"""
Structured JD analysis (spec item #2).

Turns a raw job description into a STRUCTURED set of requirements — not a flat
keyword list. Each requirement carries its category, importance, the exact JD
phrase it came from, aliases/synonyms, and where it should appear in the resume.

Design: deterministic-first. `analyze_jd` always returns a usable result from
the curated gazetteer (no model dependency). If an LLM client + cfg are passed,
its richer structured extraction is merged on top (the LLM is the breadth lever
that matches how AI checkers like Jobalytics extract; the gazetteer is the
reliable floor). Either way, company names / locations / vague buzzwords are
excluded.
"""

from __future__ import annotations

import re
from dataclasses import dataclass, field, asdict
from typing import List, Dict, Optional

from .ats_scorer import (
    extract_jd_keywords,
    _is_taxonomy_skill,
    _LOCATIONS,
)

# ── Category gazetteers (deterministic classification) ───────────────────────

_TOOLS = {
    "jira", "confluence", "figma", "notion", "asana", "miro", "trello", "linear",
    "mixpanel", "amplitude", "ga4", "google analytics", "metabase", "tableau",
    "looker", "power bi", "powerbi", "sql", "excel", "segment", "hotjar",
    "salesforce", "hubspot", "webengage", "clevertap", "braze", "slack",
    "productboard", "airtable", "python", "postgresql", "mysql", "snowflake",
    "kubernetes", "docker", "aws", "gcp", "azure", "github", "gitlab", "jenkins",
    "datadog", "splunk", "kibana", "grafana", "zendesk", "intercom",
}
_METHODS = {
    "agile", "scrum", "kanban", "lean", "sprint planning", "okrs", "okr",
    "a/b testing", "experimentation", "design thinking", "discovery",
    "roadmapping", "prioritization", "go-to-market", "gtm", "hypothesis testing",
    "user research", "agile methodologies", "backlog grooming", "story mapping",
    "competitive analysis", "market research", "wireframing", "user stories",
    "product roadmap", "product strategy", "product discovery", "user acceptance testing",
    "ci/cd", "tdd", "ml ops", "mlops",
}
_DOMAINS = {
    "fintech", "edtech", "healthtech", "martech", "ecommerce", "e-commerce",
    "saas", "b2b", "b2c", "b2b2c", "lending", "credit", "insurance", "fraud",
    "banking", "payments", "logistics", "cybersecurity", "secops", "siem",
    "soar", "xdr", "wellness", "healthcare", "supply chain", "marketplace",
    "consumer", "enterprise", "gaming", "edtech", "proptech", "insurtech",
}
_SOFT_SKILLS = {
    "communication", "leadership", "collaboration", "stakeholder management",
    "stakeholder communication", "cross-functional", "mentoring", "teamwork",
    "negotiation", "presentation", "influencing", "facilitation",
    "problem solving", "analytical thinking", "strategic thinking",
}
# Vague filler real checkers penalise — never a requirement.
_BUZZWORDS = {
    "innovation", "innovative", "solutions", "solution", "tools", "tool",
    "lifecycle", "ownership", "synergy", "dynamic", "passionate", "motivated",
    "results-driven", "detail-oriented", "team player", "track record",
    "expertise", "strengths", "best practices", "value-add", "thought leadership",
    "self-starter", "go-getter", "fast-paced", "cutting-edge", "world-class",
    "robust", "seamless", "holistic", "leverage", "leveraging", "excellence",
    "proven", "successful", "goals", "authority", "productivity", "generation",
    "organisation", "organization",
}

# Importance cue words around a term in the JD.
_MUST_CUES = ("required", "must have", "must-have", "must", "essential",
              "strong", "proven", "expert", "deep", "extensive", "mandatory",
              "minimum", "at least", "demonstrated")
_PREF_CUES = ("preferred", "nice to have", "nice-to-have", "plus", "bonus",
              "a plus", "ideally", "desirable", "advantage", "good to have")

_CERT_PAT = re.compile(
    r"\b(pmp|cspo|csm|safe|six sigma|prince2|aws certified|pmi[- ]acp|"
    r"google certified|scrum master certification|itil)\b", re.I)
# Note: avoid bare two-letter forms (be/bs/ms/me) — they match common words.
# Require dotted/explicit forms instead.
_DEGREE_PAT = re.compile(
    r"\b(bachelor'?s?|master'?s?|mba|b\.?tech|m\.?tech|b\.e\.|m\.e\.|"
    r"b\.s\.|m\.s\.|ph\.?d|degree in|engineering degree|computer science)\b", re.I)
_SENIORITY_PAT = re.compile(
    r"\b(\d{1,2}\+?\s*years?|senior|lead|principal|staff|head of|director|"
    r"junior|associate|entry[- ]level|mid[- ]level|vp\b)\b", re.I)
_TITLE_PAT = re.compile(
    r"\b(product manager|associate product manager|senior product manager|"
    r"product owner|program manager|project manager|product lead|"
    r"group product manager|technical product manager|growth product manager|"
    r"platform product manager)\b", re.I)

VALID_PLACEMENTS = {"title", "summary", "skills", "experience",
                    "certifications", "education"}


@dataclass
class Requirement:
    term: str
    category: str                      # hard_skill|tool|responsibility|domain|...
    importance: str = "preferred"      # must_have | preferred | nice_to_have
    source_phrase: str = ""            # the JD sentence/snippet it came from
    aliases: List[str] = field(default_factory=list)
    recommended_placement: List[str] = field(default_factory=list)

    def to_dict(self) -> dict:
        return asdict(self)


@dataclass
class JDRequirements:
    target_role_titles: List[str] = field(default_factory=list)
    required_hard_skills: List[Requirement] = field(default_factory=list)
    preferred_hard_skills: List[Requirement] = field(default_factory=list)
    tools_platforms: List[Requirement] = field(default_factory=list)
    responsibilities: List[Requirement] = field(default_factory=list)
    domain_terms: List[Requirement] = field(default_factory=list)
    certifications: List[Requirement] = field(default_factory=list)
    education_requirements: List[Requirement] = field(default_factory=list)
    soft_skills: List[Requirement] = field(default_factory=list)
    seniority_signals: List[Requirement] = field(default_factory=list)

    def all_requirements(self) -> List[Requirement]:
        out: List[Requirement] = []
        for f in (self.required_hard_skills, self.preferred_hard_skills,
                  self.tools_platforms, self.responsibilities, self.domain_terms,
                  self.certifications, self.education_requirements,
                  self.soft_skills, self.seniority_signals):
            out.extend(f)
        return out

    def all_terms(self) -> List[str]:
        seen, out = set(), []
        for r in self.all_requirements():
            k = r.term.lower().strip()
            if k and k not in seen:
                seen.add(k)
                out.append(r.term)
        return out

    def to_dict(self) -> dict:
        d = {}
        for k, v in self.__dict__.items():
            if k == "target_role_titles":
                d[k] = list(v)
            else:
                d[k] = [r.to_dict() for r in v]
        return d


# ── Deterministic extraction ─────────────────────────────────────────────────

def _source_phrase(term: str, jd_text: str) -> str:
    """Return the JD sentence containing the term (trimmed)."""
    low = jd_text.lower()
    i = low.find(term.lower())
    if i < 0:
        return ""
    start = jd_text.rfind(".", 0, i)
    end = jd_text.find(".", i)
    start = 0 if start < 0 else start + 1
    end = len(jd_text) if end < 0 else end
    return re.sub(r"\s+", " ", jd_text[start:end]).strip()[:160]


def _importance_for(term: str, jd_text: str) -> str:
    """Infer must_have / preferred from cue words near the term."""
    low = jd_text.lower()
    i = low.find(term.lower())
    if i < 0:
        return "preferred"
    window = low[max(0, i - 90): i + 90]
    if any(c in window for c in _PREF_CUES):
        return "preferred"
    if any(c in window for c in _MUST_CUES):
        return "must_have"
    return "preferred"


def _categorize(term: str) -> str:
    t = term.lower()
    if t in _TOOLS:
        return "tool"
    if t in _SOFT_SKILLS:
        return "soft_skill"
    if t in _DOMAINS:
        return "domain"
    if t in _METHODS:
        return "responsibility" if " " in t else "hard_skill"
    return "hard_skill"


def _placement_for(category: str, importance: str) -> List[str]:
    if category == "tool":
        return ["skills", "experience"]
    if category == "soft_skill":
        return ["experience"]          # soft skills belong in bullets, not raw list
    if category == "domain":
        return ["summary", "experience"]
    if category == "responsibility":
        return ["experience"]
    if category == "certification":
        return ["certifications"]
    if category == "education":
        return ["education"]
    # hard skill
    return ["skills", "experience"] if importance == "must_have" else ["skills"]


def _deterministic_jd_requirements(jd_text: str) -> JDRequirements:
    req = JDRequirements()

    # Titles
    req.target_role_titles = sorted({m.group(0).title()
                                     for m in _TITLE_PAT.finditer(jd_text)})

    # Certifications / education / seniority (regex driven)
    for m in {x.group(0).strip() for x in _CERT_PAT.finditer(jd_text)}:
        req.certifications.append(Requirement(
            term=m, category="certification",
            importance=_importance_for(m, jd_text),
            source_phrase=_source_phrase(m, jd_text),
            recommended_placement=["certifications"]))
    for m in {x.group(0).strip().lower() for x in _DEGREE_PAT.finditer(jd_text)}:
        req.education_requirements.append(Requirement(
            term=m, category="education",
            importance=_importance_for(m, jd_text),
            source_phrase=_source_phrase(m, jd_text),
            recommended_placement=["education"]))
    for m in {x.group(0).strip().lower() for x in _SENIORITY_PAT.finditer(jd_text)}:
        req.seniority_signals.append(Requirement(
            term=m, category="seniority",
            importance="must_have",
            source_phrase=_source_phrase(m, jd_text),
            recommended_placement=["summary"]))

    # Skills/tools/domains/soft — from the existing skills-only extractor
    for term in extract_jd_keywords(jd_text):
        t = term.lower().strip()
        if t in _BUZZWORDS or t in _LOCATIONS or len(t) < 3:
            continue
        category = _categorize(t)
        importance = _importance_for(t, jd_text)
        r = Requirement(
            term=term, category=category, importance=importance,
            source_phrase=_source_phrase(t, jd_text),
            recommended_placement=_placement_for(category, importance),
        )
        if category == "tool":
            req.tools_platforms.append(r)
        elif category == "domain":
            req.domain_terms.append(r)
        elif category == "soft_skill":
            req.soft_skills.append(r)
        elif category == "responsibility":
            req.responsibilities.append(r)
        else:  # hard_skill
            (req.required_hard_skills if importance == "must_have"
             else req.preferred_hard_skills).append(r)

    return req


# ── LLM enrichment (optional) ────────────────────────────────────────────────

def _merge_llm(req: JDRequirements, data: dict, jd_text: str) -> None:
    """Merge an LLM structured-extraction dict into the deterministic result.

    Only terms that actually appear in the JD and aren't buzzwords/locations are
    accepted. Adds terms the gazetteer missed (the breadth lever)."""
    low = jd_text.lower()
    existing = {r.term.lower() for r in req.all_requirements()}

    def _add(bucket: List[Requirement], items, category: str, default_place):
        for it in (items or []):
            if isinstance(it, str):
                it = {"term": it}
            if not isinstance(it, dict):
                continue
            term = (it.get("term") or "").strip()
            tl = term.lower()
            if (not term or tl in existing or tl in _BUZZWORDS
                    or tl in _LOCATIONS or len(tl) < 3 or tl not in low):
                continue
            existing.add(tl)
            place = it.get("recommended_placement") or default_place
            place = [p for p in place if p in VALID_PLACEMENTS] or default_place
            bucket.append(Requirement(
                term=term, category=category,
                importance=it.get("importance", "preferred")
                    if it.get("importance") in ("must_have", "preferred", "nice_to_have")
                    else "preferred",
                source_phrase=(it.get("source_phrase") or _source_phrase(tl, jd_text))[:160],
                aliases=[a for a in (it.get("aliases") or []) if isinstance(a, str)][:6],
                recommended_placement=place,
            ))

    for t in (data.get("target_role_titles") or []):
        if isinstance(t, str) and t.strip() and t not in req.target_role_titles:
            req.target_role_titles.append(t.strip())

    _add(req.required_hard_skills, data.get("required_hard_skills"), "hard_skill", ["skills", "experience"])
    _add(req.preferred_hard_skills, data.get("preferred_hard_skills"), "hard_skill", ["skills"])
    _add(req.tools_platforms, data.get("tools_platforms"), "tool", ["skills", "experience"])
    _add(req.responsibilities, data.get("responsibilities"), "responsibility", ["experience"])
    _add(req.domain_terms, data.get("domain_terms"), "domain", ["summary", "experience"])
    _add(req.certifications, data.get("certifications"), "certification", ["certifications"])
    _add(req.education_requirements, data.get("education_requirements"), "education", ["education"])
    _add(req.soft_skills, data.get("soft_skills"), "soft_skill", ["experience"])
    _add(req.seniority_signals, data.get("seniority_signals"), "seniority", ["summary"])


def analyze_jd(jd_text: str, llm=None, cfg: dict = None) -> JDRequirements:
    """Analyze a JD into structured requirements.

    Deterministic gazetteer always runs (reliable floor). If `llm` (an LLMClient)
    and `cfg` are provided, the LLM's richer structured extraction is merged in.
    """
    req = _deterministic_jd_requirements(jd_text or "")
    if llm is not None and hasattr(llm, "analyze_jd_requirements"):
        try:
            data = llm.analyze_jd_requirements(cfg or {}, jd_text)
            if isinstance(data, dict):
                _merge_llm(req, data, jd_text)
        except Exception as e:  # never let enrichment break the floor
            print(f"[jd_analyzer] LLM enrichment skipped: {e}")
    return req