Update app.py

app.py

@@ -5,12 +5,12 @@ import csv
 import os
 import cv2
 import numpy as np
-import pandas as pd
 import easyocr
 import keras_ocr
 from paddleocr import PaddleOCR
 from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
 import torch.nn.functional as F  # Added for softmax
+from save_results import save_results_to_repo  # Import the new save function
 
 # Paths
 MODEL_PATH = "./distilbert_spam_model"
@@ -74,33 +74,11 @@ def generate_ocr(method, img):
     label_map = {0: "Not Spam", 1: "Spam"}
     label = label_map[prediction]
 
-    # Save results
-    save_results(text_output, label)
+    # Save results using the external save function
+    save_results_to_repo(text_output, label)
 
     return text_output, label
 
-# Save extracted text to JSON & CSV
-def save_results(text, label):
-    data = {"text": text, "label": label}
-
-    # Save to JSON
-    if not os.path.exists(RESULTS_JSON):
-        with open(RESULTS_JSON, "w") as f:
-            json.dump([], f)
-    with open(RESULTS_JSON, "r+") as f:
-        content = json.load(f)
-        content.append(data)
-        f.seek(0)
-        json.dump(content, f, indent=4)
-
-    # Save to CSV
-    file_exists = os.path.exists(RESULTS_CSV)
-    with open(RESULTS_CSV, "a", newline="") as f:
-        writer = csv.DictWriter(f, fieldnames=["text", "label"])
-        if not file_exists:
-            writer.writeheader()
-        writer.writerow(data)
-
 # Gradio Interface
 image_input = gr.Image()
 method_input = gr.Radio(["PaddleOCR", "EasyOCR", "KerasOCR"], value="PaddleOCR")