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
|
# Needs UnicodeData.txt in the current directory.
#
# It can be obtained from unicode.org:
# - http://www.unicode.org/Public/<VERSION>/ucd/UnicodeData.txt
#
# If executed as a script, it will generate the contents of the file
# python3 scripts/generate_unicode_tolower.py header > `src/base/unicode/tolower.h`,
# python3 scripts/generate_unicode_tolower.py data > `src/base/unicode/tolower_data.h`.
import sys
import unicode
def generate_cases():
ud = unicode.data()
return [(unicode.unhex(u["Value"]), unicode.unhex(u["Simple_Lowercase_Mapping"])) for u in ud if u["Simple_Lowercase_Mapping"]]
def gen_header(cases):
print(f"""\
#include <cstdint>
struct UPPER_LOWER
{{
\tint32_t upper;
\tint32_t lower;
}};
enum
{{
\tNUM_TOLOWER = {len(cases)},
}};
extern const struct UPPER_LOWER tolowermap[];""")
def gen_data(cases):
print("""\
#ifndef TOLOWER_DATA
#error "This file must only be included in `tolower.cpp`"
#endif
const struct UPPER_LOWER tolowermap[] = {""")
for upper_code, lower_code in cases:
print(f"\t{{{upper_code}, {lower_code}}},")
print("};")
def main():
cases = generate_cases()
header = "header" in sys.argv
data = "data" in sys.argv
if header:
gen_header(cases)
elif data:
gen_data(cases)
if __name__ == '__main__':
main()
|
