"""IMP-95 u8 — capture final.html SHA baseline via the FULL Phase Z pipeline
under PHASE_Z_B4_V4_EVIDENCE=OFF (default) for mdx 01/02/04/05.

Runs ``src.phase_z2_pipeline.run_phase_z2_mvp1`` end-to-end for each mdx file
in the Stage 2 u8 scope (01/02/04/05; mdx 03 is excluded per the ``mdx 03
정비`` lock). Each run writes a real ``final.html`` to disk at the production
write site ``src/phase_z2_pipeline.py:5994-5996``; bytes are IMP-94-normalized
and SHA-256 hashed, then frozen to
``tests/regression/fixtures/imp95_pre_baseline_sha.json``.

The accompanying regression test
``tests/regression/test_b4_v4_evidence_off_sha_parity.py`` re-runs the same
pipeline shape under flag OFF and asserts SHA equality with the frozen
values. Under flag OFF, IMP-95 (u1~u7) is a strict no-op for ``final.html``
bytes — see the trace-only docstring at ``src/phase_z2_pipeline.py:86`` —
so the captured baseline IS the immediate pre-IMP-95 reference even when
captured with IMP-95 code already in tree.

Reason for a separate baseline (vs. reusing 89a_pre_baseline_sha.json)
======================================================================

The 89a baseline was captured at HEAD ``6e9e3ee`` before subsequent
working-tree changes accumulated (e.g. the Emergency P3/P4/P4b verbatim
slot_payload builders), so the 89a SHAs no longer match the current
flag-OFF pipeline output for mdx 02/04/05 — a pre-existing baseline
drift orthogonal to IMP-95. A fresh baseline keyed to the current
flag-OFF state isolates IMP-95's u8 regression axis from that upstream
drift; the 89a baseline remains the load-bearing guard for the 89-a
axis.

IMP-94 marker normalization
===========================

IMP-94 ``data-region-id`` / ``data-content-unit-id`` tokens (stamped at
``src/region_marker_stamper.py:131-135``) are stripped before hashing.
The strip is anchored on ``leading space + attr token`` shape and is
disjoint from the IMP-96 ``data-frame-slot-id`` axis by attribute name.

Run from repo root::

    python tests/regression/scripts/capture_imp95_pre_baseline.py

Idempotent. Re-run only when an upstream mapper/render/template delta is
reviewed and accepted as the new pre-IMP-95 reference. Refuses to run
with PHASE_Z_B4_V4_EVIDENCE enabled (the flag-ON state is not the
baseline axis).
"""

from __future__ import annotations

import hashlib
import json
import os
import re
import sys
import tempfile
from datetime import datetime, timezone
from pathlib import Path

_REPO_ROOT = Path(__file__).resolve().parents[3]
sys.path.insert(0, str(_REPO_ROOT))
sys.path.insert(0, str(_REPO_ROOT / "src"))

import src.phase_z2_pipeline as pz2  # noqa: E402

_SAMPLES_DIR = _REPO_ROOT / "samples" / "mdx_batch"
_MDX_BATCH = ("01.mdx", "02.mdx", "04.mdx", "05.mdx")  # Stage 2 u8 scope
_OUT_PATH = (
    _REPO_ROOT
    / "tests"
    / "regression"
    / "fixtures"
    / "imp95_pre_baseline_sha.json"
)

# IMP-94 additive marker strip patterns — must stay in sync with
# tests/regression/test_b4_v4_evidence_off_sha_parity.py.
_STRIP_REGION_ID_RE = re.compile(rb' data-region-id="[^"]*"')
_STRIP_CONTENT_UNIT_ID_RE = re.compile(rb' data-content-unit-id="[^"]*"')


def _strip_imp94_markers(raw_bytes: bytes) -> bytes:
    stripped = _STRIP_REGION_ID_RE.sub(b"", raw_bytes)
    stripped = _STRIP_CONTENT_UNIT_ID_RE.sub(b"", stripped)
    return stripped


def _capture_one(mdx_file: str, runs_root: Path) -> dict:
    mdx_path = _SAMPLES_DIR / mdx_file
    assert mdx_path.exists(), f"sample missing: {mdx_path}"

    run_id = f"imp95_baseline_{mdx_path.stem}"
    pipeline_exit_code: int | None = None
    try:
        pz2.run_phase_z2_mvp1(mdx_path, run_id=run_id)
    except SystemExit as exc:
        pipeline_exit_code = (
            int(exc.code) if isinstance(exc.code, int) else 1
        )

    final_html_path = runs_root / run_id / "phase_z2" / "final.html"
    assert final_html_path.exists(), (
        f"final.html not written by pipeline: {final_html_path} "
        f"(pipeline_exit_code={pipeline_exit_code})"
    )
    raw_bytes = final_html_path.read_bytes()
    assert len(raw_bytes) > 0, f"final.html is empty: {final_html_path}"
    normalized_bytes = _strip_imp94_markers(raw_bytes)

    return {
        "mdx_file": mdx_file,
        "run_id": run_id,
        "final_html_size_bytes": len(normalized_bytes),
        "sha256": hashlib.sha256(normalized_bytes).hexdigest(),
        "pipeline_exit_code": pipeline_exit_code,
    }


def capture() -> dict:
    assert os.environ.get("PHASE_Z_B4_V4_EVIDENCE", "") == "", (
        "PHASE_Z_B4_V4_EVIDENCE must be unset when capturing baseline "
        "(default-OFF state is the production-equivalent axis for u8). "
        "Refusing to run with the flag enabled."
    )
    assert os.environ.get("PHASE_Z_B4_MAPPER_SOURCE", "") == "", (
        "PHASE_Z_B4_MAPPER_SOURCE must also be unset — the u8 baseline "
        "is captured under both flags OFF (full pre-IMP-89/95 path)."
    )

    _OUT_PATH.parent.mkdir(parents=True, exist_ok=True)

    with tempfile.TemporaryDirectory(prefix="imp95_baseline_") as tmp:
        runs_root = Path(tmp)
        original_runs_dir = pz2.RUNS_DIR
        pz2.RUNS_DIR = runs_root
        try:
            entries = [_capture_one(mf, runs_root) for mf in _MDX_BATCH]
        finally:
            pz2.RUNS_DIR = original_runs_dir

    return {
        "schema_version": 1,
        "axis": (
            "IMP-95 u8 — final.html SHA baseline captured via FULL "
            "run_phase_z2_mvp1 pipeline under PHASE_Z_B4_V4_EVIDENCE=OFF "
            "and PHASE_Z_B4_MAPPER_SOURCE=OFF (defaults)"
        ),
        "description": (
            "Frozen SHA-256 of `final.html` bytes (production write site "
            "src/phase_z2_pipeline.py:5994-5996) for mdx 01/02/04/05 "
            "under PHASE_Z_B4_V4_EVIDENCE OFF. Under flag OFF, IMP-95 "
            "(u1~u7) is strictly no-op for final.html (planner branch "
            "falls through to legacy _select_frame at u3; u4/u5/u6 "
            "additive telemetry confined to placement_trace per the "
            "trace-only docstring at src/phase_z2_pipeline.py:86). The "
            "u8 regression test asserts SHA equality with these frozen "
            "values, so any future code change that drifts the flag-OFF "
            "render output produces a mismatch and breaks the test. "
            "mdx 03 is excluded per Stage 2 u8 scope (mdx 03 정비 LOCK). "
            "Regenerate only when an upstream delta is reviewed and "
            "accepted as the new pre-IMP-95 reference."
        ),
        "captured_at_utc": (
            datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
        ),
        "renderer": {
            "entrypoint": "src.phase_z2_pipeline.run_phase_z2_mvp1",
            "write_site": "src/phase_z2_pipeline.py:5994-5996",
            "artifact_relpath": "<RUNS_DIR>/<run_id>/phase_z2/final.html",
        },
        "mdx_batch": list(_MDX_BATCH),
        "mdx_files": {entry["mdx_file"]: entry for entry in entries},
        "total_files": len(entries),
    }


def main() -> None:
    data = capture()
    _OUT_PATH.write_text(
        json.dumps(data, indent=2, ensure_ascii=False) + "\n",
        encoding="utf-8",
    )
    print(
        f"wrote {_OUT_PATH} ({data['total_files']} files: "
        f"{', '.join(data['mdx_files'].keys())})"
    )


if __name__ == "__main__":
    main()