feat: validate every file of a folder

CONTRIBUTING.md

@@ -24,7 +24,8 @@ the most useful contribution.
 
 From a clone, the file goes to `bios/Manufacturer/Console/filename`, and
 `python scripts/validate_pr.py path/to/file` names that folder for a file still
-outside `bios/`. A file over the browser's 25 MB limit goes in that way.
+outside `bios/`. Given a folder, such as an old card's BIOS folder, it checks
+every file under it. A file over the browser's 25 MB limit goes in that way.
 
 ## Add a platform
 

scripts/generate_readme.py

@@ -931,7 +931,8 @@ the most useful contribution.
 
 From a clone, the file goes to `bios/Manufacturer/Console/filename`, and
 `python scripts/validate_pr.py path/to/file` names that folder for a file still
-outside `bios/`. A file over the browser's 25 MB limit goes in that way.
+outside `bios/`. Given a folder, such as an old card's BIOS folder, it checks
+every file under it. A file over the browser's 25 MB limit goes in that way.
 
 ## Add a platform
 

scripts/validate_pr.py

@@ -23,6 +23,7 @@ import os
 import re
 import subprocess
 import sys
+from pathlib import Path
 
 sys.path.insert(0, os.path.dirname(__file__))
 from common import (
@@ -301,8 +302,12 @@ def validate_file(
                                 "changed under bios/")
         return result
 
+    if os.path.isdir(filepath):
+        result.add_check(False, "Folder with no file in it")
+        return result
+
     if not os.path.isfile(filepath):
-        result.add_check(False, "Not a regular file")
+        result.add_check(False, "Not a regular file: a device, a pipe or a socket")
         return result
 
     result.size = os.path.getsize(filepath)
@@ -561,6 +566,26 @@ def get_changed_files() -> list[str]:
     ]
 
 
+def expand_folders(paths: list[str]) -> list[str]:
+    """Each folder named replaced by the files under it, subfolders included.
+
+    A card's BIOS folder was refused as "Not a regular file", and the
+    contributor had to list its files by hand. A link inside the folder
+    stays listed, so it is refused like a named one, and an empty folder
+    stays as itself to be reported.
+    """
+    out: list[str] = []
+    for path in paths:
+        if not os.path.isdir(path) or os.path.islink(path):
+            out.append(path)
+            continue
+        found = sorted(
+            str(f) for f in Path(path).rglob("*") if f.is_symlink() or f.is_file()
+        )
+        out.extend(found or [path])
+    return out
+
+
 def _files_to_validate(
     args: argparse.Namespace, parser: argparse.ArgumentParser
 ) -> list:
@@ -572,7 +597,7 @@ def _files_to_validate(
     if not args.changed:
         if not args.files:
             parser.error("No files specified. Use --changed or provide file paths.")
-        return args.files
+        return expand_folders(args.files)
     try:
         files = get_changed_files()
     except (RuntimeError, OSError) as exc:

tests/test_validate_pr.py

@@ -54,6 +54,17 @@ class FileShapeChecks(_Fixture):
             self.assertNotIn(label, markdown)
         self.assertIn("--changed", markdown)
 
+    def test_a_folder_is_read_file_by_file(self):
+        self._bios_file("card/bios/a.bin")
+        self._bios_file("card/bios/sub/b.bin")
+        (self.tmp / "empty").mkdir()
+        self.assertEqual(
+            validate_pr.expand_folders(["card", "empty", "loose.bin"]),
+            [str(Path("card/bios/a.bin")), str(Path("card/bios/sub/b.bin")), "empty", "loose.bin"],
+        )
+        result = validate_pr.validate_file("empty", None, EMPTY_HASHES)
+        self.assertIn("Folder with no file in it", result.to_markdown())
+
     def test_empty_file_fails(self):
         rel = self._bios_file("bios/Sony/PS/empty.bin", b"")
         result = validate_pr.validate_file(rel, None, EMPTY_HASHES)

wiki/tools.md

@@ -1349,7 +1349,7 @@ Further options, by script:
 | `romset_recipes.py` | `--dat-recipes PATH`, a snapshot or a directory of them (default `recipes/`) |
 | `split_pack.py` | `--max-size 1900M`, the ceiling per part (K, M, G, default 2G) |
 | `torrentzip.py` | `--check ZIP` reports conformance, `--rebuild ZIP -o OUT` normalizes an archive |
-| `validate_pr.py` | `--changed` takes the BIOS files the branch changes, `--markdown`, `--json` |
+| `validate_pr.py` | `--changed` takes the BIOS files the branch changes, a folder named checks every file under it, `--markdown`, `--json` |
 | `validate_site.py` | `--site-dir` (rendered site, default `website/dist`), `--base` (path the site is served under), `--max-errors N` |
 | `scraper/coreinfo_scraper.py` | `--compare-db database.json` lists the `.info` firmware the database lacks |
 | `scraper/mame_hash_scraper.py` | `--release mameNNNN --profile FILE --source-commit SHA --core NAME --built-by PLATFORM` writes the profile of a MAME build a platform compiles. `--devices --listxml FILE` documents in `mame.yml` every device set with dumped ROMs that the release's `-listxml` names (`isdevice="yes"`), with `--dry-run` to preview |