Add application file

DockerFile

@@ -0,0 +1,17 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Expose the port FastAPI runs on
+EXPOSE 8000
+
+# Run FastAPI when the container launches
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

app/main.py

@@ -0,0 +1,21 @@
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse
+from app.ocr import easyocr_ocr
+
+app = FastAPI()
+
+@app.post("/upload/")
+async def upload_image(file: UploadFile = File(...)):
+    try:
+        # Save the uploaded file to a temporary location
+        with open(f"/tmp/{file.filename}", "wb") as buffer:
+            buffer.write(await file.read())
+        
+        # Perform OCR on the saved image
+        formatted_output = easyocr_ocr(f"/tmp/{file.filename}")
+
+        # Return the formatted output
+        return JSONResponse(content={"formatted_output": formatted_output})
+
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)

app/ocr.py

@@ -0,0 +1,56 @@
+import easyocr
+
+def reformat_ocr_result(result):
+    mapping = {
+        "NIK": "NIK : ",
+        "Nama": "Nama : ",
+        "TempatITgl Lahir": "Tempat/Tgl Lahir : ",
+        "Jenis Kelamin": "Jenis Kelamin : ",
+        "GolDarah": "Gol Darah : ",
+        "Alamat": "Alamat : ",
+        "RTIRW": "RT/RW : ",
+        "KelDesa": "Kel/Desa : ",
+        "Kecamatan": "Kecamatan : ",
+        "Agama": "Agama : ",
+        "Status Perkawinan": "Status Perkawinan : ",
+        "Pekerjaan": "Pekerjaan : ",
+        "Kewarganegaraan": "Kewarganegaraan : ",
+        "Berlaku Hingga": "Berlaku Hingga : "
+    }
+    
+    formatted_output = []
+    current_key = None
+    current_value = []
+   
+    for line in result:
+        # Extract the text from each OCR result line
+        text = line.split(' (confidence: ')[0]
+
+        # Check if the text matches any of the keys
+        if any(key in text for key in mapping):
+            # If there's a current key, finalize its value
+            if current_key:
+                formatted_output.append(f"{mapping[current_key]}{' '.join(current_value)}")
+                current_value = []
+
+            # Find the key in the text
+            for key in mapping:
+                if key in text:
+                    current_key = key
+                    break
+        else:
+            if current_key:
+                # Add the text to the current value
+                current_value.append(text)
+    # Finalize the last key-value pair
+    if current_key:
+        formatted_output.append(f"{mapping[current_key]}{' '.join(current_value)}")
+    print(formatted_output)
+    return formatted_output
+
+def easyocr_ocr(image_path):
+    reader = easyocr.Reader(['en'])
+    result = reader.readtext(image_path)
+    result_list = [f"{text} (confidence: {confidence:.4f})" for (bbox, text, confidence) in result]
+    formatted_output = reformat_ocr_result(result_list)
+    return formatted_output

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+easyocr
+pillow