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 'master' into dev

Browse Source
This commit is contained in:
Jonas Winkler
2018-09-12 11:47:35 +02:00
parent 2d2ad9156d 553caefe1d
commit a48cc6c627
19 changed files with 345 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/documents/models.py
View File

@@ -1,24 +1,24 @@
# coding=utf-8
import dateutil.parser
import logging
import os
import re
import uuid
from collections import OrderedDict
import dateutil.parser
from django.conf import settings
from django.db import models
from django.template.defaultfilters import slugify
from django.utils import timezone
from fuzzywuzzy import fuzz
from django.conf import settings
from .managers import LogManager
try:
from django.core.urlresolvers import reverse
except ImportError:
from django.urls import reverse
from django.db import models
from django.template.defaultfilters import slugify
from django.utils import timezone
from .managers import LogManager
class MatchingModel(models.Model):
@@ -94,7 +94,11 @@ class Document(models.Model):
TYPE_JPG = "jpg"
TYPE_GIF = "gif"
TYPE_TIF = "tiff"
TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,)
TYPE_TXT = "txt"
TYPE_CSV = "csv"
TYPE_MD = "md"
TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,
TYPE_TXT, TYPE_CSV, TYPE_MD)
STORAGE_TYPE_UNENCRYPTED = "unencrypted"
STORAGE_TYPE_GPG = "gpg"
@@ -282,51 +286,52 @@ class FileInfo:
)
)
formats = "pdf|jpe?g|png|gif|tiff?|te?xt|md|csv"
REGEXES = OrderedDict([
("created-correspondent-title-tags", re.compile(
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
r"(?P<correspondent>.*) - "
r"(?P<title>.*) - "
r"(?P<tags>[a-z0-9\-,]*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("created-title-tags", re.compile(
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
r"(?P<title>.*) - "
r"(?P<tags>[a-z0-9\-,]*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("created-correspondent-title", re.compile(
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
r"(?P<correspondent>.*) - "
r"(?P<title>.*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("created-title", re.compile(
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
r"(?P<title>.*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("correspondent-title-tags", re.compile(
r"(?P<correspondent>.*) - "
r"(?P<title>.*) - "
r"(?P<tags>[a-z0-9\-,]*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("correspondent-title", re.compile(
r"(?P<correspondent>.*) - "
r"(?P<title>.*)?"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("title", re.compile(
r"(?P<title>.*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
))
])

16
src/documents/parsers.py
View File

@@ -1,9 +1,25 @@
import logging
import shutil
import tempfile
import re
from django.conf import settings
# This regular expression will try to find dates in the document at
# hand and will match the following formats:
# - XX.YY.ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
# - MONTH ZZZZ, with ZZZZ being 4 digits
# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
DATE_REGEX = re.compile(
r'\b([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})\b|' +
r'\b([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))\b|' +
r'\b([^\W\d_]{3,9} [0-9]{1,2}, ([0-9]{4}))\b|' +
r'\b([^\W\d_]{3,9} [0-9]{4})\b'
)
class ParseError(Exception):
pass

2
src/documents/tests/test_matchables.py
View File

@@ -166,7 +166,7 @@ class TestMatching(TestCase):
def test_match_regex(self):
self._test_matching(
"alpha\w+gamma",
r"alpha\w+gamma",
"MATCH_REGEX",
(
"I have alpha_and_gamma in me",

12
src/documents/views.py
View File

@@ -1,6 +1,8 @@
from django.http import HttpResponse, HttpResponseBadRequest
from django.views.generic import DetailView, FormView, TemplateView
from django_filters.rest_framework import DjangoFilterBackend
from django.conf import settings
from paperless.db import GnuPG
from paperless.mixins import SessionOrBasicAuthMixin
from paperless.views import StandardPagination
@@ -48,6 +50,9 @@ class FetchView(SessionOrBasicAuthMixin, DetailView):
Document.TYPE_JPG: "image/jpeg",
Document.TYPE_GIF: "image/gif",
Document.TYPE_TIF: "image/tiff",
Document.TYPE_CSV: "text/csv",
Document.TYPE_MD: "text/markdown",
Document.TYPE_TXT: "text/plain"
}
if self.kwargs["kind"] == "thumb":
@@ -60,8 +65,11 @@ class FetchView(SessionOrBasicAuthMixin, DetailView):
self._get_raw_data(self.object.source_file),
content_type=content_types[self.object.file_type]
)
response["Content-Disposition"] = 'attachment; filename="{}"'.format(
self.object.file_name)
DISPOSITION = 'inline' if settings.INLINE_DOC else 'attachment'
response["Content-Disposition"] = '{}; filename="{}"'.format(
DISPOSITION, self.object.file_name)
return response