You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
52 lines
1.4 KiB
52 lines
1.4 KiB
import re
|
|
from .psparser import PSLiteral
|
|
from .glyphlist import glyphname2unicode
|
|
from .latin_enc import ENCODING
|
|
|
|
|
|
STRIP_NAME = re.compile(r'[0-9]+')
|
|
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 chr(int(m.group(0)))
|
|
|
|
|
|
class EncodingDB:
|
|
|
|
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(cls, name, diff=None):
|
|
cid2unicode = cls.encodings.get(name, cls.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
|