paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-11-03 03:16:10 -06:00
Code Issues Packages Projects Releases Wiki Activity

Introducing language detection

Browse Source
This commit is contained in:
Daniel Quinn
2016-01-21 12:50:22 -05:00
parent dbe2df0cad
commit ec70d05517
1 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/documents/management/commands/document_consumer.py
View File

@@ -1,6 +1,6 @@
import datetime import datetime
import glob import glob
import gnupg import langdetect
import os import os
import random import random
import re import re
@@ -44,9 +44,10 @@ class Command(BaseCommand):
PARSER_REGEX_SENDER_TITLE = re.compile(r"^.*/(.*) - (.*)\.pdf$") PARSER_REGEX_SENDER_TITLE = re.compile(r"^.*/(.*) - (.*)\.pdf$")
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
self.verbosity = 0 self.verbosity = 0
self.stats = {} self.stats = {}
self.gpg = gnupg.GPG(gnupghome=settings.GNUPG_HOME)
BaseCommand.__init__(self, *args, **kwargs) BaseCommand.__init__(self, *args, **kwargs)
def handle(self, *args, **options): def handle(self, *args, **options):
@@ -132,6 +133,16 @@ class Command(BaseCommand):
self._render(" OCRing the PDF", 2) self._render(" OCRing the PDF", 2)
raw_text = self._ocr(pngs, self.OCR_LANG)
guessed_language = langdetect.detect(raw_text)
if guessed_language == self.OCR_LANG:
return raw_text
return self._ocr(pngs, guessed_language)
def _ocr(self, pngs, lang):
r = "" r = ""
for png in pngs: for png in pngs:
with Image.open(os.path.join(self.SCRATCH, png)) as f: with Image.open(os.path.join(self.SCRATCH, png)) as f: