Files
MechanicalNotes/重写规范/tools/verify_chapter.py
T

91 lines
3.7 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.
# -*- coding: utf-8 -*-
"""Verify a rewritten chapter folder (机械原理 在学练习 pattern).
Checks (per chapter folder passed as argv[1]):
1. required files exist and are non-empty: README.md, 01-知识点盘点.md,
01b-覆盖对照与接口.md, 10-速查卡.md, plus >=4 点 files 02-xx..09-xx
2. no line contains "$$" mixed with other content on the same line
(block math must have $$ alone on its own line; inline math uses single $)
3. every 点 file carries at least one 考点频率 marker (★★★/★★☆/★☆☆/⭐)
4. every 点 file carries a 出处 marker (出处:)
5. Obsidian double links [[ ]] appear in README / 01 / 10 and point files
6. 01 file links to 点 files and 10; 点 files mention [[01-知识点盘点]] or [[10-速查卡]]
7. no 旧版-snapshot folder got new files (skip; informational)
Usage: python verify_chapter.py <chapter_dir>
Exit code 0 = all pass; 1 = issues found (printed).
"""
import re
import sys
from pathlib import Path
REQ = ["README.md", "01-知识点盘点.md", "01b-覆盖对照与接口.md", "10-速查卡.md"]
FREQ = re.compile(r"(★★★|★★☆|★☆☆|⭐|必考|大题|选择|简答|了解|不考)")
SRC = re.compile(r"出处[::]")
def main():
ch = Path(sys.argv[1])
if not ch.is_dir():
print("NOT A DIR:", ch)
sys.exit(1)
issues = []
mds = sorted(ch.glob("*.md"))
names = {p.name for p in mds}
# 1. required files
for r in REQ:
if r not in names:
issues.append("缺少必需文件: " + r)
points = [p for p in mds if re.match(r"^0[2-9]-点\d+-", p.name)]
if len(points) < 4:
issues.append("点文件不足 4 个: %d" % len(points))
# per-file checks
for p in mds:
text = p.read_text(encoding="utf-8")
if len(text.strip()) == 0:
issues.append("空文件: " + p.name)
continue
# 2. $$ must stand alone on its line (strip inline-code spans first,
# so prose like "use `$$` as block math" is not flagged)
for ln, line in enumerate(text.splitlines(), 1):
line_nocode = re.sub(r"`[^`]*`", "", line)
if "$$" in line_nocode:
stripped = line_nocode.strip()
if stripped != "$$":
issues.append("%s:%d 同行块公式: %s" % (p.name, ln, stripped[:40]))
# 3/4. 点 files need frequency + source
if re.match(r"^0[2-9]-点\d+-", p.name):
if not FREQ.search(text):
issues.append("%s 缺考点频率标注" % p.name)
if not SRC.search(text):
issues.append("%s 缺出处标注" % p.name)
if "【图:" not in text and "图" not in text[:2000]:
pass # 配图占位非强制每点
# 5/6. links
if p.name in ("README.md", "01-知识点盘点.md", "10-速查卡.md", "01b-覆盖对照与接口.md"):
if "[[" not in text:
issues.append("%s 无双链" % p.name)
# 01 must link to each 点 file basename
if "01-知识点盘点.md" in names:
t01 = (ch / "01-知识点盘点.md").read_text(encoding="utf-8")
for pt in points:
if pt.stem not in t01:
issues.append("01 未链接点文件: " + pt.name)
# README must list 点 files
if "README.md" in names:
tr = (ch / "README.md").read_text(encoding="utf-8")
for pt in points:
if pt.stem not in tr:
issues.append("README 未列出点文件: " + pt.name)
if issues:
print("ISSUES (%d):" % len(issues))
for i in issues:
print(" -", i)
sys.exit(1)
print("OK: %s | %d md files, %d 点 files" % (ch.name, len(mds), len(points)))
sys.exit(0)
if __name__ == "__main__":
main()