"""Offline static HTML quality gate, bounded CPU for multi-thousand-page sites.

No network requests. Use the standard-library streaming HTML parser and a
pre-indexed build manifest instead of repeatedly opening files for every link.
"""
from html.parser import HTMLParser
from pathlib import Path, PurePosixPath
import posixpath
from urllib.parse import urlsplit,unquote
from . import db


class _Scanner(HTMLParser):
    def __init__(self):
        super().__init__(convert_charrefs=True)
        self.title_parts=[];self.in_title=False;self.h1=0;self.description=''
        self.targets=[];self.missing_alt=[];self.base_root=False

    def handle_starttag(self,tag,attrs):
        attrs=dict(attrs)
        if tag=='title':self.in_title=True
        elif tag=='h1':self.h1+=1
        elif tag=='base' and attrs.get('href')=='/':self.base_root=True
        elif tag=='meta' and str(attrs.get('name','')).lower()=='description':
            self.description=(attrs.get('content') or '').strip()
        elif tag=='img' and not attrs.get('alt'):
            self.missing_alt.append((attrs.get('src') or '')[:180])
        if tag in ('a','img','script','link'):
            if tag=='link':
                rel=(attrs.get('rel') or '').lower().split()
                if 'canonical' in rel or 'alternate' in rel:return
            target=attrs.get('href' if tag in ('a','link') else 'src')
            if target:self.targets.append(target)

    def handle_startendtag(self,tag,attrs):self.handle_starttag(tag,attrs)
    def handle_endtag(self,tag):
        if tag=='title':self.in_title=False
    def handle_data(self,data):
        if self.in_title:self.title_parts.append(data)


def _local_path(target,rel,base_root,hostname):
    parsed=urlsplit(target)
    if parsed.scheme in ('http','https'):
        if parsed.hostname!=hostname:return None
        path=parsed.path
    elif parsed.scheme or target.startswith('//') or target.startswith('#'):
        return None
    else:path=parsed.path
    if not path:return None
    raw=unquote(path)
    if raw.startswith('/') or base_root:
        combined=raw.lstrip('/')
    else:
        combined=posixpath.join(posixpath.dirname(rel),raw)
    if combined=='':return 'index.html'
    normalized=posixpath.normpath(combined)
    if normalized in ('..','.') or normalized.startswith('../') or '\\' in normalized:
        return '!unsafe!'
    if path.endswith('/') or not PurePosixPath(normalized).suffix:
        normalized=normalized.rstrip('/')+'/index.html'
    return normalized


def report(site_id,build_id):
    root=(db.DATA/'builds'/site_id/build_id/'dist').resolve()
    if not root.is_dir():raise FileNotFoundError('构建版本不存在')
    # One manifest scan replaces hundreds of thousands of repeated stat calls.
    indexed={p.relative_to(root).as_posix() for p in root.rglob('*') if p.is_file()}
    html_files=sorted(x for x in indexed if x.endswith('.html'))
    site=db.one('SELECT domain FROM sites WHERE id=?',(site_id,)) or {}
    hostname=urlsplit(site.get('domain') or '').hostname
    issues=[];seen_titles={};seen_descriptions={}
    for rel in html_files:
        scanner=_Scanner()
        scanner.feed((root/rel).read_text(encoding='utf-8',errors='replace'))
        scanner.close()
        title=' '.join(''.join(scanner.title_parts).split())
        if not title:issues.append({'file':rel,'type':'missing_title','severity':'error'})
        if scanner.h1!=1:issues.append({'file':rel,'type':'h1_count','severity':'warning','count':scanner.h1})
        if title and title in seen_titles and Path(rel).name!='404.html':
            issues.append({'file':rel,'type':'duplicate_title','severity':'warning','other':seen_titles[title]})
        if title:seen_titles[title]=rel
        if not scanner.description:issues.append({'file':rel,'type':'missing_description','severity':'warning'})
        if scanner.description and scanner.description in seen_descriptions:
            issues.append({'file':rel,'type':'duplicate_description','severity':'warning','other':seen_descriptions[scanner.description]})
        if scanner.description:seen_descriptions[scanner.description]=rel
        for img in scanner.missing_alt:
            issues.append({'file':rel,'type':'missing_image_alt','severity':'warning','src':img})
        for target in scanner.targets:
            candidate=_local_path(target,rel,scanner.base_root,hostname)
            if candidate is not None and candidate not in indexed:
                issues.append({'file':rel,'type':'broken_internal_reference','severity':'error','target':target[:220]})
    return {'files':len(html_files),'errors':sum(x['severity']=='error' for x in issues),
            'warnings':sum(x['severity']=='warning' for x in issues),
            'passed':not any(x['severity']=='error' for x in issues),'issues':issues[:500]}