paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-10-30 03:56:23 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add GS_BINARY to settings to avoid harcoded call of "gs"

Browse Source
This commit is contained in:
JensPfeifle
2019-02-03 16:57:32 +01:00
committed by jenspfeifle
parent cbf008f37b
commit ea282c22ba
3 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
paperless.conf.example
View File

@@ -247,6 +247,9 @@ PAPERLESS_EMAIL_SECRET=""
# Convert (part of the ImageMagick suite) # Convert (part of the ImageMagick suite)
#PAPERLESS_CONVERT_BINARY=/usr/bin/convert #PAPERLESS_CONVERT_BINARY=/usr/bin/convert
# Ghostscript
#PAPERLESS_GS_BINARY = /usr/bin/gs
# Unpaper # Unpaper
#PAPERLESS_UNPAPER_BINARY=/usr/bin/unpaper #PAPERLESS_UNPAPER_BINARY=/usr/bin/unpaper

3
src/paperless/settings.py
View File

@@ -263,6 +263,9 @@ CONVERT_TMPDIR = os.getenv("PAPERLESS_CONVERT_TMPDIR")
CONVERT_MEMORY_LIMIT = os.getenv("PAPERLESS_CONVERT_MEMORY_LIMIT") CONVERT_MEMORY_LIMIT = os.getenv("PAPERLESS_CONVERT_MEMORY_LIMIT")
CONVERT_DENSITY = os.getenv("PAPERLESS_CONVERT_DENSITY") CONVERT_DENSITY = os.getenv("PAPERLESS_CONVERT_DENSITY")
# Ghostscript
GS_BINARY = os.getenv("PAPERLESS_GS_BINARY", "gs")
# OptiPNG # OptiPNG
OPTIPNG_BINARY = os.getenv("PAPERLESS_OPTIPNG_BINARY", "optipng") OPTIPNG_BINARY = os.getenv("PAPERLESS_OPTIPNG_BINARY", "optipng")

11
src/paperless_tesseract/parsers.py
View File

@@ -29,6 +29,7 @@ class RasterisedDocumentParser(DocumentParser):
""" """
CONVERT = settings.CONVERT_BINARY CONVERT = settings.CONVERT_BINARY
GHOSTSCRIPT = settings.GS_BINARY
DENSITY = settings.CONVERT_DENSITY if settings.CONVERT_DENSITY else 300 DENSITY = settings.CONVERT_DENSITY if settings.CONVERT_DENSITY else 300
THREADS = int(settings.OCR_THREADS) if settings.OCR_THREADS else None THREADS = int(settings.OCR_THREADS) if settings.OCR_THREADS else None
UNPAPER = settings.UNPAPER_BINARY UNPAPER = settings.UNPAPER_BINARY
@@ -47,12 +48,14 @@ class RasterisedDocumentParser(DocumentParser):
out_path = os.path.join(self.tempdir, "convert.png") out_path = os.path.join(self.tempdir, "convert.png")
gs_out_path = os.path.join(self.tempdir, "gs_out.png") gs_out_path = os.path.join(self.tempdir, "gs_out.png")
# Run convert to get a decent thumbnail # Extract the first PDF page as a PNG using Ghostscript
# https://github.com/danielquinn/paperless/issues/447 # https://github.com/danielquinn/paperless/issues/447
# call gs first # call gs first
cmd = ["gs", "-q", "-sDEVICE=pngalpha", cmd = [self.GHOSTSCRIPT,
"-o", gs_out_path, self.document_path] "-q",
"-sDEVICE=pngalpha",
"-o", gs_out_path,
self.document_path]
if not subprocess.Popen(cmd).wait() == 0: if not subprocess.Popen(cmd).wait() == 0:
raise ParseError("Thumbnail (gs) failed at {}".format(cmd)) raise ParseError("Thumbnail (gs) failed at {}".format(cmd))
# then run convert on the output from gs # then run convert on the output from gs