
Provides subcommands for reindexing documents and optimizing the search index.
|
|
Supports conditional reindexing based on schema version and language changes.
|
|
"""
|
|
|
|
help = "Manages the document index."
|
|
|
|
supports_progress_bar = True
|
|
supports_multiprocessing = False
|
|
|
|
def add_arguments(self, parser):
|
|
super().add_arguments(parser)
|
|
parser.add_argument("command", choices=["reindex", "optimize"])
|
|
parser.add_argument(
|
|
"--recreate",
|
|
action="store_true",
|
|
default=False,
|
|
help="Wipe and recreate the index from scratch (only used with reindex).",
|
|
)
|
|
parser.add_argument(
|
|
"--if-needed",
|
|
action="store_true",
|
|
default=False,
|
|
help=(
|
|
"Skip reindex if the index is already up to date. "
|
|
"Checks schema version and search language sentinels. "
|
|
"Safe to run on every startup or upgrade."
|
|
),
|
|
)
|
|
parser.add_argument(
|
|
"--heap-size-mb",
|
|
type=int,
|
|
default=None,
|
|
help=(
|
|
"Tantivy writer memory budget in MB for a full reindex "
|
|
"(split across writer threads). Defaults to 512MB; lower "
|
|
"this on memory-constrained hosts. Larger values buffer "
|
|
"more documents before flushing a segment, deferring "
|
|
"merge work rather than avoiding it."
|
|
),
|
|
)
|
|
|
|
def handle(self, *args, **options):
|
|
with transaction.atomic():
|
|
if options["command"] == "reindex":
|
|
if options.get("if_needed") and not needs_rebuild(settings.INDEX_DIR):
|
|
self.stdout.write("Search index is up to date.")
|
|
return
|
|
if options.get("recreate"):
|
|
wipe_index(settings.INDEX_DIR)
|
|
|
|
documents = Document.objects.select_related(
|
|
"correspondent",
|
|
"document_type",
|
|
"storage_path",
|
|
"owner",
|
|
).prefetch_related(
|
|
"tags",
|
|
"notes__user",
|
|
"custom_fields__field",
|
|
"versions",
|
|
"barcodes",
|
|
"versions__barcodes",
|
|
)
|
|
total = documents.count()
|
|
rebuild_kwargs = {}
|
|
if options.get("heap_size_mb") is not None:
|
|
rebuild_kwargs["writer_heap_bytes"] = (
|
|
options["heap_size_mb"] * 1_000_000
|
|
)
|
|
get_backend().rebuild(
|
|
documents,
|
|
iter_wrapper=lambda pairs: self.track(
|
|
pairs,
|
|
description="Indexing documents...",
|
|
total=total,
|
|
),
|
|
**rebuild_kwargs,
|
|
)
|
|
reset_backend()
|
|
|
|
elif options["command"] == "optimize":
|
|
logger.info(
|
|
"document_index optimize is a no-op — Tantivy manages "
|
|
"segment merging automatically.",
|
|
)
|