Update app.py

app.py

@@ -1,138 +1,37 @@
-'''import streamlit as st
-from ocr_utils import initialize_reader, read_text_from_image, join_extracted_text
-
-def main():
-    """Main function to handle Streamlit application logic."""
-
-    # Initialize OCR reader
-    reader = initialize_reader()
-
-    # Streamlit app setup
-    st.title("OCR and Keyword Search Application")
-    st.write("Upload an image containing Hindi and English text to extract and search within the text.")
-
-    # File uploader and image display
-    uploaded_file = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"])
-    if uploaded_file is not None:
-        image = Image.open(uploaded_file)
-        st.image(image, caption='Uploaded Image', use_column_width=True)  
-  
-
-
-    # Keyword input and text extraction/highlighting
-    keyword = st.text_input("Enter Keyword to Search")
-
-    if uploaded_file is not None:
-        try:
-            extracted_text = read_text_from_image(uploaded_file.name, reader)
-            full_text = join_extracted_text(extracted_text)
-
-            st.subheader("Extracted Text")
-            st.write(full_text)
-
-            if keyword:
-                highlighted_text = full_text.replace(keyword, f"<mark>{keyword}</mark>")
-                st.subheader("Highlighted Search Results")
-                st.markdown(highlighted_text, unsafe_allow_html=True)
-            else:
-                st.subheader("Highlighted Search Results")
-                st.write("No keyword entered for highlighting.")
-        except FileNotFoundError as e:
-            st.error(str(e))
-
-if __name__ == "__main__":
-    main()
-import streamlit as st
-from PIL import Image
-from ocr_utils import initialize_reader, read_text_from_image, join_extracted_text
-
-
-def main():
-    """Main function to handle Streamlit application logic."""
-
-    # Initialize OCR reader
-    reader = initialize_reader()
-
-    # Streamlit app setup
-    st.title("OCR and Keyword Search Application")
-    st.write("Upload an image containing Hindi and English text to extract and search within the text.")
-
-    # File uploader and image display
-    uploaded_file = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"])
-    if uploaded_file is not None:
-        image = Image.open(uploaded_file)
-        st.image(image, caption="Uploaded Image", use_column_width=True)  # Corrected caption
-
-        # Keyword input and text extraction/highlighting
-        keyword = st.text_input("Enter Keyword to Search")
-
-        if uploaded_file is not None:
-            try:
-                extracted_text = read_text_from_image(uploaded_file.name, reader)
-                full_text = join_extracted_text(extracted_text)
-
-                st.subheader("Extracted Text")
-                st.write(full_text)
-
-                if keyword:
-                    highlighted_text = full_text.replace(keyword, f"<mark>{keyword}</mark>")
-                    st.subheader("Highlighted Search Results")
-                    st.markdown(highlighted_text, unsafe_allow_html=True)
-                else:
-                    st.subheader("Highlighted Search Results")
-                    st.write("No keyword entered for highlighting.")
-            except FileNotFoundError as e:
-                st.error(str(e))
-
-
-if __name__ == "__main__":
-    main()'''
 import streamlit as st
 from PIL import Image
-from ocr_utils import initialize_reader, read_text_from_image, join_extracted_text
-
-def main():
-    """Main function to handle Streamlit application logic."""
+from ocr_utils import extract_text
 
-    # Initialize OCR reader
-    reader = initialize_reader()
+# Streamlit application title
+st.title("OCR and Keyword Search Application")
+st.write("Upload an image containing Hindi and English text to extract and search within the text.")
 
-    # Streamlit app setup
-    st.title("OCR and Keyword Search Application")
-    st.write("Upload an image containing Hindi and English text to extract and search within the text.")
+# File uploader for image
+uploaded_file = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"])
 
-    # File uploader and image display
-    uploaded_file = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"])
-    if uploaded_file is not None:
-        image = Image.open(uploaded_file.name)
-        st.image(image, caption="Uploaded Image", use_column_width=True)
+if uploaded_file is not None:
+    # Open the uploaded image using PIL
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image', use_column_width=True)
 
-        # Print the file path for debugging
-        print("File path:", uploaded_file.name)
+    # Convert the image to a NumPy array
+    image_np = np.array(image)
 
-        # Keyword input and text extraction/highlighting
-        keyword = st.text_input("Enter Keyword to Search")
+    # Perform OCR on the uploaded image using the utility function
+    full_text = extract_text(image_np)
 
-        if uploaded_file is not None:
-            try:
-                extracted_text = read_text_from_image(uploaded_file.name, reader)
-                full_text = join_extracted_text(extracted_text)
-
-                st.subheader("Extracted Text")
-                st.write(full_text)
-
-                if keyword:
-                    highlighted_text = full_text.replace(keyword, f"<mark>{keyword}</mark>")
-                    st.subheader("Highlighted Search Results")
-                    st.markdown(highlighted_text, unsafe_allow_html=True)
-                else:
-                    st.subheader("Highlighted Search Results")
-                    st.write("No keyword entered for highlighting.")
-            except FileNotFoundError as e:
-                st.error(f"Image file not found: {str(e)}")
-            except Exception as e:  # Catch other potential exceptions
-                st.error(f"An error occurred: {str(e)}")
+    # Display the extracted text
+    st.subheader("Extracted Text")
+    st.write(full_text)
 
+    # Text input for keyword search
+    keyword = st.text_input("Enter Keyword to Search")
 
-if __name__ == "__main__":
-    main()
+    # Highlight the keyword in the extracted text
+    if keyword:
+        highlighted_text = full_text.replace(keyword, f"<mark>{keyword}</mark>")
+        st.subheader("Highlighted Search Results")
+        st.markdown(highlighted_text, unsafe_allow_html=True)
+    else:
+        st.subheader("Highlighted Search Results")
+        st.write("No keyword entered for highlighting.")