fabi/Syplheed-Reborn
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Cutscene voice: resolve movies via continuous-stream cue regions

Browse Source 
Cracked how the game maps a movie to its voice track and reimplemented it,
fixing wrong/short voices for RT and hokyu cutscenes.

## Mechanism (RE'd from a Canary file-I/O trace, user-confirmed by ear)

The movie voices are ONE continuous XMA stream, physically chunked into
`<lang>\Movie\VOICE_*.slb` (and `\etc\VOICE_D_*.slb`) sound.pak TOC entries
whose boundaries do NOT align with the cutscene cues. A single cue routinely
spans two `.slb` chunks, so a `.slb` does not necessarily hold the track its
name claims (they are off-by-one vs the cues). Each cue ends at an inline
trailer descriptor `(sound_id:u32be, 0x11, …)` whose id repeats at +0x800.

Resolution chain (all derivable on-disc, no guest-code RE):
  1. movie -> cue token         (ADVERTISE_MOVIE manifest VOICETRACK)
  2. cue token -> sound-id       (master sound registry, tables.pak
                                  a2c8c185=eng / b04238e0=jpn, schema 0x13cb84ba)
  3. sound-id -> [start,end)      scan the stream for trailer(id) and its
                                  predecessor; cue audio = the bytes between,
                                  read continuously across chunk boundaries.

Validated: decoded voice length matches each movie within ~0.4s, including
cross-boundary cues (ADV/RT01A/RT01B/RT01C/S00A/S01A + the 5 bound hokyu).

## Changes

- sylpheed-formats/src/movie_voice.rs (new): registry_voice_ids(),
  find_descriptor(), find_descriptor_before() (gap-tolerant predecessor).
  Unit-tested.
- viewer iso_loader.rs: resolve_movie_voice_region() + decode_voice_region()
  (continuous read via existing read_segment_range + to_xma_riffs). Voice/
  audio requests now region-first; a `\Movie\` token that fails region stays
  SILENT (never plays the wrong off-by-one chunk). Removed the old
  movie_is_demo_based suppress hack.
- Anchor tries subdirs Movie/etc/Voice so hokyu `\etc\VOICE_D_*` resolve too.
- Examples resolve_all/validate_cues/hokyu_final document + validate the pipeline.

## Status

- RT / S / ADV cutscene voices: CORRECT (user-confirmed).
- 5 manifest-bound hokyu (VOICE_D_450-454): CORRECT (user-confirmed).

## OPEN (handoff)

13 of 18 hokyu movies have NO manifest VOICETRACK; the game reuses the 5
recordings across stages via a code rule. `hokyu_fallback_token()` currently
guesses by category (ship LS/DS x source carrier-A/tanker-H: LS/A->450,
LS/H->453, DS/A->452, DS/H->454). USER REPORTS THIS IS SOMETIMES WRONG.
- LS/carrier has two takes (450 from s02A, 451 from s09A); the early-vs-late
  split is unknown — unbound LS/A currently all default to 450.
- Definitive fix = Canary `--phase_a_fileio_only` file.read trace of an unbound
  hokyu (e.g. hokyu_LS_s03A) to see which VOICE_D the game actually streams,
  then encode the real rule. Same method that cracked the RT mapping.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-23 06:53:55 +02:00
parent ed5c2f24c3
commit 053aa81953
9 changed files with 577 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
crates/sylpheed-formats/examples/hokyu_final.rs Normal file
View File

@@ -0,0 +1,36 @@
use sylpheed_formats::{hash::name_hash, movie_manifest, movie_voice, slb, PakArchive};
use std::fs;use std::io::{Read,Seek,SeekFrom};use std::process::Command;
fn rg(disc:&str,g:u64,n:usize)->Vec<u8>{let mut segs=vec![];let mut cum=0u64;for i in 0..5{let p=format!("{disc}/dat/sound.p{i:02}");if let Ok(m)=fs::metadata(&p){segs.push((cum,m.len(),p));cum+=m.len();}}let mut out=vec![];let(mut need,mut pos)=(n,g);for(base,len,path)in &segs{if need==0||pos>=base+len||pos<*base{continue;}let local=pos-base;let take=need.min((len-local)as usize);let mut f=fs::File::open(path).unwrap();f.seek(SeekFrom::Start(local)).unwrap();let mut b=vec![0u8;take];f.read_exact(&mut b).unwrap();out.extend_from_slice(&b);need-=take;pos+=take as u64;}out}
fn contains(h:&[u8],n:&[u8])->bool{h.windows(n.len()).any(|w|w==n)}
fn dur(w:&str)->String{let o=Command::new("ffprobe").args(["-v","error","-show_entries","format=duration","-of","default=nw=1:nk=1",w]).output().unwrap();String::from_utf8_lossy(&o.stdout).trim().to_string()}
fn hokyu_fallback(m:&str)->Option<String>{if !m.starts_with("hokyu_"){return None}let ls=m.contains("_LS_");let ds=m.contains("_DS_");let a=m.ends_with('A');let h=m.ends_with('H');Some(match(ls,ds,a,h){(true,_,true,_)=>"VOICE_D_450",(true,_,_,true)=>"VOICE_D_453",(_,true,true,_)=>"VOICE_D_452",(_,true,_,true)=>"VOICE_D_454",_=>return None}.into())}
fn main(){
let disc=std::env::var("SYLPHEED_DISC").unwrap();
let tpak=PakArchive::open(format!("{disc}/dat/tables.pak")).unwrap();
let manifest=tpak.entries().iter().find_map(|e|tpak.read(e).ok().filter(|b|movie_manifest::is_manifest(b))).unwrap();
let code="eng";
let registry=tpak.entries().iter().find_map(|e|tpak.read(e).ok().filter(|b|contains(b,format!("{code}\\Movie\\VOICE_ADV.slb").as_bytes()))).unwrap();
let ids=movie_voice::registry_voice_ids(&registry);
let stoc=fs::read(format!("{disc}/dat/sound.pak")).unwrap();
let entries=PakArchive::parse_toc(&stoc).unwrap();
let hokyu:Vec<String>=movie_manifest::parse(&manifest).into_iter().filter(|m|m.movie.starts_with("hokyu_")).map(|m|m.movie).collect();
for movie in &hokyu{
let bound=movie_manifest::voice_token(&manifest,movie);
let token=bound.clone().or_else(||hokyu_fallback(movie));
let Some(token)=token else{println!("{movie:16} NO TOKEN"); continue};
let src = if bound.is_some(){"bound"}else{"fallback"};
let Some(&id)=ids.get(&token) else{println!("{movie:16} {token} not in registry");continue};
let Some(anchor)=["Movie","etc","Voice"].iter().find_map(|d|{let h=name_hash(&format!("{code}\\{d}\\{token}.slb"));entries.binary_search_by_key(&h,|e|e.name_hash).ok().map(|i|entries[i].offset as u64)}) else{println!("{movie:16} no anchor");continue};
let win_start=(anchor.saturating_sub(2*1024*1024))&!3;
let window=rg(&disc,win_start,8*1024*1024);
let Some(el)=movie_voice::find_descriptor(&window,id) else{println!("{movie:16} desc not found");continue};
let end=win_start+el as u64;
let start=movie_voice::find_descriptor(&window,id.wrapping_sub(1)).or_else(||movie_voice::find_descriptor_before(&window,el)).map(|o|win_start+o as u64).filter(|&s|s<end&&end-s<1_500_000).unwrap_or(anchor);
let region=rg(&disc,start,(end-start)as usize);
let mut riffs=slb::to_xma_riffs(&region); if riffs.is_empty(){riffs=slb::to_xma_riff_best(&region).into_iter().collect();}
let mut d="?".into();
if let Some(r)=riffs.first(){let xp=format!("/tmp/hf_{movie}.xma.wav");let wp=format!("/tmp/hf_{movie}.wav");fs::write(&xp,r).unwrap();let _=Command::new("ffmpeg").args(["-hide_banner","-v","error","-y","-i",&xp,&wp]).status();d=dur(&wp);}
let mv=dur(&format!("{disc}/dat/movie/{movie}.wmv"));
println!("{movie:16} {src:8} {token:12} id={id} voice={d}s movie={mv}s");
}
}

36
crates/sylpheed-formats/examples/resolve_all.rs Normal file
View File

@@ -0,0 +1,36 @@
use sylpheed_formats::{hash::name_hash, movie_manifest, movie_voice, slb, PakArchive};
use std::fs;use std::io::{Read,Seek,SeekFrom};use std::process::Command;
fn rg(disc:&str,g:u64,n:usize)->Vec<u8>{let mut segs=vec![];let mut cum=0u64;for i in 0..5{let p=format!("{disc}/dat/sound.p{i:02}");if let Ok(m)=fs::metadata(&p){segs.push((cum,m.len(),p));cum+=m.len();}}let mut out=vec![];let(mut need,mut pos)=(n,g);for(base,len,path)in &segs{if need==0||pos>=base+len||pos<*base{continue;}let local=pos-base;let take=need.min((len-local)as usize);let mut f=fs::File::open(path).unwrap();f.seek(SeekFrom::Start(local)).unwrap();let mut b=vec![0u8;take];f.read_exact(&mut b).unwrap();out.extend_from_slice(&b);need-=take;pos+=take as u64;}out}
fn contains(h:&[u8],n:&[u8])->bool{h.windows(n.len()).any(|w|w==n)}
fn dur(w:&str)->String{let o=Command::new("ffprobe").args(["-v","error","-show_entries","format=duration","-of","default=nw=1:nk=1",w]).output().unwrap();String::from_utf8_lossy(&o.stdout).trim().to_string()}
fn main(){
let disc=std::env::var("SYLPHEED_DISC").unwrap();
let tpak=PakArchive::open(format!("{disc}/dat/tables.pak")).unwrap();
let manifest=tpak.entries().iter().find_map(|e|tpak.read(e).ok().filter(|b|movie_manifest::is_manifest(b))).unwrap();
let code="eng";
let registry=tpak.entries().iter().find_map(|e|tpak.read(e).ok().filter(|b|contains(b,format!("{code}\\Movie\\VOICE_ADV.slb").as_bytes()))).unwrap();
let ids=movie_voice::registry_voice_ids(&registry);
let stoc=fs::read(format!("{disc}/dat/sound.pak")).unwrap();
let entries=PakArchive::parse_toc(&stoc).unwrap();
for movie in ["ADV","RT01A","RT01B","RT01C_1","S00A","S01A","hokyu_LS_s02A","hokyu_LS_s09A","hokyu_LS_s02H","hokyu_DS_s07H"]{
let Some(token)=movie_manifest::voice_token(&manifest,movie) else { println!("{movie:16} no token"); continue };
let Some(&id)=ids.get(&token) else { println!("{movie:16} token {token} not in registry"); continue };
let Some(anchor)=["Movie","etc","Voice"].iter().find_map(|d|{let h=name_hash(&format!("{code}\\{d}\\{token}.slb"));entries.binary_search_by_key(&h,|e|e.name_hash).ok().map(|i|entries[i].offset as u64)}) else { println!("{movie:16} no anchor for {token}"); continue };
let win_start=(anchor.saturating_sub(2*1024*1024))&!3;
let window=rg(&disc,win_start,8*1024*1024);
let Some(end_local)=movie_voice::find_descriptor(&window,id) else { println!("{movie:16} id {id}: desc NOT FOUND"); continue };
let end=win_start+end_local as u64;
let start=movie_voice::find_descriptor(&window,id.wrapping_sub(1))
.or_else(||movie_voice::find_descriptor_before(&window,end_local))
.map(|o|win_start+o as u64)
.filter(|&s|s<end && end-s<1_500_000)
.unwrap_or(anchor);
let region=rg(&disc,start,(end-start) as usize);
let mut riffs=slb::to_xma_riffs(&region);
if riffs.is_empty(){ riffs=slb::to_xma_riff_best(&region).into_iter().collect(); }
let mut d="?".into();
if let Some(r)=riffs.first(){ let xp=format!("/tmp/ra2_{movie}.xma.wav");let wp=format!("/tmp/ra2_{movie}.wav");fs::write(&xp,r).unwrap();let _=Command::new("ffmpeg").args(["-hide_banner","-v","error","-y","-i",&xp,&wp]).status();d=dur(&wp);}
let mv=dur(&format!("{disc}/dat/movie/{movie}.wmv"));
println!("{movie:16} id={id:5} region={}KB riffs={} voice={d}s movie={mv}s", (end-start)/1024, riffs.len());
}
}

32
crates/sylpheed-formats/examples/validate_cues.rs Normal file
View File

@@ -0,0 +1,32 @@
use sylpheed_formats::slb;
use std::fs;use std::io::{Read,Seek,SeekFrom};use std::process::Command;
fn rg(disc:&str,g:u64,n:usize)->Vec<u8>{let mut segs=vec![];let mut cum=0u64;for i in 0..5{let p=format!("{disc}/dat/sound.p{i:02}");if let Ok(m)=fs::metadata(&p){segs.push((cum,m.len(),p));cum+=m.len();}}let mut out=vec![];let(mut need,mut pos)=(n,g);for(base,len,path)in &segs{if need==0||pos>=base+len||pos<*base{continue;}let local=pos-base;let take=need.min((len-local)as usize);let mut f=fs::File::open(path).unwrap();f.seek(SeekFrom::Start(local)).unwrap();let mut b=vec![0u8;take];f.read_exact(&mut b).unwrap();out.extend_from_slice(&b);need-=take;pos+=take as u64;}out}
fn dur(w:&str)->String{let o=Command::new("ffprobe").args(["-v","error","-show_entries","format=duration:stream=channels","-of","default=nw=1:nk=1",w]).output().unwrap();String::from_utf8_lossy(&o.stdout).replace('\n'," ")}
fn movdur(disc:&str,m:&str)->String{ dur(&format!("{disc}/dat/movie/{m}")) }
fn main(){
let disc=std::env::var("SYLPHEED_DISC").unwrap();
// descriptor trailer global offsets (from scan) => cue N data = [desc(N-1)..desc(N)]
// (id, end_off, movie)
let cues=[(1600u32,437044592u64,"ADV.wmv"),(1601,437345648,"RT01A.wmv"),(1602,437712240,"RT01B.wmv"),
(1603,438080880,"RT01C_1.wmv"),(1604,438451568,"RT01C_2.wmv"),(1605,438789488,"RT02A.wmv")];
for k in 1..cues.len(){
let (id,end,mov)=cues[k];
let start=cues[k-1].1;
let region=rg(&disc,start,(end-start) as usize + 12000); // +tail to include full data before next trailer
let riffs=slb::to_xma_riffs(&region);
let mut total=0.0f32; let mut parts=vec![];
for (j,r) in riffs.iter().enumerate(){
let xp=format!("/tmp/cue{id}_{j}.xma.wav"); let wp=format!("/tmp/cue{id}_{j}.wav");
fs::write(&xp,r).unwrap();
let _=Command::new("ffmpeg").args(["-hide_banner","-v","error","-y","-i",&xp,&wp]).status();
let d=dur(&wp); parts.push(d.clone());
total+=d.split_whitespace().next().unwrap_or("0").parse::<f32>().unwrap_or(0.0);
}
// spanning?
let span_adv_end=437547264u64;
let spans = start < span_adv_end && end > span_adv_end || (start/1_000 != end/1_000);
println!("cue {id} ({mov}): region[{start}..{end}] {} bytes, {} riff(s), Σ={:.1}s | movie={} parts={:?}",
end-start, riffs.len(), total, movdur(&disc,mov), parts);
}
println!("\nWAVs at /tmp/cue16XX_*.wav (listen: RT01B=1602, RT01C_1=1603, RT01C_2=1604)");
}