1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
//! Pixelogic — `bluray_project.bin`
//!
//! Binary file with embedded UTF-8 token strings in STN order per
//! playlist section. Most common format (5/10 test discs).
//!
//! Token format: `{lang}_{codec?}_{purpose?}_{region?}_`
use super::{
Confidence, LabelPurpose, LabelQualifier, ParseResult, StreamLabel, StreamLabelType, text,
vocab,
};
use crate::sector::SectorSource;
use crate::udf::UdfFs;
use std::sync::atomic::{AtomicBool, Ordering};
/// Known audio codec tokens
const AUDIO_CODECS: &[&str] = &["MLP", "AC3", "DTS", "DDL", "WAV", "AC"];
/// Known region tokens
const REGIONS: &[&str] = &[
"US", "UK", "CF", "PF", "CS", "LS", "BP", "PP", "SM", "TM", "CAN", "DUM", "FLE",
];
pub fn detect(udf: &UdfFs) -> bool {
super::jar_file_exists(udf, "bluray_project.bin")
}
pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
let data = super::read_jar_file(reader, udf, "bluray_project.bin")?;
// min_len=4 matches the prior local extract_strings impl. The token
// grammar is `{lang3}_{codec?}_{purpose?}_{region?}_` so the
// shortest meaningful run is 4 chars (lang + underscore).
let strings = text::extract_ascii_strings(&data, 4);
// Tracked across all parse_token calls in this run: did any stream
// hit an unrecognized token component (skip-unknown path)? If yes
// we downgrade confidence to Medium — the labels are still valid
// but the corpus surfaced something we don't catalogue.
let saw_unknown = AtomicBool::new(false);
let labels = assign_labels(&strings, &saw_unknown);
if labels.is_empty() {
return None;
}
let confidence = if saw_unknown.load(Ordering::Relaxed) {
Confidence::Medium
} else {
Confidence::High
};
Some(ParseResult { labels, confidence })
}
/// Walk the extracted token strings of the feature section and emit a
/// `StreamLabel` per editorial token, numbered in STN order. Split out
/// from `parse` so the section/numbering logic is unit-testable without
/// a `SectorSource`/`UdfFs`.
fn assign_labels(strings: &[String], saw_unknown: &AtomicBool) -> Vec<StreamLabel> {
// The authoritative per-feature stream list lives in the `FPL_`
// (FeaturePLaylist) section, in STN order. `SEG_*` entries are menu
// segments (intros, logos, disclaimers, previews) that can also carry
// stray stream tokens — e.g. a `SEG_MainFeature` preview segment that
// lists only a commentary track. Anchoring on such a segment grabs the
// wrong streams and misnumbers them. So when the project ships any
// `FPL_` playlist, anchor exclusively on it; only fall back to
// `SEG_MainFeature` on discs that have no `FPL_` section at all.
let has_fpl = strings.iter().any(|s| s.starts_with("FPL_"));
let mut labels = Vec::new();
let mut in_feature = false;
let mut audio_num: u16 = 0;
let mut sub_num: u16 = 0;
for s in strings {
// Detect feature section start
let is_start = if has_fpl {
s.starts_with("FPL_")
} else {
s.starts_with("SEG_MainFeature")
};
if is_start {
if in_feature {
break;
}
in_feature = true;
audio_num = 0;
sub_num = 0;
continue;
}
// Detect section end
if in_feature && (s.starts_with("SEG_") || s.starts_with("SF_") || s.starts_with("FPL_")) {
break;
}
if !in_feature {
continue;
}
// Generic audio-slot placeholder. Pixelogic lists each audio stream
// in the playlist as either an editorial `{lang}_{codec}_…` token OR
// a bare `Audio Stream N` placeholder when no editorial label was
// authored. The placeholder carries nothing to label, but it DOES
// occupy an STN slot — so it must advance `audio_num`. Otherwise a
// later editorial token (e.g. a lone `eng_ACOM_` commentary sitting
// at STN slot 4, behind three unlabelled main tracks) collapses onto
// slot 1 and its Commentary purpose lands on the main feature track.
//
// Only audio is corrected here: subtitle (`PG Stream N`) numbering is
// left exactly as-is — the corpus snapshots show forced/commentary
// subtitle tokens already align with STN without counting the
// placeholders, and counting them regresses several discs.
if s.starts_with("Audio Stream") {
audio_num += 1;
continue;
}
if let Some(label) = parse_token_inner(s, Some(saw_unknown)) {
match label.stream_type {
StreamLabelType::Audio => {
audio_num += 1;
labels.push(StreamLabel {
stream_number: audio_num,
..label
});
}
StreamLabelType::Subtitle => {
sub_num += 1;
labels.push(StreamLabel {
stream_number: sub_num,
..label
});
}
}
}
}
labels
}
fn parse_token_inner(s: &str, saw_unknown: Option<&AtomicBool>) -> Option<StreamLabel> {
let clean = s.trim().trim_start_matches('\t').trim_end_matches('_');
let parts: Vec<&str> = clean.split('_').collect();
if parts.len() < 2 {
return None;
}
let lang = parts[0];
if lang.len() != 3 || !lang.chars().all(|c| c.is_ascii_lowercase()) {
return None;
}
let mut codec = String::new();
let mut purpose = LabelPurpose::Normal;
let mut qualifier = LabelQualifier::None;
let mut variant = String::new();
let mut is_subtitle = false;
let mut is_audio = false;
for &part in &parts[1..] {
if part.is_empty() {
continue;
}
if AUDIO_CODECS.contains(&part) {
codec = vocab::codec(part).to_string();
is_audio = true;
} else if part == "ADES" {
purpose = LabelPurpose::Descriptive;
is_audio = true;
} else if part == "ACOM" {
purpose = LabelPurpose::Commentary;
is_audio = true;
} else if part == "ADLG" || part == "ATRI" {
is_audio = true;
} else if part == "SDH" {
qualifier = LabelQualifier::Sdh;
is_subtitle = true;
} else if part == "SDLG" {
is_subtitle = true;
} else if part == "SCOM" {
purpose = LabelPurpose::Commentary;
is_subtitle = true;
} else if part == "STRI" || part == "TXT" {
is_subtitle = true;
} else if part == "FOR" {
qualifier = LabelQualifier::Forced;
} else if REGIONS.contains(&part) {
variant = part.to_string();
} else if part.starts_with("PGStream") {
is_subtitle = true;
} else {
// Unknown token component — skip this single part rather
// than discarding the entire stream record. Pre-refactor
// behavior was `return None` here, which silently dropped
// any stream containing a single uncatalogued token (e.g.
// a new codec ID or framework variant). Better to surface
// what we know than discard a whole stream over one part,
// but flag the parse as Medium-confidence so callers know
// some data was elided.
tracing::debug!(part = %part, "pixelogic: unrecognized token component, skipping");
if let Some(flag) = saw_unknown {
flag.store(true, Ordering::Relaxed);
}
}
}
if !is_audio && !is_subtitle {
return None;
}
let stream_type = if is_subtitle {
StreamLabelType::Subtitle
} else {
StreamLabelType::Audio
};
Some(StreamLabel {
stream_number: 0,
stream_type,
language: lang.to_string(),
name: String::new(),
purpose,
qualifier,
codec_hint: codec,
variant,
})
}
// extract_strings removed — replaced by super::text::extract_ascii_strings(data, 4).
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn parse_token_basic_audio() {
let l = parse_token_inner("eng_MLP_", None).unwrap();
assert_eq!(l.stream_type, StreamLabelType::Audio);
assert_eq!(l.language, "eng");
assert_eq!(l.codec_hint, "TrueHD");
assert_eq!(l.purpose, LabelPurpose::Normal);
}
#[test]
fn parse_token_basic_subtitle_sdh() {
let l = parse_token_inner("eng_SDH_", None).unwrap();
assert_eq!(l.stream_type, StreamLabelType::Subtitle);
assert_eq!(l.language, "eng");
assert_eq!(l.qualifier, LabelQualifier::Sdh);
}
#[test]
fn parse_token_commentary() {
let l = parse_token_inner("eng_MLP_ACOM_", None).unwrap();
assert_eq!(l.stream_type, StreamLabelType::Audio);
assert_eq!(l.purpose, LabelPurpose::Commentary);
}
#[test]
fn parse_token_descriptive() {
let l = parse_token_inner("eng_AC3_ADES_", None).unwrap();
assert_eq!(l.purpose, LabelPurpose::Descriptive);
}
#[test]
fn parse_token_with_region() {
let l = parse_token_inner("eng_MLP_US_", None).unwrap();
assert_eq!(l.language, "eng");
assert_eq!(l.variant, "US");
}
#[test]
fn parse_token_unknown_component_does_not_kill_stream() {
// Regression: pre-refactor, an unrecognized token part returned
// None for the whole stream, silently dropping it. New
// behavior: skip the unknown part, surface what we know.
let l = parse_token_inner("eng_MLP_FUTUREFLAG_FOR_", None).unwrap();
assert_eq!(l.stream_type, StreamLabelType::Audio);
assert_eq!(l.language, "eng");
assert_eq!(l.codec_hint, "TrueHD");
assert_eq!(l.qualifier, LabelQualifier::Forced);
}
#[test]
fn parse_token_no_audio_or_subtitle_signal_returns_none() {
// A token that has only a language and an unknown part with
// no audio/subtitle classifier should still return None —
// there's no way to file it as a stream.
assert!(parse_token_inner("eng_UNKNOWN_", None).is_none());
}
#[test]
fn parse_token_rejects_non_lang_prefix() {
assert!(parse_token_inner("XX_MLP_", None).is_none());
assert!(parse_token_inner("ENG_MLP_", None).is_none()); // uppercase not accepted as ISO 639-2
}
fn strs(v: &[&str]) -> Vec<String> {
v.iter().map(|s| s.to_string()).collect()
}
#[test]
fn assign_labels_numbers_commentary_behind_placeholders() {
// Observed case: the FPL_MainFeature playlist lists three unlabelled main
// audio tracks as `Audio Stream N` placeholders, then a lone
// `eng_ACOM_` commentary at STN slot 4. The commentary must land on
// audio #4, not collapse onto #1 (which would tag the main feature
// track as commentary).
let flag = AtomicBool::new(false);
let tokens = strs(&[
"FPL_MainFeature",
"Audio Stream 1",
"Audio Stream 2",
"Audio Stream 3",
"eng_ACOM_",
]);
let labels = assign_labels(&tokens, &flag);
let audio: Vec<_> = labels
.iter()
.filter(|l| l.stream_type == StreamLabelType::Audio)
.collect();
assert_eq!(audio.len(), 1, "only the commentary carries a label");
assert_eq!(audio[0].stream_number, 4, "commentary is STN slot 4");
assert_eq!(audio[0].purpose, LabelPurpose::Commentary);
assert_eq!(audio[0].language, "eng");
}
#[test]
fn assign_labels_prefers_fpl_over_seg_mainfeature() {
// A `SEG_MainFeature` menu/preview segment carries a stray commentary
// token, but the real playlist is `FPL_MainFeature`. When an FPL_
// section exists, the SEG_ one must be ignored as an anchor — so we
// number from the FPL playlist, putting the commentary at slot 2.
let flag = AtomicBool::new(false);
let tokens = strs(&[
"SEG_MainFeature",
"eng_ACOM_", // stray token in the menu segment — must be ignored
"FPL_MainFeature",
"Audio Stream 1",
"eng_ACOM_",
]);
let labels = assign_labels(&tokens, &flag);
let audio: Vec<_> = labels
.iter()
.filter(|l| l.stream_type == StreamLabelType::Audio)
.collect();
assert_eq!(audio.len(), 1);
assert_eq!(audio[0].stream_number, 2, "numbered from the FPL playlist");
assert_eq!(audio[0].purpose, LabelPurpose::Commentary);
}
#[test]
fn assign_labels_falls_back_to_seg_without_fpl() {
// Discs with no FPL_ playlist still anchor on SEG_MainFeature.
let flag = AtomicBool::new(false);
let tokens = strs(&["SEG_MainFeature", "eng_MLP_", "spa_AC3_"]);
let labels = assign_labels(&tokens, &flag);
let audio: Vec<_> = labels
.iter()
.filter(|l| l.stream_type == StreamLabelType::Audio)
.collect();
assert_eq!(audio.len(), 2);
assert_eq!(audio[0].stream_number, 1);
assert_eq!(audio[0].language, "eng");
assert_eq!(audio[1].stream_number, 2);
assert_eq!(audio[1].language, "spa");
}
}