Spaces:
Sleeping
Sleeping
| import os | |
| import tempfile | |
| import streamlit as st | |
| from transformers import pipeline | |
| import docx | |
| import textract | |
| ##################################### | |
| # Summarization Pipeline Setup | |
| ##################################### | |
| def load_summarization_pipeline(): | |
| try: | |
| summarizer = pipeline("summarization", model="recogna-nlp/ptt5-base-summ-xlsum") | |
| return summarizer | |
| except Exception as e: | |
| st.error(f"Error loading summarization model: {e}") | |
| st.stop() | |
| summarizer = load_summarization_pipeline() | |
| st.write("Summarization model loaded successfully!") | |
| ##################################### | |
| # Function to Extract Text from File | |
| ##################################### | |
| def extract_text_from_file(file_obj): | |
| """ | |
| Extract text from .txt, .docx, and .doc files. | |
| """ | |
| filename = file_obj.name | |
| ext = os.path.splitext(filename)[1].lower() | |
| text = "" | |
| if ext == ".txt": | |
| # For text files, decode the byte stream into a string. | |
| try: | |
| text = file_obj.read().decode("utf-8") | |
| except Exception as e: | |
| text = f"Error reading text file: {e}" | |
| elif ext == ".docx": | |
| try: | |
| # Use python-docx to read .docx files. | |
| document = docx.Document(file_obj) | |
| text = "\n".join([para.text for para in document.paragraphs]) | |
| except Exception as e: | |
| text = f"Error processing DOCX file: {e}" | |
| elif ext == ".doc": | |
| # For .doc files, use textract. textract expects a filename, so save temporarily. | |
| try: | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp: | |
| tmp.write(file_obj.read()) | |
| tmp.flush() | |
| tmp_filename = tmp.name | |
| text = textract.process(tmp_filename).decode("utf-8") | |
| except Exception as e: | |
| text = f"Error processing DOC file: {e}" | |
| finally: | |
| try: | |
| os.remove(tmp_filename) | |
| except Exception: | |
| pass | |
| else: | |
| text = "Unsupported file type." | |
| return text | |
| ##################################### | |
| # Function to Summarize Extracted Text | |
| ##################################### | |
| def summarize_text(text): | |
| """ | |
| Summarize the given text using the summarization pipeline. | |
| Adjust max_length and min_length as needed. | |
| """ | |
| if not text.strip(): | |
| return "No text available to summarize." | |
| try: | |
| # Note: The summarization pipeline can have limitations on text length. | |
| # If you face issues with long documents, consider summarizing in chunks. | |
| summary = summarizer(text, max_length=150, min_length=40, do_sample=False) | |
| return summary[0]["summary_text"] | |
| except Exception as e: | |
| return f"Error during summarization: {e}" | |
| ##################################### | |
| # Main Processing Logic | |
| ##################################### | |
| def process_resume(file_obj): | |
| if file_obj is None: | |
| return None, None | |
| resume_text = extract_text_from_file(file_obj) | |
| summary_text = summarize_text(resume_text) | |
| return resume_text, summary_text | |
| ##################################### | |
| # Streamlit Interface | |
| ##################################### | |
| st.title("Resume Summarization App") | |
| st.markdown( | |
| """ | |
| Upload your resume file — supported formats: **.doc**, **.docx**, and **.txt**. | |
| The app will extract the text content from your resume and generate a summarization. | |
| """ | |
| ) | |
| uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx", "txt"]) | |
| if st.button("Summarize Resume"): | |
| if uploaded_file is None: | |
| st.error("Please upload a file first.") | |
| else: | |
| with st.spinner("Processing..."): | |
| resume_text, summary_text = process_resume(uploaded_file) | |
| st.subheader("Extracted Resume Text") | |
| st.text_area("", resume_text, height=250) | |
| st.subheader("Summarized Resume") | |
| st.text_area("", summary_text, height=150) |