Spaces:

marcosremar2
/

mineru2

Running

marcosremar2 commited on Jul 10

Commit

39baca3

1 Parent(s): 4a9d776

Simplify app for testing

- Create minimal version to test PDF upload
- Remove complex dependencies temporarily
- Add test endpoint to verify deployment
- Version 0.3.0 for tracking

Files changed (3) hide show

app.py +18 -159
app_full.py +182 -0
test_api_local.py +66 -0

app.py CHANGED Viewed

@@ -1,14 +1,8 @@
-from fastapi import FastAPI, File, UploadFile, HTTPException, BackgroundTasks
-from fastapi.responses import HTMLResponse, FileResponse
 import os
-import tempfile
-import shutil
-from pathlib import Path
-import asyncio
-from typing import Dict, Optional
-import uuid
-app = FastAPI(title="MinerU PDF Converter", version="0.2.0")
 @app.get("/")
 async def root():
@@ -16,167 +10,32 @@ async def root():
     return {
         "message": "Hello World from MinerU PDF Converter!",
         "status": "running",
         "environment": os.environ.get("SPACE_ID", "local")
     }
 @app.get("/health")
 async def health_check():
     """Health check endpoint"""
-    return {"status": "healthy", "service": "pdf2md"}
-@app.get("/test", response_class=HTMLResponse)
-async def test_page():
-    """Simple HTML test page"""
-    return """
-    <html>
-        <head>
-            <title>PDF to Markdown - Test</title>
-            <style>
-                body {
-                    font-family: Arial, sans-serif;
-                    max-width: 800px;
-                    margin: 0 auto;
-                    padding: 20px;
-                }
-                .status {
-                    background: #e8f5e9;
-                    padding: 10px;
-                    border-radius: 5px;
-                    margin: 20px 0;
-                }
-            </style>
-        </head>
-        <body>
-            <h1>PDF to Markdown Converter</h1>
-            <div class="status">
-                ✅ Service is running!
-            </div>
-            <p>This is a test deployment. Full functionality coming soon.</p>
-            <p>
-                <a href="/docs">API Documentation</a> |
-                <a href="/health">Health Check</a>
-            </p>
-        </body>
-    </html>
-    """
-@app.get("/api/info")
-async def api_info():
-    """API information endpoint"""
-    return {
-        "name": "PDF to Markdown Converter API",
-        "version": "0.2.0",
-        "endpoints": {
-            "/": "Main endpoint",
-            "/health": "Health check",
-            "/test": "Test HTML page",
-            "/docs": "FastAPI automatic documentation",
-            "/api/info": "This endpoint",
-            "/api/convert": "Convert PDF to Markdown (POST)",
-            "/api/status/{task_id}": "Check conversion status",
-            "/api/download/{task_id}": "Download converted markdown"
-        }
-    }
-# Store for conversion tasks
-conversion_tasks: Dict[str, dict] = {}
 @app.post("/api/convert")
-async def convert_pdf(
-    background_tasks: BackgroundTasks,
-    file: UploadFile = File(...)
-):
-    """Convert PDF to Markdown"""
     if not file.filename.endswith('.pdf'):
         raise HTTPException(status_code=400, detail="Only PDF files are supported")
-    # Generate unique task ID
-    task_id = str(uuid.uuid4())
-    # Save uploaded file
-    temp_dir = Path(tempfile.mkdtemp())
-    pdf_path = temp_dir / file.filename
-    try:
-        with open(pdf_path, "wb") as buffer:
-            shutil.copyfileobj(file.file, buffer)
-    except Exception as e:
-        shutil.rmtree(temp_dir)
-        raise HTTPException(status_code=500, detail=f"Failed to save file: {str(e)}")
-    # Initialize task status
-    conversion_tasks[task_id] = {
-        "status": "processing",
-        "filename": file.filename,
-        "result": None,
-        "error": None,
-        "temp_dir": str(temp_dir)
-    }
-    # Start conversion in background
-    background_tasks.add_task(process_pdf_conversion, task_id, str(pdf_path))
     return {
-        "task_id": task_id,
-        "status": "processing",
-        "message": "PDF conversion started",
-        "check_status_url": f"/api/status/{task_id}"
     }
-async def process_pdf_conversion(task_id: str, pdf_path: str):
-    """Process PDF conversion in background"""
-    try:
-        # For now, just simulate conversion
-        await asyncio.sleep(2)  # Simulate processing
-        # Create a dummy markdown file
-        output_path = Path(pdf_path).with_suffix('.md')
-        with open(output_path, 'w') as f:
-            f.write(f"# Converted from {Path(pdf_path).name}\n\n")
-            f.write("This is a placeholder conversion. Full MinerU integration coming soon.\n")
-        conversion_tasks[task_id]["status"] = "completed"
-        conversion_tasks[task_id]["result"] = str(output_path)
-    except Exception as e:
-        conversion_tasks[task_id]["status"] = "failed"
-        conversion_tasks[task_id]["error"] = str(e)
-@app.get("/api/status/{task_id}")
-async def get_conversion_status(task_id: str):
-    """Check conversion status"""
-    if task_id not in conversion_tasks:
-        raise HTTPException(status_code=404, detail="Task not found")
-    task = conversion_tasks[task_id]
-    response = {
-        "task_id": task_id,
-        "status": task["status"],
-        "filename": task["filename"]
-    }
-    if task["status"] == "completed":
-        response["download_url"] = f"/api/download/{task_id}"
-    elif task["status"] == "failed":
-        response["error"] = task["error"]
-    return response
-@app.get("/api/download/{task_id}")
-async def download_converted_file(task_id: str):
-    """Download converted markdown file"""
-    if task_id not in conversion_tasks:
-        raise HTTPException(status_code=404, detail="Task not found")
-    task = conversion_tasks[task_id]
-    if task["status"] != "completed":
-        raise HTTPException(status_code=400, detail="Conversion not completed")
-    if not task["result"] or not Path(task["result"]).exists():
-        raise HTTPException(status_code=404, detail="Converted file not found")
-    return FileResponse(
-        task["result"],
-        media_type="text/markdown",
-        filename=Path(task["result"]).name
-    )

+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import HTMLResponse, JSONResponse
 import os
+app = FastAPI(title="MinerU PDF Converter", version="0.3.0")
 @app.get("/")
 async def root():
     return {
         "message": "Hello World from MinerU PDF Converter!",
         "status": "running",
+        "version": "0.3.0",
         "environment": os.environ.get("SPACE_ID", "local")
     }
 @app.get("/health")
 async def health_check():
     """Health check endpoint"""
+    return {"status": "healthy", "service": "pdf2md", "version": "0.3.0"}
 @app.post("/api/convert")
+async def convert_pdf(file: UploadFile = File(...)):
+    """Test PDF upload endpoint"""
     if not file.filename.endswith('.pdf'):
         raise HTTPException(status_code=400, detail="Only PDF files are supported")
     return {
+        "message": "PDF upload endpoint is working!",
+        "filename": file.filename,
+        "size": len(await file.read()),
+        "status": "test_mode"
     }
+@app.get("/api/test")
+async def test_endpoint():
+    """Test that new endpoints are available"""
+    return {
+        "message": "New endpoints are working!",
+        "endpoints": ["/api/convert", "/api/test"]
+    }

app_full.py ADDED Viewed

	@@ -0,0 +1,182 @@

+from fastapi import FastAPI, File, UploadFile, HTTPException, BackgroundTasks
+from fastapi.responses import HTMLResponse, FileResponse
+import os
+import tempfile
+import shutil
+from pathlib import Path
+import asyncio
+from typing import Dict, Optional
+import uuid
+app = FastAPI(title="MinerU PDF Converter", version="0.2.0")
+@app.get("/")
+async def root():
+    """Simple hello world endpoint"""
+    return {
+        "message": "Hello World from MinerU PDF Converter!",
+        "status": "running",
+        "environment": os.environ.get("SPACE_ID", "local")
+    }
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    return {"status": "healthy", "service": "pdf2md"}
+@app.get("/test", response_class=HTMLResponse)
+async def test_page():
+    """Simple HTML test page"""
+    return """
+    <html>
+        <head>
+            <title>PDF to Markdown - Test</title>
+            <style>
+                body {
+                    font-family: Arial, sans-serif;
+                    max-width: 800px;
+                    margin: 0 auto;
+                    padding: 20px;
+                }
+                .status {
+                    background: #e8f5e9;
+                    padding: 10px;
+                    border-radius: 5px;
+                    margin: 20px 0;
+                }
+            </style>
+        </head>
+        <body>
+            <h1>PDF to Markdown Converter</h1>
+            <div class="status">
+                ✅ Service is running!
+            </div>
+            <p>This is a test deployment. Full functionality coming soon.</p>
+            <p>
+                <a href="/docs">API Documentation</a> |
+                <a href="/health">Health Check</a>
+            </p>
+        </body>
+    </html>
+    """
+@app.get("/api/info")
+async def api_info():
+    """API information endpoint"""
+    return {
+        "name": "PDF to Markdown Converter API",
+        "version": "0.2.0",
+        "endpoints": {
+            "/": "Main endpoint",
+            "/health": "Health check",
+            "/test": "Test HTML page",
+            "/docs": "FastAPI automatic documentation",
+            "/api/info": "This endpoint",
+            "/api/convert": "Convert PDF to Markdown (POST)",
+            "/api/status/{task_id}": "Check conversion status",
+            "/api/download/{task_id}": "Download converted markdown"
+        }
+    }
+# Store for conversion tasks
+conversion_tasks: Dict[str, dict] = {}
+@app.post("/api/convert")
+async def convert_pdf(
+    background_tasks: BackgroundTasks,
+    file: UploadFile = File(...)
+):
+    """Convert PDF to Markdown"""
+    if not file.filename.endswith('.pdf'):
+        raise HTTPException(status_code=400, detail="Only PDF files are supported")
+    # Generate unique task ID
+    task_id = str(uuid.uuid4())
+    # Save uploaded file
+    temp_dir = Path(tempfile.mkdtemp())
+    pdf_path = temp_dir / file.filename
+    try:
+        with open(pdf_path, "wb") as buffer:
+            shutil.copyfileobj(file.file, buffer)
+    except Exception as e:
+        shutil.rmtree(temp_dir)
+        raise HTTPException(status_code=500, detail=f"Failed to save file: {str(e)}")
+    # Initialize task status
+    conversion_tasks[task_id] = {
+        "status": "processing",
+        "filename": file.filename,
+        "result": None,
+        "error": None,
+        "temp_dir": str(temp_dir)
+    }
+    # Start conversion in background
+    background_tasks.add_task(process_pdf_conversion, task_id, str(pdf_path))
+    return {
+        "task_id": task_id,
+        "status": "processing",
+        "message": "PDF conversion started",
+        "check_status_url": f"/api/status/{task_id}"
+    }
+async def process_pdf_conversion(task_id: str, pdf_path: str):
+    """Process PDF conversion in background"""
+    try:
+        # For now, just simulate conversion
+        await asyncio.sleep(2)  # Simulate processing
+        # Create a dummy markdown file
+        output_path = Path(pdf_path).with_suffix('.md')
+        with open(output_path, 'w') as f:
+            f.write(f"# Converted from {Path(pdf_path).name}\n\n")
+            f.write("This is a placeholder conversion. Full MinerU integration coming soon.\n")
+        conversion_tasks[task_id]["status"] = "completed"
+        conversion_tasks[task_id]["result"] = str(output_path)
+    except Exception as e:
+        conversion_tasks[task_id]["status"] = "failed"
+        conversion_tasks[task_id]["error"] = str(e)
+@app.get("/api/status/{task_id}")
+async def get_conversion_status(task_id: str):
+    """Check conversion status"""
+    if task_id not in conversion_tasks:
+        raise HTTPException(status_code=404, detail="Task not found")
+    task = conversion_tasks[task_id]
+    response = {
+        "task_id": task_id,
+        "status": task["status"],
+        "filename": task["filename"]
+    }
+    if task["status"] == "completed":
+        response["download_url"] = f"/api/download/{task_id}"
+    elif task["status"] == "failed":
+        response["error"] = task["error"]
+    return response
+@app.get("/api/download/{task_id}")
+async def download_converted_file(task_id: str):
+    """Download converted markdown file"""
+    if task_id not in conversion_tasks:
+        raise HTTPException(status_code=404, detail="Task not found")
+    task = conversion_tasks[task_id]
+    if task["status"] != "completed":
+        raise HTTPException(status_code=400, detail="Conversion not completed")
+    if not task["result"] or not Path(task["result"]).exists():
+        raise HTTPException(status_code=404, detail="Converted file not found")
+    return FileResponse(
+        task["result"],
+        media_type="text/markdown",
+        filename=Path(task["result"]).name
+    )

test_api_local.py ADDED Viewed

	@@ -0,0 +1,66 @@

+#!/usr/bin/env python3
+"""Test PDF conversion API locally"""
+import requests
+import time
+import sys
+def test_pdf_conversion(pdf_path, api_base_url="http://localhost:7860"):
+    """Test PDF conversion through API"""
+    # 1. Upload PDF
+    print(f"Uploading PDF: {pdf_path}")
+    with open(pdf_path, 'rb') as f:
+        files = {'file': (pdf_path.split('/')[-1], f, 'application/pdf')}
+        response = requests.post(f"{api_base_url}/api/convert", files=files)
+    if response.status_code != 200:
+        print(f"Upload failed: {response.status_code}")
+        print(response.text)
+        return
+    result = response.json()
+    task_id = result['task_id']
+    print(f"Task ID: {task_id}")
+    print(f"Status: {result['status']}")
+    # 2. Check status
+    print("\nChecking conversion status...")
+    while True:
+        response = requests.get(f"{api_base_url}/api/status/{task_id}")
+        if response.status_code != 200:
+            print(f"Status check failed: {response.status_code}")
+            break
+        status = response.json()
+        print(f"Status: {status['status']}")
+        if status['status'] == 'completed':
+            print(f"Download URL: {status['download_url']}")
+            # 3. Download result
+            response = requests.get(f"{api_base_url}{status['download_url']}")
+            if response.status_code == 200:
+                output_file = f"output_{task_id}.md"
+                with open(output_file, 'w') as f:
+                    f.write(response.text)
+                print(f"\nMarkdown saved to: {output_file}")
+                print("\nContent preview:")
+                print(response.text[:500])
+            break
+        elif status['status'] == 'failed':
+            print(f"Conversion failed: {status.get('error', 'Unknown error')}")
+            break
+        time.sleep(1)
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        pdf_path = sys.argv[1]
+    else:
+        pdf_path = "/Users/marcos/Documents/projects/pdf2md/batch-files/test-simple.pdf"
+    # Test on HF Space
+    print("Testing on Hugging Face Space...")
+    test_pdf_conversion(pdf_path, "https://marcosremar2-mineru2.hf.space")