pengxiao
c81cf83c13
- 新增 officefile/latex/ 目录，包含 main.tex、preamble.tex 及 14 个章节 + 10 个附录 tex 文件 - md→tex 转换流程：pandoc 转换 + _postprocess.py 后处理（去编号、修破折号、清标签） - 修复 5 个 md 源文件的标题层级（H1→H2 降级，统一层级结构） - 配置 VS Code LaTeX Workshop（xelatex + ctexbook 编译链） - 新增 VS Code workspace 和 .gitignore（排除 LaTeX 编译产物） Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
66 lines
2.5 KiB
Python
66 lines
2.5 KiB
Python
import re, os
|
||
|
||
outdir = os.path.join(os.path.dirname(__file__), 'chapters')
|
||
counts = {'labels': 0, 'dashes': 0, 'rules': 0, 'chapnum': 0, 'secnum': 0, 'emdashtext': 0}
|
||
|
||
for fname in sorted(os.listdir(outdir)):
|
||
if not fname.endswith('.tex') or fname == 'ch13-conclusion.tex':
|
||
continue
|
||
|
||
fpath = os.path.join(outdir, fname)
|
||
with open(fpath, 'r', encoding='utf-8') as f:
|
||
content = f.read()
|
||
|
||
# 1. Remove Unicode labels like \label{ux7b2c...}
|
||
label_pattern = re.compile(r'\\label\{[^}]*ux[0-9a-f]+[^}]*\}')
|
||
matches = label_pattern.findall(content)
|
||
counts['labels'] += len(matches)
|
||
content = label_pattern.sub('', content)
|
||
|
||
# 2. Fix dashes + strip chapter number prefix (first line)
|
||
lines = content.split('\n')
|
||
if lines and lines[0].startswith('\\chapter{'):
|
||
old_line = lines[0]
|
||
new_line = old_line.replace('------', '——')
|
||
new_line = re.sub(r'\\chapter\{第\d+章[：:\s]+', r'\\chapter{', new_line)
|
||
if new_line != old_line:
|
||
if '------' in old_line:
|
||
counts['dashes'] += 1
|
||
if re.search(r'第\d+章', old_line):
|
||
counts['chapnum'] += 1
|
||
lines[0] = new_line
|
||
content = '\n'.join(lines)
|
||
|
||
# 3. Remove decorative rules
|
||
rule = '\\begin{center}\\rule{0.5\\linewidth}{0.5pt}\\end{center}'
|
||
count = content.count(rule)
|
||
counts['rules'] += count
|
||
content = content.replace(rule + '\n\n', '\n')
|
||
content = content.replace(rule + '\n', '\n')
|
||
|
||
# 4. Fix em-dashes in body text
|
||
count = content.count('------')
|
||
counts['emdashtext'] += count
|
||
content = content.replace('------', '——')
|
||
|
||
# 5. Strip numeric prefixes from section/subsection/subsubsection
|
||
for cmd in ['section', 'subsection', 'subsubsection']:
|
||
def make_stripper(cmd_name):
|
||
def strip_num(m):
|
||
title = m.group(1)
|
||
new_title = re.sub(r'^\d+\.(\d+(\.\d+)?)?\s*', '', title)
|
||
if new_title != title:
|
||
counts['secnum'] += 1
|
||
return '\\' + cmd_name + '{' + new_title + '}'
|
||
return m.group(0)
|
||
return strip_num
|
||
pattern = re.compile(r'\\' + cmd + r'\{([^}]+)\}')
|
||
content = pattern.sub(make_stripper(cmd), content)
|
||
|
||
with open(fpath, 'w', encoding='utf-8') as f:
|
||
f.write(content)
|
||
|
||
print(f'OK {fname}')
|
||
|
||
print(f'Done: labels={counts["labels"]} dashes={counts["dashes"]} rules={counts["rules"]} chapnum={counts["chapnum"]} secnum={counts["secnum"]} emdash_text={counts["emdashtext"]}')
|