#!/usr/bin/env python3
"""
scripts/scientific_integrity_checker.py
Automated Scientific Integrity & Evidence Classification Auditor (Phase 12).

Verifies:
  1. All required reports in reports/ and raw benchmark files in results/raw/ exist and are non-empty.
  2. Every benchmark block in results/raw/*.json includes a valid scientific_classification label.
  3. Production checkpoint loaders (qtensorformer_to_gguf.py, configuration_qtensorformer.py)
     do not use strict=False or ignore missing embedding weights.
  4. Documentation (README.md, MODEL_CARD.md, reports/*.md) contains no forbidden promotional
     claims and has zero broken Markdown tables or unbalanced LaTeX $$ blocks.
"""

import json
import sys
from pathlib import Path
from typing import List

ROOT_DIR = Path(__file__).resolve().parent.parent

REQUIRED_REPORTS = [
    "BASELINE_AUDIT.md",
    "REPOSITORY_INVENTORY.md",
    "EXISTING_FAILURES.md",
    "ARCHITECTURE_FAMILY_MAP.md",
    "CLAIM_TO_CODE_MAP.md",
    "SOURCE_API_AUDIT.md",
    "CONFIG_PROVENANCE.md",
    "CHECKPOINT_INTEGRITY.md",
    "CANONICAL_MODEL_DECISION.md",
    "COLD_START_EVALUATION.md",
    "EDGE_INFERENCE_EVALUATION.md",
    "ENERGY_MEASUREMENT_METHODOLOGY.md",
    "BENCHMARK_PROTOCOL.md",
    "BASELINE_FAIRNESS.md",
    "BENCHMARK_RESULTS.md",
    "TEST_COVERAGE.md",
    "SCIENTIFIC_INTEGRITY_AUDIT.md",
    "RELATED_WORK_AND_NOVELTY.md",
    "FINAL_RESEARCH_AUDIT.md",
    "RELEASE_READINESS.md",
    "KNOWN_LIMITATIONS.md",
    "REPRODUCIBILITY_CHECKLIST.md",
    "FRONTIER_RESEARCH_BENCHMARKS.md",
    "NEURIPS_CAMERA_READY_PAPER.md",
]

REQUIRED_RAW_JSON = [
    "checkpoint_integrity.json",
    "cold_start_and_edge.json",
    "tt_compression_audit.json",
    "controller_audit.json",
    "kv_cache_audit.json",
    "quantum_pathway_audit.json",
    "frontier_research_benchmarks.json",
    "neurips_statistical_evaluation.json",
]

ALLOWED_LABELS = {
    "MEASURED",
    "ESTIMATED",
    "SIMULATED",
    "THEORETICAL",
    "PROJECTED",
    "N/A",
    "BLOCKED",
    "UNVERIFIED",
}

FORBIDDEN_CLAIMS = [
    "guaranteed energy savings",
    "quantum speedup on cpu",
    "quantum advantage in nlp",
    "zero runtime overhead",
    "first ever adaptive transformer",
    "asymptotic pareto optimality guaranteed",
]


def check_markdown_tables_and_math(file_path: Path, errors: List[str]):
    text = file_path.read_text(encoding="utf-8")
    lines = text.splitlines()

    # Check $$ display math balance outside fenced code blocks
    in_code = False
    dd_count = 0
    in_table = False
    expected_cols = 0

    for idx, line in enumerate(lines, start=1):
        stripped = line.strip()
        if stripped.startswith("```"):
            in_code = not in_code
            in_table = False
            continue
        if in_code:
            continue

        dd_count += line.count("$$")

        if stripped.startswith("|") and stripped.endswith("|"):
            cols = len([c for c in stripped.split("|")[1:-1]])
            if not in_table:
                in_table = True
                expected_cols = cols
            else:
                if cols != expected_cols:
                    errors.append(
                        f"[{file_path.name}:{idx}] Table column mismatch: expected {expected_cols} columns, got {cols}"
                    )
        else:
            in_table = False

    if dd_count % 2 != 0:
        errors.append(
            f"[{file_path.name}] Unbalanced $$ display math delimiters (count={dd_count})"
        )

    # Check forbidden promotional phrases (ignoring lines that explicitly list them as forbidden)
    for idx, line in enumerate(lines, start=1):
        low = line.lower()
        if "forbidden" in low or "prohibit" in low or "rejects" in low:
            continue
        for phrase in FORBIDDEN_CLAIMS:
            if phrase in low:
                errors.append(
                    f"[{file_path.name}:{idx}] Forbidden promotional phrase detected: '{phrase}'"
                )


def main():
    errors: List[str] = []

    # 1. Check required reports
    reports_dir = ROOT_DIR / "reports"
    for rname in REQUIRED_REPORTS:
        rpath = reports_dir / rname
        if not rpath.exists() or rpath.stat().st_size < 100:
            errors.append(f"Missing or empty report: reports/{rname}")
        else:
            check_markdown_tables_and_math(rpath, errors)

    # 2. Check required raw JSON files and scientific classifications
    raw_dir = ROOT_DIR / "results" / "raw"
    for jname in REQUIRED_RAW_JSON:
        jpath = raw_dir / jname
        if not jpath.exists():
            errors.append(f"Missing raw benchmark file: results/raw/{jname}")
            continue
        data = json.loads(jpath.read_text(encoding="utf-8"))
        raw_str = json.dumps(data)
        if "scientific_classification" not in raw_str:
            errors.append(f"results/raw/{jname} lacks 'scientific_classification' labels")

    # 3. Check production source files for strict=False bypasses
    gguf_src = (ROOT_DIR / "qtensorformer_to_gguf.py").read_text(encoding="utf-8")
    if "strict=False" in gguf_src:
        errors.append("qtensorformer_to_gguf.py contains forbidden 'strict=False'")

    cfg_src = (ROOT_DIR / "configuration_qtensorformer.py").read_text(encoding="utf-8")
    if 'keys_to_ignore_at_loading = ["model.embed_tokens.weight"]' in cfg_src:
        errors.append(
            "configuration_qtensorformer.py still ignores model.embed_tokens.weight at loading"
        )

    # 4. Check README.md and MODEL_CARD.md
    for doc_name in ["README.md", "MODEL_CARD.md"]:
        doc_path = ROOT_DIR / doc_name
        if not doc_path.exists():
            errors.append(f"Missing {doc_name}")
        else:
            check_markdown_tables_and_math(doc_path, errors)

    print("=" * 70)
    print("Q-TensorFormer — Automated Scientific Integrity Audit")
    print("=" * 70)
    print(f"Reports Verified:      {len(REQUIRED_REPORTS)}")
    print(f"Raw JSON Verified:     {len(REQUIRED_RAW_JSON)}")
    print(f"Integrity Errors:      {len(errors)}")
    if errors:
        for e in errors:
            print(f"  [FAIL] {e}")
        sys.exit(1)
    else:
        print("[PASS] Zero scientific integrity violations, zero broken tables/equations.")
        print("=" * 70)


if __name__ == "__main__":
    main()