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
|
#!/usr/bin/env python3
# SPDX-License-Identifier: GPL-2.0-only
from sys import stderr
with open("UnicodeData.txt") as f:
data = f.read()
data = data.split("\n")
bolds = {}
def line_to_char(line):
return chr(int(line.split(";", 1)[0], 16))
for line in data:
if "BOLD" in line:
bold_name = line.split(";", 2)[1]
try_names = []
if bold_name.startswith("MATHEMATICAL BOLD CAPITAL "):
try_names.append("LATIN CAPITAL LETTER " + bold_name[len("MATHEMATICAL BOLD CAPITAL "):])
if bold_name.endswith(" SYMBOL"):
try_names.append("GREEK CAPITAL " + bold_name[len("MATHEMATICAL BOLD CAPITAL "):])
else:
try_names.append("GREEK CAPITAL LETTER " + bold_name[len("MATHEMATICAL BOLD CAPITAL "):])
elif bold_name.startswith("MATHEMATICAL BOLD SMALL "):
try_names.append("LATIN SMALL LETTER " + bold_name[len("MATHEMATICAL BOLD SMALL "):])
try_names.append("GREEK SMALL LETTER " + bold_name[len("MATHEMATICAL BOLD SMALL "):])
elif (
bold_name.startswith("MATHEMATICAL BOLD FRAKTUR ")
or bold_name.startswith("MATHEMATICAL BOLD ITALIC ")
or bold_name.startswith("MATHEMATICAL BOLD SCRIPT ")
):
if bold_name.startswith("MATHEMATICAL BOLD FRAKTUR SMALL "):
try_names.append("LATIN SMALL LETTER " + bold_name[len("MATHEMATICAL BOLD FRAKTUR SMALL "):])
if bold_name.startswith("MATHEMATICAL BOLD FRAKTUR CAPITAL "):
try_names.append("LATIN CAPITAL LETTER " + bold_name[len("MATHEMATICAL BOLD FRAKTUR CAPITAL "):])
else:
normal_name = "".join(bold_name.split("BOLD ", 1))
try_names.append("SANS-SERIF ".join(bold_name.split("BOLD ", 1)))
try_names.append(bold_name.split("BOLD ", 1)[1])
elif bold_name.startswith("MATHEMATICAL SANS-SERIF BOLD "):
try_names.append("".join(bold_name.split("BOLD ", 1)))
try_names.append("".join(normal_name.split("SANS-SERIF ", 1)))
if bold_name.endswith(" SYMBOL"):
try_names.append("GREEK " + bold_name[len("MATHEMATICAL SANS-SERIF BOLD "):])
try_names.append("GREEK LUNATE " + bold_name[len("MATHEMATICAL SANS-SERIF BOLD "):])
else:
try_names.append("GREEK " + " LETTER ".join(bold_name.split("BOLD ", 1)[1].split(" ", 1)))
try_names.append(bold_name[len("MATHEMATICAL SANS-SERIF BOLD "):])
elif bold_name.startswith("MATHEMATICAL BOLD DIGIT "):
try_names.append("DIGIT " + bold_name[len("MATHEMATICAL BOLD DIGIT "):])
elif bold_name.startswith("MATHEMATICAL BOLD "):
try_names.append("GREEK " + bold_name[len("MATHEMATICAL BOLD "):])
try_names.append("GREEK LUNATE " + bold_name[len("MATHEMATICAL BOLD "):])
try_names.append(bold_name[len("MATHEMATICAL BOLD "):])
else:
normal_name = bold_name
normal_line = None
try_names.insert(0, normal_name)
for x in try_names:
for line2 in data:
if (
";" + x + ";" in line2
and line != line2
and "<control>" not in line2
):
normal_line = line2
break
if not normal_line:
print("not found:", line, file=stderr)
continue
char = line_to_char(line)
normal = line_to_char(normal_line)
if normal not in bolds:
bolds[normal] = char
import json
print("window.unicodeMaps.toBold =", json.dumps(bolds), ";")
print(bolds, file=stderr)
|
