fix(clew): extract full archives by default

src/clew/README.md

@@ -12,7 +12,8 @@ bazel run //src/clew -- \
 ```
 
 The first version copies loose `.rpy` files and collects compiled script files.
-It extracts `.rpy`, `.rpyc`, and `.rpymc` files from `.rpa` archives.
+It extracts all files from `.rpa` archives.
+Use `--suffix` to limit archive extraction to selected file suffixes.
 It writes output under `source/`, `work/`, and `logs/`.
 
 Use `--force` to replace those Clew-managed directories.

src/clew/clew.py

@@ -11,7 +11,6 @@ from rpycdec.rpa import extract_rpa
 
 LOGGER = logging.getLogger("clew")
 MANAGED_DIRS = ("source", "work", "logs")
-SCRIPT_SUFFIXES = (".rpy", ".rpyc", ".rpymc")
 
 
 def parse_args(argv: list[str]) -> argparse.Namespace:
@@ -36,6 +35,11 @@ def parse_args(argv: list[str]) -> argparse.Namespace:
         action="store_true",
         help="Replace Clew-managed output directories.",
     )
+    parser.add_argument(
+        "--suffix",
+        action="append",
+        help="Extract only archive paths with this suffix.",
+    )
     return parser.parse_args(argv)
 
 
@@ -131,19 +135,45 @@ def archive_destination_prefix(archive_relative: Path) -> Path:
     return parent
 
 
-def extract_archive(archive: Path, game_root: Path, source_dir: Path, work_dir: Path) -> None:
+def normalize_suffixes(suffixes: list[str] | None) -> list[str] | None:
+    if suffixes is None:
+        return None
+
+    normalized = []
+    for suffix in suffixes:
+        if not suffix:
+            fail("suffix must not be empty")
+        if not suffix.startswith("."):
+            suffix = f".{suffix}"
+        normalized.append(suffix)
+    return normalized
+
+
+def extract_archive(
+    archive: Path,
+    game_root: Path,
+    source_dir: Path,
+    work_dir: Path,
+    suffixes: list[str] | None,
+) -> None:
     archive_relative = relative_to(game_root, archive)
     output_dir = archive_work_path(work_dir, archive_relative)
     output_dir.mkdir(parents=True, exist_ok=True)
 
     LOGGER.info("extracting archive: %s", archive_relative)
     with archive.open("rb") as handle:
-        extract_rpa(handle, output_dir=str(output_dir), suffixes=list(SCRIPT_SUFFIXES))
+        extract_rpa(handle, output_dir=str(output_dir), suffixes=suffixes)
     LOGGER.info("extracted archive: %s", archive_relative)
 
     destination_prefix = archive_destination_prefix(archive_relative)
     for source_file in sorted(output_dir.rglob("*.rpy")):
-        copy_source_file(source_file, output_dir, source_dir, "archived", destination_prefix)
+        copy_source_file(
+            source_file,
+            output_dir,
+            source_dir,
+            "archived",
+            destination_prefix,
+        )
 
 
 def configure_logging(logs_dir: Path) -> None:
@@ -166,6 +196,7 @@ def run(args: argparse.Namespace) -> None:
     if not game_root.is_dir():
         fail(f"game root is not a directory: {game_root}")
 
+    suffixes = normalize_suffixes(args.suffix)
     source_dir, work_dir, logs_dir = prepare_output(output_root, args.force)
     configure_logging(logs_dir)
 
@@ -180,7 +211,7 @@ def run(args: argparse.Namespace) -> None:
 
     LOGGER.info("scanning archives")
     for archive in sorted(game_root.rglob("*.rpa")):
-        extract_archive(archive, game_root, source_dir, work_dir)
+        extract_archive(archive, game_root, source_dir, work_dir, suffixes)
 
     LOGGER.info("done")