@birthday8/doc-mcp 1.0.1 → 1.0.2

package/python/html_fixer.py

@@ -0,0 +1,125 @@
+# -*- coding: utf-8 -*-
+"""HTML自动修复器 - 修正常见的格式错误"""
+
+import re
+
+
+class HTMLFixer:
+    """HTML格式自动修复类"""
+
+    # 颜色名称到十六进制的映射
+    COLOR_MAP = {
+        "red": "#FF0000",
+        "blue": "#0000FF",
+        "green": "#008000",
+        "yellow": "#FFFF00",
+        "orange": "#FFA500",
+        "purple": "#800080",
+        "pink": "#FFC0CB",
+        "brown": "#A52A2A",
+        "black": "#000000",
+        "white": "#FFFFFF",
+        "gray": "#808080",
+        "grey": "#808080",
+        "lightblue": "#ADD8E6",
+        "lightgreen": "#90EE90",
+        "lightyellow": "#FFFFE0",
+        "lightgray": "#D3D3D3",
+        "darkred": "#8B0000",
+        "darkblue": "#00008B",
+        "darkgreen": "#006400",
+    }
+
+    def __init__(self):
+        self.fixes = []
+
+    def fix(self, html_content):
+        """修复HTML内容"""
+        self.fixes = []
+        result = html_content
+
+        # 1. 修复颜色格式
+        result = self._fix_colors(result)
+
+        # 2. 修复自闭合标签
+        result = self._fix_self_closing(result)
+
+        # 3. 修复常见不支持属性
+        result = self._fix_unsupported_attrs(result)
+
+        # 4. 修复RGB颜色格式
+        result = self._fix_rgb_colors(result)
+
+        return result
+
+    def _fix_colors(self, html):
+        """修复颜色名称为十六进制"""
+        for color_name, hex_value in self.COLOR_MAP.items():
+            # 修复 style="color: red;"
+            pattern = rf"color:\s*{color_name}\b"
+            replacement = f"color: {hex_value}"
+            new_html, count = re.subn(pattern, replacement, html, flags=re.IGNORECASE)
+            if count > 0:
+                self.fixes.append(f"修复颜色: {color_name} → {hex_value} ({count}次)")
+                html = new_html
+
+            # 修复 background-color: red;
+            pattern = rf"background(?:-color)?:\s*{color_name}\b"
+            replacement = f"background-color: {hex_value}"
+            new_html, count = re.subn(pattern, replacement, html, flags=re.IGNORECASE)
+            if count > 0:
+                self.fixes.append(f"修复背景色: {color_name} → {hex_value} ({count}次)")
+                html = new_html
+
+        return html
+
+    def _fix_self_closing(self, html):
+        """修复自闭合标签"""
+        # 修复 <img> → <img />
+        self_closing_tags = ["img", "br", "hr"]
+
+        for tag in self_closing_tags:
+            # 匹配 <tag ...> (不包含 />)
+            pattern = rf"<{tag}([^/>]*?)>"
+            replacement = rf"<{tag}\1 />"
+            new_html, count = re.subn(pattern, replacement, html)
+            if count > 0:
+                self.fixes.append(f"修复自闭合标签: <{tag}> → <{tag} /> ({count}次)")
+                html = new_html
+
+        return html
+
+    def _fix_unsupported_attrs(self, html):
+        """移除不支持的属性"""
+        unsupported_attrs = ["onclick", "onload", "onerror", "loading", "crossorigin"]
+
+        for attr in unsupported_attrs:
+            pattern = rf'\s*{attr}=["\'][^"\']*["\']'
+            new_html, count = re.subn(pattern, "", html, flags=re.IGNORECASE)
+            if count > 0:
+                self.fixes.append(f"移除不支持属性: {attr} ({count}次)")
+                html = new_html
+
+        return html
+
+    def _fix_rgb_colors(self, html):
+        """修复RGB颜色格式为十六进制"""
+        # 修复 rgb(r, g, b) → #RRGGBB
+        pattern = r"rgb\(\s*(\d{1,3})\s*,\s*(\d{1,3})\s*,\s*(\d{1,3})\s*\)"
+
+        def rgb_to_hex(match):
+            r, g, b = map(int, match.groups())
+            return f"#{r:02X}{g:02X}{b:02X}"
+
+        new_html, count = re.subn(pattern, rgb_to_hex, html, flags=re.IGNORECASE)
+        if count > 0:
+            self.fixes.append(f"修复RGB颜色: rgb() → #RRGGBB ({count}次)")
+            html = new_html
+
+        return html
+
+    def get_fixes_report(self):
+        """获取修复报告"""
+        if not self.fixes:
+            return "✓ 无需修复"
+        return "\n".join([f"  • {fix}" for fix in self.fixes])

package/python/html_validator.py

@@ -0,0 +1,389 @@
+"""
+HTML格式验证器
+用于验证HTML是否符合转换规范
+"""
+
+import re
+from bs4 import BeautifulSoup
+from typing import Dict, List, Tuple
+
+
+class HTMLValidator:
+    """HTML格式验证器"""
+
+    def __init__(self):
+        # 支持的标签
+        self.supported_tags = {
+            "h1",
+            "h2",
+            "h3",
+            "h4",
+            "h5",
+            "h6",
+            "p",
+            "strong",
+            "em",
+            "u",
+            "s",
+            "sup",
+            "sub",
+            "code",
+            "span",
+            "div",
+            "ul",
+            "ol",
+            "li",
+            "table",
+            "tr",
+            "td",
+            "th",
+            "img",
+            "br",
+            "hr",
+            "math",
+            "latex",
+        }
+
+        # 支持的class
+        self.supported_classes = {
+            "center",
+            "right",
+            "dialogue",
+            "quote",
+            "highlight",
+            "red",
+            "blue",
+            "green",
+            "purple",
+            "info",
+            "warning",
+            "success",
+            "chapter",
+            "ending",
+            "page-break",
+            "columns",
+        }
+
+        # 支持的style属性
+        self.supported_styles = {
+            "color",
+            "background-color",
+            "font-family",
+            "font-size",
+            "font-weight",
+            "font-style",
+            "text-decoration",
+            "text-align",
+            "line-height",
+            "margin-top",
+            "margin-bottom",
+            "margin-left",
+            "margin-right",
+            "padding-top",
+            "padding-bottom",
+            "padding-left",
+            "padding-right",
+        }
+
+        # 支持的属性
+        self.supported_attrs = {
+            "src",
+            "alt",
+            "width",
+            "height",
+            "align",
+            "data-indent",
+            "data-cols",
+            "colspan",
+            "rowspan",
+        }
+
+    def validate(self, html_content: str) -> Dict:
+        """
+        验证HTML内容
+
+        Returns:
+            Dict: {
+                'valid': bool,
+                'errors': List[str],
+                'warnings': List[str],
+                'stats': Dict
+            }
+        """
+        result = {"valid": True, "errors": [], "warnings": [], "stats": {}}
+
+        try:
+            soup = BeautifulSoup(html_content, "html.parser")
+
+            # 检查基本结构
+            self._validate_structure(soup, result)
+
+            # 检查标签
+            self._validate_tags(soup, result)
+
+            # 检查属性
+            self._validate_attributes(soup, result)
+
+            # 检查样式
+            self._validate_styles(soup, result)
+
+            # 检查嵌套
+            self._validate_nesting(soup, result)
+
+            # 统计信息
+            self._collect_stats(soup, result)
+
+        except Exception as e:
+            result["valid"] = False
+            result["errors"].append(f"解析错误: {str(e)}")
+
+        return result
+
+    def _validate_structure(self, soup: BeautifulSoup, result: Dict):
+        """验证HTML基本结构"""
+        html_tag = soup.find("html")
+        if not html_tag:
+            result["errors"].append("缺少 <html> 标签")
+            result["valid"] = False
+
+        head_tag = soup.find("head")
+        if not head_tag:
+            result["warnings"].append("缺少 <head> 标签")
+
+        body_tag = soup.find("body")
+        if not body_tag:
+            result["errors"].append("缺少 <body> 标签")
+            result["valid"] = False
+
+        # 检查编码
+        charset = soup.find("meta", {"charset": True})
+        if not charset or charset.get("charset") != "UTF-8":
+            result["warnings"].append("建议使用 UTF-8 编码")
+
+        # 检查语言
+        if html_tag and html_tag.get("lang") != "zh-CN":
+            result["warnings"].append("建议设置 lang='zh-CN'")
+
+    def _validate_tags(self, soup: BeautifulSoup, result: Dict):
+        """验证标签"""
+        all_tags = set(tag.name for tag in soup.find_all(True))
+        unsupported = all_tags - self.supported_tags
+
+        if unsupported:
+            result["errors"].append(f"不支持的标签: {', '.join(unsupported)}")
+            result["valid"] = False
+
+        # 检查自闭合标签
+        self_closing = ["img", "br", "hr"]
+        for tag_name in self_closing:
+            for tag in soup.find_all(tag_name):
+                if str(tag).startswith(f"<{tag_name}>") and not str(tag).endswith("/>"):
+                    result["warnings"].append(f"标签 <{tag_name}> 建议自闭合")
+
+    def _validate_attributes(self, soup: BeautifulSoup, result: Dict):
+        """验证属性"""
+        for tag in soup.find_all(True):
+            for attr in tag.attrs:
+                if attr in ["class", "style"]:
+                    continue
+
+                if attr not in self.supported_attrs:
+                    result["warnings"].append(
+                        f"标签 <{tag.name}> 包含不支持的属性: {attr}"
+                    )
+
+    def _validate_styles(self, soup: BeautifulSoup, result: Dict):
+        """验证样式"""
+        for tag in soup.find_all(style=True):
+            style_str = tag.get("style", "")
+            styles = self._parse_style(style_str)
+
+            for style_name in styles:
+                if style_name not in self.supported_styles:
+                    result["warnings"].append(f"不支持的样式: {style_name}")
+
+                # 验证颜色格式
+                if style_name in ["color", "background-color"]:
+                    color = styles[style_name]
+                    if color and not color.startswith("#"):
+                        result["warnings"].append(f"颜色格式建议使用十六进制: {color}")
+                    elif color and len(color) != 7:
+                        result["errors"].append(f"颜色格式错误: {color}")
+                        result["valid"] = False
+
+    def _validate_nesting(self, soup: BeautifulSoup, result: Dict):
+        """验证嵌套"""
+        # 检查段落嵌套
+        for p in soup.find_all("p"):
+            children = p.find_all(["p", "h1", "h2", "h3", "h4", "h5", "h6", "div"])
+            if children:
+                result["errors"].append(f"<p> 标签不能包含块级元素")
+                result["valid"] = False
+
+        # 检查表格嵌套
+        for table in soup.find_all("table"):
+            direct_content = [
+                c.name for c in table.children if c.name and c.name not in ["tr"]
+            ]
+            if direct_content:
+                result["errors"].append(f"<table> 只能包含 <tr> 标签")
+                result["valid"] = False
+
+        # 检查列表嵌套
+        for li in soup.find_all("li"):
+            direct_lists = li.find_all(["ul", "ol"], recursive=False)
+            if len(direct_lists) > 1:
+                result["warnings"].append(f"<li> 建议只包含一个列表")
+
+    def _collect_stats(self, soup: BeautifulSoup, result: Dict):
+        """收集统计信息"""
+        stats = {}
+
+        # 标签统计
+        for tag in self.supported_tags:
+            count = len(soup.find_all(tag))
+            if count > 0:
+                stats[tag] = count
+
+        # 特殊统计
+        stats["total_tags"] = len(soup.find_all(True))
+        stats["text_length"] = len(soup.get_text())
+
+        result["stats"] = stats
+
+    def _parse_style(self, style_str: str) -> Dict:
+        """解析样式字符串"""
+        styles = {}
+        for item in style_str.split(";"):
+            if ":" in item:
+                key, value = item.split(":", 1)
+                styles[key.strip()] = value.strip()
+        return styles
+
+    def get_validation_report(self, result: Dict) -> str:
+        """生成验证报告"""
+        report = []
+
+        report.append("=== HTML 验证报告 ===\n")
+
+        # 验证结果
+        status = "✅ 通过" if result["valid"] else "❌ 失败"
+        report.append(f"验证状态: {status}\n")
+
+        # 统计信息
+        if result["stats"]:
+            report.append("📊 统计信息:")
+            for key, value in result["stats"].items():
+                report.append(f"  - {key}: {value}")
+            report.append("")
+
+        # 错误
+        if result["errors"]:
+            report.append("❌ 错误:")
+            for error in result["errors"]:
+                report.append(f"  - {error}")
+            report.append("")
+
+        # 警告
+        if result["warnings"]:
+            report.append("⚠️  警告:")
+            for warning in result["warnings"]:
+                report.append(f"  - {warning}")
+            report.append("")
+
+        if not result["errors"] and not result["warnings"]:
+            report.append("🎉 完美！没有发现任何问题。")
+
+        return "\n".join(report)
+
+
+class HTMLTemplateGenerator:
+    """HTML模板生成器"""
+
+    def __init__(self):
+        self.base_template = """<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>{title}</title>
+    <style>
+        body {{
+            font-family: '微软雅黑';
+            font-size: 12pt;
+            line-height: 1.8;
+            padding: 20px;
+            max-width: 800px;
+            margin: 0 auto;
+        }}
+        h1 {{ font-family: '微软雅黑'; font-size: 18pt; text-align: center; color: #333; }}
+        h2 {{ font-family: '微软雅黑'; font-size: 16pt; color: #4a3f6b; border-bottom: 2px solid #667eea; padding-bottom: 10px; }}
+        h3 {{ font-family: '微软雅黑'; font-size: 14pt; color: #5b4e8c; }}
+        p {{ margin: 6pt 0; }}
+        .center {{ text-align: center; }}
+        .right {{ text-align: right; }}
+        .highlight {{ background-color: #FFFF00; }}
+        .red {{ color: #FF0000; }}
+        .blue {{ color: #0000FF; }}
+        .green {{ color: #008000; }}
+        .purple {{ color: #800080; }}
+    </style>
+</head>
+<body>
+{content}
+</body>
+</html>"""
+
+    def generate_template(self, title: str = "文档", content: str = "") -> str:
+        """生成HTML模板"""
+        return self.base_template.format(title=title, content=content)
+
+    def get_element_examples(self) -> Dict:
+        """获取元素示例"""
+        return {
+            "headings": {
+                "h1": "<h1>一级标题</h1>",
+                "h2": "<h2>二级标题</h2>",
+                "h3": "<h3>三级标题</h3>",
+            },
+            "text": {
+                "bold": "<strong>加粗文本</strong>",
+                "italic": "<em>斜体文本</em>",
+                "underline": "<u>下划线文本</u>",
+                "strikethrough": "<s>删除线文本</s>",
+                "superscript": "X<sup>2</sup>",
+                "subscript": "H<sub>2</sub>O",
+            },
+            "colors": {
+                "red": '<span style="color: #FF0000;">红色文本</span>',
+                "blue": '<span style="color: #0000FF;">蓝色文本</span>',
+                "highlight": '<span class="highlight">高亮文本</span>',
+            },
+            "lists": {
+                "unordered": """<ul>
+    <li>列表项1</li>
+    <li>列表项2</li>
+</ul>""",
+                "ordered": """<ol>
+    <li>有序项1</li>
+    <li>有序项2</li>
+</ol>""",
+            },
+            "table": """<table>
+    <tr>
+        <th style="background-color: #E3F2FD;">表头1</th>
+        <th style="background-color: #E3F2FD;">表头2</th>
+    </tr>
+    <tr>
+        <td>单元格1</td>
+        <td>单元格2</td>
+    </tr>
+</table>""",
+            "image": '<img src="image.png" alt="图片描述" />',
+            "formula": "<math>E = mc^2</math>",
+        }
+
+
+# 全局实例
+validator = HTMLValidator()
+template_generator = HTMLTemplateGenerator()