gora/UnheardCity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Game line names across languages; RSubtitle; editor in three columns

Browse Source
This commit is contained in:
Cristian Gora
2026-10-10 02:14:06 +02:00
parent f29af40b37
commit ea3e44000a
40 changed files with 54018 additions and 53559 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
ackit/catalog.py
View File

@@ -84,16 +84,29 @@ def hash_names():
return _names
def load_characters(path=None):
"""{sound name (lower): 'Speaker' or 'A; B'} from data/catalog/characters.csv."""
def load_characters(path=None, lang=None):
"""{sound name (lower): 'Speaker' or 'A; B'} from data/catalog/characters.csv: the rows valid in every
language (keyed by the game's line names) plus the rows of `lang` (lines without a line name, labelled
by their position in that language's WAD)."""
path = path or os.path.join(catalog_dir(), "characters.csv")
out = {}
if os.path.exists(path):
for row in csv.DictReader(open(path, encoding="utf-8")):
out[row["name"].lower()] = row["character"]
if not row.get("language") or row["language"] == lang:
out[row["name"].lower()] = row["character"]
return out
def character_of(s, characters):
"""Verified speaker of a sound from a load_characters() map: by its names, and for the k-th take of a
line shown as NAME#k (an event playing several WEMs of one language) by the line name NAME."""
for n in s.names() + (s.name.split("#")[0],):
c = characters.get(n.lower())
if c:
return c
return ""
def read_csv(path):
out = []
for r in csv.DictReader(open(path, encoding="utf-8", newline="")):
@@ -160,7 +173,7 @@ 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()
characters = characters if characters is not None else load_characters()
characters = characters if characters is not None else load_characters(lang=archive)
wad = Wad(wad_path)
out = []
with open(wad_path, "rb") as f:
@@ -197,7 +210,7 @@ def scan_archive(archive, wad_path, characters=None, progress=None):
s.name, s.aliases = s.aliases[0], (s.name,)
for s in out:
s.characters_inferred = "; ".join(classify.infer_characters(s.name))
s.character = next((characters[a.lower()] for a in s.names() if a.lower() in characters), "")
s.character = character_of(s, characters)
return out
@@ -223,7 +236,7 @@ def bank_sounds(sc, characters=None):
sha1=next(iter(e["sha1"])) if len(e["sha1"]) == 1 else "")
s.group, s.category = classify.classify(name, bank=bank)
s.characters_inferred = "; ".join(classify.infer_characters(_CAMEL.sub("_", name + "_" + bank)))
s.character = next((characters[a.lower()] for a in s.names() if a.lower() in characters), "")
s.character = character_of(s, characters)
out.append(s)
out.sort(key=lambda s: (s.bank.lower(), s.name.lower()))
return out
@@ -264,6 +277,57 @@ def scan_banks(game, progress=None, characters=None, visit=None):
return bank_sounds(sc, characters), locs, sc
def speech_line_names(game, sc):
"""{WAD sound key: the game's name of that line} for every speech sound some event plays. The name is the
speech event (e.g. Speech_CH_ZERO_CH0_fight_intro_01): the same line has the same name in every language,
while the position of a variation inside a WAD entry differs between languages (WEMs are stored in
media-ID order and every language has its own media IDs). If several events reach a sound, the most
specific one (fewest sounds in that language) names it."""
ev = {n: ms for n, ms in banks.event_media(sc).items() if n.lower().startswith("speech_")}
owners = media_owners(game, sc, {m for ms in ev.values() for m in ms})
best = {}
for n, ms in ev.items():
keys = collections.defaultdict(set)
for m in ms:
if m in owners:
k = owners[m]
keys[k.split(":")[0]].add(k)
for lang, ks in keys.items():
for k in ks:
rank = (len(ks), n.lower())
if k not in best or rank < best[k][0]:
best[k] = (rank, n)
return {k: n for k, (_, n) in best.items()}
def apply_line_names(sounds, line_names):
"""Rename WAD speech sounds after the game's line names (see speech_line_names). The position-based name
stays available as alias NAME#i (single-WEM entries keep their entry name as alias)."""
used = collections.Counter()
for s in sounds:
ev = line_names.get(s.key)
if not ev:
continue
used[ev.lower()] += 1
name = ev if used[ev.lower()] == 1 else "%s#%d" % (ev, used[ev.lower()])
if ":" in s.target: # variation: keep NAME#i (position in this language's WAD)
pos = [a for a in s.names() if "#" in a]
s.aliases = tuple(pos)
else: # single WEM: the entry name stays an alias
s.aliases = (s.name,) + tuple(a for a in s.aliases if a != s.name)
s.name = name
taken = collections.Counter(s.name.lower() for s in sounds)
for s in sounds: # a positional name equal to another sound's line name -> NAME#i
if taken[s.name.lower()] > 1 and s.key not in line_names and ":" in s.target:
pos = [a for a in s.aliases if "#" in a]
if pos:
s.aliases, s.name = (s.name,), pos[0]
for s in sounds:
s.group, s.category = classify.classify(s.name)
s.characters_inferred = "; ".join(classify.infer_characters(s.name))
return sounds
def subtitle_links(game, sc, speech_names):
"""{speech event name: {language: sound key}}: event -> actions -> containers -> sounds -> the
per-language media of the line (exact, no name matching). The media is a streamed WAD sound, or an
@@ -288,12 +352,17 @@ def subtitle_links(game, sc, speech_names):
def scan_text(game, progress=None, characters=None):
"""One pass over every package: (bank sounds, bank locations, Scan, {lang: [SubLine]}, [SubLoc], issues)."""
"""One pass over every package: (bank sounds, bank locations, Scan, {lang: [SubLine]}, [SubLoc], issues,
{WAD sound key: game line name})."""
col = subtitles.Collector()
snd, locs, sc = scan_banks(game, progress, characters, visit=col)
line_names = speech_line_names(game, sc)
names = {n for n in sc.names if n.lower().startswith("speech_")} | set(line_names.values())
names |= {s.name for s in snd if s.name.lower().startswith("speech_")}
col.resolve(names)
links = subtitle_links(game, sc, list(col.dialogues))
texts, sublocs = subtitles.rows(col, links)
return snd, locs, sc, texts, sublocs, col.issues
return snd, locs, sc, texts, sublocs, col.issues, line_names
def load_subtitles(game, lang, progress=None):
@@ -307,7 +376,7 @@ def load_subtitles(game, lang, progress=None):
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)
_, _, _, 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)