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
83
84
85
86
87
88
89
90
91
92
93
94
95
|
#!/usr/bin/env python3
"""Every font here against HarfBuzz, on random runs:
python3 text/fonts.py VEGA_SYMBOLS [--runs N] [--only TEXT] [FONT...]
The fonts given, else every font fontconfig lists (of a collection, its
Korean face: CJK collections are why there are collections here). Each is
built (those with outlines) into a symbol file with its characters in the ranges below and
shaping for each script it has ten letters of (and Common); the build
refuses a file whose shaping differs from HarfBuzz's (vega-symbols build
--runs). A line per font; the last is JSON: fonts, plans, runs that
differed, fonts that failed. Needs fontTools; exits 1 on a difference.
"""
import argparse
import json
import os
import subprocess
import sys
import tempfile
from fontTools.ttLib import TTCollection, TTFont
RANGES = [(0x20, 0x24F), (0x250, 0x2FF), (0x300, 0x36F), (0x370, 0x52F), (0x590, 0x5FF), (0x600, 0x6FF),
(0x750, 0x77F), (0x1E00, 0x1FFF), (0x2000, 0x206F), (0x20A0, 0x20CF), (0xFB00, 0xFB4F), (0xFE70, 0xFEFF),
(0x1100, 0x11FF), (0x302E, 0x302F), (0x3130, 0x318F), (0xA960, 0xA97F), (0xAC00, 0xD7A3), (0xD7B0, 0xD7FF),
(0x900, 0xD7F), (0x1CD0, 0x1CFF), (0xA8E0, 0xA8FF), (0x25CC, 0x25CC), (0x1000, 0x109F), (0xA9E0, 0xA9FF),
(0xAA60, 0xAA7F), (0x1780, 0x17FF), (0x19E0, 0x19FF), (0xD80, 0xDFF), (0xF00, 0xFFF), (0xA980, 0xA9DF),
(0x1B00, 0x1B7F), (0x1800, 0x18AF), (0xE00, 0xEFF), (0x700, 0x74F), (0x860, 0x86F), (0xFB50, 0xFDFF),
(0xFE00, 0xFE0F)]
LETTERS = {'Latn': (0x41, 0x7A), 'Grek': (0x391, 0x3C9), 'Cyrl': (0x410, 0x44F), 'Hebr': (0x5D0, 0x5EA),
'Arab': (0x621, 0x64A), 'Hang': (0xAC00, 0xD7A3), 'Deva': (0x915, 0x939), 'Beng': (0x995, 0x9B9),
'Guru': (0xA15, 0xA39), 'Gujr': (0xA95, 0xAB9), 'Orya': (0xB15, 0xB39), 'Taml': (0xB95, 0xBB9),
'Telu': (0xC15, 0xC39), 'Knda': (0xC95, 0xCB9), 'Mlym': (0xD15, 0xD39), 'Khmr': (0x1780, 0x17B3),
'Mymr': (0x1000, 0x102A), 'Sinh': (0xD9A, 0xDC6), 'Tibt': (0xF40, 0xF6C), 'Java': (0xA98F, 0xA9B2),
'Bali': (0x1B13, 0x1B33), 'Mong': (0x1820, 0x1878), 'Thai': (0xE01, 0xE2E), 'Laoo': (0xE81, 0xEAE),
'Syrc': (0x710, 0x72C)}
def main():
parser = argparse.ArgumentParser()
parser.add_argument('tool')
parser.add_argument('fonts', nargs='*')
parser.add_argument('--runs', default='500')
parser.add_argument('--only', default='')
args = parser.parse_args()
fonts = args.fonts or sorted(set(subprocess.run(['fc-list', '--format', '%{file}\n'], capture_output=True,
text=True).stdout.split()))
total = {'fonts': 0, 'plans': 0, 'differences': 0, 'failed': 0}
with tempfile.TemporaryDirectory(prefix='vega-fonts-') as work:
for path in fonts:
if args.only not in path:
continue
face = 0
try:
if path.endswith('.ttc'):
names = [f['name'].getDebugName(4) or '' for f in TTCollection(path, lazy=True).fonts]
korean = [i for i, n in enumerate(names) if n.endswith(' KR')]
if not korean:
continue
face = korean[0]
font = TTFont(path, fontNumber=face, lazy=True)
if not any(tag in font for tag in ('glyf', 'CFF ', 'CFF2')):
continue # bitmaps alone (color emoji): nothing to draw from
cmap = font.getBestCmap() or {}
except Exception as e: # not a font fontTools reads
print('skip', path, e)
continue
codes = sorted(c for c in cmap if any(a <= c <= b for a, b in RANGES))
if not codes:
continue
spans, start = [], codes[0]
for a, b in zip(codes, codes[1:] + [None]):
if b != a + 1:
spans.append(f'{start:#x}-{a:#x}' if a != start else f'{a:#x}')
start = b
scripts = [s for s, (a, b) in LETTERS.items() if sum(1 for c in codes if a <= c <= b) >= 10] + ['Zyyy']
built = subprocess.run([args.tool, 'build', '--font', path] + (['--face', str(face)] if face else []) +
['--codes', ','.join(spans), '--shape', ','.join(scripts), '--runs', args.runs,
'-o', os.path.join(work, 'font.vsym')], capture_output=True, text=True)
plans = [json.loads(line) for line in built.stdout.splitlines() if line.startswith('{"script"')]
differences = sum(p['differences'] for p in plans)
status = 'ok' if built.returncode == 0 else 'FAIL'
why = (built.stderr.strip().splitlines() or [''])[-1][:150] if built.returncode else ''
print(f'{status:4} {os.path.basename(path):40} {",".join(scripts):30} plans={len(plans):2} '
f'differences={differences}', why, flush=True)
total['fonts'] += 1
total['plans'] += len(plans)
total['differences'] += differences
total['failed'] += built.returncode != 0 and not differences
print(json.dumps(total))
return 1 if total['differences'] or total['failed'] else 0
if __name__ == '__main__':
sys.exit(main())
|
