1 # This file is part of lyx2lyx
2 # -*- coding: utf-8 -*-
3 # Copyright (C) 2011 The LyX team
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 " Import unicode_reps from this module for access to the unicode<->LaTeX mapping. "
21 import sys, os, re, codecs
23 # Provide support for both python 2 and 3
24 PY2 = sys.version_info[0] == 2
27 # End of code to support for both python 2 and 3
29 def read_unicodesymbols():
30 " Read the unicodesymbols list of unicode characters and corresponding commands."
31 pathname = os.path.abspath(os.path.dirname(__file__))
32 filename = os.path.join(pathname.strip('lyx2lyx'), 'unicodesymbols')
34 # Read as Unicode strings in both, Python 2 and 3
35 # Specify the encoding for those systems where the default is not UTF-8
36 fp = codecs.open(filename, encoding="utf8")
38 # A backslash, followed by some non-word character, and then a character
39 # in brackets. The idea is to check for constructs like: \"{u}, which is how
40 # they are written in the unicodesymbols file; but they can also be written
41 # as: \"u or even \" u.
42 # The two backslashes in the string literal are needed to specify a literal
43 # backslash in the regex. Without r prefix, these would be four backslashes.
44 r = re.compile(r'\\(\W)\{(\w)\}')
47 for line in fp.readlines():
48 if not line.strip() or line.startswith('#'):
49 # skip empty lines and comments
51 # Note: backslashes in the string literals with r prefix are not escaped,
52 # so one backslash in the source file equals one backslash in memory.
53 # Without r prefix backslahses are escaped, so two backslashes in the
54 # source file equal one backslash in memory.
55 line=line.replace(' "',' ') # remove all quotation marks with spaces before
56 line=line.replace('" ',' ') # remove all quotation marks with spaces after
57 line=line.replace(r'\"','"') # unescape "
58 line=line.replace(r'\\','\\') # unescape \
60 [ucs4,command,dead] = line.split(None,2)
61 if command[0:1] != "\\":
63 literal_char = unichr(int(ucs4, 16))
64 if (line.find("notermination=text") < 0 and
65 line.find("notermination=both") < 0 and command[-1] != "}"):
66 command = command + "{}"
67 spec_chars.append([command, literal_char])
74 command += m.group(1) + m.group(2)
75 commandbl += m.group(1) + ' ' + m.group(2)
76 spec_chars.append([command, literal_char])
77 spec_chars.append([commandbl, literal_char])
82 unicode_reps = read_unicodesymbols()