fix: rm other attr

app/services/converter.py

@@ -339,8 +339,10 @@ class Converter:
     def _postprocess_mathml_for_word(mathml: str) -> str:
         """Post-process MathML to improve Word compatibility.
         
-        Applies transformations to make MathML more compatible with Word:
+        Applies transformations to make MathML more compatible and concise:
         - Remove <semantics> and <annotation> wrappers (Word doesn't need them)
+        - Remove unnecessary attributes (form, stretchy, fence, columnalign, etc.)
+        - Remove redundant single <mrow> wrappers
         - Change display="inline" to display="block" for better rendering
         - Decode Unicode entities to actual characters (Word prefers this)
         - Ensure proper namespace
@@ -349,7 +351,7 @@ class Converter:
             mathml: MathML string.
             
         Returns:
-            Word-compatible MathML string.
+            Simplified, Word-compatible MathML string.
         """
         import re
         
@@ -370,18 +372,52 @@ class Converter:
                 # Rebuild without semantics
                 mathml = f'<math{math_attrs}>{content}</math>'
         
-        # Step 2: Change display to block for better Word rendering
+        # Step 2: Remove unnecessary attributes that don't affect rendering
+        # These are verbose and Word doesn't need them
+        unnecessary_attrs = [
+            r'\s+form="prefix"',
+            r'\s+form="postfix"',
+            r'\s+form="infix"',
+            r'\s+stretchy="true"',
+            r'\s+stretchy="false"',
+            r'\s+fence="true"',
+            r'\s+fence="false"',
+            r'\s+separator="true"',
+            r'\s+separator="false"',
+            r'\s+columnalign="[^"]*"',
+            r'\s+columnspacing="[^"]*"',
+            r'\s+rowspacing="[^"]*"',
+            r'\s+class="[^"]*"',
+            r'\s+style="[^"]*"',
+        ]
+        
+        for attr_pattern in unnecessary_attrs:
+            mathml = re.sub(attr_pattern, '', mathml)
+        
+        # Step 3: Remove redundant single <mrow> wrapper at the top level
+        # Pattern: <math ...><mrow>content</mrow></math>
+        # Simplify to: <math ...>content</math>
+        mrow_pattern = r'(<math[^>]*>)\s*<mrow>(.*?)</mrow>\s*(</math>)'
+        match = re.search(mrow_pattern, mathml, re.DOTALL)
+        if match:
+            # Check if there's only one mrow at the top level
+            content = match.group(2)
+            # Only remove if the content doesn't have other top-level elements
+            if not re.search(r'</[^>]+>\s*<[^/]', content):
+                mathml = f'{match.group(1)}{content}{match.group(3)}'
+        
+        # Step 4: Change display to block for better Word rendering
         mathml = mathml.replace('display="inline"', 'display="block"')
         
-        # Step 3: If no display attribute, add it
+        # Step 5: If no display attribute, add it
         if 'display=' not in mathml and '<math' in mathml:
             mathml = mathml.replace('<math', '<math display="block"', 1)
         
-        # Step 4: Ensure xmlns is present
+        # Step 6: 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)
+        # Step 7: Decode common Unicode entities to actual characters (Word prefers this)
         unicode_map = {
             '&#x0002B;': '+',
             '&#x0002D;': '-',
@@ -402,11 +438,26 @@ class Converter:
             '&#x03B3;': 'γ',
             '&#x03C6;': 'φ',
             '&#x03D5;': 'ϕ',
+            '&#x03B1;': 'α',
+            '&#x03B2;': 'β',
+            '&#x03B4;': 'δ',
+            '&#x03B5;': 'ε',
+            '&#x03B8;': 'θ',
+            '&#x03BB;': 'λ',
+            '&#x03BC;': 'μ',
+            '&#x03C0;': 'π',
+            '&#x03C1;': 'ρ',
+            '&#x03C3;': 'σ',
+            '&#x03C4;': 'τ',
+            '&#x03C9;': 'ω',
         }
         
         for entity, char in unicode_map.items():
             mathml = mathml.replace(entity, char)
         
+        # Step 8: Clean up extra whitespace
+        mathml = re.sub(r'>\s+<', '><', mathml)
+        
         return mathml
 
     def _latex_to_mathml(self, latex_formula: str) -> str: