chore: scrub non-shippable references from tests/comments

src/labels/bdmt.rs

@@ -38,7 +38,7 @@ use std::collections::BTreeMap;
 #[derive(Debug, Clone, serde::Serialize, serde::Deserialize, Default)]
 pub struct DiscMetadata {
     /// Localized titles, keyed by 3-char ISO 639-2 lang code
-    /// (e.g. "eng" → "Dune Part Two")
+    /// (e.g. "eng" → "Aurora Drift")
     pub titles: BTreeMap<String, String>,
     /// First-line / short description, per lang
     pub descriptions: BTreeMap<String, String>,
@@ -146,7 +146,7 @@ pub(crate) fn parse_bdmt_xml(_lang_code: &str, xml_text: &str) -> Option<BdmtFie
 }
 
 /// Reject candidate description strings that are themselves XML
-/// fragments — observed on disc-04 (Top Gun: Maverick), where
+/// fragments — observed on a captured disc, where
 /// `<di:description>` contained `<di:thumbnail href="…"/>` child
 /// elements and no actual prose. Surfacing that raw to the JSON
 /// output is worse than dropping the field entirely.
@@ -210,10 +210,10 @@ mod tests {
         // carrier inside a <discInfo> root.
         let xml = r#"<?xml version="1.0" encoding="UTF-8"?>
 <discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
-  <di:name>Dune Part Two</di:name>
+  <di:name>Aurora Drift</di:name>
 </discInfo>"#;
         let (title, desc, set) = parse_bdmt_xml("eng", xml).expect("title should parse");
-        assert_eq!(title, "Dune Part Two");
+        assert_eq!(title, "Aurora Drift");
         assert_eq!(desc, None);
         assert_eq!(set, None);
     }
@@ -223,12 +223,12 @@ mod tests {
         // <di:title> is the alternate carrier; should be picked up
         // when <di:name> is absent.
         let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
-  <di:title>The Matrix</di:title>
-  <di:description>A film about computers.</di:description>
+  <di:title>Echo Chamber</di:title>
+  <di:description>A film about machines.</di:description>
 </discInfo>"#;
         let (title, desc, _) = parse_bdmt_xml("eng", xml).unwrap();
-        assert_eq!(title, "The Matrix");
-        assert_eq!(desc.as_deref(), Some("A film about computers."));
+        assert_eq!(title, "Echo Chamber");
+        assert_eq!(desc.as_deref(), Some("A film about machines."));
     }
 
     #[test]
@@ -238,17 +238,17 @@ mod tests {
         // titleName inside tableOfContents.
         let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
   <di:tableOfContents>
-    <di:titleName>Inside Out 2</di:titleName>
+    <di:titleName>Feelings Two</di:titleName>
   </di:tableOfContents>
 </discInfo>"#;
         let (title, _, _) = parse_bdmt_xml("eng", xml).unwrap();
-        assert_eq!(title, "Inside Out 2");
+        assert_eq!(title, "Feelings Two");
     }
 
     #[test]
     fn extract_box_set_position() {
         let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
-  <di:name>LOTR Disc 2</di:name>
+  <di:name>Box Set Disc 2</di:name>
   <di:discNumber>2</di:discNumber>
   <di:numSets>5</di:numSets>
 </discInfo>"#;
@@ -287,11 +287,11 @@ mod tests {
         // would. This exercises the BTreeMap key handling without
         // needing a UdfFs.
         let eng_xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
-  <di:name>Dune Part Two</di:name>
+  <di:name>Aurora Drift</di:name>
 </discInfo>"#;
         let fra_xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
-  <di:name>Dune Deuxième Partie</di:name>
-  <di:description>Suite du film de 2021.</di:description>
+  <di:name>Aurora Drift (Partie Deux)</di:name>
+  <di:description>Suite du film fictif.</di:description>
 </discInfo>"#;
 
         let mut meta = DiscMetadata::default();
@@ -310,16 +310,16 @@ mod tests {
 
         assert_eq!(
             meta.titles.get("eng").map(String::as_str),
-            Some("Dune Part Two")
+            Some("Aurora Drift")
         );
         assert_eq!(
             meta.titles.get("fra").map(String::as_str),
-            Some("Dune Deuxième Partie")
+            Some("Aurora Drift (Partie Deux)")
         );
         assert!(meta.descriptions.get("eng").is_none());
         assert_eq!(
             meta.descriptions.get("fra").map(String::as_str),
-            Some("Suite du film de 2021.")
+            Some("Suite du film fictif.")
         );
         assert_eq!(meta.disc_number, None);
     }
@@ -342,21 +342,21 @@ mod tests {
 
     #[test]
     fn description_with_only_child_xml_is_dropped() {
-        // Real-world bug from disc-04 (Top Gun: Maverick, 2026-05-11
+        // Real-world bug from a captured disc (2026-05-11
         // capture): <di:description> contained only <di:thumbnail/>
         // child elements with no actual prose. The previous parser
         // surfaced the raw XML fragment as the description string.
         // Now we reject candidates that begin with `<`.
         let xml = r#"<discInfo>
-            <di:name>Top Gun: Maverick</di:name>
+            <di:name>Skyline Run</di:name>
             <di:description>
-              <di:thumbnail href="tgm_meta_sm.jpg" />
-              <di:thumbnail href="tgm_meta_lg.jpg" />
+              <di:thumbnail href="sample_meta_sm.jpg" />
+              <di:thumbnail href="sample_meta_lg.jpg" />
             </di:description>
         </discInfo>"#;
         let (title, description, _) =
             parse_bdmt_xml("eng", xml).expect("title is present so parse must succeed");
-        assert_eq!(title, "Top Gun: Maverick");
+        assert_eq!(title, "Skyline Run");
         assert!(
             description.is_none(),
             "description containing only XML children must be dropped, got {description:?}"
@@ -381,10 +381,10 @@ mod tests {
     #[test]
     fn whitespace_in_title_is_trimmed() {
         let xml = r#"<discInfo><di:name>
-            Dune Part Two
+            Aurora Drift
         </di:name></discInfo>"#;
         let (title, _, _) = parse_bdmt_xml("eng", xml).unwrap();
-        assert_eq!(title, "Dune Part Two");
+        assert_eq!(title, "Aurora Drift");
     }
 
     #[test]

src/labels/dbp.rs

@@ -7,8 +7,7 @@
 //! Stream labels live as plain ASCII strings inside compiled `.class`
 //! files in the jar — a quirk of the menu-rendering layer encoding
 //! its TextField positions and content as constant strings the
-//! Java compiler retained in the class string pool. Format observed
-//! in the corpus (Civil War UHD, 2024):
+//! Java compiler retained in the class string pool. Observed format:
 //!
 //! ```text
 //! LTextField,Audio1,English Dolby Atmos,Fontstrip_Composite,...

src/labels/deluxe.rs

@@ -1,83 +1,65 @@
 //! Deluxe BD-J framework — `com/bydeluxe/bluray/` package signature.
 //!
-//! Used by major studios (Disney, Warner, others) for their UHD
-//! BD-J authoring. Detected on discs whose `/BDMV/JAR/<x>.jar`
-//! contains a `com/bydeluxe/` directory entry.
+//! Detected on discs whose `/BDMV/JAR/<x>.jar` contains a
+//! `com/bydeluxe/` directory entry.
 //!
-//! ## Why this parser exists
+//! ## What this parser reads
 //!
-//! Deluxe-authored discs store stream labels as **ordinal references
-//! into obfuscated enum classes**. The label text isn't a literal
-//! string in any anchor pattern (unlike dbp's `TextField,...` rows).
-//! Instead, the binding code is roughly:
-//!
-//! ```java
-//! streamTable.put(1, new AudioSlot(LanguageEnum.English,
-//!                                  CodecEnum.ATMOS_HD_AUDIO,
-//!                                  PurposeEnum.Normal));
-//! ```
-//!
-//! The class names `LanguageEnum`, `CodecEnum`, `PurposeEnum`, and
-//! `AudioSlot` are obfuscated per-disc (`be.class`, `ma.class`,
-//! `lp.class`, etc.) — no name pattern survives the obfuscator. But
-//! the **shape of `<clinit>`** is framework-stable:
+//! Deluxe-authored discs store stream labels as ordinal references into
+//! enum classes whose names are obfuscated per-disc, so a name-based
+//! match won't work. The label data is instead recovered by matching on
+//! the **shape of each enum's `<clinit>`**, which is framework-stable:
 //!
 //! | Enum | Signature |
 //! |---|---|
 //! | Language | 70 `ldc` operations in `<clinit>`, sequence starts `English, French, Spanish, Dutch, ...` |
 //! | Purpose | 8 ldcs starting `Normal, Commentary, PiP, Trivia, ...` |
 //! | VideoFormat | 7 ldcs starting `HD, HDR10 Plus, HD Dolby, ...` |
-//! | Region | 22 ldcs starting `USA_D1, LIC1, LIC2, LIC3, ...` (Disney only) |
-//! | Studio | 6 ldcs starting `Disney, Marvel, Pixar, ...` (Disney only) |
-//! | Codec | ~46 `new` instructions, 0 ldcs in `<clinit>` (codec strings live in subclasses) |
+//! | Region | 22 ldcs starting `USA_D1, LIC1, LIC2, LIC3, ...` |
+//! | Studio | 6 ldcs starting `Disney, Marvel, Pixar, ...` |
+//! | Codec | many `new` instructions, 0 ldcs in `<clinit>` (codec strings live in subclasses) |
 //!
-//! Match on the SHAPE, not the name, and the parser survives obfuscation.
+//! Matching on the shape rather than the class name keeps the parser
+//! working across obfuscation variants.
 //!
 //! ## Implementation phases
 //!
 //! - **Phase A** — master enum identification (`identify_master_enums`).
 //!   Walks every `.class`'s `<clinit>` ldc sequence and matches against
 //!   the framework-stable fingerprints. Output: `Vec<(label, MasterEnum)>`
-//!   with full ordinal → string-value tables. **Empirically verified**
-//!   on disc-01 (Disney) + disc-09 (Warner).
+//!   with full ordinal → string-value tables.
 //!
 //! - **Phase B** — codec enum subclass walk (`decode_codec_enum`).
-//!   The codec enum's `<clinit>` has ~46 `new` instructions and zero
+//!   The codec enum's `<clinit>` has many `new` instructions and zero
 //!   string ldcs — codec name strings live in the subclasses each
 //!   `new` constructs. Walks every referenced subclass's constant
-//!   pool, extracts the codec name string. **Structural shape
-//!   verified** on disc-01 (ma.class, 41 `new` ops) + disc-09
-//!   (ea.class, 46 `new` ops); per-subclass string extraction
-//!   designed against the published Java enum compilation convention
-//!   (each enum value's `<init>` is called with its name string as
-//!   the first arg).
+//!   pool, extracts the codec name string, following the standard Java
+//!   enum compilation convention (each enum value's `<init>` is called
+//!   with its name string as the first arg).
 //!
 //! - **Phase C** — binding-class identification (`find_binding_classes`).
 //!   The per-stream table is built by some class via repeated
 //!   `getstatic` references to the master enums identified in A.
 //!   That class has the highest such `getstatic` count in the jar.
-//!   **Heuristic shape**; precise threshold may need tuning.
+//!   Heuristic shape; precise threshold may need tuning.
 //!
 //! - **Phase D** — binding-class bytecode decoder (`decode_binding`).
 //!   Walks the binding class's `<clinit>` with a tiny symbolic stack
 //!   machine. For each `new X / dup / ... / invokespecial X.<init>`
 //!   sequence, collects the int values and enum-reference operands
 //!   between the `dup` and the constructor call, then emits a
-//!   `DecodedStream`. **Mechanism verified** in unit tests against
-//!   synthetic class fixtures; the **signal-to-StreamLabel mapping**
-//!   (which arg is stream index? which is language? audio vs
-//!   subtitle?) uses a documented heuristic that needs corpus-disc
-//!   verification — see `interpret_stream` for the mapping rules.
+//!   `DecodedStream`. The signal-to-StreamLabel mapping (which arg is
+//!   stream index? which is language? audio vs subtitle?) uses a
+//!   heuristic — see `interpret_streams` for the mapping rules.
 //!
 //! ## Confidence
 //!
 //! [`parse`] returns `Some(ParseResult::medium(labels))` when Phases A
 //! through D produce at least one stream — `Medium` because the
-//! signal-to-label mapping is heuristic until real disc bytecode
-//! confirms the binding pattern. Once verified the parser can promote
-//! to `High`. `None` when the disc isn't Deluxe-authored or when
-//! decoding produces zero streams (a recognized-but-broken state that
-//! the analyzer still surfaces via `parsers_detected`).
+//! signal-to-label mapping is heuristic. `None` when the disc isn't
+//! Deluxe-authored or when decoding produces zero streams (a
+//! recognized-but-broken state that the analyzer still surfaces via
+//! `parsers_detected`).
 
 use super::class_reader::{
     AASTORE, BIPUSH, ClassFile, CodeAttribute, ConstantPool, CpInfo, GETSTATIC, ICONST_0, ICONST_1,
@@ -559,10 +541,9 @@ fn clinit_news_and_ldcs(
 /// candidates ordered by descending getstatic count, filtered to a
 /// minimum concentration of master-enum references.
 ///
-/// Empirically (POC v0.3 dumps): on disc-01 the audio binding class
-///   (`ma.class`) has ~82 getstatic refs, the subtitle binding
-///   (`ko.class`) has ~63. Both share the master Language + Purpose
-///   enums.
+/// A disc that splits the table commonly has one audio binding class
+/// with the most getstatic refs and a subtitle binding class with
+/// somewhat fewer; both share the master Language + Purpose enums.
 pub(crate) fn find_binding_classes(
     archive: &mut jar::Jar,
     master_enum_classes: &HashSet<&str>,
@@ -641,10 +622,9 @@ pub(crate) enum StackVal {
     /// name (e.g. `DOLBY_AC3_AUDIO`, `DOLBY_LOSSLESS_AUDIO`) is the
     /// codec identifier. Deluxe binding constructors take a
     /// `LCodingType;` arg directly — codecs are NOT a Deluxe-internal
-    /// enum (Phase B's codec-subclass walk was based on a wrong
-    /// assumption; the actual codec source is the standard BD-J API
-    /// enum). Discovered via deluxe-poc v0.3 binding-bytecode dump
-    /// against disc-01 (Disney) + disc-09 (Warner) on 2026-05-10.
+    /// enum; the codec source is the standard BD-J API `CodingType`
+    /// enum, so the binding constructor's codec arg is read straight
+    /// from that getstatic operand.
     CodingType(String),
     /// An uninitialized `new` object — popped by the matching
     /// invokespecial.
@@ -988,11 +968,10 @@ impl MasterEnumTable {
 // ── interpret_streams: Constructions → StreamLabels ─────────────────────────
 
 /// Convert the per-construction tuples from Phase D into
-/// [`StreamLabel`]s. Pattern verified against corpus discs via
-/// deluxe-poc v0.3 binding-bytecode dump (2026-05-10):
+/// [`StreamLabel`]s. Two binding-constructor shapes are handled:
 ///
-/// Disney binding (5-arg): `BindingType.<init>(I, Lbe;, Llp;, I, LCodingType;)V`
-/// Warner binding (4-arg): `BindingType.<init>(I, Law;, Lgp;, LCodingType;)V`
+/// 5-arg: `BindingType.<init>(I, Lang;, Lpurpose;, I, LCodingType;)V`
+/// 4-arg: `BindingType.<init>(I, Lang;, Lpurpose;, LCodingType;)V`
 ///
 /// Args are identified by **TYPE**, not position:
 /// - First `EnumRef{kind: "Language"}` → audio/subtitle language
@@ -1098,11 +1077,10 @@ fn interpret_streams(constructions: &[Construction], master: &MasterEnumTable) -
 /// getstatic operands on Deluxe binding classes) to a human-readable
 /// codec hint string.
 ///
-/// CodingType is the standard BD-J API enum; values are documented
-/// in the BD-J specification and verified empirically against the
-/// binding-bytecode dumps in `(internal)/research/deluxe-poc/data/`.
-/// Unknown field names pass through unchanged so unfamiliar codecs
-/// still surface something rather than going silent.
+/// CodingType is the standard BD-J API enum; values are documented in
+/// the BD-J specification. Unknown field names pass through unchanged
+/// so unfamiliar codecs still surface something rather than going
+/// silent.
 fn coding_type_to_codec_hint(field: &str) -> &str {
     match field {
         // Lossless / hi-res.

src/labels/mod.rs

@@ -954,7 +954,7 @@ mod gap_fill_tests {
 
     #[test]
     fn partial_yield_fills_gaps_keeps_framework() {
-        // Oppenheimer-style: framework matched but only labeled 2 of 6 audios.
+        // Partial-coverage case: framework matched but only labeled 2 of 6 audios.
         let mut framework = vec![
             label(StreamLabelType::Audio, 1, "eng", "Atmos"),
             label(StreamLabelType::Audio, 4, "eng", "Commentary"),

src/labels/pixelogic.rs

@@ -300,7 +300,7 @@ mod tests {
 
     #[test]
     fn assign_labels_numbers_commentary_behind_placeholders() {
-        // Wicked: the FPL_MainFeature playlist lists three unlabelled main
+        // 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

src/labels/vocab.rs

@@ -10,8 +10,7 @@
 //! - English text → [`LabelPurpose`] (Commentary / Descriptive / etc.).
 //! - English text → [`LabelQualifier`] (SDH / Forced / Descriptive Service).
 //!
-//! Rules of engagement (carried over from
-//! `(internal)/memory/feedback_label_data_rules.md`):
+//! Rules of engagement:
 //!
 //! 1. Only map values we are 100% certain about — published codec
 //!    names, well-known ISO 639-2 mappings, vendor-documented purpose