change

cadfs_to_cdsl/cli.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import argparse, json
 from pathlib import Path
+from .describe import describe_samples
 from .pipeline import load_samples, run_stage, scan, select_samples
 from .reports import generate_markdown_report, generate_reports, read_json
 
@@ -12,11 +13,20 @@ DEFAULT_OUTPUT = Path("cadfs_to_cdsl/output")
 def _parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(description="Convert CADFS FeatureScript to CDSL and validate against STEP")
     commands = parser.add_subparsers(dest="command", required=True)
-    for name in ("scan", "convert", "rebuild", "compare", "report", "pipeline"):
+    for name in ("scan", "convert", "rebuild", "compare", "report", "pipeline", "describe"):
         command = commands.add_parser(name)
         command.add_argument("--input", type=Path, default=DEFAULT_INPUT)
         command.add_argument("--output", type=Path, default=DEFAULT_OUTPUT)
-        if name != "scan":
+        if name == "describe":
+            command.add_argument("--shard", help="input shard directory to describe, for example 0005")
+            command.add_argument("--sample-id", action="append")
+            command.add_argument("--offset", type=int, default=0)
+            command.add_argument("--limit", type=int)
+            command.add_argument("--seed", type=int)
+            command.add_argument("--workers", type=int, default=1)
+            command.add_argument("--mode", choices=("local", "hybrid", "vision"), default="hybrid")
+            command.add_argument("--force", action="store_true")
+        elif name != "scan":
             command.add_argument("--sample-id", action="append")
             command.add_argument("--offset", type=int, default=0)
             command.add_argument("--limit", type=int)
@@ -31,9 +41,23 @@ def _parser() -> argparse.ArgumentParser:
 
 
 def main(argv: list[str] | None = None) -> int:
-    args = _parser().parse_args(argv); args.output.mkdir(parents=True, exist_ok=True)
+    args = _parser().parse_args(argv)
+    if args.command != "describe":
+        args.output.mkdir(parents=True, exist_ok=True)
     if args.command == "scan":
         records = scan(args.input, args.output); result = {"sample_count": len(records), "output": str(args.output / "dataset_index.json")}
+    elif args.command == "describe":
+        records, result = describe_samples(
+            args.input,
+            shard=args.shard,
+            sample_ids=args.sample_id,
+            mode=args.mode,
+            offset=args.offset,
+            limit=args.limit,
+            seed=args.seed,
+            force=args.force,
+            workers=args.workers,
+        )
     elif args.command == "report":
         manifest = args.output / "manifest.jsonl"; records = [json.loads(line) for line in manifest.read_text().splitlines() if line.strip()]
         result = generate_reports(args.output, records)