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

One language setting; localized in-memory speech per language

Browse Source
This commit is contained in:
Cristian Gora
2026-10-09 23:09:07 +02:00
parent 98ec2fe9c4
commit f29af40b37
40 changed files with 77414 additions and 77240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

105
ackit/banks.py
View File

@@ -14,6 +14,7 @@ import gzip
import hashlib
import io
import os
import re
import struct
from collections import defaultdict, namedtuple
@@ -155,9 +156,40 @@ class Scan:
self.issues = [] # (kind, detail)
_LANG = re.compile(rb"([\x01-\x10])\x00\x00\x00\x04\x00\x00\x00[A-Z]{3}\x00")
def bank_languages(data, start, imports, exports, banks, issues=None, rel=""):
"""{bank offset in data: language} for localized banks. A localized AkBank export starts with its list of
languages (FStrings, e.g. INT FRA ITA DEU ESN) and holds one bank per language, in that order
(docs/formats/banks.md). Banks of other exports are language-neutral (not in the result)."""
out = {}
akbank = {-(i + 1) for i, (c, o, _) in enumerate(imports) if c == "Class" and o == "AkBank"}
starts = sorted(bk.at for bk in banks)
for x in exports:
if x.cls not in akbank or x.size <= 0:
continue
o0 = x.offset - start
m = _LANG.search(data, o0, min(o0 + 256, o0 + x.size))
if not m:
continue
n = m.group(1)[0]
langs, o = [], m.start() + 4
for _ in range(n):
ln = struct.unpack_from("<i", data, o)[0]
langs.append(bytes(data[o + 4:o + 3 + ln]).decode("latin-1"))
o += 4 + ln
inside = [a for a in starts if o0 <= a < o0 + x.size]
if len(inside) != len(langs):
if issues is not None:
issues.append(("languages", "%s: %s has %d banks for %d languages" % (rel, x.name, len(inside), len(langs))))
continue
out.update(zip(inside, langs))
return out
def _bkpk_tables(data, packs):
"""BKPK tables (docs/formats/wad.md) embedded in a package: WAD entry -> media offsets/sizes."""
import re
for m in re.finditer(b"BKPK", data):
p = m.start()
if p + 0x48 > len(data) or struct.unpack_from("<I", data, p + 0x1C)[0] != 0x48:
@@ -189,14 +221,16 @@ def scan(cooked, progress=None, cooked_banks=None, files=None, visit=None):
except (PackageError, OSError) as e:
sc.issues.append(("unreadable", "%s: %s" % (rel, e)))
continue
lang_of = {}
if isinstance(r, Package):
names, _, exports = r.tables(data, start)
names, imports, exports = r.tables(data, start)
sc.names.update(names) # base names ...
sc.names.update(x.name for x in exports) # ... and numbered object names (Speech_X_04)
_bkpk_tables(data, sc.packs)
if visit:
visit(rel, r, start, data)
banks = list(find_banks(data))
lang_of = bank_languages(data, start, imports, exports, banks, sc.issues, rel)
else:
try:
banks = [Bank(data, 0)]
@@ -217,7 +251,8 @@ def scan(cooked, progress=None, cooked_banks=None, files=None, visit=None):
if kind == PREFETCH_HEAD:
sc.prefetch.add(m.id)
e = sc.media.setdefault(m.id, {"size": m.size, "sha1": set(), "head": w[:0x60], "banks": set(),
"kinds": set()})
"kinds": set(), "langs": set()})
e["langs"].add(lang_of.get(bk.at, ""))
e["sha1"].add(hashlib.sha1(w).hexdigest()[:16])
e["banks"].add(bk.id)
e["kinds"].add(kind)
@@ -270,39 +305,57 @@ def event_media(sc):
return out
def media_language(sc, m):
"""Language of a localized in-memory media ('' = language-neutral)."""
langs = sc.media[m].get("langs", set()) - {""}
return next(iter(langs)) if len(langs) == 1 else ""
def media_names(sc):
"""{media id: (display name, primary bank name)}: named after the most specific 'Play' event that
reaches the media, otherwise after its bank (<Bank>_<n>)."""
reaches the media, otherwise after its bank (<Bank>_<n>). Localized speech has one media per language
for the same line: they share the name, variations are numbered within a language. Names are unique
among the language-neutral media plus any one language (what a catalog shows at a time)."""
ev = event_media(sc)
best = {}
for name, ms in ev.items():
rank = (0 if name.lower().startswith("play") else 1, len(ms), name.lower())
for i, m in enumerate(ms):
if m in sc.media and (m not in best or rank < best[m][0]):
best[m] = (rank, name, i, len(ms))
groups = defaultdict(list)
for m in ms:
if m in sc.media:
groups[media_language(sc, m)].append(m)
for g in groups.values():
rank = (0 if name.lower().startswith("play") else 1, len(g), name.lower())
for i, m in enumerate(g):
if m not in best or rank < best[m][0]:
best[m] = (rank, name, i, len(g))
out = {}
taken = set()
for m, (_, name, i, n) in sorted(best.items(), key=lambda x: (x[1][1].lower(), x[1][2])):
nm = name if n == 1 else "%s_%d" % (name, i + 1)
if nm.lower() in taken:
nm = "%s_%08X" % (nm, m)
taken.add(nm.lower())
out[m] = nm
# the rest: by bank, numbered in media id order
per_bank = defaultdict(list)
taken = set() # (language, lower-case name)
def free(lang, nm):
k = nm.lower()
if lang:
return (lang, k) not in taken and ("", k) not in taken
return not any(n == k for _, n in taken)
def take(lang, nm, m, base):
if not free(lang, nm):
nm = "%s_%08X" % (base, m)
taken.add((lang, nm.lower()))
return nm
for m, (_, name, i, n) in sorted(best.items(), key=lambda x: (x[1][1].lower(), x[1][2], x[0])):
out[m] = take(media_language(sc, m), name if n == 1 else "%s_%d" % (name, i + 1), m, name)
# the rest: by bank (and language), numbered in media id order
groups = defaultdict(list)
for m, e in sc.media.items():
bank = sorted(sc.bank_names.get(b, "%08X" % b) for b in e["banks"])[0]
per_bank[bank].append(m)
if m in out:
out[m] = (out[m], bank)
for bank, ms in per_bank.items():
rest = sorted(m for m in ms if m not in out)
for i, m in enumerate(rest):
nm = "%s_%d" % (bank, i + 1)
if nm.lower() in taken:
nm = "%s_%08X" % (bank, m)
taken.add(nm.lower())
out[m] = (nm, bank)
else:
groups[(bank, media_language(sc, m))].append(m)
for (bank, lang), ms in sorted(groups.items()):
for i, m in enumerate(sorted(ms)):
out[m] = (take(lang, "%s_%d" % (bank, i + 1), m, bank), bank)
return out