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

Rename .TEXT_CACHE to .text

Browse Source 
Properties should use snake_case, and only constants should be ALL_CAPS.
This change also makes use of the convention of "private" properties
being prefixed with `_`.
This commit is contained in:
Daniel Quinn
2018-02-18 16:00:43 +00:00
parent 3302ee2a78
commit e53033d1b3
1 changed files with 11 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/paperless_tesseract/parsers.py
View File

@@ -36,7 +36,10 @@ class RasterisedDocumentParser(DocumentParser):
DATE_ORDER = settings.DATE_ORDER
DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
OCR_ALWAYS = settings.OCR_ALWAYS
TEXT_CACHE = None
def __init__(self, path):
super().__init__(path)
self._text = None
def get_thumbnail(self):
"""
@@ -62,19 +65,20 @@ class RasterisedDocumentParser(DocumentParser):
return len(text) > 50
def get_text(self):
if self.TEXT_CACHE is not None:
return self.TEXT_CACHE
if self._text is not None:
return self._text
if not self.OCR_ALWAYS and self._is_ocred():
self.log("info", "Skipping OCR, using Text from PDF")
self.TEXT_CACHE = get_text_from_pdf(self.document_path)
return self.TEXT_CACHE
self._text = get_text_from_pdf(self.document_path)
return self._text
images = self._get_greyscale()
try:
self.TEXT_CACHE = self._get_ocr(images)
return self.TEXT_CACHE
self._text = self._get_ocr(images)
return self._text
except OCRError as e:
raise ParseError(e)