"""Per-paper completion report.

Usage: python status_report.py <plan.json> <base_dir>
"""
import json
import os
import re
import sys

plan = json.load(open(sys.argv[1], encoding='utf-8'))
base = sys.argv[2]
SECS = ['一、', '二、', '三、', '四、', '五、', '六、']

rows = []
incomplete = []
for p in plan:
    pdf = os.path.join(base, p['pdf_path'])
    md = os.path.join(base, p['md_path'])
    pdf_ok = os.path.exists(pdf) and open(pdf, 'rb').read(4) == b'%PDF' and os.path.getsize(pdf) > 20000
    md_ok = os.path.exists(md)
    cjk = 0
    miss = []
    link_ok = False
    if md_ok:
        t = open(md, encoding='utf-8').read()
        cjk = len(re.findall(r'[\u4e00-\u9fff]', t))
        for s in SECS:
            if '## ' + s not in t:
                miss.append(s[0])
        m = re.search(r'\]\(\./([^)]+\.pdf)\)', t)
        if m:
            link_ok = os.path.exists(os.path.join(os.path.dirname(md), m.group(1)))
    if md_ok and not miss and link_ok and pdf_ok:
        pass
    else:
        incomplete.append((p['id'], p['stem'], pdf_ok, md_ok, miss, link_ok))
    rows.append((p['dir'], p['stem'], pdf_ok, md_ok, cjk, ''.join(miss) or '-', link_ok))

print('%-16s %-46s %-6s %-6s %-7s %-8s %s' % ('类别', '文件前缀', 'PDF', 'MD', '汉字', '缺章节', 'PDF链接'))
print('-' * 120)
for d, stem, po, mo, cjk, miss, lo in rows:
    print('%-16s %-46s %-6s %-6s %-7d %-8s %s' % (
        d, stem, 'OK' if po else 'MISSING', 'OK' if mo else 'MISSING',
        cjk, miss, 'OK' if lo else 'BROKEN'))
print('-' * 120)
print('总计 %d 篇；未完成 %d 篇' % (len(rows), len(incomplete)))
for i in incomplete:
    print('  ! 未完成:', i)