refactor: annotate every remaining signature

scripts/scraper/_hash_merge.py

@@ -537,7 +537,7 @@ def _append_new_entries(text: str, files: list[dict], original: str) -> str:
     return text
 
 
-def _yaml_scalar(value) -> str:
+def _yaml_scalar(value: object) -> str:
     """Quote a scalar so YAML reads back exactly what the source said.
 
     A MAME ROM named ``01`` written bare re-parses as the integer 1, and the

scripts/scraper/base_scraper.py

@@ -163,7 +163,7 @@ def fetch_bytes(
 class BaseScraper(ABC):
     """Abstract base class for platform BIOS requirement scrapers."""
 
-    def __init__(self, url: str = ""):
+    def __init__(self, url: str = "") -> None:
         self.url = url
         self._raw_data: str | None = None
 

scripts/scraper/batocera_scraper.py

@@ -249,7 +249,7 @@ def _resolve_truncated_md5(md5: str, md5_index: dict[str, str]) -> str:
 class Scraper(BaseScraper):
     """Scraper for batocera-systems Python dict."""
 
-    def __init__(self):
+    def __init__(self) -> None:
         self.tag = fetch_stable_tag()
         super().__init__(url=SOURCE_URL.format(tag=self.tag))
 
@@ -466,7 +466,7 @@ class Scraper(BaseScraper):
         return result
 
 
-def main():
+def main() -> None:
     from scripts.scraper.base_scraper import scraper_cli
 
     scraper_cli(Scraper, "Scrape batocera BIOS requirements")

scripts/scraper/bizhawk_scraper.py

@@ -331,7 +331,7 @@ def parse_firmware_database(
 class Scraper(BaseScraper):
     """BizHawk firmware database scraper."""
 
-    def __init__(self):
+    def __init__(self) -> None:
         self.tag = fetch_github_latest_version(GITHUB_REPO)
         super().__init__(url=SOURCE_URL.format(tag=self.tag))
 
@@ -386,7 +386,7 @@ class Scraper(BaseScraper):
         }
 
 
-def main():
+def main() -> None:
     scraper_cli(Scraper, "Scrape BizHawk BIOS requirements")
 
 

scripts/scraper/coreinfo_scraper.py

@@ -206,7 +206,7 @@ def _extract_md5_from_notes(info: dict) -> dict[str, str]:
 class Scraper(BaseScraper):
     """Scraper for libretro-core-info firmware declarations."""
 
-    def __init__(self):
+    def __init__(self) -> None:
         super().__init__()
         self._info_files: dict[str, dict] | None = None
 
@@ -303,7 +303,7 @@ class Scraper(BaseScraper):
         return {"version": version}
 
 
-def main():
+def main() -> None:
     """CLI entry point."""
     import argparse
 

scripts/scraper/dat_pack_importer.py

@@ -16,6 +16,7 @@ from __future__ import annotations
 import argparse
 import sys
 import zipfile
+from collections.abc import Iterator
 from datetime import datetime, timezone
 from pathlib import Path
 
@@ -50,7 +51,7 @@ def _bios_entries(source: str, dat: LogiqxDat) -> list[dict]:
     ]
 
 
-def _iter_dat_contents(pack: Path):
+def _iter_dat_contents(pack: Path) -> Iterator[tuple[str, bytes]]:
     """Yield (member name, content bytes) for DAT files in a pack.
 
     Accepts a ZIP archive or a directory of extracted DATs.

scripts/scraper/emudeck_scraper.py

@@ -221,7 +221,7 @@ class Scraper(BaseScraper):
 
     def __init__(
         self, checkbios_url: str = CHECKBIOS_URL, csv_base_url: str = CSV_BASE_URL
-    ):
+    ) -> None:
         super().__init__(url=checkbios_url)
         self.checkbios_url = checkbios_url
         self.csv_base_url = csv_base_url
@@ -492,7 +492,7 @@ class Scraper(BaseScraper):
         return sorted(cores)
 
 
-def main():
+def main() -> None:
     from scripts.scraper.base_scraper import scraper_cli
 
     scraper_cli(Scraper, "Scrape emudeck BIOS requirements")

scripts/scraper/libretro_scraper.py

@@ -125,7 +125,7 @@ def _core_info_files() -> list[str]:
 class Scraper(BaseScraper):
     """Scraper for libretro System.dat."""
 
-    def __init__(self, url: str = SOURCE_URL):
+    def __init__(self, url: str = SOURCE_URL) -> None:
         super().__init__(url=url)
 
     def fetch_requirements(self) -> list[BiosRequirement]:
@@ -516,7 +516,7 @@ class Scraper(BaseScraper):
         }
 
 
-def main():
+def main() -> None:
     from scripts.scraper.base_scraper import scraper_cli
 
     scraper_cli(Scraper, "Scrape libretro BIOS requirements")

scripts/scraper/misterfpga_scraper.py

@@ -126,7 +126,7 @@ def system_of(path: str) -> str:
 class Scraper(BaseScraper):
     """Scraper for the MiSTer BiosDB database."""
 
-    def __init__(self, url: str = SOURCE_URL):
+    def __init__(self, url: str = SOURCE_URL) -> None:
         super().__init__(url=url)
 
     def _fetch_raw(self) -> str:

scripts/scraper/recalbox_scraper.py

@@ -199,7 +199,7 @@ def board_cores(text: str, board: str, enabled: set[str]) -> set[str]:
 class Scraper(BaseScraper):
     """Scraper for Recalbox es_bios.xml."""
 
-    def __init__(self, tag: str | None = None):
+    def __init__(self, tag: str | None = None) -> None:
         # A target scraper passes the tag platforms/recalbox.yml pins.
         self.tag = tag or _fetch_gitlab_stable_tag()
         super().__init__(url=SOURCE_URL.format(tag=self.tag))
@@ -365,7 +365,7 @@ class Scraper(BaseScraper):
         }
 
 
-def main():
+def main() -> None:
     """CLI entry point."""
     from .base_scraper import scraper_cli
 

scripts/scraper/retrobat_scraper.py

@@ -88,7 +88,7 @@ SYSTEM_SLUG_MAP = {
 class Scraper(BaseScraper):
     """Scraper for RetroBat batocera-systems.json."""
 
-    def __init__(self, url: str = SOURCE_URL):
+    def __init__(self, url: str = SOURCE_URL) -> None:
         super().__init__(url=url)
         self._parsed: dict | None = None
 
@@ -227,7 +227,7 @@ class Scraper(BaseScraper):
         }
 
 
-def main():
+def main() -> None:
     from scripts.scraper.base_scraper import scraper_cli
 
     scraper_cli(Scraper, "Scrape retrobat BIOS requirements")

scripts/scraper/retropie_scraper.py

@@ -51,7 +51,7 @@ _PACKAGE_DIRS = ("emulators", "libretrocores", "ports")
 class Scraper(BaseScraper):
     """Scraper for the RetroPie package list."""
 
-    def __init__(self, url: str = SOURCE_URL):
+    def __init__(self, url: str = SOURCE_URL) -> None:
         super().__init__(url=url)
         self._modules: list[str] | None = None
         self._version = ""

scripts/scraper/rocknix_scraper.py

@@ -147,7 +147,7 @@ def parse_systems(source: str) -> dict[str, dict]:
 class Scraper(BaseScraper):
     """Scraper for the ROCKNIX rocknix-systems script."""
 
-    def __init__(self, url: str | None = None):
+    def __init__(self, url: str | None = None) -> None:
         self.tag = None if url else fetch_github_latest_version(GITHUB_REPO)
         super().__init__(url=url or SOURCE_TEMPLATE.format(ref=self.tag))
 

scripts/scraper/romm_scraper.py

@@ -122,7 +122,7 @@ FIRMWARE_MIRRORS: dict[str, tuple[str, ...]] = {
 class Scraper(BaseScraper):
     """Scraper for RomM known_bios_files.json."""
 
-    def __init__(self):
+    def __init__(self) -> None:
         self.tag = fetch_github_latest_version(GITHUB_REPO)
         super().__init__(url=SOURCE_URL.format(tag=self.tag))
         self._parsed: dict | None = None
@@ -225,7 +225,7 @@ class Scraper(BaseScraper):
         }
 
 
-def main():
+def main() -> None:
     from scripts.scraper.base_scraper import scraper_cli
 
     scraper_cli(Scraper, "Scrape RomM BIOS requirements")

scripts/scraper/romset_dat_importer.py

@@ -25,6 +25,7 @@ from __future__ import annotations
 
 import argparse
 import hashlib
+import io
 import json
 import os
 import re
@@ -32,6 +33,7 @@ import shutil
 import sys
 import urllib.request
 import zipfile
+from collections.abc import Callable, Iterator
 from datetime import datetime, timezone
 from pathlib import Path
 
@@ -146,7 +148,9 @@ def _machine_roms(blob: bytes) -> list[dict]:
     return members
 
 
-def _scan_listxml(stream, selector) -> dict[str, tuple[str | None, list[dict]]]:
+def _scan_listxml(
+    stream: io.BufferedIOBase, selector: Callable[[str], bool]
+) -> dict[str, tuple[str | None, list[dict]]]:
     """Stream a MAME -listxml document, keeping the machines *selector* wants.
 
     The document is 311 MB for MAME 0.289, so it is never held whole: the
@@ -178,7 +182,7 @@ def _scan_listxml(stream, selector) -> dict[str, tuple[str | None, list[dict]]]:
 
 
 def listxml_entries(
-    open_stream, label: str, keep: set[str] | None
+    open_stream: Callable[[], io.BufferedIOBase], label: str, keep: set[str] | None
 ) -> list[dict]:
     """Recipes from a MAME -listxml document, parents resolved.
 
@@ -291,7 +295,7 @@ def merge_snapshot(
     return write_snapshot(output, snapshot)
 
 
-def _iter_dat_contents(pack: Path):
+def _iter_dat_contents(pack: Path) -> Iterator[tuple[str, bytes]]:
     """Yield (member name, content bytes) for DAT files in *pack*."""
     if pack.is_dir():
         for path in sorted(pack.rglob("*")):
@@ -424,10 +428,10 @@ def _is_listxml(pack: Path) -> bool:
         return b"<!ELEMENT mame" in handle.read(4096)
 
 
-def _listxml_opener(pack: Path):
+def _listxml_opener(pack: Path) -> Callable[[], io.BufferedIOBase]:
     """A callable giving a fresh byte stream over the listxml document."""
     if pack.suffix.lower() == ".zip":
-        def opener():
+        def opener() -> zipfile.ZipExtFile:
             archive = zipfile.ZipFile(pack)
             name = next(n for n in archive.namelist() if n.lower().endswith(".xml"))
             stream = archive.open(name)

scripts/scraper/targets/__init__.py

@@ -15,7 +15,7 @@ from pathlib import Path
 class BaseTargetScraper(ABC):
     """Base class for target scrapers."""
 
-    def __init__(self, url: str = ""):
+    def __init__(self, url: str = "") -> None:
         self.url = url
 
     @abstractmethod

scripts/scraper/targets/batocera_targets_scraper.py

@@ -292,7 +292,9 @@ def _arch_from_flag(flag: str) -> str:
 class Scraper(BaseTargetScraper):
     """Cross-references Batocera boards, Config.in, and es_systems to build target lists."""
 
-    def __init__(self, url: str = "https://github.com/batocera-linux/batocera.linux"):
+    def __init__(
+        self, url: str = "https://github.com/batocera-linux/batocera.linux"
+    ) -> None:
         super().__init__(url=url)
         self.tag = ""
 

scripts/scraper/targets/emudeck_targets_scraper.py

@@ -90,7 +90,7 @@ def _script_to_core(filename: str) -> str | None:
 class Scraper(BaseTargetScraper):
     """Fetches emulator lists for EmuDeck SteamOS and Windows targets."""
 
-    def __init__(self, url: str = "https://github.com/dragoonDorise/EmuDeck"):
+    def __init__(self, url: str = "https://github.com/dragoonDorise/EmuDeck") -> None:
         super().__init__(url=url)
 
     def _fetch_cores_for_target(

scripts/scraper/targets/recalbox_targets_scraper.py

@@ -58,7 +58,7 @@ def defconfig_arch(defconfig: str) -> str:
 class Scraper(BaseTargetScraper):
     """Per-board core lists from Recalbox's defconfigs and system.ini files."""
 
-    def __init__(self, url: str = "https://gitlab.com/recalbox/recalbox"):
+    def __init__(self, url: str = "https://gitlab.com/recalbox/recalbox") -> None:
         super().__init__(url=url)
 
     def fetch_targets(self) -> dict:

scripts/scraper/targets/retroarch_targets_scraper.py

@@ -86,7 +86,7 @@ _CORE_NAME_RE = re.compile(r"^(.+?)_libretro")
 class Scraper(BaseTargetScraper):
     """Fetches core lists per target from RetroArch buildbot nightly."""
 
-    def __init__(self, url: str = BUILDBOT_URL):
+    def __init__(self, url: str = BUILDBOT_URL) -> None:
         super().__init__(url=url)
 
     def _fetch_url(self, url: str) -> str:

scripts/scraper/targets/retropie_targets_scraper.py

@@ -113,7 +113,7 @@ def _parse_module(content: str) -> tuple[str | None, str]:
 class Scraper(BaseTargetScraper):
     """Fetches RetroPie package availability by parsing scriptmodules."""
 
-    def __init__(self, url: str = GITHUB_API_URL):
+    def __init__(self, url: str = GITHUB_API_URL) -> None:
         super().__init__(url=url)
 
     def _list_scriptmodules(self) -> list[str]:

scripts/scraper/targets/rocknix_targets_scraper.py

@@ -127,7 +127,7 @@ def metapackage_cores(package_mk: str, arch: str) -> list[str]:
 class Scraper(BaseTargetScraper):
     """Per-device core lists from ROCKNIX's emulators metapackage."""
 
-    def __init__(self, url: str = "https://github.com/ROCKNIX/distribution"):
+    def __init__(self, url: str = "https://github.com/ROCKNIX/distribution") -> None:
         super().__init__(url=url)
         self.tag = ""