Upload 5 files

BeckUp.py

@@ -0,0 +1,177 @@
+from flask import Flask, request, redirect, flash, session, render_template, url_for
+import os
+import json
+from werkzeug.utils import secure_filename
+import logging
+from utils.error import handle_file_not_found, handle_invalid_file_type, handle_file_processing_error, page_not_found, internal_server_error
+from utils.spacy import Parser_from_model
+from utils.mistral import process_resume_data
+import platform
+from waitress import serve
+
+if platform.system() == "Windows":
+    app = Flask(__name__)
+    app.secret_key = 'your_secret_key'
+    app.config['UPLOAD_FOLDER'] = 'uploads'
+# else:
+#     # For Hugging Face Spaces or other Linux environments
+#     if __name__ != "__main__":
+#     serve(app, host="0.0.0.0", port=7860)
+
+
+# Error handlers
+app.register_error_handler(404, page_not_found)
+app.register_error_handler(500, internal_server_error)
+
+# Allowed extensions
+ALLOWED_EXTENSIONS = {'pdf', 'docx', 'rsf', 'odt', 'png', 'jpg', 'jpeg'}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    uploaded_file = session.get('uploaded_file', None)
+    return render_template('index.html', uploaded_file=uploaded_file)
+
+# @app.route('/upload', methods=['POST'])
+# def upload_file():
+#     if 'file' not in request.files:
+#         flash('No file part')
+#         return redirect(request.url)
+    
+#     file = request.files['file']
+
+#     if file.filename == '':
+#         flash('No selected file')
+#         return redirect(request.url)
+
+#     if file and allowed_file(file.filename):
+#         filename = secure_filename(file.filename)
+#         file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
+#         logging.debug(f"File uploaded: {filename}")
+#         session['uploaded_file'] = filename
+#         flash('File successfully uploaded')
+#         return redirect(url_for('index'))
+#     else:
+#         return handle_invalid_file_type()
+
+# def process_file():
+#     selected_file = session.get('uploaded_file')
+#     if not selected_file:
+#         flash('No file selected for processing')
+#         return redirect(url_for('index'))
+
+#     file_path = os.path.join(app.config['UPLOAD_FOLDER'], selected_file)
+#     if not os.path.exists(file_path):
+#         return handle_file_not_found()
+#     parsed_data = process_resume_data(file_path)
+#     if not parsed_data or 'error' in parsed_data:
+#         return handle_file_processing_error()
+
+#     session['processed_data'] = parsed_data
+#     flash('Data processed successfully')
+#     return redirect(url_for('result'))
+
+@app.route('/upload_and_process', methods=['POST', 'GET'])
+def upload_and_process():
+    if 'file' not in request.files:
+        flash('No file part')
+        return redirect(request.url)
+
+    file = request.files['file']
+
+    if file.filename == '':
+        flash('No selected file')
+        return redirect(request.url)
+
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(file_path)
+        logging.debug(f"File uploaded: {filename}")
+        session['uploaded_file'] = filename
+
+        # Process the file after uploading
+        parsed_data = process_resume_data(file_path)
+        if not parsed_data or 'error' in parsed_data:
+            return handle_file_processing_error()
+
+        session['processed_data'] = parsed_data
+        flash('File uploaded and data processed successfully')
+        return redirect(url_for('result'))
+    else:
+        return handle_invalid_file_type()
+
+
+
+@app.route('/remove_file')
+def remove_file():
+    uploaded_file = session.get('uploaded_file')
+    if uploaded_file:
+        os.remove(os.path.join(app.config['UPLOAD_FOLDER'], uploaded_file))
+        session.pop('uploaded_file', None)
+        flash('File successfully removed')
+    return redirect(url_for('index'))
+
+@app.route('/reset_upload')
+def reset_upload():
+    uploaded_file = session.get('uploaded_file')
+    if uploaded_file:
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], uploaded_file)
+        if os.path.exists(file_path):
+            os.remove(file_path)
+        
+        session.pop('uploaded_file', None)
+    
+    session.pop('processed_data', None)
+    flash('File reset. You can upload a new file.')
+    return redirect(url_for('index'))
+
+# @app.route('/process', methods=['GET', 'POST'])
+# def process_file():
+#     selected_file = session.get('uploaded_file')
+#     if not selected_file:
+#         flash('No file selected for processing')
+#         return redirect(url_for('index'))
+
+#     file_path = os.path.join(app.config['UPLOAD_FOLDER'], selected_file)
+#     if not os.path.exists(file_path):
+#         return handle_file_not_found()
+#     parsed_data = process_resume_data(file_path)
+#     if not parsed_data or 'error' in parsed_data:
+#         return handle_file_processing_error()
+
+#     session['processed_data'] = parsed_data
+#     flash('Data processed successfully')
+#     return redirect(url_for('result'))
+
+@app.route('/loading')
+def loading():
+    selected_file = session.get('uploaded_file')
+    if not selected_file:
+        flash('No file selected for processing')
+        return redirect(url_for('index'))
+
+    file_path = os.path.join(app.config['UPLOAD_FOLDER'], selected_file)
+
+    parsed_data = process_resume_data(file_path)
+    
+    if parsed_data and 'error' not in parsed_data:
+        session['processed_data'] = json.loads(parsed_data)
+        flash('Data processed successfully')
+        return redirect(url_for('result'))
+    else:
+        return handle_file_processing_error()
+
+@app.route('/result')
+def result():
+    processed_data = session.get('processed_data', None)
+    if not processed_data:
+        flash('No data to display. Please upload and process a file.')
+        return redirect(url_for('index'))
+
+    return render_template('result.html', parsed_data=processed_data)
+
+if __name__ == '__main__':
+    app.run(debug=True)

app.py

@@ -0,0 +1,115 @@
+from flask import Flask, request, redirect, flash, session, render_template, url_for
+import os
+import json
+import logging
+from werkzeug.utils import secure_filename
+from utils.error import handle_file_not_found, handle_invalid_file_type, handle_file_processing_error, page_not_found, internal_server_error
+from utils.spacy import Parser_from_model
+from utils.mistral import process_resume_data
+import platform
+from waitress import serve
+
+# Initialize the Flask application
+app = Flask(__name__)
+app.secret_key = 'your_secret_key'
+app.config['UPLOAD_FOLDER'] = 'uploads'
+
+# Allowed file extensions
+ALLOWED_EXTENSIONS = {'pdf', 'docx', 'rsf', 'odt', 'png', 'jpg', 'jpeg'}
+
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+
+# Error handlers
+app.register_error_handler(404, page_not_found)
+app.register_error_handler(500, internal_server_error)
+
+def allowed_file(filename):
+    """Check if the file has an allowed extension."""
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    """Display the index page with the uploaded file information."""
+    uploaded_file = session.get('uploaded_file', None)
+    return render_template('index.html', uploaded_file=uploaded_file)
+
+@app.route('/upload_and_process', methods=['POST'])
+def upload_and_process():
+    """Handle file upload and process the file."""
+    if 'file' not in request.files or request.files['file'].filename == '':
+        flash('No file selected for upload.')
+        return redirect(request.url)
+
+    file = request.files['file']
+    
+    # Check if the file is allowed
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(file_path)
+        logging.debug(f"File uploaded: {filename}")
+        session['uploaded_file'] = filename
+
+        # Process the file after uploading
+        try:
+            parsed_data = process_resume_data(file_path)
+            if not parsed_data or 'error' in parsed_data:
+                flash('An error occurred during file processing.')
+                return redirect(url_for('index'))
+
+            session['processed_data'] = parsed_data
+            flash('File uploaded and data processed successfully.')
+            return redirect(url_for('result'))
+
+        except Exception as e:
+            logging.error(f"File processing error: {str(e)}")
+            flash('An error occurred while processing the file.')
+            return handle_file_processing_error()
+    else:
+        return handle_invalid_file_type()
+
+@app.route('/remove_file', methods=['POST'])
+def remove_file():
+    """Remove the uploaded file and reset the session."""
+    uploaded_file = session.get('uploaded_file')
+    if uploaded_file:
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], uploaded_file)
+        if os.path.exists(file_path):
+            os.remove(file_path)
+        session.pop('uploaded_file', None)
+        flash('File successfully removed.')
+    else:
+        flash('No file to remove.')
+    return redirect(url_for('index'))
+
+@app.route('/reset_upload')
+def reset_upload():
+    """Reset the uploaded file and the processed data."""
+    uploaded_file = session.get('uploaded_file')
+    if uploaded_file:
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], uploaded_file)
+        if os.path.exists(file_path):
+            os.remove(file_path)
+        session.pop('uploaded_file', None)
+
+    session.pop('processed_data', None)
+    flash('File and data reset. You can upload a new file.')
+    return redirect(url_for('index'))
+
+@app.route('/result')
+def result():
+    """Display the processed data result."""
+    processed_data = session.get('processed_data', None)
+    if not processed_data:
+        flash('No data to display. Please upload and process a file.')
+        return redirect(url_for('index'))
+    return render_template('result.html', parsed_data=processed_data)
+
+if __name__ == '__main__':
+    # For Windows development
+    if platform.system() == "Windows":
+        app.run(debug=True)
+    # For Linux or production with Waitress
+    else:
+        serve(app, host="0.0.0.0", port=7860)

app_error.log

@@ -0,0 +1 @@
+2024-09-28 13:31:17,959 ERROR: 404 Error: http://127.0.0.1:5000/favicon.ico

readme

@@ -0,0 +1,146 @@
+_\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\_
+_\\----------- **Resume Parser** ----------\\_
+_\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\_
+
+# Overview:
+This project is a comprehensive Resume Parsing tool built using Python,
+integrating the Mistral-Nemo-Instruct-2407 model for primary parsing.
+If Mistral fails or encounters issues,
+the system falls back to a custom-trained spaCy model to ensure continued functionality.
+The tool is wrapped with a Flask API and has a user interface built using HTML and CSS.
+
+
+# Installation Guide:
+
+1. Create and Activate a Virtual Environment
+    python -m venv venv
+    source venv/bin/activate  # For Linux/Mac
+    # or
+    venv\Scripts\activate  # For Windows
+
+    # NOTE: If the virtual environment (venv) is already created, you can skip the creation step and just activate.
+        - For Linux/Mac:
+            source venv/bin/activate
+        - For Windows:
+            venv\Scripts\activate
+
+2. Install Required Libraries
+    pip install -r requirements.txt
+
+    # Ensure the following dependencies are included:
+    - Flask
+    - spaCy
+    - huggingface_hub
+    - PyMuPDF
+    - python-docx
+    - Tesseract-OCR (for image-based parsing)
+
+3. Set up Hugging Face Token
+    - Add your Hugging Face token to the .env file as:
+    HF_TOKEN=<your_huggingface_token>
+
+
+# File Structure Overview:
+    Mistral_With_Spacy/
+    │
+    ├── Spacy_Models/
+    │   └── ner_model_05_3  # Pretrained spaCy model directory for resume parsing
+    │
+    ├── templates/
+    │   ├── index.html  # UI for file upload
+    │   └── result.html  # Display parsed results in structured JSON
+    │
+    ├── uploads/  # Directory for uploaded resume files
+    │
+    ├── utils/
+    │   ├── mistral.py  # Code for calling Mistral API and handling responses
+    │   ├── spacy.py  # spaCy fallback model for parsing resumes
+    │   ├── error.py  # Error handling utilities
+    │   └── fileTotext.py  # Functions to extract text from different file formats (PDF, DOCX, etc.)
+    │
+    ├── venv/  # Virtual environment
+    │
+    ├── .env  # Environment variables file (contains Hugging Face token)
+    │
+    ├── main.py  # Flask app handling API routes for uploading and processing resumes
+    │
+    └── requirements.txt  # Dependencies required for the project
+
+
+# Program Overview:
+
+    # Mistral Integration (utils/mistral.py)
+        - Mistral API Calls: Uses Hugging Face’s Mistral-Nemo-Instruct-2407 model to parse resumes.
+        - Personal and Professional Extraction: Two functions extract personal and professional information in structured JSON format.
+        - Fallback Mechanism: If Mistral fails, spaCy NER model is used as a fallback.
+
+    # SpaCy Integration (utils/spacy.py)
+        - Custom Trained Model: Uses a spaCy model (ner_model_05_3) trained specifically for resume parsing.
+        - Named Entity Recognition: Extracts key information like Name, Email, Contact, Location, Skills, Experience, etc., from resumes.
+        - Validation: Includes validation for extracted emails and contacts.
+
+    # File Conversion (utils/fileTotext.py)
+       - Text Extraction: Handles different resume formats (PDF, DOCX, ODT, RSF, and images like PNG, JPG, JPEG) and extracts text for further processing.
+          - PDF Files: Uses PyMuPDF to extract text and, if necessary, Tesseract-OCR for image-based PDF content.
+          - DOCX Files: Uses `python-docx` to extract structured text from Word documents.
+          - ODT Files: Uses `odfpy` to extract text from ODT (OpenDocument) files.
+          - RSF Files: Reads plain text from RSF files.
+          - Images (PNG, JPG, JPEG): Uses Tesseract-OCR to extract text from image-based resumes.
+
+       - Hyperlink Extraction: Extracts hyperlinks from PDF files, capturing any embedded URLs during the parsing process.
+
+
+    # Error Handling (utils/error.py)
+        - Handles API response errors, file format errors, and ensures smooth fallbacks without crashing the app.
+
+    # Flask API (main.py)
+        Endpoints:
+        - /upload for uploading resumes.
+        - Displays parsed results in JSON format on the results page.
+        - UI: Simple interface for uploading resumes and viewing the parsing results.
+
+
+# Tree map of your program:
+
+    main.py
+    ├── Handles API side
+    ├── File upload/remove
+    ├── Process resumes
+    └── Show result
+
+    utils
+    ├── fileTotext.py
+    │   └── Converts files to text
+    │       ├── PDF
+    │       ├── DOCX
+    │       ├── RTF
+    │       ├── ODT
+    │       ├── PNG
+    │       ├── JPG
+    │       └── JPEG
+    ├── mistral.py
+    │   ├── Mistral API Calls
+    │   │   └── Uses Mistral-Nemo-Instruct-2407 model
+    │   ├── Personal and Professional Extraction
+    │   │   ├── Extracts personal information
+    │   │   └── Extracts professional information
+    │   └── Fallback Mechanism
+    │       └── Uses spaCy NER model if Mistral fails
+    └── spacy.py
+        ├── Custom Trained Model
+        │   └── Uses spaCy model (ner_model_05_3)
+        ├── Named Entity Recognition
+        │   └── Extracts key information (Name, Email, Contact, etc.)
+        └── Validation
+            └── Validates emails and contacts
+
+
+# References:
+
+- [Flask Documentation](https://flask.palletsprojects.com/)
+- [spaCy Documentation](https://spacy.io/usage)
+- [Hugging Face Hub API](https://huggingface.co/docs/huggingface_hub/index)
+- [PyMuPDF (MuPDF) Documentation](https://pymupdf.readthedocs.io/en/latest/)
+- [python-docx Documentation](https://python-docx.readthedocs.io/en/latest/)
+- [Tesseract OCR Documentation](https://github.com/tesseract-ocr/tesseract)
+- [Virtual Environments in Python](https://docs.python.org/3/tutorial/venv.html)

requirements.txt

@@ -0,0 +1,148 @@
+alembic==1.13.2
+amqp==5.2.0
+annotated-types==0.7.0
+attrs==24.2.0
+bcrypt==4.2.0
+blinker==1.8.2
+blis==0.7.11
+cachetools==5.5.0
+catalogue==2.0.10
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.19.0
+colorama==0.4.6
+confection==0.1.5
+croniter==3.0.3
+cryptography==43.0.1
+cymem==2.0.8
+debtcollector==3.0.0
+decorator==5.1.1
+defusedxml==0.7.1
+dnspython==2.6.1
+dogpile.cache==1.3.3
+eventlet==0.37.0
+fasteners==0.19
+filelock==3.16.0
+Flask==3.0.3
+fsspec==2024.9.0
+futurist==3.0.0
+greenlet==3.1.0
+huggingface-hub==0.24.7
+idna==3.8
+importlib_metadata==8.5.0
+iso8601==2.1.0
+itsdangerous==2.2.0
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+keystoneauth1==5.8.0
+keystonemiddleware==10.7.1
+kombu==5.4.1
+langcodes==3.4.0
+language_data==1.2.0
+logutils==0.3.5
+lxml==5.3.0
+Mako==1.3.5
+marisa-trie==1.2.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mistral==18.0.1
+mistral-lib==3.0.0
+msgpack==1.1.0
+murmurhash==1.0.10
+netaddr==1.3.0
+netifaces==0.11.0
+networkx==3.3
+numpy==1.26.4
+odfpy==1.4.1
+os-service-types==1.7.0
+oslo.cache==3.8.0
+oslo.concurrency==6.1.0
+oslo.config==9.6.0
+oslo.context==5.6.0
+oslo.db==16.0.0
+oslo.i18n==6.4.0
+oslo.log==6.1.2
+oslo.messaging==14.9.0
+oslo.metrics==0.9.0
+oslo.middleware==6.2.0
+oslo.policy==4.4.0
+oslo.serialization==5.5.0
+oslo.service==3.5.0
+oslo.utils==7.3.0
+osprofiler==4.2.0
+packaging==24.1
+paramiko==3.4.1
+Paste==3.10.1
+PasteDeploy==3.1.0
+pbr==6.1.0
+pdf2image==1.17.0
+pecan==1.5.1
+pillow==10.4.0
+ply==3.11
+preshed==3.0.9
+prettytable==3.11.0
+prometheus_client==0.20.0
+pycadf==3.1.1
+pycparser==2.22
+pydantic==2.9.1
+pydantic_core==2.23.3
+Pygments==2.18.0
+PyJWT==2.9.0
+PyMuPDF==1.24.10
+PyMuPDFb==1.24.10
+PyNaCl==1.5.0
+pyparsing==3.1.4
+pytesseract==0.3.13
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+python-dotenv==1.0.1
+python-keystoneclient==5.5.0
+pytz==2024.2
+PyYAML==6.0.2
+referencing==0.35.1
+repoze.lru==0.7
+requests==2.32.3
+rfc3986==2.0.0
+rich==13.8.1
+Routes==2.5.1
+rpds-py==0.20.0
+setuptools==74.1.2
+shellingham==1.5.4
+simplegeneric==0.8.1
+six==1.16.0
+smart-open==7.0.4
+spacy==3.8.0
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+SQLAlchemy==2.0.34
+srsly==2.4.8
+statsd==4.0.1
+stevedore==5.3.0
+tenacity==9.0.0
+testresources==2.0.1
+testscenarios==0.5.0
+testtools==2.7.2
+thinc==8.2.5
+tooz==6.3.0
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.3
+vine==5.1.0
+voluptuous==0.15.2
+waitress==3.0.0
+wasabi==1.1.3
+wcwidth==0.2.13
+weasel==0.4.1
+WebOb==1.8.8
+Werkzeug==3.0.4
+wrapt==1.16.0
+WSME==0.12.1
+yappi==1.6.0
+yaql==3.0.0
+zipp==3.20.1