paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-09-01 01:46:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

fixes #90

Browse Source
This commit is contained in:
jonaswinkler
2020-12-08 13:54:35 +01:00
parent c240fa1883
commit 9da11f29c7
10 changed files with 245 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
src/documents/consumer.py
View File

@@ -8,13 +8,14 @@ from django.conf import settings
from django.db import transaction
from django.db.models import Q
from django.utils import timezone
from filelock import FileLock
from .classifier import DocumentClassifier, IncompatibleClassifierVersionError
from .file_handling import create_source_path_directory
from .file_handling import create_source_path_directory, \
generate_unique_filename
from .loggers import LoggingMixin
from .models import Document, FileInfo, Correspondent, DocumentType, Tag
from .parsers import ParseError, get_parser_class_for_mime_type, \
get_supported_file_extensions, parse_date
from .parsers import ParseError, get_parser_class_for_mime_type, parse_date
from .signals import (
document_consumption_finished,
document_consumption_started
@@ -38,6 +39,10 @@ class Consumer(LoggingMixin):
def pre_check_file_exists(self):
if not os.path.isfile(self.path):
self.log(
"error",
"Cannot consume {}: It is not a file.".format(self.path)
)
raise ConsumerError("Cannot consume {}: It is not a file".format(
self.path))
@@ -47,6 +52,10 @@ class Consumer(LoggingMixin):
if Document.objects.filter(Q(checksum=checksum) | Q(archive_checksum=checksum)).exists(): # NOQA: E501
if settings.CONSUMER_DELETE_DUPLICATES:
os.unlink(self.path)
self.log(
"error",
"Not consuming {}: It is a duplicate.".format(self.filename)
)
raise ConsumerError(
"Not consuming {}: It is a duplicate.".format(self.filename)
)
@@ -148,8 +157,9 @@ class Consumer(LoggingMixin):
classifier = DocumentClassifier()
classifier.reload()
except (FileNotFoundError, IncompatibleClassifierVersionError) as e:
logging.getLogger(__name__).warning(
"Cannot classify documents: {}.".format(e))
self.log(
"warning",
f"Cannot classify documents: {e}.")
classifier = None
# now that everything is done, we can start to store the document
@@ -176,31 +186,26 @@ class Consumer(LoggingMixin):
# After everything is in the database, copy the files into
# place. If this fails, we'll also rollback the transaction.
with FileLock(settings.MEDIA_LOCK):
document.filename = generate_unique_filename(
document, settings.ORIGINALS_DIR)
create_source_path_directory(document.source_path)
# TODO: not required, since this is done by the file handling
# logic
create_source_path_directory(document.source_path)
self._write(document.storage_type,
self.path, document.source_path)
self._write(document.storage_type,
thumbnail, document.thumbnail_path)
if archive_path and os.path.isfile(archive_path):
self._write(document.storage_type,
archive_path, document.archive_path)
self.path, document.source_path)
with open(archive_path, 'rb') as f:
document.archive_checksum = hashlib.md5(
f.read()).hexdigest()
document.save()
self._write(document.storage_type,
thumbnail, document.thumbnail_path)
if archive_path and os.path.isfile(archive_path):
create_source_path_directory(document.archive_path)
self._write(document.storage_type,
archive_path, document.archive_path)
with open(archive_path, 'rb') as f:
document.archive_checksum = hashlib.md5(
f.read()).hexdigest()
# Afte performing all database operations and moving files
# into place, tell paperless where the file is.
document.filename = os.path.basename(document.source_path)
# Saving the document now will trigger the filename handling
# logic.
document.save()
# Delete the file only if it was successfully consumed