fix: rm other attr in mathml

app/services/converter.py

@@ -340,9 +340,10 @@ class Converter:
         """Post-process MathML to improve Word compatibility.
         
         Applies transformations to make MathML more compatible with Word:
+        - Remove <semantics> and <annotation> wrappers (Word doesn't need them)
         - Change display="inline" to display="block" for better rendering
         - Decode Unicode entities to actual characters (Word prefers this)
-        - Clean up unnecessary attributes
+        - Ensure proper namespace
         
         Args:
             mathml: MathML string.
@@ -350,23 +351,57 @@ class Converter:
         Returns:
             Word-compatible MathML string.
         """
-        # Change display to block for better Word rendering
+        import re
+        
+        # Step 1: Remove <semantics> and <annotation> wrappers
+        # These often cause Word import issues
+        if '<semantics>' in mathml:
+            # Extract content between <semantics> and <annotation>
+            match = re.search(r'<semantics>(.*?)<annotation', mathml, re.DOTALL)
+            if match:
+                content = match.group(1).strip()
+                
+                # Get the math element attributes
+                math_attrs = ""
+                math_match = re.search(r'<math([^>]*)>', mathml)
+                if math_match:
+                    math_attrs = math_match.group(1)
+                
+                # Rebuild without semantics
+                mathml = f'<math{math_attrs}>{content}</math>'
+        
+        # Step 2: Change display to block for better Word rendering
         mathml = mathml.replace('display="inline"', 'display="block"')
         
-        # If no display attribute, add it
+        # Step 3: If no display attribute, add it
         if 'display=' not in mathml and '<math' in mathml:
             mathml = mathml.replace('<math', '<math display="block"', 1)
         
-        # Decode common Unicode entities to actual characters (Word prefers this)
+        # Step 4: Ensure xmlns is present
+        if 'xmlns=' not in mathml and '<math' in mathml:
+            mathml = mathml.replace('<math', '<math xmlns="http://www.w3.org/1998/Math/MathML"', 1)
+        
+        # Step 5: Decode common Unicode entities to actual characters (Word prefers this)
         unicode_map = {
             '&#x0002B;': '+',
-            '&#x02026;': '⋯',
+            '&#x0002D;': '-',
-            '&#x022EE;': '⋮',
+            '&#x0002A;': '*',
+            '&#x0002F;': '/',
             '&#x0003D;': '=',
-            '&#x0007C;': '|',
+            '&#x0003C;': '<',
-            '&#x0002C;': ',',
+            '&#x0003E;': '>',
             '&#x00028;': '(',
             '&#x00029;': ')',
+            '&#x0002C;': ',',
+            '&#x0002E;': '.',
+            '&#x0007C;': '|',
+            '&#x02026;': '⋯',
+            '&#x022EE;': '⋮',
+            '&#x022EF;': '⋯',
+            '&#x00B0;': '°',
+            '&#x03B3;': 'γ',
+            '&#x03C6;': 'φ',
+            '&#x03D5;': 'ϕ',
         }
         
         for entity, char in unicode_map.items():

docs/WORD_MATHML_GUIDE.md

@@ -0,0 +1,204 @@
+# MathML 导入 Word 完整指南
+
+## 问题诊断
+
+如果 MathML 无法在 Word 中渲染，通常是以下原因：
+
+### 1. **MathML 格式问题**
+- ❌ 包含 `<semantics>` 和 `<annotation>` 包装器
+- ❌ 使用 `display="inline"` 而不是 `display="block"`
+- ❌ 缺少 `xmlns` 命名空间
+- ❌ 使用 HTML 实体编码而不是实际字符
+
+### 2. **Word 粘贴方法不正确**
+- ❌ 直接粘贴到正文
+- ❌ 使用"选择性粘贴"
+- ❌ 粘贴位置不对
+
+## 已修复的问题
+
+我们的代码现在会自动：
+✅ 移除 `<semantics>` 和 `<annotation>` 包装器
+✅ 设置 `display="block"`
+✅ 添加正确的 `xmlns` 命名空间
+✅ 解码 Unicode 实体为实际字符
+
+## Word 中正确的粘贴方法
+
+### 方法 1：使用 MathType（推荐）✨
+
+如果你安装了 MathType：
+
+1. 复制 MathML 内容
+2. 在 Word 中：**插入** → **对象** → **MathType 公式**
+3. 在 MathType 中：**编辑** → **粘贴 MathML**
+4. 点击"确定"
+
+### 方法 2：使用 Word 内置公式编辑器
+
+#### 选项 A：Alt 文本方法（最可靠）
+
+1. 在 Word 中：**插入** → **公式**
+2. 输入任意内容（如 `x`）
+3. 选中公式，右键 → **公式选项** → **另存为新公式**
+4. 取消，返回文档
+5. 右键公式 → **编辑替换文本**
+6. 将 MathML 粘贴到替换文本框
+7. 按 Enter
+
+#### 选项 B：XML 方法（需要开发者模式）
+
+1. **文件** → **选项** → **自定义功能区**
+2. 勾选"开发工具"
+3. **开发工具** → **XML 映射**
+4. 粘贴 MathML
+
+#### 选项 C：宏方法（高级）
+
+使用 VBA 宏：
+
+```vba
+Sub InsertMathML()
+    Dim mathML As String
+    mathML = "<math>...</math>" ' 粘贴你的 MathML
+    
+    Selection.Range.InsertXML mathML
+End Sub
+```
+
+### 方法 3：使用在线工具转换
+
+1. 访问 https://www.mathcha.io/
+2. 粘贴 MathML
+3. 导出为 Word 格式
+
+## 测试你的 MathML
+
+运行诊断工具：
+
+```bash
+python test_mathml_word_compatibility.py
+```
+
+这会检查：
+- ✓ 命名空间是否正确
+- ✓ Display 属性
+- ✓ 是否有 semantics 包装器
+- ✓ Unicode 实体
+
+## 示例：正确的 MathML 格式
+
+```xml
+<math display="block" xmlns="http://www.w3.org/1998/Math/MathML">
+  <mrow>
+    <mi>γ</mi>
+    <mo>=</mo>
+    <mn>22.2</mn>
+    <mo>,</mo>
+    <mi>c</mi>
+    <mo>=</mo>
+    <mn>30.4</mn>
+  </mrow>
+</math>
+```
+
+**不要有：**
+```xml
+<math>
+  <semantics>    ❌ Word 可能不识别
+    <mrow>...</mrow>
+    <annotation>...</annotation>    ❌ Word 不需要
+  </semantics>
+</math>
+```
+
+## API 使用
+
+### 获取 Word 兼容的 MathML
+
+```bash
+curl -X POST "http://localhost:8000/api/v1/image/ocr" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "image_base64": "...",
+    "model_name": "mineru"
+  }'
+```
+
+响应中的 `mathml` 字段已经过优化，可以直接用于 Word。
+
+### 如果还是不工作
+
+1. **检查 Word 版本**
+   - Word 2010+ 支持 MathML
+   - Word Online 支持有限
+
+2. **检查 MathML 内容**
+   ```bash
+   python test_mathml_word_compatibility.py
+   ```
+
+3. **尝试 OMML 格式（Word 原生）**
+   ```bash
+   curl -X POST "http://localhost:8000/api/v1/convert/latex-to-omml" \
+     -H "Content-Type: application/json" \
+     -d '{"latex": "\\gamma = 22.2"}'
+   ```
+   
+   OMML 是 Word 的原生格式，兼容性最好。
+
+## 为什么 OMML 更好？
+
+| 格式 | 用途 | Word 兼容性 |
+|------|------|------------|
+| **MathML** | Web 标准、跨平台 | ⭐⭐⭐ 需要转换 |
+| **OMML** | Word 原生格式 | ⭐⭐⭐⭐⭐ 完美 |
+
+**建议**：
+- 手动粘贴 → 使用 MathML
+- 编程生成 Word 文档 → 使用 OMML
+
+## 常见错误
+
+### 错误 1：粘贴后显示为文本
+
+**原因**：粘贴位置不对或格式不对
+
+**解决**：
+1. 确保 MathML 以 `<math` 开头
+2. 使用 Alt 文本方法
+3. 或使用 OMML 接口
+
+### 错误 2：显示为方框
+
+**原因**：Word 无法解析 MathML 结构
+
+**解决**：
+1. 检查是否有 `<semantics>` 包装器（我们已移除）
+2. 使用 OMML 格式
+
+### 错误 3：部分显示不正确
+
+**原因**：某些 LaTeX 命令不支持
+
+**解决**：
+1. 检查 LaTeX 语法
+2. 使用 Word 支持的标准命令
+
+## 最终建议
+
+**最简单的方法**：使用 OMML 格式
+
+```bash
+# 1. 获取 LaTeX
+POST /api/v1/image/ocr
+→ 获取 "latex" 字段
+
+# 2. 转换为 OMML
+POST /api/v1/convert/latex-to-omml
+→ 获取 "omml" 字段
+
+# 3. 使用 python-docx 或 Office.js 插入
+```
+
+这样可以避免所有 MathML 兼容性问题！

test_mathml_word_compatibility.py

@@ -0,0 +1,236 @@
+"""Diagnostic tool for MathML Word compatibility issues."""
+
+from app.services.converter import Converter
+
+
+def diagnose_mathml(latex: str) -> dict:
+    """Diagnose MathML generation and Word compatibility.
+    
+    Args:
+        latex: LaTeX formula to convert.
+        
+    Returns:
+        Dictionary with diagnostic information.
+    """
+    converter = Converter()
+    
+    print("=" * 80)
+    print("MathML Word Compatibility Diagnostic")
+    print("=" * 80)
+    
+    print(f"\nInput LaTeX: {latex}")
+    
+    # Convert
+    try:
+        result = converter.convert_to_formats(f"${latex}$")
+        mathml = result.mathml
+        
+        print(f"\n✓ Conversion successful")
+        print(f"MathML length: {len(mathml)} characters")
+        
+    except Exception as e:
+        print(f"\n✗ Conversion failed: {e}")
+        return {"success": False, "error": str(e)}
+    
+    # Diagnostic checks
+    print("\n" + "-" * 80)
+    print("Word Compatibility Checks:")
+    print("-" * 80)
+    
+    issues = []
+    
+    # Check 1: Has proper namespace
+    if 'xmlns="http://www.w3.org/1998/Math/MathML"' in mathml:
+        print("✓ Has correct MathML namespace")
+    else:
+        print("✗ Missing or incorrect MathML namespace")
+        issues.append("namespace")
+    
+    # Check 2: Display attribute
+    if 'display="block"' in mathml:
+        print("✓ Has display='block' attribute")
+    elif 'display="inline"' in mathml:
+        print("⚠ Has display='inline' (Word prefers 'block')")
+        issues.append("display_inline")
+    else:
+        print("✗ Missing display attribute")
+        issues.append("no_display")
+    
+    # Check 3: Check for problematic elements
+    if '<semantics>' in mathml:
+        print("⚠ Contains <semantics> element")
+        print("  Note: Word may ignore semantics wrapper")
+        issues.append("semantics")
+    
+    if '<annotation' in mathml:
+        print("⚠ Contains <annotation> element")
+        print("  Note: Word doesn't need annotation, may cause issues")
+        issues.append("annotation")
+    
+    # Check 4: Unicode entities
+    problematic_entities = ['&#x', '&gt;', '&lt;', '&amp;']
+    has_entities = any(entity in mathml for entity in problematic_entities)
+    if has_entities:
+        print("⚠ Contains encoded entities (Word prefers actual characters)")
+        issues.append("entities")
+    else:
+        print("✓ No problematic entities")
+    
+    # Check 5: Root element structure
+    if mathml.startswith('<math'):
+        print("✓ Starts with <math> element")
+    else:
+        print("✗ Doesn't start with <math> element")
+        issues.append("no_math_root")
+    
+    # Check 6: Check for common Word-incompatible attributes
+    if 'class=' in mathml:
+        print("⚠ Contains 'class' attribute (Word ignores these)")
+    
+    if 'style=' in mathml:
+        print("⚠ Contains 'style' attribute (Word ignores these)")
+    
+    # Print MathML structure
+    print("\n" + "-" * 80)
+    print("MathML Structure:")
+    print("-" * 80)
+    
+    # Show first 500 chars
+    print(mathml[:500])
+    if len(mathml) > 500:
+        print("...")
+        print(mathml[-200:])
+    
+    # Recommendations
+    print("\n" + "-" * 80)
+    print("Recommendations:")
+    print("-" * 80)
+    
+    if not issues:
+        print("✓ MathML appears to be Word-compatible!")
+        print("\nHow to paste into Word:")
+        print("  1. Copy the MathML XML")
+        print("  2. In Word: Insert → Equation → Ink Equation")
+        print("  3. Right-click the equation → 'Professional'")
+        print("  4. Right-click again → 'Save as new equation'")
+        print("\nOR use Alt text method:")
+        print("  1. Insert → Equation")
+        print("  2. Type any formula")
+        print("  3. Right-click → Edit Alt Text")
+        print("  4. Paste MathML in Alt Text field")
+    else:
+        print("Issues found:")
+        if "semantics" in issues or "annotation" in issues:
+            print("\n1. Remove <semantics> and <annotation> wrappers")
+            print("   Word only needs the <mrow> content inside")
+        
+        if "display_inline" in issues:
+            print("\n2. Change display='inline' to display='block'")
+        
+        if "entities" in issues:
+            print("\n3. Decode HTML entities to actual characters")
+        
+        if "namespace" in issues:
+            print("\n4. Add xmlns='http://www.w3.org/1998/Math/MathML'")
+    
+    return {
+        "success": True,
+        "mathml": mathml,
+        "issues": issues,
+        "length": len(mathml)
+    }
+
+
+def test_simple_formula():
+    """Test with a simple formula."""
+    print("\nTest 1: Simple formula")
+    diagnose_mathml(r"\frac{a}{b}")
+
+
+def test_complex_formula():
+    """Test with a complex formula."""
+    print("\n\nTest 2: Complex formula with matrix")
+    diagnose_mathml(r"\left| \begin{array}{cc} a & b \\ c & d \end{array} \right|")
+
+
+def test_problematic_formula():
+    """Test with the user's problematic formula."""
+    print("\n\nTest 3: User's formula (after OCR fix)")
+    diagnose_mathml(r"\gamma = 22.2, c = 30.4, \phi = 25.4 ^ {\circ}")
+
+
+def generate_clean_mathml():
+    """Generate a clean MathML without semantics/annotation."""
+    
+    print("\n" + "=" * 80)
+    print("Generating Clean MathML for Word")
+    print("=" * 80)
+    
+    converter = Converter()
+    latex = r"\gamma = 22.2, c = 30.4, \phi = 25.4 ^ {\circ}"
+    
+    result = converter.convert_to_formats(f"${latex}$")
+    mathml = result.mathml
+    
+    # Remove semantics wrapper if present
+    import re
+    
+    # Extract content from semantics if present
+    if '<semantics>' in mathml:
+        print("\n⚠ Original has <semantics> wrapper")
+        
+        # Try to extract just the mrow content
+        match = re.search(r'<semantics>(.*?)<annotation', mathml, re.DOTALL)
+        if match:
+            content = match.group(1).strip()
+            
+            # Rebuild without semantics
+            clean_mathml = f'<math display="block" xmlns="http://www.w3.org/1998/Math/MathML">{content}</math>'
+            
+            print("\nCleaned MathML (without semantics):")
+            print("-" * 80)
+            print(clean_mathml)
+            
+            print("\n✓ Try pasting this version into Word")
+            return clean_mathml
+    
+    print("\nGenerated MathML:")
+    print("-" * 80)
+    print(mathml)
+    
+    return mathml
+
+
+if __name__ == "__main__":
+    print("MathML Word Compatibility Diagnostic Tool\n")
+    
+    try:
+        test_simple_formula()
+        test_complex_formula()
+        test_problematic_formula()
+        
+        print("\n\n")
+        clean = generate_clean_mathml()
+        
+        print("\n" + "=" * 80)
+        print("SUMMARY")
+        print("=" * 80)
+        print("\nCommon reasons MathML doesn't work in Word:")
+        print("  1. <semantics> wrapper - Word may not parse it correctly")
+        print("  2. <annotation> element - Word doesn't need it")
+        print("  3. HTML entities - Word prefers actual Unicode characters")
+        print("  4. Missing xmlns attribute")
+        print("  5. Wrong paste location in Word")
+        
+        print("\nBest practice for Word:")
+        print("  • Use simple MathML without semantics wrapper")
+        print("  • Include xmlns attribute")
+        print("  • Use display='block'")
+        print("  • Use actual characters, not entities")
+        
+        print("\n" + "=" * 80)
+        
+    except Exception as e:
+        print(f"\nError: {e}")
+        import traceback
+        traceback.print_exc()