Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import os | |
| import json | |
| def is_new_file_upload(uploaded_file): | |
| if 'last_uploaded_file' in st.session_state: | |
| # Check if the newly uploaded file is different from the last one | |
| if (uploaded_file.name != st.session_state.last_uploaded_file['name'] or | |
| uploaded_file.size != st.session_state.last_uploaded_file['size']): | |
| st.session_state.last_uploaded_file = {'name': uploaded_file.name, 'size': uploaded_file.size} | |
| # st.write("A new src image file has been uploaded.") | |
| return True | |
| else: | |
| # st.write("The same src image file has been re-uploaded.") | |
| return False | |
| else: | |
| # st.write("This is the first file upload detected.") | |
| st.session_state.last_uploaded_file = {'name': uploaded_file.name, 'size': uploaded_file.size} | |
| return True | |
| big_text = """ | |
| <div style='text-align: center;'> | |
| <h1 style='font-size: 30x;'>Knowledge Extraction 1</h1> | |
| </div> | |
| """ | |
| # Display the styled text | |
| st.markdown(big_text, unsafe_allow_html=True) | |
| uploaded_json_file = st.file_uploader("Upload a pre-processed file", | |
| type=['json']) | |
| st.markdown( | |
| f'<a href="https://ikmtechnology.github.io/ikmtechnology/untethered_extracted_paragraphs.json" target="_blank">Sample 1 download and then upload to above</a>', | |
| unsafe_allow_html=True) | |
| if uploaded_json_file is not None: | |
| if is_new_file_upload(uploaded_json_file): | |
| print("is new file uploaded") | |
| save_path = './uploaded_files' | |
| if not os.path.exists(save_path): | |
| os.makedirs(save_path) | |
| with open(os.path.join(save_path, uploaded_json_file.name), "wb") as f: | |
| f.write(uploaded_json_file.getbuffer()) # Write the file to the specified location | |
| st.success(f'Saved file temp_{uploaded_json_file.name} in {save_path}') | |
| st.session_state.uploaded_path=os.path.join(save_path, uploaded_json_file.name) | |
| # st.session_state.page_count = utils.get_pdf_page_count(st.session_state.uploaded_pdf_path) | |
| # print("page_count=",st.session_state.page_count) | |
| content = uploaded_json_file.read() | |
| try: | |
| data = json.loads(content) | |
| #print(data) | |
| # Check if the parsed data is a dictionary | |
| if isinstance(data, list): | |
| # Count the number of top-level elements | |
| st.session_state.list_count = len(data) | |
| st.write(f'The number of elements at the top level of the hierarchy: {st.session_state.list_count }') | |
| else: | |
| st.write('The JSON content is not a dictionary.') | |
| except json.JSONDecodeError: | |
| st.write('Invalid JSON file.') | |
| st.rerun() | |
| if 'list_count' in st.session_state: | |
| st.write(f'The number of elements at the top level of the hierarchy: {st.session_state.list_count }') |