marki-docx/tests/regression/test_level3_roundtrip.py

"""LEVEL3 end-to-end round-trip regression tests (FR-1100, MRKD-WP-0003 T07).

Tests the full build → import → compare cycle for each corpus file in
tests/regression/level3/, using feature_level: level3.

All LEVEL1 regression tests must remain green (non-regression gate).
"""

from __future__ import annotations

from pathlib import Path

import pytest
import yaml

from markidocx.builder import build_document
from markidocx.differ import compare
from markidocx.importer import import_document
from markidocx.manifest import load_manifest

# Corpus files in tests/regression/level3/
CORPUS_DIR = Path(__file__).parent / "level3"
CORPUS_FILES = [
    "xref_document.md",
    "figures_document.md",
    "diagrams_document.md",
    "bibliography_document.md",
    "combined_document.md",
]


def _make_level3_project(tmp_path: Path, markdown: str, name: str = "test") -> Path:
    (tmp_path / "doc.md").write_text(markdown, encoding="utf-8")
    manifest_path = tmp_path / "manifest.yaml"
    manifest_path.write_text(
        yaml.dump(
            {
                "project": {"name": name, "feature_level": "level3", "family": "article"},
                "sources": [{"path": "doc.md"}],
                "output": {"dir": "./dist"},
            }
        )
    )
    (tmp_path / "dist").mkdir()
    return manifest_path


# ---------------------------------------------------------------------------
# Corpus round-trip tests
# ---------------------------------------------------------------------------


@pytest.mark.parametrize("corpus_file", CORPUS_FILES)
def test_level3_corpus_builds(tmp_path: Path, corpus_file: str) -> None:
    """Each corpus file builds successfully under LEVEL3."""
    md = (CORPUS_DIR / corpus_file).read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name=corpus_file.replace(".md", ""))
    manifest = load_manifest(manifest_path)

    result = build_document(manifest)
    assert result.success, f"Build failed for {corpus_file}: {result.errors}"
    assert result.output_path.exists()
    assert result.feature_level == "level3"


@pytest.mark.parametrize("corpus_file", CORPUS_FILES)
def test_level3_corpus_imports(tmp_path: Path, corpus_file: str) -> None:
    """Each corpus file imports successfully after build."""
    md = (CORPUS_DIR / corpus_file).read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name=corpus_file.replace(".md", ""))
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success, f"Build failed for {corpus_file}"

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success, f"Import failed for {corpus_file}: {import_result.warnings}"


@pytest.mark.parametrize("corpus_file", CORPUS_FILES)
def test_level3_corpus_no_unexpected_breakage(tmp_path: Path, corpus_file: str) -> None:
    """Round-trip diff for each corpus file has no broken headings."""
    md = (CORPUS_DIR / corpus_file).read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name=corpus_file.replace(".md", ""))
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    report = compare(md, reimported)

    # Headings must not be broken
    broken_headings = [b for b in report.broken if b.startswith("heading:")]
    assert not broken_headings, (
        f"Broken headings in {corpus_file}: {broken_headings}"
    )


# ---------------------------------------------------------------------------
# Specific corpus: xref_document — cross-ref anchors preserved
# ---------------------------------------------------------------------------


def test_xref_document_anchors_preserved(tmp_path: Path) -> None:
    md = (CORPUS_DIR / "xref_document.md").read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name="xref")
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    # Core anchors must survive
    assert "{#intro}" in reimported
    assert "{#bg}" in reimported
    assert "{#method}" in reimported
    assert "{#results}" in reimported


# ---------------------------------------------------------------------------
# Specific corpus: figures_document — figure labels preserved
# ---------------------------------------------------------------------------


def test_figures_document_labels_preserved(tmp_path: Path) -> None:
    md = (CORPUS_DIR / "figures_document.md").read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name="figures")
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    assert "fig:arch" in reimported
    assert "fig:dataflow" in reimported
    assert "fig:results" in reimported


# ---------------------------------------------------------------------------
# Specific corpus: diagrams_document — diagram sources preserved
# ---------------------------------------------------------------------------


def test_diagrams_document_sources_preserved(tmp_path: Path, monkeypatch) -> None:
    """Diagram sources survive round-trip in source-only path."""
    import shutil

    monkeypatch.setattr(shutil, "which", lambda _cmd: None)
    md = (CORPUS_DIR / "diagrams_document.md").read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name="diagrams")
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    # At least one diagram type must appear in reimported
    assert "mermaid" in reimported or "graphviz" in reimported or "plantuml" in reimported


# ---------------------------------------------------------------------------
# Specific corpus: bibliography_document — citation keys preserved
# ---------------------------------------------------------------------------


def test_bibliography_document_citations_preserved(tmp_path: Path) -> None:
    md = (CORPUS_DIR / "bibliography_document.md").read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name="bibliography")
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    assert "smith2020" in reimported
    assert "jones2021" in reimported
    assert "brown2019" in reimported


# ---------------------------------------------------------------------------
# Specific corpus: combined_document — all LEVEL3 constructs
# ---------------------------------------------------------------------------


def test_combined_document_roundtrip(tmp_path: Path, monkeypatch) -> None:
    """Combined document with all LEVEL3 constructs survives build+import."""
    import shutil

    monkeypatch.setattr(shutil, "which", lambda _cmd: None)
    md = (CORPUS_DIR / "combined_document.md").read_text(encoding="utf-8")
    manifest_path = _make_level3_project(tmp_path, md, name="combined")
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")

    # Anchors preserved
    assert "{#intro}" in reimported

    # Figures preserved (at least the label)
    assert "fig:arch" in reimported

    # Citations preserved
    assert "smith2020" in reimported


# ---------------------------------------------------------------------------
# CLI: markidocx test executes LEVEL1 + LEVEL3 corpus (non-regression gate)
# ---------------------------------------------------------------------------


def test_level1_regression_still_passes(tmp_path: Path) -> None:
    """LEVEL1 round-trip must remain green after LEVEL3 changes (non-regression)."""
    from tests.regression.test_roundtrip import LEVEL1_MARKDOWN

    (tmp_path / "doc.md").write_text(LEVEL1_MARKDOWN, encoding="utf-8")
    manifest_path = tmp_path / "manifest.yaml"
    manifest_path.write_text(
        yaml.dump(
            {
                "project": {"name": "l1-nonreg", "feature_level": "level1", "family": "article"},
                "sources": [{"path": "doc.md"}],
                "output": {"dir": "./dist"},
            }
        )
    )
    (tmp_path / "dist").mkdir()
    manifest = load_manifest(manifest_path)

    build_result = build_document(manifest)
    assert build_result.success
    assert not build_result.errors

    import_result = import_document(manifest, build_result.output_path)
    assert import_result.success

    reimported = import_result.output_files[0].read_text(encoding="utf-8")
    report = compare(LEVEL1_MARKDOWN, reimported)
    broken_headings = [b for b in report.broken if b.startswith("heading:")]
    assert not broken_headings