feat: add omml api

app/api/v1/endpoints/convert.py

@@ -1,10 +1,10 @@
-"""Markdown to DOCX conversion endpoint."""
+"""Format conversion endpoints."""
 
 from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import Response
 
 from app.core.dependencies import get_converter
-from app.schemas.convert import MarkdownToDocxRequest
+from app.schemas.convert import MarkdownToDocxRequest, LatexToOmmlRequest, LatexToOmmlResponse
 from app.services.converter import Converter
 
 router = APIRouter()
@@ -28,3 +28,39 @@ async def convert_markdown_to_docx(
         )
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Conversion failed: {e}")
+
+
+@router.post("/latex-to-omml", response_model=LatexToOmmlResponse)
+async def convert_latex_to_omml(
+    request: LatexToOmmlRequest,
+    converter: Converter = Depends(get_converter),
+) -> LatexToOmmlResponse:
+    """Convert LaTeX formula to OMML (Office Math Markup Language).
+
+    OMML is the math format used by Microsoft Word and other Office applications.
+    This endpoint is separate from the main OCR endpoint due to the performance
+    overhead of OMML conversion (requires creating a temporary DOCX file).
+
+    Args:
+        request: Contains the LaTeX formula to convert (without $ or $$ delimiters).
+
+    Returns:
+        OMML representation of the formula.
+
+    Example:
+        ```bash
+        curl -X POST "http://localhost:8000/api/v1/convert/latex-to-omml" \\
+          -H "Content-Type: application/json" \\
+          -d '{"latex": "\\\\frac{a}{b} + \\\\sqrt{c}"}'
+        ```
+    """
+    if not request.latex or not request.latex.strip():
+        raise HTTPException(status_code=400, detail="LaTeX formula cannot be empty")
+
+    try:
+        omml = converter.convert_to_omml(request.latex)
+        return LatexToOmmlResponse(omml=omml)
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except RuntimeError as e:
+        raise HTTPException(status_code=503, detail=str(e))

app/api/v1/endpoints/image.py

@@ -2,12 +2,11 @@
 
 from fastapi import APIRouter, Depends, HTTPException
 
-from app.core.dependencies import get_image_processor, get_layout_detector, get_ocr_service, get_mineru_ocr_service, get_converter
+from app.core.dependencies import get_image_processor, get_layout_detector, get_ocr_service, get_mineru_ocr_service
-from app.schemas.image import ImageOCRRequest, ImageOCRResponse, LatexToOmmlRequest, LatexToOmmlResponse
+from app.schemas.image import ImageOCRRequest, ImageOCRResponse
 from app.services.image_processor import ImageProcessor
 from app.services.layout_detector import LayoutDetector
 from app.services.ocr_service import OCRService, MineruOCRService
-from app.services.converter import Converter
 
 router = APIRouter()
 
@@ -31,7 +30,7 @@ async def process_image_ocr(
     4. Convert output to LaTeX, Markdown, and MathML formats
 
     Note: OMML conversion is not included due to performance overhead.
-    Use the /latex-to-omml endpoint to convert LaTeX to OMML separately.
+    Use the /convert/latex-to-omml endpoint to convert LaTeX to OMML separately.
     """
 
     image = image_processor.preprocess(
@@ -55,32 +54,3 @@ async def process_image_ocr(
         mathml=ocr_result.get("mathml", ""),
         mml=ocr_result.get("mml", ""),
     )
-
-
-@router.post("/latex-to-omml", response_model=LatexToOmmlResponse)
-async def convert_latex_to_omml(
-    request: LatexToOmmlRequest,
-    converter: Converter = Depends(get_converter),
-) -> LatexToOmmlResponse:
-    """Convert LaTeX formula to OMML (Office Math Markup Language).
-
-    OMML is the math format used by Microsoft Word and other Office applications.
-    This endpoint is separate from the main OCR endpoint due to the performance
-    overhead of OMML conversion (requires creating a temporary DOCX file).
-
-    Args:
-        request: Contains the LaTeX formula to convert (without $ or $$ delimiters).
-
-    Returns:
-        OMML representation of the formula.
-    """
-    if not request.latex or not request.latex.strip():
-        raise HTTPException(status_code=400, detail="LaTeX formula cannot be empty")
-
-    try:
-        omml = converter.convert_to_omml(request.latex)
-        return LatexToOmmlResponse(omml=omml)
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    except RuntimeError as e:
-        raise HTTPException(status_code=503, detail=str(e))

app/schemas/convert.py

@@ -1,4 +1,4 @@
-"""Request and response schemas for markdown to DOCX conversion endpoint."""
+"""Request and response schemas for format conversion endpoints."""
 
 from pydantic import BaseModel, Field, field_validator
 
@@ -17,3 +17,23 @@ class MarkdownToDocxRequest(BaseModel):
             raise ValueError("Markdown content cannot be empty")
         return v
 
+
+class LatexToOmmlRequest(BaseModel):
+    """Request body for LaTeX to OMML conversion endpoint."""
+
+    latex: str = Field(..., description="Pure LaTeX formula (without $ or $$ delimiters)")
+
+    @field_validator("latex")
+    @classmethod
+    def validate_latex_not_empty(cls, v: str) -> str:
+        """Validate that LaTeX formula is not empty."""
+        if not v or not v.strip():
+            raise ValueError("LaTeX formula cannot be empty")
+        return v
+
+
+class LatexToOmmlResponse(BaseModel):
+    """Response body for LaTeX to OMML conversion endpoint."""
+
+    omml: str = Field("", description="OMML (Office Math Markup Language) representation")
+

app/schemas/image.py

@@ -47,14 +47,3 @@ class ImageOCRResponse(BaseModel):
     layout_info: LayoutInfo = Field(default_factory=LayoutInfo)
     recognition_mode: str = Field("", description="Recognition mode used: mixed_recognition or formula_recognition")
 
-
-class LatexToOmmlRequest(BaseModel):
-    """Request body for LaTeX to OMML conversion endpoint."""
-
-    latex: str = Field(..., description="Pure LaTeX formula (without $ or $$ delimiters)")
-
-
-class LatexToOmmlResponse(BaseModel):
-    """Response body for LaTeX to OMML conversion endpoint."""
-
-    omml: str = Field("", description="OMML (Office Math Markup Language) representation")

test_omml_api.py

@@ -0,0 +1,112 @@
+"""Test script for OMML conversion API endpoint."""
+
+import requests
+import json
+
+
+def test_latex_to_omml():
+    """Test the /convert/latex-to-omml endpoint."""
+    
+    # Test cases
+    test_cases = [
+        {
+            "name": "Simple fraction",
+            "latex": "\\frac{a}{b}",
+        },
+        {
+            "name": "Quadratic formula",
+            "latex": "x = \\frac{-b \\pm \\sqrt{b^2 - 4ac}}{2a}",
+        },
+        {
+            "name": "Integral",
+            "latex": "\\int_0^\\infty e^{-x^2} dx = \\frac{\\sqrt{\\pi}}{2}",
+        },
+        {
+            "name": "Matrix",
+            "latex": "\\begin{matrix} a & b \\\\ c & d \\end{matrix}",
+        },
+    ]
+    
+    base_url = "http://localhost:8000/api/v1/convert/latex-to-omml"
+    
+    print("Testing OMML Conversion API")
+    print("=" * 80)
+    
+    for i, test_case in enumerate(test_cases, 1):
+        print(f"\nTest {i}: {test_case['name']}")
+        print("-" * 80)
+        print(f"LaTeX: {test_case['latex']}")
+        
+        try:
+            response = requests.post(
+                base_url,
+                json={"latex": test_case["latex"]},
+                headers={"Content-Type": "application/json"},
+                timeout=10,
+            )
+            
+            if response.status_code == 200:
+                result = response.json()
+                omml = result.get("omml", "")
+                
+                print(f"✓ Status: {response.status_code}")
+                print(f"OMML length: {len(omml)} characters")
+                print(f"OMML preview: {omml[:150]}...")
+                
+            else:
+                print(f"✗ Status: {response.status_code}")
+                print(f"Error: {response.text}")
+                
+        except requests.exceptions.RequestException as e:
+            print(f"✗ Request failed: {e}")
+        except Exception as e:
+            print(f"✗ Error: {e}")
+    
+    print("\n" + "=" * 80)
+
+
+def test_invalid_input():
+    """Test error handling with invalid input."""
+    
+    print("\nTesting Error Handling")
+    print("=" * 80)
+    
+    base_url = "http://localhost:8000/api/v1/convert/latex-to-omml"
+    
+    # Empty LaTeX
+    print("\nTest: Empty LaTeX")
+    response = requests.post(
+        base_url,
+        json={"latex": ""},
+        headers={"Content-Type": "application/json"},
+    )
+    print(f"Status: {response.status_code}")
+    print(f"Response: {response.json()}")
+    
+    # Missing LaTeX field
+    print("\nTest: Missing LaTeX field")
+    response = requests.post(
+        base_url,
+        json={},
+        headers={"Content-Type": "application/json"},
+    )
+    print(f"Status: {response.status_code}")
+    print(f"Response: {response.json()}")
+    
+    print("\n" + "=" * 80)
+
+
+if __name__ == "__main__":
+    print("OMML API Test Suite")
+    print("Make sure the API server is running on http://localhost:8000")
+    print()
+    
+    try:
+        test_latex_to_omml()
+        test_invalid_input()
+        print("\n✓ All tests completed!")
+        
+    except KeyboardInterrupt:
+        print("\n\n✗ Tests interrupted by user")
+    except Exception as e:
+        print(f"\n✗ Test suite failed: {e}")