UI and backend for basic OCR functionality

backend/generate_tests.py

@@ -0,0 +1,20 @@
+from reportlab.pdfgen import canvas
+from PIL import Image, ImageDraw
+
+def create_pdf(filename, text):
+    c = canvas.Canvas(filename)
+    c.drawString(100, 750, text)
+    c.save()
+    print(f"Created {filename}")
+
+def create_image(filename, text):
+    img = Image.new('RGB', (400, 100), color = (255, 255, 255))
+    d = ImageDraw.Draw(img)
+    # Default font is usually tiny, but readable by tesseract
+    d.text((10,10), text, fill=(0,0,0))
+    img.save(filename)
+    print(f"Created {filename}")
+
+if __name__ == "__main__":
+    create_pdf("test_ocr.pdf", "Hello World PDF OCR")
+    create_image("test_ocr.png", "Hello World Image OCR")

backend/main.py

@@ -0,0 +1,105 @@
+import io
+from typing import Optional
+from fastapi import FastAPI, File, UploadFile, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from pypdf import PdfReader
+import pytesseract
+from PIL import Image
+
+app = FastAPI()
+
+# CORS configuration
+origins = [
+    "http://localhost",
+    "http://localhost:3000",
+    "http://localhost:5173", # Vite default
+    "http://localhost:4200", # Angular default
+    "http://127.0.0.1:4200",
+]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Models
+class LoginRequest(BaseModel):
+    username: str
+    password: str
+
+class LoginResponse(BaseModel):
+    token: str
+    message: str
+
+class NERResponse(BaseModel):
+    text: str
+
+# 1. User Login Module (Dummy)
+@app.post("/api/login", response_model=LoginResponse)
+async def login(request: LoginRequest):
+    if request.username == "admin" and request.password == "admin":
+        return LoginResponse(token="dummy-jwt-token-123", message="Login Successful")
+    raise HTTPException(status_code=401, detail="Invalid credentials")
+
+# 2. OCR Module
+def extract_text_from_pdf(file_bytes: bytes) -> str:
+    try:
+        reader = PdfReader(io.BytesIO(file_bytes))
+        text = ""
+        for page in reader.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+        return text.strip()
+    except Exception as e:
+        print(f"Error reading PDF: {e}")
+        return ""
+
+def extract_text_from_image(file_bytes: bytes) -> str:
+    try:
+        image = Image.open(io.BytesIO(file_bytes))
+        text = pytesseract.image_to_string(image)
+        return text.strip()
+    except Exception as e:
+        print(f"Error reading Image: {e}")
+        return ""
+
+from pdf2image import convert_from_bytes
+
+# ... (imports)
+
+@app.post("/api/ocr/extract", response_model=NERResponse)
+async def extract_text(file: UploadFile = File(...)):
+    content = await file.read()
+    filename = file.filename.lower()
+    
+    extracted_text = ""
+    
+    if filename.endswith(".pdf"):
+        # Try text extraction first
+        extracted_text = extract_text_from_pdf(content)
+        
+        # If text is empty, it might be a scanned PDF. 
+        if not extracted_text.strip():
+             try:
+                 images = convert_from_bytes(content)
+                 for i, image in enumerate(images):
+                     page_text = pytesseract.image_to_string(image)
+                     extracted_text += f"\n--- Page {i+1} ---\n{page_text}"
+             except Exception as e:
+                 extracted_text = f"Error processing Scanned PDF: {str(e)}\n\n(Hint: Ensure 'poppler' is installed on your system. Run 'brew install poppler')"
+
+    elif filename.endswith((".png", ".jpg", ".jpeg", ".tiff", ".bmp")):
+        extracted_text = extract_text_from_image(content)
+    else:
+        raise HTTPException(status_code=400, detail="Unsupported file type")
+    
+    return NERResponse(text=extracted_text)
+
+@app.get("/")
+def read_root():
+    return {"message": "OCR Backend API is running"}

backend/requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+python-multipart
+pypdf
+pytesseract
+Pillow

backend/test.txt

@@ -0,0 +1 @@
+This is a test PDF content

backend/test_ocr.pdf

@@ -0,0 +1,68 @@
+%PDF-1.3
+%<25><><EFBFBD><EFBFBD> ReportLab Generated PDF document (opensource)
+1 0 obj
+<<
+/F1 2 0 R
+>>
+endobj
+2 0 obj
+<<
+/BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font
+>>
+endobj
+3 0 obj
+<<
+/Contents 7 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 6 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+4 0 obj
+<<
+/PageMode /UseNone /Pages 6 0 R /Type /Catalog
+>>
+endobj
+5 0 obj
+<<
+/Author (anonymous) /CreationDate (D:20260121205329+05'00') /Creator (anonymous) /Keywords () /ModDate (D:20260121205329+05'00') /Producer (ReportLab PDF Library - \(opensource\)) 
+  /Subject (unspecified) /Title (untitled) /Trapped /False
+>>
+endobj
+6 0 obj
+<<
+/Count 1 /Kids [ 3 0 R ] /Type /Pages
+>>
+endobj
+7 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 115
+>>
+stream
+GapQh0E=F,0U\H3T\pNYT^QKk?tc>IP,;W#U1^23ihPEM_?CW4KISi90MjG^2,FS#<RC5+c,n(/#gY0H8Pob4EDu@N%an;^a\iDl!bkQj!W^(m'ef~>endstream
+endobj
+xref
+0 8
+0000000000 65535 f 
+0000000061 00000 n 
+0000000092 00000 n 
+0000000199 00000 n 
+0000000402 00000 n 
+0000000470 00000 n 
+0000000731 00000 n 
+0000000790 00000 n 
+trailer
+<<
+/ID 
+[<6da718d498e92fec48910ff2674542d2><6da718d498e92fec48910ff2674542d2>]
+% ReportLab generated PDF document -- digest (opensource)
+
+/Info 5 0 R
+/Root 4 0 R
+/Size 8
+>>
+startxref
+995
+%%EOF