Edit subtitles and menu text

ackit/catalog.py

@@ -18,7 +18,7 @@ import re
 import struct
 from dataclasses import dataclass, asdict
 
-from . import banks, classify
+from . import banks, classify, subtitles
 from .game import wad_fingerprint
 from .inject import pack_bnk_path
 from .pack import Pack
@@ -228,9 +228,13 @@ def bank_sounds(sc, characters=None):
 
 
 def head_owners(game, sc, archives=None):
-    """{prefetch media id: WAD sound key} -- the speech line (one language) each prefetch head belongs to,
-    found through the per-language BKPK tables of the packages (docs/formats/banks.md)."""
-    want = {m for m, e in sc.media.items() if banks.PREFETCH_HEAD in e["kinds"]}
+    """{prefetch media id: WAD sound key} -- the speech line (one language) each prefetch head belongs to."""
+    return media_owners(game, sc, {m for m, e in sc.media.items() if banks.PREFETCH_HEAD in e["kinds"]}, archives)
+
+
+def media_owners(game, sc, want, archives=None):
+    """{media id: WAD sound key} for streamed speech media, found through the per-language BKPK tables of
+    the packages (docs/formats/banks.md): every language has its own media IDs for the same WAD entry."""
     out = {}
     for a in archives or [x for x in game.archives if x != "SFX"]:
         wad = Wad(game.wad(a))
@@ -250,14 +254,61 @@ def head_owners(game, sc, archives=None):
     return out
 
 
-def scan_banks(game, progress=None, characters=None):
+def scan_banks(game, progress=None, characters=None, visit=None):
     """Full scan of the game's banks -> ([Sound], [Location] with WAD keys on prefetch heads, Scan)."""
-    sc = banks.scan(game.cooked, progress)
+    sc = banks.scan(game.cooked, progress, visit=visit)
     owners = head_owners(game, sc)
     locs = [l._replace(sound=owners.get(l.media, "")) if l.kind == banks.PREFETCH_HEAD else l for l in sc.locations]
     return bank_sounds(sc, characters), locs, sc
 
 
+def subtitle_links(game, sc, speech_names):
+    """{speech event name: {language: WAD sound key}}: event -> actions -> containers -> sounds -> the
+    per-language media of the streamed speech line (exact, no name matching)."""
+    ev = banks.event_media(sc)
+    want = {m for n in speech_names for m in ev.get(n, ())}
+    owners = media_owners(game, sc, want)
+    out = {}
+    for n in speech_names:
+        keys = {}
+        for m in ev.get(n, ()):
+            k = owners.get(m)
+            if k:
+                keys.setdefault(k.split(":")[0], k)
+        if keys:
+            out[n] = keys
+    return out
+
+
+def scan_text(game, progress=None, characters=None):
+    """One pass over every package: (bank sounds, bank locations, Scan, {lang: [SubLine]}, [SubLoc], issues)."""
+    col = subtitles.Collector()
+    snd, locs, sc = scan_banks(game, progress, characters, visit=col)
+    links = subtitle_links(game, sc, list(col.dialogues))
+    texts, sublocs = subtitles.rows(col, links)
+    return snd, locs, sc, texts, sublocs, col.issues
+
+
+def load_subtitles(game, lang, progress=None):
+    """([SubLine], {SUB key: [SubLoc]}) of one language: shipped catalog when the game matches it, else a
+    cached or fresh scan of the packages (several minutes)."""
+    fp = banks.game_fingerprint(game.cooked)
+    shipped = _shipped_index().get("SUB", {})
+    t = os.path.join(catalog_dir(), "SUB_%s.csv" % lang)
+    loc = os.path.join(catalog_dir(), subtitles.LOCATIONS)
+    if shipped.get("fingerprint") == fp and os.path.exists(t) and os.path.exists(loc):
+        return subtitles.read_texts(t, lang), subtitles.read_locations(loc, lang)
+    cache = os.path.join(user_dir("cache"), "scan_SUB_%s_v%d" % (fp, SCAN_VERSION))
+    if not os.path.exists(cache + ".locations.csv.gz"):
+        _, _, _, texts, sublocs, _ = scan_text(game, progress)
+        for lg, rows in texts.items():
+            subtitles.write_texts(cache + "_%s.csv" % lg, rows)
+        subtitles.write_locations(cache + ".locations.csv.gz", sublocs)
+    t = cache + "_%s.csv" % lang
+    return (subtitles.read_texts(t, lang) if os.path.exists(t) else []), \
+        subtitles.read_locations(cache + ".locations.csv.gz", lang)
+
+
 def load_banks(game, progress=None):
     """([Sound], {media: [Location]}) of the in-memory sounds: shipped catalog when the game's bank set
     matches it, else a cached or fresh scan (several minutes)."""