paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-08-14 00:26:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master'

Browse Source
This commit is contained in:
Jonas Winkler
2018-09-11 14:43:59 +02:00
parent c765ef5eeb 2edf65dd1e
commit e72735c4f0
20 changed files with 348 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
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):
@@ -135,7 +135,7 @@ class MatchingModel(models.Model):
Example:
' some random words "with quotes " and spaces'
==>
["some", "random", "words", "with\s+quotes", "and", "spaces"]
["some", "random", "words", "with+quotes", "and", "spaces"]
"""
findterms = re.compile(r'"([^"]+)"|(\S+)').findall
normspace = re.compile(r"\s+").sub
@@ -192,7 +192,11 @@ 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"
@@ -365,51 +369,52 @@ 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
))
])