Files
MathNotesVersion2/.workbuddy/tools/md2pdf/prep_exam.py
T
Yimu 2719009408 feat(模拟卷三): 出做题版与题目解析合订版 PDF
- 新增 prep_exam.py:清洗试卷(去考点行、去 △ 预测标记、相对链接降级为文字、切掉收尾段),做题版不泄题
- md2pdf.js 增 exam 模式:客观题连排不留白,解答题每题独占一页、留白框 flex 撑满纸面;部分标题与首题同页
- 做题版 10 页 545KB,合订版 16 页 638KB
- README 补 PDF 两行与版本记录
2026-10-31 17:23:39 +08:00

99 lines
3.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""prep_exam.py —— 模拟卷 Markdown 预处理,产出可直接打印的干净稿
把「第三次模拟-数学一」这类目录下的
01-模拟卷.md / 02a-答案与解析-客观题.md / 02b-答案与解析-解答题.md
清洗成两份:
paper.md —— 只留试卷(去掉每题末尾的考点行与 △ 预测标记,否则等于泄题)
full.md —— 试卷 + 两册解析,供对答案时通读
用法:
python prep_exam.py <模拟卷目录> [--outdir <输出目录>]
默认输出到 <仓库>/.workbuddy/tools/md2pdf/build/<目录名>/
"""
import os
import re
import sys
import io
FM_RE = re.compile(r'^---\r?\n[\s\S]*?\r?\n---\r?\n?')
KP_RE = re.compile(r'^>\s*\*\*考点\*\*\s*·') # 每题末尾的考点跳转行
TRI_NOTE_RE = re.compile(r'带\s*\*\*△\*\*\s*的是[^\n]*') # △ 图例说明
LINK_RE = re.compile(r'(?<!\!)\[([^\]]*)\]\((?!https?:)[^)]*\)')
def strip_frontmatter(md):
m = FM_RE.match(md)
return md[m.end():] if m else md
def clean(md, drop_kp=True, drop_tri=True, drop_tail=False):
"""drop_kp: 去掉考点行(做题版必须去掉);drop_tri: 去掉 △ 预测标记;drop_tail: 去掉「交卷后」收尾段"""
md = strip_frontmatter(md)
lines = [ln for ln in md.split('\n')
if not (drop_kp and KP_RE.match(ln.strip()))]
md = '\n'.join(lines)
if drop_tri:
md = TRI_NOTE_RE.sub('', md)
md = md.replace('△ ', '').replace('△', '')
if drop_tail:
md = re.split(r'^##\s*交卷后\s*$', md, flags=re.M)[0]
md = re.sub(r'\n*-{3,}\s*$', '', md.rstrip()) + '\n'
md = LINK_RE.sub(r'\1', md) # 相对链接降级成纯文字,PDF 里点不动
md = re.sub(r'[ \t]+\n', '\n', md) # 行尾空白
md = re.sub(r'\n{3,}', '\n\n', md) # 压掉连续空行
return md.strip() + '\n'
def build(volume_dir, outdir=None):
volume_dir = os.path.abspath(volume_dir)
name = os.path.basename(volume_dir.rstrip('/\\'))
repo = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..', '..'))
outdir = outdir or os.path.join(repo, '.workbuddy', 'tools', 'md2pdf', 'build', name)
os.makedirs(outdir, exist_ok=True)
def read(fn):
p = os.path.join(volume_dir, fn)
if not os.path.exists(p):
return None
return io.open(p, encoding='utf-8').read()
paper = read('01-模拟卷.md')
if paper is None:
raise SystemExit('找不到 01-模拟卷.md:%s' % volume_dir)
paper_clean = clean(paper, drop_tail=True)
p_paper = os.path.join(outdir, 'paper.md')
io.open(p_paper, 'w', encoding='utf-8').write(paper_clean)
parts = [paper_clean]
for fn, head in (('02a-答案与解析-客观题.md', '答案与解析 · 客观题'),
('02b-答案与解析-解答题.md', '答案与解析 · 解答题')):
raw = read(fn)
if raw is None:
continue
parts.append('<div style="break-before: page"></div>\n')
parts.append(clean(raw, drop_kp=False, drop_tri=False))
p_full = os.path.join(outdir, 'full.md')
io.open(p_full, 'w', encoding='utf-8').write('\n'.join(parts))
print('OK %s' % p_paper)
print('OK %s' % p_full)
return p_paper, p_full
if __name__ == '__main__':
if len(sys.argv) < 2:
print(__doc__)
sys.exit(1)
args = sys.argv[1:]
outdir = None
if '--outdir' in args:
i = args.index('--outdir')
outdir = args[i + 1]
del args[i:i + 2]
build(args[0], outdir)