"""
Per-job validation package (spec #9).

For every generated resume we can export a self-contained folder that bundles
everything needed for MANUAL Jobalytics / Simplify verification and for auditing
the model-independent pipeline:

    final resume DOCX + PDF
    parsed_resume.txt        (the EXPORTED file re-parsed back to text)
    jd.txt                   (the job description we tailored against)
    manifest.json            (scores, keyword lists, risk terms, provider info)
    README.md                (human-readable summary)

It never generates or scores anything — it only collects what the pipeline
already produced on the job dict (`_v2_report`). This is what the user opens to
confirm our internal numbers against a real external checker.
"""

from __future__ import annotations

import os
import re
import json
import shutil
from datetime import datetime


def _safe(s: str, n: int = 60) -> str:
    return re.sub(r'[\\/*?:"<>|]', "", str(s or ""))[:n].strip() or "item"


def build_validation_package(job: dict, base_resume_text: str = None,
                             out_root: str = "data/output/validation") -> str:
    """Write a validation package folder for one job and return its path."""
    report = job.get("_v2_report", {}) or {}
    est = report.get("estimated_scores", {}) or {}

    date_str = datetime.now().strftime("%Y-%m-%d")
    folder = os.path.join(
        out_root, date_str,
        f"{_safe(job.get('company', 'Company'), 40)}_{_safe(job.get('title', 'Role'), 40)}",
    )
    os.makedirs(folder, exist_ok=True)

    # 1. Copy the resume files
    docx_path = job.get("resume_path", "")
    pdf_path = job.get("resume_pdf_path", "")
    parsed_text = ""
    if docx_path and os.path.exists(docx_path):
        try:
            shutil.copy2(docx_path, os.path.join(folder, "resume" + os.path.splitext(docx_path)[1]))
        except Exception:
            pass
        try:
            from .resume_customizer import _read_docx_text
            parsed_text = _read_docx_text(docx_path)
        except Exception:
            parsed_text = ""
    if pdf_path and os.path.exists(pdf_path):
        try:
            shutil.copy2(pdf_path, os.path.join(folder, "resume.pdf"))
        except Exception:
            pass

    # 2. Parsed text + JD
    jd_text = job.get("description", "") or ""
    with open(os.path.join(folder, "parsed_resume.txt"), "w", encoding="utf-8") as f:
        f.write(parsed_text)
    with open(os.path.join(folder, "jd.txt"), "w", encoding="utf-8") as f:
        f.write(jd_text)

    # 3. Manifest — every field spec #9 asks for
    risky = report.get("risky_review_table", []) or []
    medium_terms = report.get("review_terms_for_user_review", []) or []
    high_terms = report.get("high_risk_terms_for_confirmation", []) or []
    blocked_terms = [d.get("keyword") for d in report.get("unsupported_missing_keywords", []) or []]

    manifest = {
        "job": {
            "title": job.get("title", ""),
            "company": job.get("company", ""),
            "location": job.get("location", ""),
            "platform": job.get("platform", job.get("source", "")),
            "url": job.get("url", ""),
        },
        "status": job.get("status", report.get("status", "")),
        "download_allowed": bool(report.get("download_allowed", job.get("download_allowed"))),
        "quality_flag": report.get("quality_flag", job.get("quality_flag", "")),
        "scores": {
            "internal_jd_match": est.get("jd_match", job.get("ats_score_after", 0)),
            "independent_jd_match": report.get("independent_jd_match",
                                               job.get("independent_jd_match", 0)),
            "ats_readability": est.get("ats_readability", 0),
            "combined_range": est.get("combined_range", ""),
        },
        "provider": {
            "provider_used": report.get("provider_used", job.get("provider_used", "")),
            "provider_response_quality": report.get("provider_response_quality", ""),
            "provider_attempts": report.get("provider_attempts", []),
        },
        "repair_attempts": report.get("repair_attempts", []),
        "keywords": {
            "jd_covered_terms": report.get("covered_terms", []),
            "jd_missing_terms": report.get("missing_terms", []),
            "keywords_added_evidenced": report.get("evidenced_terms", []),
            "keywords_added_skills_only": report.get("skills_only_terms", []),
            "medium_risk_terms": medium_terms,
            "high_risk_terms": high_terms,
            "blocked_terms": blocked_terms,
        },
        "risky_review_table": risky,
        "files": {
            "docx": os.path.basename(docx_path) if docx_path else "",
            "pdf": "resume.pdf" if (pdf_path and os.path.exists(os.path.join(folder, "resume.pdf"))) else "",
            "parsed_resume": "parsed_resume.txt",
            "jd": "jd.txt",
        },
        "generated_at": datetime.now().isoformat(timespec="seconds"),
    }
    with open(os.path.join(folder, "manifest.json"), "w", encoding="utf-8") as f:
        json.dump(manifest, f, ensure_ascii=False, indent=2)

    # 4. Human-readable summary
    s = manifest["scores"]
    lines = [
        f"# Validation Package — {job.get('title','')} at {job.get('company','')}",
        "",
        f"- Status: **{manifest['status']}**  |  Download allowed: {manifest['download_allowed']}",
        f"- Provider used: **{manifest['provider']['provider_used']}** "
        f"(schema: {manifest['provider']['provider_response_quality']})",
        f"- Internal JD match: **{s['internal_jd_match']}**",
        f"- Independent JD match: **{s['independent_jd_match']}**",
        f"- ATS readability: **{s['ats_readability']}**",
        f"- Repair attempts: {len(manifest['repair_attempts'])}",
        "",
        "## How to verify",
        "1. Open `resume.pdf` (or the DOCX) and upload it to Jobalytics / Simplify.",
        "2. Paste `jd.txt` as the job description.",
        "3. Compare the external score to the independent score above.",
        "4. Review `manifest.json` -> keywords.medium_risk_terms / high_risk_terms / blocked_terms.",
        "",
        "## Provider attempts",
    ]
    for a in manifest["provider"]["provider_attempts"]:
        lines.append(f"- {a}")
    with open(os.path.join(folder, "README.md"), "w", encoding="utf-8") as f:
        f.write("\n".join(lines))

    return folder


def build_packages_for_jobs(jobs: list, base_resume_text: str = None,
                            out_root: str = "data/output/validation") -> list:
    """Build packages for a list of jobs; returns list of folder paths."""
    paths = []
    for job in jobs:
        if not job.get("resume_path"):
            continue
        try:
            paths.append(build_validation_package(job, base_resume_text, out_root))
        except Exception as e:
            print(f"[validation-package] {job.get('company','?')}: {e}")
    return paths