feat: add swap_sources.py for incremental RST-to-MyST migration

Pre-build swap/restore script that renames md-{name}.md → {name}.md
before Sphinx builds and restores after. Includes state tracking,
exclude file generation, collision detection, and partial-failure
rollback. 10 tests cover all specified behaviors plus rollback path.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2 files changed, 548 insertions, 0 deletions

diff --git a/scripts/swap_sources.py b/scripts/swap_sources.py
new file mode 100644
index 00000000..f983dbfa
--- /dev/null
+++ b/scripts/swap_sources.py
@@ -0,0 +1,310 @@
+#!/usr/bin/env python3
+"""swap_sources.py — Pre-build swap/restore for incremental RST-to-MyST migration.
+
+Usage
+-----
+  python scripts/swap_sources.py --swap          # rename md-{name}.md → {name}.md
+  python scripts/swap_sources.py --restore       # undo renames
+  python scripts/swap_sources.py --dry-run       # show what would be swapped
+  python scripts/swap_sources.py --status        # show current swap state
+  python scripts/swap_sources.py --swap --docs-dir /path/to/docs
+
+Swap list
+---------
+  docs/_swap.txt — one stem per line, relative to docs/, comments (#) skipped.
+  Example:
+      # migrated pages
+      configuration/firewall/zone
+      quick-start
+
+State files (in docs/_build/, gitignored)
+-----------------------------------------
+  _swap_state.json  — records completed renames
+  _swap_exclude.txt — RST paths to pass to Sphinx exclude_patterns
+"""
+
+import argparse
+import json
+import os
+import sys
+from pathlib import Path
+
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+STATE_FILE = "_swap_state.json"
+EXCLUDE_FILE = "_swap_exclude.txt"
+SWAP_LIST_FILE = "_swap.txt"
+STATE_VERSION = 1
+
+
+# ---------------------------------------------------------------------------
+# Core helpers
+# ---------------------------------------------------------------------------
+
+def parse_swap_list(path: Path) -> list:
+    """Read *path* and return a list of stems (comments/blanks skipped).
+
+    Returns [] if the file does not exist.
+    """
+    if not path.exists():
+        return []
+    stems = []
+    for line in path.read_text().splitlines():
+        stripped = line.strip()
+        if stripped and not stripped.startswith("#"):
+            stems.append(stripped)
+    return stems
+
+
+def _build_dir(docs_dir: Path) -> Path:
+    build = docs_dir / "_build"
+    build.mkdir(parents=True, exist_ok=True)
+    return build
+
+
+def _state_path(docs_dir: Path) -> Path:
+    return docs_dir / "_build" / STATE_FILE
+
+
+def _exclude_path(docs_dir: Path) -> Path:
+    return docs_dir / "_build" / EXCLUDE_FILE
+
+
+def _resolve_stem_paths(docs_dir: Path, stem: str):
+    """Return (md_from, md_to, rst_path) as absolute Paths for a given stem."""
+    p = Path(stem)
+    name = p.name
+    parent = p.parent  # may be PosixPath('.')
+    if str(parent) == ".":
+        target_dir = docs_dir
+    else:
+        target_dir = docs_dir / parent
+
+    md_from = target_dir / f"md-{name}.md"    # source: md-prefixed
+    md_to = target_dir / f"{name}.md"          # destination: plain .md
+    rst_path = target_dir / f"{name}.rst"      # RST that will be excluded
+    return md_from, md_to, rst_path
+
+
+# ---------------------------------------------------------------------------
+# do_swap
+# ---------------------------------------------------------------------------
+
+def do_swap(docs_dir: Path) -> None:
+    """Rename md-{name}.md → {name}.md for each stem in _swap.txt.
+
+    Validates collisions, records state, writes exclude file.
+    Rolls back all completed renames on any failure.
+    """
+    docs_dir = Path(docs_dir)
+    swap_list = parse_swap_list(docs_dir / SWAP_LIST_FILE)
+    if not swap_list:
+        print("swap_sources: no stems in swap list, nothing to do.", file=sys.stderr)
+        return
+
+    # Stale state: warn and auto-restore first
+    state_path = _state_path(docs_dir)
+    if state_path.exists():
+        print(
+            "swap_sources: WARNING — stale swap state detected. Auto-restoring before new swap.",
+            file=sys.stderr,
+        )
+        do_restore(docs_dir)
+
+    # Validate all stems before touching the filesystem
+    planned = []  # list of (md_from, md_to, rst_path, stem)
+    for stem in swap_list:
+        md_from, md_to, rst_path = _resolve_stem_paths(docs_dir, stem)
+
+        if not md_from.exists():
+            print(
+                f"swap_sources: skipping {stem!r} — md- source file not found: {md_from}",
+                file=sys.stderr,
+            )
+            continue
+
+        if not rst_path.exists():
+            print(
+                f"swap_sources: skipping {stem!r} — RST file not found: {rst_path}",
+                file=sys.stderr,
+            )
+            continue
+
+        if md_to.exists():
+            raise RuntimeError(
+                f"collision: both RST and unprefixed .md exist for stem {stem!r}. "
+                f"Remove {md_to} before swapping."
+            )
+
+        planned.append((md_from, md_to, rst_path, stem))
+
+    # Execute renames with rollback on failure
+    completed = []  # list of (md_from, md_to) that succeeded
+    try:
+        for md_from, md_to, rst_path, stem in planned:
+            os.rename(md_from, md_to)
+            completed.append((md_from, md_to))
+    except Exception as exc:
+        # Rollback completed renames in reverse order
+        for from_path, to_path in reversed(completed):
+            try:
+                os.rename(to_path, from_path)
+            except Exception as rollback_exc:
+                print(
+                    f"swap_sources: ROLLBACK ERROR for {to_path}: {rollback_exc}",
+                    file=sys.stderr,
+                )
+        raise RuntimeError(f"swap_sources: rename failed, rolled back. Cause: {exc}") from exc
+
+    if not completed:
+        return
+
+    # Build state and exclude data using relative paths (relative to docs_dir)
+    _build_dir(docs_dir)
+    swaps = []
+    exclude_lines = []
+    for md_from, md_to, rst_path, stem in planned:
+        rel_from = md_from.relative_to(docs_dir)
+        rel_to = md_to.relative_to(docs_dir)
+        rel_rst = rst_path.relative_to(docs_dir)
+        swaps.append({
+            "stem": stem,
+            "md_from": str(rel_from),
+            "md_to": str(rel_to),
+            "rst_excluded": str(rel_rst),
+        })
+        exclude_lines.append(str(rel_rst))
+
+    state = {"version": STATE_VERSION, "swaps": swaps}
+    state_path.write_text(json.dumps(state, indent=2))
+    _exclude_path(docs_dir).write_text("\n".join(exclude_lines) + "\n")
+
+    print(f"swap_sources: swapped {len(completed)} file(s).", file=sys.stderr)
+
+
+# ---------------------------------------------------------------------------
+# do_restore
+# ---------------------------------------------------------------------------
+
+def do_restore(docs_dir: Path) -> None:
+    """Undo all renames recorded in _swap_state.json (reverse order)."""
+    docs_dir = Path(docs_dir)
+    state_path = _state_path(docs_dir)
+
+    if not state_path.exists():
+        return  # no-op
+
+    state = json.loads(state_path.read_text())
+    swaps = state.get("swaps", [])
+
+    for entry in reversed(swaps):
+        md_from = docs_dir / entry["md_from"]   # original source (md-prefixed)
+        md_to = docs_dir / entry["md_to"]        # current location (plain .md)
+        if md_to.exists():
+            os.rename(md_to, md_from)
+        else:
+            print(
+                f"swap_sources: WARNING — expected swapped file not found: {md_to}",
+                file=sys.stderr,
+            )
+
+    # Clean up state and exclude files
+    state_path.unlink(missing_ok=True)
+    exclude_path = _exclude_path(docs_dir)
+    exclude_path.unlink(missing_ok=True)
+
+    print(f"swap_sources: restored {len(swaps)} file(s).", file=sys.stderr)
+
+
+# ---------------------------------------------------------------------------
+# do_dry_run / do_status
+# ---------------------------------------------------------------------------
+
+def do_dry_run(docs_dir: Path) -> None:
+    """Print what would be swapped without making any changes."""
+    docs_dir = Path(docs_dir)
+    swap_list = parse_swap_list(docs_dir / SWAP_LIST_FILE)
+    if not swap_list:
+        print("(dry-run) No stems in swap list.")
+        return
+
+    for stem in swap_list:
+        md_from, md_to, rst_path = _resolve_stem_paths(docs_dir, stem)
+        issues = []
+        if not md_from.exists():
+            issues.append("md- source missing")
+        if not rst_path.exists():
+            issues.append("RST missing")
+        if md_to.exists():
+            issues.append("COLLISION: plain .md already exists")
+        if issues:
+            print(f"  SKIP  {stem}: {', '.join(issues)}")
+        else:
+            print(f"  SWAP  {md_from.name} → {md_to.name}  (in {md_from.parent.relative_to(docs_dir) if md_from.parent != docs_dir else '.'})")
+
+
+def do_status(docs_dir: Path) -> None:
+    """Show current swap state."""
+    docs_dir = Path(docs_dir)
+    state_path = _state_path(docs_dir)
+    if not state_path.exists():
+        print("swap_sources: no active swap state.")
+        return
+
+    state = json.loads(state_path.read_text())
+    swaps = state.get("swaps", [])
+    print(f"swap_sources: {len(swaps)} file(s) currently swapped:")
+    for entry in swaps:
+        print(f"  {entry['md_from']} → {entry['md_to']}  (excludes {entry['rst_excluded']})")
+
+
+# ---------------------------------------------------------------------------
+# CLI
+# ---------------------------------------------------------------------------
+
+def main(argv=None):
+    parser = argparse.ArgumentParser(
+        description="Swap md-prefixed MyST files in place of RST files before Sphinx builds."
+    )
+    group = parser.add_mutually_exclusive_group(required=True)
+    group.add_argument("--swap", action="store_true", help="Perform swap")
+    group.add_argument("--restore", action="store_true", help="Restore original files")
+    group.add_argument("--dry-run", action="store_true", help="Show what would be swapped")
+    group.add_argument("--status", action="store_true", help="Show current swap state")
+
+    parser.add_argument(
+        "--docs-dir",
+        type=Path,
+        default=None,
+        help="Path to docs/ directory (default: auto-detected from script location)",
+    )
+
+    args = parser.parse_args(argv)
+
+    if args.docs_dir is None:
+        # Default: repo_root/docs where repo_root = parent of scripts/
+        repo_root = Path(__file__).resolve().parent.parent
+        docs_dir = repo_root / "docs"
+    else:
+        docs_dir = args.docs_dir.resolve()
+
+    if not docs_dir.is_dir():
+        parser.error(f"docs directory not found: {docs_dir}")
+
+    if args.swap:
+        import atexit
+        atexit.register(do_restore, docs_dir)
+        do_swap(docs_dir)
+    elif args.restore:
+        do_restore(docs_dir)
+    elif args.dry_run:
+        do_dry_run(docs_dir)
+    elif args.status:
+        do_status(docs_dir)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tests/test_swap_sources.py b/tests/test_swap_sources.py
new file mode 100644
index 00000000..8576e056
--- /dev/null
+++ b/tests/test_swap_sources.py
@@ -0,0 +1,238 @@
+"""Tests for swap_sources.py — run with:
+  cd tests && PYTHONPATH=../scripts python -m pytest test_swap_sources.py -v
+"""
+import json
+import os
+import sys
+from pathlib import Path
+
+import pytest
+
+# ---------------------------------------------------------------------------
+# Helper
+# ---------------------------------------------------------------------------
+
+def _setup_docs(tmp_path: Path, stems: list[str]) -> Path:
+    """Create a minimal docs/ tree with RST + md-prefixed MD files for each stem."""
+    docs = tmp_path / "docs"
+    for stem in stems:
+        p = Path(stem)
+        name = p.name
+        parent = p.parent  # may be "." for flat stems
+        target_dir = docs / parent if str(parent) != "." else docs
+        target_dir.mkdir(parents=True, exist_ok=True)
+        # RST file that would normally be the Sphinx source
+        (target_dir / f"{name}.rst").write_text(f".. _{name}:\n\nDummy RST for {stem}\n")
+        # md- prefixed MyST file waiting to be swapped in
+        (target_dir / f"md-{name}.md").write_text(f"# {name}\nDummy MyST for {stem}\n")
+    return docs
+
+
+# ---------------------------------------------------------------------------
+# parse_swap_list
+# ---------------------------------------------------------------------------
+
+def test_parse_swap_list_basic(tmp_path):
+    from swap_sources import parse_swap_list
+
+    swap_txt = tmp_path / "_swap.txt"
+    swap_txt.write_text(
+        "# comment\n"
+        "\n"
+        "configuration/firewall/zone\n"
+        "  quick-start  \n"  # leading/trailing whitespace
+        "# another comment\n"
+        "installation/virtual/vmware\n"
+    )
+    stems = parse_swap_list(swap_txt)
+    assert stems == [
+        "configuration/firewall/zone",
+        "quick-start",
+        "installation/virtual/vmware",
+    ]
+
+
+def test_parse_swap_list_empty(tmp_path):
+    from swap_sources import parse_swap_list
+
+    missing = tmp_path / "_swap.txt"
+    assert parse_swap_list(missing) == []
+
+
+# ---------------------------------------------------------------------------
+# do_swap
+# ---------------------------------------------------------------------------
+
+def test_swap_renames_files(tmp_path):
+    from swap_sources import do_swap
+
+    stems = ["quick-start"]
+    docs = _setup_docs(tmp_path, stems)
+    (tmp_path / "docs" / "_swap.txt").write_text("quick-start\n")
+
+    do_swap(docs)
+
+    assert (docs / "quick-start.md").exists(), "md- file should be renamed to plain .md"
+    assert not (docs / "md-quick-start.md").exists(), "md- prefix file should be gone"
+    assert (docs / "quick-start.rst").exists(), "RST file should still exist"
+
+
+def test_swap_creates_state_file(tmp_path):
+    from swap_sources import do_swap
+
+    stems = ["quick-start"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("quick-start\n")
+
+    do_swap(docs)
+
+    state_file = docs / "_build" / "_swap_state.json"
+    assert state_file.exists(), "state file should be created in _build/"
+
+    state = json.loads(state_file.read_text())
+    assert state["version"] == 1
+    assert len(state["swaps"]) == 1
+
+    entry = state["swaps"][0]
+    assert entry["stem"] == "quick-start"
+    assert "md_from" in entry
+    assert "md_to" in entry
+    assert "rst_excluded" in entry
+
+
+def test_swap_creates_exclude_file(tmp_path):
+    from swap_sources import do_swap
+
+    stems = ["quick-start"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("quick-start\n")
+
+    do_swap(docs)
+
+    exclude_file = docs / "_build" / "_swap_exclude.txt"
+    assert exclude_file.exists(), "exclude file should be created in _build/"
+
+    lines = [l.strip() for l in exclude_file.read_text().splitlines() if l.strip()]
+    assert "quick-start.rst" in lines
+
+
+# ---------------------------------------------------------------------------
+# do_restore
+# ---------------------------------------------------------------------------
+
+def test_restore_undoes_renames(tmp_path):
+    from swap_sources import do_restore, do_swap
+
+    stems = ["quick-start"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("quick-start\n")
+
+    do_swap(docs)
+    assert (docs / "quick-start.md").exists()
+
+    do_restore(docs)
+
+    assert (docs / "md-quick-start.md").exists(), "md- prefix file should be restored"
+    assert not (docs / "quick-start.md").exists(), "plain .md should be gone after restore"
+
+    state_file = docs / "_build" / "_swap_state.json"
+    exclude_file = docs / "_build" / "_swap_exclude.txt"
+    assert not state_file.exists(), "state file should be deleted after restore"
+    assert not exclude_file.exists(), "exclude file should be deleted after restore"
+
+
+def test_restore_noop_without_state(tmp_path):
+    from swap_sources import do_restore
+
+    docs = tmp_path / "docs"
+    docs.mkdir()
+    # Should not raise even with no state file
+    do_restore(docs)  # no error = pass
+
+
+# ---------------------------------------------------------------------------
+# Collision / validation
+# ---------------------------------------------------------------------------
+
+def test_swap_fails_on_collision(tmp_path):
+    from swap_sources import do_swap
+
+    stems = ["quick-start", "cli"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("quick-start\ncli\n")
+
+    # Simulate a collision: unprefixed .md already exists for "cli"
+    (docs / "cli.md").write_text("# collision\n")
+
+    with pytest.raises(RuntimeError, match="collision"):
+        do_swap(docs)
+
+    # Rollback: first stem's rename should be undone
+    assert (docs / "md-quick-start.md").exists(), "rollback should undo completed renames"
+    assert not (docs / "quick-start.md").exists(), "renamed file should not exist after rollback"
+
+    # State file should NOT be written on failure
+    state_file = docs / "_build" / "_swap_state.json"
+    assert not state_file.exists(), "no state file should be written on failure"
+
+
+# ---------------------------------------------------------------------------
+# Rollback on rename failure (monkeypatched os.rename)
+# ---------------------------------------------------------------------------
+
+def test_swap_rollback_on_rename_failure(tmp_path, monkeypatch):
+    """If os.rename raises on the second call, the first rename must be undone."""
+    from swap_sources import do_swap
+
+    stems = ["quick-start", "cli"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("quick-start\ncli\n")
+
+    call_count = {"n": 0}
+    real_rename = os.rename
+
+    def failing_rename(src, dst):
+        call_count["n"] += 1
+        if call_count["n"] == 2:
+            raise OSError("simulated rename failure")
+        real_rename(src, dst)
+
+    monkeypatch.setattr(os, "rename", failing_rename)
+
+    with pytest.raises(RuntimeError):
+        do_swap(docs)
+
+    # First rename (quick-start) should have been rolled back
+    assert (docs / "md-quick-start.md").exists(), "rollback should undo the first rename"
+    assert not (docs / "quick-start.md").exists(), "renamed file should not exist after rollback"
+
+    # No state file should exist
+    assert not (docs / "_build" / "_swap_state.json").exists()
+
+
+# ---------------------------------------------------------------------------
+# Nested paths
+# ---------------------------------------------------------------------------
+
+def test_swap_nested_paths(tmp_path):
+    from swap_sources import do_swap, do_restore
+
+    stems = ["configuration/firewall/zone"]
+    docs = _setup_docs(tmp_path, stems)
+    (docs / "_swap.txt").write_text("configuration/firewall/zone\n")
+
+    do_swap(docs)
+
+    swapped = docs / "configuration" / "firewall" / "zone.md"
+    md_source = docs / "configuration" / "firewall" / "md-zone.md"
+    assert swapped.exists(), "nested md file should be renamed"
+    assert not md_source.exists()
+
+    exclude_file = docs / "_build" / "_swap_exclude.txt"
+    lines = [l.strip() for l in exclude_file.read_text().splitlines() if l.strip()]
+    assert "configuration/firewall/zone.rst" in lines
+
+    do_restore(docs)
+
+    assert md_source.exists(), "nested md- file should be restored"
+    assert not swapped.exists()