Version 3.2.0: fast lists with loading spinners, names from the game files, INT docs and screenshots, cleanup

ackit/catalog.py

@@ -5,7 +5,8 @@ Sources, in order:
   1. data/catalog/<ARCHIVE>.csv  -- shipped catalog (instant) when the WAD fingerprint matches;
   2. otherwise a header scan of the WAD (a few seconds, cached in the user cache), classified with
      `classify` and labelled with data/catalog/characters.csv (speaker per sound name).
-Names follow the community hash list (ackit/data/hashlist.txt): an entry with one WEM is NAME
+Names come from the game: a WAD entry ID is the Wwise ID (FNV-1) of a soundbank listed in the game's
+CookedPCConsole/CookedBanks.txt (`bank_names`); an entry with one WEM is NAME
 (alias NAME_1), entries with n variations are NAME_1..NAME_n (alias NAME#i); stream-pack media are
 named by their ID or <Pack>_<ID>.
 """
@@ -21,10 +22,11 @@ from dataclasses import dataclass, asdict
 from . import banks, classify, subtitles
 from . import lines as lines_mod
 from .game import wad_fingerprint
+from .bnk import fnv1
 from .lines import bank_langs
 from .inject import pack_bnk_path
 from .pack import Pack
-from .paths import catalog_dir, package_data, user_dir
+from .paths import catalog_dir, user_dir
 from .wad import Wad
 
 FIELDS = ["archive", "target", "name", "aliases", "group", "category", "bank", "language", "line", "character",
@@ -78,21 +80,28 @@ class Sound:
 
 
 # --- static data ---------------------------------------------------------------------------
-_names = None
+_names = {}                     # cooked folder -> {Wwise ID: bank name}
 
 
-def hash_names():
-    global _names
-    if _names is None:
-        _names = {}
-        for ln in open(package_data("hashlist.txt"), encoding="latin-1"):
-            p = ln.rstrip("\r\n").split("\t")
-            if len(p) >= 2 and p[1]:
-                try:
-                    _names[int(p[0], 16)] = p[1]
-                except ValueError:
-                    pass
-    return _names
+def bank_names(cooked):
+    """{Wwise ID: name} of the game's soundbanks, from its own CookedBanks.txt (ID = FNV-1 of the name). They
+    name the WAD entries (each entry holds the streamed media of one bank) and the stream packs."""
+    key = os.path.normcase(os.path.abspath(cooked))
+    if key not in _names:
+        out = {}
+        p = os.path.join(cooked, "CookedBanks.txt")
+        if os.path.exists(p):
+            for ln in open(p, encoding="latin-1"):
+                n = ln.strip()
+                if n:
+                    out.setdefault(fnv1(n), n)
+        _names[key] = out
+    return _names[key]
+
+
+def cooked_of(wad_path):
+    """CookedPCConsole folder of a WAD (WADs are in CookedPCConsole/<language or SFX>/)."""
+    return os.path.dirname(os.path.dirname(os.path.abspath(wad_path)))
 
 
 def load_characters(path=None, lang=None):
@@ -180,7 +189,7 @@ def _walk_entry(f, offset, size):
 
 def scan_archive(archive, wad_path, characters=None, progress=None):
     """Header scan of one WAD -> [Sound]."""
-    names = hash_names()
+    names = bank_names(cooked_of(wad_path))
     characters = characters if characters is not None else load_characters(lang=archive)
     wad = Wad(wad_path)
     out = []