#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
value-scan / value-dig 产物机械校验（Python 版，等价移植自 check.ps1，跨平台）
------------------------------------------------------------------
用法：
  # S1 候选清单
  python check.py scan <产物路径> --template <skills>/value-scan/assets/候选清单模板.md

  # S4 功能点清单
  python check.py dig <产物路径> --template <skills>/value-dig/assets/深度模板/功能点清单模板.md

  # S4 设计思路与取舍 / 改造方案（整篇级文档，只跑通用校验）
  python check.py doc <产物路径> --template <路径>

退出码：0 = 无 FAIL；1 = 有 FAIL；2 = 用法/IO 错误
说明：FAIL = 必错；WARN = 需人判断
"""
import argparse
import re
import sys
from pathlib import Path

FAIL, WARN, PASS = [], [], []

# ⟨ ⟩ 占位符（U+27E8 / U+27E9）
PH_L, PH_R = '\u27e8', '\u27e9'


def fail(m):
    FAIL.append(m)


def warn(m):
    WARN.append(m)


def pass_(m):
    PASS.append(m)


def read_text(path_str):
    p = Path(path_str)
    if not p.is_file():
        print(f"[ERROR] 文件不存在: {path_str}", file=sys.stderr)
        sys.exit(2)
    text = p.read_text(encoding='utf-8-sig')  # 自动剥 BOM
    return text, text.splitlines()


def head_index(lines, pattern):
    for i, line in enumerate(lines):
        if re.search(pattern, line):
            return i
    return -1


def next_head_index(lines, start):
    for i in range(start + 1, len(lines)):
        if re.match(r'^\s*#+\s+\S', lines[i]):
            return i
    return len(lines)


def line_snip(line, width=40):
    """报错附带的行内容摘要（改进：报错不指内容曾导致误诊）"""
    s = line.strip().replace('|', '\\|')
    return s[:width] + ('…' if len(s) > width else '')


def main():
    ap = argparse.ArgumentParser(description='value-scan/value-dig 产物机械校验')
    ap.add_argument('mode', choices=['scan', 'dig', 'doc'])
    ap.add_argument('product', help='产物路径')
    ap.add_argument('--template', '-t', help='模板路径')
    ap.add_argument('-Mode', '-Product', '-Template', dest='legacy', help=argparse.SUPPRESS)
    args = ap.parse_args()

    prod_path = Path(args.product).resolve()
    text, lines = read_text(args.product)

    # ------------------------------------------------ 围栏代码块
    fences = []
    in_fence = False
    f_start, f_lang = 0, ''
    for i, line in enumerate(lines):
        if re.match(r'^\s*```', line):
            if not in_fence:
                in_fence, f_start = True, i
                f_lang = re.sub(r'^\s*```', '', line).strip()
            else:
                in_fence = False
                fences.append({'start': f_start, 'end': i, 'lang': f_lang,
                               'body': i - f_start - 1})
    if in_fence:
        fail(f'存在未闭合的代码围栏（起始行 {f_start + 1}）')

    # ------------------------------------------------ 通用 1：引号逐行配对
    odd_quote = [i + 1 for i, line in enumerate(lines)
                 if line.count('"') % 2 != 0]
    if not odd_quote:
        pass_('引号逐行配对')
    else:
        fail('引号未配对的行: ' + ', '.join(map(str, odd_quote)))

    # ------------------------------------------------ 通用 2：mermaid 合法性
    mermaid_fences = [f for f in fences if f['lang'] == 'mermaid']
    mm_bad = 0
    for f in mermaid_fences:
        body_lines = lines[f['start'] + 1:f['end']]
        body = '\n'.join(body_lines)
        first = next((l for l in body_lines if l.strip()), '')
        end_count = len(re.findall(r'(?m)^\s*end\s*$', body))
        if 'sequenceDiagram' in first:
            blk = len(re.findall(r'(?m)^\s*(alt|opt|loop|par|critical|break|rect)\b', body))
            if blk != end_count:
                fail(f"mermaid 时序图（第 {f['start'] + 1} 行起）alt/opt/loop 等 {blk} 个但 end={end_count}")
                mm_bad += 1
        else:
            sg = len(re.findall(r'(?m)^\s*subgraph\s', body))
            if sg != end_count:
                fail(f"mermaid 流程图（第 {f['start'] + 1} 行起）subgraph={sg} 但 end={end_count}")
                mm_bad += 1
            if (re.search(r'(?m)^\s*subgraph\s+\S+\s*\[', body)
                    and not re.search(r'(?m)^\s*subgraph\s+\S+\s*\["', body)):
                fail(f'mermaid（第 {f["start"] + 1} 行起）subgraph 缺引号标题，必须写 subgraph id["标题"]')
                mm_bad += 1
            if re.search(r'(?m)^\s*subgraph\s+\S+\s*\[\(', body):
                fail(f'mermaid（第 {f["start"] + 1} 行起）用了 subgraph xxx[(...)]，会解析失败')
                mm_bad += 1
    if mermaid_fences and mm_bad == 0:
        pass_(f'mermaid 块 {len(mermaid_fences)} 个通过')

    # ------------------------------------------------ 通用 3：表格列数一致（含行内容摘要）
    ti = 0
    while ti < len(lines):
        if re.match(r'^\s*\|', lines[ti]):
            bs = ti
            blk = []
            while ti < len(lines) and re.match(r'^\s*\|', lines[ti]):
                blk.append(lines[ti])
                ti += 1
            counts = sorted({b.count('|') for b in blk})
            if len(counts) > 1:
                fail(f"表格列数不一致（第 {bs + 1} 行起）：pipe 数 = {'/'.join(map(str, counts))}"
                     f"｜首行内容: {line_snip(blk[0])}")
        else:
            ti += 1

    # ------------------------------------------------ 通用 3b：表格不得缩进
    indented = [i + 1 for i, line in enumerate(lines) if re.match(r'^[ \t]+\|', line)]
    if not indented:
        pass_('表格均顶格（无嵌套缩进表）')
    else:
        fail('表格存在缩进（第 ' + ', '.join(map(str, indented)) + ' 行起）——嵌套在列表里的表多数渲染器不显示，必须顶格')

    # ------------------------------------------------ 通用 4：章节完整性
    if args.template:
        _, t_lines = read_text(args.template)
        t_heads = [l for l in t_lines if re.match(r'^\s*#+\s+\S', l)]
        missing_literal, missing_ph = [], []
        for h in t_heads:
            t = re.sub(r'\s+$', '', re.sub(r'^\s*#+\s+', '', h))
            has_ph = PH_L in t
            ph_rx = re.escape(PH_L) + '[^' + re.escape(PH_R) + ']*' + re.escape(PH_R)
            rx = re.escape(re.sub(ph_rx, '@@PH@@', t)).replace('@@PH@@', '.*')
            hit = any(re.match(r'^\s*#+\s+' + rx + r'\s*$', pl) for pl in lines)
            if not hit:
                (missing_ph if has_ph else missing_literal).append(t)
        if not missing_literal:
            pass_('章节完整性：模板必备节全部存在')
        else:
            fail('缺章节（字面量，必错）: ' + ' | '.join(missing_literal))
        if missing_ph:
            warn('示例性章节未匹配（可能条数不同，需人判）: ' + ' | '.join(missing_ph))

    # ------------------------------------------------ scan 专属
    if args.mode == 'scan':
        non_mermaid = [f for f in fences if f['lang'] != 'mermaid']
        if not non_mermaid:
            pass_('深度闸门：S1 无围栏代码块（仅 mermaid）')
        else:
            fail('S1 不允许围栏代码块，发现 {} 个（第 {} 行起）'.format(
                len(non_mermaid),
                ', '.join(str(f['start'] + 1) for f in non_mermaid)))

        bad_anchor, anchor_count = [], 0
        for line in lines:
            m = re.match(r'^\s*\*\*锚点\*\*\s*[：:]\s*(.+?)\s*$', line)
            if not m:
                continue
            anchor_count += 1
            items = [s for s in re.split(r'[、,，]', m.group(1)) if s.strip()]
            if len(items) > 2:
                bad_anchor.append(f'锚点超过 2 个（{len(items)} 个）: {line.strip()}')
            for it in items:
                a = it.strip().strip('`')
                if re.search(r':\d', a):
                    bad_anchor.append(f'S1 锚点不写行号 -> {a}')
                elif not re.search(r'\w[/\\]\w', a):
                    bad_anchor.append(f'S1 锚点须为 路径#方法名（机制级可到类名） -> {a}')
        if anchor_count == 0:
            warn('未找到 **锚点** 行（若产物为空则忽略）')
        elif not bad_anchor:
            pass_(f'锚点格式合规（{anchor_count} 处，路径#方法名）')
        else:
            fail('锚点格式不合规: ' + ' ; '.join(bad_anchor))

        if head_index(lines, r'^\s*#+\s*闸门状态') >= 0:
            pass_('有「闸门状态」节（S2 门控有证据）')
        else:
            fail('缺「闸门状态」节 —— S2 门控没有证据')

        star_count = sum(1 for l in lines if re.match(r'^\s*#+\s*★', l))
        if star_count <= 12:
            pass_(f'候选条数 {star_count}（≤12）')
        else:
            fail(f'候选条数 {star_count} 超过 12（颗粒度掉到实现层，需重并）')
        if 0 < star_count < 5:
            warn(f'候选条数 {star_count} 少于 5——先确认是否采样不到位，而非真没有')

    # ------------------------------------------------ dig 专属
    if args.mode == 'dig':
        skel_idx = head_index(lines, r'^\s*#+\s*主干调用骨架')
        skel_end = next_head_index(lines, skel_idx) if skel_idx >= 0 else -1
        if skel_idx >= 0:
            pass_('有「主干调用骨架」节')
        else:
            warn('未找到「主干调用骨架」节（仅 S4 ① 功能点清单必需）')

        exempt = 0
        for f in fences:
            if f['lang'] == 'mermaid':
                continue
            if skel_idx >= 0 and skel_idx < f['start'] < skel_end:
                exempt += 1
                continue
            if f['body'] > 10:
                warn(f"局部代码块超过 10 行（第 {f['start'] + 1} 行起，{f['body']} 行）"
                     f"——行数非硬限，请人判断是关键片段还是源码摘录")
        pass_(f'局部代码块行数检查完成（豁免骨架块 {exempt} 个）')

        if skel_idx >= 0:
            skel_fences = [f for f in fences if skel_idx < f['start'] < skel_end]
            if not skel_fences:
                warn('骨架节里没有代码块')
            else:
                sf = skel_fences[0]
                miss_tag = []
                for bl in lines[sf['start'] + 1:sf['end']]:
                    if not bl.strip():
                        continue
                    if re.match(r'^\s*//', bl):
                        continue
                    if re.search(r':\s*$', bl):
                        continue
                    if not re.search(r'[(\[]', bl):
                        continue
                    if '//' not in bl:
                        miss_tag.append(bl.strip())
                if not miss_tag:
                    pass_('骨架每行都带方式标记')
                else:
                    fail(f"骨架有 {len(miss_tag)} 行缺方式标记: "
                         + ' ; '.join(miss_tag[:3]))
        if not re.search(r'\.(java|xml|yaml|yml|sql):\d+', text):
            fail('未找到任何 `文件:行号` 证据（本阶段必须有可核对的锚点）')
        else:
            pass_('存在 `文件:行号` 形式的证据')

    # ------------------------------------------------ doc 专属
    if args.mode == 'doc':
        is_plan = head_index(lines, r'^\s*#+\s*0\.\s*现状问题登记') >= 0
        if is_plan:
            code_fences = [f for f in fences if f['lang'] != 'mermaid']
            if len(code_fences) >= 1:
                pass_(f'改造方案含关键片段 {len(code_fences)} 个')
            else:
                fail('改造方案缺「关键片段」代码块——必须"照着能讲代码"（伪代码/SQL 均可，只禁大段源码摘录）')
            if len(code_fences) >= 2:
                pass_(f"关键片段 {len(code_fences)} 个（骨架 + 改造点）")
            elif len(code_fences) == 1:
                warn('只有 1 个关键片段——可能只有链路骨架，各改造点未给伪代码，需人判')

    # ------------------------------------------------ 输出
    print()
    print('=' * 68)
    print(f'机械校验  Mode={args.mode}')
    print(f'  product  : {prod_path}')
    if args.template:
        print(f"  template : {Path(args.template).resolve()}")
    print('=' * 68)

    for tag, bucket, mark in (('[PASS]', PASS, '+ '), ('[WARN] 需人判断', WARN, '! '), ('[FAIL] 必错', FAIL, 'x ')):
        if bucket:
            print()
            print(tag)
            for m in bucket:
                print(f'  {mark}{m}')

    print()
    print(f'结果：PASS {len(PASS)} / WARN {len(WARN)} / FAIL {len(FAIL)}')
    sys.exit(1 if FAIL else 0)


if __name__ == '__main__':
    main()