372 lines
13 KiB
Python
372 lines
13 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
字体子集化脚本 - 安全版本
|
||
从HTML和CSS文件中提取实际使用的字符，生成优化的子集字体
|
||
"""
|
||
|
||
import os
|
||
import re
|
||
import sys
|
||
from fontTools.ttLib import TTFont
|
||
from fontTools.subset import Subsetter, Options
|
||
|
||
def extract_chars_from_files(directories, extensions=('.html', '.md', '.css')):
|
||
"""从文件中提取使用的字符"""
|
||
chars = set()
|
||
|
||
for directory in directories:
|
||
if not os.path.exists(directory):
|
||
print(f"⚠️ 目录不存在，跳过: {directory}")
|
||
continue
|
||
|
||
print(f"🔍 扫描目录: {directory}")
|
||
|
||
for root, dirs, files in os.walk(directory):
|
||
for file in files:
|
||
if any(file.endswith(ext) for ext in extensions):
|
||
filepath = os.path.join(root, file)
|
||
try:
|
||
with open(filepath, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
|
||
# 提取中文字符
|
||
chinese_chars = re.findall(r'[一-鿿]', content)
|
||
chars.update(chinese_chars)
|
||
|
||
# 提取中文标点
|
||
cjk_punct = re.findall(r'[ -〿-]', content)
|
||
chars.update(cjk_punct)
|
||
|
||
# 提取英文和数字
|
||
ascii_chars = re.findall(r'[a-zA-Z0-9]', content)
|
||
chars.update(ascii_chars)
|
||
|
||
# 提取常用英文标点
|
||
en_punct = set('!@#$%^&*()_+-=[]{}|;:,.<>?/\\`~"\'-')
|
||
chars.update(en_punct)
|
||
|
||
except Exception as e:
|
||
print(f"⚠️ 读取文件失败 {filepath}: {e}")
|
||
|
||
return chars
|
||
|
||
def extract_chars_from_json(json_files):
|
||
"""从JSON数据文件中提取字符（用于友链、朋友圈等动态内容）"""
|
||
chars = set()
|
||
|
||
import json
|
||
|
||
for json_file in json_files:
|
||
if not os.path.exists(json_file):
|
||
print(f"⚠️ JSON文件不存在，跳过: {json_file}")
|
||
continue
|
||
|
||
print(f"🔍 扫描JSON文件: {json_file}")
|
||
|
||
try:
|
||
with open(json_file, 'r', encoding='utf-8') as f:
|
||
data = json.load(f)
|
||
|
||
# 将整个JSON转换为字符串，提取所有字符
|
||
content = json.dumps(data, ensure_ascii=False)
|
||
|
||
# 提取中文字符
|
||
chinese_chars = re.findall(r'[一-鿿]', content)
|
||
chars.update(chinese_chars)
|
||
|
||
# 提取中文标点
|
||
cjk_punct = re.findall(r'[ -〿-]', content)
|
||
chars.update(cjk_punct)
|
||
|
||
# 提取英文和数字
|
||
ascii_chars = re.findall(r'[a-zA-Z0-9]', content)
|
||
chars.update(ascii_chars)
|
||
|
||
print(f" ✅ 从 {json_file} 提取了 {len(chinese_chars)} 个中文字符")
|
||
|
||
except Exception as e:
|
||
print(f"⚠️ 读取JSON文件失败 {json_file}: {e}")
|
||
|
||
return chars
|
||
|
||
def fetch_and_extract_chars_from_api(urls):
|
||
"""从API接口获取数据并提取字符（用于动态内容如友链、朋友圈）"""
|
||
chars = set()
|
||
|
||
try:
|
||
import urllib.request
|
||
import json
|
||
import ssl
|
||
|
||
# 创建不验证SSL的上下文（用于内网或自签名证书）
|
||
context = ssl._create_unverified_context()
|
||
|
||
for url in urls:
|
||
print(f"🌐 尝试从API获取: {url}")
|
||
try:
|
||
req = urllib.request.Request(
|
||
url,
|
||
headers={
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
|
||
}
|
||
)
|
||
|
||
with urllib.request.urlopen(req, context=context, timeout=15) as response:
|
||
data = response.read().decode('utf-8')
|
||
|
||
try:
|
||
json_data = json.loads(data)
|
||
content = json.dumps(json_data, ensure_ascii=False)
|
||
|
||
# 提取中文字符
|
||
chinese_chars = re.findall(r'[一-鿿]', content)
|
||
chars.update(chinese_chars)
|
||
|
||
print(f" ✅ 从API提取了 {len(chinese_chars)} 个中文字符")
|
||
except json.JSONDecodeError:
|
||
print(f" ⚠️ 响应不是有效的JSON，跳过")
|
||
|
||
except urllib.error.URLError as e:
|
||
print(f" ❌ API请求失败: {e}")
|
||
except Exception as e:
|
||
print(f" ❌ 处理API响应失败: {e}")
|
||
|
||
except ImportError:
|
||
print("⚠️ urllib不可用，跳过API扫描")
|
||
|
||
return chars
|
||
|
||
def subset_font(input_font_path, output_font_path, chars):
|
||
"""生成子集字体"""
|
||
print(f"\n📦 加载字体: {input_font_path}")
|
||
|
||
# 检查输入文件
|
||
if not os.path.exists(input_font_path):
|
||
print(f"❌ 字体文件不存在: {input_font_path}")
|
||
return False
|
||
|
||
# 加载原始字体
|
||
try:
|
||
font = TTFont(input_font_path)
|
||
except Exception as e:
|
||
print(f"❌ 加载字体失败: {e}")
|
||
return False
|
||
|
||
# 获取原始字符数
|
||
cmap = font.getBestCmap()
|
||
original_count = len(cmap) if cmap else 0
|
||
original_size = os.path.getsize(input_font_path)
|
||
|
||
print(f"📊 原始字体信息:")
|
||
print(f" 字符数: {original_count}")
|
||
print(f" 文件大小: {original_size / 1024:.1f} KB")
|
||
|
||
# 配置子集化选项
|
||
options = Options()
|
||
if output_font_path.endswith('.woff2'):
|
||
options.flavor = 'woff2'
|
||
elif output_font_path.endswith('.woff'):
|
||
options.flavor = 'woff'
|
||
|
||
options.desubroutinize = True
|
||
options.layout_features = ['kern', 'liga'] # 保留基本的排版特性
|
||
|
||
# 创建子集化器
|
||
subsetter = Subsetter(options=options)
|
||
|
||
# 填充字符集
|
||
char_text = ''.join(chars)
|
||
print(f"\n✂️ 正在生成子集字体...")
|
||
print(f" 提取的字符数: {len(chars)}")
|
||
|
||
try:
|
||
subsetter.populate(text=char_text)
|
||
subsetter.subset(font)
|
||
except Exception as e:
|
||
print(f"❌ 子集化失败: {e}")
|
||
return False
|
||
|
||
# 保存子集字体
|
||
try:
|
||
font.save(output_font_path)
|
||
except Exception as e:
|
||
print(f"❌ 保存字体失败: {e}")
|
||
return False
|
||
|
||
# 获取子集信息
|
||
subset_size = os.path.getsize(output_font_path)
|
||
subset_font_obj = TTFont(output_font_path)
|
||
subset_cmap = subset_font_obj.getBestCmap()
|
||
subset_count = len(subset_cmap) if subset_cmap else 0
|
||
|
||
# 计算优化效果
|
||
reduction = original_size - subset_size
|
||
percentage = (reduction / original_size) * 100 if original_size > 0 else 0
|
||
|
||
print(f"\n✅ 子集化完成！")
|
||
print(f"📊 优化结果:")
|
||
print(f" 子集字符数: {subset_count}")
|
||
print(f" 子集文件大小: {subset_size / 1024:.1f} KB")
|
||
print(f" 减少: {reduction / 1024:.1f} KB ({percentage:.1f}%)")
|
||
|
||
# 验证是否真的优化了
|
||
if subset_size >= original_size:
|
||
print(f"\n⚠️ 警告: 子集字体反而变大了！")
|
||
print(f" 原因可能是提取了太多字符")
|
||
print(f" 建议检查扫描范围或使用更小的字符集")
|
||
return False
|
||
|
||
return True
|
||
|
||
def main():
|
||
print("🔤 字体子集化工具（安全版本）")
|
||
print("=" * 50)
|
||
|
||
# 配置路径
|
||
font_dir = "themes/Ying/static/font"
|
||
input_font = os.path.join(font_dir, "zql-v2.woff2")
|
||
chars_file = os.path.join(font_dir, "used_chars.txt")
|
||
|
||
# 检查输入文件
|
||
if not os.path.exists(input_font):
|
||
print(f"❌ 字体文件不存在: {input_font}")
|
||
print(f" 请确保在博客根目录运行此脚本")
|
||
sys.exit(1)
|
||
|
||
# 读取现有的字符列表（如果存在）
|
||
existing_chars = set()
|
||
if os.path.exists(chars_file):
|
||
with open(chars_file, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
existing_chars = set(content)
|
||
print(f"📖 读取现有字符: {len(existing_chars)} 个")
|
||
|
||
# 检查特殊字符是否存在
|
||
special_chars = ['—', '庶', '尉', '谏', '簿', '丞']
|
||
found_special = [c for c in special_chars if c in existing_chars]
|
||
print(f"🔍 检查特殊字符: {len(found_special)}/{len(special_chars)} 个已存在")
|
||
if found_special:
|
||
print(f" 已找到: {''.join(found_special)}")
|
||
else:
|
||
print(f"⚠️ 现有字符文件不存在，将创建新文件")
|
||
|
||
# 扫描目录
|
||
scan_dirs = ["content", "layouts"]
|
||
|
||
# 检查public目录是否存在
|
||
if os.path.exists("public"):
|
||
scan_dirs.append("public")
|
||
print(f"✅ 找到public目录，将扫描构建后的HTML")
|
||
else:
|
||
print(f"⚠️ 未找到public目录，请先运行: hugo --destination=public")
|
||
print(f" 将只扫描content和layouts目录")
|
||
|
||
print(f"\n🔍 扫描目录: {', '.join(scan_dirs)}")
|
||
|
||
# 提取字符（静态文件）
|
||
new_chars = extract_chars_from_files(scan_dirs)
|
||
print(f"\n📝 从文件中提取了 {len(new_chars)} 个唯一字符")
|
||
|
||
# 扫描动态数据文件（友链、朋友圈等）
|
||
json_data_files = [
|
||
"themes/Ying/static/json/link_lite.json", # 友链数据
|
||
"themes/Ying/static/json/friend_circle_data.json", # 朋友圈数据
|
||
"themes/Ying/data/links.yaml", # 友链配置
|
||
"themes/Ying/data/links.yml", # 友链配置（备用）
|
||
]
|
||
|
||
print(f"\n{'='*50}")
|
||
print(f"🔄 扫描动态数据文件（友链、朋友圈等）")
|
||
dynamic_chars = extract_chars_from_json(json_data_files)
|
||
print(f"📝 从动态数据中提取了 {len(dynamic_chars)} 个唯一字符")
|
||
|
||
# 从API获取动态数据（用于CI环境）
|
||
api_urls = [
|
||
"https://api.usj.cc/api/links?all=1", # 友链列表
|
||
"https://api.usj.cc/api/feeds", # 订阅源列表
|
||
"https://api.usj.cc/api/articles?limit=50", # 朋友圈文章
|
||
]
|
||
|
||
# 如果有环境变量，追加额外的API地址
|
||
if os.environ.get('FONT_SUBSET_API_URLS'):
|
||
extra_urls = os.environ['FONT_SUBSET_API_URLS'].split(',')
|
||
api_urls.extend(extra_urls)
|
||
print(f"\n{'='*50}")
|
||
print(f"🌐 从环境变量获取额外API地址")
|
||
print(f" 额外URLs: {', '.join(extra_urls)}")
|
||
|
||
print(f"\n{'='*50}")
|
||
print(f"🌐 扫描远程API（友链、朋友圈等）")
|
||
print(f" 共 {len(api_urls)} 个API端点")
|
||
|
||
api_chars = fetch_and_extract_chars_from_api(api_urls)
|
||
print(f"📝 从API提取了 {len(api_chars)} 个唯一字符")
|
||
dynamic_chars = dynamic_chars | api_chars
|
||
|
||
# 合并静态和动态字符
|
||
new_chars = new_chars | dynamic_chars
|
||
print(f"\n📊 合并后总字符数: {len(new_chars)}")
|
||
|
||
# 合并字符（保留现有字符 + 新提取的字符）
|
||
all_chars = existing_chars | new_chars
|
||
print(f"📊 合并后字符数: {len(all_chars)}")
|
||
|
||
# 验证特殊字符是否在合并后的字符集中
|
||
special_chars = ['—', '庶', '尉', '谏', '簿', '丞']
|
||
missing_special = [c for c in special_chars if c not in all_chars]
|
||
if missing_special:
|
||
print(f"⚠️ 警告：以下特殊字符不在合并后的字符集中: {''.join(missing_special)}")
|
||
print(f" 将强制添加这些字符...")
|
||
all_chars.update(special_chars)
|
||
else:
|
||
print(f"✅ 所有特殊字符都已保留在字符集中")
|
||
|
||
if len(all_chars) == 0:
|
||
print("❌ 未找到任何字符，请检查扫描目录")
|
||
sys.exit(1)
|
||
|
||
# 保存合并后的字符列表
|
||
with open(chars_file, 'w', encoding='utf-8') as f:
|
||
sorted_chars = sorted(all_chars)
|
||
f.write(''.join(sorted_chars))
|
||
print(f"💾 字符列表已保存到: {chars_file}")
|
||
|
||
# 显示部分字符（用于验证）
|
||
sample_chars = sorted(list(all_chars))[:50]
|
||
print(f"📋 前50个字符: {''.join(sample_chars)}")
|
||
|
||
# 生成woff2子集字体
|
||
output_woff2 = os.path.join(font_dir, "zql-v2-subset.woff2")
|
||
print(f"\n{'='*50}")
|
||
print(f"🎯 生成 woff2 子集字体...")
|
||
success_woff2 = subset_font(input_font, output_woff2, all_chars)
|
||
|
||
# 生成woff子集字体
|
||
output_woff = os.path.join(font_dir, "zql-v2-subset.woff")
|
||
print(f"\n{'='*50}")
|
||
print(f"🎯 生成 woff 子集字体...")
|
||
success_woff = subset_font(input_font, output_woff, all_chars)
|
||
|
||
# 总结
|
||
print(f"\n{'='*50}")
|
||
if success_woff2 and success_woff:
|
||
print(f"🎉 所有子集字体生成成功！")
|
||
|
||
# 显示最终文件大小
|
||
print(f"\n📂 最终文件:")
|
||
for f in [output_woff2, output_woff]:
|
||
if os.path.exists(f):
|
||
size = os.path.getsize(f)
|
||
print(f" {os.path.basename(f)}: {size / 1024:.1f} KB")
|
||
|
||
print(f"\n✅ 下一步:")
|
||
print(f" 1. 更新CSS字体声明（将zql-v2.woff2改为zql-v2-subset.woff2）")
|
||
print(f" 2. 重新构建Hugo: hugo server -D")
|
||
print(f" 3. 测试字体显示是否正常")
|
||
else:
|
||
print(f"⚠️ 部分字体生成失败或未优化")
|
||
print(f" 建议使用fallback方案（保留原始字体）")
|
||
|
||
if __name__ == "__main__":
|
||
main()
|