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 'ENH_text_consumer' of git://github.com/jat255/paperless into jat255-ENH_text_consumer

Browse Source
This commit is contained in:
Daniel Quinn
2018-09-09 20:52:59 +01:00
parent f4c399f0dd 72c828170e
commit 2dc35cc856
9 changed files with 203 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/documents/models.py
View File

@@ -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
))
])

15
src/documents/parsers.py
View File

@@ -1,9 +1,24 @@
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
pattern = 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

3
src/documents/views.py
View File

@@ -48,6 +48,9 @@ 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":