import os
import io
import streamlit as st
import docx
import docx2txt
import tempfile
import time
import re
import pandas as pd
from functools import lru_cache

# Handle imports
try:
    from transformers import pipeline
    has_pipeline = True
except ImportError:
    from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForSeq2SeqLM
    import torch
    has_pipeline = False
    st.warning("Using basic transformers functionality instead of pipeline API")

# Set page title and hide sidebar
st.set_page_config(page_title="Resume-Job Fit Analyzer", initial_sidebar_state="collapsed")
st.markdown("""<style>[data-testid="collapsedControl"] {display: none;}section[data-testid="stSidebar"] {display: none;}</style>""", unsafe_allow_html=True)

#####################################
# Preload Models & Helper Functions
#####################################
@st.cache_resource(show_spinner=True)
def load_models():
    """Load models at startup"""
    with st.spinner("Loading AI models... This may take a minute on first run."):
        models = {}
        
        # Load summarization model
        if has_pipeline:
            models['summarizer'] = pipeline("summarization", model="Falconsai/text_summarization", max_length=100, truncation=True)
        else:
            try:
                models['summarizer_model'] = AutoModelForSeq2SeqLM.from_pretrained("Falconsai/text_summarization")
                models['summarizer_tokenizer'] = AutoTokenizer.from_pretrained("Falconsai/text_summarization")
            except Exception as e:
                st.error(f"Error loading summarization model: {e}")
                models['summarizer_model'] = models['summarizer_tokenizer'] = None
        
        # Load evaluation model
        if has_pipeline:
            models['evaluator'] = pipeline("sentiment-analysis", model="CR7CAD/RobertaFinetuned")
        else:
            try:
                models['evaluator_model'] = AutoModelForSequenceClassification.from_pretrained("CR7CAD/RobertaFinetuned")
                models['evaluator_tokenizer'] = AutoTokenizer.from_pretrained("CR7CAD/RobertaFinetuned")
            except Exception as e:
                st.error(f"Error loading sentiment model: {e}")
                models['evaluator_model'] = models['evaluator_tokenizer'] = None
        
        return models

def summarize_text(text, models, max_length=100):
    """Summarize text using available models with fallbacks"""
    # Truncate input to prevent issues with long texts
    input_text = text[:1024]
    
    # Try pipeline first
    if has_pipeline and 'summarizer' in models:
        try:
            return models['summarizer'](input_text)[0]['summary_text']
        except Exception as e:
            st.warning(f"Error in pipeline summarization: {e}")
    
    # Try manual model
    if 'summarizer_model' in models and 'summarizer_tokenizer' in models and models['summarizer_model']:
        try:
            tokenizer = models['summarizer_tokenizer']
            model = models['summarizer_model']
            inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)
            summary_ids = model.generate(inputs.input_ids, max_length=max_length, min_length=30, num_beams=4, early_stopping=True)
            return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
        except Exception as e:
            st.warning(f"Error in manual summarization: {e}")
    
    # Fallback to basic summarization
    return basic_summarize(text, max_length)

def basic_summarize(text, max_length=100):
    """Basic extractive text summarization"""
    sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
    
    # Score and filter sentences
    scored_sentences = []
    for i, sentence in enumerate(sentences):
        if len(sentence.split()) >= 4:
            score = 1.0 / (i + 1) - (0.01 * max(0, len(sentence.split()) - 20))
            scored_sentences.append((score, sentence))
    
    # Get top sentences
    scored_sentences.sort(reverse=True)
    summary_sentences = []
    current_length = 0
    
    for _, sentence in scored_sentences:
        if current_length + len(sentence.split()) <= max_length:
            summary_sentences.append(sentence)
            current_length += len(sentence.split())
        else:
            break
    
    # Restore original sentence order
    if summary_sentences:
        original_order = [(sentences.index(s), s) for s in summary_sentences]
        original_order.sort()
        summary_sentences = [s for _, s in original_order]
    
    return " ".join(summary_sentences)

#####################################
# Information Extraction Functions
#####################################
@st.cache_data(show_spinner=False)
def extract_text_from_file(file_obj):
    """Extract text from uploaded document file"""
    filename = file_obj.name
    ext = os.path.splitext(filename)[1].lower()
    
    if ext == ".docx":
        try:
            document = docx.Document(file_obj)
            text = "\n".join(para.text for para in document.paragraphs if para.text.strip())
        except Exception as e:
            return f"Error processing DOCX file: {e}"
    elif ext == ".doc":
        try:
            with tempfile.NamedTemporaryFile(delete=False, suffix='.doc') as temp_file:
                temp_file.write(file_obj.getvalue())
                temp_path = temp_file.name
            
            text = docx2txt.process(temp_path)
            os.unlink(temp_path)
        except Exception as e:
            return f"Error processing DOC file: {e}"
    elif ext == ".txt":
        try:
            text = file_obj.getvalue().decode("utf-8")
        except Exception as e:
            return f"Error processing TXT file: {e}"
    else:
        return "Unsupported file type. Please upload a .docx, .doc, or .txt file."
    
    return text[:15000] if text else text

def extract_skills(text):
    """Extract key skills from the resume"""
    skill_keywords = {
        "Programming": ["Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "C++", "C#", "Go", "React", "Angular", "Vue", "Node.js"],
        "Data Science": ["Machine Learning", "Data Analysis", "Statistics", "TensorFlow", "PyTorch", "AI", "Algorithms", "NLP", "Deep Learning"],
        "Database": ["SQL", "MySQL", "MongoDB", "Database", "NoSQL", "PostgreSQL", "Oracle", "Redis"],
        "Web Development": ["React", "Angular", "Node.js", "Frontend", "Backend", "Full-Stack", "REST API", "GraphQL"],
        "Software Development": ["Agile", "Scrum", "Git", "DevOps", "Docker", "System Design", "CI/CD", "Jenkins"],
        "Cloud": ["AWS", "Azure", "Google Cloud", "Cloud Computing", "Lambda", "S3", "EC2"],
        "Security": ["Cybersecurity", "Network Security", "Encryption", "Security"],
        "Business": ["Project Management", "Business Analysis", "Leadership", "Teamwork", "Agile", "Scrum"],
        "Design": ["UX/UI", "User Experience", "Design Thinking", "Adobe", "Figma"]
    }
    
    text_lower = text.lower()
    return [skill for category, skills in skill_keywords.items() 
            for skill in skills if skill.lower() in text_lower]

@lru_cache(maxsize=32)
def extract_name(text_start):
    """Extract candidate name from the beginning of resume text"""
    lines = text_start.split('\n')
    potential_name_lines = [line.strip() for line in lines[:5] if line.strip()]
    
    if potential_name_lines:
        first_line = potential_name_lines[0]
        if 5 <= len(first_line) <= 40 and not any(x in first_line.lower() for x in ["resume", "cv", "curriculum", "vitae", "profile"]):
            return first_line
    
    for line in potential_name_lines[:3]:
        if len(line.split()) <= 4 and not any(x in line.lower() for x in ["address", "phone", "email", "resume", "cv"]):
            return line

    return "Unknown (please extract from resume)"

def extract_age(text):
    """Extract candidate age from resume text"""
    age_patterns = [
        r'age:?\s*(\d{1,2})',
        r'(\d{1,2})\s*years\s*old',
        r'dob:.*(\d{4})',
        r'date of birth:.*(\d{4})'
    ]
    
    text_lower = text.lower()
    for pattern in age_patterns:
        matches = re.search(pattern, text_lower)
        if matches:
            # Convert birth year to age if needed
            if len(matches.group(1)) == 4:
                try:
                    return str(2025 - int(matches.group(1)))
                except:
                    pass
            return matches.group(1)
    
    return "Not specified"

def extract_industry(text):
    """Extract expected job industry from resume"""
    industry_keywords = {
        "Technology": ["software", "programming", "developer", "IT", "tech", "computer", "digital"],
        "Finance": ["banking", "financial", "accounting", "finance", "analyst"],
        "Healthcare": ["medical", "health", "hospital", "clinical", "nurse", "doctor", "patient"],
        "Education": ["teaching", "teacher", "professor", "education", "university", "school", "academic"],
        "Marketing": ["marketing", "advertising", "digital marketing", "social media", "brand"],
        "Engineering": ["engineer", "engineering", "mechanical", "civil", "electrical"],
        "Data Science": ["data science", "machine learning", "AI", "analytics", "big data"],
        "Management": ["manager", "management", "leadership", "executive", "director"],
        "Consulting": ["consultant", "consulting", "advisor"],
        "Sales": ["sales", "business development", "account manager", "client relations"]
    }
    
    text_lower = text.lower()
    industry_counts = {industry: sum(text_lower.count(keyword.lower()) for keyword in keywords) 
                       for industry, keywords in industry_keywords.items()}
    
    return max(industry_counts.items(), key=lambda x: x[1])[0] if any(industry_counts.values()) else "Not clearly specified"

def extract_job_position(text):
    """Extract expected job position from resume"""
    objective_patterns = [
        r'objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
        r'career\s*objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
        r'professional\s*summary:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
        r'summary:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
        r'seeking\s*(?:a|an)?\s*(?:position|role|opportunity)\s*(?:as|in)?\s*(?:a|an)?\s*([^.]*)'
    ]
    
    text_lower = text.lower()
    for pattern in objective_patterns:
        match = re.search(pattern, text_lower, re.IGNORECASE | re.DOTALL)
        if match:
            objective_text = match.group(1).strip()
            job_titles = ["developer", "engineer", "analyst", "manager", "director", "specialist", 
                          "coordinator", "consultant", "designer", "architect", "administrator"]
            
            for title in job_titles:
                if title in objective_text:
                    title_pattern = r'(?:a|an)?\s*(\w+\s+' + title + r'|\w+\s+\w+\s+' + title + r')'
                    title_match = re.search(title_pattern, objective_text)
                    if title_match:
                        return title_match.group(1).strip().title()
                    return title.title()
            
            if len(objective_text) > 10:
                words = objective_text.split()
                return " ".join(words[:10]).title() + "..." if len(words) > 10 else objective_text.title()
    
    job_patterns = [
        r'experience:.*?(\w+\s+\w+(?:\s+\w+)?)(?=\s*at|\s*\(|\s*-|\s*,|\s*\d{4}|\n)',
        r'(\w+\s+\w+(?:\s+\w+)?)\s*\(\s*current\s*\)',
        r'(\w+\s+\w+(?:\s+\w+)?)\s*\(\s*present\s*\)'
    ]
    
    for pattern in job_patterns:
        match = re.search(pattern, text_lower, re.IGNORECASE)
        if match:
            return match.group(1).strip().title()
    
    return "Not explicitly stated"

#####################################
# Core Analysis Functions
#####################################
def summarize_resume_text(resume_text, models):
    """Generate a structured summary of resume text"""
    start_time = time.time()
    
    # Extract critical information
    name = extract_name(resume_text[:500])
    age = extract_age(resume_text)
    industry = extract_industry(resume_text)
    job_position = extract_job_position(resume_text)
    skills = extract_skills(resume_text)
    
    # Generate overall summary
    try:
        if has_pipeline and 'summarizer' in models:
            model_summary = models['summarizer'](resume_text[:2000], max_length=100, min_length=30, do_sample=False)[0]['summary_text']
        else:
            model_summary = summarize_text(resume_text, models, max_length=100)
    except Exception as e:
        st.warning(f"Error in resume summarization: {e}")
        model_summary = "Error generating summary. Please check the original resume."
    
    # Format the structured summary
    formatted_summary = f"Name: {name}\n\n"
    formatted_summary += f"Age: {age}\n\n"
    formatted_summary += f"Expected Industry: {industry}\n\n"
    formatted_summary += f"Expected Job Position: {job_position}\n\n"
    formatted_summary += f"Skills: {', '.join(skills)}\n\n"
    formatted_summary += f"Summary: {model_summary}"
    
    return formatted_summary, time.time() - start_time

def extract_job_requirements(job_description, models):
    """Extract key requirements from a job description"""
    # Combined skill list (abridged for brevity)
    tech_skills = [
        "Python", "Java", "C++", "JavaScript", "TypeScript", "SQL", "HTML", "CSS", "React", "Angular", 
        "Machine Learning", "Data Science", "AI", "AWS", "Azure", "Docker", "Kubernetes", "MySQL", 
        "MongoDB", "PostgreSQL", "Project Management", "Agile", "Scrum", "Leadership", "Communication",
        "Problem Solving", "Git", "DevOps", "Full Stack", "Mobile Development", "Android", "iOS"
    ]
    
    clean_job_text = job_description.lower()
    
    # Extract job title
    title_patterns = [
        r'^([^:.\n]+?)(position|role|job|opening|vacancy)',
        r'^([^:.\n]+?)\n',
        r'(hiring|looking for(?: a| an)?|recruiting)(?: a| an)? ([^:.\n]+?)(:-|[.:]|\n|$)'
    ]
    
    job_title = "Not specified"
    for pattern in title_patterns:
        title_match = re.search(pattern, clean_job_text, re.IGNORECASE)
        if title_match:
            potential_title = title_match.group(1).strip() if len(title_match.groups()) >= 1 else title_match.group(2).strip()
            if 3 <= len(potential_title) <= 50:
                job_title = potential_title.capitalize()
                break
    
    # Extract years of experience
    exp_patterns = [
        r'(\d+)(?:\+)?\s*(?:years|yrs)(?:\s*of)?\s*(?:experience|exp)',
        r'experience\s*(?:of)?\s*(\d+)(?:\+)?\s*(?:years|yrs)'
    ]
    
    years_required = 0
    for pattern in exp_patterns:
        exp_match = re.search(pattern, clean_job_text, re.IGNORECASE)
        if exp_match:
            try:
                years_required = int(exp_match.group(1))
                break
            except:
                pass
    
    # Extract required skills
    required_skills = [skill for skill in tech_skills if re.search(r'\b' + re.escape(skill.lower()) + r'\b', clean_job_text)]
    
    # Fallback if no skills found
    if not required_skills:
        words = re.findall(r'\b\w{4,}\b', clean_job_text)
        word_counts = {}
        for word in words:
            if word not in ["with", "that", "this", "have", "from", "they", "will", "what", "your", "their", "about"]:
                word_counts[word] = word_counts.get(word, 0) + 1
        sorted_words = sorted(word_counts.items(), key=lambda x: x[1], reverse=True)
        required_skills = [word.capitalize() for word, _ in sorted_words[:5]]
    
    job_summary = summarize_text(job_description, models, max_length=100)
    
    return {
        "title": job_title,
        "years_experience": years_required,
        "required_skills": required_skills,
        "summary": job_summary
    }

def evaluate_job_fit(resume_summary, job_requirements, models):
    """Evaluate how well a resume matches job requirements"""
    start_time = time.time()
    
    # Extract information
    required_skills = job_requirements["required_skills"]
    years_required = job_requirements["years_experience"]
    job_title = job_requirements["title"]
    skills_mentioned = extract_skills(resume_summary)
    
    # Calculate match percentages
    matching_skills = [skill for skill in required_skills if skill in skills_mentioned]
    skill_match_percentage = len(matching_skills) / len(required_skills) if required_skills else 0
    
    # Extract experience level from resume
    experience_pattern = r'(\d+)\+?\s*years?\s*(?:of)?\s*experience'
    years_experience = 0
    experience_match = re.search(experience_pattern, resume_summary, re.IGNORECASE)
    if experience_match:
        try:
            years_experience = int(experience_match.group(1))
        except:
            pass
    
    # Calculate match scores
    exp_match_ratio = min(1.0, years_experience / max(1, years_required)) if years_required > 0 else 0.5
    
    # Job title match score
    title_words = [word for word in job_title.lower().split() if len(word) > 3]
    title_matches = sum(1 for word in title_words if word in resume_summary.lower())
    title_match = title_matches / len(title_words) if title_words else 0
    
    # Calculate individual scores
    skill_score = min(2, skill_match_percentage * 3)
    exp_score = min(2, exp_match_ratio * 2)
    title_score = min(2, title_match * 2)
    
    # Extract candidate info
    name_match = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
    name = name_match.group(1).strip() if name_match else "The candidate"
    
    industry_match = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
    industry = industry_match.group(1).strip() if industry_match else "unspecified industry"
    
    # Calculate final weighted score
    weighted_score = (skill_score * 0.5) + (exp_score * 0.3) + (title_score * 0.2)
    
    # Determine fit score
    if weighted_score >= 1.5:
        fit_score = 2  # Good fit
    elif weighted_score >= 0.8:
        fit_score = 1  # Potential fit
    else:
        fit_score = 0  # Not a fit
    
    # Generate assessment text
    missing_skills = [skill for skill in required_skills if skill not in skills_mentioned]
    
    if fit_score == 2:
        fit_assessment = f"{fit_score}: GOOD FIT - {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} and professional experience appear well-suited for this role's requirements. The technical expertise matches what the position demands."
    elif fit_score == 1:
        fit_assessment = f"{fit_score}: POTENTIAL FIT - {name} shows potential for the {job_title} role with some relevant experience, though there are gaps in certain technical areas. Their {industry} background provides partial alignment with the position requirements. Additional training might be needed in {', '.join(missing_skills[:2])} if pursuing this opportunity."
    else:
        fit_assessment = f"{fit_score}: NO FIT - {name}'s current background shows limited alignment with this {job_title} position. Their experience level and technical background differ significantly from the role requirements. A position better matching their {industry} expertise might be more suitable."
    
    return fit_assessment, fit_score, time.time() - start_time

def analyze_job_fit(resume_summary, job_description, models):
    """End-to-end job fit analysis"""
    start_time = time.time()
    job_requirements = extract_job_requirements(job_description, models)
    assessment, fit_score, execution_time = evaluate_job_fit(resume_summary, job_requirements, models)
    return assessment, fit_score, time.time() - start_time

#####################################
# Main Function
#####################################
def main():
    """Main function for the Streamlit application"""
    st.title("Resume-Job Fit Analyzer")
    st.markdown("Upload your resume file in **.docx**, **.doc**, or **.txt** format and enter a job description to see how well you match with the job requirements.")

    # Load models
    models = load_models()
    
    # User inputs
    uploaded_file = st.file_uploader("Upload your resume (.docx, .doc, or .txt)", type=["docx", "doc", "txt"])
    job_description = st.text_area("Enter Job Description", height=200, placeholder="Paste the job description here...")

    # Process when button clicked
    if uploaded_file is not None and job_description and st.button("Analyze Job Fit"):
        progress_bar = st.progress(0)
        status_text = st.empty()
        
        # Step 1: Extract text
        status_text.text("Step 1/3: Extracting text from resume...")
        resume_text = extract_text_from_file(uploaded_file)
        progress_bar.progress(25)
        
        if resume_text.startswith("Error") or resume_text == "Unsupported file type. Please upload a .docx, .doc, or .txt file.":
            st.error(resume_text)
        else:
            # Step 2: Generate summary
            status_text.text("Step 2/3: Analyzing resume and generating summary...")
            summary, summarization_time = summarize_resume_text(resume_text, models)
            progress_bar.progress(50)
            
            # Display summary
            st.subheader("Your Resume Summary")
            st.markdown(summary)
            
            # Step 3: Generate job fit assessment
            status_text.text("Step 3/3: Evaluating job fit (this will take a moment)...")
            assessment, fit_score, assessment_time = analyze_job_fit(summary, job_description, models)
            progress_bar.progress(100)
            status_text.empty()

            # Display results
            st.subheader("Job Fit Assessment")
            
            # Display score with appropriate styling
            fit_labels = {0: "NOT FIT", 1: "POTENTIAL FIT", 2: "GOOD FIT"}
            score_colors = {0: "red", 1: "orange", 2: "green"}
            st.markdown(f"<h2 style='color: {score_colors[fit_score]};'>{fit_labels[fit_score]}</h2>", unsafe_allow_html=True)
            st.markdown(assessment)
            st.info(f"Analysis completed in {(summarization_time + assessment_time):.2f} seconds")
            
            # Recommendations
            st.subheader("Recommended Next Steps")
            
            if fit_score == 2:
                st.markdown("""
                - Apply for this position as you appear to be a good match
                - Prepare for interviews by focusing on your relevant experience
                - Highlight your matching skills in your cover letter
                """)
            elif fit_score == 1:
                st.markdown("""
                - Consider applying but address skill gaps in your cover letter
                - Emphasize transferable skills and relevant experience
                - Prepare to discuss how you can quickly develop missing skills
                """)
            else:
                st.markdown("""
                - Look for positions better aligned with your current skills
                - If interested in this field, focus on developing the required skills
                - Consider similar roles with fewer experience requirements
                """)

if __name__ == "__main__":
    main()