"""
INDEPENDENT validation scorer (anti-circular).

The generation pipeline uses candidate_fit ("plausible" expansion) to decide what
to include, and ats_scoring_v2 to score. If the same "plausible" logic both
inserts a term AND credits it, the 90%+ is self-confirming. This module scores
the FINAL EXPORTED, RE-PARSED resume with a deliberately DIFFERENT, stricter
ruleset that knows nothing about candidate_fit:

  - exact / alias presence ONLY in the parsed text — never "plausible" credit
  - EVIDENCE-WEIGHTED: a required skill that appears only in the Skills list but
    is NOT evidenced in an Experience bullet earns partial credit (0.5)
  - NO seniority fuzzing: if the JD asks for N years, the resume must actually
    show >= N years, else the seniority bucket fails
  - NO education fuzzing beyond a real degree token being present
  - title/domain require the actual term in the parsed text

It answers one question: "If a stranger's ATS read ONLY this exported file, would
it still score 90%+?" Used to label WEAK_90_INTERNAL_ONLY and to gate downloads.
"""

from __future__ import annotations

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

from .ats_scorer import _kw_in_text, _detect_sections
from .jd_analyzer import analyze_jd, JDRequirements, Requirement
from .ats_scoring_v2 import score_ats_readability, _WEIGHTS


@dataclass
class ValidationResult:
    independent_jd_match: int
    ats_readability: int
    breakdown: Dict[str, dict] = field(default_factory=dict)
    evidenced_terms: List[str] = field(default_factory=list)
    skills_only_terms: List[str] = field(default_factory=list)
    missing_terms: List[str] = field(default_factory=list)
    seniority_ok: bool = True
    notes: List[str] = field(default_factory=list)

    def to_dict(self):
        return self.__dict__


def _max_years(text: str) -> int:
    yrs = [int(m) for m in re.findall(r"(\d{1,2})\+?\s*years?", text.lower())]
    return max(yrs) if yrs else 0


def _coverage(reqs: List[Requirement], full_low: str, exp_low: str) -> tuple:
    """Evidence-weighted coverage. Returns (credit, total, evidenced, skills_only,
    missing). A term in experience = 1.0; only elsewhere (skills) = 0.5; absent = 0."""
    if not reqs:
        return (0.0, 0, [], [], [])
    credit = 0.0
    evidenced, skills_only, missing = [], [], []
    for r in reqs:
        terms = [r.term] + list(r.aliases or [])
        in_exp = any(_kw_in_text(t, exp_low) for t in terms)
        in_full = any(_kw_in_text(t, full_low) for t in terms)
        if in_exp:
            credit += 1.0
            evidenced.append(r.term)
        elif in_full:
            credit += 0.5
            skills_only.append(r.term)
        else:
            missing.append(r.term)
    return (credit, len(reqs), evidenced, skills_only, missing)


def validate_resume(jd_text: str, parsed_text: str,
                    experience_text: str = None,
                    base_resume_text: str = None) -> ValidationResult:
    req = analyze_jd(jd_text)               # structure only; deterministic
    full_low = (parsed_text or "").lower()
    exp_low = (experience_text or parsed_text or "").lower()

    buckets = {
        "must_have_hard": req.required_hard_skills,
        "responsibilities": req.responsibilities,
        "tools": req.tools_platforms,
        "title_domain": req.domain_terms,
        "seniority": req.seniority_signals,
        "certs_education": req.certifications + req.education_requirements,
        "soft": req.soft_skills,
    }

    breakdown: Dict[str, dict] = {}
    weighted = 0.0
    all_evidenced, all_skills_only, all_missing = [], [], []
    notes: List[str] = []

    # Strict seniority: JD's required years vs the candidate's REAL years. We
    # measure from the BASE resume when provided — never the generated text,
    # which could have a JD year-phrase ("12+ years") injected into it (that
    # would let the system game its own seniority check).
    jd_years = _max_years(jd_text)
    resume_years = _max_years(base_resume_text if base_resume_text else parsed_text)
    seniority_ok = (jd_years == 0) or (resume_years >= jd_years)
    if not seniority_ok:
        notes.append(f"JD wants {jd_years}y; candidate shows {resume_years}y")

    for key, reqs in buckets.items():
        credit, tot, ev, so, miss = _coverage(reqs, full_low, exp_low)
        all_evidenced += ev; all_skills_only += so; all_missing += miss
        if key == "title_domain":
            tcov = sum(1 for t in req.target_role_titles if _kw_in_text(t, full_low))
            credit += tcov
            tot += len(req.target_role_titles)
        if key == "seniority":
            # STRICT: no fuzzy credit. Full only if the actual year bar is met.
            frac = 1.0 if (tot == 0 or seniority_ok) else 0.0
        else:
            frac = (credit / tot) if tot else 1.0
        w = _WEIGHTS[key]
        contrib = frac * w
        weighted += contrib
        breakdown[key] = {"credit": round(credit, 1), "total": tot,
                          "weight": w, "contribution": round(contrib * 100, 1)}

    score = round(max(0, min(100, weighted * 100)))
    readability = score_ats_readability(parsed_text).score

    return ValidationResult(
        independent_jd_match=score,
        ats_readability=readability,
        breakdown=breakdown,
        evidenced_terms=all_evidenced,
        skills_only_terms=all_skills_only,
        missing_terms=all_missing,
        seniority_ok=seniority_ok,
        notes=notes,
    )