paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Style and removal of Python 2.7 stuff

Browse Source
This commit is contained in:
Daniel Quinn 2018-02-18 15:55:55 +00:00
parent 9cef689106
commit fb1da4834c
2 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/documents/consumer.py
View File

@ -22,7 +22,7 @@ class ConsumerError(Exception):
pass pass
class Consumer(object): class Consumer:
""" """
Loop over every file found in CONSUMPTION_DIR and: Loop over every file found in CONSUMPTION_DIR and:
1. Convert it to a greyscale pnm 1. Convert it to a greyscale pnm

8
src/paperless_tesseract/parsers.py
View File

@ -52,15 +52,13 @@ class RasterisedDocumentParser(DocumentParser):
return os.path.join(self.tempdir, "convert-0000.png") return os.path.join(self.tempdir, "convert-0000.png")
def _is_ocred(self): def _is_ocred(self):
# Extract text from PDF using pdftotext # Extract text from PDF using pdftotext
text = get_text_from_pdf(self.document_path) text = get_text_from_pdf(self.document_path)
# We assume, that a PDF with at least 50 characters contains text # We assume, that a PDF with at least 50 characters contains text
# (so no OCR required) # (so no OCR required)
if len(text) > 50: return len(text) > 50
return True
return False
def get_text(self): def get_text(self):
if self.TEXT_CACHE is not None: if self.TEXT_CACHE is not None:
@ -74,7 +72,6 @@ class RasterisedDocumentParser(DocumentParser):
images = self._get_greyscale() images = self._get_greyscale()
try: try:
self.TEXT_CACHE = self._get_ocr(images) self.TEXT_CACHE = self._get_ocr(images)
return self.TEXT_CACHE return self.TEXT_CACHE
except OCRError as e: except OCRError as e:
@ -262,6 +259,7 @@ def image_to_string(args):
def get_text_from_pdf(pdf_file): def get_text_from_pdf(pdf_file):
with open(pdf_file, "rb") as f: with open(pdf_file, "rb") as f:
try: try:
pdf = pdftotext.PDF(f) pdf = pdftotext.PDF(f)