298 lines
14 KiB
Python
298 lines
14 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""生成中文子集位图字体 ui_font_cn_12.c（LVGL 格式，输出到 Drivers/BSP/UI/）。
|
||
|
||
前置依赖：
|
||
npm i -g lv_font_conv # 离线 TTF/OTF -> LVGL 字体 转换器
|
||
pip install fonttools # 仅当字体源是 .ttc 集合时需要（用于抽取单字重）
|
||
|
||
用法：
|
||
python tools/font_gen/make_font.py # 默认：宋体, 12px, 1bpp
|
||
python tools/font_gen/make_font.py --bpp 2 # 宋体细笔画发虚时改用 2bpp
|
||
python tools/font_gen/make_font.py --font C:/path/to/font.ttf
|
||
"""
|
||
import os
|
||
import sys
|
||
import argparse
|
||
import tempfile
|
||
import subprocess
|
||
|
||
ROOT = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||
OUT = os.path.join(ROOT, 'Drivers', 'BSP', 'UI', 'ui_font_cn_12.c')
|
||
CHARS_FILE = os.path.join(ROOT, 'ui_cn_chars.txt')
|
||
FONT_NAME = 'ui_font_cn_12'
|
||
|
||
|
||
def resolve_lv_font_conv():
|
||
# 1) 全局 node 模块路径（npm i -g）
|
||
try:
|
||
groot = subprocess.check_output(['npm', 'root', '-g'], text=True).strip()
|
||
p = os.path.join(groot, 'lv_font_conv', 'lv_font_conv.js')
|
||
if os.path.exists(p):
|
||
return ['node', p]
|
||
except Exception:
|
||
pass
|
||
# 2) PATH 上的可执行
|
||
for cmd in ('lv_font_conv.cmd', 'lv_font_conv'):
|
||
if subprocess.run(['where', cmd], capture_output=True, shell=True).returncode == 0:
|
||
return [cmd]
|
||
sys.exit('ERROR: 找不到 lv_font_conv。请先执行: npm i -g lv_font_conv')
|
||
|
||
|
||
def resolve_font(path):
|
||
if path:
|
||
if not os.path.exists(path):
|
||
sys.exit('ERROR: --font 指定的文件不存在: ' + path)
|
||
return path
|
||
# 默认字体：Windows 宋体集合 simsun.ttc（lv_font_conv 不支持 .ttc，需先抽取 face0）
|
||
ttc = r'C:\Windows\Fonts\simsun.ttc'
|
||
if os.path.exists(ttc):
|
||
try:
|
||
from fontTools.ttLib import TTCollection
|
||
coll = TTCollection(ttc)
|
||
tmp = os.path.join(tempfile.gettempdir(), 'simsun_regular.ttf')
|
||
coll.fonts[0].save(tmp)
|
||
print('extracted SimSun regular (face0) ->', tmp)
|
||
return tmp
|
||
except Exception as e:
|
||
sys.exit('ERROR: 抽取 simsun.ttc 失败，请 pip install fonttools，或用 --font 指定 ttf: ' + str(e))
|
||
sys.exit('ERROR: 未找到 C:\\Windows\\Fonts\\simsun.ttc，请用 --font 指定字体 ttf/otf 路径')
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# 箭头字形合并
|
||
# 宋体（simsun.ttc）没有 U+25B6（▶）字形，lv_font_conv 会静默跳过 → 真机显示成方框。
|
||
# 该字形从 Segoe UI Symbol（seguisym.ttf，Windows 自带）提取，全量重生成字体后
|
||
# 自动补回，避免"重生成字体箭头又变方框"。
|
||
# ---------------------------------------------------------------------------
|
||
ARROW_CP_DEC = 9654 # U+25B6 ▶
|
||
ARROW_BITMAP = [0x80, 0xe0, 0xf0, 0xfc, 0xff, 0xfe, 0xf8, 0xf0, 0xc0, 0x0]
|
||
ARROW_ADV_W, ARROW_BOX_W, ARROW_BOX_H, ARROW_OFS_X, ARROW_OFS_Y = 165, 8, 10, 1, -1
|
||
|
||
|
||
def merge_arrow_glyph(font_path):
|
||
"""若字体缺 U+25B6(▶)，把预提取的箭头字形合并进去（位图 + glyph_dsc + cmap）。"""
|
||
import re
|
||
raw = open(font_path, 'rb').read()
|
||
has_bom = raw.startswith(b'\xef\xbb\xbf')
|
||
src = raw.decode('utf-8-sig')
|
||
if re.search(r'\.range_start\s*=\s*9654\s*,', src):
|
||
print('arrow U+25B6 已存在，跳过合并')
|
||
return
|
||
# 当前位图总字节数（新字形 bitmap_index 的取值）
|
||
bm = re.search(r'glyph_bitmap\[\]\s*=\s*\{', src)
|
||
end_bm = src.find('\n};', bm.end())
|
||
body_bm = re.sub(r'/\*.*?\*/', '', src[bm.end():end_bm], flags=re.S)
|
||
total = len(re.findall(r'0x[0-9a-fA-F]+', body_bm))
|
||
glyph_count = len(re.findall(r'\.bitmap_index\s*=\s*\d+', src))
|
||
# 1) 追加位图
|
||
bmp = ',\n\n /* U+25B6 "▶"（来源：Segoe UI Symbol；宋体无此字形） */\n ' + \
|
||
', '.join('0x%02x' % b for b in ARROW_BITMAP)
|
||
src = src[:end_bm] + bmp + src[end_bm:]
|
||
# 2) 追加 glyph_dsc
|
||
gd = re.search(r'glyph_dsc\[\]\s*=\s*\{', src)
|
||
end_gd = src.find('\n};', gd.end())
|
||
entry = ',\n {.bitmap_index = %d, .adv_w = %d, .box_w = %d, .box_h = %d, .ofs_x = %d, .ofs_y = %d} /* U+25B6 */' % (
|
||
total, ARROW_ADV_W, ARROW_BOX_W, ARROW_BOX_H, ARROW_OFS_X, ARROW_OFS_Y)
|
||
src = src[:end_gd] + entry + src[end_gd:]
|
||
# 3) 追加 cmap（单码位映射）
|
||
cm = re.search(r'cmaps\[\]\s*=\s*\{', src)
|
||
end_cm = src.find('\n};', cm.end())
|
||
cmap = ',\n {\n .range_start = %d, .range_length = 1, .glyph_id_start = %d,\n' \
|
||
' .unicode_list = NULL, .glyph_id_ofs_list = NULL, .list_length = 0, .type = LV_FONT_FMT_TXT_CMAP_FORMAT0_TINY\n }' % (
|
||
ARROW_CP_DEC, glyph_count)
|
||
src = src[:end_cm] + cmap + src[end_cm:]
|
||
# 4) cmap_num +1
|
||
src = re.sub(r'\.cmap_num = (\d+),',
|
||
lambda m: '.cmap_num = %d,' % (int(m.group(1)) + 1), src, count=1)
|
||
out = b'\xef\xbb\xbf' if has_bom else b''
|
||
open(font_path, 'wb').write(out + src.encode('utf-8'))
|
||
print('已合并箭头 U+25B6：位图+%d 字节，glyph_id=%d' % (len(ARROW_BITMAP), glyph_count))
|
||
|
||
|
||
def fix_trailing_newline(path):
|
||
"""规范化文件末尾为恰好一个 \n（pre-commit end-of-file-fixer 要求）。
|
||
|
||
lv_font_conv 产物末尾多一个空行（`#endif` 之后 `\n\n`），统一在此收敛为单个换行，
|
||
避免每次重生成字体都触发 end-of-file-fixer 拦截提交。
|
||
"""
|
||
with open(path, 'rb') as fp:
|
||
data = fp.read()
|
||
body = data
|
||
while body.endswith(b'\r\n') or body.endswith(b'\n'):
|
||
body = body[:-2] if body.endswith(b'\r\n') else body[:-1]
|
||
fixed = body + b'\n'
|
||
if fixed != data:
|
||
with open(path, 'wb') as fp:
|
||
fp.write(fixed)
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# 低码位符号补回（与箭头字形合并同一模式）
|
||
# lv_font_conv 的稀疏 cmap 从符号集中最小码位起算，低于该起点的符号被静默丢弃
|
||
# （实测：U+3001 全角逗号 < 0x4E2D 范围起点，未进字体 → 页脚"，"长期渲染为空白）。
|
||
# 处理：对每个此类符号单独生成迷你字体（真实宋体位图），再并入主字体
|
||
# （位图 + glyph_dsc + 单码位 cmap，幂等）。
|
||
# ---------------------------------------------------------------------------
|
||
EXTRA_SYMBOLS = ['，'] # U+3001 全角逗号（页脚"第 X 页，共 Y 页"）
|
||
|
||
|
||
def merge_extra_symbols(font_path, size, bpp):
|
||
"""把 lv_font_conv 丢失的低码位符号从迷你字体并入主字体（逐符号、幂等）。"""
|
||
import re
|
||
for ch in EXTRA_SYMBOLS:
|
||
cp = ord(ch)
|
||
raw = open(font_path, 'rb').read()
|
||
has_bom = raw.startswith(b'\xef\xbb\xbf')
|
||
src = raw.decode('utf-8-sig')
|
||
if re.search(r'\.range_start\s*=\s*%d\s*,' % cp, src):
|
||
print('U+%04X %r 已存在，跳过合并' % (cp, ch))
|
||
continue
|
||
|
||
# 1) 单独生成仅含该符号的迷你字体（真实宋体位图/度量）
|
||
tmp = os.path.join(tempfile.gettempdir(), 'font_extra_%04x.c' % cp)
|
||
cmd = resolve_lv_font_conv() + ['--font', resolve_font(None),
|
||
'--size', str(size), '--bpp', str(bpp),
|
||
'--symbols', ch, '--no-compress',
|
||
'--format', 'lvgl', '--lv-font-name', 'tmp_extra',
|
||
'-o', tmp]
|
||
r = subprocess.run(cmd)
|
||
if r.returncode != 0:
|
||
sys.exit('ERROR: 生成 U+%04X 迷你字体失败' % cp)
|
||
mini = open(tmp, encoding='utf-8-sig').read()
|
||
|
||
# 2) 从迷你字体提取位图字节 / glyph_dsc 字段 / 码位
|
||
bm = re.search(r'glyph_bitmap\[\]\s*=\s*\{', mini)
|
||
end_bm = mini.find('\n};', bm.end())
|
||
body_bm = re.sub(r'/\*.*?\*/', '', mini[bm.end():end_bm], flags=re.S)
|
||
bytes_ = re.findall(r'0x[0-9a-fA-F]+', body_bm)
|
||
gd = re.search(r'glyph_dsc\[\]\s*=\s*\{', mini)
|
||
end_gd = mini.find('\n};', gd.end())
|
||
entries = re.findall(r'\{\.bitmap_index = (\d+), \.adv_w = (\d+), \.box_w = (\d+), '
|
||
r'\.box_h = (\d+), \.ofs_x = (-?\d+), \.ofs_y = (-?\d+)\}',
|
||
mini[gd.end():end_gd])
|
||
if len(entries) < 2:
|
||
sys.exit('ERROR: 无法解析 U+%04X 迷你字体 glyph_dsc' % cp)
|
||
# 取第 1 项（下标 0 是保留空字形）
|
||
bmp_ofs, adv, bw, bh, ox, oy = (int(v) for v in entries[1])
|
||
cm = re.search(r'cmaps\[\]\s*=\s*\{', mini)
|
||
m = re.search(r'\.range_start\s*=\s*(\d+)\s*,\s*\.range_length\s*=\s*(\d+)',
|
||
mini[cm.end():])
|
||
if not m or int(m.group(2)) != 1:
|
||
sys.exit('ERROR: U+%04X 迷你字体 cmap 非单码位，无法并入' % cp)
|
||
sym_cp, sym_len = int(m.group(1)), 1
|
||
|
||
# 3) 并入主字体：位图追加（偏移平移）+ glyph_dsc 追加 + 单码位 cmap 追加
|
||
body = re.search(r'glyph_bitmap\[\]\s*=\s*\{', src)
|
||
end_main_bm = src.find('\n};', body.end())
|
||
main_bytes = len(re.findall(r'0x[0-9a-fA-F]+',
|
||
re.sub(r'/\*.*?\*/', '', src[body.end():end_main_bm], flags=re.S)))
|
||
glyph_count = len(re.findall(r'\.bitmap_index\s*=\s*\d+', src))
|
||
|
||
bmp = ',\n\n /* U+%04X %r（来源：宋体迷你字体并入；lv_font_conv 丢低码位符号） */\n ' % (cp, ch) \
|
||
+ ', '.join(bytes_)
|
||
src = src[:end_main_bm] + bmp + src[end_main_bm:]
|
||
|
||
gd = re.search(r'glyph_dsc\[\]\s*=\s*\{', src)
|
||
end_main_gd = src.find('\n};', gd.end())
|
||
entry = ',\n {.bitmap_index = %d, .adv_w = %d, .box_w = %d, .box_h = %d, ' \
|
||
'.ofs_x = %d, .ofs_y = %d} /* U+%04X */' % (
|
||
main_bytes + bmp_ofs, adv, bw, bh, ox, oy, cp)
|
||
src = src[:end_main_gd] + entry + src[end_main_gd:]
|
||
|
||
cm = re.search(r'cmaps\[\]\s*=\s*\{', src)
|
||
end_main_cm = src.find('\n};', cm.end())
|
||
cmap = ',\n {\n .range_start = %d, .range_length = %d, ' \
|
||
'.glyph_id_start = %d,\n' \
|
||
' .unicode_list = NULL, .glyph_id_ofs_list = NULL, .list_length = 0, ' \
|
||
'.type = LV_FONT_FMT_TXT_CMAP_FORMAT0_TINY\n }' % (sym_cp, sym_len, glyph_count)
|
||
src = src[:end_main_cm] + cmap + src[end_main_cm:]
|
||
|
||
src = re.sub(r'\.cmap_num = (\d+),',
|
||
lambda m: '.cmap_num = %d,' % (int(m.group(1)) + 1), src, count=1)
|
||
|
||
out = b'\xef\xbb\xbf' if has_bom else b''
|
||
open(font_path, 'wb').write(out + src.encode('utf-8'))
|
||
print('已合并 U+%04X %r：%d 字节位图，glyph_id=%d' % (cp, ch, len(bytes_), glyph_count))
|
||
|
||
|
||
def verify_coverage(font_path):
|
||
"""生成后校验：ui_cn_chars.txt 的全部码位必须进字体 cmap（防静默丢字）。
|
||
|
||
lv_font_conv 对某些码位会静默丢弃（低于稀疏范围起点、或源字体缺字形），
|
||
静默缺字在 UI 上表现为空白，极难发现。此校验把"缺字"变成生成期硬错误。
|
||
须在 merge_arrow_glyph / merge_extra_symbols 之后调用（合并的符号也要计入）。
|
||
"""
|
||
import re
|
||
src = open(font_path, encoding='utf-8-sig').read()
|
||
# 稀疏 cmap 的 unicode_list_N：十六进制偏移（相对 range_start）
|
||
ulists = {}
|
||
for m in re.finditer(r'static const uint16_t (unicode_list_\d+)\[\] = \{(.*?)\};', src, re.S):
|
||
ulists[m.group(1)] = [int(x, 16) for x in re.findall(r'0x[0-9a-fA-F]+', m.group(2))]
|
||
cmaps = [] # (range_start, range_length, sparse_offsets_or_None)
|
||
for m in re.finditer(r'\.range_start = (\d+), \.range_length = (\d+), \.glyph_id_start = (\d+),\s*'
|
||
r'\.unicode_list = ([^,]+), \.glyph_id_ofs_list = ([^,]+), \.list_length = (\d+), '
|
||
r'\.type = (\w+)', src):
|
||
ul = m.group(4).strip()
|
||
cmaps.append((int(m.group(1)), int(m.group(2)), ulists.get(ul)))
|
||
|
||
def covered(cp):
|
||
for rs, rl, offs in cmaps:
|
||
if offs is None:
|
||
if rs <= cp < rs + rl:
|
||
return True
|
||
elif (cp - rs) in offs:
|
||
return True
|
||
return False
|
||
|
||
chars = sorted(set(open(CHARS_FILE, encoding='utf-8').read().strip()))
|
||
missing = [c for c in chars if not covered(ord(c))]
|
||
if missing:
|
||
sys.exit('ERROR: 字体缺字 %d 个（UI 将显示空白）: %s'
|
||
% (len(missing), ' '.join('U+%04X' % ord(c) for c in missing)))
|
||
print('coverage OK: %d 个字符全部进字体' % len(chars))
|
||
|
||
|
||
def main():
|
||
# Windows GBK 控制台无法打印 ▶ 等符号：降级为替换字符，避免 UnicodeEncodeError 崩溃
|
||
try:
|
||
sys.stdout.reconfigure(errors='replace')
|
||
except Exception:
|
||
pass
|
||
|
||
ap = argparse.ArgumentParser()
|
||
ap.add_argument('--bpp', type=int, default=1, help='字体位深 1/2/3（默认 1）')
|
||
ap.add_argument('--size', type=int, default=12, help='字号（默认 12）')
|
||
ap.add_argument('--font', default=None, help='自定义字体 ttf/otf 路径（默认宋体）')
|
||
args = ap.parse_args()
|
||
|
||
if not os.path.exists(CHARS_FILE):
|
||
sys.exit('ERROR: 请先运行 extract_cn.py 生成 ui_cn_chars.txt')
|
||
|
||
chars = open(CHARS_FILE, encoding='utf-8').read().strip()
|
||
cmd = resolve_lv_font_conv()
|
||
font = resolve_font(args.font)
|
||
cmd += ['--font', font,
|
||
'--size', str(args.size),
|
||
'--bpp', str(args.bpp),
|
||
'-r', '0x20-0x7E', # 含 ASCII，使字体自包含
|
||
'--symbols', chars, # 本工程实际显示的汉字子集
|
||
'--no-compress', # 关闭 RLE 压缩，保证兼容
|
||
'--format', 'lvgl',
|
||
'--lv-font-name', FONT_NAME,
|
||
'-o', OUT]
|
||
|
||
print('RUN:', ' '.join(cmd))
|
||
r = subprocess.run(cmd)
|
||
if r.returncode != 0:
|
||
sys.exit('FAILED rc=%d' % r.returncode)
|
||
merge_arrow_glyph(OUT) # 补回宋体缺失的 ▶ 字形（幂等）
|
||
merge_extra_symbols(OUT, args.size, args.bpp) # 补回 lv_font_conv 丢弃的低码位符号（幂等）
|
||
verify_coverage(OUT) # 生成后校验：字符集全部码位必须进字体（防静默丢字）
|
||
fix_trailing_newline(OUT) # 规范化末尾换行（pre-commit end-of-file-fixer）
|
||
print('OK %d bytes -> %s' % (os.path.getsize(OUT), OUT))
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|