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

change tesseract parser to only convert first page to save (potentially) massive amounts of work

Browse Source
This commit is contained in:
Joshua Taillon 2018-09-05 15:18:35 -04:00
parent 939a67bd4b
commit cac63494f0
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/paperless_tesseract/parsers.py
View File

@ -50,10 +50,11 @@ class RasterisedDocumentParser(DocumentParser):
self.CONVERT, self.CONVERT,
"-scale", "500x5000", "-scale", "500x5000",
"-alpha", "remove", "-alpha", "remove",
self.document_path, os.path.join(self.tempdir, "convert-%04d.png") "{}[0]".format(self.document_path),
os.path.join(self.tempdir, "convert.png")
) )
return os.path.join(self.tempdir, "convert-0000.png") return os.path.join(self.tempdir, "convert.png")
def _is_ocred(self): def _is_ocred(self):