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

try to run convert, but fall back on gs if needed

Browse Source
This commit is contained in:
JensPfeifle 2019-02-03 18:19:06 +01:00 committed by jenspfeifle
parent ea282c22ba
commit 29b0886950
1 changed files with 32 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
src/paperless_tesseract/parsers.py
View File

@ -46,25 +46,39 @@ class RasterisedDocumentParser(DocumentParser):
"""
out_path = os.path.join(self.tempdir, "convert.png")
gs_out_path = os.path.join(self.tempdir, "gs_out.png")
# Extract the first PDF page as a PNG using Ghostscript
# https://github.com/danielquinn/paperless/issues/447
# call gs first
cmd = [self.GHOSTSCRIPT,
"-q",
"-sDEVICE=pngalpha",
"-o", gs_out_path,
self.document_path]
if not subprocess.Popen(cmd).wait() == 0:
raise ParseError("Thumbnail (gs) failed at {}".format(cmd))
# then run convert on the output from gs
run_convert(
self.CONVERT,
"-scale", "500x5000",
"-alpha", "remove",
gs_out_path,
out_path
# Run convert to get a decent thumbnail
try:
run_convert(
self.CONVERT,
"-scale", "500x5000",
"-alpha", "remove",
"{}[0]".format(self.document_path),
out_path
)
except ParseError:
# if convert fails, fall back to extracting
# the first PDF page as a PNG using Ghostscript
self.log(
"warning",
"Thumbnail generation with ImageMagick failed, "
"falling back to Ghostscript."
)
gs_out_path = os.path.join(self.tempdir, "gs_out.png")
cmd = [self.GHOSTSCRIPT,
"-q",
"-sDEVICE=pngalpha",
"-o", gs_out_path,
self.document_path]
if not subprocess.Popen(cmd).wait() == 0:
raise ParseError("Thumbnail (gs) failed at {}".format(cmd))
# then run convert on the output from gs
run_convert(
self.CONVERT,
"-scale", "500x5000",
"-alpha", "remove",
gs_out_path,
out_path
)
return out_path