yujunjun/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2025-11-02 10:50:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Drop support for pdfminer.six 20181108

Browse Source 
This version required a patch that has since been mainlined, and also did not
declare its dependency on chardet
correctly. We can remove both hacks now.
This commit is contained in:
James R. Barlow 2020-01-05 17:51:09 -08:00
parent 31b5f63f85
commit 4581027246
2 changed files with 1 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
setup.py
View File

@ -95,11 +95,10 @@ setup(
use_scm_version={'version_scheme': 'post-release'},
cffi_modules=['src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'],
install_requires=[
'chardet >= 3.0.4, < 4', # unlisted requirement of pdfminer.six 20181108
'cffi >= 1.9.1', # must be a setup and install requirement
'coloredlogs >= 14.0', # strictly optional
'img2pdf >= 0.3.0, < 0.4', # pure Python, so track HEAD closely
'pdfminer.six >= 20181108, <= 20200124',
'pdfminer.six >= 20191110, <= 20200124',
'pikepdf >= 1.8.1, < 2',
'Pillow >= 6.2.0',
'reportlab >= 3.3.0', # oldest released version with sane image handling

48
src/ocrmypdf/pdfinfo/layout.py
View File

@ -36,54 +36,6 @@ from ..exceptions import EncryptedPdfError
STRIP_NAME = re.compile(r'[0-9]+')
#
# pdfminer 20181108 patches
#
if pdfminer.__version__ == '20181108':
def name2unicode(name):
"""Fix pdfminer's name2unicode function
Font cids that are mapped to names of the form /g123 seem to be, by convention
characters with no corresponding Unicode entry. These can be subsetted fonts
or symbolic fonts. There seems to be no way to map /g123 fonts to Unicode,
barring a ToUnicode data structure.
"""
if name in glyphname2unicode:
return glyphname2unicode[name]
if name.startswith('g') or name.startswith('a'):
raise KeyError(name)
if name.startswith('uni'):
try:
return chr(int(name[3:], 16))
except ValueError: # Not hexadecimal
raise KeyError(name)
m = STRIP_NAME.search(name)
if not m:
raise KeyError(name)
return chr(int(m.group(0)))
pdfminer.encodingdb.name2unicode = name2unicode
original_PDFFont_init = PDFFont.__init__
def PDFFont__init__(self, descriptor, widths, default_width=None):
original_PDFFont_init(self, descriptor, widths, default_width)
# PDF spec says descent should be negative
# A font with a positive descent implies it floats entirely above the
# baseline, i.e. it's not really a baseline anymore. I have fonts that
# claim a positive descent, but treating descent as positive always seems
# to misposition text.
if self.descent > 0:
self.descent = -self.descent
PDFFont.__init__ = PDFFont__init__
#
# end of pdfminer 20181108 patches
#
original_PDFSimpleFont_init = PDFSimpleFont.__init__