/usr/lib/python2.7/dist-packages/pdfminer/encodingdb.py is in python-pdfminer 20140328+dfsg-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | #!/usr/bin/env python
import re
from psparser import PSLiteral
from glyphlist import glyphname2unicode
from latin_enc import ENCODING
STRIP_NAME = re.compile(r'[0-9]+')
## name2unicode
##
def name2unicode(name):
"""Converts Adobe glyph names to Unicode numbers."""
if name in glyphname2unicode:
return glyphname2unicode[name]
m = STRIP_NAME.search(name)
if not m:
raise KeyError(name)
return unichr(int(m.group(0)))
## EncodingDB
##
class EncodingDB(object):
std2unicode = {}
mac2unicode = {}
win2unicode = {}
pdf2unicode = {}
for (name, std, mac, win, pdf) in ENCODING:
c = name2unicode(name)
if std:
std2unicode[std] = c
if mac:
mac2unicode[mac] = c
if win:
win2unicode[win] = c
if pdf:
pdf2unicode[pdf] = c
encodings = {
'StandardEncoding': std2unicode,
'MacRomanEncoding': mac2unicode,
'WinAnsiEncoding': win2unicode,
'PDFDocEncoding': pdf2unicode,
}
@classmethod
def get_encoding(klass, name, diff=None):
cid2unicode = klass.encodings.get(name, klass.std2unicode)
if diff:
cid2unicode = cid2unicode.copy()
cid = 0
for x in diff:
if isinstance(x, int):
cid = x
elif isinstance(x, PSLiteral):
try:
cid2unicode[cid] = name2unicode(x.name)
except KeyError:
pass
cid += 1
return cid2unicode
|