first commit

articles.py

@@ -0,0 +1,116 @@
+"""Local article validation and portable packages. Never changes downloaded files."""
+import hashlib
+import json
+from pathlib import Path
+import re
+import unicodedata
+from urllib.parse import unquote
+
+from modules.package import make_package
+
+MAX_PACKAGE_BYTES = 48 * 1024 * 1024
+FOOTER = re.compile(r'(?:^|\n)来源：([^\n]+)，如有侵权，请联系删除。\s*$')
+
+
+def validate_images(body, directory):
+    """Conservative inline-image preflight; the importer remains the final parser."""
+    if re.search(r'!\[[^\]]*\]\s*\[', body):
+        raise ValueError('不支持引用式图片，请改成内联图片路径')
+    for start in re.finditer(r'!\[[^\]]*\]\(', body):
+        pos, depth, quote, angle = start.end(), 1, '', False
+        begin = pos
+        while pos < len(body):
+            ch = body[pos]
+            if ch == '\\':
+                pos += 2
+                continue
+            if quote:
+                if ch == quote:
+                    quote = ''
+            elif not angle and depth == 1 and body[pos - 1].isspace() and ch in ('"', "'"):
+                quote = ch
+            elif ch == '<':
+                angle = True
+            elif ch == '>':
+                angle = False
+            elif not angle and ch == '(':
+                depth += 1
+            elif not angle and ch == ')':
+                depth -= 1
+                if not depth:
+                    break
+            pos += 1
+        if depth:
+            raise ValueError('图片引用括号不完整')
+        target = body[begin:pos].strip()
+        target = target[1:target.index('>')] if target.startswith('<') and '>' in target else re.sub(r'\s+["\'][\s\S]*["\']\s*$', '', target)
+        target = unquote(re.sub(r'\\([()\\ ])', r'\1', target))
+        if re.match(r'^(?:[a-zA-Z][\w+.-]*:|/|\\)', target):
+            raise ValueError('图片必须使用目录内相对路径：' + target)
+        image = (directory / target).resolve()
+        if not image.is_relative_to(directory) or not image.is_file():
+            raise ValueError('缺图或图片路径超出目录：' + target)
+        if image.suffix.lower() not in ('.jpg', '.jpeg', '.png', '.gif'):
+            raise ValueError('不支持的配图格式：' + target)
+        if not 0 < image.stat().st_size < 20 * 1024 * 1024:
+            raise ValueError('配图为空或达到 20 MiB：' + target)
+
+
+def short_title(title, budget=80):
+    # Conservative UTF-16 budget: do not split astral characters / surrogate pairs.
+    if len(title.encode('utf-16-le')) // 2 <= budget:
+        return title
+    out = ''
+    for ch in title:
+        if len((out + ch).encode('utf-16-le')) // 2 > budget - 3:
+            break
+        out += ch
+    return out + '...'
+
+
+def inspect_article(directory):
+    directory = Path(directory).resolve(strict=True)
+    candidates = sorted(directory.glob('*.md'))
+    if len(candidates) != 1:
+        raise ValueError('每个文章目录必须恰好包含一个 Markdown 文件')
+    md = candidates[0]
+    if not md.resolve().is_relative_to(directory):
+        raise ValueError('Markdown 不得链接到目录外')
+    raw = md.read_text(encoding='utf-8-sig')
+    heading = re.match(r'^\s*#\s+([^\n]+)\n?', raw)
+    title = (heading[1] if heading else md.stem).strip()
+    body = raw[heading.end():].strip() if heading else raw.strip()
+    footer = FOOTER.search(body)
+    if not footer:
+        raise ValueError('文末缺少标准来源尾注，请补充来源后再扫描')
+    source = footer[1].strip()
+    body = body[:footer.start()].strip()
+    if not title or not body:
+        raise ValueError('标题或正文为空')
+    validate_images(body, directory)
+    for file in directory.rglob('*'):
+        if file.suffix.lower() in ('.webp', '.avif', '.svg'):
+            raise ValueError('发现暂不支持的图片格式：' + file.name + '；请另存为 JPG/PNG/GIF 并更新引用')
+    pack = make_package(directory)
+    if sum(len(i['base64']) for i in pack['images']) > MAX_PACKAGE_BYTES:
+        raise ValueError('文章包超过 48 MiB，请减少单篇图片体积')
+    pack['title'] = short_title(title)
+    # Preserve body and exact final footer for the formatter; the original file stays intact.
+    pack['markdown'] = '# ' + pack['title'] + '\n\n' + body + '\n\n来源：' + source + '，如有侵权，请联系删除。\n'
+    content = unicodedata.normalize('NFC', body)
+    # Hash file contents, not directory/title; renamed copies share their article identity.
+    image_hashes = []
+    for item in pack['images']:
+        import base64
+        digest = hashlib.sha256(base64.b64decode(item['base64'])).hexdigest()
+        content = content.replace(item['path'], 'image:' + digest)
+        image_hashes.append(digest)
+    identity = hashlib.sha256((content + '\n' + '\n'.join(sorted(set(image_hashes)))).encode()).hexdigest()
+    metadata = {}
+    marker = directory / '.article.json'
+    if marker.is_file():
+        metadata = json.loads(marker.read_text())
+    return dict(article_key=identity, markdown_sha256=hashlib.sha256(md.read_bytes()).hexdigest(),
+                directory=str(directory), original_title=title, title=pack['title'], source=source,
+                image_count=len(pack['images']), package=pack,
+                source_keys=metadata.get('fingerprints', []))