Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix reading metadata from PDF broken by poppler >= 0.47.0

Browse Source
This commit is contained in:
Kovid Goyal 2016-09-08 21:05:32 +05:30
parent 8f655cd610
commit 59e8070ef9
1 changed files with 19 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/calibre/ebooks/metadata/pdf.py
View File

@ -33,22 +33,17 @@ def read_info(outputdir, get_cover):
ans = {}
try:
raw = subprocess.check_output([pdfinfo, '-meta', '-enc', 'UTF-8', 'src.pdf'])
raw = subprocess.check_output([pdfinfo, '-enc', 'UTF-8', 'src.pdf'])
except subprocess.CalledProcessError as e:
prints('pdfinfo errored out with return code: %d'%e.returncode)
return None
# The XMP metadata could be in an encoding other than UTF-8, so split it
# out before trying to decode raw
parts = re.split(br'^Metadata:', raw, 1, flags=re.MULTILINE)
if len(parts) > 1:
raw, ans['xmp_metadata'] = parts
try:
raw = raw.decode('utf-8')
info_raw = raw.decode('utf-8')
except UnicodeDecodeError:
prints('pdfinfo returned no UTF-8 data')
return None
for line in raw.splitlines():
for line in info_raw.splitlines():
if u':' not in line:
continue
field, val = line.partition(u':')[::2]
@ -56,6 +51,22 @@ def read_info(outputdir, get_cover):
if field and val:
ans[field] = val.strip()
# Now read XMP metadata
# Versions of poppler before 0.47.0 used to print out both the Info dict and
# XMP metadata packet together. However, since that changed in
# https://cgit.freedesktop.org/poppler/poppler/commit/?id=c91483aceb1b640771f572cb3df9ad707e5cad0d
# we can no longer rely on it.
try:
raw = subprocess.check_output([pdfinfo, '-meta', 'src.pdf']).strip()
except subprocess.CalledProcessError as e:
prints('pdfinfo errored out with return code: %d'%e.returncode)
parts = re.split(br'^Metadata:', raw, 1, flags=re.MULTILINE)
if len(parts) > 1:
raw, ans['xmp_metadata'] = parts
elif raw:
ans['xmp_metadata'] = raw
if get_cover:
try:
subprocess.check_call([pdftoppm, '-singlefile', '-jpeg', '-cropbox',