paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'feature-websockets-status' into dev

Browse Source
This commit is contained in:
jonaswinkler
2021-01-31 14:37:15 +01:00
parent 8cd1dd71e8 46ea86a6d2
commit fd59def1bd
45 changed files with 1763 additions and 371 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
src/documents/consumer.py
View File

@@ -1,9 +1,12 @@
import datetime
import hashlib
import os
import uuid
from subprocess import Popen
import magic
from asgiref.sync import async_to_sync
from channels.layers import get_channel_layer
from django.conf import settings
from django.db import transaction
from django.db.models import Q
@@ -27,8 +30,43 @@ class ConsumerError(Exception):
pass
MESSAGE_DOCUMENT_ALREADY_EXISTS = "document_already_exists"
MESSAGE_FILE_NOT_FOUND = "file_not_found"
MESSAGE_PRE_CONSUME_SCRIPT_NOT_FOUND = "pre_consume_script_not_found"
MESSAGE_PRE_CONSUME_SCRIPT_ERROR = "pre_consume_script_error"
MESSAGE_POST_CONSUME_SCRIPT_NOT_FOUND = "post_consume_script_not_found"
MESSAGE_POST_CONSUME_SCRIPT_ERROR = "post_consume_script_error"
MESSAGE_NEW_FILE = "new_file"
MESSAGE_UNSUPPORTED_TYPE = "unsupported_type"
MESSAGE_PARSING_DOCUMENT = "parsing_document"
MESSAGE_GENERATING_THUMBNAIL = "generating_thumbnail"
MESSAGE_PARSE_DATE = "parse_date"
MESSAGE_SAVE_DOCUMENT = "save_document"
MESSAGE_FINISHED = "finished"
class Consumer(LoggingMixin):
def _send_progress(self, current_progress, max_progress, status,
message=None, document_id=None):
payload = {
'filename': os.path.basename(self.filename) if self.filename else None, # NOQA: E501
'task_id': self.task_id,
'current_progress': current_progress,
'max_progress': max_progress,
'status': status,
'message': message,
'document_id': document_id
}
async_to_sync(self.channel_layer.group_send)("status_updates",
{'type': 'status_update',
'data': payload})
def _fail(self, message, log_message=None):
self._send_progress(100, 100, 'FAILED', message)
self.log("error", log_message or message)
raise ConsumerError(f"{self.filename}: {log_message or message}")
def __init__(self):
super().__init__()
self.path = None
@@ -37,15 +75,16 @@ class Consumer(LoggingMixin):
self.override_correspondent_id = None
self.override_tag_ids = None
self.override_document_type_id = None
self.task_id = None
self.channel_layer = get_channel_layer()
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)
self._fail(
MESSAGE_FILE_NOT_FOUND,
f"Cannot consume {self.path}: File not found."
)
raise ConsumerError("Cannot consume {}: It is not a file".format(
self.path))
def pre_check_duplicate(self):
with open(self.path, "rb") as f:
@@ -53,12 +92,9 @@ 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)
self._fail(
MESSAGE_DOCUMENT_ALREADY_EXISTS,
f"Not consuming {self.filename}: It is a duplicate."
)
def pre_check_directories(self):
@@ -72,14 +108,16 @@ class Consumer(LoggingMixin):
return
if not os.path.isfile(settings.PRE_CONSUME_SCRIPT):
raise ConsumerError(
self._fail(
MESSAGE_PRE_CONSUME_SCRIPT_NOT_FOUND,
f"Configured pre-consume script "
f"{settings.PRE_CONSUME_SCRIPT} does not exist.")
try:
Popen((settings.PRE_CONSUME_SCRIPT, self.path)).wait()
except Exception as e:
raise ConsumerError(
self._fail(
MESSAGE_PRE_CONSUME_SCRIPT_ERROR,
f"Error while executing pre-consume script: {e}"
)
@@ -88,9 +126,11 @@ class Consumer(LoggingMixin):
return
if not os.path.isfile(settings.POST_CONSUME_SCRIPT):
raise ConsumerError(
self._fail(
MESSAGE_POST_CONSUME_SCRIPT_NOT_FOUND,
f"Configured post-consume script "
f"{settings.POST_CONSUME_SCRIPT} does not exist.")
f"{settings.POST_CONSUME_SCRIPT} does not exist."
)
try:
Popen((
@@ -106,8 +146,9 @@ class Consumer(LoggingMixin):
"name", flat=True)))
)).wait()
except Exception as e:
raise ConsumerError(
f"Error while executing pre-consume script: {e}"
self._fail(
MESSAGE_POST_CONSUME_SCRIPT_ERROR,
f"Error while executing post-consume script: {e}"
)
def try_consume_file(self,
@@ -116,7 +157,8 @@ class Consumer(LoggingMixin):
override_title=None,
override_correspondent_id=None,
override_document_type_id=None,
override_tag_ids=None):
override_tag_ids=None,
task_id=None):
"""
Return the document object if it was successfully created.
"""
@@ -127,6 +169,9 @@ class Consumer(LoggingMixin):
self.override_correspondent_id = override_correspondent_id
self.override_document_type_id = override_document_type_id
self.override_tag_ids = override_tag_ids
self.task_id = task_id or str(uuid.uuid4())
self._send_progress(0, 100, 'STARTING', MESSAGE_NEW_FILE)
# this is for grouping logging entries for this particular file
# together.
@@ -149,11 +194,12 @@ class Consumer(LoggingMixin):
parser_class = get_parser_class_for_mime_type(mime_type)
if not parser_class:
raise ConsumerError(
f"Unsupported mime type {mime_type} of file {self.filename}")
self._fail(
MESSAGE_UNSUPPORTED_TYPE,
f"Unsupported mime type {mime_type}"
)
else:
self.log("debug",
f"Parser: {parser_class.__name__}")
self.log("debug", f"Parser: {parser_class.__name__}")
# Notify all listeners that we're going to do some work.
@@ -165,35 +211,50 @@ class Consumer(LoggingMixin):
self.run_pre_consume_script()
def progress_callback(current_progress, max_progress):
# recalculate progress to be within 20 and 80
p = int((current_progress / max_progress) * 50 + 20)
self._send_progress(p, 100, "WORKING")
# This doesn't parse the document yet, but gives us a parser.
document_parser = parser_class(self.logging_group)
document_parser = parser_class(self.logging_group, progress_callback)
# However, this already created working directories which we have to
# clean up.
# Parse the document. This may take some time.
text = None
date = None
thumbnail = None
archive_path = None
try:
self._send_progress(20, 100, 'WORKING', MESSAGE_PARSING_DOCUMENT)
self.log("debug", "Parsing {}...".format(self.filename))
document_parser.parse(self.path, mime_type, self.filename)
self.log("debug", f"Generating thumbnail for {self.filename}...")
self._send_progress(70, 100, 'WORKING',
MESSAGE_GENERATING_THUMBNAIL)
thumbnail = document_parser.get_optimised_thumbnail(
self.path, mime_type)
text = document_parser.get_text()
date = document_parser.get_date()
if not date:
self._send_progress(90, 100, 'WORKING',
MESSAGE_PARSE_DATE)
date = parse_date(self.filename, text)
archive_path = document_parser.get_archive_path()
except ParseError as e:
document_parser.cleanup()
self.log(
"error",
f"Error while consuming document {self.filename}: {e}")
raise ConsumerError(e)
self._fail(
str(e),
f"Error while consuming document {self.filename}: {e}"
)
# Prepare the document classifier.
@@ -203,6 +264,7 @@ class Consumer(LoggingMixin):
classifier = load_classifier()
self._send_progress(95, 100, 'WORKING', MESSAGE_SAVE_DOCUMENT)
# now that everything is done, we can start to store the document
# in the system. This will be a transaction and reasonably fast.
try:
@@ -256,12 +318,11 @@ class Consumer(LoggingMixin):
os.unlink(self.path)
except Exception as e:
self.log(
"error",
self._fail(
str(e),
f"The following error occured while consuming "
f"{self.filename}: {e}"
)
raise ConsumerError(e)
finally:
document_parser.cleanup()
@@ -272,6 +333,8 @@ class Consumer(LoggingMixin):
"Document {} consumption finished".format(document)
)
self._send_progress(100, 100, 'SUCCESS', MESSAGE_FINISHED, document.id)
return document
def _store(self, text, date, mime_type):

8
src/documents/parsers.py
View File

@@ -261,7 +261,7 @@ class DocumentParser(LoggingMixin):
`paperless_tesseract.parsers` for inspiration.
"""
def __init__(self, logging_group):
def __init__(self, logging_group, progress_callback=None):
super().__init__()
self.logging_group = logging_group
os.makedirs(settings.SCRATCH_DIR, exist_ok=True)
@@ -271,6 +271,12 @@ class DocumentParser(LoggingMixin):
self.archive_path = None
self.text = None
self.date = None
self.progress_callback = progress_callback
def progress(self, current, max):
print(self.progress_callback)
if self.progress_callback:
self.progress_callback(current, max)
def extract_metadata(self, document_path, mime_type):
return []

6
src/documents/serialisers.py
View File

@@ -8,6 +8,8 @@ from .models import Correspondent, Tag, Document, Log, DocumentType, \
SavedView, SavedViewFilterRule
from .parsers import is_mime_type_supported
from django.utils.translation import gettext as _
# https://www.django-rest-framework.org/api-guide/serializers/#example
class DynamicFieldsModelSerializer(serializers.ModelSerializer):
@@ -378,7 +380,9 @@ class PostDocumentSerializer(serializers.Serializer):
if not is_mime_type_supported(mime_type):
raise serializers.ValidationError(
"This file type is not supported.")
_("File type %(type)s not supported") %
{'type': mime_type}
)
return document.name, document_data

7
src/documents/tasks.py
View File

@@ -66,7 +66,8 @@ def consume_file(path,
override_title=None,
override_correspondent_id=None,
override_document_type_id=None,
override_tag_ids=None):
override_tag_ids=None,
task_id=None):
document = Consumer().try_consume_file(
path,
@@ -74,7 +75,9 @@ def consume_file(path,
override_title=override_title,
override_correspondent_id=override_correspondent_id,
override_document_type_id=override_document_type_id,
override_tag_ids=override_tag_ids)
override_tag_ids=override_tag_ids,
task_id=task_id
)
if document:
return "Success. New document id {} created".format(

141
src/documents/tests/test_consumer.py
View File

@@ -170,7 +170,7 @@ class DummyParser(DocumentParser):
raise NotImplementedError()
def __init__(self, logging_group, scratch_dir, archive_path):
super(DummyParser, self).__init__(logging_group)
super(DummyParser, self).__init__(logging_group, None)
_, self.fake_thumb = tempfile.mkstemp(suffix=".png", dir=scratch_dir)
self.archive_path = archive_path
@@ -212,10 +212,24 @@ def fake_magic_from_file(file, mime=False):
@mock.patch("documents.consumer.magic.from_file", fake_magic_from_file)
class TestConsumer(DirectoriesMixin, TestCase):
def make_dummy_parser(self, logging_group):
def _assert_first_last_send_progress(self, first_status="STARTING", last_status="SUCCESS", first_progress=0, first_progress_max=100, last_progress=100, last_progress_max=100):
self._send_progress.assert_called()
args, kwargs = self._send_progress.call_args_list[0]
self.assertEqual(args[0], first_progress)
self.assertEqual(args[1], first_progress_max)
self.assertEqual(args[2], first_status)
args, kwargs = self._send_progress.call_args_list[len(self._send_progress.call_args_list) - 1]
self.assertEqual(args[0], last_progress)
self.assertEqual(args[1], last_progress_max)
self.assertEqual(args[2], last_status)
def make_dummy_parser(self, logging_group, progress_callback=None):
return DummyParser(logging_group, self.dirs.scratch_dir, self.get_test_archive_file())
def make_faulty_parser(self, logging_group):
def make_faulty_parser(self, logging_group, progress_callback=None):
return FaultyParser(logging_group, self.dirs.scratch_dir)
def setUp(self):
@@ -228,7 +242,11 @@ class TestConsumer(DirectoriesMixin, TestCase):
"mime_types": {"application/pdf": ".pdf"},
"weight": 0
})]
self.addCleanup(patcher.stop)
# this prevents websocket message reports during testing.
patcher = mock.patch("documents.consumer.Consumer._send_progress")
self._send_progress = patcher.start()
self.addCleanup(patcher.stop)
self.consumer = Consumer()
@@ -274,6 +292,8 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertFalse(os.path.isfile(filename))
self._assert_first_last_send_progress()
def testOverrideFilename(self):
filename = self.get_test_file()
override_filename = "Statement for November.pdf"
@@ -282,21 +302,26 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertEqual(document.title, "Statement for November")
self._assert_first_last_send_progress()
def testOverrideTitle(self):
document = self.consumer.try_consume_file(self.get_test_file(), override_title="Override Title")
self.assertEqual(document.title, "Override Title")
self._assert_first_last_send_progress()
def testOverrideCorrespondent(self):
c = Correspondent.objects.create(name="test")
document = self.consumer.try_consume_file(self.get_test_file(), override_correspondent_id=c.pk)
self.assertEqual(document.correspondent.id, c.id)
self._assert_first_last_send_progress()
def testOverrideDocumentType(self):
dt = DocumentType.objects.create(name="test")
document = self.consumer.try_consume_file(self.get_test_file(), override_document_type_id=dt.pk)
self.assertEqual(document.document_type.id, dt.id)
self._assert_first_last_send_progress()
def testOverrideTags(self):
t1 = Tag.objects.create(name="t1")
@@ -307,37 +332,42 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertIn(t1, document.tags.all())
self.assertNotIn(t2, document.tags.all())
self.assertIn(t3, document.tags.all())
self._assert_first_last_send_progress()
def testNotAFile(self):
try:
self.consumer.try_consume_file("non-existing-file")
except ConsumerError as e:
self.assertTrue(str(e).endswith('It is not a file'))
return
self.fail("Should throw exception")
self.assertRaisesMessage(
ConsumerError,
"File not found",
self.consumer.try_consume_file,
"non-existing-file"
)
self._assert_first_last_send_progress(last_status="FAILED")
def testDuplicates1(self):
self.consumer.try_consume_file(self.get_test_file())
try:
self.consumer.try_consume_file(self.get_test_file())
except ConsumerError as e:
self.assertTrue(str(e).endswith("It is a duplicate."))
return
self.assertRaisesMessage(
ConsumerError,
"It is a duplicate",
self.consumer.try_consume_file,
self.get_test_file()
)
self.fail("Should throw exception")
self._assert_first_last_send_progress(last_status="FAILED")
def testDuplicates2(self):
self.consumer.try_consume_file(self.get_test_file())
try:
self.consumer.try_consume_file(self.get_test_archive_file())
except ConsumerError as e:
self.assertTrue(str(e).endswith("It is a duplicate."))
return
self.assertRaisesMessage(
ConsumerError,
"It is a duplicate",
self.consumer.try_consume_file,
self.get_test_archive_file()
)
self.fail("Should throw exception")
self._assert_first_last_send_progress(last_status="FAILED")
def testDuplicates3(self):
self.consumer.try_consume_file(self.get_test_archive_file())
@@ -347,13 +377,15 @@ class TestConsumer(DirectoriesMixin, TestCase):
def testNoParsers(self, m):
m.return_value = []
try:
self.consumer.try_consume_file(self.get_test_file())
except ConsumerError as e:
self.assertEqual("Unsupported mime type application/pdf of file sample.pdf", str(e))
return
self.assertRaisesMessage(
ConsumerError,
"sample.pdf: Unsupported mime type application/pdf",
self.consumer.try_consume_file,
self.get_test_file()
)
self._assert_first_last_send_progress(last_status="FAILED")
self.fail("Should throw exception")
@mock.patch("documents.parsers.document_consumer_declaration.send")
def testFaultyParser(self, m):
@@ -363,24 +395,28 @@ class TestConsumer(DirectoriesMixin, TestCase):
"weight": 0
})]
try:
self.consumer.try_consume_file(self.get_test_file())
except ConsumerError as e:
self.assertEqual(str(e), "Does not compute.")
return
self.assertRaisesMessage(
ConsumerError,
"sample.pdf: Error while consuming document sample.pdf: Does not compute.",
self.consumer.try_consume_file,
self.get_test_file()
)
self.fail("Should throw exception.")
self._assert_first_last_send_progress(last_status="FAILED")
@mock.patch("documents.consumer.Consumer._write")
def testPostSaveError(self, m):
filename = self.get_test_file()
m.side_effect = OSError("NO.")
try:
self.consumer.try_consume_file(filename)
except ConsumerError as e:
self.assertEqual(str(e), "NO.")
else:
self.fail("Should raise exception")
self.assertRaisesMessage(
ConsumerError,
"sample.pdf: The following error occured while consuming sample.pdf: NO.",
self.consumer.try_consume_file,
filename
)
self._assert_first_last_send_progress(last_status="FAILED")
# file not deleted
self.assertTrue(os.path.isfile(filename))
@@ -397,6 +433,8 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertEqual(document.title, "new docs")
self.assertEqual(document.filename, "none/new docs.pdf")
self._assert_first_last_send_progress()
@override_settings(PAPERLESS_FILENAME_FORMAT="{correspondent}/{title}")
@mock.patch("documents.signals.handlers.generate_unique_filename")
def testFilenameHandlingUnstableFormat(self, m):
@@ -420,6 +458,8 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertIsNotNone(os.path.isfile(document.title))
self.assertTrue(os.path.isfile(document.source_path))
self._assert_first_last_send_progress()
@mock.patch("documents.consumer.load_classifier")
def testClassifyDocument(self, m):
correspondent = Correspondent.objects.create(name="test")
@@ -439,19 +479,26 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertIn(t1, document.tags.all())
self.assertNotIn(t2, document.tags.all())
self._assert_first_last_send_progress()
@override_settings(CONSUMER_DELETE_DUPLICATES=True)
def test_delete_duplicate(self):
dst = self.get_test_file()
self.assertTrue(os.path.isfile(dst))
doc = self.consumer.try_consume_file(dst)
self._assert_first_last_send_progress()
self.assertFalse(os.path.isfile(dst))
self.assertIsNotNone(doc)
self._send_progress.reset_mock()
dst = self.get_test_file()
self.assertTrue(os.path.isfile(dst))
self.assertRaises(ConsumerError, self.consumer.try_consume_file, dst)
self.assertFalse(os.path.isfile(dst))
self._assert_first_last_send_progress(last_status="FAILED")
@override_settings(CONSUMER_DELETE_DUPLICATES=False)
def test_no_delete_duplicate(self):
@@ -467,6 +514,8 @@ class TestConsumer(DirectoriesMixin, TestCase):
self.assertRaises(ConsumerError, self.consumer.try_consume_file, dst)
self.assertTrue(os.path.isfile(dst))
self._assert_first_last_send_progress(last_status="FAILED")
class PreConsumeTestCase(TestCase):
@@ -479,9 +528,11 @@ class PreConsumeTestCase(TestCase):
m.assert_not_called()
@mock.patch("documents.consumer.Popen")
@mock.patch("documents.consumer.Consumer._send_progress")
@override_settings(PRE_CONSUME_SCRIPT="does-not-exist")
def test_pre_consume_script_not_found(self, m):
def test_pre_consume_script_not_found(self, m, m2):
c = Consumer()
c.filename = "somefile.pdf"
c.path = "path-to-file"
self.assertRaises(ConsumerError, c.run_pre_consume_script)
@@ -503,7 +554,6 @@ class PreConsumeTestCase(TestCase):
self.assertEqual(command[1], "path-to-file")
class PostConsumeTestCase(TestCase):
@mock.patch("documents.consumer.Popen")
@@ -519,12 +569,13 @@ class PostConsumeTestCase(TestCase):
m.assert_not_called()
@override_settings(POST_CONSUME_SCRIPT="does-not-exist")
def test_post_consume_script_not_found(self):
@mock.patch("documents.consumer.Consumer._send_progress")
def test_post_consume_script_not_found(self, m):
doc = Document.objects.create(title="Test", mime_type="application/pdf")
self.assertRaises(ConsumerError, Consumer().run_post_consume_script, doc)
c = Consumer()
c.filename = "somefile.pdf"
self.assertRaises(ConsumerError, c.run_post_consume_script, doc)
@mock.patch("documents.consumer.Popen")
def test_post_consume_script_simple(self, m):

6
src/documents/views.py
View File

@@ -1,6 +1,7 @@
import logging
import os
import tempfile
import uuid
from datetime import datetime
from time import mktime
@@ -213,7 +214,7 @@ class DocumentViewSet(RetrieveModelMixin,
parser_class = get_parser_class_for_mime_type(mime_type)
if parser_class:
parser = parser_class(logging_group=None)
parser = parser_class(progress_callback=None, logging_group=None)
try:
return parser.extract_metadata(file, mime_type)
@@ -403,6 +404,8 @@ class PostDocumentView(APIView):
os.utime(f.name, times=(t, t))
temp_filename = f.name
task_id = str(uuid.uuid4())
async_task("documents.tasks.consume_file",
temp_filename,
override_filename=doc_name,
@@ -410,6 +413,7 @@ class PostDocumentView(APIView):
override_correspondent_id=correspondent_id,
override_document_type_id=document_type_id,
override_tag_ids=tag_ids,
task_id=task_id,
task_name=os.path.basename(doc_name)[:100])
return Response("OK")

173
src/locale/en-us/LC_MESSAGES/django.po
View File

@@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2021-01-10 21:41+0000\n"
"POT-Creation-Date: 2021-01-28 22:02+0100\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\n"
@@ -21,323 +21,328 @@ msgstr ""
msgid "Documents"
msgstr ""
#: documents/models.py:32
#: documents/models.py:33
msgid "Any word"
msgstr ""
#: documents/models.py:33
#: documents/models.py:34
msgid "All words"
msgstr ""
#: documents/models.py:34
#: documents/models.py:35
msgid "Exact match"
msgstr ""
#: documents/models.py:35
#: documents/models.py:36
msgid "Regular expression"
msgstr ""
#: documents/models.py:36
#: documents/models.py:37
msgid "Fuzzy word"
msgstr ""
#: documents/models.py:37
#: documents/models.py:38
msgid "Automatic"
msgstr ""
#: documents/models.py:41 documents/models.py:354 paperless_mail/models.py:25
#: documents/models.py:42 documents/models.py:352 paperless_mail/models.py:25
#: paperless_mail/models.py:109
msgid "name"
msgstr ""
#: documents/models.py:45
#: documents/models.py:46
msgid "match"
msgstr ""
#: documents/models.py:49
#: documents/models.py:50
msgid "matching algorithm"
msgstr ""
#: documents/models.py:55
#: documents/models.py:56
msgid "is insensitive"
msgstr ""
#: documents/models.py:80 documents/models.py:140
#: documents/models.py:75 documents/models.py:135
msgid "correspondent"
msgstr ""
#: documents/models.py:81
#: documents/models.py:76
msgid "correspondents"
msgstr ""
#: documents/models.py:103
#: documents/models.py:98
msgid "color"
msgstr ""
#: documents/models.py:107
#: documents/models.py:102
msgid "is inbox tag"
msgstr ""
#: documents/models.py:109
#: documents/models.py:104
msgid ""
"Marks this tag as an inbox tag: All newly consumed documents will be tagged "
"with inbox tags."
msgstr ""
#: documents/models.py:114
#: documents/models.py:109
msgid "tag"
msgstr ""
#: documents/models.py:115 documents/models.py:171
#: documents/models.py:110 documents/models.py:166
msgid "tags"
msgstr ""
#: documents/models.py:121 documents/models.py:153
#: documents/models.py:116 documents/models.py:148
msgid "document type"
msgstr ""
#: documents/models.py:122
#: documents/models.py:117
msgid "document types"
msgstr ""
#: documents/models.py:130
#: documents/models.py:125
msgid "Unencrypted"
msgstr ""
#: documents/models.py:131
#: documents/models.py:126
msgid "Encrypted with GNU Privacy Guard"
msgstr ""
#: documents/models.py:144
#: documents/models.py:139
msgid "title"
msgstr ""
#: documents/models.py:157
#: documents/models.py:152
msgid "content"
msgstr ""
#: documents/models.py:159
#: documents/models.py:154
msgid ""
"The raw, text-only data of the document. This field is primarily used for "
"searching."
msgstr ""
#: documents/models.py:164
#: documents/models.py:159
msgid "mime type"
msgstr ""
#: documents/models.py:175
#: documents/models.py:170
msgid "checksum"
msgstr ""
#: documents/models.py:179
#: documents/models.py:174
msgid "The checksum of the original document."
msgstr ""
#: documents/models.py:183
#: documents/models.py:178
msgid "archive checksum"
msgstr ""
#: documents/models.py:188
#: documents/models.py:183
msgid "The checksum of the archived document."
msgstr ""
#: documents/models.py:192 documents/models.py:332
#: documents/models.py:187 documents/models.py:330
msgid "created"
msgstr ""
#: documents/models.py:196
#: documents/models.py:191
msgid "modified"
msgstr ""
#: documents/models.py:200
#: documents/models.py:195
msgid "storage type"
msgstr ""
#: documents/models.py:208
#: documents/models.py:203
msgid "added"
msgstr ""
#: documents/models.py:212
#: documents/models.py:207
msgid "filename"
msgstr ""
#: documents/models.py:217
#: documents/models.py:212
msgid "Current filename in storage"
msgstr ""
#: documents/models.py:221
#: documents/models.py:216
msgid "archive serial number"
msgstr ""
#: documents/models.py:226
#: documents/models.py:221
msgid "The position of this document in your physical document archive."
msgstr ""
#: documents/models.py:232
#: documents/models.py:227
msgid "document"
msgstr ""
#: documents/models.py:233
#: documents/models.py:228
msgid "documents"
msgstr ""
#: documents/models.py:315
#: documents/models.py:313
msgid "debug"
msgstr ""
#: documents/models.py:316
#: documents/models.py:314
msgid "information"
msgstr ""
#: documents/models.py:317
#: documents/models.py:315
msgid "warning"
msgstr ""
#: documents/models.py:318
#: documents/models.py:316
msgid "error"
msgstr ""
#: documents/models.py:319
#: documents/models.py:317
msgid "critical"
msgstr ""
#: documents/models.py:323
#: documents/models.py:321
msgid "group"
msgstr ""
#: documents/models.py:326
#: documents/models.py:324
msgid "message"
msgstr ""
#: documents/models.py:329
#: documents/models.py:327
msgid "level"
msgstr ""
#: documents/models.py:336
#: documents/models.py:334
msgid "log"
msgstr ""
#: documents/models.py:337
#: documents/models.py:335
msgid "logs"
msgstr ""
#: documents/models.py:348 documents/models.py:398
#: documents/models.py:346 documents/models.py:396
msgid "saved view"
msgstr ""
#: documents/models.py:349
#: documents/models.py:347
msgid "saved views"
msgstr ""
#: documents/models.py:352
#: documents/models.py:350
msgid "user"
msgstr ""
#: documents/models.py:358
#: documents/models.py:356
msgid "show on dashboard"
msgstr ""
#: documents/models.py:361
#: documents/models.py:359
msgid "show in sidebar"
msgstr ""
#: documents/models.py:365
#: documents/models.py:363
msgid "sort field"
msgstr ""
#: documents/models.py:368
#: documents/models.py:366
msgid "sort reverse"
msgstr ""
#: documents/models.py:374
#: documents/models.py:372
msgid "title contains"
msgstr ""
#: documents/models.py:375
#: documents/models.py:373
msgid "content contains"
msgstr ""
#: documents/models.py:376
#: documents/models.py:374
msgid "ASN is"
msgstr ""
#: documents/models.py:377
#: documents/models.py:375
msgid "correspondent is"
msgstr ""
#: documents/models.py:378
#: documents/models.py:376
msgid "document type is"
msgstr ""
#: documents/models.py:379
#: documents/models.py:377
msgid "is in inbox"
msgstr ""
#: documents/models.py:380
#: documents/models.py:378
msgid "has tag"
msgstr ""
#: documents/models.py:381
#: documents/models.py:379
msgid "has any tag"
msgstr ""
#: documents/models.py:382
#: documents/models.py:380
msgid "created before"
msgstr ""
#: documents/models.py:383
#: documents/models.py:381
msgid "created after"
msgstr ""
#: documents/models.py:384
#: documents/models.py:382
msgid "created year is"
msgstr ""
#: documents/models.py:385
#: documents/models.py:383
msgid "created month is"
msgstr ""
#: documents/models.py:386
#: documents/models.py:384
msgid "created day is"
msgstr ""
#: documents/models.py:387
#: documents/models.py:385
msgid "added before"
msgstr ""
#: documents/models.py:388
#: documents/models.py:386
msgid "added after"
msgstr ""
#: documents/models.py:389
#: documents/models.py:387
msgid "modified before"
msgstr ""
#: documents/models.py:390
#: documents/models.py:388
msgid "modified after"
msgstr ""
#: documents/models.py:391
#: documents/models.py:389
msgid "does not have tag"
msgstr ""
#: documents/models.py:402
#: documents/models.py:400
msgid "rule type"
msgstr ""
#: documents/models.py:406
#: documents/models.py:404
msgid "value"
msgstr ""
#: documents/models.py:412
#: documents/models.py:410
msgid "filter rule"
msgstr ""
#: documents/models.py:413
#: documents/models.py:411
msgid "filter rules"
msgstr ""
#: documents/serialisers.py:383
#, python-format
msgid "File type %(type)s not supported"
msgstr ""
#: documents/templates/index.html:20
msgid "Paperless-ng is loading..."
msgstr ""
@@ -378,23 +383,23 @@ msgstr ""
msgid "Sign in"
msgstr ""
#: paperless/settings.py:268
#: paperless/settings.py:286
msgid "English"
msgstr ""
#: paperless/settings.py:269
#: paperless/settings.py:287
msgid "German"
msgstr ""
#: paperless/settings.py:270
#: paperless/settings.py:288
msgid "Dutch"
msgstr ""
#: paperless/settings.py:271
#: paperless/settings.py:289
msgid "French"
msgstr ""
#: paperless/urls.py:108
#: paperless/urls.py:114
msgid "Paperless-ng administration"
msgstr ""

23
src/paperless/asgi.py Normal file
View File

@@ -0,0 +1,23 @@
import os
from django.core.asgi import get_asgi_application
# Fetch Django ASGI application early to ensure AppRegistry is populated
# before importing consumers and AuthMiddlewareStack that may import ORM
# models.
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "paperless.settings")
django_asgi_app = get_asgi_application()
from channels.auth import AuthMiddlewareStack # NOQA: E402
from channels.routing import ProtocolTypeRouter, URLRouter # NOQA: E402
from paperless.urls import websocket_urlpatterns # NOQA: E402
application = ProtocolTypeRouter({
"http": get_asgi_application(),
"websocket": AuthMiddlewareStack(
URLRouter(
websocket_urlpatterns
)
),
})

18
src/paperless/consumers.py Normal file
View File

@@ -0,0 +1,18 @@
import json
from asgiref.sync import async_to_sync
from channels.generic.websocket import WebsocketConsumer
class StatusConsumer(WebsocketConsumer):
def connect(self):
self.accept()
async_to_sync(self.channel_layer.group_add)(
'status_updates', self.channel_name)
def disconnect(self, close_code):
async_to_sync(self.channel_layer.group_discard)(
'status_updates', self.channel_name)
def status_update(self, event):
self.send(json.dumps(event['data']))

12
src/paperless/settings.py
View File

@@ -100,6 +100,8 @@ INSTALLED_APPS = [
"django_q",
"channels",
] + env_apps
REST_FRAMEWORK = {
@@ -133,6 +135,7 @@ ROOT_URLCONF = 'paperless.urls'
FORCE_SCRIPT_NAME = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
WSGI_APPLICATION = 'paperless.wsgi.application'
ASGI_APPLICATION = "paperless.asgi.application"
STATIC_URL = os.getenv("PAPERLESS_STATIC_URL", "/static/")
@@ -153,6 +156,15 @@ TEMPLATES = [
},
]
CHANNEL_LAYERS = {
"default": {
"BACKEND": "channels_redis.core.RedisChannelLayer",
"CONFIG": {
"hosts": [os.getenv("PAPERLESS_REDIS", "redis://localhost:6379")],
},
},
}
###############################################################################
# Security #
###############################################################################

6
src/paperless/urls.py
View File

@@ -9,6 +9,7 @@ from rest_framework.routers import DefaultRouter
from django.utils.translation import gettext_lazy as _
from paperless.consumers import StatusConsumer
from documents.views import (
CorrespondentViewSet,
DocumentViewSet,
@@ -100,6 +101,11 @@ urlpatterns = [
re_path(r".*", login_required(IndexView.as_view())),
]
websocket_urlpatterns = [
re_path(r'ws/status/$', StatusConsumer.as_asgi()),
]
# Text in each page's <h1> (and above login form).
admin.site.site_header = 'Paperless-ng'
# Text at the end of each page's <title>.

4
src/paperless_tesseract/parsers.py
View File

@@ -190,11 +190,11 @@ class RasterisedDocumentParser(DocumentParser):
# Also, no archived file.
if not self.text:
# However, if we don't have anything, fail:
raise ParseError(e)
raise ParseError(e.__class__.__name__ + ": " + str(e))
except Exception as e:
# Anything else is probably serious.
raise ParseError(e)
raise ParseError(e.__class__.__name__ + ": " + str(e))
if not self.text:
# This may happen for files that don't have any text.