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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
#
# mini-script to generate the pylatexenc.latexencode._uni2latexmap_xml dict mapping
#
import re
import sys
if sys.version_info.major > 2:
# python 3
unichr = chr
from xml.etree import ElementTree as ET
e = ET.parse('unicode.xml')
d = {}
dnames = {}
for chxml in e.find('charlist').iter('character'):
Uid = chxml.attrib['id']
if '-' in Uid:
# composite/multiple characters not supported
continue
charord = int(Uid.lstrip('U'), 16)
latexxml = chxml.find('latex')
if latexxml is None:
continue
latexval = latexxml.text
if latexval == unichr(charord):
# "latex" representation is the same char directly
continue
if charord == 0x20:
# skip space char
continue
if latexval.startswith(r'\ElsevierGlyph') or latexval.startswith(r'\El') \
or latexval.startswith(r'\ensuremath{\El'):
continue
if re.search(r'\\[a-zA-Z]+\s+$', latexval):
# ends with named macro+space, remove space because
# latexencode.UnicodeToLatexEncoder will handle that with
# replacement_latex_protection
latexval = latexval.rstrip()
d[charord] = latexval
dnames[charord] = chxml.find('description').text
# dump dictionary into new module file in current working directory
outputfile = '_uni2latexmap_xml.py'
HEADER = """\
# -*- coding: utf-8 -*-
#
# Automatically generated from unicode.xml by gen_xml_dic.py
#
"""
with open(outputfile, 'w') as f:
f.write(HEADER)
f.write("uni2latex = {\n")
for k,v in d.items():
f.write("0x%04X: %r,\n"%(k, v))
f.write("}\n")
print("Successfully generated file %s"%(outputfile))
# Now see which characters we don't have in our default set of symbols
from pylatexenc.latexencode._uni2latexmap import uni2latex as uni2latex_defaults
missing_keys = set(d.keys()).difference(set(uni2latex_defaults.keys()))
if missing_keys:
print("#\n# Missing keys added from unicode.xml\n#\n")
for k in sorted(missing_keys):
if "'" not in d[k]:
therepr = "r'"+d[k]+"'"
else:
therepr = repr(d[k])
thedef = "0x%04X: %s,"%(k, therepr)
print("%-50s# %s [%s]"%(thedef, dnames[k], unichr(k)))
|
