app.py

import os
import tempfile
import re
import streamlit as st
import docx
import textract

#####################################
# Function: Extract Text from File
#####################################
def extract_text_from_file(file_obj):
    """
    Extract text from .doc and .docx files.
    Returns the extracted text or an error message if extraction fails.
    """
    filename = file_obj.name
    ext = os.path.splitext(filename)[1].lower()
    text = ""

    if ext == ".docx":
        try:
            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":
        try:
            # textract requires a file name; save the file temporarily.
            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: Extract Basic Resume Information
#####################################
def extract_basic_resume_info(text):
    """
    Parse the extracted text to extract/summarize:
    - Name
    - Age
    - Job Experience (capturing the block under the "experience" section)
    - Skills
    - Education

    Returns a dictionary with the extracted elements.
    """
    info = {
        "Name": None,
        "Age": None,
        "Job Experience": None,
        "Skills": None,
        "Education": None,
    }

    # Extract Name (e.g., "Name: John Doe" or from heuristics)
    name_match = re.search(r"[Nn]ame[:\-]\s*([A-Za-z\s,]+)", text)
    if name_match:
        info["Name"] = name_match.group(1).strip()
    else:
        # Heuristic: Assume the first line or a line with two or three capitalized words is the candidate's name.
        potential_names = re.findall(r"\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+){1,2}\b", text)
        if potential_names:
            info["Name"] = potential_names[0]

    # Extract Age (e.g., "Age: 28")
    age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,3})", text)
    if age_match:
        info["Age"] = age_match.group(1)

    # Extract Job Experience using the "experience" section.
    # This regex captures everything after the word "experience" until the next section heading (e.g., "additional information" or "skills")
    experience_match = re.search(r"experience\s*(.*?)(?:\n\s*\n|additional information|$)", text, re.IGNORECASE | re.DOTALL)
    if experience_match:
        # Clean up the extracted block by removing any extra whitespace or newlines.
        job_experience = experience_match.group(1).strip()
        info["Job Experience"] = " ".join(job_experience.split())
    else:
        # Fallback if a labeled section isn't found.
        exp_match = re.search(r"(\d+)\s+(years|yrs)\s+(?:of\s+)?experience", text, re.IGNORECASE)
        if exp_match:
            info["Job Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"

    # Extract Skills (e.g., "Skills: Python, Java, SQL")
    skills_match = re.search(r"(Skills|Technical Skills)[:\-]\s*(.+)", text, re.IGNORECASE)
    if skills_match:
        skills_str = skills_match.group(2).strip()
        info["Skills"] = skills_str.rstrip(".")

    # Extract Education (e.g., "Education: ...")
    edu_match = re.search(r"education\s*(.*?)(?:\n\s*\n|experience|$)", text, re.IGNORECASE | re.DOTALL)
    if edu_match:
        education_block = edu_match.group(1).strip()
        info["Education"] = " ".join(education_block.split())
    else:
        # Fallback: search for lines starting with common degree words.
        edu_match = re.search(r"(Bachelor|Master|B\.Sc|M\.Sc|Ph\.D)[^\n]+", text)
        if edu_match:
            info["Education"] = edu_match.group(0)

    return info

#####################################
# Function: Summarize Basic Info into a Paragraph
#####################################
def summarize_basic_info(info):
    """
    Combine the extracted resume elements into a concise summary paragraph.
    """
    parts = []

    if info.get("Name"):
        parts.append(f"Candidate {info['Name']}")
    else:
        parts.append("The candidate")
    
    if info.get("Age"):
        parts.append(f"aged {info['Age']}")
    
    if info.get("Job Experience"):
        parts.append(f"with job experience: {info['Job Experience']}")
    
    if info.get("Skills"):
        parts.append(f"skilled in {info['Skills']}")
    
    if info.get("Education"):
        parts.append(f"and educated in {info['Education']}")
    
    summary_paragraph = ", ".join(parts) + "."
    return summary_paragraph

#####################################
# Main Resume Processing Logic
#####################################
def process_resume(file_obj):
    if file_obj is None:
        return None, None
    # Extract the full resume text.
    resume_text = extract_text_from_file(file_obj)
    # Extract basic info from the text.
    basic_info = extract_basic_resume_info(resume_text)
    # Create a summary paragraph from the basic info.
    summary_paragraph = summarize_basic_info(basic_info)
    return resume_text, summary_paragraph

#####################################
# Streamlit Interface
#####################################
st.title("Resume Basic Information Summary")
st.markdown("""
Upload your resume file in **.doc** or **.docx** format. The app extracts key details such as name, age, job experience, skills, 
and education, then summarizes them into a single paragraph.
""")

uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])

if st.button("Process Resume"):
    if uploaded_file is None:
        st.error("Please upload a file first.")
    else:
        with st.spinner("Processing resume..."):
            resume_text, summary_paragraph = process_resume(uploaded_file)

        st.subheader("Summary Paragraph")
        st.markdown(summary_paragraph)

        st.subheader("Full Extracted Resume Text")
        st.text_area("", resume_text, height=300)