fc-case/fc-case.py | 74 +++++++++++++++++++++++++----------------------------
1 file changed, 35 insertions(+), 39 deletions(-)
New commits:
commit 3bb79f0a4ac7977942d75a16a9e7ac9cb353509d
Merge: 6e1081d 2bb54d3
Author: Akira TAGOH <akira@xxxxxxxxx>
Date: Fri Nov 22 12:52:46 2024 +0000
Merge branch 'issues/433' into 'main'
fc-case: Correct the license header of fccase.h
Closes #433
See merge request fontconfig/fontconfig!347
commit 2bb54d3b815d9932ed57d875b3077c1c7a4d767d
Author: Akira TAGOH <akira@xxxxxxxxx>
Date: Fri Nov 22 19:49:27 2024 +0900
fc-case: Correct the license header of fccase.h
fccase.h is generated against CaseFolding.txt from Unicode.org.
All the data available in this file should be licensed under
a terms of use https://www.unicode.org/terms_of_use.html
Fixes https://gitlab.freedesktop.org/fontconfig/fontconfig/-/issues/433
diff --git a/fc-case/fc-case.py b/fc-case/fc-case.py
index 360bd32..be808b3 100755
--- a/fc-case/fc-case.py
+++ b/fc-case/fc-case.py
@@ -28,29 +28,32 @@ import argparse
import string
import sys
+
class CaseFoldClass(Enum):
COMMON = 1
FULL = 2
SIMPLE = 3
TURKIC = 4
+
class CaseFoldMethod(Enum):
RANGE = 0
EVEN_ODD = 1
FULL = 2
+
caseFoldClassMap = {
- 'C' : CaseFoldClass.COMMON,
- 'F' : CaseFoldClass.FULL,
- 'S' : CaseFoldClass.SIMPLE,
- 'T' : CaseFoldClass.TURKIC
+ 'C': CaseFoldClass.COMMON,
+ 'F': CaseFoldClass.FULL,
+ 'S': CaseFoldClass.SIMPLE,
+ 'T': CaseFoldClass.TURKIC
}
folds = []
def ucs4_to_utf8(ucs4):
utf8_rep = []
-
+
if ucs4 < 0x80:
utf8_rep.append(ucs4)
bits = -6
@@ -70,17 +73,19 @@ def ucs4_to_utf8(ucs4):
utf8_rep.append(((ucs4 >> 30) & 0x01) | 0xFC)
bits = 24
else:
- return [];
+ return []
while bits >= 0:
utf8_rep.append(((ucs4 >> bits) & 0x3F) | 0x80)
- bits-= 6
+ bits -= 6
return utf8_rep
+
def utf8_size(ucs4):
return len(ucs4_to_utf8(ucs4))
+
case_fold_method_name_map = {
CaseFoldMethod.RANGE: 'FC_CASE_FOLD_RANGE,',
CaseFoldMethod.EVEN_ODD: 'FC_CASE_FOLD_EVEN_ODD,',
@@ -115,7 +120,8 @@ if __name__=='__main__':
tokens = line.split('; ')
if len(tokens) < 3:
- print('Not enough tokens in line {}'.format(cnt), file=sys.stderr)
+ print('Not enough tokens in line {}'.format(cnt),
+ file=sys.stderr)
sys.exit(1)
# Get upper case value
@@ -125,14 +131,14 @@ if __name__=='__main__':
cfclass = caseFoldClassMap[tokens.pop(0)]
# Get list of result characters
- lower = list(map(lambda s: int(s,16), tokens.pop(0).split()))
+ lower = list(map(lambda s: int(s, 16), tokens.pop(0).split()))
# print('\t----> {:04X} {} {}'.format(upper, cfclass, lower))
if not minFoldChar:
minFoldChar = upper
- maxFoldChar = upper;
+ maxFoldChar = upper
if cfclass in [CaseFoldClass.COMMON, CaseFoldClass.FULL]:
if len(lower) == 1:
@@ -146,18 +152,18 @@ if __name__=='__main__':
if foldExtends:
# This modifies the last fold item in the array too
- fold['count'] = upper - fold['upper'] + 1;
+ fold['count'] = upper - fold['upper'] + 1
else:
fold = {}
fold['upper'] = upper
- fold['offset'] = lower[0] - upper;
+ fold['offset'] = lower[0] - upper
if fold['offset'] == 1:
fold['method'] = CaseFoldMethod.EVEN_ODD
else:
fold['method'] = CaseFoldMethod.RANGE
fold['count'] = 1
folds.append(fold)
- expand = utf8_size (lower[0]) - utf8_size(upper)
+ expand = utf8_size(lower[0]) - utf8_size(upper)
else:
fold = {}
fold['upper'] = upper
@@ -185,20 +191,14 @@ if __name__=='__main__':
if args.output_file:
sys.stdout = open(args.output_file, 'w', encoding='utf-8')
- # Read the template file
- if args.template_file:
- tmpl_file = open(args.template_file, 'r', encoding='utf-8')
- else:
- tmpl_file = sys.stdin
-
- # Scan the input until the marker is found
- # FIXME: this is a bit silly really, might just as well harcode
- # the license header in the script and drop the template
- for line in tmpl_file:
- if line.strip() == '@@@':
- break
- print(line, end='')
-
+ print('/*')
+ print(' * This file was generated against CaseFolding.txt from'
+ ' Unicode.org.')
+ print(' * All the data in array is a part of them and licensed'
+ ' under a terms of use:')
+ print(' * https://www.unicode.org/terms_of_use.html')
+ print(' */')
+ print('')
# Dump these tables
print('#define FC_NUM_CASE_FOLD\t{}'.format(len(folds)))
print('#define FC_NUM_CASE_FOLD_CHARS\t{}'.format(len(foldChars)))
@@ -211,14 +211,14 @@ if __name__=='__main__':
# Dump out ranges
print('static const FcCaseFold fcCaseFold[FC_NUM_CASE_FOLD] = {')
for f in folds:
- short_offset = f['offset']
- if short_offset < -32367:
- short_offset += 65536
- if short_offset > 32368:
- short_offset -= 65536
- print(' {} 0x{:08x}, {:22s} 0x{:04x}, {:6d} {},'.format('{',
- f['upper'], case_fold_method_name_map[f['method']],
- f['count'], short_offset, '}'))
+ short_offset = f['offset']
+ if short_offset < -32367:
+ short_offset += 65536
+ if short_offset > 32368:
+ short_offset -= 65536
+ print(f' {{ 0x{f["upper"]:08x}, '
+ f'{case_fold_method_name_map[f["method"]]:22s} '
+ f'0x{f["count"]:04x}, {short_offset:6d} }},')
print('};\n')
# Dump out "other" values
@@ -233,8 +233,4 @@ if __name__=='__main__':
print('0x{:02x}'.format(c), end=end)
print('\n};')
- # And flush out the rest of the input file
- for line in tmpl_file:
- print(line, end='')
-
sys.stdout.flush()
