Nassira/completeness

1import streamlit as st2from PIL import Image3import json4import logging5import tempfile6import os7from cv_analyzer import analyze_cv8from ocr_utils import extract_text_aws, extract_text_doctr, extract_text_easyocr, extract_text_paddleocr, load_models, combine_ocr_results, detect_language9from config import weights10from spelling_grammar_checker import evaluate_cv_text11from personal_info_extractor import analyze_personal_info12 13# Configure logging14logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')15 16def main():17    st.title("CV Text Extraction and Analysis")18    uploaded_file = st.file_uploader("Choose a CV image file", type=["png", "jpg", "jpeg"])19 20    if uploaded_file is not None:21        image = Image.open(uploaded_file)22        with st.spinner('Processing CV...'):23            try:24                # Save the uploaded file temporarily25                with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(uploaded_file.name)[1]) as temp_file:26                    temp_file.write(uploaded_file.getvalue())27                    temp_file_path = temp_file.name28 29                # Extract text using AWS30                aws_results = extract_text_aws(uploaded_file.getvalue())31                32                # Detect language33                sample_text = ' '.join([item[0] for item in aws_results[:10]])34                detected_language = detect_language(sample_text)35                36                # Load OCR models37                doctr_model, easyocr_reader, paddleocr_reader = load_models(detected_language)38                39                if doctr_model is None or easyocr_reader is None or paddleocr_reader is None:40                    st.error("Failed to load OCR models. Please check the logs for details.")41                    return42 43                # Extract text using different OCR methods44                results = {45                    "aws": aws_results,46                    "doctr": extract_text_doctr(image, doctr_model),47                    "easyocr": extract_text_easyocr(image, easyocr_reader),48                    "paddleocr": extract_text_paddleocr(image, paddleocr_reader),49                }50                51                # Combine OCR results52                combined_text = combine_ocr_results(results, weights)53                54                # Analyze CV (including completeness check)55                cv_analysis = analyze_cv(temp_file_path)56                57                # Analyze personal information58                personal_info = analyze_personal_info(temp_file_path)59                60                # Evaluate spelling and grammar61                spelling_grammar_result = evaluate_cv_text(temp_file_path)62                63                # Display results64                st.subheader("Extracted Text")65                st.text_area("", combined_text, height=300)66                67                st.subheader("Detected CV Sections")68                st.write(cv_analysis["present_sections"])69                70                st.subheader("CV Completeness Analysis")71                completeness = cv_analysis["completeness_analysis"]72                for section in completeness["sections"]:73                    st.write(f"**{section['name']}**")74                    for element in section['elements']:75                        status = "✅" if element['exists'] else "❌"76                        st.write(f"{status} {element['name']} (Score: {element['score']})")77                    st.write("---")78                79                st.subheader("Total Completeness Score")80                st.write(f"{completeness['score_of_completeness']:.2f} / 10")81                82                st.subheader("Personal Information")83                st.write(f"Email: {personal_info['email']}")84                st.write(f"Phone: {personal_info['phone']}")85                st.write(f"City: {personal_info['city']}")86                st.write(f"Country: {personal_info['country']}")87                88                st.subheader("Personal Information Score")89                st.write(personal_info["score_personal_information"])90                91                st.subheader("Spelling and Grammar")92                st.write(f"Error percentage: {spelling_grammar_result['error_percentage']:.2f}%")93                st.write(f"Score: {spelling_grammar_result['score']}")94                95                st.subheader("Total Score")96                total_score = (97                    completeness['score_of_completeness'] +98                    personal_info["score_personal_information"] +99                    spelling_grammar_result["score"]100                )101                st.write(f"{total_score:.2f}")102                103                # Clean up the temporary file104                os.unlink(temp_file_path)105            106            except Exception as e:107                logging.error(f"Error in main processing: {str(e)}", exc_info=True)108                st.error(f"An error occurred during processing: {str(e)}")109 110if __name__ == "__main__":111    main()