@birthday8/doc-mcp 1.0.1 → 1.0.3

package/python/sample/html_schema.py

@@ -0,0 +1,283 @@
+# -*- coding: utf-8 -*-
+"""HTML格式约束Schema - 基于实际代码支持"""
+
+HTML_SCHEMA = {
+    "version": "2.0",
+    "description": "HTML转Word文档的结构化格式约束（基于实际代码支持）",
+    
+    "globalStyle": {
+        "body": {
+            "font-family": {
+                "type": "string",
+                "description": "全局默认字体",
+                "default": "微软雅黑",
+                "note": "支持任意中英文字体名称，如：微软雅黑、宋体、黑体、Arial、Times New Roman等"
+            },
+            "font-size": {
+                "type": "string",
+                "description": "全局默认字号",
+                "default": "12pt",
+                "pattern": "\\d+pt",
+                "note": "单位必须是pt，支持任意正整数"
+            },
+            "color": {
+                "type": "string",
+                "description": "文本颜色",
+                "default": "#333333",
+                "pattern": "#[0-9A-Fa-f]{6}",
+                "note": "必须使用6位十六进制格式"
+            }
+        }
+    },
+    
+    "allowedTags": [
+        "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"
+    ],
+    
+    "allowedStyles": {
+        "color": {
+            "type": "color",
+            "pattern": "#[0-9A-Fa-f]{6}",
+            "description": "文本颜色，必须使用十六进制格式",
+            "note": "例如：#FF0000（红色）、#0000FF（蓝色）、#00FF00（绿色）"
+        },
+        "background-color": {
+            "type": "color",
+            "pattern": "#[0-9A-Fa-f]{6}",
+            "description": "背景颜色，必须使用十六进制格式",
+            "note": "例如：#E3F2FD（浅蓝）、#D4EDDA（浅绿）"
+        },
+        "font-family": {
+            "type": "string",
+            "description": "字体名称（支持任意字体）",
+            "note": "可以使用系统中已安装的任何字体，如：微软雅黑、宋体、黑体、楷体、Arial、Times New Roman、Consolas等"
+        },
+        "font-size": {
+            "type": "string",
+            "pattern": "\\d+pt",
+            "description": "字号（单位必须是pt）",
+            "note": "支持任意正整数，如：12pt、14pt、16pt、18pt、20pt等"
+        },
+        "text-align": {
+            "type": "string",
+            "allowed": ["left", "center", "right", "justify"],
+            "description": "文本对齐方式",
+            "note": "left（左对齐）、center（居中）、right（右对齐）、justify（两端对齐）"
+        },
+        "line-height": {
+            "type": "string",
+            "pattern": "\\d+(\\.\\d+)?",
+            "description": "行距（数字或小数）",
+            "note": "如：1.5、1.8、2.0等"
+        },
+        "margin-top": {
+            "type": "string",
+            "pattern": "\\d+pt",
+            "description": "上边距（单位必须是pt）",
+            "note": "如：10pt、12pt、15pt等"
+        },
+        "margin-bottom": {
+            "type": "string",
+            "pattern": "\\d+pt",
+            "description": "下边距（单位必须是pt）",
+            "note": "如：10pt、12pt、15pt等"
+        }
+    },
+    
+    "allowedAttributes": {
+        "src": {
+            "tags": ["img"],
+            "required": True,
+            "description": "资源路径",
+            "note": "图片文件路径，可以是相对路径或绝对路径"
+        },
+        "alt": {
+            "tags": ["img"],
+            "description": "替代文本",
+            "note": "图片的描述文本，提高可访问性"
+        },
+        "width": {
+            "tags": ["img"],
+            "type": "number",
+            "description": "宽度（像素）",
+            "note": "如：384、512、768等"
+        },
+        "height": {
+            "tags": ["img"],
+            "type": "number",
+            "description": "高度（像素）",
+            "note": "如：288、384、512等"
+        },
+        "align": {
+            "tags": ["img"],
+            "allowed": ["left", "center", "right"],
+            "description": "对齐方式",
+            "note": "图片在段落中的对齐方式"
+        },
+        "data-indent": {
+            "tags": ["p"],
+            "type": "string",
+            "description": "首行缩进（em单位）",
+            "note": "如：0.5em、1em、2em等"
+        },
+        "data-cols": {
+            "tags": ["div"],
+            "type": "number",
+            "description": "栏数",
+            "note": "支持任意正整数，常用：1（单栏）、2（双栏）、3（三栏）、4（四栏）等。多栏结束后必须用 data-cols=\"1\" 恢复单栏"
+        },
+        "colspan": {
+            "tags": ["td", "th"],
+            "type": "number",
+            "description": "跨列数",
+            "note": "单元格跨越的列数"
+        },
+        "rowspan": {
+            "tags": ["td", "th"],
+            "type": "number",
+            "description": "跨行数",
+            "note": "单元格跨越的行数"
+        }
+    },
+    
+    "colorFormatRules": {
+        "required": "hex",
+        "pattern": "#[0-9A-Fa-f]{6}",
+        "examples": {
+            "correct": ["#FF0000", "#00FF00", "#0000FF", "#FFFFFF", "#000000", "#333333", "#666666", "#999999"],
+            "incorrect": ["red", "blue", "green", "yellow", "rgb(255,0,0)", "rgba(255,0,0,0.5)", "hsl(0,100%,50%)"]
+        }
+    },
+    
+    "selfClosingTags": ["img", "br", "hr"],
+    
+    "nestingRules": {
+        "forbidden": [
+            {
+                "parent": "p", 
+                "children": ["p", "h1", "h2", "h3", "h4", "h5", "h6", "div", "table", "ul", "ol"], 
+                "reason": "段落不能包含块级元素（p只能包含行内元素）",
+                "example": "<p><div>内容</div></p> ❌",
+                "correct": "<div><p>内容</p></div> ✓"
+            },
+            {
+                "parent": "strong", 
+                "children": ["p", "div", "table", "ul", "ol"], 
+                "reason": "行内元素不能包含块级元素",
+                "example": "<strong><p>段落</p></strong> ❌",
+                "correct": "<p><strong>段落</strong></p> ✓"
+            },
+            {
+                "parent": "em", 
+                "children": ["p", "div", "table", "ul", "ol"], 
+                "reason": "行内元素不能包含块级元素"
+            },
+            {
+                "parent": "table", 
+                "children": ["p", "div", "h1", "h2", "h3", "ul", "ol"], 
+                "reason": "表格只能包含行元素（tr）",
+                "example": "<table><p>内容</p></table> ❌",
+                "correct": "<table><tr><td>内容</td></tr></table> ✓"
+            }
+        ],
+        "recommended": [
+            {
+                "parent": "p", 
+                "children": ["strong", "em", "u", "s", "sup", "sub", "code", "span"], 
+                "reason": "段落可以包含行内格式化元素",
+                "example": "<p><strong>加粗</strong><em>斜体</em></p> ✓"
+            },
+            {
+                "parent": "div", 
+                "children": ["h1", "h2", "h3", "h4", "h5", "h6", "p", "table", "ul", "ol"], 
+                "reason": "div可以包含块级元素",
+                "example": "<div><h2>标题</h2><p>段落</p></div> ✓"
+            }
+        ]
+    },
+    
+    "commonErrors": [
+        {
+            "error": "颜色格式错误", 
+            "example": "<span style=\"color: red;\">红色</span>", 
+            "correct": "<span style=\"color: #FF0000;\">红色</span>", 
+            "note": "必须使用6位十六进制格式 #RRGGBB"
+        },
+        {
+            "error": "未自闭合标签", 
+            "example": "<img src=\"image.jpg\">", 
+            "correct": "<img src=\"image.jpg\" alt=\"描述\" />", 
+            "note": "空标签必须自闭合，包含斜杠"
+        },
+        {
+            "error": "不支持的样式", 
+            "example": "<p style=\"float: right;\">浮动</p>", 
+            "correct": "<p class=\"right\">右对齐</p>", 
+            "note": "不支持float、text-shadow、display、position等CSS属性"
+        },
+        {
+            "error": "错误的嵌套", 
+            "example": "<strong><p>段落</p></strong>", 
+            "correct": "<p><strong>段落</strong></p>", 
+            "note": "块级元素不能嵌套在行内元素内"
+        },
+        {
+            "error": "忘记恢复单栏", 
+            "example": "<div class=\"columns\" data-cols=\"2\">双栏</div>", 
+            "correct": "<div class=\"columns\" data-cols=\"2\">双栏</div><div class=\"columns\" data-cols=\"1\"></div>", 
+            "note": "多栏布局后必须使用 data-cols=\"1\" 恢复单栏"
+        },
+        {
+            "error": "RGB颜色格式", 
+            "example": "<span style=\"color: rgb(255,0,0);\">红色</span>", 
+            "correct": "<span style=\"color: #FF0000;\">红色</span>", 
+            "note": "不支持rgb()和rgba()格式，必须使用十六进制"
+        }
+    ],
+    
+    "bestPractices": [
+        "颜色必须使用十六进制格式 #RRGGBB（如 #FF0000）",
+        "空标签必须自闭合（如 <img /> <br /> <hr />）",
+        "字体可以使用任意系统已安装的字体（如 微软雅黑、宋体、Arial、Times New Roman）",
+        "字号单位必须是pt（如 12pt、14pt、16pt、18pt）",
+        "栏数支持任意正整数（1=单栏、2=双栏、3=三栏、4=四栏等）",
+        "多栏布局后必须恢复单栏（data-cols=\"1\"）",
+        "图片必须包含 alt 属性以提高可访问性",
+        "优先使用语义化标签（h1-h6）而非仅用 font-size",
+        "表格单元格使用 th（表头）和 td（数据）区分",
+        "行内元素（strong、em、u、s、sup、sub、code、span）可以嵌套在块级元素（p、div）内",
+        "块级元素（p、div、table、ul、ol）不能嵌套在行内元素内",
+        "行距可以是数字或小数（如 1.5、1.8、2.0）"
+    ],
+    
+    "validationWorkflow": [
+        "1. 检查HTML基本结构（DOCTYPE, html, head, body）",
+        "2. 验证所有标签是否在允许列表中",
+        "3. 检查所有属性是否被支持",
+        "4. 验证所有样式是否符合规范（特别是颜色格式）",
+        "5. 检查颜色格式是否为十六进制 #RRGGBB",
+        "6. 验证标签嵌套是否正确",
+        "7. 确认自闭合标签格式正确",
+        "8. 检查多栏布局是否恢复单栏"
+    ]
+}
+
+
+def get_schema():
+    """获取HTML格式约束schema"""
+    return HTML_SCHEMA
+
+
+def get_schema_json():
+    """获取JSON格式的schema"""
+    import json
+    return json.dumps(HTML_SCHEMA, ensure_ascii=False, indent=2)
+
+
+if __name__ == "__main__":
+    print(get_schema_json())