utils.py

import re
from datetime import datetime

# ── Resume Scoring ────────────────────────────────────

def score_resume_vs_job(resume_text: str, job: dict) -> int:
    """
    Score how well a resume matches a job.
    Returns integer 0–100.
    Pure keyword + heuristic scoring (no LLM cost).
    """
    if not resume_text or not job:
        return 0

    resume_lower = resume_text.lower()

    score = 0
    max_score = 0

    # 1. Job title words in resume (up to 30 pts)
    title_words = _tokenize(job.get("title", ""))
    title_hits = sum(1 for w in title_words if w in resume_lower)
    title_score = int((title_hits / max(len(title_words), 1)) * 30)
    score += title_score
    max_score += 30

    # 2. Tags / tech stack match (up to 40 pts)
    tags = [t.lower() for t in job.get("tags", [])]
    tag_hits = sum(1 for t in tags if t in resume_lower)
    tag_score = int((tag_hits / max(len(tags), 1)) * 40)
    score += tag_score
    max_score += 40

    # 3. Description keywords in resume (up to 20 pts)
    desc_words = _tokenize(job.get("description", ""))
    important = _extract_important_words(desc_words)
    desc_hits = sum(1 for w in important if w in resume_lower)
    desc_score = int((desc_hits / max(len(important), 1)) * 20)
    score += desc_score
    max_score += 20

    # 4. Resume length bonus (up to 10 pts)
    word_count = len(resume_text.split())
    if word_count > 300:
        score += 10
    elif word_count > 150:
        score += 5
    max_score += 10

    # Normalize to 100
    final = int((score / max_score) * 100) if max_score > 0 else 0
    return min(final, 100)


def rank_jobs(resume_text: str, jobs: list) -> list:
    """
    Return jobs sorted by match score (highest first).
    Adds 'match_score' key to each job dict.
    """
    scored = []
    for job in jobs:
        job_copy = dict(job)
        job_copy["match_score"] = score_resume_vs_job(resume_text, job)
        scored.append(job_copy)
    scored.sort(key=lambda x: x["match_score"], reverse=True)
    return scored


# ── Text Helpers ──────────────────────────────────────

def _tokenize(text: str) -> list:
    """Split text into lowercase word tokens, remove noise."""
    words = re.findall(r'\b[a-zA-Z]{3,}\b', text.lower())
    stopwords = {
        "the", "and", "for", "with", "this", "that", "are", "you",
        "will", "have", "our", "your", "from", "not", "but", "can",
        "all", "work", "team", "role", "join", "looking", "able",
        "must", "help", "well", "also", "more", "who", "what",
        "how", "when", "they", "their", "about", "into"
    }
    return [w for w in words if w not in stopwords]


def _extract_important_words(words: list) -> list:
    """Return the most meaningful/unique words for matching."""
    # Prioritize longer words (usually technical terms)
    return list(set([w for w in words if len(w) > 4]))[:40]


def format_match_score(score: int) -> tuple:
    """Return (emoji, label, color) for a score."""
    if score >= 80:
        return "🟢", "Excellent Match", "green"
    elif score >= 60:
        return "🟡", "Good Match", "orange"
    elif score >= 40:
        return "🟠", "Fair Match", "orange"
    else:
        return "🔴", "Low Match", "red"


# ── Date Helpers ──────────────────────────────────────

def format_date(iso_string: str) -> str:
    """Convert ISO timestamp to human-readable."""
    if not iso_string:
        return "Unknown"
    try:
        dt = datetime.fromisoformat(iso_string.replace("Z", "+00:00"))
        return dt.strftime("%b %d, %Y at %I:%M %p")
    except Exception:
        return iso_string[:10]


def days_ago(iso_string: str) -> str:
    """Return '3 days ago' style string."""
    if not iso_string:
        return ""
    try:
        dt = datetime.fromisoformat(iso_string.replace("Z", "+00:00"))
        delta = datetime.now(dt.tzinfo) - dt
        days = delta.days
        if days == 0:
            return "Today"
        elif days == 1:
            return "Yesterday"
        else:
            return f"{days} days ago"
    except Exception:
        return ""


# ── Resume Helpers ────────────────────────────────────

def extract_name_from_resume(resume_text: str) -> str:
    """Best-effort extract name from first line of resume."""
    if not resume_text:
        return "Candidate"
    first_line = resume_text.strip().split("\n")[0].strip()
    if len(first_line) < 40:
        return first_line
    return "Candidate"


def truncate(text: str, max_chars: int = 300) -> str:
    """Truncate text with ellipsis."""
    if not text:
        return ""
    if len(text) <= max_chars:
        return text
    return text[:max_chars].rstrip() + "..."


def sanitize_for_json(text: str) -> str:
    """Remove characters that break JSON storage."""
    return text.replace("\x00", "").strip()