v0.20.2: delete dead retry block + wedge-family cooldown in Disc::patch

WO-3c: Delete dead non-NOT_READY retry block (~100 LOC). The block
declared retry_count = 0 inside the per-iteration Err arm, so the
'MAX_NON_NOT_READY_RETRIES=3' budget actually fired exactly once
(1s pause + 1 retry) before falling through to NonTrimmed. The
'exponential backoff: 2s, 4s, 8s' comment was wrong by construction.
Cross-pass NonTrimmed retry (each pass gives the same sectors another
shot) already covers the recovery case, and gives the drive minutes
between attempts instead of 1-8 seconds — empirically what stochastic
recovery on the BU40N actually needs.

WO-4 (targeted slice): Add wedge-family cooldown on HARDWARE_ERROR /
ILLEGAL_REQUEST senses. These are what the BU40N's firmware fast-fail
state returns; every subsequent read in that state comes back in
<100ms. Pre-fix patch hammered the drive: mark NonTrimmed, sleep 1s,
advance, hit next wedge, mark, sleep 1s — exactly the rapid-retry
cadence the firmware is sensitive to. Now a wedge-family sense triggers
WEDGE_FAMILY_COOLDOWN_SECS=30 cooldown (matches read_error.rs's
ZONE_ENTRY_COOLDOWN_SECS), and WEDGE_ABORT_THRESHOLD=16 consecutive
wedges aborts the pass for autorip eject+reload. Any non-wedge read
clears the counter.

Also drops the duplicate NonTrimmed dispatch (Mapfile::record is
idempotent so it wasn't a correctness bug, but it doubled per-failure
consumer work).

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "libfreemkv"
-version = "0.18.7"
+version = "0.20.2"
 edition = "2024"
 rust-version = "1.86"
 license = "AGPL-3.0-only"

src/aacs/keys.rs

@@ -247,6 +247,7 @@ fn validate_processing_key(
 /// Find Verify Media Key Record (type 0x10) in MKB.
 fn mkb_find_mk_dv(mkb: &[u8]) -> Option<[u8; 16]> {
     let mut pos = 0;
+    let mut type10_seen: Vec<(usize, usize)> = Vec::new();
     while pos + 4 <= mkb.len() {
         let rec_type = mkb[pos];
         let rec_len = u32::from_be_bytes([0, mkb[pos + 1], mkb[pos + 2], mkb[pos + 3]]) as usize;
@@ -254,14 +255,32 @@ fn mkb_find_mk_dv(mkb: &[u8]) -> Option<[u8; 16]> {
             break;
         }
 
+        if rec_type == 0x10 {
+            type10_seen.push((pos, rec_len));
+        }
+
         if rec_type == 0x10 && rec_len >= 20 {
             // mk_dv is at offset 4 (after record header)
             let mut dv = [0u8; 16];
             dv.copy_from_slice(&mkb[pos + 4..pos + 20]);
+            tracing::warn!(
+                target: "freemkv::disc",
+                phase = "mkb_mk_dv_found",
+                pos,
+                rec_len,
+                "mk_dv extracted from MKB"
+            );
             return Some(dv);
         }
         pos += rec_len;
     }
+    tracing::warn!(
+        target: "freemkv::disc",
+        phase = "mkb_mk_dv_not_found",
+        type10_seen = ?type10_seen,
+        scanned_bytes = pos,
+        "no 0x10 record with rec_len>=20 found"
+    );
     None
 }
 
@@ -628,32 +647,70 @@ pub fn resolve_keys(
         }
     };
 
+    tracing::warn!(
+        target: "freemkv::disc",
+        phase = "resolve_keys_start",
+        aacs2,
+        bus_encryption,
+        disc_hash = %hash_hex,
+        mkb_present = mkb_data.is_some(),
+        "resolve_keys: starting"
+    );
+
     // Path 1: Look up VUK by disc hash in KEYDB
     if let Some(entry) = keydb.find_disc(&hash_hex) {
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path1_hit_entry", "disc hash found in keydb");
         if let Some(vuk) = entry.vuk {
             return Some(build(vuk, 1));
         }
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path1_no_vuk", "disc hash entry has no VUK");
+    } else {
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path1_miss", "disc hash NOT in keydb");
     }
 
     // Path 2: Find entry with matching VID → derive VUK from MK + VID
+    let mut path2_mk_did_count = 0usize;
     for entry in keydb.disc_entries.values() {
         if let (Some(mk), Some(did)) = (entry.media_key, entry.disc_id) {
+            path2_mk_did_count += 1;
             if did == *volume_id {
+                tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path2_hit", "MK+VID entry matched volume_id");
                 return Some(build(derive_vuk(&mk, volume_id), 2));
             }
         }
     }
+    tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path2_miss", mk_did_entries = path2_mk_did_count, "no MK+VID entry matched volume_id");
 
     // Path 3: MKB + processing keys → media key → VUK
     if let Some(mkb) = mkb_data {
+        let mk_dv = mkb_find_mk_dv(mkb);
+        let subdiff = mkb_find_subdiff_records(mkb);
+        let cvalues = mkb_find_cvalues(mkb);
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "resolve_keys_mkb_records",
+            mk_dv_found = mk_dv.is_some(),
+            subdiff_found = subdiff.is_some(),
+            subdiff_len = subdiff.as_ref().map(|s| s.len()).unwrap_or(0),
+            cvalues_found = cvalues.is_some(),
+            cvalues_len = cvalues.as_ref().map(|c| c.len()).unwrap_or(0),
+            "MKB record scan results"
+        );
+
         if let Some(mk) = derive_media_key_from_pk(mkb, &keydb.processing_keys) {
+            tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path3_hit", "media key derived from processing key");
             return Some(build(derive_vuk(&mk, volume_id), 3));
         }
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path3_miss", pk_count = keydb.processing_keys.len(), "PK derivation failed");
 
         // Path 4: MKB + device keys → processing key → media key → VUK
         if let Some(mk) = derive_media_key_from_dk(mkb, &keydb.device_keys) {
+            tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path4_hit", "media key derived from device key");
             return Some(build(derive_vuk(&mk, volume_id), 4));
         }
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_path4_miss", dk_count = keydb.device_keys.len(), "DK derivation failed");
+    } else {
+        tracing::warn!(target: "freemkv::disc", phase = "resolve_keys_no_mkb", "no MKB data available; paths 3/4 skipped");
     }
 
     None

src/clpi.rs

@@ -20,6 +20,35 @@ pub struct ClipInfo {
     pub ep_coarse: Vec<EpCoarse>,
     /// Fine EP entries for the primary video stream
     pub ep_fine: Vec<EpFine>,
+    /// Per-stream metadata from the ProgramInfo section (BD spec).
+    /// Cross-validates the MPLS STN view — see `labels/clpi.rs`.
+    /// Empty when program_info is missing or malformed.
+    pub streams: Vec<ClpiStream>,
+}
+
+/// One stream descriptor from the CLPI ProgramInfo / stream_coding_info
+/// table. Mirrors the same fields the MPLS STN table carries — see
+/// `mpls::StreamEntry` for the playlist-side equivalent.
+#[derive(Debug, Clone)]
+#[allow(dead_code)]
+pub struct ClpiStream {
+    /// PID of the stream in the MPEG-TS (matches MPLS).
+    pub pid: u16,
+    /// SCSI/BD coding type byte (0x80 LPCM, 0x83 TrueHD, 0x86 DTS-HD MA,
+    /// 0x90 PG, etc.). See `labels::mpls_universal::coding_type_to_codec_hint`.
+    pub coding_type: u8,
+    /// ISO 639-2 3-char language code. Empty for video streams.
+    pub language: String,
+    /// Audio format byte (1=mono, 3=stereo, 6=5.1, 12=7.1).
+    /// Zero for non-audio streams.
+    pub audio_format: u8,
+    /// Audio sample rate (1=48kHz, 4=96kHz, 5=192kHz). Zero for non-audio.
+    pub audio_rate: u8,
+    /// Video format byte (1=480i, 4=1080i, 5=720p, 6=1080p, 8=2160p).
+    /// Zero for non-video.
+    pub video_format: u8,
+    /// Video rate (1=23.976, 2=24, 3=25, 4=29.97, 6=50, 7=59.94).
+    pub video_rate: u8,
 }
 
 #[derive(Debug, Clone)]
@@ -128,7 +157,7 @@ pub fn parse(data: &[u8]) -> Result<ClipInfo> {
 
     // Header offsets
     let _seq_info_start = u32::from_be_bytes([data[8], data[9], data[10], data[11]]) as usize;
-    let _prog_info_start = u32::from_be_bytes([data[12], data[13], data[14], data[15]]) as usize;
+    let prog_info_start = u32::from_be_bytes([data[12], data[13], data[14], data[15]]) as usize;
     let cpi_start = u32::from_be_bytes([data[16], data[17], data[18], data[19]]) as usize;
 
     // ClipInfo section at offset 40
@@ -139,6 +168,16 @@ pub fn parse(data: &[u8]) -> Result<ClipInfo> {
         0
     };
 
+    // Parse ProgramInfo (per-stream language + codec). Best-effort:
+    // malformed program_info doesn't fail the parse, just gives an
+    // empty streams list. EP map is unaffected — sector-range lookups
+    // continue to work.
+    let streams = if prog_info_start > 0 && prog_info_start + 6 < data.len() {
+        parse_program_info(&data[prog_info_start..])
+    } else {
+        Vec::new()
+    };
+
     // Parse CPI / EP Map
     let (ep_coarse, ep_fine) = if cpi_start > 0 && cpi_start + 8 < data.len() {
         parse_cpi(&data[cpi_start..])?
@@ -151,9 +190,127 @@ pub fn parse(data: &[u8]) -> Result<ClipInfo> {
         source_packet_count,
         ep_coarse,
         ep_fine,
+        streams,
     })
 }
 
+/// Parse the ProgramInfo section: per-stream (pid, coding_type,
+/// language, codec sub-fields). Layout per BD spec / libbluray
+/// clpi_parse.c:
+///
+/// ```text
+/// ProgramInfo:
+///   length: 4 bytes
+///   reserved: 1 byte
+///   num_programs: 1 byte
+///   for each program:
+///     spn_program_sequence_start: 4 bytes
+///     program_map_pid: 2 bytes
+///     num_streams: 1 byte
+///     num_groups: 1 byte
+///     for each stream:
+///       pid: 2 bytes
+///       stream_coding_info_length: 1 byte
+///       stream_coding_info: (varies by coding_type)
+///         coding_type: 1 byte
+///         per-type bytes (see match arms below)
+/// ```
+///
+/// Returns `Vec::new()` on any structural mismatch — we don't propagate
+/// errors because the EP map is the primary CLPI output, and a corrupt
+/// program_info shouldn't break sector-range lookups.
+fn parse_program_info(data: &[u8]) -> Vec<ClpiStream> {
+    let mut out = Vec::new();
+    if data.len() < 6 {
+        return out;
+    }
+    // length: 4 bytes (skipped — we trust the section bounds in the
+    // caller's slice and read the bytes that follow). Reserved 1 byte
+    // at offset 4. num_programs at offset 5.
+    let num_programs = data[5] as usize;
+    let mut pos = 6usize;
+    for _ in 0..num_programs {
+        // Program header: 4 (spn) + 2 (pmt_pid) + 1 (num_streams) + 1 (num_groups) = 8 bytes
+        if pos + 8 > data.len() {
+            return out;
+        }
+        let num_streams = data[pos + 6] as usize;
+        pos += 8;
+
+        for _ in 0..num_streams {
+            // Stream header: 2 (pid) + 1 (sci_length) + sci bytes
+            if pos + 3 > data.len() {
+                return out;
+            }
+            let pid = u16::from_be_bytes([data[pos], data[pos + 1]]);
+            let sci_len = data[pos + 2] as usize;
+            let sci_end = pos + 3 + sci_len;
+            if sci_end > data.len() || sci_len < 1 {
+                return out;
+            }
+            let sci = &data[pos + 3..sci_end];
+            let coding_type = sci[0];
+
+            let mut audio_format = 0u8;
+            let mut audio_rate = 0u8;
+            let mut video_format = 0u8;
+            let mut video_rate = 0u8;
+            let mut language = String::new();
+
+            match coding_type {
+                // Video — MPEG-2 (0x02), H.264 (0x1B), HEVC (0x24)
+                0x02 | 0x1B | 0x24 => {
+                    if sci.len() >= 2 {
+                        video_format = (sci[1] >> 4) & 0x0F;
+                        video_rate = sci[1] & 0x0F;
+                    }
+                }
+                // Primary audio — LPCM(0x80), AC-3(0x81), DTS(0x82),
+                // TrueHD(0x83), AC-3+(0x84), DTS-HD(0x85), DTS-HD MA(0x86)
+                0x80..=0x86 => {
+                    if sci.len() >= 2 {
+                        audio_format = (sci[1] >> 4) & 0x0F;
+                        audio_rate = sci[1] & 0x0F;
+                    }
+                    if sci.len() >= 5 {
+                        language = String::from_utf8_lossy(&sci[2..5]).to_string();
+                    }
+                }
+                // Secondary audio (0xA1 AC-3+, 0xA2 DTS-HD)
+                0xA1 | 0xA2 => {
+                    if sci.len() >= 2 {
+                        audio_format = (sci[1] >> 4) & 0x0F;
+                        audio_rate = sci[1] & 0x0F;
+                    }
+                    if sci.len() >= 5 {
+                        language = String::from_utf8_lossy(&sci[2..5]).to_string();
+                    }
+                }
+                // PG (0x90), IG (0x91): coding_type + 3-byte language [+ char_code for PG]
+                0x90 | 0x91 => {
+                    if sci.len() >= 4 {
+                        language = String::from_utf8_lossy(&sci[1..4]).to_string();
+                    }
+                }
+                _ => {}
+            }
+
+            out.push(ClpiStream {
+                pid,
+                coding_type,
+                language,
+                audio_format,
+                audio_rate,
+                video_format,
+                video_rate,
+            });
+
+            pos = sci_end;
+        }
+    }
+    out
+}
+
 /// Parse the CPI section containing the EP map.
 fn parse_cpi(data: &[u8]) -> Result<(Vec<EpCoarse>, Vec<EpFine>)> {
     if data.len() < 8 {

src/css/mod.rs

@@ -16,7 +16,7 @@ pub mod lfsr;
 pub(crate) mod tables;
 
 use crate::disc::Extent;
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 
 /// CSS decryption state for a DVD title.
 #[derive(Debug, Clone)]
@@ -34,7 +34,7 @@ pub struct CssState {
 /// 0x80 (start of the encrypted region). This only happens when a new PES
 /// packet begins at exactly sector offset 128. We scan up to 50000
 /// scrambled sectors sequentially across all extents.
-pub fn crack_key(reader: &mut dyn SectorReader, extents: &[Extent]) -> Option<CssState> {
+pub fn crack_key(reader: &mut dyn SectorSource, extents: &[Extent]) -> Option<CssState> {
     let mut tried = 0u32;
     let max_tries = 50_000;
 

src/disc/bluray.rs

@@ -3,13 +3,13 @@
 use super::*;
 use crate::clpi;
 use crate::mpls;
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use crate::udf;
 
 impl Disc {
     /// Scan Blu-ray titles from MPLS playlists.
     pub(super) fn scan_bluray_titles(
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         udf_fs: &udf::UdfFs,
     ) -> Vec<DiscTitle> {
         let mut titles = Vec::new();
@@ -31,7 +31,7 @@ impl Disc {
     }
 
     pub(super) fn parse_playlist(
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         udf_fs: &udf::UdfFs,
         filename: &str,
         data: &[u8],
@@ -199,7 +199,7 @@ impl Disc {
     /// Prefers English, falls back to first available language.
     /// Returns None if META directory is empty or XML has no usable title.
     pub(super) fn read_meta_title(
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         udf_fs: &udf::UdfFs,
     ) -> Option<String> {
         let meta_dir = udf_fs.find_dir("/BDMV/META")?;

src/disc/dvd.rs

@@ -2,13 +2,13 @@
 
 use super::*;
 use crate::ifo;
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use crate::udf;
 
 impl Disc {
     /// Scan DVD titles from IFO files (VIDEO_TS.IFO + VTS_XX_0.IFO).
     pub(super) fn scan_dvd_titles(
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         udf_fs: &udf::UdfFs,
     ) -> Vec<DiscTitle> {
         let dvd_info = match ifo::parse_vmg(reader, udf_fs) {

src/disc/encrypt.rs

@@ -2,7 +2,7 @@
 
 use super::*;
 use crate::error::{Error, Result};
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use crate::udf;
 
 /// Result of SCSI AACS handshake (ECDH authentication).
@@ -22,42 +22,103 @@ impl Disc {
     ) -> Option<HandshakeResult> {
         use crate::aacs::{self, KeyDb};
 
-        let keydb_path = opts.resolve_keydb()?;
-        let keydb = KeyDb::load(&keydb_path).ok()?;
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "handshake_entry",
+            "do_handshake entered"
+        );
+        let keydb_path = match opts.resolve_keydb() {
+            Some(p) => p,
+            None => {
+                tracing::warn!(
+                    target: "freemkv::disc",
+                    phase = "handshake_no_keydb",
+                    "no KEYDB found in search paths; handshake skipped"
+                );
+                return None;
+            }
+        };
+        let keydb = match KeyDb::load(&keydb_path) {
+            Ok(db) => db,
+            Err(e) => {
+                tracing::warn!(
+                    target: "freemkv::disc",
+                    phase = "handshake_keydb_load_failed",
+                    io_error_kind = ?e.kind(),
+                    keydb = %keydb_path.display(),
+                    "KEYDB load failed; handshake skipped"
+                );
+                return None;
+            }
+        };
+
+        let host_cert_count = keydb.host_certs.len();
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "handshake_start",
+            host_cert_count,
+            keydb = %keydb_path.display(),
+            "handshake starting"
+        );
 
         const MAX_CERT_ATTEMPTS: usize = 16;
-        for hc in keydb.host_certs.iter().take(MAX_CERT_ATTEMPTS) {
+        let mut last_err_code: Option<u16> = None;
+        for (idx, hc) in keydb.host_certs.iter().take(MAX_CERT_ATTEMPTS).enumerate() {
             match aacs::handshake::aacs_authenticate(session, &hc.private_key, &hc.certificate) {
                 Ok(mut auth) => {
                     let volume_id = match aacs::handshake::read_volume_id(session, &mut auth) {
                         Ok(vid) => vid,
-                        Err(_) => return None, // handshake succeeded but can't read VID
+                        Err(e) => {
+                            tracing::warn!(
+                                target: "freemkv::disc",
+                                phase = "handshake_vid_read_failed",
+                                cert_index = idx,
+                                error_code = e.code(),
+                                "auth ok but volume ID read failed"
+                            );
+                            return None;
+                        }
                     };
                     let read_data_key = aacs::handshake::read_data_keys(session, &mut auth)
                         .ok()
                         .map(|(rdk, _)| rdk);
+                    tracing::debug!(
+                        target: "freemkv::disc",
+                        phase = "handshake_ok",
+                        cert_index = idx,
+                        has_read_data_key = read_data_key.is_some(),
+                    );
                     return Some(HandshakeResult {
                         volume_id,
                         read_data_key,
                     });
                 }
-                Err(_) => {
+                Err(e) => {
+                    last_err_code = Some(e.code());
                     continue;
                 }
             }
         }
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "handshake_all_certs_failed",
+            host_cert_count,
+            tried = host_cert_count.min(MAX_CERT_ATTEMPTS),
+            last_error_code = last_err_code,
+            "all host certs in KEYDB rejected by drive"
+        );
         // All host certs failed — return None, not a fake success
         None
     }
 
     /// Resolve disc encryption — AACS 1.0, AACS 2.0, CSS, or none.
     ///
-    /// Reads AACS files from UDF (via SectorReader), resolves keys through
+    /// Reads AACS files from UDF (via SectorSource), resolves keys through
     /// whatever path works: KEYDB VUK lookup, media key derivation, processing
     /// keys, device keys. Uses handshake result (volume ID, bus key) if available.
     pub(super) fn resolve_encryption(
         udf_fs: &udf::UdfFs,
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         keydb_path: &std::path::Path,
         handshake: Option<&HandshakeResult>,
     ) -> Result<AacsState> {
@@ -73,6 +134,19 @@ impl Disc {
             .or_else(|_| udf_fs.read_file(reader, "/AACS/DUPLICATE/Unit_Key_RO.inf"))
             .map_err(|_| Error::AacsNoKeys)?;
 
+        // Log the disc hash so we can confirm whether it's present in KEYDB
+        // when key resolution fails. The disc hash is SHA-1 of the full
+        // Unit_Key_RO.inf file bytes — same value KEYDB.cfg keys VUK entries by.
+        let dh = crate::aacs::disc_hash(&uk_ro_data);
+        let dh_hex = crate::aacs::disc_hash_hex(&dh);
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "scan_aacs_disc_hash",
+            disc_hash = %dh_hex,
+            uk_ro_len = uk_ro_data.len(),
+            "disc hash computed (compare with keydb.cfg entries)"
+        );
+
         let cc_data = udf_fs
             .read_file(reader, "/AACS/Content000.cer")
             .or_else(|_| udf_fs.read_file(reader, "/AACS/Content001.cer"))
@@ -84,6 +158,28 @@ impl Disc {
             .ok();
         let mkb_ver = mkb_data.as_deref().and_then(aacs::mkb_version);
 
+        let mkb_first_64_hex = mkb_data
+            .as_deref()
+            .map(|m| {
+                m.iter()
+                    .take(64)
+                    .map(|b| format!("{b:02x}"))
+                    .collect::<String>()
+            })
+            .unwrap_or_default();
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "scan_aacs_mkb_info",
+            mkb_present = mkb_data.is_some(),
+            mkb_len = mkb_data.as_deref().map(|m| m.len()).unwrap_or(0),
+            mkb_version = ?mkb_ver,
+            mkb_first_64 = %mkb_first_64_hex,
+            keydb_disc_count = keydb.disc_entries.len(),
+            keydb_dk_count = keydb.device_keys.len(),
+            keydb_pk_count = keydb.processing_keys.len(),
+            "AACS resolution inputs"
+        );
+
         // Use handshake volume ID if available, otherwise zeros
         // (KEYDB VUK lookup by disc hash works without volume ID)
         let volume_id = handshake.map(|h| h.volume_id).unwrap_or([0u8; 16]);

src/disc/read_error.rs

@@ -65,6 +65,80 @@ pub struct ReadCtx {
     /// is its core job, and it has the right tools (single-sector
     /// reads, 60s recovery timeout, retry budget, escalating skip).
     pub bisect_on_marginal: bool,
+    /// Count of consecutive firmware-wedge responses (HARDWARE_ERROR
+    /// or ILLEGAL_REQUEST sense keys) since the last successful read.
+    /// Pass 1 uses this to drive the wedge-skip path: each wedge
+    /// triggers a 1 GB jump + cooldown pause. Reaching
+    /// `WEDGE_ABORT_THRESHOLD` consecutive wedges with no good read
+    /// in between → real AbortPass.
+    pub wedge_count: u64,
+    // ── Diagnostic counters (added 2026-05-10) ──
+    //
+    // Aggregate state for post-mortem analysis of wedge incidents.
+    // Every Pass 1 / Pass N sweep now produces a structured summary
+    // at the WARN log on each error AND an end-of-pass INFO summary.
+    // Goal: when a wedge happens, the operator should be able to tell
+    // from the logs whether it was triggered by ONE read at a
+    // physically-damaged sector (immediate failure) or by accumulated
+    // exposure across MANY reads (firmware-state buildup), and what
+    // the timing pattern looked like.
+    /// `Instant` of the most recent successful read. Used to compute
+    /// "time since last good" for the WARN log on each error. None
+    /// before the first successful read.
+    pub last_success_at: Option<std::time::Instant>,
+    /// `Instant` of the most recent failed read. Used to compute
+    /// "time since last error" for the WARN log. None before the
+    /// first error.
+    pub last_error_at: Option<std::time::Instant>,
+    /// Last error's sense-key "family" (Medium / Hardware / IllegalRequest
+    /// / NotReady / Other). Used to detect WEDGE TRANSITIONS — when
+    /// the family changes from Medium → Hardware/IllegalRequest, the
+    /// drive almost certainly just entered fast-fail mode. That
+    /// transition gets its own WARN log so the trace is unambiguous.
+    pub last_error_family: Option<SenseFamily>,
+    /// Sum of all errors observed during this sweep. Reported in the
+    /// end-of-pass summary.
+    pub total_errors: u64,
+    /// Sum of all successful reads during this sweep.
+    pub total_reads_ok: u64,
+    /// Count of damage zones entered (transitions from clean → in-damage).
+    pub zones_entered: u64,
+    /// Count of damage-jumps executed during this sweep.
+    pub jumps_taken: u64,
+    /// True between "first error after a clean period" and "16 consecutive
+    /// good reads after the last error in the cluster." Used to count
+    /// zone entries and to bound zone_reads accurately.
+    pub in_damage_zone: bool,
+}
+
+/// Coarse classification of a SCSI sense key for diagnostic logging.
+/// Wedge-family events (Hardware + IllegalRequest) get their own
+/// transition log when the sense family changes.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum SenseFamily {
+    NotReady,
+    Medium,
+    Hardware,
+    IllegalRequest,
+    Other,
+}
+
+impl SenseFamily {
+    pub fn from_sense_key(sense_key: u8) -> Self {
+        match sense_key {
+            scsi::SENSE_KEY_NOT_READY => SenseFamily::NotReady,
+            scsi::SENSE_KEY_MEDIUM_ERROR => SenseFamily::Medium,
+            scsi::SENSE_KEY_HARDWARE_ERROR => SenseFamily::Hardware,
+            scsi::SENSE_KEY_ILLEGAL_REQUEST => SenseFamily::IllegalRequest,
+            _ => SenseFamily::Other,
+        }
+    }
+
+    /// True for the "wedge family" — Hardware + IllegalRequest are
+    /// the senses the BU40N firmware returns in its fast-fail state.
+    pub fn is_wedge_family(self) -> bool {
+        matches!(self, SenseFamily::Hardware | SenseFamily::IllegalRequest)
+    }
 }
 
 impl ReadCtx {
@@ -73,8 +147,13 @@ impl ReadCtx {
     /// is the one that grinds on the bad ranges. So bisect-on-
     /// marginal is OFF (failed batches become SkipBlock; whole 32-
     /// sector blocks marked NonTrimmed for Pass N to revisit), and
-    /// the damage-jump fast-path triggers after just 4 consecutive
-    /// outer-batch failures.
+    /// the damage-jump fast-path triggers after just 1 consecutive
+    /// outer-batch failure — the user's wedge-prevention principle
+    /// (2026-05-11): once the drive returns ANY recoverable error,
+    /// retrying the same LBA quickly is what triggers the firmware
+    /// fast-fail transition. Jump immediately, never retry in Pass 1.
+    /// Pass N owns retries — it gets per-sector timeouts that don't
+    /// hammer the firmware the same way.
     pub fn for_sweep(batch: u16) -> Self {
         Self {
             batch,
@@ -84,12 +163,21 @@ impl ReadCtx {
             damage_window: Vec::with_capacity(16),
             damage_window_max: 16,
             damage_threshold_pct: 12,
-            fast_jump_threshold: 4,
+            fast_jump_threshold: 1,
             jump_multiplier: 1,
             not_ready_retries: 0,
             bridge_degradation_count: 0,
             bisecting: false,
             bisect_on_marginal: false,
+            wedge_count: 0,
+            last_success_at: None,
+            last_error_at: None,
+            last_error_family: None,
+            total_errors: 0,
+            total_reads_ok: 0,
+            zones_entered: 0,
+            jumps_taken: 0,
+            in_damage_zone: false,
         }
     }
 
@@ -115,6 +203,15 @@ impl ReadCtx {
             bridge_degradation_count: 0,
             bisecting: false,
             bisect_on_marginal: true,
+            wedge_count: 0,
+            last_success_at: None,
+            last_error_at: None,
+            last_error_family: None,
+            total_errors: 0,
+            total_reads_ok: 0,
+            zones_entered: 0,
+            jumps_taken: 0,
+            in_damage_zone: false,
         }
     }
 
@@ -123,6 +220,10 @@ impl ReadCtx {
         self.consecutive_good += 1;
         self.consecutive_failures = 0;
         self.not_ready_retries = 0;
+        // Any successful read clears the wedge-skip counter — the
+        // drive recovered, so further wedges should reset the skip
+        // budget instead of accumulating toward a real abort.
+        self.wedge_count = 0;
         // Outer-success only: a good single-sector read inside a
         // bisect doesn't mean we've left the damaged batch. Only an
         // outer-batch success resets the outer-failure counter.
@@ -133,7 +234,40 @@ impl ReadCtx {
         if self.damage_window.len() > self.damage_window_max {
             self.damage_window.remove(0);
         }
+        // Diagnostic state.
+        self.total_reads_ok += 1;
+        self.last_success_at = Some(std::time::Instant::now());
+        // If we were in a damage zone and accumulated enough good
+        // reads to exit (damage_window now all-good), the zone is
+        // over. Don't reset zones_entered — that's a sweep total.
+        if self.in_damage_zone && self.consecutive_good >= self.damage_window_max as u64 {
+            self.in_damage_zone = false;
+            self.last_error_family = None;
+        }
     }
+
+    /// Final per-pass summary suitable for an INFO log at the end of
+    /// `sweep` / `patch`. Caller renders this to a single structured
+    /// log line.
+    pub fn pass_summary(&self) -> PassSummary {
+        PassSummary {
+            total_reads_ok: self.total_reads_ok,
+            total_errors: self.total_errors,
+            zones_entered: self.zones_entered,
+            jumps_taken: self.jumps_taken,
+        }
+    }
+}
+
+/// End-of-pass stats logged at INFO for post-mortem analysis. Lets
+/// an operator answer "how damaged is this disc?" from a single log
+/// line per pass.
+#[derive(Debug, Clone, Copy)]
+pub struct PassSummary {
+    pub total_reads_ok: u64,
+    pub total_errors: u64,
+    pub zones_entered: u64,
+    pub jumps_taken: u64,
 }
 
 /// What the caller should do after a read failure. The caller owns the
@@ -165,7 +299,42 @@ pub enum ReadAction {
 // Pause budget constants. Tuned from 2026-05-07 BU40N traces showing
 // bridge wedges 524 ms after a 5.4-second internal ECC retry. The
 // post-failure pauses give the drive — and the bridge — time to settle.
-const POST_FAILURE_PAUSE_SECS: u64 = 1;
+/// Pause between a failed read and the next read attempt — applied
+/// uniformly to Pass 1 sweep and Pass N patch.
+///
+/// 2026-05-11 reframe: a failed read is a failed read, regardless of
+/// which pass is running. The prior split (1s for Pass N, 5s for Pass
+/// 1 via `PASS_1_FAIL_PAUSE_SECS`) was solving an imaginary cost
+/// problem — real damaged-disc cases mark <50 MB NonTrimmed, and the
+/// extra 5s/error is single-digit minutes per pass, not hours. The
+/// cost of NOT pausing — a drive wedge that aborts the entire
+/// multi-pass recovery — is much worse.
+///
+/// The wedge avoidance principle: error → drive ECC retry (5-10s
+/// internal) → return → cooldown pause → next read. Same shape
+/// everywhere reads can fail.
+const FAIL_PAUSE_SECS: u64 = 5;
+/// Long cooldown applied when a damage zone is first entered (the
+/// FIRST read failure after a clean run, before the drive has had a
+/// chance to cycle in retries that push it toward fast-fail).
+///
+/// Empirical: 2026-05-11 Dune Pt 2 wedge incident showed 7 medium
+/// errors in 6.5 seconds (~1s per attempt + ~1s pause) push the
+/// BU40N's firmware into IllegalRequest fast-fail mode permanently.
+/// Once there, only physical eject + reload clears it. Giving the
+/// drive 30s of breathing room after the FIRST error in a zone —
+/// before we start adding more error counts in the firmware's
+/// internal window — prevents the transition.
+///
+/// Cost on clean discs: zero (first-error path doesn't trigger).
+/// Cost on damaged discs: ~30s × N damage zones; on a 5-zone disc
+/// that's 2.5 min extra. Trade for never wedging the drive.
+const ZONE_ENTRY_COOLDOWN_SECS: u64 = 30;
+/// Cooldown when a long streak of failures suggests the drive is
+/// stuck in a damage zone and needs MORE breathing room than the
+/// standard inter-error pause. Same value as `FAIL_PAUSE_SECS`
+/// because empirically 5s is enough; kept as a separate name so the
+/// escalation policy is explicit at the call site.
 const CONSECUTIVE_FAIL_LONG_PAUSE_SECS: u64 = 5;
 const CONSECUTIVE_FAIL_LONG_PAUSE_THRESHOLD: u64 = 10;
 const POST_JUMP_EXTRA_PAUSE_SECS: u64 = 2;
@@ -174,6 +343,64 @@ const NOT_READY_MAX_RETRIES: u32 = 3;
 const BRIDGE_DEGRADATION_PAUSE_SECS: u64 = 15;
 const BRIDGE_DEGRADATION_MAX_RETRIES: u32 = 5;
 
+/// Base of the damage-jump distance formula: `jump_sectors =
+/// JUMP_BASE_SECTORS × batch × jump_multiplier`. Bumped 2026-05-10
+/// from 256 → 1024 (4×) so the first damage-jump at batch=32 covers
+/// 64 MB instead of 16 MB. Empirically the BU40N's damage clusters
+/// are 100+ MB wide; 16 MB jumps landed inside the cluster and the
+/// re-read added to the firmware wedge counter. 64 MB → 128 MB
+/// (after one doubling) clears almost any single-cluster damage in
+/// 2 jumps.
+const JUMP_BASE_SECTORS: u64 = 1024;
+
+// Firmware-wedge skip policy for Pass 1 sweep
+// ===========================================
+//
+// When the BU40N (or similar drives) hits a physical-damage cluster,
+// its firmware can transition into a "wedge" state where it returns
+// HARDWARE_ERROR or ILLEGAL_REQUEST for every subsequent read —
+// often for many LBAs after the actual bad sector. Per project docs
+// "Bad-sector handling" rule #2: "Recovery requires eject+reload OR
+// significant cool-down."
+//
+// Pass 1's pre-fix behavior was to immediately AbortPass on the
+// first HARDWARE_ERROR / ILLEGAL_REQUEST, killing the rip at
+// whatever percentage it had reached. That's the wrong call when:
+//   - the damage zone may be small (jumping past it could resume
+//     normal reads), AND
+//   - even if the drive stays wedged, finishing the sweep gives us
+//     an honest mapfile for Pass N to attack later.
+//
+// New policy: treat wedge sense codes the same way the damage-window
+// treats persistent failure — JumpAhead by a large distance with a
+// cooldown pause. Allow up to WEDGE_ABORT_THRESHOLD consecutive
+// wedges (no successful read in between) before declaring the drive
+// truly stuck and surfacing AbortPass to autorip.
+
+/// One-gigabyte jump (1024 MiB) on each wedge. Big enough to clear
+/// almost any single-cluster damage zone we've seen.
+const WEDGE_JUMP_SECTORS: u64 = 524_288;
+/// Cooldown pause after each wedge. Per project docs the drive needs
+/// "significant cool-down"; 30 s strikes a balance between giving
+/// the drive a chance to recover and not stalling the rip if the
+/// drive is permanently stuck.
+const WEDGE_PAUSE_SECS: u64 = 30;
+/// Bail after this many consecutive wedges with no good read in
+/// between. At 1 GB jumps this lets us scan ~16 GB worth of fully
+/// wedged area before giving up — generous enough to clear most
+/// physical-damage clusters, bounded enough to not loop forever on
+/// a permanently bricked drive.
+const WEDGE_ABORT_THRESHOLD: u64 = 16;
+
+/// Pass-N wedge-skip distance. Pass N's batch=1 reads target
+/// specific NonTrimmed sectors from Pass 1, so a big 1 GB skip
+/// would blow past the current NonTrimmed range and abandon many
+/// sectors that might still recover. Use a smaller skip just to
+/// move past the bricked LBA + a small buffer — the outer patch
+/// loop's next iteration picks up the next sector in the same or
+/// next range.
+const WEDGE_PASS_N_SKIP_SECTORS: u64 = 64;
+
 /// THE single error-handling entry point. Updates `ctx`, returns the
 /// action the caller must apply.
 ///
@@ -191,12 +418,53 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
         ctx.consecutive_outer_failures += 1;
     }
 
+    // Diagnostic instrumentation — compute timing context BEFORE
+    // mutating the timestamps so the log reflects the gap to the
+    // PREVIOUS error / success, not zero.
+    let now = std::time::Instant::now();
+    let ms_since_last_error = ctx
+        .last_error_at
+        .map(|t| now.duration_since(t).as_millis() as u64);
+    let ms_since_last_success = ctx
+        .last_success_at
+        .map(|t| now.duration_since(t).as_millis() as u64);
+
+    let current_family = err
+        .scsi_sense()
+        .map(|s| SenseFamily::from_sense_key(s.sense_key))
+        .unwrap_or(SenseFamily::Other);
+
+    // Zone-entry tracking: this is the first error after a clean run
+    // (or the first error of the sweep).
+    if !ctx.in_damage_zone && !ctx.bisecting {
+        ctx.in_damage_zone = true;
+        ctx.zones_entered += 1;
+    }
+
+    ctx.total_errors += 1;
+    ctx.last_error_at = Some(now);
+
+    // Wedge transition: previous error was MEDIUM, this one is
+    // HARDWARE or ILLEGAL_REQUEST. That's the moment the drive's
+    // firmware flipped into fast-fail mode. Distinct WARN so logs
+    // make it unambiguous when the wedge "started."
+    let is_wedge_transition = matches!(ctx.last_error_family, Some(prev) if !prev.is_wedge_family())
+        && current_family.is_wedge_family();
+    ctx.last_error_family = Some(current_family);
+
     tracing::warn!(
         target: "freemkv::disc",
         phase = "read_error",
         consecutive_failures = ctx.consecutive_failures,
+        consecutive_outer_failures = ctx.consecutive_outer_failures,
+        ms_since_last_error,
+        ms_since_last_success,
+        total_errors = ctx.total_errors,
+        total_reads_ok = ctx.total_reads_ok,
         batch = ctx.batch,
         bisecting = ctx.bisecting,
+        wedge_count = ctx.wedge_count,
+        sense_family = ?current_family,
         sense_key = err.scsi_sense().map(|s| s.sense_key),
         asc = err.scsi_sense().map(|s| s.asc),
         ascq = err.scsi_sense().map(|s| s.ascq),
@@ -204,6 +472,17 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
         "read failed; classifying"
     );
 
+    if is_wedge_transition {
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "wedge_transition",
+            errors_in_zone = ctx.total_errors,
+            ms_since_last_success,
+            new_family = ?current_family,
+            "drive entered wedge / fast-fail family (was returning recoverable medium errors before this)"
+        );
+    }
+
     // 1. Transport failure: bridge crash / USB disconnect. The outer
     //    pass loop knows how to handle this (rediscover sg path,
     //    re-open drive). Inline single-sector retry here was tried in
@@ -239,11 +518,62 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
         ctx.not_ready_retries = 0;
     }
 
-    // 4. Hardware / illegal request: the drive said "no, won't do it".
-    //    Retrying won't change the answer. Surface to the outer layer
-    //    so it can eject + prompt user.
+    // 4. Hardware error / illegal request — the firmware-wedge family.
+    //    The drive transitioned into a fast-fail state where it
+    //    rejects reads near the LBA. Same response shape for both
+    //    passes (2026-05-11 reframe — error handling is centralized,
+    //    and the wedge is a code-induced state we can avoid via
+    //    pacing + skip):
+    //
+    //    - Pass 1 sweep (bisect_on_marginal=false): jump
+    //      WEDGE_JUMP_SECTORS (1 GB) ahead, pause WEDGE_PAUSE_SECS,
+    //      mark skipped region NonTrimmed.
+    //    - Pass N patch (bisect_on_marginal=true): give up on the
+    //      current sector (the granular target), pause for cooldown,
+    //      let the outer patch loop move to the next NonTrimmed
+    //      range. Implemented as a small JumpAhead so the same code
+    //      path serves both — Pass N's batch=1 means JumpAhead by
+    //      WEDGE_PASS_N_SKIP_SECTORS effectively skips just this
+    //      sector and a small buffer (gives the drive room to
+    //      recover before the next per-sector attempt).
+    //
+    //    Both paths share the WEDGE_ABORT_THRESHOLD budget — only
+    //    AbortPass after N consecutive wedges with no successful
+    //    read in between.
     if sense_key == scsi::SENSE_KEY_HARDWARE_ERROR || sense_key == scsi::SENSE_KEY_ILLEGAL_REQUEST {
-        return ReadAction::AbortPass;
+        if !ctx.bisecting {
+            ctx.wedge_count += 1;
+        }
+        if ctx.wedge_count >= WEDGE_ABORT_THRESHOLD {
+            tracing::warn!(
+                target: "freemkv::disc",
+                phase = "wedge_abort",
+                wedge_count = ctx.wedge_count,
+                threshold = WEDGE_ABORT_THRESHOLD,
+                pass = if ctx.bisect_on_marginal { "N" } else { "1" },
+                "wedge-skip exhausted — drive appears permanently stuck"
+            );
+            return ReadAction::AbortPass;
+        }
+        let jump_sectors = if ctx.bisect_on_marginal {
+            WEDGE_PASS_N_SKIP_SECTORS
+        } else {
+            WEDGE_JUMP_SECTORS
+        };
+        tracing::warn!(
+            target: "freemkv::disc",
+            phase = "wedge_skip",
+            pass = if ctx.bisect_on_marginal { "N" } else { "1" },
+            wedge_count = ctx.wedge_count,
+            jump_sectors,
+            pause_secs = WEDGE_PAUSE_SECS,
+            "wedge detected — skipping ahead and pausing for drive cooldown"
+        );
+        ctx.jumps_taken += 1;
+        return ReadAction::JumpAhead {
+            sectors: jump_sectors,
+            pause_secs: WEDGE_PAUSE_SECS,
+        };
     }
 
     // 5. Marginal media (MEDIUM_ERROR / ABORTED_COMMAND) on a multi-
@@ -290,17 +620,31 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
         bad_count * 100 / ctx.damage_window.len()
     };
 
-    // Pass 1's job is to get to the end of the disc fast. Inter-
-    // block pauses help the drive cool down on Pass N (gentle
-    // recovery on bad ranges) but on Pass 1 they just turn a 30 s
-    // damage zone into 30 minutes of dead-air sleep. Pass N
-    // (`bisect_on_marginal=true`) keeps the original cooldown logic.
-    let pause_secs = if !ctx.bisect_on_marginal {
-        0
+    // Inter-error pause — wedge prevention via pacing.
+    //
+    // Zone-entry case (first error after a clean run): apply the
+    // long ZONE_ENTRY_COOLDOWN_SECS pause. The empirical wedge
+    // observed 2026-05-11 happened ~7 errors into a damage zone,
+    // each retry adding to the firmware's internal counter. A 30s
+    // pause at zone entry lets the drive's bridge / firmware
+    // counters reset before we issue the next read.
+    //
+    // Subsequent errors in the same zone: the standard 5s pause.
+    // (We've already jumped past the initial damage; further errors
+    // mean we landed in another bad cluster — same pacing applies.)
+    //
+    // Long-streak escalation: same 5s currently; kept as a separate
+    // branch for future tuning. Pass N (bisect_on_marginal=true)
+    // uses the standard pauses — it's running single-sector retries
+    // on already-known-bad LBAs by design.
+    let is_zone_entry =
+        ctx.consecutive_outer_failures == 1 && !ctx.bisecting && !ctx.bisect_on_marginal;
+    let pause_secs = if is_zone_entry {
+        ZONE_ENTRY_COOLDOWN_SECS
     } else if ctx.consecutive_failures >= CONSECUTIVE_FAIL_LONG_PAUSE_THRESHOLD {
         CONSECUTIVE_FAIL_LONG_PAUSE_SECS
     } else {
-        POST_FAILURE_PAUSE_SECS
+        FAIL_PAUSE_SECS
     };
 
     // 7. Damage-jump: too many failures → skip ahead by an escalating
@@ -309,6 +653,14 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
     //    multiplier produced a 56 GB jump). Saturating arithmetic on
     //    the sector calc as defence in depth.
     //
+    //    Jump base bumped 2026-05-10 from 256 to 1024 sectors per
+    //    multiplier unit (= 64 MB first jump at batch=32, up from
+    //    16 MB). The smaller base routinely landed jumps back inside
+    //    damage clusters of 100+ MB, each landing adding to the
+    //    firmware's wedge counter. 64 MB initial + 128 MB second +
+    //    256 MB third clears almost any single-cluster damage
+    //    pattern we've seen in 2 jumps.
+    //
     //    Two triggers, evaluated in order:
     //
     //    a. **Fast-entry** — `consecutive_outer_failures >= fast_jump_threshold`.
@@ -321,18 +673,21 @@ pub fn handle_read_error(err: &Error, ctx: &mut ReadCtx) -> ReadAction {
     //       sliding window of 16 outer reads. Pass N's only path,
     //       and Pass 1's fallback if the failures are scattered
     //       enough that we don't hit the consecutive threshold.
-    const MAX_JUMP_MULTIPLIER: u64 = 64; // 64 × 256 × batch sectors
+    const MAX_JUMP_MULTIPLIER: u64 = 64;
     let fast_trigger = !ctx.bisecting && ctx.consecutive_outer_failures >= ctx.fast_jump_threshold;
     let window_trigger =
         ctx.damage_window.len() >= ctx.damage_window_max && bad_pct >= ctx.damage_threshold_pct;
     if fast_trigger || window_trigger {
         let mult = ctx.jump_multiplier.min(MAX_JUMP_MULTIPLIER);
-        let sectors = 256u64.saturating_mul(ctx.batch as u64).saturating_mul(mult);
+        let sectors = JUMP_BASE_SECTORS
+            .saturating_mul(ctx.batch as u64)
+            .saturating_mul(mult);
         ctx.jump_multiplier = (ctx.jump_multiplier.saturating_mul(2)).min(MAX_JUMP_MULTIPLIER);
         // Reset the outer-failure counter so a long damaged region
         // doesn't keep firing fast-jump every read after the initial
         // jump fired. The window-based trigger handles further jumps.
         ctx.consecutive_outer_failures = 0;
+        ctx.jumps_taken += 1;
         return ReadAction::JumpAhead {
             sectors,
             pause_secs: pause_secs + POST_JUMP_EXTRA_PAUSE_SECS,
@@ -374,6 +729,18 @@ mod tests {
         }
     }
 
+    fn illegal_request_err() -> Error {
+        Error::DiscRead {
+            sector: 100,
+            status: Some(2),
+            sense: Some(ScsiSense {
+                sense_key: scsi::SENSE_KEY_ILLEGAL_REQUEST,
+                asc: 0x24,
+                ascq: 0x00,
+            }),
+        }
+    }
+
     #[test]
     fn pass_n_marginal_with_batch_gt_1_bisects() {
         let mut ctx = ReadCtx::for_patch(32);
@@ -382,15 +749,18 @@ mod tests {
     }
 
     #[test]
-    fn pass_1_marginal_skips_instead_of_bisecting() {
-        // Pass 1's job is "fast and accurate" — leave bisection to
-        // Pass N. A failed batch becomes SkipBlock (whole 32-sector
-        // block marked NonTrimmed for Pass N to revisit).
+    fn pass_1_marginal_jumps_immediately_not_bisecting() {
+        // 2026-05-11 wedge-prevention rewrite: Pass 1 jumps on the
+        // FIRST marginal error (fast_jump_threshold=1) rather than
+        // SkipBlock. Retrying the same LBA quickly is what triggers
+        // the BU40N's firmware fast-fail transition; immediate jump
+        // prevents the cascade. Pass N still bisects (its job is
+        // per-sector recovery on already-known-bad LBAs).
         let mut ctx = ReadCtx::for_sweep(32);
         let action = handle_read_error(&medium_err(), &mut ctx);
         match action {
-            ReadAction::SkipBlock { .. } => {}
-            other => panic!("expected SkipBlock for Pass 1, got {other:?}"),
+            ReadAction::JumpAhead { .. } => {}
+            other => panic!("expected JumpAhead on first Pass 1 marginal error, got {other:?}"),
         }
     }
 
@@ -416,26 +786,18 @@ mod tests {
     }
 
     #[test]
-    fn pass_1_jumps_after_4_consecutive_outer_failures() {
-        // The fast-entry trigger: Pass 1 should JumpAhead after 4
-        // consecutive outer-batch failures, BEFORE the 16-block
-        // damage window has filled. Otherwise we spend ~40 minutes
-        // of bisecting/grinding to fill the window before the first
-        // jump on a damage zone we entered cleanly.
+    fn pass_1_jumps_immediately_on_first_outer_failure() {
+        // 2026-05-11 rewrite: fast_jump_threshold is 1 on Pass 1, not
+        // 4. Even ONE error triggers a jump because BU40N's firmware
+        // fast-fail mode is sensitive to retry cadence. The wedge
+        // observed 2026-05-11 happened at 7 errors / 6.5s — by then
+        // we were already wedged. Jumping on error #1 means we
+        // physically can't reach the cascade.
         let mut ctx = ReadCtx::for_sweep(32);
-        // First three should NOT jump (still under threshold of 4).
-        for _ in 0..3 {
-            let a = handle_read_error(&medium_err(), &mut ctx);
-            assert!(
-                !matches!(a, ReadAction::JumpAhead { .. }),
-                "should not jump until 4 consecutive outer failures"
-            );
-        }
-        // Fourth should jump.
         let a = handle_read_error(&medium_err(), &mut ctx);
         assert!(
             matches!(a, ReadAction::JumpAhead { .. }),
-            "expected JumpAhead at 4th consecutive outer failure, got {a:?}"
+            "expected JumpAhead on first outer failure (fast_jump_threshold=1), got {a:?}"
         );
     }
 
@@ -456,12 +818,15 @@ mod tests {
 
     #[test]
     fn outer_success_resets_consecutive_outer_failures() {
+        // With fast_jump_threshold=1 each Pass 1 error fires a jump
+        // and resets `consecutive_outer_failures` to 0 inside the
+        // handler. So we can't accumulate "3" the old way — instead,
+        // verify the counter goes back to 0 after on_success too.
         let mut ctx = ReadCtx::for_sweep(32);
-        for _ in 0..3 {
-            handle_read_error(&medium_err(), &mut ctx);
-        }
-        assert_eq!(ctx.consecutive_outer_failures, 3);
-        // An outer-success (bisecting=false) should reset the counter.
+        handle_read_error(&medium_err(), &mut ctx);
+        // After fast-jump, consecutive_outer_failures already 0.
+        assert_eq!(ctx.consecutive_outer_failures, 0);
+        // on_success keeps it at 0 (defensive).
         ctx.bisecting = false;
         ctx.on_success();
         assert_eq!(ctx.consecutive_outer_failures, 0);
@@ -485,12 +850,113 @@ mod tests {
     }
 
     #[test]
-    fn hardware_error_aborts() {
+    fn pass_1_hardware_error_jumps_ahead_not_aborts() {
+        // New wedge-skip policy: Pass 1 (bisect_on_marginal=false)
+        // should JumpAhead with a 1 GB skip + cooldown pause instead
+        // of immediately aborting. Aborting on first wedge was the
+        // pre-fix behavior that killed rips at 48% on damaged discs.
         let mut ctx = ReadCtx::for_sweep(32);
         let action = handle_read_error(&hardware_err(), &mut ctx);
+        match action {
+            ReadAction::JumpAhead {
+                sectors,
+                pause_secs,
+            } => {
+                assert_eq!(sectors, WEDGE_JUMP_SECTORS);
+                assert_eq!(pause_secs, WEDGE_PAUSE_SECS);
+            }
+            other => panic!("expected JumpAhead, got {other:?}"),
+        }
+        assert_eq!(ctx.wedge_count, 1);
+    }
+
+    #[test]
+    fn pass_1_hardware_error_aborts_after_threshold() {
+        // After WEDGE_ABORT_THRESHOLD consecutive wedges with no good
+        // read in between, autorip should see a real AbortPass so it
+        // can surface "drive is stuck, power-cycle required" to the
+        // user — rather than looping forever on a permanently bricked
+        // drive.
+        let mut ctx = ReadCtx::for_sweep(32);
+        for i in 0..WEDGE_ABORT_THRESHOLD - 1 {
+            let action = handle_read_error(&hardware_err(), &mut ctx);
+            assert!(
+                matches!(action, ReadAction::JumpAhead { .. }),
+                "iter {i}: expected JumpAhead, got {action:?}"
+            );
+        }
+        // The Nth wedge crosses the threshold.
+        let action = handle_read_error(&hardware_err(), &mut ctx);
         assert_eq!(action, ReadAction::AbortPass);
     }
 
+    #[test]
+    fn pass_1_good_read_resets_wedge_count() {
+        // A single successful read between wedges must clear the
+        // skip counter — otherwise a disc with a few scattered bad
+        // zones would eventually run out of skip budget even though
+        // the drive was recovering between zones.
+        let mut ctx = ReadCtx::for_sweep(32);
+        for _ in 0..(WEDGE_ABORT_THRESHOLD - 1) {
+            handle_read_error(&hardware_err(), &mut ctx);
+        }
+        assert_eq!(ctx.wedge_count, WEDGE_ABORT_THRESHOLD - 1);
+        ctx.on_success();
+        assert_eq!(ctx.wedge_count, 0);
+        // After the success, we should still get JumpAhead (not
+        // AbortPass) on the next wedge.
+        let action = handle_read_error(&hardware_err(), &mut ctx);
+        assert!(matches!(action, ReadAction::JumpAhead { .. }));
+    }
+
+    #[test]
+    fn pass_n_hardware_error_also_skips_not_aborts() {
+        // 2026-05-11 reframe: error handling is centralized, the
+        // wedge is a code-induced state, and the avoidance principle
+        // (skip + pause + continue) applies to Pass N too. Previously
+        // Pass N AbortPass'd on first wedge — same fatal-at-48% bug
+        // Pass 1 had pre-fix. Now Pass N gets a smaller skip
+        // (WEDGE_PASS_N_SKIP_SECTORS, not the 1 GB Pass 1 jump)
+        // because Pass N's job IS to revisit specific NonTrimmed
+        // ranges; over-skipping abandons recoverable sectors.
+        let mut ctx = ReadCtx::for_patch(1);
+        let action = handle_read_error(&hardware_err(), &mut ctx);
+        match action {
+            ReadAction::JumpAhead {
+                sectors,
+                pause_secs,
+            } => {
+                assert_eq!(sectors, WEDGE_PASS_N_SKIP_SECTORS);
+                assert_eq!(pause_secs, WEDGE_PAUSE_SECS);
+            }
+            other => panic!("expected JumpAhead, got {other:?}"),
+        }
+        assert_eq!(ctx.wedge_count, 1);
+    }
+
+    #[test]
+    fn pass_n_hardware_error_aborts_after_threshold() {
+        // Same threshold as Pass 1 — after WEDGE_ABORT_THRESHOLD
+        // consecutive wedges with no good read in between, give up.
+        let mut ctx = ReadCtx::for_patch(1);
+        for _ in 0..WEDGE_ABORT_THRESHOLD - 1 {
+            let action = handle_read_error(&hardware_err(), &mut ctx);
+            assert!(matches!(action, ReadAction::JumpAhead { .. }));
+        }
+        let action = handle_read_error(&hardware_err(), &mut ctx);
+        assert_eq!(action, ReadAction::AbortPass);
+    }
+
+    #[test]
+    fn pass_1_illegal_request_also_routes_to_wedge_skip() {
+        // ILLEGAL_REQUEST is the other half of the wedge family:
+        // drive saying "I won't parse your CDB" after entering the
+        // fast-fail state. Same treatment as HARDWARE_ERROR.
+        let mut ctx = ReadCtx::for_sweep(32);
+        let action = handle_read_error(&illegal_request_err(), &mut ctx);
+        assert!(matches!(action, ReadAction::JumpAhead { .. }));
+    }
+
     #[test]
     fn long_failure_streak_extends_pause_on_pass_n() {
         // Pass N keeps the cooldown behaviour: after many consecutive
@@ -514,15 +980,43 @@ mod tests {
     }
 
     #[test]
-    fn pass_1_does_not_pause_on_skip() {
-        // Pass 1 must zoom — a damage zone is Pass N's problem to
-        // recover from. Sleeping between failed batches turned a 30s
-        // damaged region into a 30-minute Pass-1 grind on real discs.
+    fn pass_1_zone_entry_uses_long_cooldown() {
+        // 2026-05-11 wedge-prevention rewrite: Pass 1's FIRST error
+        // (zone entry) gets a 30 s ZONE_ENTRY_COOLDOWN_SECS pause +
+        // a 2 s POST_JUMP_EXTRA on top (since we're also jumping).
+        // The long pause prevents the retry cadence that triggers
+        // firmware fast-fail. Subsequent errors in the same zone fall
+        // back to the standard 5 s FAIL_PAUSE_SECS.
         let mut ctx = ReadCtx::for_sweep(32);
         let action = handle_read_error(&medium_err(), &mut ctx);
         match action {
-            ReadAction::SkipBlock { pause_secs } => assert_eq!(pause_secs, 0),
-            other => panic!("expected SkipBlock, got {other:?}"),
+            ReadAction::JumpAhead { pause_secs, .. } => {
+                assert_eq!(
+                    pause_secs,
+                    ZONE_ENTRY_COOLDOWN_SECS + POST_JUMP_EXTRA_PAUSE_SECS,
+                    "first-error pause should be 30 + 2 = 32 s"
+                );
+            }
+            other => panic!("expected JumpAhead on first Pass 1 error, got {other:?}"),
+        }
+    }
+
+    #[test]
+    fn pass_n_pauses_uniformly_on_failed_read() {
+        // Pass N (bisect_on_marginal=true) is exempt from the
+        // zone-entry long pause — its whole job is to retry single
+        // sectors on already-known-bad LBAs, and the 30 s pause every
+        // single-sector failure would multiply slow recovery
+        // pointlessly. Pass N keeps the standard 5 s FAIL_PAUSE_SECS.
+        let mut ctx = ReadCtx::for_patch(1);
+        let action = handle_read_error(&medium_err(), &mut ctx);
+        match action {
+            ReadAction::SkipBlock { pause_secs } => assert_eq!(pause_secs, FAIL_PAUSE_SECS),
+            ReadAction::JumpAhead { pause_secs, .. } => {
+                assert_eq!(pause_secs, FAIL_PAUSE_SECS + POST_JUMP_EXTRA_PAUSE_SECS)
+            }
+            ReadAction::Bisect => {}
+            other => panic!("expected pausing action, got {other:?}"),
         }
     }
 

src/disc/sweep.rs

@@ -20,7 +20,7 @@
 //! - Mapfile is single-writer (consumer-only). No locking.
 //! - All `read_error::ReadCtx` state stays on the producer thread.
 //! - `set_speed` calls happen on the producer thread (same thread that
-//!   owns the `SectorReader`). No new SCSI concurrency.
+//!   owns the `SectorSource`). No new SCSI concurrency.
 //! - Per-iteration ordering of file-write → mapfile-record is kept
 //!   intact in the consumer (write before record), so the on-disk
 //!   invariant "mapfile only marks Finished what the file has

src/drive/mod.rs

@@ -29,7 +29,7 @@ use crate::platform::PlatformDriver;
 use crate::platform::mt1959::Mt1959;
 use crate::profile::{self, DriveProfile};
 use crate::scsi::ScsiTransport;
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use std::path::Path;
 use std::sync::Arc;
 use std::sync::atomic::{AtomicBool, Ordering};
@@ -707,7 +707,7 @@ fn open_block_device_for_sg(sg_path: &Path) -> Option<std::os::unix::io::RawFd>
     }
 }
 
-impl SectorReader for Drive {
+impl SectorSource for Drive {
     fn read_sectors(
         &mut self,
         lba: u32,

src/ifo.rs

@@ -9,7 +9,7 @@
 
 use crate::disc::{Codec, Resolution};
 use crate::error::{Error, Result};
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use crate::udf::UdfFs;
 
 // ── Public types ────────────────────────────────────────────────────────────
@@ -184,7 +184,7 @@ fn bcd_byte(b: u8) -> u32 {
 ///
 /// Reads the VMG (Video Manager) to discover title sets, then reads each
 /// VTS IFO to extract PGC chains, cell addresses, and stream attributes.
-pub fn parse_vmg(reader: &mut dyn SectorReader, udf: &UdfFs) -> Result<DvdInfo> {
+pub fn parse_vmg(reader: &mut dyn SectorSource, udf: &UdfFs) -> Result<DvdInfo> {
     let vmg_data = udf.read_file(reader, "/VIDEO_TS/VIDEO_TS.IFO")?;
 
     // Validate VMG magic
@@ -263,7 +263,7 @@ pub fn parse_vmg(reader: &mut dyn SectorReader, udf: &UdfFs) -> Result<DvdInfo>
 ///
 /// `titles_info` is a list of (chapter_count, vts_title_number) from TT_SRPT.
 fn parse_vts(
-    reader: &mut dyn SectorReader,
+    reader: &mut dyn SectorSource,
     udf: &UdfFs,
     vts_number: u8,
     titles_info: &[(u16, u8)],

src/io/mod.rs

@@ -27,5 +27,7 @@ pub(crate) use writeback_file::WritebackFile;
 // caller — the targeted `#[allow]` keeps the re-export visible without
 // dragging the rest of the module under `dead_code`.
 #[allow(unused_imports)]
-pub use pipeline::WRITE_THROUGH_DEPTH;
-pub use pipeline::{DEFAULT_PIPELINE_DEPTH, Flow, Pipeline, Sink};
+pub use pipeline::{
+    DEFAULT_PIPELINE_DEPTH, Flow, Pipeline, READ_PIPELINE_DEPTH, Sink, WRITE_PIPELINE_DEPTH,
+    WRITE_THROUGH_DEPTH,
+};

src/io/pipeline.rs

@@ -27,15 +27,11 @@
 //! - Consumer panic is converted into
 //!   `Error::IoError { source: io::Error::other(...) }`.
 //!
-//! ## Dead-code suppression
+//! ## Debug logging
 //!
-//! Both `Disc::sweep` (`DEFAULT_PIPELINE_DEPTH`, `spawn_named`,
-//! `try_send`) and `Disc::patch` (`WRITE_THROUGH_DEPTH`, `Flow::Stop`)
-//! are now in-tree callers (0.18 round 2). The targeted `#[allow]`
-//! markers below cover the corners of the API not exercised by either
-//! call site (e.g. `Pipeline::spawn` without a name; `Flow::Stop`
-//! return path from sweep's sink — sweep always consumes the producer's
-//! full work-list). Drop the allows once mux migrates.
+//! Set `FREEMKV_DEBUG=1` environment variable to enable verbose debug
+//! logging throughout the pipeline (channel sends/receives, backpressure,
+//! consumer lag detection). This is critical for diagnosing stalls.
 
 use std::io;
 use std::sync::mpsc::{SyncSender, sync_channel};
@@ -43,20 +39,29 @@ use std::thread::{self, JoinHandle};
 
 use crate::error::Error;
 
+/// Check if verbose debug logging is enabled via FREEMKV_DEBUG env var.
+pub fn debug_enabled() -> bool {
+    std::env::var("FREEMKV_DEBUG")
+        .ok()
+        .map(|v| v == "1" || v == "true" || v == "yes")
+        .unwrap_or(false)
+}
+
 /// Default channel depth for callers without a specific reason to
-/// pick another value.
-///
-/// Empirically tuned for sweep and mux — both want enough slack that
-/// short consumer stalls don't immediately back up onto the producer,
-/// but not so much that a producer outpacing the consumer accumulates
-/// arbitrary buffered work. `4` matches the depth sweep has used
-/// since 0.17.11 (originally in `disc/sweep_pipeline.rs`, now in
-/// `disc/sweep.rs::SweepSink`). Patch should usually use
-/// [`WRITE_THROUGH_DEPTH`] (`1`) instead — write-through gives clean
-/// back-pressure between every read attempt and the matching write,
-/// which matters when the consumer is updating the mapfile in lockstep.
+/// pick another value. Kept conservative (4) — most callers should
+/// use READ_PIPELINE_DEPTH or WRITE_PIPELINE_DEPTH instead.
 pub const DEFAULT_PIPELINE_DEPTH: usize = 4;
 
+/// Read pipeline depth. Larger buffer compensates for drive variability
+/// and NFS sync_file_range stalls; keeps ISO reader thread fed even when
+/// consumer blocks on write.
+pub const READ_PIPELINE_DEPTH: usize = 32;
+
+/// Write pipeline depth. Smaller buffer reduces backpressure risk when
+/// sync_file_range blocks; prevents producer from accumulating too much
+/// work while consumer waits for NFS to drain.
+pub const WRITE_PIPELINE_DEPTH: usize = 16;
+
 /// Channel depth for write-through pipelines. Each `send` fully
 /// drains before the next can enqueue. Use this when the producer
 /// must observe consumer side-effects (e.g. mapfile state) before
@@ -149,6 +154,12 @@ impl<I: Send + 'static, R: Send + 'static> Pipeline<I, R> {
                 let mut stopped = false;
 
                 while let Ok(item) = rx.recv() {
+                    if debug_enabled() {
+                        tracing::debug!("Pipeline receive: item={}", std::any::type_name::<I>());
+                    }
+
+                    let apply_start = std::time::Instant::now();
+
                     if first_err.is_some() || stopped {
                         // Drain remaining items so the producer never
                         // blocks on a dead receiver. `apply` is not
@@ -159,11 +170,32 @@ impl<I: Send + 'static, R: Send + 'static> Pipeline<I, R> {
                         Ok(Flow::Continue) => {}
                         Ok(Flow::Stop) => {
                             stopped = true;
+                            if debug_enabled() {
+                                tracing::debug!("Pipeline: consumer returned Flow::Stop");
+                            }
                         }
                         Err(e) => {
+                            if debug_enabled() {
+                                tracing::debug!("Pipeline: apply error, stopping, err={:?}", e);
+                            }
                             first_err = Some(e);
                         }
                     }
+
+                    let apply_elapsed = apply_start.elapsed();
+                    if debug_enabled() && apply_elapsed > std::time::Duration::from_millis(100) {
+                        tracing::debug!(
+                            "Pipeline apply: took {:.2}s, item={}",
+                            apply_elapsed.as_secs_f64(),
+                            std::any::type_name::<I>()
+                        );
+                    } else if debug_enabled() {
+                        tracing::debug!(
+                            "Pipeline apply: OK in {:.3}ms, item={}",
+                            apply_elapsed.as_micros(),
+                            std::any::type_name::<I>()
+                        );
+                    }
                 }
 
                 match first_err {
@@ -188,7 +220,35 @@ impl<I: Send + 'static, R: Send + 'static> Pipeline<I, R> {
     /// independent signal (e.g. `Halt`) — `send` alone is not the
     /// notification edge.
     pub fn send(&self, item: I) -> Result<(), I> {
-        self.tx.send(item).map_err(|e| e.0)
+        let start = std::time::Instant::now();
+        match self.tx.send(item) {
+            Ok(()) => {
+                let elapsed = start.elapsed();
+                if debug_enabled() && elapsed > std::time::Duration::from_millis(10) {
+                    tracing::debug!(
+                        "Pipeline send: blocked {:.2}s, item={}",
+                        elapsed.as_secs_f64(),
+                        std::any::type_name::<I>()
+                    );
+                } else if debug_enabled() {
+                    tracing::debug!("Pipeline send: OK in {:.3}ms", elapsed.as_micros());
+                }
+                Ok(())
+            }
+            Err(e) => {
+                let elapsed = start.elapsed();
+                if debug_enabled() && elapsed > std::time::Duration::from_millis(10) {
+                    tracing::debug!(
+                        "Pipeline send: blocked {:.2}s before channel closed, item={}",
+                        elapsed.as_secs_f64(),
+                        std::any::type_name::<I>()
+                    );
+                } else if debug_enabled() {
+                    tracing::debug!("Pipeline send: failed after {:.3}ms", elapsed.as_micros());
+                }
+                Err(e.0)
+            }
+        }
     }
 
     /// Non-blocking variant of [`Pipeline::send`]. If the channel is

src/io/writeback_file.rs

@@ -27,7 +27,7 @@ use std::path::Path;
 
 use super::writeback::WritebackPipeline;
 
-const CHUNK_BYTES: u64 = 32 * 1024 * 1024;
+const WRITEBACK_CHUNK_BYTES: u64 = 32 * 1024 * 1024;
 
 pub(crate) struct WritebackFile {
     file: File,
@@ -42,7 +42,7 @@ impl WritebackFile {
     /// or appended files).
     pub(crate) fn new(mut file: File) -> io::Result<Self> {
         let pos = file.stream_position()?;
-        let pipeline = WritebackPipeline::new(&file, pos, CHUNK_BYTES);
+        let pipeline = WritebackPipeline::new(&file, pos, WRITEBACK_CHUNK_BYTES);
         Ok(Self {
             file,
             pipeline,

src/labels/bdmt.rs

@@ -0,0 +1,402 @@
+//! BDMV disc-library metadata (`/BDMV/META/DL/bdmt_<lang>.xml`).
+//!
+//! Every commercial Blu-ray carries a disc-library metadata directory
+//! with one XML file per shipped language. The schema is the Blu-ray
+//! "disc library metadata" namespace (`urn:BDA:bdmv;disclibmeta`),
+//! conventionally prefixed `di:`. Fields commonly present:
+//!
+//! - `<di:title>` or `<di:name>` — the title string. Vendor practice
+//!   varies (Paramount discs tend to use `<di:name>`).
+//! - `<di:description>` — optional synopsis (often absent on retail
+//!   discs; common on box sets and special editions).
+//! - `<di:discNumber>` / `<di:numSets>` (or `<di:numberOfSets>`) —
+//!   set position for multi-disc releases.
+//!
+//! This module is intentionally separate from the BD-J `StreamLabel`
+//! parsers under `labels/*.rs`. The XML here is disc-level (title,
+//! description, set position), not per-stream — wiring into the main
+//! parser registry happens elsewhere.
+//!
+//! Real-world XML is irregular: missing description elements, multiple
+//! title elements (first one wins), and occasional malformed content.
+//! Extraction is best-effort — a malformed file is treated as "no
+//! metadata" (returns `None` from the helper), and the caller can
+//! still get metadata from sibling-language XML files.
+
+// The module wiring (registry hook + public re-export) is added
+// separately. Until then the parse/detect entry points have no
+use super::xml;
+use crate::sector::SectorSource;
+use crate::udf::UdfFs;
+use std::collections::BTreeMap;
+
+/// Disc-level metadata extracted from `/BDMV/META/DL/bdmt_*.xml`.
+///
+/// All maps are keyed by 3-char ISO 639-2 language code (e.g.
+/// `"eng"`, `"fra"`, `"jpn"`) — the same key segment used in the
+/// `bdmt_<lang>.xml` filename.
+#[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")
+    pub titles: BTreeMap<String, String>,
+    /// First-line / short description, per lang
+    pub descriptions: BTreeMap<String, String>,
+    /// Disc N of M for box sets (None if not a box set)
+    pub disc_number: Option<(u32, u32)>,
+}
+
+/// True if `/BDMV/META/DL/` exists and contains at least one
+/// `bdmt_*.xml` file.
+pub fn detect(udf: &UdfFs) -> bool {
+    let Some(dir) = udf.find_dir("/BDMV/META/DL") else {
+        return false;
+    };
+    dir.entries
+        .iter()
+        .any(|e| !e.is_dir && is_bdmt_filename(&e.name))
+}
+
+/// Read every `bdmt_<lang>.xml` under `/BDMV/META/DL/` and return the
+/// aggregated [`DiscMetadata`]. Returns `None` if no titles could be
+/// extracted from any file.
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<DiscMetadata> {
+    let dir = udf.find_dir("/BDMV/META/DL")?;
+    let mut out = DiscMetadata::default();
+
+    for entry in &dir.entries {
+        if entry.is_dir {
+            continue;
+        }
+        let Some(lang) = lang_code_from_filename(&entry.name) else {
+            continue;
+        };
+        let path = format!("/BDMV/META/DL/{}", entry.name);
+        let Ok(bytes) = udf.read_file(reader, &path) else {
+            continue;
+        };
+        let Ok(text) = std::str::from_utf8(&bytes) else {
+            continue;
+        };
+        let Some((title, description, disc_set)) = parse_bdmt_xml(&lang, text) else {
+            continue;
+        };
+        out.titles.insert(lang.clone(), title);
+        if let Some(desc) = description {
+            out.descriptions.insert(lang.clone(), desc);
+        }
+        // Disc-set position is disc-global; first one we successfully
+        // read wins. (All bdmt_*.xml on a given disc carry the same
+        // value in practice.)
+        if out.disc_number.is_none() {
+            if let Some(ds) = disc_set {
+                out.disc_number = Some(ds);
+            }
+        }
+    }
+
+    if out.titles.is_empty() {
+        None
+    } else {
+        Some(out)
+    }
+}
+
+/// True if `name` matches the `bdmt_<lang>.xml` convention with a
+/// 3-character ISO 639-2 lang code segment. Case-insensitive.
+fn is_bdmt_filename(name: &str) -> bool {
+    lang_code_from_filename(name).is_some()
+}
+
+/// Extract the 3-char language code from a `bdmt_<lang>.xml` filename.
+/// Returns `None` if the filename doesn't match. Lang code is
+/// lowercased so callers always see e.g. `"eng"` not `"ENG"`.
+fn lang_code_from_filename(name: &str) -> Option<String> {
+    let lower = name.to_ascii_lowercase();
+    let stem = lower.strip_suffix(".xml")?;
+    let lang = stem.strip_prefix("bdmt_")?;
+    // ISO 639-2 codes are exactly 3 ASCII letters. Be strict — keeps
+    // us from picking up unrelated `bdmt_foo.xml` siblings.
+    if lang.len() != 3 || !lang.chars().all(|c| c.is_ascii_alphabetic()) {
+        return None;
+    }
+    Some(lang.to_string())
+}
+
+/// Tuple returned by [`parse_bdmt_xml`]: `(title, description?, disc_set?)`.
+/// Aliased so the function signature isn't a clippy::type-complexity offender.
+pub(crate) type BdmtFields = (String, Option<String>, Option<(u32, u32)>);
+
+/// Parse one `bdmt_<lang>.xml` document and return
+/// `(title, description?, disc_set?)`. Returns `None` if no title
+/// could be located — the caller treats this as "skip this file".
+///
+/// Title-element preference: `<di:name>` → `<di:title>` →
+/// `<di:tableOfContents>/<di:titleName>` (first match wins, per the
+/// authoring-tool conventions documented at the module level).
+pub(crate) fn parse_bdmt_xml(_lang_code: &str, xml_text: &str) -> Option<BdmtFields> {
+    let title = extract_title(xml_text)?;
+    let description = xml::text(xml_text, "description")
+        .filter(|s| !s.is_empty())
+        .filter(|s| !looks_like_xml(s))
+        .map(|s| s.trim().to_string())
+        .filter(|s| !s.is_empty());
+    let disc_set = extract_disc_set(xml_text);
+    Some((title, description, disc_set))
+}
+
+/// Reject candidate description strings that are themselves XML
+/// fragments — observed on disc-04 (Top Gun: Maverick), 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.
+fn looks_like_xml(s: &str) -> bool {
+    let t = s.trim_start();
+    t.starts_with('<')
+}
+
+/// Try title-bearing element variants in priority order. The `xml`
+/// helpers are case- and namespace-insensitive, so callers pass the
+/// bare local name (no `di:` prefix).
+fn extract_title(xml_text: &str) -> Option<String> {
+    // Order matches the module-level convention: <di:name> first
+    // (Paramount-style), then <di:title>, then the nested
+    // tableOfContents/titleName form.
+    for tag in ["name", "title"] {
+        if let Some(s) = xml::text(xml_text, tag) {
+            let trimmed = s.trim();
+            if !trimmed.is_empty() {
+                return Some(trimmed.to_string());
+            }
+        }
+    }
+    // tableOfContents/titleName: search inside the toc block so we
+    // don't accidentally pick a stray <titleName> from elsewhere.
+    if let Some((s, e)) = xml::find_element(xml_text, "tableOfContents", 0) {
+        let block = &xml_text[s..e];
+        if let Some(t) = xml::text(block, "titleName") {
+            let trimmed = t.trim();
+            if !trimmed.is_empty() {
+                return Some(trimmed.to_string());
+            }
+        }
+    }
+    None
+}
+
+/// Extract `(discNumber, numSets)` if both are present and parse as
+/// `u32`. Accepts either `<di:numSets>` or `<di:numberOfSets>` for
+/// the denominator (both forms appear in the wild).
+fn extract_disc_set(xml_text: &str) -> Option<(u32, u32)> {
+    let n = xml::text(xml_text, "discNumber")?
+        .trim()
+        .parse::<u32>()
+        .ok()?;
+    let total = xml::text(xml_text, "numSets")
+        .or_else(|| xml::text(xml_text, "numberOfSets"))?
+        .trim()
+        .parse::<u32>()
+        .ok()?;
+    Some((n, total))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn extract_simple_title() {
+        // Minimal Paramount-style document: <di:name> as the title
+        // 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>
+</discInfo>"#;
+        let (title, desc, set) = parse_bdmt_xml("eng", xml).expect("title should parse");
+        assert_eq!(title, "Dune Part Two");
+        assert_eq!(desc, None);
+        assert_eq!(set, None);
+    }
+
+    #[test]
+    fn extract_title_element_variant() {
+        // <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>
+</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."));
+    }
+
+    #[test]
+    fn extract_title_from_table_of_contents_fallback() {
+        // Some authoring tools nest the title under tableOfContents.
+        // No <di:name> or <di:title> at top level → fall back to
+        // titleName inside tableOfContents.
+        let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
+  <di:tableOfContents>
+    <di:titleName>Inside Out 2</di:titleName>
+  </di:tableOfContents>
+</discInfo>"#;
+        let (title, _, _) = parse_bdmt_xml("eng", xml).unwrap();
+        assert_eq!(title, "Inside Out 2");
+    }
+
+    #[test]
+    fn extract_box_set_position() {
+        let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
+  <di:name>LOTR Disc 2</di:name>
+  <di:discNumber>2</di:discNumber>
+  <di:numSets>5</di:numSets>
+</discInfo>"#;
+        let (_, _, set) = parse_bdmt_xml("eng", xml).unwrap();
+        assert_eq!(set, Some((2, 5)));
+    }
+
+    #[test]
+    fn extract_box_set_position_alternate_total_tag() {
+        // <di:numberOfSets> is an alternate spelling we've seen.
+        let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
+  <di:name>X</di:name>
+  <di:discNumber>3</di:discNumber>
+  <di:numberOfSets>6</di:numberOfSets>
+</discInfo>"#;
+        let (_, _, set) = parse_bdmt_xml("eng", xml).unwrap();
+        assert_eq!(set, Some((3, 6)));
+    }
+
+    #[test]
+    fn extract_box_set_requires_both_fields() {
+        // discNumber alone (no total) yields None — we don't fabricate
+        // a denominator.
+        let xml = r#"<discInfo xmlns:di="urn:BDA:bdmv;disclibmeta">
+  <di:name>X</di:name>
+  <di:discNumber>1</di:discNumber>
+</discInfo>"#;
+        let (_, _, set) = parse_bdmt_xml("eng", xml).unwrap();
+        assert_eq!(set, None);
+    }
+
+    #[test]
+    fn multiple_languages_keyed_correctly() {
+        // Simulate driving parse_bdmt_xml from two synthetic XML
+        // blobs and aggregating into DiscMetadata the same way parse()
+        // 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>
+</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>
+</discInfo>"#;
+
+        let mut meta = DiscMetadata::default();
+        for (lang, blob) in [("eng", eng_xml), ("fra", fra_xml)] {
+            let (title, desc, ds) = parse_bdmt_xml(lang, blob).unwrap();
+            meta.titles.insert(lang.to_string(), title);
+            if let Some(d) = desc {
+                meta.descriptions.insert(lang.to_string(), d);
+            }
+            if meta.disc_number.is_none() {
+                if let Some(d) = ds {
+                    meta.disc_number = Some(d);
+                }
+            }
+        }
+
+        assert_eq!(
+            meta.titles.get("eng").map(String::as_str),
+            Some("Dune Part Two")
+        );
+        assert_eq!(
+            meta.titles.get("fra").map(String::as_str),
+            Some("Dune Deuxième Partie")
+        );
+        assert!(meta.descriptions.get("eng").is_none());
+        assert_eq!(
+            meta.descriptions.get("fra").map(String::as_str),
+            Some("Suite du film de 2021.")
+        );
+        assert_eq!(meta.disc_number, None);
+    }
+
+    #[test]
+    fn malformed_xml_returns_none() {
+        // Random gibberish has no recognizable title element. We
+        // document the contract: parse_bdmt_xml returns None, and
+        // parse() (the caller) skips the file. Aggregating across
+        // zero files leaves DiscMetadata::default() — which parse()
+        // surfaces as None to its caller. Either is documented as
+        // acceptable per the module spec.
+        let bad = "this is not xml &&& <<< nope";
+        assert!(parse_bdmt_xml("eng", bad).is_none());
+
+        // Half-open tag, no body, no close: also yields no title.
+        let truncated = "<discInfo><di:name>";
+        assert!(parse_bdmt_xml("eng", truncated).is_none());
+    }
+
+    #[test]
+    fn description_with_only_child_xml_is_dropped() {
+        // Real-world bug from disc-04 (Top Gun: Maverick, 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:description>
+              <di:thumbnail href="tgm_meta_sm.jpg" />
+              <di:thumbnail href="tgm_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!(
+            description.is_none(),
+            "description containing only XML children must be dropped, got {description:?}"
+        );
+    }
+
+    #[test]
+    fn description_with_plain_text_passes_through() {
+        // The legitimate case still works: a description with actual
+        // prose survives the looks_like_xml filter.
+        let xml = r#"<discInfo>
+            <di:name>Some Movie</di:name>
+            <di:description>An epic tale of one man's quest for tea.</di:description>
+        </discInfo>"#;
+        let (_, description, _) = parse_bdmt_xml("eng", xml).expect("must parse");
+        assert_eq!(
+            description.as_deref(),
+            Some("An epic tale of one man's quest for tea.")
+        );
+    }
+
+    #[test]
+    fn whitespace_in_title_is_trimmed() {
+        let xml = r#"<discInfo><di:name>
+            Dune Part Two
+        </di:name></discInfo>"#;
+        let (title, _, _) = parse_bdmt_xml("eng", xml).unwrap();
+        assert_eq!(title, "Dune Part Two");
+    }
+
+    #[test]
+    fn lang_code_extraction() {
+        assert_eq!(lang_code_from_filename("bdmt_eng.xml"), Some("eng".into()));
+        assert_eq!(lang_code_from_filename("BDMT_FRA.XML"), Some("fra".into()));
+        assert_eq!(lang_code_from_filename("bdmt_jpn.xml"), Some("jpn".into()));
+        // Non-matching cases:
+        assert_eq!(lang_code_from_filename("bdmt_.xml"), None);
+        assert_eq!(lang_code_from_filename("bdmt_engl.xml"), None);
+        assert_eq!(lang_code_from_filename("bdmt_e1g.xml"), None);
+        assert_eq!(lang_code_from_filename("bdmt_eng.txt"), None);
+        assert_eq!(lang_code_from_filename("foo.xml"), None);
+    }
+}

src/labels/clpi_audit.rs

@@ -0,0 +1,291 @@
+//! CLPI vs MPLS cross-validation diagnostic.
+//!
+//! Empirical question (raised 2026-05-11): is CLPI's per-stream
+//! language and codec data truly redundant with MPLS's STN-table data
+//! on real-world Blu-rays?
+//!
+//! Build a quick audit that walks both sources, normalizes their stream
+//! lists by (PID, language, coding_type), and flags any disagreement.
+//!
+//! Three classes of mismatch we want to detect:
+//!
+//! 1. **CLPI has streams MPLS doesn't reference.** Orphan streams in
+//!    the .m2ts that no playlist's STN table includes. Means the user
+//!    can't reach them through the menu but they're physically on the
+//!    disc.
+//! 2. **MPLS has streams CLPI doesn't list.** Should never happen if
+//!    both parsers are correct — playlists reference clips which
+//!    reference streams. If it happens, one of our parsers has a bug.
+//! 3. **Same PID, different language / coding_type.** The playlist re-
+//!    tagged a stream's metadata. Rare but spec-permitted. Means CLPI
+//!    and MPLS disagree about the same physical stream's properties.
+//!
+//! If audits across the corpus show zero mismatches of any class, CLPI
+//! program_info extraction is **empirically redundant** for labels and
+//! we can leave it out of the registry. If even one mismatch surfaces,
+//! we add a CLPI label parser to the registry as belt-and-suspenders.
+//!
+//! This module exposes `audit(reader, udf)` returning a structured
+//! report. Surfaced via the labels-analyze tool — not part of the
+//! `analyze()` pipeline (no impact on the label output).
+
+use crate::sector::SectorSource;
+use crate::udf::UdfFs;
+use std::collections::BTreeMap;
+
+/// One row in the audit: a stream PID that's known to one source or
+/// both, with the fields each source reported.
+#[derive(Debug, Clone)]
+pub struct ClpiVsMplsRow {
+    pub pid: u16,
+    pub clpi_coding_type: Option<u8>,
+    pub clpi_language: Option<String>,
+    pub mpls_coding_type: Option<u8>,
+    pub mpls_language: Option<String>,
+}
+
+impl ClpiVsMplsRow {
+    /// Three rules for classification:
+    /// - both sources missing (impossible — caller wouldn't insert)
+    /// - one source missing → class A or B (orphan-on-disc / playlist-only)
+    /// - both present but fields differ → class C (metadata divergence)
+    /// - both present and identical → no mismatch
+    pub fn class(&self) -> ClpiVsMplsClass {
+        match (
+            self.clpi_coding_type.is_some(),
+            self.mpls_coding_type.is_some(),
+        ) {
+            (true, false) => ClpiVsMplsClass::ClpiOnly,
+            (false, true) => ClpiVsMplsClass::MplsOnly,
+            (true, true) => {
+                let coding_match = self.clpi_coding_type == self.mpls_coding_type;
+                let lang_match = self.clpi_language == self.mpls_language;
+                if coding_match && lang_match {
+                    ClpiVsMplsClass::Match
+                } else {
+                    ClpiVsMplsClass::Divergent
+                }
+            }
+            (false, false) => ClpiVsMplsClass::Match,
+        }
+    }
+}
+
+/// Classification of one (PID) row.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ClpiVsMplsClass {
+    /// PID seen in CLPI ProgramInfo but no MPLS STN table references
+    /// it. Orphan on disc.
+    ClpiOnly,
+    /// PID seen in MPLS STN table but no CLPI ProgramInfo includes it.
+    /// One of our parsers probably has a bug.
+    MplsOnly,
+    /// Both sources see this PID with the same coding_type + language.
+    Match,
+    /// Both sources see this PID but disagree on coding_type or language.
+    /// MPLS wins for label rendering (playlist-authoritative view); CLPI
+    /// is the per-clip ground truth.
+    Divergent,
+}
+
+/// Full audit report.
+#[derive(Debug, Clone, Default)]
+pub struct ClpiVsMplsAudit {
+    pub rows: Vec<ClpiVsMplsRow>,
+}
+
+impl ClpiVsMplsAudit {
+    pub fn class_counts(&self) -> (usize, usize, usize, usize) {
+        let mut clpi_only = 0;
+        let mut mpls_only = 0;
+        let mut matches = 0;
+        let mut divergent = 0;
+        for r in &self.rows {
+            match r.class() {
+                ClpiVsMplsClass::ClpiOnly => clpi_only += 1,
+                ClpiVsMplsClass::MplsOnly => mpls_only += 1,
+                ClpiVsMplsClass::Match => matches += 1,
+                ClpiVsMplsClass::Divergent => divergent += 1,
+            }
+        }
+        (clpi_only, mpls_only, matches, divergent)
+    }
+}
+
+/// Walk `/BDMV/CLIPINF/*.clpi` and `/BDMV/PLAYLIST/*.mpls`, build a
+/// dedup-by-PID table of (CLPI fields, MPLS fields), return the
+/// merged view. Missing files (read errors, parse failures) are
+/// silently skipped — this is diagnostic, not correctness-critical.
+pub fn audit(reader: &mut dyn SectorSource, udf: &UdfFs) -> ClpiVsMplsAudit {
+    // Aggregate by PID across all CLPI files. If a PID appears in
+    // multiple clips (typical — main movie clip + trailers reference
+    // the same audio stream PIDs), first encountered wins (they should
+    // all agree per BD spec).
+    let mut clpi_by_pid: BTreeMap<u16, (u8, String)> = BTreeMap::new();
+    if let Some(dir) = udf.find_dir("/BDMV/CLIPINF") {
+        let names: Vec<String> = dir
+            .entries
+            .iter()
+            .filter(|e| !e.is_dir && e.name.to_ascii_lowercase().ends_with(".clpi"))
+            .map(|e| e.name.clone())
+            .collect();
+        for name in names {
+            let path = format!("/BDMV/CLIPINF/{}", name);
+            let Ok(data) = udf.read_file(reader, &path) else {
+                continue;
+            };
+            let Ok(clip) = crate::clpi::parse(&data) else {
+                continue;
+            };
+            for s in clip.streams {
+                clpi_by_pid
+                    .entry(s.pid)
+                    .or_insert((s.coding_type, s.language));
+            }
+        }
+    }
+
+    // Same for MPLS streams.
+    let mut mpls_by_pid: BTreeMap<u16, (u8, String)> = BTreeMap::new();
+    if let Some(dir) = udf.find_dir("/BDMV/PLAYLIST") {
+        let names: Vec<String> = dir
+            .entries
+            .iter()
+            .filter(|e| !e.is_dir && e.name.to_ascii_lowercase().ends_with(".mpls"))
+            .map(|e| e.name.clone())
+            .collect();
+        for name in names {
+            let path = format!("/BDMV/PLAYLIST/{}", name);
+            let Ok(data) = udf.read_file(reader, &path) else {
+                continue;
+            };
+            let Ok(pl) = crate::mpls::parse(&data) else {
+                continue;
+            };
+            for s in pl.streams {
+                if s.pid == 0 {
+                    // PID 0 means "no PID in stream entry" — skip rather
+                    // than collide with other entries.
+                    continue;
+                }
+                mpls_by_pid
+                    .entry(s.pid)
+                    .or_insert((s.coding_type, s.language));
+            }
+        }
+    }
+
+    // Merge views: every PID seen anywhere gets a row.
+    let mut all_pids: std::collections::BTreeSet<u16> = std::collections::BTreeSet::new();
+    all_pids.extend(clpi_by_pid.keys().copied());
+    all_pids.extend(mpls_by_pid.keys().copied());
+
+    let mut rows = Vec::with_capacity(all_pids.len());
+    for pid in all_pids {
+        let clpi = clpi_by_pid.get(&pid);
+        let mpls = mpls_by_pid.get(&pid);
+        rows.push(ClpiVsMplsRow {
+            pid,
+            clpi_coding_type: clpi.map(|(c, _)| *c),
+            clpi_language: clpi.map(|(_, l)| l.clone()),
+            mpls_coding_type: mpls.map(|(c, _)| *c),
+            mpls_language: mpls.map(|(_, l)| l.clone()),
+        });
+    }
+
+    ClpiVsMplsAudit { rows }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn class_match_when_identical() {
+        let r = ClpiVsMplsRow {
+            pid: 0x1100,
+            clpi_coding_type: Some(0x83),
+            clpi_language: Some("eng".into()),
+            mpls_coding_type: Some(0x83),
+            mpls_language: Some("eng".into()),
+        };
+        assert_eq!(r.class(), ClpiVsMplsClass::Match);
+    }
+
+    #[test]
+    fn class_clpi_only_when_mpls_missing() {
+        let r = ClpiVsMplsRow {
+            pid: 0x1100,
+            clpi_coding_type: Some(0x83),
+            clpi_language: Some("eng".into()),
+            mpls_coding_type: None,
+            mpls_language: None,
+        };
+        assert_eq!(r.class(), ClpiVsMplsClass::ClpiOnly);
+    }
+
+    #[test]
+    fn class_mpls_only_when_clpi_missing() {
+        let r = ClpiVsMplsRow {
+            pid: 0x1100,
+            clpi_coding_type: None,
+            clpi_language: None,
+            mpls_coding_type: Some(0x90),
+            mpls_language: Some("fra".into()),
+        };
+        assert_eq!(r.class(), ClpiVsMplsClass::MplsOnly);
+    }
+
+    #[test]
+    fn class_divergent_on_lang_disagreement() {
+        let r = ClpiVsMplsRow {
+            pid: 0x1100,
+            clpi_coding_type: Some(0x83),
+            clpi_language: Some("eng".into()),
+            mpls_coding_type: Some(0x83),
+            mpls_language: Some("und".into()),
+        };
+        assert_eq!(r.class(), ClpiVsMplsClass::Divergent);
+    }
+
+    #[test]
+    fn class_counts_sum_rows() {
+        let audit = ClpiVsMplsAudit {
+            rows: vec![
+                ClpiVsMplsRow {
+                    pid: 0x1100,
+                    clpi_coding_type: Some(0x83),
+                    clpi_language: Some("eng".into()),
+                    mpls_coding_type: Some(0x83),
+                    mpls_language: Some("eng".into()),
+                }, // Match
+                ClpiVsMplsRow {
+                    pid: 0x1101,
+                    clpi_coding_type: Some(0x83),
+                    clpi_language: Some("fra".into()),
+                    mpls_coding_type: None,
+                    mpls_language: None,
+                }, // ClpiOnly
+                ClpiVsMplsRow {
+                    pid: 0x1102,
+                    clpi_coding_type: None,
+                    clpi_language: None,
+                    mpls_coding_type: Some(0x90),
+                    mpls_language: Some("eng".into()),
+                }, // MplsOnly
+                ClpiVsMplsRow {
+                    pid: 0x1103,
+                    clpi_coding_type: Some(0x86),
+                    clpi_language: Some("spa".into()),
+                    mpls_coding_type: Some(0x86),
+                    mpls_language: Some("ita".into()),
+                }, // Divergent
+            ],
+        };
+        let (co, mo, m, d) = audit.class_counts();
+        assert_eq!(co, 1);
+        assert_eq!(mo, 1);
+        assert_eq!(m, 1);
+        assert_eq!(d, 1);
+    }
+}

src/labels/criterion.rs

@@ -3,8 +3,8 @@
 //! Clean structured XML with Content/Qualifier per stream and
 //! stream number mapping via playbackconfig.
 
-use super::{LabelPurpose, LabelQualifier, StreamLabel, StreamLabelType};
-use crate::sector::SectorReader;
+use super::{LabelPurpose, LabelQualifier, ParseResult, StreamLabel, StreamLabelType, xml};
+use crate::sector::SectorSource;
 use crate::udf::UdfFs;
 use std::collections::HashMap;
 
@@ -12,7 +12,7 @@ pub fn detect(udf: &UdfFs) -> bool {
     super::jar_file_exists(udf, "streamproperties.xml")
 }
 
-pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
     let sp_data = super::read_jar_file(reader, udf, "streamproperties.xml")?;
     let sp_text = std::str::from_utf8(&sp_data).ok()?;
 
@@ -66,7 +66,8 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     if labels.is_empty() {
         return None;
     }
-    Some(labels)
+    // High confidence: streamproperties.xml is fully structured.
+    Some(ParseResult::high(labels))
 }
 
 struct StreamInfo {
@@ -78,105 +79,68 @@ struct StreamInfo {
     qualifier: LabelQualifier,
 }
 
-fn parse_stream_infos(xml: &str) -> Vec<StreamInfo> {
+fn parse_stream_infos(text: &str) -> Vec<StreamInfo> {
     let mut infos = Vec::new();
-    let mut pos = 0;
 
-    while pos < xml.len() {
-        let (tag, stream_type) = if let Some(p) = xml[pos..].find("<AudioStreamInfos>") {
-            (p + pos, StreamLabelType::Audio)
-        } else if let Some(p) = xml[pos..].find("<SubtitleStreamInfos>") {
-            (p + pos, StreamLabelType::Subtitle)
-        } else {
-            break;
-        };
+    for (tag_name, stream_type) in [
+        ("AudioStreamInfos", StreamLabelType::Audio),
+        ("SubtitleStreamInfos", StreamLabelType::Subtitle),
+    ] {
+        let mut from = 0;
+        while let Some((start, end)) = xml::find_element(text, tag_name, from) {
+            let block = &text[start..end];
+            let id = xml::text(block, "ID").unwrap_or_default();
+            let lang_id = xml::text(block, "LangInfoID").unwrap_or_default();
+            let content = xml::text(block, "Content").unwrap_or_default();
+            let qualifier_str = xml::text(block, "Qualifier").unwrap_or_default();
 
-        let end_tag = match stream_type {
-            StreamLabelType::Audio => "</AudioStreamInfos>",
-            StreamLabelType::Subtitle => "</SubtitleStreamInfos>",
-        };
+            let (language, variant) = if lang_id.contains('_') {
+                let parts: Vec<&str> = lang_id.splitn(2, '_').collect();
+                (parts[0].to_lowercase(), parts[1].to_string())
+            } else {
+                (lang_id.to_lowercase(), String::new())
+            };
 
-        let block_end = match xml[tag..].find(end_tag) {
-            Some(p) => tag + p + end_tag.len(),
-            None => break,
-        };
+            let purpose = if content.eq_ignore_ascii_case("COMMENTARY") {
+                LabelPurpose::Commentary
+            } else {
+                LabelPurpose::Normal
+            };
 
-        let block = &xml[tag..block_end];
-        let id = extract_tag(block, "ID").unwrap_or_default();
-        let lang_id = extract_tag(block, "LangInfoID").unwrap_or_default();
-        let content = extract_tag(block, "Content").unwrap_or_default();
-        let qualifier_str = extract_tag(block, "Qualifier").unwrap_or_default();
+            let qualifier = match qualifier_str.to_ascii_uppercase().as_str() {
+                "SDH" => LabelQualifier::Sdh,
+                "DS" => LabelQualifier::DescriptiveService,
+                _ => LabelQualifier::None,
+            };
 
-        let (language, variant) = if lang_id.contains('_') {
-            let parts: Vec<&str> = lang_id.splitn(2, '_').collect();
-            (parts[0].to_lowercase(), parts[1].to_string())
-        } else {
-            (lang_id.to_lowercase(), String::new())
-        };
-
-        let purpose = match content.as_str() {
-            "COMMENTARY" => LabelPurpose::Commentary,
-            _ => LabelPurpose::Normal,
-        };
-
-        let qualifier = match qualifier_str.as_str() {
-            "SDH" => LabelQualifier::Sdh,
-            "DS" => LabelQualifier::DescriptiveService,
-            _ => LabelQualifier::None,
-        };
-
-        infos.push(StreamInfo {
-            id,
-            stream_type,
-            language,
-            variant,
-            purpose,
-            qualifier,
-        });
-        pos = block_end;
+            infos.push(StreamInfo {
+                id,
+                stream_type,
+                language,
+                variant,
+                purpose,
+                qualifier,
+            });
+            from = end;
+        }
     }
     infos
 }
 
-fn parse_playback_config(xml: &str, map: &mut HashMap<String, u16>) {
-    let mut pos = 0;
-    while pos < xml.len() {
-        let tag_start = if let Some(p) = xml[pos..].find("<AudioStreams>") {
-            Some(p + pos)
-        } else {
-            xml[pos..].find("<SubtitlesStreams>").map(|p| p + pos)
-        };
-
-        let tag_start = match tag_start {
-            Some(p) => p,
-            None => break,
-        };
-
-        let block_end = xml[tag_start..]
-            .find("</AudioStreams>")
-            .or_else(|| xml[tag_start..].find("</SubtitlesStreams>"))
-            .map(|p| tag_start + p + 20)
-            .unwrap_or(xml.len());
-
-        let block = &xml[tag_start..block_end];
-
-        if let (Some(stream_id_str), Some(info_id)) = (
-            extract_tag(block, "StreamID"),
-            extract_tag(block, "StreamInfo_ID"),
-        ) {
-            if let Ok(stream_num) = stream_id_str.parse::<u16>() {
-                map.insert(info_id, stream_num);
+fn parse_playback_config(text: &str, map: &mut HashMap<String, u16>) {
+    for tag_name in ["AudioStreams", "SubtitlesStreams"] {
+        let mut from = 0;
+        while let Some((start, end)) = xml::find_element(text, tag_name, from) {
+            let block = &text[start..end];
+            if let (Some(stream_id_str), Some(info_id)) = (
+                xml::text(block, "StreamID"),
+                xml::text(block, "StreamInfo_ID"),
+            ) {
+                if let Ok(stream_num) = stream_id_str.parse::<u16>() {
+                    map.insert(info_id, stream_num);
+                }
             }
+            from = end;
         }
-
-        pos = block_end;
     }
 }
-
-fn extract_tag(xml: &str, tag: &str) -> Option<String> {
-    let open = format!("<{tag}>");
-    let close = format!("</{tag}>");
-    let start = xml.find(&open)? + open.len();
-    let end = xml[start..].find(&close)? + start;
-    Some(xml[start..end].trim().to_string())
-}

src/labels/ctrm.rs

@@ -4,8 +4,8 @@
 //! When both exist, language_streams.txt provides structured types while
 //! menu_base.prop provides stream number → button name mapping.
 
-use super::{LabelPurpose, LabelQualifier, StreamLabel, StreamLabelType, vocab};
-use crate::sector::SectorReader;
+use super::{LabelPurpose, LabelQualifier, ParseResult, StreamLabel, StreamLabelType, vocab};
+use crate::sector::SectorSource;
 use crate::udf::UdfFs;
 use std::collections::HashMap;
 
@@ -14,7 +14,7 @@ pub fn detect(udf: &UdfFs) -> bool {
         || super::jar_file_exists(udf, "language_streams.txt")
 }
 
-pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
     // Try language_streams.txt first (richer structured data)
     let ls_labels = parse_language_streams(reader, udf);
 
@@ -22,12 +22,18 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     let mb_labels = parse_menu_base(reader, udf);
 
     // If we have both, merge: language_streams for structure, menu_base for names
-    match (ls_labels, mb_labels) {
-        (Some(ls), Some(mb)) => Some(merge(ls, mb)),
-        (Some(ls), None) => Some(ls),
-        (None, Some(mb)) => Some(mb),
-        (None, None) => None,
+    let labels = match (ls_labels, mb_labels) {
+        (Some(ls), Some(mb)) => merge(ls, mb),
+        (Some(ls), None) => ls,
+        (None, Some(mb)) => mb,
+        (None, None) => return None,
+    };
+    if labels.is_empty() {
+        return None;
     }
+    // High confidence: both language_streams.txt and menu_base.prop
+    // are structured key-value formats with documented types.
+    Some(ParseResult::high(labels))
 }
 
 fn merge(ls: Vec<StreamLabel>, mb: Vec<StreamLabel>) -> Vec<StreamLabel> {
@@ -49,7 +55,7 @@ fn merge(ls: Vec<StreamLabel>, mb: Vec<StreamLabel>) -> Vec<StreamLabel> {
 
 // ── language_streams.txt parser ────────────────────────────────────────────
 
-fn parse_language_streams(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+fn parse_language_streams(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
     let data = super::read_jar_file(reader, udf, "language_streams.txt")?;
     let text = std::str::from_utf8(&data).ok()?;
 
@@ -172,9 +178,167 @@ fn parse_language_streams(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<
     Some(labels)
 }
 
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    /// Build a minimal menu_base.prop text and run `parse_menu_base`'s
+    /// inner logic via a temporary closure. This isolates the prop
+    /// parsing without needing a SectorSource.
+    fn parse_props(text: &str) -> Vec<StreamLabel> {
+        // Mirror the inner loop of parse_menu_base exactly. Kept
+        // separate so the test doesn't need disc fixtures.
+        use std::collections::HashMap;
+        let mut entries: HashMap<String, HashMap<String, String>> = HashMap::new();
+        for line in text.lines() {
+            let line = line.trim();
+            if line.is_empty() || line.starts_with('#') {
+                continue;
+            }
+            let Some(eq_pos) = line.find('=') else {
+                continue;
+            };
+            let full_key = &line[..eq_pos];
+            let value = &line[eq_pos + 1..];
+            if let Some(dot_pos) = full_key.rfind('.') {
+                entries
+                    .entry(full_key[..dot_pos].to_string())
+                    .or_default()
+                    .insert(full_key[dot_pos + 1..].to_string(), value.to_string());
+            }
+        }
+        let mut labels = Vec::new();
+        for (prefix, props) in &entries {
+            let is_audio = props
+                .get("class")
+                .is_some_and(|c| c.contains("AudioButton"))
+                || prefix.starts_with("audio_");
+            let is_subtitle = props
+                .get("class")
+                .is_some_and(|c| c.contains("SubtitleButton"))
+                || prefix.starts_with("subtitle_");
+            let stream_num_str = props
+                .get("streamNumber")
+                .or_else(|| props.get("audioStream"))
+                .or_else(|| props.get("subtitleStream"));
+            let stream_num: u16 = match stream_num_str.and_then(|s| s.parse().ok()) {
+                Some(n) if n > 0 => n,
+                _ => continue,
+            };
+            if !is_audio && !is_subtitle {
+                continue;
+            }
+            let name = props.get("name").cloned().unwrap_or_default();
+            let purpose = match vocab::purpose(&name) {
+                LabelPurpose::Normal if prefix.contains("comm") => LabelPurpose::Commentary,
+                p => p,
+            };
+            let qualifier = if is_subtitle {
+                vocab::qualifier(&name)
+            } else {
+                LabelQualifier::None
+            };
+            let stream_type = if is_audio {
+                StreamLabelType::Audio
+            } else {
+                StreamLabelType::Subtitle
+            };
+            let language = props
+                .get("audioLanguage")
+                .or_else(|| props.get("subtitleLanguage"))
+                .cloned()
+                .unwrap_or_default();
+            labels.push(StreamLabel {
+                stream_number: stream_num,
+                stream_type,
+                language,
+                name,
+                purpose,
+                qualifier,
+                codec_hint: String::new(),
+                variant: String::new(),
+            });
+        }
+        labels.sort_by_key(|l| (l.stream_type as u8, l.stream_number));
+        labels
+    }
+
+    #[test]
+    fn commentary_via_name() {
+        let labels = parse_props(
+            "audio_1.class=AudioButton\n\
+             audio_1.streamNumber=2\n\
+             audio_1.name=Director's Commentary\n\
+             audio_1.audioLanguage=eng\n",
+        );
+        assert_eq!(labels.len(), 1);
+        assert_eq!(labels[0].purpose, LabelPurpose::Commentary);
+        assert_eq!(labels[0].language, "eng");
+    }
+
+    #[test]
+    fn commentary_via_prefix_when_name_silent() {
+        let labels = parse_props(
+            "audio_commentary_1.class=AudioButton\n\
+             audio_commentary_1.streamNumber=2\n\
+             audio_commentary_1.name=Track 2\n\
+             audio_commentary_1.audioLanguage=eng\n",
+        );
+        assert_eq!(labels[0].purpose, LabelPurpose::Commentary);
+    }
+
+    #[test]
+    fn commenter_does_not_false_match_commentary() {
+        // Regression for the pre-refactor `name.contains("comment")`
+        // bug: this would wrongly classify a "Commenter Pro" track as
+        // Commentary. vocab::purpose enforces a word boundary.
+        let labels = parse_props(
+            "audio_1.class=AudioButton\n\
+             audio_1.streamNumber=2\n\
+             audio_1.name=Commenter Pro Track\n\
+             audio_1.audioLanguage=eng\n",
+        );
+        assert_eq!(labels[0].purpose, LabelPurpose::Normal);
+    }
+
+    #[test]
+    fn descriptive_via_name() {
+        let labels = parse_props(
+            "audio_1.class=AudioButton\n\
+             audio_1.streamNumber=3\n\
+             audio_1.name=English Descriptive Audio\n",
+        );
+        assert_eq!(labels[0].purpose, LabelPurpose::Descriptive);
+    }
+
+    #[test]
+    fn sdh_only_on_subtitles() {
+        // SDH applied to a subtitle stream.
+        let labels = parse_props(
+            "subtitle_1.class=SubtitleButton\n\
+             subtitle_1.streamNumber=4\n\
+             subtitle_1.name=English SDH\n",
+        );
+        assert_eq!(labels[0].qualifier, LabelQualifier::Sdh);
+    }
+
+    #[test]
+    fn sdh_not_applied_to_audio_stream_even_if_name_contains_sdh() {
+        // Audio streams should not pick up SDH (it's a subtitle
+        // concept). Edge case: badly-authored name happens to include
+        // "SDH" — we don't propagate it to audio metadata.
+        let labels = parse_props(
+            "audio_1.class=AudioButton\n\
+             audio_1.streamNumber=5\n\
+             audio_1.name=English SDH (track?)\n",
+        );
+        assert_eq!(labels[0].qualifier, LabelQualifier::None);
+    }
+}
+
 // ── menu_base.prop parser ──────────────────────────────────────────────────
 
-fn parse_menu_base(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+fn parse_menu_base(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
     let data = super::read_jar_file(reader, udf, "menu_base.prop")?;
     let text = std::str::from_utf8(&data).ok()?;
 
@@ -231,16 +395,20 @@ fn parse_menu_base(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<Str
         }
 
         let name = props.get("name").cloned().unwrap_or_default();
-        let name_lower = name.to_lowercase();
 
-        let purpose = if name_lower.contains("comment") || prefix.contains("comm") {
-            LabelPurpose::Commentary
-        } else {
-            LabelPurpose::Normal
+        // Purpose: ask vocab first (word-boundary matched — avoids the
+        // "Commenter" false positive the prior `name.contains("comment")`
+        // had). Then fall back to the structural prefix check
+        // (`audio_commentary.foo`-style keys group commentary streams
+        // regardless of display name).
+        let purpose = match vocab::purpose(&name) {
+            LabelPurpose::Normal if prefix.contains("comm") => LabelPurpose::Commentary,
+            p => p,
         };
 
-        let qualifier = if is_subtitle && name_lower.contains("sdh") {
-            LabelQualifier::Sdh
+        // Qualifier: only apply to subtitles (SDH is a subtitle concept).
+        let qualifier = if is_subtitle {
+            vocab::qualifier(&name)
         } else {
             LabelQualifier::None
         };

src/labels/dbp.rs

@@ -0,0 +1,261 @@
+//! "dbp" framework — Magnolia Pictures BD-J authoring shop (per
+//! `bd-live.magpictures.com` referenced in the disc's
+//! `com/dbp/bluray.MenuXlet.perm`). Detected on UHD discs whose
+//! `/BDMV/JAR/<x>.jar` (top-level, not in a subdir) contains
+//! `com/dbp/` package paths.
+//!
+//! 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):
+//!
+//! ```text
+//! LTextField,Audio1,English Dolby Atmos,Fontstrip_Composite,...
+//! RTextField,Audio2,English Descriptive Audio,Fontstrip_Composite,...
+//! HTextField,Subtitle1,English SDH,Fontstrip_Composite,...
+//! ATextField,Subtitle0,None,Fontstrip_Composite,...
+//! ```
+//!
+//! The single uppercase letter before `TextField` is string-pool
+//! prefix noise — the parser anchors on `TextField,` regardless of
+//! what precedes it. `Subtitle0` is the disable-subtitles menu
+//! button and is skipped (not a real subtitle stream).
+//!
+//! ## Implementation
+//!
+//! v2 (2026-05-10): rewritten on top of [`super::class_reader`] —
+//! iterates `CpInfo::Utf8` constant-pool entries instead of raw byte
+//! scanning each class file. Equivalent label coverage (the literal
+//! `TextField,...` strings live in the CP as Utf8 entries), but
+//! structurally cleaner: no false-positive risk from method bytecode
+//! or attribute names happening to contain `TextField,`. Language /
+//! purpose / qualifier classification moved to [`super::vocab`] so all
+//! Java-parser families share one source of truth.
+
+use super::class_reader::CpInfo;
+use super::{ParseResult, StreamLabel, StreamLabelType, jar, vocab};
+use crate::sector::SectorSource;
+use crate::udf::UdfFs;
+use std::collections::BTreeMap;
+
+/// dbp detect can't peek inside a jar without a SectorSource (the
+/// trait function only takes `&UdfFs`), so we trigger on the cheap
+/// signal "any top-level .jar in /BDMV/JAR/." That fires on every
+/// BD-J disc, but parse() does the real `com/dbp/` check and
+/// returns None on a mismatch — so this parser only ever consumes
+/// time on discs that fell through every earlier parser.
+pub fn detect(udf: &UdfFs) -> bool {
+    jar::has_any_top_level_jar(udf)
+}
+
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
+    jar::for_each_jar(reader, udf, |_entry_name, archive| {
+        if !jar::has_path_prefix(archive, "com/dbp/") {
+            return None;
+        }
+        let labels = scan_jar(archive);
+        if labels.is_empty() {
+            None
+        } else {
+            // High confidence: TextField,Audio1,... is a stable anchor
+            // pattern + vocab routes language/purpose/qualifier.
+            Some(ParseResult::high(labels))
+        }
+    })
+}
+
+fn scan_jar(archive: &mut jar::Jar) -> Vec<StreamLabel> {
+    // BTreeMap so we keep the highest-numbered (last-written) label
+    // for each stream slot deterministic across runs. The same
+    // TextField,Audio1,... string can appear in multiple classes
+    // (button-state variants, localization fallbacks). Last write
+    // wins — they should all agree, but the structure is defensive.
+    let mut audios: BTreeMap<u16, String> = BTreeMap::new();
+    let mut subs: BTreeMap<u16, String> = BTreeMap::new();
+
+    jar::for_each_class(archive, |_class_name, class| {
+        for (_idx, cp) in class.constant_pool.iter() {
+            if let CpInfo::Utf8(s) = cp {
+                collect_textfield(s, &mut audios, &mut subs);
+            }
+        }
+    });
+
+    let mut out = Vec::new();
+    for (num, label) in audios {
+        out.push(make_label(num, label, StreamLabelType::Audio));
+    }
+    for (num, label) in subs {
+        out.push(make_label(num, label, StreamLabelType::Subtitle));
+    }
+    out
+}
+
+fn collect_textfield(
+    s: &str,
+    audios: &mut BTreeMap<u16, String>,
+    subs: &mut BTreeMap<u16, String>,
+) {
+    // Anchor on "TextField," — the prefix character before it varies
+    // (string-pool ordering inside compiled Java) and is irrelevant.
+    let Some(idx) = s.find("TextField,") else {
+        return;
+    };
+    let after = &s[idx + "TextField,".len()..];
+    let mut parts = after.splitn(3, ',');
+    let kind_n = parts.next().unwrap_or("").trim();
+    let label = parts.next().unwrap_or("").trim();
+    if label.is_empty() {
+        return;
+    }
+    if let Some(rest) = kind_n.strip_prefix("Audio") {
+        if let Ok(n) = rest.parse::<u16>() {
+            audios.insert(n, label.to_string());
+        }
+    } else if let Some(rest) = kind_n.strip_prefix("Subtitle") {
+        if let Ok(n) = rest.parse::<u16>() {
+            // Subtitle0 is conventionally the "None / Off" disable
+            // button, not an actual subtitle stream.
+            if n > 0 {
+                subs.insert(n, label.to_string());
+            }
+        }
+    }
+}
+
+fn make_label(num: u16, label: String, stream_type: StreamLabelType) -> StreamLabel {
+    let lang_info = vocab::lang(&label);
+    let language = lang_info.map(|l| l.code).unwrap_or("").to_string();
+    let variant = lang_info.map(|l| l.variant).unwrap_or("").to_string();
+    let qualifier = vocab::qualifier(&label);
+    let purpose = vocab::purpose(&label);
+    StreamLabel {
+        stream_number: num,
+        stream_type,
+        language,
+        name: label,
+        purpose,
+        qualifier,
+        codec_hint: String::new(),
+        variant,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::super::{LabelPurpose, LabelQualifier};
+    use super::*;
+
+    #[test]
+    fn collect_extracts_audio_and_subtitle_indices() {
+        let mut audios = BTreeMap::new();
+        let mut subs = BTreeMap::new();
+        let lines = [
+            "LTextField,Audio1,English Dolby Atmos,Fontstrip_Composite,296,763,275,25,left",
+            "RTextField,Audio2,English Descriptive Audio,Fontstrip_Composite,296,803,275,25,left",
+            "RTextField,Audio3,Spanish 5.1 Dolby Digital,Fontstrip_Composite,296,843,275,25,left",
+            "ATextField,Subtitle0,None,Fontstrip_Composite,1312,843,275,25,left",
+            "HTextField,Subtitle1,English SDH,Fontstrip_Composite,1312,763,275,25,left",
+            "DTextField,Subtitle2,Spanish,Fontstrip_Composite,1312,803,275,25,left",
+        ];
+        for s in &lines {
+            collect_textfield(s, &mut audios, &mut subs);
+        }
+        assert_eq!(audios.len(), 3);
+        assert_eq!(audios[&1], "English Dolby Atmos");
+        assert_eq!(audios[&2], "English Descriptive Audio");
+        assert_eq!(audios[&3], "Spanish 5.1 Dolby Digital");
+        // Subtitle0 ("None") is skipped — disable button, not a stream.
+        assert_eq!(subs.len(), 2);
+        assert_eq!(subs[&1], "English SDH");
+        assert_eq!(subs[&2], "Spanish");
+    }
+
+    #[test]
+    fn collect_ignores_non_textfield_strings() {
+        let mut audios = BTreeMap::new();
+        let mut subs = BTreeMap::new();
+        for s in [
+            "GraphicButton,SU_Audio",
+            "AudioMenu",
+            "CommentaryMenuAlternateScenes",
+            "PrimaryAudioControl",
+        ] {
+            collect_textfield(s, &mut audios, &mut subs);
+        }
+        assert!(audios.is_empty());
+        assert!(subs.is_empty());
+    }
+
+    #[test]
+    fn make_label_routes_via_vocab() {
+        let l = make_label(1, "English SDH".to_string(), StreamLabelType::Subtitle);
+        assert_eq!(l.language, "eng");
+        assert_eq!(l.qualifier, LabelQualifier::Sdh);
+        assert_eq!(l.purpose, LabelPurpose::Normal);
+    }
+
+    #[test]
+    fn make_label_descriptive_audio() {
+        let l = make_label(
+            2,
+            "English Descriptive Audio".to_string(),
+            StreamLabelType::Audio,
+        );
+        assert_eq!(l.language, "eng");
+        assert_eq!(l.purpose, LabelPurpose::Descriptive);
+    }
+
+    #[test]
+    fn make_label_commentary() {
+        let l = make_label(
+            3,
+            "English Director's Commentary".to_string(),
+            StreamLabelType::Audio,
+        );
+        assert_eq!(l.language, "eng");
+        assert_eq!(l.purpose, LabelPurpose::Commentary);
+    }
+
+    #[test]
+    fn make_label_compound_languages_populate_variant() {
+        let brazilian = make_label(1, "Brazilian Portuguese 5.1".into(), StreamLabelType::Audio);
+        assert_eq!(brazilian.language, "por");
+        assert_eq!(brazilian.variant, "Brazilian");
+
+        let castilian = make_label(1, "Castilian Spanish".into(), StreamLabelType::Audio);
+        assert_eq!(castilian.language, "spa");
+        assert_eq!(castilian.variant, "Castilian");
+
+        let canadian = make_label(
+            1,
+            "Canadian French Dolby Digital".into(),
+            StreamLabelType::Audio,
+        );
+        assert_eq!(canadian.language, "fra");
+        assert_eq!(canadian.variant, "Canadian");
+    }
+
+    #[test]
+    fn make_label_bare_language_has_empty_variant() {
+        let l = make_label(1, "English Dolby Atmos".into(), StreamLabelType::Audio);
+        assert_eq!(l.language, "eng");
+        assert_eq!(l.variant, "");
+    }
+
+    #[test]
+    fn make_label_unknown_language_is_empty() {
+        // vocab::lang returns None — make_label converts both fields to "".
+        let l = make_label(1, "Klingon Dolby Atmos".into(), StreamLabelType::Audio);
+        assert_eq!(l.language, "");
+        assert_eq!(l.variant, "");
+    }
+
+    #[test]
+    fn make_label_rnib_descriptive_service() {
+        let l = make_label(1, "English RNIB".into(), StreamLabelType::Subtitle);
+        assert_eq!(l.language, "eng");
+        assert_eq!(l.qualifier, LabelQualifier::DescriptiveService);
+    }
+}

src/labels/jar.rs

@@ -0,0 +1,151 @@
+//! BD-J jar utilities — common scaffolding for parsers that read
+//! `/BDMV/JAR/*.jar`.
+//!
+//! Composes with [`class_reader`](super::class_reader) for structured
+//! `.class` access. Used by `dbp` (string-pool scan via constant pool)
+//! and `deluxe` (bytecode pattern matching) — those parsers express
+//! "open every top-level jar, look at every .class inside" without
+//! repeating the zip-archive boilerplate.
+
+// `try_each_class` is staged for `labels::deluxe`, which needs the
+// early-return form to short-circuit class iteration on a match.
+// dead-code allow comes off when deluxe lands.
+#![allow(dead_code)]
+
+use super::class_reader::ClassFile;
+use crate::sector::SectorSource;
+use crate::udf::UdfFs;
+use std::io::Cursor;
+use zip::ZipArchive;
+
+/// In-memory zip archive: backed by a `Vec<u8>` read from UDF. Owns
+/// the buffer; callers pass it to [`has_path_prefix`], [`for_each_class`],
+/// etc.
+pub type Jar = ZipArchive<Cursor<Vec<u8>>>;
+
+/// True if `/BDMV/JAR/` contains at least one top-level `.jar` file
+/// (not under a subdir). Used by `detect()` in parsers whose real
+/// signal lives inside a jar — they can't open the jar without a
+/// `SectorSource`, so they use this cheap pre-check and do the real
+/// `com/<vendor>/` discriminator in `parse()`.
+pub fn has_any_top_level_jar(udf: &UdfFs) -> bool {
+    let Some(jar_dir) = udf.find_dir("/BDMV/JAR") else {
+        return false;
+    };
+    jar_dir
+        .entries
+        .iter()
+        .any(|e| !e.is_dir && e.name.to_lowercase().ends_with(".jar"))
+}
+
+/// Open every top-level `*.jar` entry in `/BDMV/JAR/` and yield each
+/// `(entry_name, Jar)` to `f`. Returns the first `Some(R)` the callback
+/// produces, or `None` if every jar was visited without a hit.
+///
+/// "Top-level" means entries directly under `/BDMV/JAR/`, not nested
+/// under a subdir. (Pixelogic, Criterion, Paramount, etc. put their
+/// data files inside `/BDMV/JAR/<x>/`; dbp and Deluxe put their jar
+/// directly at `/BDMV/JAR/<name>.jar`.)
+///
+/// Entries that fail to read from UDF or that aren't valid zips are
+/// silently skipped — same defensive shape as the existing dbp parser.
+pub fn for_each_jar<R, F>(reader: &mut dyn SectorSource, udf: &UdfFs, mut f: F) -> Option<R>
+where
+    F: FnMut(&str, &mut Jar) -> Option<R>,
+{
+    let jar_dir = udf.find_dir("/BDMV/JAR")?;
+    for entry in &jar_dir.entries {
+        if entry.is_dir {
+            continue;
+        }
+        if !entry.name.to_lowercase().ends_with(".jar") {
+            continue;
+        }
+        let path = format!("/BDMV/JAR/{}", entry.name);
+        let Ok(bytes) = udf.read_file(reader, &path) else {
+            continue;
+        };
+        let Ok(mut archive) = ZipArchive::new(Cursor::new(bytes)) else {
+            continue;
+        };
+        if let Some(r) = f(&entry.name, &mut archive) {
+            return Some(r);
+        }
+    }
+    None
+}
+
+/// True if any entry in this jar's central directory starts with
+/// `prefix`. Fast — only reads filenames, never extracts bytes.
+///
+/// Used by parsers as a cheap "is this MY framework's jar?" check
+/// (e.g. `has_path_prefix(archive, "com/dbp/")` for dbp,
+/// `has_path_prefix(archive, "com/bydeluxe/")` for Deluxe).
+pub fn has_path_prefix(archive: &mut Jar, prefix: &str) -> bool {
+    for i in 0..archive.len() {
+        if let Ok(f) = archive.by_index(i) {
+            if f.name().starts_with(prefix) {
+                return true;
+            }
+        }
+    }
+    false
+}
+
+/// Iterate every `.class` entry in the jar, parse it with
+/// [`class_reader`], and call `f` with `(entry_name, &ClassFile)`.
+///
+/// Entries that fail to read or parse are silently skipped — this is
+/// label-extraction code, robustness matters more than completeness.
+/// Callers that need to know which classes failed should use the
+/// lower-level [`class_reader`] API directly.
+pub fn for_each_class<F>(archive: &mut Jar, mut f: F)
+where
+    F: FnMut(&str, &ClassFile),
+{
+    for i in 0..archive.len() {
+        let Ok(mut entry) = archive.by_index(i) else {
+            continue;
+        };
+        if !entry.name().ends_with(".class") {
+            continue;
+        }
+        let name = entry.name().to_string();
+        let mut bytes = Vec::with_capacity(entry.size() as usize);
+        if std::io::Read::read_to_end(&mut entry, &mut bytes).is_err() {
+            continue;
+        }
+        let Ok(class) = ClassFile::parse(&bytes) else {
+            continue;
+        };
+        f(&name, &class);
+    }
+}
+
+/// Like [`for_each_class`] but allows the callback to short-circuit
+/// iteration. Returns the first `Some(R)` the callback produces.
+pub fn try_each_class<R, F>(archive: &mut Jar, mut f: F) -> Option<R>
+where
+    F: FnMut(&str, &ClassFile) -> Option<R>,
+{
+    for i in 0..archive.len() {
+        let Ok(mut entry) = archive.by_index(i) else {
+            continue;
+        };
+        if !entry.name().ends_with(".class") {
+            continue;
+        }
+        let name = entry.name().to_string();
+        let mut bytes = Vec::with_capacity(entry.size() as usize);
+        if std::io::Read::read_to_end(&mut entry, &mut bytes).is_err() {
+            continue;
+        }
+        let Ok(class) = ClassFile::parse(&bytes) else {
+            continue;
+        };
+        if let Some(r) = f(&name, &class) {
+            return Some(r);
+        }
+    }
+    None
+}

src/labels/mpls_universal.rs

@@ -0,0 +1,597 @@
+//! Universal MPLS-based stream labels.
+//!
+//! Unlike the framework-specific parsers in this directory (dbp,
+//! pixelogic, ctrm, criterion, ...), this module is the *floor*:
+//! every Blu-ray ships with MPLS playlists under `/BDMV/PLAYLIST/`,
+//! and every MPLS file has an STN table with per-stream ISO 639-2
+//! language codes plus coding-type / channel-layout / sample-rate
+//! bytes from the BD spec.
+//!
+//! The framework parsers extract richer editorial labels ("English
+//! Dolby Atmos", "Director's Commentary") when the disc was authored
+//! with a recognized tool. When none of them match (e.g. a "no BD-J"
+//! disc, or an authoring framework we haven't catalogued), MPLS still
+//! gives us language + codec on every stream — enough to render
+//! something more useful than the bare PID.
+//!
+//! Output confidence is Low: MPLS carries language + codec but
+//! never purpose/qualifier info (no way to tell "Commentary" from
+//! "Normal" from the STN table alone). Higher-confidence framework
+//! parsers, when present, always win on the registry's max-by-confidence
+//! tiebreaker — MPLS is only chosen when nothing else matched.
+
+use super::{
+    LabelPurpose, LabelQualifier, ParseResult, StreamLabel, StreamLabelType,
+    vocab::{self, LangInfo},
+};
+use crate::sector::SectorSource;
+use crate::udf::UdfFs;
+
+/// True iff `/BDMV/PLAYLIST/` exists and contains at least one
+/// `.mpls` file. Cheap directory walk only — no sector reads.
+pub fn detect(udf: &UdfFs) -> bool {
+    let Some(dir) = udf.find_dir("/BDMV/PLAYLIST") else {
+        return false;
+    };
+    dir.entries
+        .iter()
+        .any(|e| !e.is_dir && has_mpls_extension(&e.name))
+}
+
+/// Walk every `*.mpls` in `/BDMV/PLAYLIST/`, parse it, and convert
+/// each StreamEntry to a [`StreamLabel`]. Streams shared across
+/// playlists (same PID) are deduped.
+///
+/// Returns `None` if no labels could be produced (e.g. no .mpls files
+/// parsed successfully, or every parsed stream was a type we skip
+/// like IG / DV EL).
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
+    let playlist_dir = udf.find_dir("/BDMV/PLAYLIST")?;
+
+    // Collect mpls filenames first so we don't hold a borrow on udf
+    // while we call udf.read_file (which takes &self).
+    let mpls_names: Vec<String> = playlist_dir
+        .entries
+        .iter()
+        .filter(|e| !e.is_dir && has_mpls_extension(&e.name))
+        .map(|e| e.name.clone())
+        .collect();
+
+    if mpls_names.is_empty() {
+        return None;
+    }
+
+    let mut labels: Vec<StreamLabel> = Vec::new();
+    // (stream_type_tag, language, codec_hint, pid) — PID is the
+    // canonical "same physical stream" key; type+lang+codec round
+    // out the rare case where two distinct logical streams happen
+    // to share a PID across playlists with different metadata.
+    let mut seen: Vec<(u8, String, String, u16)> = Vec::new();
+
+    // Global 1-based counters keyed by StreamLabelType. Incremented
+    // only when an entry survives dedup, so stream_numbers are dense
+    // (1, 2, 3, ...) per type across the whole disc — not reset per
+    // playlist. A disc with 2 MPLS files that each list the same
+    // 8 audio streams ends up with audio_1..audio_8, not audio_1..
+    // audio_16 or audio_1..audio_8 with audio_1 duplicated.
+    let mut audio_idx: u16 = 0;
+    let mut sub_idx: u16 = 0;
+
+    for name in &mpls_names {
+        let path = format!("/BDMV/PLAYLIST/{}", name);
+        let Ok(data) = udf.read_file(reader, &path) else {
+            continue;
+        };
+        let Ok(playlist) = crate::mpls::parse(&data) else {
+            continue;
+        };
+
+        for entry in &playlist.streams {
+            let label_type = match entry.stream_type {
+                2 | 5 => StreamLabelType::Audio, // primary + secondary audio
+                3 => StreamLabelType::Subtitle,  // PG subtitle
+                // 1 = primary video, 6 = secondary video, 7 = DV EL
+                //     → no StreamLabelType variant for video, skip.
+                // 4 = IG (interactive graphics) — not a user-facing
+                //     stream, skip.
+                _ => continue,
+            };
+
+            let language = normalize_language(&entry.language);
+            let name = language_display_name(&language);
+            let codec_hint = build_codec_hint(label_type, entry);
+
+            let type_tag = type_tag(label_type);
+            let key = (type_tag, language.clone(), codec_hint.clone(), entry.pid);
+            if seen.contains(&key) {
+                continue;
+            }
+            seen.push(key);
+
+            let stream_number = match label_type {
+                StreamLabelType::Audio => {
+                    audio_idx += 1;
+                    audio_idx
+                }
+                StreamLabelType::Subtitle => {
+                    sub_idx += 1;
+                    sub_idx
+                }
+            };
+
+            labels.push(StreamLabel {
+                stream_number,
+                stream_type: label_type,
+                language,
+                name,
+                purpose: LabelPurpose::Normal,
+                qualifier: LabelQualifier::None,
+                codec_hint,
+                variant: String::new(),
+            });
+        }
+    }
+
+    if labels.is_empty() {
+        return None;
+    }
+
+    // MPLS gives language + codec but never editorial info (no
+    // commentary/SDH/director's cut). Low confidence means framework
+    // parsers (paramount, criterion, pixelogic, ctrm, dbp, deluxe) always
+    // win when they match. MPLS only gets chosen as the parser when
+    // nothing else fired — exactly the universal-fallback role we want.
+    Some(ParseResult::low(labels))
+}
+
+fn has_mpls_extension(name: &str) -> bool {
+    // Case-insensitive ".mpls" suffix. Some discs use uppercase,
+    // some lowercase; UDF filenames preserve case but we don't.
+    let n = name.len();
+    if n < 5 {
+        return false;
+    }
+    name[n - 5..].eq_ignore_ascii_case(".mpls")
+}
+
+/// Lowercase + trim the raw 3-char ISO 639-2 code. If the lowered
+/// string maps via [`vocab::lang`] (it won't for plain "eng" — that
+/// matcher is for English-name fragments, not codes) use its
+/// canonical code; otherwise return the trimmed lowercase string.
+fn normalize_language(raw: &str) -> String {
+    let trimmed = raw.trim().to_ascii_lowercase();
+    if trimmed.is_empty() {
+        return String::new();
+    }
+    // vocab::lang() matches free-form English names, not ISO 639-2
+    // codes — so for the typical MPLS payload ("eng", "fra", ...)
+    // it returns None and we keep the trimmed code.
+    if let Some(LangInfo { code, .. }) = vocab::lang(&trimmed) {
+        return code.to_string();
+    }
+    trimmed
+}
+
+/// Human-readable English name for an ISO 639-2 code, or empty if
+/// the code is unknown. Kept inline rather than in vocab because
+/// vocab is the *reverse* mapping (name → code).
+pub(crate) fn language_display_name(iso: &str) -> String {
+    match iso {
+        "eng" => "English",
+        "fra" | "fre" => "French",
+        "spa" => "Spanish",
+        "deu" | "ger" => "German",
+        "ita" => "Italian",
+        "jpn" => "Japanese",
+        "zho" | "chi" => "Chinese",
+        "kor" => "Korean",
+        "por" => "Portuguese",
+        "pol" => "Polish",
+        "ces" | "cze" => "Czech",
+        "hun" => "Hungarian",
+        "nld" | "dut" => "Dutch",
+        "ara" => "Arabic",
+        "hin" => "Hindi",
+        "tur" => "Turkish",
+        "tha" => "Thai",
+        "swe" => "Swedish",
+        "nor" => "Norwegian",
+        "dan" => "Danish",
+        "fin" => "Finnish",
+        "heb" => "Hebrew",
+        "rus" => "Russian",
+        "ell" | "gre" => "Greek",
+        "vie" => "Vietnamese",
+        "ind" => "Indonesian",
+        "msa" | "may" => "Malay",
+        "ukr" => "Ukrainian",
+        "ron" | "rum" => "Romanian",
+        "bul" => "Bulgarian",
+        "hrv" => "Croatian",
+        "srp" => "Serbian",
+        "slk" | "slo" => "Slovak",
+        "slv" => "Slovenian",
+        "est" => "Estonian",
+        "lav" => "Latvian",
+        "lit" => "Lithuanian",
+        "isl" | "ice" => "Icelandic",
+        "eus" | "baq" => "Basque",
+        "cat" => "Catalan",
+        "glg" => "Galician",
+        _ => "",
+    }
+    .to_string()
+}
+
+/// Map BD coding_type byte → codec name. Returns empty for unknown
+/// bytes (the table covers everything the spec defines, but unknown
+/// values are still possible on malformed discs).
+pub(crate) fn codec_name(coding_type: u8) -> &'static str {
+    match coding_type {
+        0x02 => "MPEG-2",
+        0x1B => "H.264",
+        0x24 => "HEVC",
+        0x80 => "LPCM",
+        0x81 => "AC-3",
+        0x82 => "DTS",
+        0x83 => "TrueHD",
+        0x84 => "AC-3+",
+        0x85 => "DTS-HD",
+        0x86 => "DTS-HD MA",
+        0x90 => "PG",
+        0x91 => "IG",
+        0xA1 => "AC-3+ Secondary",
+        0xA2 => "DTS-HD Secondary",
+        _ => "",
+    }
+}
+
+/// Build the final `codec_hint`. For audio streams, optionally
+/// append " <channels>" and/or " <rate>" suffixes. Sample rate is
+/// only spelled out for non-48k (the universal default).
+fn build_codec_hint(label_type: StreamLabelType, entry: &crate::mpls::StreamEntry) -> String {
+    let base = codec_name(entry.coding_type);
+    if base.is_empty() {
+        return String::new();
+    }
+
+    if label_type != StreamLabelType::Audio {
+        return base.to_string();
+    }
+
+    let mut out = base.to_string();
+
+    let channels = match entry.audio_format {
+        1 => Some("mono"),
+        3 => Some("2.0"),
+        6 => Some("5.1"),
+        12 => Some("7.1"),
+        _ => None,
+    };
+    if let Some(ch) = channels {
+        out.push(' ');
+        out.push_str(ch);
+    }
+
+    // 1 = 48 kHz (universal default, omit). Only call out higher rates.
+    let rate = match entry.audio_rate {
+        4 => Some("96kHz"),
+        5 => Some("192kHz"),
+        _ => None,
+    };
+    if let Some(r) = rate {
+        out.push(' ');
+        out.push_str(r);
+    }
+
+    out
+}
+
+/// Dedup-tag for the label type. `u8` instead of `StreamLabelType`
+/// itself because the enum does not derive `Hash` / `Eq`-by-discriminant
+/// in a way that we want to couple to (and `==` works fine for the
+/// linear `Vec::contains` lookup we do).
+fn type_tag(t: StreamLabelType) -> u8 {
+    match t {
+        StreamLabelType::Audio => 1,
+        StreamLabelType::Subtitle => 2,
+    }
+}
+
+// ── Tests ────────────────────────────────────────────────────────────
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::mpls::{Playlist, StreamEntry};
+
+    fn audio_entry(pid: u16, coding: u8, fmt: u8, rate: u8, lang: &str) -> StreamEntry {
+        StreamEntry {
+            stream_type: 2,
+            pid,
+            coding_type: coding,
+            video_format: 0,
+            video_rate: 0,
+            audio_format: fmt,
+            audio_rate: rate,
+            language: lang.to_string(),
+            dynamic_range: 0,
+            color_space: 0,
+            secondary: false,
+        }
+    }
+
+    fn pg_entry(pid: u16, lang: &str) -> StreamEntry {
+        StreamEntry {
+            stream_type: 3,
+            pid,
+            coding_type: 0x90,
+            video_format: 0,
+            video_rate: 0,
+            audio_format: 0,
+            audio_rate: 0,
+            language: lang.to_string(),
+            dynamic_range: 0,
+            color_space: 0,
+            secondary: false,
+        }
+    }
+
+    fn playlist_with(streams: Vec<StreamEntry>) -> Playlist {
+        Playlist {
+            version: "0200".to_string(),
+            play_items: Vec::new(),
+            streams,
+            marks: Vec::new(),
+        }
+    }
+
+    /// Drive the same conversion logic that `parse()` runs on real
+    /// disc data, but starting from already-parsed Playlists so we
+    /// don't have to synthesize valid MPLS bytes.
+    fn labels_from_playlists(playlists: &[Playlist]) -> Vec<StreamLabel> {
+        let mut labels: Vec<StreamLabel> = Vec::new();
+        let mut seen: Vec<(u8, String, String, u16)> = Vec::new();
+
+        for playlist in playlists {
+            let mut audio_idx: u16 = 0;
+            let mut sub_idx: u16 = 0;
+
+            for entry in &playlist.streams {
+                let label_type = match entry.stream_type {
+                    2 | 5 => StreamLabelType::Audio,
+                    3 => StreamLabelType::Subtitle,
+                    _ => continue,
+                };
+                let stream_number = match label_type {
+                    StreamLabelType::Audio => {
+                        audio_idx += 1;
+                        audio_idx
+                    }
+                    StreamLabelType::Subtitle => {
+                        sub_idx += 1;
+                        sub_idx
+                    }
+                };
+                let language = normalize_language(&entry.language);
+                let name = language_display_name(&language);
+                let codec_hint = build_codec_hint(label_type, entry);
+                let key = (
+                    type_tag(label_type),
+                    language.clone(),
+                    codec_hint.clone(),
+                    entry.pid,
+                );
+                if seen.contains(&key) {
+                    continue;
+                }
+                seen.push(key);
+                labels.push(StreamLabel {
+                    stream_number,
+                    stream_type: label_type,
+                    language,
+                    name,
+                    purpose: LabelPurpose::Normal,
+                    qualifier: LabelQualifier::None,
+                    codec_hint,
+                    variant: String::new(),
+                });
+            }
+        }
+        labels
+    }
+
+    #[test]
+    fn mpls_audio_streams_become_labels() {
+        // Two audio streams: English TrueHD 7.1 48k, French AC-3 5.1 48k.
+        let pl = playlist_with(vec![
+            audio_entry(0x1100, 0x83, 12, 1, "eng"),
+            audio_entry(0x1101, 0x81, 6, 1, "fra"),
+        ]);
+        let labels = labels_from_playlists(&[pl]);
+        assert_eq!(labels.len(), 2);
+
+        // English TrueHD 7.1
+        let a = &labels[0];
+        assert_eq!(a.stream_type, StreamLabelType::Audio);
+        assert_eq!(a.stream_number, 1);
+        assert_eq!(a.language, "eng");
+        assert_eq!(a.name, "English");
+        assert_eq!(a.codec_hint, "TrueHD 7.1");
+        assert_eq!(a.purpose, LabelPurpose::Normal);
+        assert_eq!(a.qualifier, LabelQualifier::None);
+        assert_eq!(a.variant, "");
+
+        // French AC-3 5.1
+        let b = &labels[1];
+        assert_eq!(b.stream_type, StreamLabelType::Audio);
+        assert_eq!(b.stream_number, 2);
+        assert_eq!(b.language, "fra");
+        assert_eq!(b.name, "French");
+        assert_eq!(b.codec_hint, "AC-3 5.1");
+    }
+
+    #[test]
+    fn mpls_pg_streams_become_subtitle_labels() {
+        let pl = playlist_with(vec![
+            pg_entry(0x1200, "eng"),
+            pg_entry(0x1201, "spa"),
+            pg_entry(0x1202, "fra"),
+        ]);
+        let labels = labels_from_playlists(&[pl]);
+        assert_eq!(labels.len(), 3);
+        for label in &labels {
+            assert_eq!(label.stream_type, StreamLabelType::Subtitle);
+            assert_eq!(label.codec_hint, "PG");
+        }
+        assert_eq!(labels[0].stream_number, 1);
+        assert_eq!(labels[0].language, "eng");
+        assert_eq!(labels[0].name, "English");
+        assert_eq!(labels[1].stream_number, 2);
+        assert_eq!(labels[1].language, "spa");
+        assert_eq!(labels[1].name, "Spanish");
+        assert_eq!(labels[2].stream_number, 3);
+        assert_eq!(labels[2].language, "fra");
+    }
+
+    #[test]
+    fn dedup_streams_across_playlists() {
+        // Two playlists, same English TrueHD 7.1 PID 0x1100 in both.
+        // Expect one Audio label, not two.
+        let pl1 = playlist_with(vec![
+            audio_entry(0x1100, 0x83, 12, 1, "eng"),
+            audio_entry(0x1101, 0x81, 6, 1, "fra"),
+        ]);
+        let pl2 = playlist_with(vec![
+            audio_entry(0x1100, 0x83, 12, 1, "eng"), // duplicate
+            audio_entry(0x1102, 0x82, 6, 1, "deu"),  // new
+        ]);
+        let labels = labels_from_playlists(&[pl1, pl2]);
+        // Expected: eng@0x1100, fra@0x1101, deu@0x1102 — three uniques.
+        assert_eq!(labels.len(), 3);
+        // PID isn't stored on StreamLabel, so assert on the surviving
+        // language set instead.
+        let mut langs: Vec<String> = labels.iter().map(|l| l.language.clone()).collect();
+        langs.sort();
+        assert_eq!(langs, vec!["deu", "eng", "fra"]);
+    }
+
+    #[test]
+    fn coding_type_to_codec_hint_table() {
+        // Spot-check every entry in the spec table. Audio entries
+        // come back bare (no channels/rate set) so codec_hint is the
+        // codec name alone.
+        let cases: &[(u8, &str)] = &[
+            (0x02, "MPEG-2"),
+            (0x1B, "H.264"),
+            (0x24, "HEVC"),
+            (0x80, "LPCM"),
+            (0x81, "AC-3"),
+            (0x82, "DTS"),
+            (0x83, "TrueHD"),
+            (0x84, "AC-3+"),
+            (0x85, "DTS-HD"),
+            (0x86, "DTS-HD MA"),
+            (0x90, "PG"),
+            (0x91, "IG"),
+            (0xA1, "AC-3+ Secondary"),
+            (0xA2, "DTS-HD Secondary"),
+        ];
+        for (ct, expected) in cases {
+            assert_eq!(
+                codec_name(*ct),
+                *expected,
+                "coding_type 0x{:02X} should map to {}",
+                ct,
+                expected
+            );
+        }
+        // Unknown bytes return empty.
+        assert_eq!(codec_name(0x00), "");
+        assert_eq!(codec_name(0xFF), "");
+    }
+
+    #[test]
+    fn audio_format_appends_channel_layout() {
+        let mono = audio_entry(1, 0x83, 1, 1, "eng");
+        let stereo = audio_entry(2, 0x83, 3, 1, "eng");
+        let surround_51 = audio_entry(3, 0x83, 6, 1, "eng");
+        let surround_71 = audio_entry(4, 0x83, 12, 1, "eng");
+        let unknown = audio_entry(5, 0x83, 0, 1, "eng");
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &mono),
+            "TrueHD mono"
+        );
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &stereo),
+            "TrueHD 2.0"
+        );
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &surround_51),
+            "TrueHD 5.1"
+        );
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &surround_71),
+            "TrueHD 7.1"
+        );
+        assert_eq!(build_codec_hint(StreamLabelType::Audio, &unknown), "TrueHD");
+    }
+
+    #[test]
+    fn audio_rate_only_shows_above_48k() {
+        // 48 kHz (rate=1) is the universal default → not surfaced.
+        let r48 = audio_entry(1, 0x83, 6, 1, "eng");
+        // 96 kHz (rate=4) → surfaced.
+        let r96 = audio_entry(2, 0x83, 6, 4, "eng");
+        // 192 kHz (rate=5) → surfaced.
+        let r192 = audio_entry(3, 0x83, 6, 5, "eng");
+        assert_eq!(build_codec_hint(StreamLabelType::Audio, &r48), "TrueHD 5.1");
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &r96),
+            "TrueHD 5.1 96kHz"
+        );
+        assert_eq!(
+            build_codec_hint(StreamLabelType::Audio, &r192),
+            "TrueHD 5.1 192kHz"
+        );
+    }
+
+    #[test]
+    fn unknown_iso_code_passes_through_without_display_name() {
+        // Made-up code: keep the raw lowercase code as `language`,
+        // but `name` is empty because we don't know it.
+        let pl = playlist_with(vec![audio_entry(0x1100, 0x83, 6, 1, "xyz")]);
+        let labels = labels_from_playlists(&[pl]);
+        assert_eq!(labels.len(), 1);
+        assert_eq!(labels[0].language, "xyz");
+        assert_eq!(labels[0].name, "");
+    }
+
+    #[test]
+    fn ig_and_dv_streams_are_skipped() {
+        // stream_type 4 = IG, 7 = DV EL — both must not surface.
+        let mut ig = pg_entry(0x1400, "eng");
+        ig.stream_type = 4;
+        let mut dv = audio_entry(0x1011, 0x24, 0, 0, "");
+        dv.stream_type = 7;
+        let pl = playlist_with(vec![ig, dv]);
+        let labels = labels_from_playlists(&[pl]);
+        assert!(labels.is_empty());
+    }
+
+    #[test]
+    fn secondary_audio_becomes_audio_label() {
+        // stream_type 5 = secondary audio. The conversion should
+        // still produce an Audio label (the registry's apply path
+        // can ignore secondary if it wants — this module just
+        // surfaces what's there).
+        let mut sec = audio_entry(0x1A00, 0x83, 3, 1, "eng");
+        sec.stream_type = 5;
+        sec.secondary = true;
+        let pl = playlist_with(vec![sec]);
+        let labels = labels_from_playlists(&[pl]);
+        assert_eq!(labels.len(), 1);
+        assert_eq!(labels[0].stream_type, StreamLabelType::Audio);
+        assert_eq!(labels[0].codec_hint, "TrueHD 2.0");
+    }
+}

src/labels/paramount.rs

@@ -12,15 +12,15 @@
 //!   sub_com1_idx="23,24,25" />
 //! ```
 
-use super::{LabelPurpose, LabelQualifier, StreamLabel, StreamLabelType};
-use crate::sector::SectorReader;
+use super::{LabelPurpose, LabelQualifier, ParseResult, StreamLabel, StreamLabelType, xml};
+use crate::sector::SectorSource;
 use crate::udf::UdfFs;
 
 pub fn detect(udf: &UdfFs) -> bool {
     super::jar_file_exists(udf, "playlists.xml")
 }
 
-pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
     let data = super::read_jar_file(reader, udf, "playlists.xml")?;
     let text = std::str::from_utf8(&data).ok()?;
 
@@ -30,8 +30,8 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     let mut labels = Vec::new();
 
     // Parse audio streams
-    if let Some(aud) = extract_attr(&feature, "aud") {
-        let com_idx = extract_attr(&feature, "aud_com1_idx").and_then(|s| s.parse::<usize>().ok());
+    if let Some(aud) = xml::attr(&feature, "aud") {
+        let com_idx = xml::attr(&feature, "aud_com1_idx").and_then(|s| s.parse::<usize>().ok());
 
         for (i, lang) in aud.split(',').enumerate() {
             let lang = lang.trim();
@@ -57,12 +57,12 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     }
 
     // Parse subtitle streams
-    if let Some(sub) = extract_attr(&feature, "sub") {
-        let forced: Vec<bool> = extract_attr(&feature, "forced_sub")
+    if let Some(sub) = xml::attr(&feature, "sub") {
+        let forced: Vec<bool> = xml::attr(&feature, "forced_sub")
             .map(|s| s.split(',').map(|f| f.trim() == "1").collect())
             .unwrap_or_default();
 
-        let com_indices: Vec<usize> = extract_attr(&feature, "sub_com1_idx")
+        let com_indices: Vec<usize> = xml::attr(&feature, "sub_com1_idx")
             .map(|s| s.split(',').filter_map(|i| i.trim().parse().ok()).collect())
             .unwrap_or_default();
 
@@ -100,32 +100,29 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     if labels.is_empty() {
         return None;
     }
-    Some(labels)
+    // High confidence: paramount's playlists.xml is fully structured
+    // and we extract every documented field.
+    Some(ParseResult::high(labels))
 }
 
 /// Find the feature playlist element (the one with the most audio tracks).
-fn find_feature_playlist(xml: &str) -> Option<String> {
+fn find_feature_playlist(text: &str) -> Option<String> {
     let mut best: Option<String> = None;
     let mut best_aud_count = 0;
+    let mut from = 0;
 
-    let mut pos = 0;
-    while let Some(start) = xml[pos..].find("<playlist ") {
-        let abs_start = pos + start;
-        let end = match xml[abs_start..].find("/>") {
-            Some(p) => abs_start + p + 2,
-            None => break,
-        };
-        let element = &xml[abs_start..end];
+    while let Some((start, end)) = xml::find_element(text, "playlist", from) {
+        let element = &text[start..end];
 
-        // Prefer name="Feature" explicitly
-        if let Some(name) = extract_attr(element, "name") {
+        // Prefer name="Feature" explicitly.
+        if let Some(name) = xml::attr(element, "name") {
             if name.eq_ignore_ascii_case("Feature") {
                 return Some(element.to_string());
             }
         }
 
-        // Otherwise pick the one with the most audio streams
-        if let Some(aud) = extract_attr(element, "aud") {
+        // Otherwise pick the one with the most audio streams.
+        if let Some(aud) = xml::attr(element, "aud") {
             let count = aud.split(',').count();
             if count > best_aud_count {
                 best_aud_count = count;
@@ -133,15 +130,7 @@ fn find_feature_playlist(xml: &str) -> Option<String> {
             }
         }
 
-        pos = end;
+        from = end;
     }
     best
 }
-
-/// Extract an XML attribute value from an element string.
-fn extract_attr(element: &str, name: &str) -> Option<String> {
-    let needle = format!("{name}=\"");
-    let start = element.find(&needle)? + needle.len();
-    let end = element[start..].find('"')? + start;
-    Some(element[start..end].to_string())
-}

src/labels/pixelogic.rs

@@ -5,9 +5,13 @@
 //!
 //! Token format: `{lang}_{codec?}_{purpose?}_{region?}_`
 
-use super::{LabelPurpose, LabelQualifier, StreamLabel, StreamLabelType, vocab};
-use crate::sector::SectorReader;
+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"];
@@ -20,9 +24,18 @@ pub fn detect(udf: &UdfFs) -> bool {
     super::jar_file_exists(udf, "bluray_project.bin")
 }
 
-pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLabel>> {
+pub fn parse(reader: &mut dyn SectorSource, udf: &UdfFs) -> Option<ParseResult> {
     let data = super::read_jar_file(reader, udf, "bluray_project.bin")?;
-    let strings = extract_strings(&data);
+    // 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 mut labels = Vec::new();
     let mut in_feature = false;
@@ -50,7 +63,7 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
             continue;
         }
 
-        if let Some(label) = parse_token(s) {
+        if let Some(label) = parse_token_inner(s, Some(&saw_unknown)) {
             match label.stream_type {
                 StreamLabelType::Audio => {
                     audio_num += 1;
@@ -73,10 +86,15 @@ pub fn parse(reader: &mut dyn SectorReader, udf: &UdfFs) -> Option<Vec<StreamLab
     if labels.is_empty() {
         return None;
     }
-    Some(labels)
+    let confidence = if saw_unknown.load(Ordering::Relaxed) {
+        Confidence::Medium
+    } else {
+        Confidence::High
+    };
+    Some(ParseResult { labels, confidence })
 }
 
-fn parse_token(s: &str) -> Option<StreamLabel> {
+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 {
@@ -127,7 +145,18 @@ fn parse_token(s: &str) -> Option<StreamLabel> {
         } else if part.starts_with("PGStream") {
             is_subtitle = true;
         } else {
-            return None;
+            // 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);
+            }
         }
     }
 
@@ -153,22 +182,72 @@ fn parse_token(s: &str) -> Option<StreamLabel> {
     })
 }
 
-fn extract_strings(data: &[u8]) -> Vec<String> {
-    let mut strings = Vec::new();
-    let mut current = String::new();
+// extract_strings removed — replaced by super::text::extract_ascii_strings(data, 4).
 
-    for &b in data {
-        if (0x20..0x7f).contains(&b) {
-            current.push(b as char);
-        } else {
-            if current.len() > 3 {
-                strings.push(current.clone());
-            }
-            current.clear();
-        }
+#[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);
     }
-    if current.len() > 3 {
-        strings.push(current);
+
+    #[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
     }
-    strings
 }

src/labels/text.rs

@@ -0,0 +1,89 @@
+//! Text-extraction helpers used by parsers that scan binary blobs for
+//! embedded label strings.
+//!
+//! Promoted from two near-duplicate implementations:
+//! - `pixelogic::extract_strings` (`bluray_project.bin`, min_len=4)
+//! - `dbp::extract_printable` (`.class` files in jars, min_len=5)
+//!
+//! Single implementation, threshold passed in. Callers that have a
+//! more structured parse path (e.g. `class_reader` for .class) should
+//! prefer that — this helper is for genuinely unstructured input.
+
+/// Walk `data`, emit every maximal run of printable-ASCII bytes
+/// (`0x20..=0x7E`) whose length is at least `min_len`.
+///
+/// Non-printable bytes (including `\t`, `\n`, NUL) terminate the
+/// current run. Output strings are guaranteed valid UTF-8 (they're
+/// pure 7-bit ASCII). Strings shorter than `min_len` are dropped.
+pub fn extract_ascii_strings(data: &[u8], min_len: usize) -> Vec<String> {
+    let mut out = Vec::new();
+    let mut current = String::new();
+    for &b in data {
+        if (0x20..=0x7E).contains(&b) {
+            current.push(b as char);
+        } else if current.len() >= min_len {
+            out.push(std::mem::take(&mut current));
+        } else {
+            current.clear();
+        }
+    }
+    if current.len() >= min_len {
+        out.push(current);
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn extracts_simple_runs() {
+        let got = extract_ascii_strings(b"hello\0world\0", 3);
+        assert_eq!(got, vec!["hello", "world"]);
+    }
+
+    #[test]
+    fn applies_minimum_length() {
+        let got = extract_ascii_strings(b"hi\0ok\0longer\0", 5);
+        assert_eq!(got, vec!["longer"]);
+    }
+
+    #[test]
+    fn treats_tab_and_newline_as_separators() {
+        // \t (0x09) and \n (0x0A) are below 0x20, so they break runs.
+        let got = extract_ascii_strings(b"alpha\tbeta\ngamma", 3);
+        assert_eq!(got, vec!["alpha", "beta", "gamma"]);
+    }
+
+    #[test]
+    fn handles_trailing_run_without_terminator() {
+        // Run at the very end of the buffer should still be emitted.
+        let got = extract_ascii_strings(b"prefix\0tail", 3);
+        assert_eq!(got, vec!["prefix", "tail"]);
+    }
+
+    #[test]
+    fn rejects_high_bit_bytes() {
+        // 0x80+ is non-printable per this helper's definition.
+        let mut buf = b"good".to_vec();
+        buf.push(0xC3);
+        buf.push(0xA9);
+        buf.extend_from_slice(b"more");
+        let got = extract_ascii_strings(&buf, 3);
+        assert_eq!(got, vec!["good", "more"]);
+    }
+
+    #[test]
+    fn empty_input_returns_empty() {
+        let got = extract_ascii_strings(&[], 1);
+        assert!(got.is_empty());
+    }
+
+    #[test]
+    fn min_len_zero_emits_singletons() {
+        // Pathological but well-defined.
+        let got = extract_ascii_strings(b"a\0b", 0);
+        assert_eq!(got, vec!["a", "b"]);
+    }
+}

src/labels/vocab.rs

@@ -1,19 +1,40 @@
-//! Shared label vocabulary — values we are 100% confident about.
+//! Shared label vocabulary — canonical mappings used by ≥1 label parser.
 //!
 //! Labels come from BD-J authoring tool files (bluray_project.bin,
-//! playlists.xml, menu_base.prop, etc.) — NOT from BD spec fields.
-//! This is NOT for MPLS/CLPI/STN data. Those follow the BD spec directly.
+//! playlists.xml, menu_base.prop, .class string pools, etc.) — NOT
+//! from BD spec fields. This module is the central, regression-tested
+//! source of truth for:
 //!
-//! Rules:
-//! - Only map values we are 100% certain about (published codec names).
-//! - Unknown codes (csp, eda, cf, etc.) pass through raw from disc.
-//! - The app/CLI handles display text, not the lib.
+//! - Codec brand name aliases (`MLP` → `TrueHD`).
+//! - English / multi-word language name → ISO 639-2 code.
+//! - 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`):
+//!
+//! 1. Only map values we are 100% certain about — published codec
+//!    names, well-known ISO 639-2 mappings, vendor-documented purpose
+//!    keywords.
+//! 2. Unknown codes / unrecognized phrases pass through raw or return
+//!    `None`. We never guess.
+//! 3. Matching is case-insensitive and word-boundary-aware where
+//!    relevant (so "Commenter" doesn't match "commentary"). Anchoring
+//!    on whole tokens is the responsibility of this module — callers
+//!    pass raw text, we handle it.
+//!
+//! This module is NOT for BD spec STN codec IDs; those decode in
+//! `mpls.rs` separately.
+
+use super::{LabelPurpose, LabelQualifier};
+
+// ── Codec aliases ────────────────────────────────────────────────────────────
 
 /// Map a codec identifier found in label data to its display name.
 ///
 /// These are well-known codec identifiers used across multiple BD-J
-/// authoring tools. NOT BD spec STN codec IDs — those are decoded
-/// separately in mpls.rs.
+/// authoring tools. Unknown codes pass through unchanged so callers
+/// can still surface vendor-specific tokens we haven't catalogued.
 pub fn codec(code: &str) -> &str {
     match code {
         "MLP" => "TrueHD",
@@ -25,3 +46,405 @@ pub fn codec(code: &str) -> &str {
         _ => code,
     }
 }
+
+// ── Language: English / multi-word names → ISO 639-2 ─────────────────────────
+
+/// Result of [`lang`] — ISO code + human-readable regional variant.
+///
+/// `code` is ISO 639-2 (always 3 lowercase letters).
+/// `variant` is the regional dialect as a human-readable English word
+/// (`"Brazilian"`, `"Castilian"`, `"Canadian"`, `"Simplified"`, ...)
+/// or `""` when the input names just a bare language without
+/// dialect ("Spanish" → variant=""). The variant matches the
+/// convention pixelogic / ctrm / criterion already use for their
+/// `StreamLabel::variant` field: a short display token the UI can
+/// surface verbatim.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct LangInfo {
+    pub code: &'static str,
+    pub variant: &'static str,
+}
+
+/// Map a free-form language label fragment to an ISO 639-2 code AND
+/// (where applicable) its regional variant.
+///
+/// Handles both bare English names ("English", "Spanish") and the
+/// multi-word vendor variants we've seen in the corpus ("Brazilian
+/// Portuguese", "Castilian Spanish", "Canadian French"). Match is
+/// case-insensitive; longer compound phrases win over their bare
+/// counterparts (so "Brazilian Portuguese" returns
+/// `LangInfo { code: "por", variant: "Brazilian" }`, not consumed by
+/// the bare "Portuguese" entry).
+///
+/// Bare-name matches return `variant: ""`.
+///
+/// Returns `None` for unrecognized input — callers decide whether to
+/// fall back to MPLS spec codes, pass through raw, or drop the stream.
+/// Never guesses.
+///
+/// Why the variant: the prior `lang() -> Option<&str>` shape silently
+/// dropped regional dialect info. "Brazilian Portuguese 5.1" became
+/// `language="por", variant=""` — UI displayed plain "Portuguese"
+/// even though the disc had explicitly labeled this stream Brazilian.
+/// Capturing the variant here parallels how pixelogic and ctrm
+/// populate `StreamLabel::variant` from their own region tables.
+pub fn lang(text: &str) -> Option<LangInfo> {
+    let lower = text.to_lowercase();
+    // Multi-word compounds first — longest-match wins.
+    for (needle, code, variant) in COMPOUND_LANGS {
+        if lower.contains(needle) {
+            return Some(LangInfo { code, variant });
+        }
+    }
+    // Bare names: word-boundary match (avoid "english" inside "englishman"
+    // or any other accidental substring).
+    for (needle, code) in BARE_LANGS {
+        if has_word(&lower, needle) {
+            return Some(LangInfo { code, variant: "" });
+        }
+    }
+    None
+}
+
+const COMPOUND_LANGS: &[(&str, &str, &str)] = &[
+    ("brazilian portuguese", "por", "Brazilian"),
+    ("euro portuguese", "por", "European"),
+    ("european portuguese", "por", "European"),
+    ("castilian spanish", "spa", "Castilian"),
+    ("latin american spanish", "spa", "Latin American"),
+    ("latin spanish", "spa", "Latin American"),
+    ("canadian french", "fra", "Canadian"),
+    ("parisian french", "fra", "Parisian"),
+    ("australian english", "eng", "Australian"),
+    ("austrailian english", "eng", "Australian"), // disc-corpus typo, keep matching
+    ("british english", "eng", "British"),
+    ("simplified chinese", "zho", "Simplified"),
+    ("traditional chinese", "zho", "Traditional"),
+    ("mandarin chinese", "zho", "Mandarin"),
+    ("cantonese chinese", "zho", "Cantonese"),
+];
+
+const BARE_LANGS: &[(&str, &str)] = &[
+    ("english", "eng"),
+    ("spanish", "spa"),
+    ("french", "fra"),
+    ("german", "deu"),
+    ("italian", "ita"),
+    ("japanese", "jpn"),
+    ("chinese", "zho"),
+    ("mandarin", "zho"),
+    ("cantonese", "zho"),
+    ("portuguese", "por"),
+    ("polish", "pol"),
+    ("czech", "ces"),
+    ("hungarian", "hun"),
+    ("dutch", "nld"),
+    ("korean", "kor"),
+    ("arabic", "ara"),
+    ("hindi", "hin"),
+    ("turkish", "tur"),
+    ("thai", "tha"),
+    ("swedish", "swe"),
+    ("norwegian", "nor"),
+    ("danish", "dan"),
+    ("finnish", "fin"),
+    ("hebrew", "heb"),
+    ("russian", "rus"),
+    ("greek", "ell"),
+    ("vietnamese", "vie"),
+    ("indonesian", "ind"),
+    ("malay", "msa"),
+    ("ukrainian", "ukr"),
+    ("romanian", "ron"),
+    ("bulgarian", "bul"),
+    ("croatian", "hrv"),
+    ("serbian", "srp"),
+    ("slovak", "slk"),
+    ("slovenian", "slv"),
+    ("estonian", "est"),
+    ("latvian", "lav"),
+    ("lithuanian", "lit"),
+    ("icelandic", "isl"),
+    ("basque", "eus"),
+    ("catalan", "cat"),
+    ("galician", "glg"),
+];
+
+// ── Purpose ──────────────────────────────────────────────────────────────────
+
+/// Classify a free-form English label string into a [`LabelPurpose`].
+///
+/// Recognized keywords (case-insensitive, word-boundary matched):
+/// - "commentary", "director's commentary" → `Commentary`
+/// - "descriptive", "description", "audio description", "described" → `Descriptive`
+/// - "score", "music only" → `Score`
+/// - "ime" (alternate music for closing themes etc.) → `Ime`
+/// - anything else → `Normal`
+///
+/// Word-boundary matching means "Commentary track" matches but
+/// "Commenter Pro audio" does not.
+pub fn purpose(text: &str) -> LabelPurpose {
+    let lower = text.to_lowercase();
+    // Multi-word compounds first — they're more specific.
+    if lower.contains("audio description") || lower.contains("descriptive service") {
+        return LabelPurpose::Descriptive;
+    }
+    if lower.contains("music only") {
+        return LabelPurpose::Score;
+    }
+    if has_word(&lower, "commentary") {
+        return LabelPurpose::Commentary;
+    }
+    if has_word(&lower, "descriptive")
+        || has_word(&lower, "description")
+        || has_word(&lower, "described")
+    {
+        return LabelPurpose::Descriptive;
+    }
+    if has_word(&lower, "score") {
+        return LabelPurpose::Score;
+    }
+    if has_word(&lower, "ime") {
+        return LabelPurpose::Ime;
+    }
+    LabelPurpose::Normal
+}
+
+// ── Qualifier ────────────────────────────────────────────────────────────────
+
+/// Classify a free-form English label string into a [`LabelQualifier`].
+///
+/// Recognized keywords (case-insensitive, word-boundary matched):
+/// - "sdh", "captions" → `Sdh`
+/// - "forced", "forced narrative" → `Forced`
+/// - "rnib", "descriptive service" → `DescriptiveService`
+/// - anything else → `None`
+///
+/// SDH (Subtitles for the Deaf and Hard of hearing) wins over Forced
+/// when both keywords are present, because an SDH track is its own
+/// stream regardless of whether the player flags it as "forced".
+pub fn qualifier(text: &str) -> LabelQualifier {
+    let lower = text.to_lowercase();
+    if has_word(&lower, "sdh") || has_word(&lower, "captions") {
+        return LabelQualifier::Sdh;
+    }
+    if lower.contains("descriptive service") || has_word(&lower, "rnib") {
+        return LabelQualifier::DescriptiveService;
+    }
+    if has_word(&lower, "forced") {
+        return LabelQualifier::Forced;
+    }
+    LabelQualifier::None
+}
+
+// ── Internal: word-boundary matching ────────────────────────────────────────
+
+/// True if `needle` appears in `haystack` surrounded by non-alphanumeric
+/// boundaries (or string ends). `haystack` is assumed lowercase already.
+///
+/// This is the load-bearing primitive for `lang` / `purpose` /
+/// `qualifier`: bare-token matchers MUST use it, otherwise we match
+/// "english" inside "englishman" and "sdh" inside "lambdash". The
+/// existing parsers used `.contains()` and got lucky on the corpus;
+/// vocab guarantees the boundary.
+fn has_word(haystack: &str, needle: &str) -> bool {
+    if needle.is_empty() {
+        return false;
+    }
+    let bytes = haystack.as_bytes();
+    let nb = needle.as_bytes();
+    let mut i = 0;
+    while i + nb.len() <= bytes.len() {
+        if &bytes[i..i + nb.len()] == nb {
+            let before = if i == 0 { None } else { Some(bytes[i - 1]) };
+            let after = bytes.get(i + nb.len()).copied();
+            let bound = |c: Option<u8>| match c {
+                None => true,
+                Some(b) => !b.is_ascii_alphanumeric(),
+            };
+            if bound(before) && bound(after) {
+                return true;
+            }
+        }
+        i += 1;
+    }
+    false
+}
+
+// ── Tests ────────────────────────────────────────────────────────────────────
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn codec_known_aliases() {
+        assert_eq!(codec("MLP"), "TrueHD");
+        assert_eq!(codec("AC3"), "Dolby Digital");
+        assert_eq!(codec("AC"), "Dolby Digital");
+        assert_eq!(codec("DDL"), "Dolby Digital Plus");
+        assert_eq!(codec("atmos"), "Dolby Atmos");
+    }
+
+    #[test]
+    fn codec_unknown_passes_through() {
+        assert_eq!(codec("FX9"), "FX9");
+        assert_eq!(codec(""), "");
+    }
+
+    fn li(code: &'static str, variant: &'static str) -> LangInfo {
+        LangInfo { code, variant }
+    }
+
+    #[test]
+    fn lang_bare_names_have_empty_variant() {
+        assert_eq!(lang("English"), Some(li("eng", "")));
+        assert_eq!(lang("english"), Some(li("eng", "")));
+        assert_eq!(lang("Spanish 5.1 Dolby Digital"), Some(li("spa", "")));
+        assert_eq!(lang("japanese"), Some(li("jpn", "")));
+        assert_eq!(lang("Italian"), Some(li("ita", "")));
+    }
+
+    #[test]
+    fn lang_compounds_carry_variant() {
+        assert_eq!(
+            lang("Brazilian Portuguese 5.1"),
+            Some(li("por", "Brazilian"))
+        );
+        assert_eq!(lang("Castilian Spanish"), Some(li("spa", "Castilian")));
+        assert_eq!(
+            lang("Canadian French Dolby Digital"),
+            Some(li("fra", "Canadian"))
+        );
+        assert_eq!(
+            lang("Latin American Spanish"),
+            Some(li("spa", "Latin American"))
+        );
+        assert_eq!(lang("Simplified Chinese"), Some(li("zho", "Simplified")));
+        assert_eq!(lang("British English"), Some(li("eng", "British")));
+    }
+
+    #[test]
+    fn lang_compounds_win_over_bare() {
+        // Brazilian Portuguese must map to (por, Brazilian) via the
+        // compound rule, not be intercepted by bare "portuguese"
+        // (which would yield (por, "") and lose the variant).
+        assert_eq!(lang("Brazilian Portuguese").unwrap().variant, "Brazilian");
+        assert_eq!(lang("Canadian French").unwrap().variant, "Canadian");
+    }
+
+    #[test]
+    fn lang_unknown_returns_none() {
+        assert_eq!(lang("Klingon Dolby Atmos"), None);
+        assert_eq!(lang(""), None);
+        assert_eq!(lang("eng"), None); // 3-letter codes are not English names
+    }
+
+    #[test]
+    fn lang_word_boundary_avoids_substring_false_positive() {
+        // No false positive — "engineering" must NOT match "english".
+        assert_eq!(lang("Audio Engineering Demo"), None);
+    }
+
+    #[test]
+    fn purpose_recognizes_commentary() {
+        assert_eq!(purpose("English Commentary"), LabelPurpose::Commentary);
+        assert_eq!(purpose("Director's Commentary"), LabelPurpose::Commentary);
+    }
+
+    #[test]
+    fn purpose_recognizes_descriptive() {
+        assert_eq!(
+            purpose("English Descriptive Audio"),
+            LabelPurpose::Descriptive
+        );
+        assert_eq!(purpose("Audio Description"), LabelPurpose::Descriptive);
+        assert_eq!(purpose("Described Video"), LabelPurpose::Descriptive);
+    }
+
+    #[test]
+    fn purpose_descriptive_service_routes_to_descriptive() {
+        // "Descriptive Service" is qualifier territory but the purpose
+        // implication is Descriptive — vocab::purpose treats it as such.
+        assert_eq!(
+            purpose("English Descriptive Service"),
+            LabelPurpose::Descriptive
+        );
+    }
+
+    #[test]
+    fn purpose_word_boundary_avoids_commenter_false_positive() {
+        // "Commenter Pro audio" does NOT match "commentary" — the
+        // existing dbp/ctrm hand-rolls would have. Vocab is stricter.
+        assert_eq!(purpose("Commenter Pro audio track"), LabelPurpose::Normal);
+    }
+
+    #[test]
+    fn purpose_recognizes_score() {
+        assert_eq!(purpose("Music Only"), LabelPurpose::Score);
+        assert_eq!(purpose("Isolated Score"), LabelPurpose::Score);
+    }
+
+    #[test]
+    fn purpose_unknown_is_normal() {
+        assert_eq!(purpose("English Dolby Atmos"), LabelPurpose::Normal);
+        assert_eq!(purpose(""), LabelPurpose::Normal);
+    }
+
+    #[test]
+    fn qualifier_recognizes_sdh() {
+        assert_eq!(qualifier("English SDH"), LabelQualifier::Sdh);
+        assert_eq!(qualifier("English Captions"), LabelQualifier::Sdh);
+    }
+
+    #[test]
+    fn qualifier_recognizes_forced() {
+        assert_eq!(qualifier("English Forced"), LabelQualifier::Forced);
+        assert_eq!(qualifier("Forced Narrative"), LabelQualifier::Forced);
+    }
+
+    #[test]
+    fn qualifier_recognizes_descriptive_service() {
+        assert_eq!(
+            qualifier("English RNIB"),
+            LabelQualifier::DescriptiveService
+        );
+        assert_eq!(
+            qualifier("English Descriptive Service"),
+            LabelQualifier::DescriptiveService
+        );
+    }
+
+    #[test]
+    fn qualifier_sdh_wins_over_forced_when_both_present() {
+        // SDH track is its own stream regardless of forced flag.
+        assert_eq!(qualifier("English Forced SDH"), LabelQualifier::Sdh);
+    }
+
+    #[test]
+    fn qualifier_unknown_is_none() {
+        assert_eq!(qualifier("English"), LabelQualifier::None);
+        assert_eq!(qualifier(""), LabelQualifier::None);
+    }
+
+    #[test]
+    fn has_word_basic() {
+        assert!(has_word("english forced", "english"));
+        assert!(has_word("english forced", "forced"));
+        assert!(has_word("english", "english"));
+    }
+
+    #[test]
+    fn has_word_rejects_substring() {
+        assert!(!has_word("engineering", "english"));
+        assert!(!has_word("englishman", "english"));
+        assert!(!has_word("aenglish", "english"));
+    }
+
+    #[test]
+    fn has_word_punctuation_boundary() {
+        // "(SDH)" is a valid boundary — parentheses count as non-alphanum.
+        assert!(has_word("english (sdh)", "sdh"));
+        assert!(has_word("commentary,extra,info", "commentary"));
+    }
+}

src/labels/xml.rs

@@ -0,0 +1,452 @@
+//! Tolerant XML scraping helpers — promoted from two near-duplicate
+//! hand-rolls in `paramount.rs` (attribute extraction) and `criterion.rs`
+//! (tag-text extraction).
+//!
+//! These are NOT a full XML parser. They handle the subset of XML the
+//! BD-J authoring tools we've seen actually emit: ASCII tag/attr
+//! names, no entity references inside label strings, optional XML
+//! namespaces. Hardening goals over the prior `find("<tag>")` /
+//! `find(r#"name=""#)` matchers:
+//!
+//! 1. **Case-insensitive** tag and attribute names — vendors casing
+//!    is inconsistent across authoring-tool revisions.
+//! 2. **Namespace-aware** — strip an optional `ns:` prefix so
+//!    `<ns:playlist>` and `<playlist>` both match.
+//! 3. **Whitespace-tolerant** — multiple/tab/newline characters
+//!    around `=` between attribute name and value; whitespace inside
+//!    the opening tag.
+//! 4. **Quote-style tolerant** — both `"value"` and `'value'`.
+//! 5. **Self-closing tag handling** — `<tag />` and `<tag/>` both
+//!    work; [`text`] returns `Some("")` for empty content.
+//!
+//! Out of scope (intentionally simple): XML entity decoding
+//! (`&amp;`, `&lt;`, etc.), CDATA sections, comments, processing
+//! instructions, DTD declarations. None of the BD-J authored disc
+//! data we've observed exercises any of those — labels are plain
+//! ASCII/Latin-1 in attribute values.
+
+/// Extract the value of attribute `name` from one XML element
+/// fragment (e.g. `<playlist name="Feature" id="00222" />`).
+///
+/// Returns the raw attribute text (no entity decoding) or `None` if
+/// the attribute isn't present. Empty string for `name=""` is
+/// represented as `Some("")`.
+pub fn attr(element: &str, name: &str) -> Option<String> {
+    let bytes = element.as_bytes();
+    let name_lower = name.to_ascii_lowercase();
+    let name_bytes = name_lower.as_bytes();
+    let mut i = 0;
+    while i + name_bytes.len() < bytes.len() {
+        // Find the next position where `name=` could start. We need
+        // a word boundary before the name (whitespace or `<` or `:`).
+        if i > 0 && is_name_char(bytes[i - 1]) {
+            i += 1;
+            continue;
+        }
+        if !slice_eq_ignore_case(&bytes[i..i + name_bytes.len()], name_bytes) {
+            i += 1;
+            continue;
+        }
+        let after_name = i + name_bytes.len();
+        // The character immediately after the name must not be a
+        // name-continuation (otherwise we matched a prefix like
+        // `lang_id` when looking for `lang`).
+        if after_name < bytes.len() && is_name_char(bytes[after_name]) {
+            i = after_name;
+            continue;
+        }
+        // Walk past whitespace, then `=`, then more whitespace, then
+        // the opening quote.
+        let mut j = after_name;
+        while j < bytes.len() && is_ws(bytes[j]) {
+            j += 1;
+        }
+        if j >= bytes.len() || bytes[j] != b'=' {
+            i = j.max(i + 1);
+            continue;
+        }
+        j += 1; // past '='
+        while j < bytes.len() && is_ws(bytes[j]) {
+            j += 1;
+        }
+        if j >= bytes.len() {
+            return None;
+        }
+        let quote = bytes[j];
+        if quote != b'"' && quote != b'\'' {
+            // Unquoted attribute values aren't part of well-formed
+            // XML (HTML5 allows them, XML doesn't). Skip.
+            i = j;
+            continue;
+        }
+        let value_start = j + 1;
+        let close = bytes[value_start..].iter().position(|&b| b == quote)?;
+        let value = &element[value_start..value_start + close];
+        return Some(value.to_string());
+    }
+    None
+}
+
+/// Extract the trimmed text content of the first occurrence of
+/// `<tag>...</tag>` in `xml`. Returns `None` if the tag isn't found
+/// or its opening tag is malformed.
+///
+/// Whitespace around the inner text is stripped. Self-closing
+/// `<tag />` yields `Some("")`. Nested same-name tags are NOT
+/// handled — the first close encountered wins (this matches the
+/// prior behavior in criterion.rs).
+pub fn text(xml: &str, tag: &str) -> Option<String> {
+    let (open_end, body_start) = find_open_tag(xml, tag, 0)?;
+    // Self-closing — already consumed in find_open_tag if `/>`.
+    if open_end == body_start {
+        // Means find_open_tag returned the same offset twice for
+        // self-closing form. (Not currently the case in our impl,
+        // but defensive.)
+        return Some(String::new());
+    }
+    // For self-closing tags, body_start is past `/>` and we have no
+    // content. Detect by checking the char at body_start - 1 was `/`.
+    if body_start >= 2 && &xml[body_start - 2..body_start] == "/>" {
+        return Some(String::new());
+    }
+    // Find the matching close tag. Case-insensitive + namespace-aware.
+    let close_start = find_close_tag(xml, tag, body_start)?;
+    Some(xml[body_start..close_start].trim().to_string())
+}
+
+/// Locate the next `<tag>` opening AND its closing `</tag>` in
+/// `xml`, starting at byte offset `from`. Returns `(element_start,
+/// element_end)` — `element_start` is the `<` of the opening tag,
+/// `element_end` is one past the `>` of the closing tag. Useful for
+/// iterating over repeated elements like `<playlist>` blocks in
+/// `paramount`.
+///
+/// Self-closing elements return the same offset for body_end as the
+/// element_end (i.e. `element_end - element_start` includes only the
+/// `<tag .../>` text).
+pub fn find_element(xml: &str, tag: &str, from: usize) -> Option<(usize, usize)> {
+    let bytes = xml.as_bytes();
+    let mut i = from;
+    while i < bytes.len() {
+        if bytes[i] != b'<' {
+            i += 1;
+            continue;
+        }
+        // Try matching tag name at i+1 (after `<`).
+        let after_lt = i + 1;
+        if !matches_tag_name_at(bytes, after_lt, tag) {
+            i += 1;
+            continue;
+        }
+        // Found an open tag at offset i. Walk to find the closing `>`
+        // of the open tag itself.
+        let mut j = after_lt;
+        // Skip past the tag name (and optional namespace prefix).
+        while j < bytes.len() && (is_name_char(bytes[j]) || bytes[j] == b':') {
+            j += 1;
+        }
+        // Walk attributes — track quoting state.
+        let mut self_closing = false;
+        while j < bytes.len() {
+            match bytes[j] {
+                b'>' => {
+                    j += 1;
+                    break;
+                }
+                b'/' if j + 1 < bytes.len() && bytes[j + 1] == b'>' => {
+                    self_closing = true;
+                    j += 2;
+                    break;
+                }
+                b'"' | b'\'' => {
+                    let q = bytes[j];
+                    j += 1;
+                    while j < bytes.len() && bytes[j] != q {
+                        j += 1;
+                    }
+                    if j < bytes.len() {
+                        j += 1;
+                    }
+                }
+                _ => j += 1,
+            }
+        }
+        if self_closing {
+            return Some((i, j));
+        }
+        // Find matching close. Doesn't handle nested same-name; OK
+        // for our authoring-tool subset.
+        let close_start = find_close_tag(xml, tag, j)?;
+        let close_end = find_byte(bytes, b'>', close_start)? + 1;
+        return Some((i, close_end));
+    }
+    None
+}
+
+// ── Internal helpers ───────────────────────────────────────────────────────
+
+/// True if `bytes[start..]` opens a tag named `tag`, allowing an
+/// optional `ns:` namespace prefix. Comparison is case-insensitive.
+/// The character after the tag name must not be a name-continuation
+/// (so `<player>` doesn't match `<play>`).
+fn matches_tag_name_at(bytes: &[u8], start: usize, tag: &str) -> bool {
+    let tag_lower = tag.to_ascii_lowercase();
+    let tag_bytes = tag_lower.as_bytes();
+    // Skip optional `prefix:` (one or more name chars + `:`).
+    let mut name_start = start;
+    let mut scan = start;
+    while scan < bytes.len() && is_name_char(bytes[scan]) {
+        scan += 1;
+    }
+    if scan < bytes.len() && bytes[scan] == b':' {
+        name_start = scan + 1;
+    }
+    if name_start + tag_bytes.len() > bytes.len() {
+        return false;
+    }
+    if !slice_eq_ignore_case(&bytes[name_start..name_start + tag_bytes.len()], tag_bytes) {
+        return false;
+    }
+    // Boundary: char after the tag name must be `>`, `/`, whitespace.
+    let after = name_start + tag_bytes.len();
+    if after >= bytes.len() {
+        return false;
+    }
+    matches!(bytes[after], b'>' | b'/' | b' ' | b'\t' | b'\n' | b'\r')
+}
+
+/// Find the offset of the next `</tag>` (or `</ns:tag>`) in `xml`
+/// starting at `from`. Case-insensitive; returns the offset of the
+/// `<`. None if not found.
+fn find_close_tag(xml: &str, tag: &str, from: usize) -> Option<usize> {
+    let bytes = xml.as_bytes();
+    let mut i = from;
+    while i + 2 < bytes.len() {
+        if bytes[i] == b'<' && bytes[i + 1] == b'/' {
+            // Check tag name (with optional namespace).
+            if matches_tag_name_at(bytes, i + 2, tag) {
+                return Some(i);
+            }
+        }
+        i += 1;
+    }
+    None
+}
+
+/// Find the open tag of `<tag>` in `xml` starting at `from`. Returns
+/// `(after_open_lt, after_open_gt)` — the offsets are: just past
+/// the `<` of the open tag, and just past the `>` of the open tag.
+fn find_open_tag(xml: &str, tag: &str, from: usize) -> Option<(usize, usize)> {
+    let bytes = xml.as_bytes();
+    let (elem_start, _) = find_element(xml, tag, from)?;
+    let after_lt = elem_start + 1;
+    // Find the `>` that ends the open tag (handling quoted attrs).
+    let mut j = after_lt;
+    while j < bytes.len() {
+        match bytes[j] {
+            b'>' => return Some((after_lt, j + 1)),
+            b'/' if j + 1 < bytes.len() && bytes[j + 1] == b'>' => {
+                return Some((after_lt, j + 2));
+            }
+            b'"' | b'\'' => {
+                let q = bytes[j];
+                j += 1;
+                while j < bytes.len() && bytes[j] != q {
+                    j += 1;
+                }
+                if j < bytes.len() {
+                    j += 1;
+                }
+            }
+            _ => j += 1,
+        }
+    }
+    None
+}
+
+fn find_byte(bytes: &[u8], target: u8, from: usize) -> Option<usize> {
+    bytes[from..]
+        .iter()
+        .position(|&b| b == target)
+        .map(|p| p + from)
+}
+
+/// True if `c` can be part of an XML name token (rough). We accept
+/// alphanumerics, `_`, `-`, `.`.
+fn is_name_char(c: u8) -> bool {
+    c.is_ascii_alphanumeric() || c == b'_' || c == b'-' || c == b'.'
+}
+
+fn is_ws(c: u8) -> bool {
+    matches!(c, b' ' | b'\t' | b'\n' | b'\r')
+}
+
+fn slice_eq_ignore_case(a: &[u8], b_lower: &[u8]) -> bool {
+    if a.len() != b_lower.len() {
+        return false;
+    }
+    a.iter()
+        .zip(b_lower.iter())
+        .all(|(&x, &y)| x.to_ascii_lowercase() == y)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn attr_basic() {
+        assert_eq!(
+            attr(r#"<playlist name="Feature" id="00222" />"#, "name"),
+            Some("Feature".into())
+        );
+        assert_eq!(
+            attr(r#"<playlist name="Feature" id="00222" />"#, "id"),
+            Some("00222".into())
+        );
+    }
+
+    #[test]
+    fn attr_case_insensitive_name() {
+        assert_eq!(
+            attr(r#"<playlist Name="Feature" />"#, "name"),
+            Some("Feature".into())
+        );
+        assert_eq!(
+            attr(r#"<playlist NAME="Feature" />"#, "Name"),
+            Some("Feature".into())
+        );
+    }
+
+    #[test]
+    fn attr_accepts_single_quotes() {
+        assert_eq!(
+            attr(r#"<playlist name='Feature' />"#, "name"),
+            Some("Feature".into())
+        );
+    }
+
+    #[test]
+    fn attr_whitespace_around_equals() {
+        assert_eq!(
+            attr(r#"<playlist name = "Feature" />"#, "name"),
+            Some("Feature".into())
+        );
+        assert_eq!(
+            attr("<playlist name\n=\n\"Feature\" />", "name"),
+            Some("Feature".into())
+        );
+    }
+
+    #[test]
+    fn attr_missing_returns_none() {
+        assert_eq!(attr(r#"<playlist name="X" />"#, "id"), None);
+        assert_eq!(attr("", "name"), None);
+    }
+
+    #[test]
+    fn attr_no_substring_false_positive() {
+        // Looking for "lang" should NOT match "lang_id" or
+        // "language" because of the name-char boundary check.
+        assert_eq!(attr(r#"<x lang_id="fra" language="eng" />"#, "lang"), None);
+    }
+
+    #[test]
+    fn attr_empty_value() {
+        assert_eq!(attr(r#"<x name="" id="1" />"#, "name"), Some("".into()));
+    }
+
+    #[test]
+    fn text_basic() {
+        assert_eq!(text("<x>hello</x>", "x"), Some("hello".into()));
+        assert_eq!(
+            text("<x>  hello world  </x>", "x"),
+            Some("hello world".into())
+        );
+    }
+
+    #[test]
+    fn text_case_insensitive_tag() {
+        assert_eq!(text("<X>foo</X>", "x"), Some("foo".into()));
+        assert_eq!(text("<Foo>bar</foo>", "foo"), Some("bar".into()));
+    }
+
+    #[test]
+    fn text_namespace_prefix() {
+        assert_eq!(text("<ns:tag>value</ns:tag>", "tag"), Some("value".into()));
+        assert_eq!(text("<foo:Bar>v</foo:Bar>", "bar"), Some("v".into()));
+    }
+
+    #[test]
+    fn text_self_closing() {
+        assert_eq!(text("<x/>", "x"), Some("".into()));
+        assert_eq!(text("<x />", "x"), Some("".into()));
+        assert_eq!(text("<x  attr=\"y\" />", "x"), Some("".into()));
+    }
+
+    #[test]
+    fn text_with_attrs() {
+        assert_eq!(
+            text(r#"<x id="1" name="y">hello</x>"#, "x"),
+            Some("hello".into())
+        );
+    }
+
+    #[test]
+    fn text_missing_close_returns_none() {
+        assert_eq!(text("<x>hello", "x"), None);
+    }
+
+    #[test]
+    fn text_skips_inner_tags_naively() {
+        // Limitation noted: nested same-name tags aren't handled.
+        // Different-name nesting works (we just return everything
+        // between the open and close).
+        assert_eq!(
+            text("<x><y>nested</y></x>", "x"),
+            Some("<y>nested</y>".into())
+        );
+    }
+
+    #[test]
+    fn find_element_basic() {
+        let xml = r#"<x />  <y attr="1">body</y>"#;
+        let (s, e) = find_element(xml, "y", 0).unwrap();
+        assert_eq!(&xml[s..e], r#"<y attr="1">body</y>"#);
+    }
+
+    #[test]
+    fn find_element_self_closing() {
+        let xml = r#"<x />"#;
+        let (s, e) = find_element(xml, "x", 0).unwrap();
+        assert_eq!(&xml[s..e], "<x />");
+    }
+
+    #[test]
+    fn find_element_handles_quoted_gt_in_attr() {
+        // A `>` inside a quoted attribute value should not terminate
+        // the open tag prematurely.
+        let xml = r#"<x attr="foo>bar">body</x>"#;
+        let (s, e) = find_element(xml, "x", 0).unwrap();
+        assert_eq!(&xml[s..e], r#"<x attr="foo>bar">body</x>"#);
+    }
+
+    #[test]
+    fn find_element_iteration() {
+        let xml = "<p>a</p><p>b</p><p>c</p>";
+        let mut positions = Vec::new();
+        let mut from = 0;
+        while let Some((s, e)) = find_element(xml, "p", from) {
+            positions.push(&xml[s..e]);
+            from = e;
+        }
+        assert_eq!(positions, vec!["<p>a</p>", "<p>b</p>", "<p>c</p>"]);
+    }
+
+    #[test]
+    fn find_element_with_namespace() {
+        let xml = r#"<root><ns:item id="1" /></root>"#;
+        let (s, e) = find_element(xml, "item", 0).unwrap();
+        assert_eq!(&xml[s..e], r#"<ns:item id="1" />"#);
+    }
+}

src/lib.rs

@@ -82,7 +82,7 @@ pub mod event;
 pub mod halt;
 pub(crate) mod identity;
 pub(crate) mod ifo;
-pub(crate) mod io;
+pub mod io;
 pub mod keydb;
 pub mod labels;
 pub(crate) mod mpls;
@@ -128,16 +128,19 @@ pub use halt::Halt;
 
 // Generic bounded producer/consumer primitive used by sweep, patch, and
 // mux to overlap reads with writes via a dedicated consumer thread.
-// `Pipeline::spawn(depth, sink)` spawns the consumer; `pipe.send(item)`
+// `Pipeline::spawn(name, depth, sink)` spawns a named consumer; `pipe.send(item)`
 // pushes one item with back-pressure; `pipe.finish()` joins the
 // consumer and surfaces its `close()` output. Callers implement `Sink`
 // to define per-item behaviour and end-of-stream finalisation.
 //
-// `DEFAULT_PIPELINE_DEPTH` (=4) is the depth sweep + mux use; patch
-// uses `WRITE_THROUGH_DEPTH` (=1) so each read fully drains before the
-// next can enqueue. Returning `Flow::Stop` from `apply` ends the
-// consumer cleanly (still calls `close()`).
-pub use io::pipeline::{DEFAULT_PIPELINE_DEPTH, Flow, Pipeline, Sink, WRITE_THROUGH_DEPTH};
+// `DEFAULT_PIPELINE_DEPTH` (=4) is for callers without specific needs;
+// most should use READ_PIPELINE_DEPTH or WRITE_PIPELINE_DEPTH instead.
+// Patch uses `WRITE_THROUGH_DEPTH` (=1). Returning `Flow::Stop` from
+// `apply` ends the consumer cleanly (still calls `close()`).
+pub use io::pipeline::{
+    DEFAULT_PIPELINE_DEPTH, Flow, Pipeline, READ_PIPELINE_DEPTH, Sink, WRITE_PIPELINE_DEPTH,
+    WRITE_THROUGH_DEPTH,
+};
 
 // ─── Drive events (low-level callbacks) ─────────────────────────────────────
 pub use event::{Event, EventKind};
@@ -162,8 +165,8 @@ pub use decrypt::{DecryptKeys, decrypt_sectors};
 // structured representation; never compare against display strings.
 // Note: `disc::Stream` here is the codec enum (audio / video / sub kind)
 // — not the `pes::Stream` trait re-exported below as `PesStream`. Two
-// different concepts, the same short name; both stay because both are
-// load-bearing in their respective domains.
+// different concepts, the same short name; the trait gets the `Pes`
+// prefix at the crate root to keep both addressable.
 pub use disc::{
     AacsState, AudioChannels, AudioStream, Clip, Codec, ColorSpace, ContentFormat, DamageSeverity,
     Disc, DiscFormat, DiscId, DiscTitle, Extent, FrameRate, HdrFormat, KeySource, LabelPurpose,
@@ -176,7 +179,7 @@ pub use disc::{
 // All stream types implement `pes::Stream` — read PES frames from a source,
 // write PES frames to a sink. Pick the right type at construction:
 //
-// - `DiscStream` — physical drive or ISO (any `SectorReader`). Always read.
+// - `DiscStream` — physical drive or ISO (any `SectorSource`). Read-only.
 // - `MkvStream`  — Matroska container. Read on `open()`, write on `create()`.
 // - `M2tsStream` — Blu-ray Transport Stream. Read on `open()`, write on `create()`.
 // - `NetworkStream` — TCP. Read on `listen()`, write on `connect()`.
@@ -186,14 +189,11 @@ pub use disc::{
 // Most consumers use the URL resolvers (`input()` / `output()`) which pick
 // the right type from a scheme:// URL. Direct construction is for callers
 // that need to wire custom readers (e.g. autorip's drive-session reuse).
-// 0.18 trait split: `FrameSource` (read-only) and `FrameSink` (write-only)
-// supersede the unified `pes::Stream`. The old `Stream` re-export below
-// stays available for the deprecation window — re-exported as
-// `PesStream` to disambiguate from `disc::Stream` (the codec-kind enum
-// re-exported above), which would otherwise collide at the crate root.
-#[allow(deprecated)]
+// The trait is re-exported as `PesStream` here to disambiguate from
+// `disc::Stream` (the codec-kind enum re-exported above), which would
+// otherwise collide at the crate root.
+pub use pes::PesFrame;
 pub use pes::Stream as PesStream;
-pub use pes::{FrameSink, FrameSource, PesFrame};
 
 pub use mux::DiscStream;
 pub use mux::M2tsStream;
@@ -206,18 +206,14 @@ pub use mux::{InputOptions, StreamUrl, input, output, parse_url};
 // ─── Lower-level surfaces ───────────────────────────────────────────────────
 //
 // `ScsiTransport` is the platform-abstraction trait Drive uses; expose for
-// out-of-tree platform backends. `SectorSource` / `SectorSink` are the 0.18
+// out-of-tree platform backends. `SectorSource` / `SectorSink` are the
 // direction-typed read/write traits; `FileSectorSource` and `FileSectorSink`
 // are the ISO-on-disk implementations. [`DecryptingSectorSource`] is the
 // single decrypt-on-read decorator (AACS / CSS / none) — wrap any
-// `SectorSource` to get plaintext sectors out. The legacy `SectorReader` /
-// `FileSectorReader` names stay re-exported through the 0.18 migration
-// window so existing call sites compile unchanged; a blanket impl makes
-// every `SectorReader` automatically usable as a `SectorSource`.
+// `SectorSource` to get plaintext sectors out.
 pub use scsi::{DriveInfo, ScsiSense, ScsiTransport, drive_has_disc, list_drives};
 pub use sector::{
-    DecryptingSectorSource, FileSectorReader, FileSectorSink, FileSectorSource, SectorReader,
-    SectorSink, SectorSource,
+    DecryptingSectorSource, FileSectorSink, FileSectorSource, SectorSink, SectorSource,
 };
 pub use speed::DriveSpeed;
 pub use udf::{UdfFs, read_filesystem};

src/mux/disc.rs

@@ -1,6 +1,6 @@
 //! DiscStream — read any disc (physical drive or ISO file) → PES frames.
 //!
-//! One stream type for all disc sources. The source is a SectorReader —
+//! One stream type for all disc sources. The source is a SectorSource —
 //! Drive (hardware) or IsoSectorReader (file). DiscStream doesn't care.
 //!
 //! Read-only. For disc→ISO (raw sector copy), use `Disc::copy()`.
@@ -9,7 +9,7 @@ use crate::disc::{Disc, DiscTitle, Extent};
 use crate::drive::extract_scsi_context;
 use crate::event::{BatchSizeReason, Event, EventKind};
 use crate::halt::Halt;
-use crate::sector::{DecryptingSectorSource, SectorReader, SectorSource};
+use crate::sector::{DecryptingSectorSource, SectorSource};
 use std::io;
 use std::sync::Arc;
 use std::sync::atomic::AtomicBool;
@@ -97,7 +97,7 @@ impl AdaptiveBatch {
 
 /// Disc stream. Reads sectors from any source → PES frames.
 ///
-/// Sources: physical drive, ISO file, or any SectorReader.
+/// Sources: physical drive, ISO file, or any SectorSource.
 /// Decrypt, demux, and codec parsing happen internally.
 pub struct DiscStream {
     /// Underlying sector source wrapped in the 0.18
@@ -105,7 +105,7 @@ pub struct DiscStream {
     /// call yields plaintext, so `fill_extents` no longer needs an
     /// inline `decrypt::decrypt_sectors` step. `DecryptKeys::None`
     /// (raw / unencrypted disc) makes the decorator a pass-through.
-    reader: DecryptingSectorSource<Box<dyn SectorReader>>,
+    reader: DecryptingSectorSource<Box<dyn SectorSource>>,
     title: DiscTitle,
     disc: Option<Disc>,
     /// Mirror of the keys handed in at construction. The decorator
@@ -160,11 +160,11 @@ pub struct DiscStream {
 impl DiscStream {
     /// Create a disc stream from any sector reader.
     ///
-    /// Works with physical drives and ISO files — both implement SectorReader.
+    /// Works with physical drives and ISO files — both implement SectorSource.
     /// The caller opens the source, scans for titles/keys, and passes them in.
     /// The stream handles demuxing, decryption, and codec parsing internally.
     pub fn new(
-        reader: Box<dyn SectorReader>,
+        reader: Box<dyn SectorSource>,
         title: DiscTitle,
         decrypt_keys: crate::decrypt::DecryptKeys,
         batch_sectors: u16,
@@ -173,6 +173,13 @@ impl DiscStream {
         let extents = title.extents.clone();
         let bytes_total_extents: u64 = extents.iter().map(|e| e.sector_count as u64 * 2048).sum();
 
+        // Debug log reader type at construction — critical for diagnosing mux reading from drive instead of ISO
+        tracing::debug!(
+            target: "mux",
+            "DiscStream constructed with reader type: {}",
+            std::any::type_name::<dyn SectorSource>()
+        );
+
         let mut pids = Vec::new();
         let mut parsers = Vec::new();
         let mut pid_to_track = Vec::new();
@@ -315,10 +322,19 @@ impl DiscStream {
         // this loop can spend minutes shrinking and skipping sectors; without
         // the check, Stop wouldn't take effect until the outer PES read() loop
         // finally emits a frame, which may never happen.
+
+        let start_time = std::time::Instant::now();
+
         loop {
             if self.is_halted() {
                 return Err(crate::error::Error::Halted.into());
             }
+
+            // Debug: log slow reads during mux — helps diagnose stalls
+            if cfg!(debug_assertions) && start_time.elapsed().as_secs() > 5 {
+                tracing::debug!(target: "mux", "fill_extents waiting at LBA {} ({}s elapsed, sectors={})", lba, start_time.elapsed().as_secs(), remaining);
+            }
+
             let mut sectors = remaining.min(self.adaptive.current() as u32) as u16;
             // Align to 3-sector AACS units when possible. Partial units at
             // extent boundaries are safely handled by decrypt_sectors().
@@ -387,7 +403,6 @@ impl DiscStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
 impl crate::pes::Stream for DiscStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         if let Some(frame) = self.pending_frames.pop_front() {
@@ -568,31 +583,26 @@ impl crate::pes::Stream for DiscStream {
 
 #[cfg(test)]
 mod tests {
-    //! `DiscStream` is the only meaningful `FrameSource` impl in tree (every
-    //! other concrete `pes::Stream` impl in `mux/*` is a sink). The 0.18
-    //! round-1 blanket `impl<T: pes::Stream + Send> pes::FrameSource for T`
-    //! covers `DiscStream` for free as long as it is `Send`. These tests
-    //! lock that down: a static `Send` assertion plus a `Box<dyn FrameSource>`
-    //! round trip exercising every `FrameSource` method through the trait
-    //! object, so future Send-breaking edits to `DiscStream`'s interior
-    //! types fail at compile time and the trait-bridge dispatch is verified
-    //! at runtime.
-    #![allow(deprecated)] // exercising the 0.18 deprecation-window blanket bridge.
+    //! `DiscStream` is the only read-only `Stream` impl in tree (every
+    //! other concrete impl in `mux/*` is bidirectional or write-only).
+    //! These tests lock down a static `Send` assertion plus a
+    //! `Box<dyn Stream>` round trip exercising every method through the
+    //! trait object, so future Send-breaking edits to `DiscStream`'s
+    //! interior types fail at compile time.
     use super::*;
     use crate::disc::{ContentFormat, DiscTitle};
-    use crate::pes::FrameSource;
+    use crate::pes::Stream;
 
-    /// Static-assert `DiscStream: Send`. The blanket
-    /// `impl<T: pes::Stream + Send> pes::FrameSource for T` only fires for
-    /// `Send` types — if a future field on `DiscStream` is non-`Send` (e.g.
-    /// a `Box<dyn Read>` instead of `Box<dyn SectorReader>`), this fails
+    /// Static-assert `DiscStream: Send`. The `Stream` trait has `Send` as a
+    /// supertrait — if a future field on `DiscStream` is non-`Send` (e.g.
+    /// a `Box<dyn Read>` instead of `Box<dyn SectorSource>`), this fails
     /// at compile time, before the runtime trait-object test below.
     fn _assert_disc_stream_is_send() {
         fn requires_send<T: Send>() {}
         requires_send::<DiscStream>();
     }
 
-    /// Trivial `SectorReader` that yields zeroed sectors. Empty title means
+    /// Trivial `SectorSource` that yields zeroed sectors. Empty title means
     /// the demuxer produces no PES frames, so `read()` walks the extents to
     /// EOF and returns `Ok(None)`. That's enough to exercise the trait-object
     /// dispatch — the goal here is the bridge, not the demuxer.
@@ -600,7 +610,7 @@ mod tests {
         capacity: u32,
     }
 
-    impl crate::sector::SectorReader for ZeroReader {
+    impl crate::sector::SectorSource for ZeroReader {
         fn read_sectors(
             &mut self,
             _lba: u32,
@@ -613,7 +623,7 @@ mod tests {
             Ok(bytes)
         }
 
-        fn capacity(&self) -> u32 {
+        fn capacity_sectors(&self) -> u32 {
             self.capacity
         }
     }
@@ -628,13 +638,11 @@ mod tests {
         }
     }
 
-    /// Smallest credible witness that `DiscStream` flows through the
-    /// `FrameSource` blanket impl: build a `Box<dyn FrameSource>`, drive
-    /// `read()` to EOF, exercise `info()` / `headers_ready()` /
-    /// `codec_private()` through the trait object. The trait-bridge
-    /// correctness is what's being verified — not demuxer behaviour.
+    /// Smallest credible witness that `DiscStream` flows through `dyn Stream`:
+    /// build a `Box<dyn Stream>`, drive `read()` to EOF, exercise `info()` /
+    /// `headers_ready()` / `codec_private()` through the trait object.
     #[test]
-    fn frame_source_via_dyn_object() {
+    fn stream_via_dyn_object() {
         let reader = ZeroReader { capacity: 8 };
         let title = synthetic_title(8);
         let stream = DiscStream::new(
@@ -645,7 +653,7 @@ mod tests {
             ContentFormat::BdTs,
         );
 
-        let mut src: Box<dyn FrameSource> = Box::new(stream);
+        let mut src: Box<dyn Stream> = Box::new(stream);
 
         // Empty-title fixture has no streams configured, so headers are
         // trivially ready and codec_private() yields nothing on track 0.
@@ -657,11 +665,8 @@ mod tests {
         // produces no frames, but the call still routes through the blanket
         // dispatch into Stream::read.
         let mut frames = 0usize;
-        loop {
-            match src.read().expect("read") {
-                Some(_) => frames += 1,
-                None => break,
-            }
+        while src.read().expect("read").is_some() {
+            frames += 1;
             if frames > 1024 {
                 panic!("unexpected unbounded frame stream from empty title");
             }

src/mux/iso.rs

@@ -1,10 +1,10 @@
-//! ISO sector reader — file-backed SectorReader for Blu-ray ISO images.
+//! ISO sector reader — file-backed SectorSource for Blu-ray ISO images.
 //!
 //! An ISO is a flat image of 2048-byte sectors. Sector N starts at byte offset N * 2048.
 //! Used by DiscStream::open_iso() and Disc::scan_image().
 
 use crate::error::{Error, Result};
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use std::fs::File;
 use std::io::{Read, Seek, SeekFrom};
 use std::path::Path;
@@ -32,12 +32,12 @@ impl IsoSectorReader {
         Ok(Self { file, capacity })
     }
 
-    pub fn capacity(&self) -> u32 {
+    pub fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
 
-impl SectorReader for IsoSectorReader {
+impl SectorSource for IsoSectorReader {
     fn read_sectors(
         &mut self,
         lba: u32,
@@ -73,7 +73,7 @@ mod tests {
         std::fs::write(&dir, &data).unwrap();
 
         let mut reader = IsoSectorReader::open(dir.to_str().unwrap()).unwrap();
-        assert_eq!(reader.capacity(), 4);
+        assert_eq!(reader.capacity_sectors(), 4);
 
         let mut buf = [0u8; 2048];
         reader.read_sectors(0, 1, &mut buf, true).unwrap();
@@ -94,7 +94,7 @@ mod tests {
         std::fs::write(&dir, &data).unwrap();
 
         let reader = IsoSectorReader::open(dir.to_str().unwrap()).unwrap();
-        assert_eq!(reader.capacity(), 10);
+        assert_eq!(reader.capacity_sectors(), 10);
 
         std::fs::remove_file(&dir).ok();
     }

src/mux/m2ts.rs

@@ -173,7 +173,6 @@ impl M2tsStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
 impl crate::pes::Stream for M2tsStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         if let Some(frame) = self.pending_frames.pop_front() {
@@ -284,27 +283,3 @@ impl crate::pes::Stream for M2tsStream {
         true
     }
 }
-
-/// FrameSink sibling to the deprecated Stream impl; both coexist during the
-/// 0.18 deprecation window. Caller may pick either at the trait-object
-/// boundary — `Box<dyn Stream>` (deprecated) or `Box<dyn FrameSink>` (new).
-/// Use `M2tsStream::create(writer, title)` to construct the write half;
-/// calling `FrameSink::write` on an `M2tsStream::open(reader)` instance
-/// returns `StreamReadOnly`.
-#[allow(deprecated)] // delegating to deprecated Stream during the 0.18 deprecation window so callers don't see the deprecation twice.
-impl crate::pes::FrameSink for M2tsStream {
-    fn write(&mut self, frame: &crate::pes::PesFrame) -> io::Result<()> {
-        <Self as crate::pes::Stream>::write(self, frame)
-    }
-
-    fn finish(self: Box<Self>) -> io::Result<()> {
-        // Why: Stream::finish takes &mut self, FrameSink::finish takes Box<Self>.
-        // Re-borrow inside the box, call Stream::finish, drop the box.
-        let mut s: Self = *self;
-        <Self as crate::pes::Stream>::finish(&mut s)
-    }
-
-    fn info(&self) -> &crate::disc::DiscTitle {
-        <Self as crate::pes::Stream>::info(self)
-    }
-}

src/mux/mkvstream.rs

@@ -92,7 +92,6 @@ impl MkvStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
 impl crate::pes::Stream for MkvStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         let rs = match self.mode {
@@ -189,35 +188,6 @@ impl crate::pes::Stream for MkvStream {
     }
 }
 
-/// FrameSink sibling to the deprecated Stream impl; both coexist during the
-/// 0.18 deprecation window. Caller may pick either at the trait-object
-/// boundary — `Box<dyn Stream>` (deprecated) or `Box<dyn FrameSink>` (new).
-/// Use `MkvStream::create(writer, title)` to construct the write half;
-/// calling `FrameSink::write` on a `MkvStream::open(reader)` instance returns
-/// `StreamReadOnly`. `finish` is where the Cues index is written, so it must
-/// be called for the resulting MKV to be seekable.
-#[allow(deprecated)] // delegating to deprecated Stream during the 0.18 deprecation window so callers don't see the deprecation twice.
-impl crate::pes::FrameSink for MkvStream {
-    fn write(&mut self, frame: &crate::pes::PesFrame) -> io::Result<()> {
-        <Self as crate::pes::Stream>::write(self, frame)
-    }
-
-    fn finish(self: Box<Self>) -> io::Result<()> {
-        // Why: Stream::finish takes &mut self, FrameSink::finish takes Box<Self>.
-        // Re-borrow inside the box, call Stream::finish, drop the box.
-        // The inner `MkvMuxer` is owned via `Option`, and `Stream::finish`
-        // already takes it via `Option::take()` — moving `*self` out of the
-        // box hands it the same field by-value, so the muxer's own
-        // by-value `finish()` runs correctly.
-        let mut s: Self = *self;
-        <Self as crate::pes::Stream>::finish(&mut s)
-    }
-
-    fn info(&self) -> &crate::disc::DiscTitle {
-        <Self as crate::pes::Stream>::info(self)
-    }
-}
-
 // ── MKV header parsing (read side) ────────────────────────────
 
 /// Returns (DiscTitle, codec_privates: Vec<(track_number, codec_private_bytes)>)

src/mux/network.rs

@@ -70,7 +70,6 @@ impl NetworkStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
 impl crate::pes::Stream for NetworkStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         match &mut self.mode {
@@ -109,30 +108,6 @@ impl crate::pes::Stream for NetworkStream {
     }
 }
 
-/// FrameSink sibling to the deprecated Stream impl; both coexist during the
-/// 0.18 deprecation window. Caller may pick either at the trait-object
-/// boundary — `Box<dyn Stream>` (deprecated) or `Box<dyn FrameSink>` (new).
-/// Use `NetworkStream::connect(addr).meta(title)` to construct the write
-/// half; calling `FrameSink::write` on `NetworkStream::listen(addr)` returns
-/// `StreamReadOnly`.
-#[allow(deprecated)] // delegating to deprecated Stream during the 0.18 deprecation window so callers don't see the deprecation twice.
-impl crate::pes::FrameSink for NetworkStream {
-    fn write(&mut self, frame: &crate::pes::PesFrame) -> io::Result<()> {
-        <Self as crate::pes::Stream>::write(self, frame)
-    }
-
-    fn finish(self: Box<Self>) -> io::Result<()> {
-        // Why: Stream::finish takes &mut self, FrameSink::finish takes Box<Self>.
-        // Re-borrow inside the box, call Stream::finish, drop the box.
-        let mut s: Self = *self;
-        <Self as crate::pes::Stream>::finish(&mut s)
-    }
-
-    fn info(&self) -> &DiscTitle {
-        <Self as crate::pes::Stream>::info(self)
-    }
-}
-
 // NetworkStream is PES-only — no IOStream/Read/Write byte interface.
 
 #[cfg(test)]
@@ -182,7 +157,6 @@ mod tests {
 
     #[test]
     #[ignore] // Requires TCP; may be flaky in CI environments
-    #[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
     fn network_pes_roundtrip() {
         use crate::pes;
 

src/mux/null.rs

@@ -16,7 +16,6 @@ impl NullStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSink in follow-up commit.
 impl crate::pes::Stream for NullStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         Ok(None)
@@ -32,43 +31,16 @@ impl crate::pes::Stream for NullStream {
     }
 }
 
-/// FrameSink sibling to the deprecated Stream impl; both coexist during the
-/// 0.18 deprecation window. Caller may pick either at the trait-object
-/// boundary — `Box<dyn Stream>` (deprecated) or `Box<dyn FrameSink>` (new).
-/// The deprecation-window callers eventually migrate; this impl exists so
-/// new callers can target `FrameSink` without waiting for the rest of the
-/// migration to complete.
-#[allow(deprecated)] // delegating to deprecated Stream during the 0.18 deprecation window so callers don't see the deprecation twice.
-impl crate::pes::FrameSink for NullStream {
-    fn write(&mut self, frame: &crate::pes::PesFrame) -> io::Result<()> {
-        <Self as crate::pes::Stream>::write(self, frame)
-    }
-
-    fn finish(self: Box<Self>) -> io::Result<()> {
-        // Why: Stream::finish takes &mut self, FrameSink::finish takes Box<Self>.
-        // Re-borrow inside the box, call Stream::finish, drop the box.
-        let mut s: Self = *self;
-        <Self as crate::pes::Stream>::finish(&mut s)
-    }
-
-    fn info(&self) -> &DiscTitle {
-        <Self as crate::pes::Stream>::info(self)
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::pes::FrameSink;
+    use crate::pes::Stream;
 
-    /// Smallest credible witness that the new FrameSink impl on a concrete
-    /// `mux/*` sink works through the trait object: build a boxed
-    /// `dyn FrameSink`, write a frame, finish it. The trait-bridge correctness
-    /// is what's being verified — not NullStream-specific behaviour.
+    /// Verify NullStream routes through the `Stream` trait object cleanly.
     #[test]
-    fn frame_sink_via_dyn_object_writes_and_finishes() {
+    fn stream_via_dyn_object_writes_and_finishes() {
         let title = DiscTitle::empty();
-        let mut sink: Box<dyn FrameSink> = Box::new(NullStream::new(&title));
+        let mut sink: Box<dyn Stream> = Box::new(NullStream::new(&title));
 
         let frame = crate::pes::PesFrame {
             track: 0,
@@ -77,9 +49,7 @@ mod tests {
             data: vec![0x01, 0x02, 0x03],
         };
         sink.write(&frame).unwrap();
-        // info() routes through the trait object.
         let _ = sink.info();
-        // finish() consumes the Box<Self> — must compile and run.
         sink.finish().unwrap();
     }
 }

src/mux/resolve.rs

@@ -167,7 +167,6 @@ pub struct InputOptions {
 }
 
 /// Open a PES input stream (produces PES frames).
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource in follow-up commit.
 pub fn input(url: &str, opts: &InputOptions) -> io::Result<Box<dyn crate::pes::Stream>> {
     let parsed = parse_url(url);
     match parsed {
@@ -187,7 +186,7 @@ pub fn input(url: &str, opts: &InputOptions) -> io::Result<Box<dyn crate::pes::S
                 None => crate::disc::ScanOptions::default(),
             };
             let mut reader = super::iso::IsoSectorReader::open(&path.to_string_lossy())?;
-            let capacity = reader.capacity();
+            let capacity = reader.capacity_sectors();
             let disc = crate::disc::Disc::scan_image(&mut reader, capacity, &scan_opts)
                 .map_err(|e| -> io::Error { e.into() })?;
             if disc.titles.is_empty() {
@@ -204,7 +203,11 @@ pub fn input(url: &str, opts: &InputOptions) -> io::Result<Box<dyn crate::pes::S
             let title = disc.titles[idx].clone();
             let keys = disc.decrypt_keys();
             let format = disc.content_format;
-            let mut stream = DiscStream::new(Box::new(reader), title, keys, 64, format);
+            // ISO file: use large batch size (16 MB) — sequential read from fast storage, no bad sectors.
+            // Physical drives need small batches for adaptive error handling and retry logic.
+            const ISO_MUX_BATCH_SECTORS: u16 = 8192;
+            let mut stream =
+                DiscStream::new(Box::new(reader), title, keys, ISO_MUX_BATCH_SECTORS, format);
             if opts.raw {
                 stream.set_raw();
             }
@@ -235,7 +238,6 @@ pub fn input(url: &str, opts: &InputOptions) -> io::Result<Box<dyn crate::pes::S
 }
 
 /// Open a PES output stream (consumes PES frames).
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSink in follow-up commit.
 pub fn output(
     url: &str,
     title: &crate::disc::DiscTitle,

src/mux/stdio.rs

@@ -60,7 +60,6 @@ impl StdioStream {
     }
 }
 
-#[allow(deprecated)] // 0.18 trait split: migrate to FrameSource/FrameSink in follow-up commit.
 impl crate::pes::Stream for StdioStream {
     fn read(&mut self) -> io::Result<Option<crate::pes::PesFrame>> {
         self.ensure_header_read()?;
@@ -105,26 +104,3 @@ impl crate::pes::Stream for StdioStream {
         self.header_read || self.writer.is_some()
     }
 }
-
-/// FrameSink sibling to the deprecated Stream impl; both coexist during the
-/// 0.18 deprecation window. Caller may pick either at the trait-object
-/// boundary — `Box<dyn Stream>` (deprecated) or `Box<dyn FrameSink>` (new).
-/// Use `StdioStream::output(title)` to construct the write half; calling
-/// `FrameSink::write` on a `StdioStream::input()` returns `StreamReadOnly`.
-#[allow(deprecated)] // delegating to deprecated Stream during the 0.18 deprecation window so callers don't see the deprecation twice.
-impl crate::pes::FrameSink for StdioStream {
-    fn write(&mut self, frame: &crate::pes::PesFrame) -> io::Result<()> {
-        <Self as crate::pes::Stream>::write(self, frame)
-    }
-
-    fn finish(self: Box<Self>) -> io::Result<()> {
-        // Why: Stream::finish takes &mut self, FrameSink::finish takes Box<Self>.
-        // Re-borrow inside the box, call Stream::finish, drop the box.
-        let mut s: Self = *self;
-        <Self as crate::pes::Stream>::finish(&mut s)
-    }
-
-    fn info(&self) -> &DiscTitle {
-        <Self as crate::pes::Stream>::info(self)
-    }
-}

src/pes.rs

@@ -78,19 +78,20 @@ impl PesFrame {
     }
 }
 
-/// Deprecated; use [`FrameSource`] for read-only sources or [`FrameSink`]
-/// for write-only sinks. The runtime direction-error semantics
-/// (`StreamReadOnly` / `StreamWriteOnly` from a wrong-direction call) are
-/// removed in 0.18 — direction is type-checked.
-#[deprecated(
-    since = "0.18.0",
-    note = "use FrameSource (read-only) or FrameSink (write-only) instead"
-)]
-pub trait Stream {
-    /// Read the next frame, or `Ok(None)` at end of stream.
+/// A PES frame stream. One trait per format — same type opens for read
+/// (`open()` / `listen()` / `input()`) or write (`create()` / `connect()` /
+/// `output()`). Calling the wrong-direction method returns a typed
+/// `StreamReadOnly` / `StreamWriteOnly` error.
+///
+/// `Send` is required so streams can move across the producer/consumer
+/// threads in autorip's mux pipeline.
+pub trait Stream: Send {
+    /// Read the next frame, or `Ok(None)` at end of stream. Returns
+    /// `StreamWriteOnly` on a stream opened for writing.
     fn read(&mut self) -> std::io::Result<Option<PesFrame>>;
 
-    /// Write a frame to the sink.
+    /// Write a frame to the sink. Returns `StreamReadOnly` on a stream
+    /// opened for reading.
     fn write(&mut self, frame: &PesFrame) -> std::io::Result<()>;
 
     /// Finalize the stream: flush buffered frames, write any container
@@ -116,115 +117,10 @@ pub trait Stream {
     }
 }
 
-/// Read-only source of PES frames.
-///
-/// Replaces the read half of the deprecated [`Stream`] trait. Implementors
-/// produce frames via [`read`](FrameSource::read) and never accept writes —
-/// passing a `FrameSource` where a sink is expected is a compile error,
-/// not a runtime `E9001`.
-///
-/// `info()` returns the source's `DiscTitle` metadata (track list, codec
-/// info, duration). It must be stable across the lifetime of the source.
-///
-/// `codec_private(track)` exposes per-track codec initialization data
-/// (H.264 SPS/PPS, HEVC VPS/SPS/PPS, AC-3 fscod, etc.) that downstream
-/// muxers may need before any frame is written. `headers_ready()` returns
-/// false until enough input frames have been seen to populate every video
-/// track's codec-private blob — callers buffer frames they read until
-/// `headers_ready()` returns true.
-pub trait FrameSource: Send {
-    /// Read the next frame, or `Ok(None)` at end of stream.
-    fn read(&mut self) -> std::io::Result<Option<PesFrame>>;
-
-    /// Source metadata. Stable across reads — implementors must return a
-    /// consistent reference for the lifetime of the source.
-    fn info(&self) -> &crate::disc::DiscTitle;
-
-    /// Codec initialization data for a track (SPS/PPS, AC-3 fscod, etc.).
-    /// `None` for tracks that don't need codec_private (raw passthrough).
-    fn codec_private(&self, _track: usize) -> Option<Vec<u8>> {
-        None
-    }
-
-    /// True when `codec_private` is available for every video track —
-    /// callers buffer input frames until this flips, since some output
-    /// formats (MKV) can't write frames without codec init data.
-    fn headers_ready(&self) -> bool {
-        true
-    }
-}
-
-/// Write-only sink of PES frames.
-///
-/// Replaces the write half of the deprecated [`Stream`] trait. Implementors
-/// accept frames via [`write`](FrameSink::write) and finalize via
-/// [`finish`](FrameSink::finish) — passing a `FrameSink` where a source is
-/// expected is a compile error, not a runtime `E9000`.
-///
-/// `finish` takes `Box<Self>` (rather than `&mut self` like `Stream::finish`)
-/// so that finalization is a one-shot terminal operation: callers cannot use
-/// the sink after `finish` returns. This is the standard idiom for terminal
-/// methods on `dyn Trait` objects.
-pub trait FrameSink: Send {
-    /// Write a frame to the sink.
-    fn write(&mut self, frame: &PesFrame) -> std::io::Result<()>;
-
-    /// Finalize the sink: flush buffered frames, write any container index
-    /// (e.g. MKV `Cues`), close the underlying file/socket. Consumes the
-    /// sink — callers cannot use it afterwards.
-    fn finish(self: Box<Self>) -> std::io::Result<()>;
-
-    /// Sink metadata. Stable across writes — implementors must return a
-    /// consistent reference for the lifetime of the sink.
-    fn info(&self) -> &crate::disc::DiscTitle;
-}
-
-// Bridge: any **`Send`** type implementing the deprecated `Stream` trait
-// is also a `FrameSource`. This lets existing concrete `Stream` impls in
-// `mux/*` satisfy `FrameSource` bounds without per-type migration during
-// the 0.18 deprecation window.
-//
-// **Send caveat (read me before tightening `Stream` itself).** This
-// blanket carries a `T: Send` bound rather than promoting `Send` to a
-// supertrait of `Stream`, because not every concrete in-tree `Stream`
-// impl is `Send`: `MkvStream` and `M2tsStream` carry `Box<dyn Read>`
-// and `Box<dyn Write>` fields whose trait objects don't include `Send`.
-// Adding `Stream: Send` would force a wider audit (every `Box<dyn Read>`
-// becomes `Box<dyn Read + Send>`) than this commit is taking on, and
-// the type-level migration target is `FrameSource` / `FrameSink`
-// directly anyway. Consequence: coercing a non-Send `Box<dyn Stream>`
-// (the return shape of `crate::mux::input` / `output`) to
-// `Box<dyn FrameSource>` will fail with a `T: Send` trait-bound error.
-// The fix on the consumer side is to construct a Send-compliant
-// `FrameSource` / `FrameSink` directly rather than relying on this
-// bridge for non-Send streams.
-//
-// Note: `FrameSink` cannot be blanket-impl'd from `Stream` because
-// `Stream::finish` takes `&mut self` while `FrameSink::finish` takes
-// `Box<Self>`; concrete types will be migrated in a follow-up commit.
-#[allow(deprecated)]
-impl<T: Stream + Send + ?Sized> FrameSource for T {
-    fn read(&mut self) -> std::io::Result<Option<PesFrame>> {
-        <Self as Stream>::read(self)
-    }
-
-    fn info(&self) -> &crate::disc::DiscTitle {
-        <Self as Stream>::info(self)
-    }
-
-    fn codec_private(&self, track: usize) -> Option<Vec<u8>> {
-        <Self as Stream>::codec_private(self, track)
-    }
-
-    fn headers_ready(&self) -> bool {
-        <Self as Stream>::headers_ready(self)
-    }
-}
-
 /// Wraps any output stream and counts bytes written.
 ///
 /// Progress tracking is a CLI concern — streams don't know their size.
-/// Wrap the output with CountingStream, then query bytes_written().
+/// Wrap the output with `CountingStream`, then query `bytes_written()`.
 ///
 /// ```text
 /// let mut output = CountingStream::new(libfreemkv::output(dest, &title)?);
@@ -233,13 +129,11 @@ impl<T: Stream + Send + ?Sized> FrameSource for T {
 ///     let pct = output.bytes_written() as f64 / total as f64;
 /// }
 /// ```
-#[allow(deprecated)]
 pub struct CountingStream {
     inner: Box<dyn Stream>,
     written: u64,
 }
 
-#[allow(deprecated)]
 impl CountingStream {
     pub fn new(inner: Box<dyn Stream>) -> Self {
         Self { inner, written: 0 }
@@ -251,7 +145,6 @@ impl CountingStream {
     }
 }
 
-#[allow(deprecated)]
 impl Stream for CountingStream {
     fn read(&mut self) -> std::io::Result<Option<PesFrame>> {
         self.inner.read()
@@ -293,88 +186,35 @@ mod tests {
         }
     }
 
-    /// Direct `FrameSource` impl (not via the deprecated `Stream` blanket).
-    struct MockSource {
-        frames: std::vec::IntoIter<PesFrame>,
+    /// Minimal in-memory `Stream` for trait-shape tests. `read` replays
+    /// pre-seeded frames; `write` collects them.
+    struct MockStream {
+        read_queue: std::vec::IntoIter<PesFrame>,
+        written: Vec<PesFrame>,
         title: DiscTitle,
     }
 
-    impl MockSource {
-        fn new(frames: Vec<PesFrame>) -> Self {
+    impl MockStream {
+        fn new(read_frames: Vec<PesFrame>) -> Self {
             Self {
-                frames: frames.into_iter(),
+                read_queue: read_frames.into_iter(),
+                written: Vec::new(),
                 title: DiscTitle::empty(),
             }
         }
     }
 
-    impl FrameSource for MockSource {
+    impl Stream for MockStream {
         fn read(&mut self) -> std::io::Result<Option<PesFrame>> {
-            Ok(self.frames.next())
+            Ok(self.read_queue.next())
         }
 
-        fn info(&self) -> &DiscTitle {
-            &self.title
-        }
-    }
-
-    /// Direct `FrameSink` impl (not via the deprecated `Stream` blanket).
-    struct MockSink {
-        collected: Vec<PesFrame>,
-        title: DiscTitle,
-    }
-
-    impl MockSink {
-        fn new() -> Self {
-            Self {
-                collected: Vec::new(),
-                title: DiscTitle::empty(),
-            }
-        }
-    }
-
-    impl FrameSink for MockSink {
         fn write(&mut self, frame: &PesFrame) -> std::io::Result<()> {
-            self.collected.push(frame.clone());
+            self.written.push(frame.clone());
             Ok(())
         }
 
-        fn finish(self: Box<Self>) -> std::io::Result<()> {
-            // Drop self; in real sinks this is where flush/fsync/close happens.
-            Ok(())
-        }
-
-        fn info(&self) -> &DiscTitle {
-            &self.title
-        }
-    }
-
-    /// Variant of `MockSink` whose `finish` returns the collected frames so
-    /// the test can assert on them after the consuming `Box<Self>` call.
-    struct CollectingSink {
-        collected: Vec<PesFrame>,
-        title: DiscTitle,
-    }
-
-    impl CollectingSink {
-        fn new() -> Self {
-            Self {
-                collected: Vec::new(),
-                title: DiscTitle::empty(),
-            }
-        }
-    }
-
-    impl FrameSink for CollectingSink {
-        fn write(&mut self, frame: &PesFrame) -> std::io::Result<()> {
-            self.collected.push(frame.clone());
-            Ok(())
-        }
-
-        fn finish(self: Box<Self>) -> std::io::Result<()> {
-            // Real CollectingSink consumers would expose `take()` before
-            // finish; this trait method just confirms the boxed signature
-            // compiles and runs.
+        fn finish(&mut self) -> std::io::Result<()> {
             Ok(())
         }
 
@@ -384,72 +224,43 @@ mod tests {
     }
 
     #[test]
-    fn frame_source_yields_frames_then_eof() {
+    fn stream_read_yields_frames_then_eof() {
         let frames = vec![make_frame(0, 0), make_frame(1, 1_000), make_frame(0, 2_000)];
-        let mut src = MockSource::new(frames.clone());
+        let mut s = MockStream::new(frames.clone());
 
-        let f0 = src.read().unwrap().expect("first frame");
+        let f0 = s.read().unwrap().expect("first frame");
         assert_eq!(f0.track, frames[0].track);
         assert_eq!(f0.pts, frames[0].pts);
         assert!(f0.keyframe);
 
-        let f1 = src.read().unwrap().expect("second frame");
-        assert_eq!(f1.track, frames[1].track);
+        let f1 = s.read().unwrap().expect("second frame");
         assert_eq!(f1.pts, frames[1].pts);
 
-        let f2 = src.read().unwrap().expect("third frame");
-        assert_eq!(f2.track, frames[2].track);
+        let f2 = s.read().unwrap().expect("third frame");
         assert_eq!(f2.pts, frames[2].pts);
 
-        assert!(src.read().unwrap().is_none());
-        assert!(src.read().unwrap().is_none()); // idempotent at EOF
+        assert!(s.read().unwrap().is_none());
+        assert!(s.read().unwrap().is_none()); // idempotent at EOF
     }
 
     #[test]
-    fn frame_sink_collects_then_finishes() {
-        let mut sink = MockSink::new();
+    fn stream_write_collects_then_finishes() {
+        let mut s = MockStream::new(Vec::new());
         let frames = [make_frame(0, 0), make_frame(1, 100), make_frame(2, 200)];
 
         for f in &frames {
-            sink.write(f).unwrap();
+            s.write(f).unwrap();
         }
-        assert_eq!(sink.collected.len(), 3);
-        assert_eq!(sink.collected[0].pts, 0);
-        assert_eq!(sink.collected[1].pts, 100);
-        assert_eq!(sink.collected[2].pts, 200);
-
-        // Box-and-finish — the `self: Box<Self>` shape must compile and run.
-        Box::new(sink).finish().unwrap();
+        assert_eq!(s.written.len(), 3);
+        s.finish().unwrap();
     }
 
     #[test]
-    fn frame_sink_via_dyn_object() {
-        let frames = [make_frame(0, 0), make_frame(0, 33)];
-        let mut sink: Box<dyn FrameSink> = Box::new(CollectingSink::new());
-
-        for f in &frames {
-            sink.write(f).unwrap();
-        }
-        // info() routes through the trait object.
-        let _ = sink.info();
-        sink.finish().unwrap();
-    }
-
-    /// The deprecated blanket impl: any concrete `Stream` should also act as
-    /// a `FrameSource`. `NullStream` has the simplest constructor of every
-    /// concrete `Stream` impl in `mux/*`, so it's the smallest credible
-    /// witness that the bridge compiles and dispatches correctly.
-    #[test]
-    #[allow(deprecated)]
-    fn deprecated_stream_satisfies_frame_source() {
-        let title = DiscTitle::empty();
-        let mut null = crate::mux::NullStream::new(&title);
-
-        let src: &mut dyn FrameSource = &mut null;
-        // NullStream::read returns Ok(None) — it's a write-only sink.
-        assert!(src.read().unwrap().is_none());
-        // info() forwards through the blanket impl.
-        let _ = src.info();
-        assert!(src.headers_ready());
+    fn stream_via_dyn_object() {
+        let mut s: Box<dyn Stream> = Box::new(MockStream::new(vec![make_frame(0, 0)]));
+        let frame = s.read().unwrap().expect("first frame");
+        s.write(&frame).unwrap();
+        let _ = s.info();
+        s.finish().unwrap();
     }
 }

src/sector/file.rs

@@ -13,7 +13,7 @@ use std::path::Path;
 
 use crate::error::{Error, Result};
 
-use super::{SectorReader, SectorSink};
+use super::{SectorSink, SectorSource};
 
 /// SectorSource backed by a file (ISO image).
 ///
@@ -49,14 +49,14 @@ impl FileSectorSource {
     }
 }
 
-// Implement the legacy `SectorReader` trait. The blanket impl in
+// Implement the legacy `SectorSource` trait. The blanket impl in
 // `super` produces the `SectorSource` impl automatically — no need
 // to write both, and writing both would conflict. This keeps the
-// 0.17 method-resolution path intact (callers with `SectorReader`
+// 0.17 method-resolution path intact (callers with `SectorSource`
 // in scope can still write `fsr.read_sectors(..)` against a
 // `FileSectorSource`).
-impl SectorReader for FileSectorSource {
-    fn capacity(&self) -> u32 {
+impl SectorSource for FileSectorSource {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 
@@ -147,8 +147,8 @@ impl SectorSink for FileSectorSink {
 #[cfg(test)]
 mod tests {
     // Bring the 0.18 trait into scope (not super::*: the super
-    // module also re-exports the legacy `SectorReader`, and
-    // having both `SectorReader::read_sectors` and
+    // module also re-exports the legacy `SectorSource`, and
+    // having both `SectorSource::read_sectors` and
     // `SectorSource::read_sectors` visible would force every
     // call site to disambiguate). External consumers see the
     // same surface this test exercises.

src/sector/mod.rs

@@ -1,29 +1,17 @@
 //! Sector-level I/O traits.
 //!
-//! 0.18 splits the unidirectional read trait from a write trait at
-//! the sector layer, so the type system catches "wrong direction"
-//! mistakes at compile time instead of runtime. See
-//! `(internal)/memory/0_18_redesign.md`.
+//! The sector layer is direction-typed: [`SectorSource`] reads
+//! 2048-byte sectors, [`SectorSink`] writes them. Concrete impls
+//! never do both — physical drives are read-only, file-backed
+//! ISO images are opened for read OR write at construction time.
 //!
-//! - [`SectorSource`] reads 2048-byte sectors. Implemented by
-//!   `Drive` (via the legacy [`SectorReader`] alias) and
-//!   [`FileSectorSource`] (ISO-backed).
-//! - [`SectorSink`] writes 2048-byte sectors. Implemented by
-//!   [`FileSectorSink`] (ISO-backed) and, in later commits, by
-//!   sweep/patch consumer adapters.
+//! - [`SectorSource`] is implemented by `Drive` (hardware) and
+//!   [`FileSectorSource`] / `IsoSectorReader` (file-backed).
+//! - [`SectorSink`] is implemented by [`FileSectorSink`]
+//!   (ISO-backed) and sweep/patch consumer adapters.
 //! - [`DecryptingSectorSource`] is a decorator that wraps any
-//!   `SectorSource` and applies the existing AACS / CSS in-place
-//!   decrypt to plaintext-out.
-//!
-//! [`SectorReader`] is the 0.17 read trait. It stays on through
-//! the 0.18 migration window so existing call sites
-//! (`Drive`, `IsoSectorReader`, `BufferedSectorReader`,
-//! `DiscStream`, `verify`) compile unchanged. A blanket impl
-//! forwards every `SectorReader` impl to `SectorSource`, so new
-//! code should target `SectorSource` / `SectorSink` directly. The
-//! formal `#[deprecated]` attribute lands once the internal
-//! callers have migrated; see the comment on `SectorReader` for
-//! why this commit holds it back.
+//!   `SectorSource` and applies AACS / CSS in-place decrypt to
+//!   yield plaintext sectors.
 
 pub mod decrypting;
 pub mod file;
@@ -32,13 +20,14 @@ use crate::error::Result;
 
 /// Read 2048-byte sectors from a disc, image, or composed source.
 ///
-/// Direction-typed: a `SectorSource` cannot be written to. Wrap the
-/// inner source in [`DecryptingSectorSource`] to get plaintext
-/// sectors out of an encrypted disc.
+/// Wrap the inner source in [`DecryptingSectorSource`] to get
+/// plaintext sectors out of an encrypted disc.
 pub trait SectorSource: Send {
-    /// Total capacity in sectors, if known. Returns 0 when unknown
+    /// Total capacity in sectors, if known. Default `0` = unknown
     /// (e.g. live drives that haven't completed `READ CAPACITY` yet).
-    fn capacity_sectors(&self) -> u32;
+    fn capacity_sectors(&self) -> u32 {
+        0
+    }
 
     /// Read `count` sectors starting at `lba` into `buf`.
     /// `buf` must be at least `count * 2048` bytes.
@@ -60,10 +49,52 @@ pub trait SectorSource: Send {
     fn set_speed(&mut self, _kbs: u16) {}
 }
 
+// Forwarding impls so `Box<dyn SectorSource>` and `&mut dyn SectorSource`
+// satisfy the `SectorSource` trait bound when wrapped by generic
+// decorators like `DecryptingSectorSource<S: SectorSource>`.
+impl SectorSource for Box<dyn SectorSource> {
+    fn capacity_sectors(&self) -> u32 {
+        (**self).capacity_sectors()
+    }
+
+    fn read_sectors(
+        &mut self,
+        lba: u32,
+        count: u16,
+        buf: &mut [u8],
+        recovery: bool,
+    ) -> Result<usize> {
+        (**self).read_sectors(lba, count, buf, recovery)
+    }
+
+    fn set_speed(&mut self, kbs: u16) {
+        (**self).set_speed(kbs)
+    }
+}
+
+impl SectorSource for &mut (dyn SectorSource + '_) {
+    fn capacity_sectors(&self) -> u32 {
+        (**self).capacity_sectors()
+    }
+
+    fn read_sectors(
+        &mut self,
+        lba: u32,
+        count: u16,
+        buf: &mut [u8],
+        recovery: bool,
+    ) -> Result<usize> {
+        (**self).read_sectors(lba, count, buf, recovery)
+    }
+
+    fn set_speed(&mut self, kbs: u16) {
+        (**self).set_speed(kbs)
+    }
+}
+
 /// Write 2048-byte sectors to a disc image or composed sink.
 ///
-/// Direction-typed: a `SectorSink` cannot be read from. The
-/// terminal [`finish`] takes `Box<Self>` so it can run on `dyn
+/// The terminal [`finish`] takes `Box<Self>` so it can run on `dyn
 /// SectorSink` and consume the sink (`fsync` + close).
 ///
 /// [`finish`]: SectorSink::finish
@@ -78,125 +109,5 @@ pub trait SectorSink: Send {
     fn finish(self: Box<Self>) -> Result<()>;
 }
 
-/// 0.17 read trait. Slated for removal once internal call sites
-/// migrate to [`SectorSource`] in follow-up commits; until then
-/// it remains the trait that `Drive`, `IsoSectorReader`,
-/// `BufferedSectorReader`, and existing `&mut dyn SectorReader`
-/// signatures use unchanged.
-///
-/// New code should implement [`SectorSource`] directly. The
-/// blanket impl below makes any `SectorReader` automatically
-/// usable wherever a `SectorSource` is expected, so a one-way
-/// migration off `SectorReader` is possible per-callsite without
-/// touching the impls.
-//
-// NOTE: not marked `#[deprecated]` in this commit — `cargo clippy
-// -- -D warnings` (the CI gauntlet) treats deprecation as an
-// error, and the existing `Drive` / `udf::BufferedSectorReader` /
-// `mux::DiscStream` / `verify` call sites all go through this
-// trait. The deprecation attribute lands together with the
-// migration commits that move those call sites to
-// `SectorSource`. The behavioural contract — "this trait is
-// going away in 0.18" — is documented above and tracked in
-// `(internal)/memory/0_18_redesign.md`.
-pub trait SectorReader: Send {
-    /// Read `count` sectors starting at `lba` into `buf`.
-    /// See [`SectorSource::read_sectors`] for semantics.
-    fn read_sectors(
-        &mut self,
-        lba: u32,
-        count: u16,
-        buf: &mut [u8],
-        recovery: bool,
-    ) -> Result<usize>;
-
-    /// Total capacity in sectors, if known.
-    fn capacity(&self) -> u32 {
-        0
-    }
-
-    fn set_speed(&mut self, _kbs: u16) {}
-}
-
-// Blanket impl: anything implementing the legacy `SectorReader`
-// trait automatically satisfies `SectorSource`. This is what keeps
-// existing impls (`Drive`, `IsoSectorReader`, `BufferedSectorReader`,
-// etc.) compiling without source changes during the migration. The
-// reverse direction (impl SectorReader for SectorSource) is
-// intentionally NOT provided — new code targets the new trait.
-impl<T: SectorReader + ?Sized> SectorSource for T {
-    fn capacity_sectors(&self) -> u32 {
-        <T as SectorReader>::capacity(self)
-    }
-
-    fn read_sectors(
-        &mut self,
-        lba: u32,
-        count: u16,
-        buf: &mut [u8],
-        recovery: bool,
-    ) -> Result<usize> {
-        <T as SectorReader>::read_sectors(self, lba, count, buf, recovery)
-    }
-
-    fn set_speed(&mut self, kbs: u16) {
-        <T as SectorReader>::set_speed(self, kbs)
-    }
-}
-
-// Forwarding impls so callers can wrap `&mut dyn SectorReader` /
-// `Box<dyn SectorReader>` in [`DecryptingSectorSource`] without
-// having to unbox or re-borrow inside the lib's hot paths. The
-// generic `&mut T` / `Box<T>` blankets would conflict with the
-// `SectorReader → SectorSource` blanket above (a downstream crate
-// could `impl SectorReader for &mut U`); the specific
-// `dyn SectorReader` instantiations are unambiguous because
-// `SectorReader` is the very trait whose `dyn` we're targeting.
-impl SectorSource for &mut (dyn SectorReader + '_) {
-    fn capacity_sectors(&self) -> u32 {
-        <dyn SectorReader as SectorReader>::capacity(*self)
-    }
-
-    fn read_sectors(
-        &mut self,
-        lba: u32,
-        count: u16,
-        buf: &mut [u8],
-        recovery: bool,
-    ) -> Result<usize> {
-        <dyn SectorReader as SectorReader>::read_sectors(*self, lba, count, buf, recovery)
-    }
-
-    fn set_speed(&mut self, kbs: u16) {
-        <dyn SectorReader as SectorReader>::set_speed(*self, kbs)
-    }
-}
-
-impl SectorSource for Box<dyn SectorReader> {
-    fn capacity_sectors(&self) -> u32 {
-        <dyn SectorReader as SectorReader>::capacity(&**self)
-    }
-
-    fn read_sectors(
-        &mut self,
-        lba: u32,
-        count: u16,
-        buf: &mut [u8],
-        recovery: bool,
-    ) -> Result<usize> {
-        <dyn SectorReader as SectorReader>::read_sectors(&mut **self, lba, count, buf, recovery)
-    }
-
-    fn set_speed(&mut self, kbs: u16) {
-        <dyn SectorReader as SectorReader>::set_speed(&mut **self, kbs)
-    }
-}
-
 pub use decrypting::DecryptingSectorSource;
 pub use file::{FileSectorSink, FileSectorSource};
-
-// Backwards-compat alias for the public API. `FileSectorReader` is
-// the 0.17 name; new code uses `FileSectorSource`. Both point at
-// the same type. The `#[deprecated]` attribute lands together with
-// the migration commits that retire the alias from internal uses.
-pub type FileSectorReader = FileSectorSource;

src/udf.rs

@@ -19,7 +19,7 @@
 //!   BD-ROM Part 3 — Blu-ray filesystem profile
 
 use crate::error::{Error, Result};
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 
 /// A UDF filesystem parsed from disc.
 #[derive(Debug)]
@@ -84,7 +84,7 @@ impl UdfFs {
     /// Reads sector by sector from disc — no buffering.
     /// Get the absolute starting LBA of a file on disc.
     /// Used by the rip pipeline to locate m2ts content sectors.
-    pub fn file_start_lba(&self, reader: &mut dyn SectorReader, path: &str) -> Result<u32> {
+    pub fn file_start_lba(&self, reader: &mut dyn SectorSource, path: &str) -> Result<u32> {
         let parts: Vec<&str> = path.trim_matches('/').split('/').collect();
         let mut current = &self.root;
         for part in &parts[..parts.len() - 1] {
@@ -115,7 +115,7 @@ impl UdfFs {
         Ok(self.partition_start + data_lba)
     }
 
-    pub fn read_file(&self, reader: &mut dyn SectorReader, path: &str) -> Result<Vec<u8>> {
+    pub fn read_file(&self, reader: &mut dyn SectorSource, path: &str) -> Result<Vec<u8>> {
         let parts: Vec<&str> = path.trim_matches('/').split('/').collect();
         let mut current = &self.root;
 
@@ -175,7 +175,7 @@ impl UdfFs {
     ///
     /// Skips: STREAM/ (video), BACKUP/, DUPLICATE/,
     ///   MKB_RO.inf, ContentHash*, ContentRevocation*
-    pub fn metadata_sector_ranges(&self, reader: &mut dyn SectorReader) -> Result<Vec<(u32, u32)>> {
+    pub fn metadata_sector_ranges(&self, reader: &mut dyn SectorSource) -> Result<Vec<(u32, u32)>> {
         let mut ranges = Vec::new();
 
         // UDF structure: sector 0 through end of metadata partition
@@ -194,7 +194,7 @@ impl UdfFs {
 
     /// All sector ranges that contain data (metadata + all files including STREAM).
     /// For full disc-to-ISO dumps — reads only allocated sectors, skips gaps.
-    pub fn all_sector_ranges(&self, reader: &mut dyn SectorReader) -> Result<Vec<(u32, u32)>> {
+    pub fn all_sector_ranges(&self, reader: &mut dyn SectorSource) -> Result<Vec<(u32, u32)>> {
         let mut ranges = Vec::new();
 
         // UDF structure sectors
@@ -212,7 +212,7 @@ impl UdfFs {
 
     fn collect_all_file_ranges(
         &self,
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         entry: &DirEntry,
         ranges: &mut Vec<(u32, u32)>,
     ) -> Result<()> {
@@ -238,7 +238,7 @@ impl UdfFs {
 
     fn collect_file_ranges(
         &self,
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         entry: &DirEntry,
         ranges: &mut Vec<(u32, u32)>,
     ) -> Result<()> {
@@ -276,7 +276,7 @@ impl UdfFs {
     /// Read an Extended File Entry (tag 266) or File Entry (tag 261)
     /// and return its first allocation extent: (data_lba, data_length).
     /// The data_lba is partition-relative.
-    fn read_icb_extent(&self, reader: &mut dyn SectorReader, meta_lba: u32) -> Result<(u32, u32)> {
+    fn read_icb_extent(&self, reader: &mut dyn SectorSource, meta_lba: u32) -> Result<(u32, u32)> {
         let extents = self.read_icb_extents(reader, meta_lba)?;
         extents.first().copied().ok_or(Error::DiscRead {
             sector: 0,
@@ -290,7 +290,7 @@ impl UdfFs {
     /// Handles files with many extents (e.g. 88 GB m2ts files have ~90 extents).
     fn read_icb_extents(
         &self,
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         meta_lba: u32,
     ) -> Result<Vec<(u32, u32)>> {
         let mut icb = [0u8; 2048];
@@ -367,7 +367,7 @@ impl UdfFs {
     /// Returns Vec of (absolute_lba, sector_count) covering the entire file.
     pub fn file_extents(
         &self,
-        reader: &mut dyn SectorReader,
+        reader: &mut dyn SectorSource,
         path: &str,
     ) -> Result<Vec<(u32, u32)>> {
         let parts: Vec<&str> = path.trim_matches('/').split('/').collect();
@@ -417,7 +417,7 @@ impl UdfFs {
 /// 3. Metadata partition file → metadata content location
 /// 4. FSD → root directory ICB
 /// 5. Root directory → file tree
-pub fn read_filesystem(reader: &mut dyn SectorReader) -> Result<UdfFs> {
+pub fn read_filesystem(reader: &mut dyn SectorSource) -> Result<UdfFs> {
     // Step 1: Anchor Volume Descriptor Pointer at sector 256
     // ECMA-167 §10.2 — always at sector 256
     let mut avdp = [0u8; 2048];
@@ -593,7 +593,7 @@ pub fn read_filesystem(reader: &mut dyn SectorReader) -> Result<UdfFs> {
 /// and points to its ICB.
 #[allow(clippy::only_used_in_recursion)]
 fn read_directory(
-    reader: &mut dyn SectorReader,
+    reader: &mut dyn SectorSource,
     part_start: u32,
     meta_start: u32,
     meta_lba: u32,
@@ -758,7 +758,7 @@ fn read_directory(
 }
 
 /// Read file size (info_length) from an Extended File Entry ICB.
-fn read_file_size(reader: &mut dyn SectorReader, meta_start: u32, meta_lba: u32) -> Result<u64> {
+fn read_file_size(reader: &mut dyn SectorSource, meta_start: u32, meta_lba: u32) -> Result<u64> {
     let mut icb = [0u8; 2048];
     read_sector(reader, meta_start + meta_lba, &mut icb)?;
 
@@ -874,7 +874,7 @@ fn parse_dstring(data: &[u8]) -> String {
 /// Each SCSI command has ~500ms overhead on USB drives, so reading 32 sectors
 /// at once (one command) is 32x faster than 32 individual reads.
 pub(crate) struct BufferedSectorReader<'a> {
-    inner: &'a mut dyn SectorReader,
+    inner: &'a mut dyn SectorSource,
     cache_start: u32,
     cache: Vec<u8>,
     cache_sectors: u32,
@@ -884,7 +884,7 @@ pub(crate) struct BufferedSectorReader<'a> {
 }
 
 impl<'a> BufferedSectorReader<'a> {
-    pub(crate) fn new(inner: &'a mut dyn SectorReader, batch: u16) -> Self {
+    pub(crate) fn new(inner: &'a mut dyn SectorSource, batch: u16) -> Self {
         Self {
             inner,
             cache_start: u32::MAX,
@@ -952,7 +952,7 @@ impl BufferedSectorReader<'_> {
     }
 }
 
-impl SectorReader for BufferedSectorReader<'_> {
+impl SectorSource for BufferedSectorReader<'_> {
     fn read_sectors(
         &mut self,
         lba: u32,
@@ -996,7 +996,7 @@ impl SectorReader for BufferedSectorReader<'_> {
     }
 }
 
-fn read_sector(reader: &mut dyn SectorReader, lba: u32, buf: &mut [u8]) -> Result<()> {
+fn read_sector(reader: &mut dyn SectorSource, lba: u32, buf: &mut [u8]) -> Result<()> {
     reader.read_sectors(lba, 1, buf, true)?;
     Ok(())
 }

src/verify.rs

@@ -2,7 +2,7 @@
 
 use crate::disc::{Chapter, DiscTitle};
 use crate::progress::Progress;
-use crate::sector::SectorReader;
+use crate::sector::SectorSource;
 use std::time::Instant;
 
 /// Health status of a single sector read.
@@ -82,7 +82,7 @@ impl VerifyResult {
 /// Reads in batches for speed, falls back to single-sector on failure.
 /// The progress callback returns false to request early stop.
 pub fn verify_title(
-    reader: &mut dyn SectorReader,
+    reader: &mut dyn SectorSource,
     title: &DiscTitle,
     batch_sectors: u16,
     on_progress: Option<&dyn Progress>,

tests/disc_tests.rs

@@ -1,6 +1,6 @@
 //! Disc scanning pipeline tests.
 
-use libfreemkv::SectorReader;
+use libfreemkv::SectorSource;
 use libfreemkv::error::Result;
 use libfreemkv::{Disc, DiscTitle, ScanOptions};
 use std::collections::HashMap;
@@ -20,7 +20,7 @@ impl MockSectorReader {
     }
 }
 
-impl SectorReader for MockSectorReader {
+impl SectorSource for MockSectorReader {
     fn read_sectors(
         &mut self,
         lba: u32,

tests/integration_progress_and_halt.rs

@@ -1,17 +1,12 @@
 //! Integration tests for progress reporting, halt behavior, drop safety,
 //! and the file-backed sector reader round trip.
 
-// 0.18 trait split: this suite still drives the deprecated `pes::Stream`
-// trait directly. It will be migrated to `FrameSource`/`FrameSink` in the
-// follow-up that ports concrete impls.
-#![allow(deprecated)]
-
 use libfreemkv::disc::{CopyOptions, DiscRegion};
 use libfreemkv::error::Result;
 use libfreemkv::pes::Stream as PesStream;
 use libfreemkv::{
-    ContentFormat, Disc, DiscFormat, DiscStream, DiscTitle, EventKind, Extent, FileSectorReader,
-    SectorReader,
+    ContentFormat, Disc, DiscFormat, DiscStream, DiscTitle, EventKind, Extent, FileSectorSource,
+    SectorSource,
 };
 use std::io::Write;
 use std::sync::Arc;
@@ -37,7 +32,7 @@ impl ZeroSectorReader {
     }
 }
 
-impl SectorReader for ZeroSectorReader {
+impl SectorSource for ZeroSectorReader {
     fn read_sectors(
         &mut self,
         _lba: u32,
@@ -51,7 +46,7 @@ impl SectorReader for ZeroSectorReader {
         Ok(bytes)
     }
 
-    fn capacity(&self) -> u32 {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
@@ -72,7 +67,7 @@ impl SlowZeroSectorReader {
     }
 }
 
-impl SectorReader for SlowZeroSectorReader {
+impl SectorSource for SlowZeroSectorReader {
     fn read_sectors(
         &mut self,
         _lba: u32,
@@ -86,7 +81,7 @@ impl SectorReader for SlowZeroSectorReader {
         Ok(bytes)
     }
 
-    fn capacity(&self) -> u32 {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
@@ -106,6 +101,7 @@ fn synthetic_disc(capacity_sectors: u32) -> Disc {
         aacs: None,
         css: None,
         encrypted: false,
+        aacs_error: None,
         content_format: ContentFormat::BdTs,
     }
 }
@@ -308,7 +304,7 @@ fn test_drop_impls_do_not_panic_or_block() {
     panic!("DiscStream drop did not complete within 100ms");
 }
 
-// ── 5. FileSectorReader round trip ────────────────────────────────────────
+// ── 5. FileSectorSource round trip ────────────────────────────────────────
 
 #[test]
 fn test_file_sector_reader_round_trip() {
@@ -325,9 +321,13 @@ fn test_file_sector_reader_round_trip() {
     tmp.flush().expect("flush");
 
     let path = tmp.path().to_path_buf();
-    let mut fsr = FileSectorReader::open(&path).expect("open FileSectorReader");
+    let mut fsr = FileSectorSource::open(&path).expect("open FileSectorSource");
 
-    assert_eq!(fsr.capacity(), N_SECTORS as u32, "capacity mismatch");
+    assert_eq!(
+        fsr.capacity_sectors(),
+        N_SECTORS as u32,
+        "capacity mismatch"
+    );
 
     // Read each sector individually and compare.
     let mut buf = vec![0u8; SECTOR_SIZE];
@@ -395,7 +395,7 @@ impl FailingSectorReader {
     }
 }
 
-impl SectorReader for FailingSectorReader {
+impl SectorSource for FailingSectorReader {
     fn read_sectors(
         &mut self,
         _lba: u32,
@@ -422,7 +422,7 @@ impl SectorReader for FailingSectorReader {
         })
     }
 
-    fn capacity(&self) -> u32 {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
@@ -459,11 +459,17 @@ fn test_disc_copy_completes_full_disc_with_failing_reader() {
     let _ = std::fs::remove_file(&iso_path);
     let _ = std::fs::remove_file(libfreemkv::disc::mapfile_path_for(&iso_path));
 
-    // Hard bound — even at 0 ms per read, 1024 sectors with skip-forward
-    // should complete in well under a second on any host.
+    // Hard bound — Pass 1 must NOT infinite-loop on a fully-failing
+    // reader. The threshold accommodates the 2026-05-10 wedge-
+    // avoidance pause (PASS_1_FAIL_PAUSE_SECS = 5 s on each failed
+    // batch). With batch=32 and 1024 sectors that's up to ~5 batch
+    // failures + a few damage-jump pauses before fast-trigger jumps
+    // us past end-of-disc — well-bounded total, ~20-30 s typical.
+    // The point of this test is "finishes cleanly, not infinitely",
+    // not "completes in milliseconds."
     assert!(
-        elapsed < Duration::from_secs(5),
-        "Pass 1 took {elapsed:?} on a 2 MB synthetic disc — expected < 5 s"
+        elapsed < Duration::from_secs(60),
+        "Pass 1 took {elapsed:?} on a 2 MB synthetic disc — expected < 60 s (not infinite)"
     );
 
     // Per RIP_DESIGN.md §2.1: Pass 1 must reach end of disc regardless of
@@ -565,7 +571,7 @@ struct BlockSizeFailingReader {
     capacity: u32,
 }
 
-impl SectorReader for BlockSizeFailingReader {
+impl SectorSource for BlockSizeFailingReader {
     fn read_sectors(
         &mut self,
         lba: u32,
@@ -591,7 +597,7 @@ impl SectorReader for BlockSizeFailingReader {
         }
     }
 
-    fn capacity(&self) -> u32 {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
@@ -649,12 +655,16 @@ fn test_disc_copy_marks_failed_ecc_blocks_as_nontrimmed() {
 
 // ── 9. PassProgress carries separate unreadable vs pending byte counts ─────
 //
-// The video-damage-time display needs bytes_unreadable_total (confirmed dead)
-// separate from bytes_pending_total (might still recover). This test verifies
-// that a Pass 2 with some confirmed failures produces correct field values.
+// 2026-05-11 design call: Pass N never marks bytes as `Unreadable` mid-multipass —
+// failed reads stay `NonTrimmed` so the next pass can retry them. The orchestrator
+// (autorip) promotes still-NonTrimmed bytes to Unreadable after the FINAL retry
+// pass completes. This test was rewritten from its pre-design-call shape (which
+// asserted Pass 2 produced bytes_unreadable > 0) to verify the new invariant:
+// pass-level retries keep failed bytes in `bytes_pending` so subsequent passes
+// get more shots at them.
 
 #[test]
-fn test_pass_progress_separates_unreadable_from_pending() {
+fn test_pass2_leaves_failed_reads_as_pending_not_unreadable() {
     let capacity_sectors: u32 = 128;
     let total_bytes: u64 = capacity_sectors as u64 * SECTOR_SIZE as u64;
 
@@ -728,24 +738,30 @@ fn test_pass_progress_separates_unreadable_from_pending() {
         pass2.bytes_good, 0,
         "pass2: still no good sectors (reader always fails)"
     );
-    assert!(
-        pass2.bytes_unreadable > 0,
-        "pass2: some sectors confirmed unreadable"
+    // 2026-05-11 design: pass-level retries do NOT promote failed bytes
+    // to Unreadable. Failed bytes stay NonTrimmed (pending) so a later
+    // pass can retry. End-of-recovery promotion is an orchestrator
+    // concern (autorip), not the patch loop's.
+    assert_eq!(
+        pass2.bytes_unreadable, 0,
+        "pass2: Disc::patch never marks Unreadable mid-multipass — orchestrator promotes after final pass"
     );
-    assert!(
-        pass2.bytes_pending < pass1.bytes_pending,
-        "pass2: fewer pending sectors than pass1"
+    // bytes_pending stays at total_bytes because everything still
+    // failed and nothing got recovered or promoted out of pending.
+    assert_eq!(
+        pass2.bytes_pending, total_bytes,
+        "pass2: failed bytes remain NonTrimmed for the next pass to retry"
     );
 
     let observed_unreadable = last_unreadable.load(Ordering::Relaxed);
     let observed_pending = last_pending.load(Ordering::Relaxed);
-    assert!(
-        observed_unreadable > 0,
-        "progress should report confirmed unreadable bytes"
+    assert_eq!(
+        observed_unreadable, 0,
+        "progress should report zero confirmed-unreadable mid-pass under the new design"
     );
     assert!(
-        observed_pending == 0 || observed_pending < total_bytes,
-        "pending should shrink as sectors are confirmed unreadable"
+        observed_pending > 0,
+        "progress should report pending bytes as the reader keeps failing"
     );
 
     // Video damage time: unreadable / total * duration

tests/pass_n_size_aware_skip.rs

@@ -15,7 +15,7 @@ use libfreemkv::disc::CopyOptions;
 use libfreemkv::disc::DiscRegion;
 use libfreemkv::disc::mapfile::{Mapfile, SectorStatus};
 use libfreemkv::error::Result;
-use libfreemkv::{ContentFormat, Disc, DiscFormat, SectorReader};
+use libfreemkv::{ContentFormat, Disc, DiscFormat, SectorSource};
 use std::collections::HashSet;
 use std::sync::{Arc, Mutex};
 
@@ -30,8 +30,10 @@ struct PatternedSectorReader {
     trace: Arc<Mutex<Vec<(u32, u16)>>>,
 }
 
+type ReadTrace = Arc<Mutex<Vec<(u32, u16)>>>;
+
 impl PatternedSectorReader {
-    fn new(capacity: u32, bad_lbas: HashSet<u32>) -> (Self, Arc<Mutex<Vec<(u32, u16)>>>) {
+    fn new(capacity: u32, bad_lbas: HashSet<u32>) -> (Self, ReadTrace) {
         let trace = Arc::new(Mutex::new(Vec::new()));
         (
             Self {
@@ -44,7 +46,7 @@ impl PatternedSectorReader {
     }
 }
 
-impl SectorReader for PatternedSectorReader {
+impl SectorSource for PatternedSectorReader {
     fn read_sectors(
         &mut self,
         lba: u32,
@@ -68,13 +70,19 @@ impl SectorReader for PatternedSectorReader {
                 });
             }
         }
-        for chunk in buf.chunks_mut(SECTOR_SIZE) {
-            chunk.fill((lba & 0xff) as u8);
+        // Fill each sector with ITS OWN LBA byte, not the starting LBA's
+        // byte. This matches real drive behavior: a multi-sector READ
+        // returns per-sector-correct data. Pre-0.18.13 only single-sector
+        // reads were exercised by patch tests, so the cheaper "fill the
+        // whole batch with one byte" worked; adaptive batching needs the
+        // per-sector pattern to verify correct positioning.
+        for (i, chunk) in buf.chunks_mut(SECTOR_SIZE).enumerate() {
+            chunk.fill(((lba + i as u32) & 0xff) as u8);
         }
         Ok(buf.len())
     }
 
-    fn capacity(&self) -> u32 {
+    fn capacity_sectors(&self) -> u32 {
         self.capacity
     }
 }
@@ -92,6 +100,7 @@ fn synthetic_disc(capacity_sectors: u32) -> Disc {
         aacs: None,
         css: None,
         encrypted: false,
+        aacs_error: None,
         content_format: ContentFormat::BdTs,
     }
 }

tests/streams.rs

@@ -1,10 +1,5 @@
 //! Integration tests for the PES stream pipeline.
 
-// 0.18 trait split: this suite still drives the deprecated `pes::Stream`
-// trait directly. It will be migrated to `FrameSource`/`FrameSink` in the
-// follow-up that ports concrete impls.
-#![allow(deprecated)]
-
 use libfreemkv::mux::meta::M2tsMeta;
 use libfreemkv::pes::Stream as PesStream;
 use libfreemkv::*;

tests/udf_tests.rs

@@ -1,7 +1,7 @@
 //! UDF parser tests using a MockSectorReader.
 
 use libfreemkv::error::Result;
-use libfreemkv::{SectorReader, read_filesystem};
+use libfreemkv::{SectorSource, read_filesystem};
 use std::collections::HashMap;
 
 const SECTOR_SIZE: usize = 2048;
@@ -38,7 +38,7 @@ impl MockSectorReader {
     }
 }
 
-impl SectorReader for MockSectorReader {
+impl SectorSource for MockSectorReader {
     fn read_sectors(
         &mut self,
         lba: u32,
@@ -463,11 +463,11 @@ fn find_dir_case_insensitive() {
 
 #[test]
 fn sector_reader_is_object_safe() {
-    // Verify SectorReader can be used as a trait object
+    // Verify SectorSource can be used as a trait object
     let mut reader = MockSectorReader::new();
     reader.set_sector(0, vec![42u8; SECTOR_SIZE]);
 
-    let dyn_reader: &mut dyn SectorReader = &mut reader;
+    let dyn_reader: &mut dyn SectorSource = &mut reader;
     let mut buf = vec![0u8; SECTOR_SIZE];
     let n = dyn_reader.read_sectors(0, 1, &mut buf, true).unwrap();
     assert_eq!(n, SECTOR_SIZE);