Probe 7z listings and ZIP starts

7z keeps its file list at the end of the archive, so the 7z-tail
candidates (the last segment of the highest volume) were queued but
never probed, and the .7z.001 start only gave the type. The prober now
claims 7z-tail candidates after the archives; lib/sevenzip finds the end
header in the article, decodes the LZMA-packed header (a TypeScript port
of the LZMA SDK's reference decoder) and lists the files with their
sizes. An AES-encrypted header means passworded without names. Names
feed the inner name and the judge's fake rule.

An unsplit .7z of several segments now also gets a tail candidate, and
.zip files an archive candidate: their first segment's local headers
give the first entries and whether they are encrypted. Both in the Rust
edge and the TypeScript indexer.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

REBUILD.md

@@ -260,7 +260,7 @@ with 68,032 releases with a password):
 | Passwords (from spots, NZB meta, names) | D29, D26 | from spots (title, text) and their NZBs' meta, in `release_passwords`; else only *whether* passworded (the prober); the export's 68 k not imported |
 | SFV grouping and naming | D34 | not yet (SFV files aren't probe candidates) |
 | Complete RAR listings by walking volume headers | D40 | no: the prober reads the first volume's first article only |
-| 7z listings | D19 | no: `7z-tail` candidates are queued, not probed; one release keeps only the tails of its highest volume (the live tail's pieces each queued one; `seven_zip_tails`) |
+| 7z listings | D19 | yes (2026-10-23): the prober reads the `7z-tail` (the last segment of the highest volume, or of an unsplit multi-segment .7z) and `lib/sevenzip` lists it from the archive's end header (LZMA-packed, decoded in TypeScript); an encrypted header (`-mhe`) means passworded without names. One release keeps only the tails of its highest volume (`seven_zip_tails`). ZIP: the first segment's local headers (first entries, encryption) |
 | Names from yEnc bodies for obfuscated subjects | D13, D21, D36 | no: obfuscated and per-article subjects are only counted (part 5); their message-ids aren't stored, so a body path needs those ranges read again |
 | Garbage dropped after probing (no real name, no password) | D42 (its second filter) | the junk judge hides it (below); nothing dropped yet |
 

app/services/prober.ts

@@ -20,7 +20,8 @@ type Outcome = { candidate: Candidate; status: 'done' | 'missing' | 'error' | 'w
 
 /**
  * The order candidates are probed in: what the par2 merge needs first (a random-named file's own start, then the
- * par2 sets and archives of releases without a readable name), then the rest (names and passwords of readable ones).
+ * par2 sets and archives of releases without a readable name), then the rest (names and passwords of readable ones),
+ * then 7z listings (the end of a split 7z's last volume; queued from 2026-10-13, probed from 2026-10-23).
  */
 const TIERS: { kind: string; unreadable: boolean }[] = [
   { kind: 'lone', unreadable: false },
@@ -28,6 +29,8 @@ const TIERS: { kind: string; unreadable: boolean }[] = [
   { kind: 'archive', unreadable: true },
   { kind: 'par2', unreadable: false },
   { kind: 'archive', unreadable: false },
+  { kind: '7z-tail', unreadable: true },
+  { kind: '7z-tail', unreadable: false },
 ]
 const FLUSH_MS = 2000
 
@@ -169,7 +172,7 @@ export class Prober {
             }
             this.stats.bytes += body.length
             try {
-              this.outcomes.push({ candidate, status: 'done', inspection: inspect(body) })
+              this.outcomes.push({ candidate, status: 'done', inspection: inspect(body, candidate.kind) })
             } catch (error: any) {
               // Not yEnc, a broken one, or data a parser chokes on: a final answer, not a connection problem.
               if (!(error instanceof YencError)) logger.warn(`Probing ${candidate.messageId}: ${error.message}`)

app/services/release_judge.ts

@@ -59,7 +59,7 @@ export const RULES: Rule[] = [
     // An archive whose entries are all executables, under a media name (its own or its entries'); or a file that is
     // an executable by name or by its first bytes, under a media name.
     sql: (scoped) => `SELECT i.release_id FROM release_inspections i JOIN releases r ON r.id = i.release_id ${only(scoped, 'i.release_id')}
-          WHERE i.kind = 'archive' AND jsonb_array_length(i.result->'names') > 0
+          WHERE i.kind IN ('archive', '7z-tail') AND jsonb_array_length(i.result->'names') > 0
             AND NOT EXISTS (SELECT 1 FROM jsonb_array_elements_text(i.result->'names') n WHERE n !~* '${EXECUTABLE}')
             AND (r.name ~* '${MEDIA}' OR (i.result->>'names') ~* '${MEDIA}')
           UNION

edge/src/indexer.rs

@@ -915,12 +915,17 @@ fn candidates_of(key: &str, files: &[Vec<Seg>], upload: usize) -> Vec<Candidate>
     let c = |kind, s: &Seg| Candidate { release_key: key.to_string(), upload, kind, message_id: s.message_id.clone(), file: s.file.name.clone() };
     for f in files {
         let name = &f[0].file.name;
-        if let Some(volume) = names::seven_zip_volume(name).filter(|&v| v > 1) {
+        let volume = names::seven_zip_volume(name);
+        if let Some(volume) = volume.filter(|&v| v > 1) {
             if tail.is_none_or(|(v, _)| volume > v) {
                 tail = Some((volume, f));
             }
             continue;
         }
+        // An unsplit 7z of more than one segment: its listing is in its last one.
+        if volume == Some(0) && f.len() > 1 && tail.is_none() {
+            tail = Some((0, f));
+        }
         if names::is_archive_start(name) {
             out.push(c("archive", &f[0]));
         } else if names::is_par2(name) && !names::is_later_volume(name) {
@@ -965,6 +970,40 @@ mod tests {
         assert_eq!(batch.releases[0].key, batch.releases[1].key);
     }
 
+    #[test]
+    fn archive_candidates_as_in_the_typescript() {
+        let mut priorities = FxHashMap::default();
+        priorities.insert(GROUP.to_string(), 1);
+        let mut ix = RangeIndexer::new(GROUP, 1, 10_000, 1, Rules::defaults(priorities), 5);
+        let file = |at: i64, release: &str, name: &str, n: usize, parts: i64| -> Vec<String> {
+            (0..parts).map(|i| line(at + i, &format!(r#"{release} [{n}/3] - "{name}" yEnc ({}/{parts})"#, i + 1), 0)).collect()
+        };
+        let mut lines = Vec::new();
+        // A split 7z: its start, and the end of its highest volume.
+        lines.extend(file(100, "Split.Seven", "Split.Seven.7z.001", 1, 2));
+        lines.extend(file(110, "Split.Seven", "Split.Seven.7z.003", 3, 2));
+        lines.extend(file(120, "Split.Seven", "Split.Seven.7z.002", 2, 2));
+        // An unsplit 7z of 3 segments: its start and its end.
+        lines.extend(file(200, "Whole.Seven", "Whole.Seven.7z", 1, 3));
+        // A ZIP: its start.
+        lines.extend(file(300, "Some.Zip", "Some.Zip.zip", 1, 2));
+        ix.add_text(&lines.join("\r\n"), 10_001);
+        ix.finish();
+        let batch = ix.take();
+        let mut got: Vec<(&str, &str, &str)> = batch.candidates.iter().map(|c| (c.kind, c.file.as_str(), c.message_id.as_str())).collect();
+        got.sort();
+        assert_eq!(
+            got,
+            vec![
+                ("7z-tail", "Split.Seven.7z.003", "u111@test"),
+                ("7z-tail", "Whole.Seven.7z", "u202@test"),
+                ("archive", "Some.Zip.zip", "u300@test"),
+                ("archive", "Split.Seven.7z.001", "u100@test"),
+                ("archive", "Whole.Seven.7z", "u200@test"),
+            ]
+        );
+    }
+
     #[test]
     fn copies_and_fills_as_in_the_typescript() {
         let hour = 3_600_000i64;

edge/src/names.rs

@@ -1030,7 +1030,7 @@ static SEVEN: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.7z$"));
 static PART1: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.part0*1\.rar$"));
 static RAR: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.rar$"));
 static PART: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.part([0-9]+)\.rar$"));
-static BIN: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.bin$"));
+static BIN: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.(bin|zip)$"));
 static OLD_RAR: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.r[0-9]{2,3}$"));
 static PAR2_VOL: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.vol[0-9]+[+-][0-9]+\.par2$"));
 pub static PAR2: LazyLock<Regex> = LazyLock::new(|| re(r"(?i)\.par2$"));

lib/edge/range_indexer.ts

@@ -434,6 +434,8 @@ export function candidatesOf(key: string, files: AggregatedFile<EdgeSegment>[],
       if (!tail || volume > tail.volume) tail = { volume, file: f }
       continue
     }
+    // An unsplit 7z of more than one segment: its listing is in its last one.
+    if (volume === 0 && f.segments.length > 1 && !tail) tail = { volume, file: f }
     if (isArchiveStart(name)) out.push({ releaseKey: key, upload, kind: 'archive', messageId: f.segments[0].messageId, file: name })
     else if (/\.par2$/i.test(name) && !isLaterVolume(name)) out.push({ releaseKey: key, upload, kind: 'par2', messageId: f.segments[0].messageId, file: name })
   }

lib/files/volumes.ts

@@ -1,10 +1,11 @@
 /**
  * Files whose first segment says what an archive holds: named first RAR
- * volumes (.part01.rar, .rar), 7z (.7z, .7z.001) and `.bin`, an extension
+ * volumes (.part01.rar, .rar), 7z (.7z, .7z.001: its type; the listing is at
+ * its end, the 7z-tail), ZIP (its first entries) and `.bin`, an extension
  * uploaders use for archive volumes too (sniffed by content).
  */
 export function isArchiveStart(name: string): boolean {
-  if (/\.bin$/i.test(name)) return true
+  if (/\.(bin|zip)$/i.test(name)) return true
   const volume = sevenZipVolume(name)
   if (volume === 0 || volume === 1) return true
   return /\.part0*1\.rar$/i.test(name) || (/\.rar$/i.test(name) && !/\.part\d+\.rar$/i.test(name))

lib/probe/inspect.ts

@@ -2,6 +2,8 @@ import { createHash } from 'node:crypto'
 import { decodeSegment, YencCrcError, YencError, type DecodedSegment } from '#lib/yenc/index'
 import { isPar2, parsePar2 } from '#lib/par2/index'
 import { parseRarHeaders } from '#lib/rar/index'
+import { parseSevenZipTail } from '#lib/sevenzip/index'
+import { parseZipStart } from '#lib/zip/index'
 import { sniffContentType, type ContentType } from '#lib/content/index'
 
 /** What one probed article showed (REBUILD.md, part 6; stored per release and kind). */
@@ -55,8 +57,11 @@ function largestFirst(items: { name: string; size: number }[]): string[] {
     .map((i) => i.name.slice(0, MAX_NAME_LENGTH))
 }
 
-/** One article's body: its yEnc header, what the first bytes are, and for par2 and RAR what's inside. Throws when it isn't yEnc. */
-export function inspect(body: Buffer): Inspection {
+/**
+ * One article's body: its yEnc header, what the first bytes are, and for par2, RAR, ZIP and 7z what's inside.
+ * Throws when it isn't yEnc. `kind` is the probe candidate's: a 7z-tail's article ends the archive.
+ */
+export function inspect(body: Buffer, kind?: string): Inspection {
   const segment = decodeBody(body)
   const result: Inspection = { yencName: segment.meta.begin.name.slice(0, MAX_NAME_LENGTH), size: segment.meta.begin.size, type: sniffContentType(segment.data) }
   // The file's first 16 KiB, or all of a smaller file.
@@ -85,6 +90,23 @@ export function inspect(body: Buffer): Inspection {
       result.passworded = info.headersEncrypted || files.some((e) => e.encrypted)
     }
   }
+  if (result.type === 'zip') {
+    const start = parseZipStart(segment.data)
+    if (start) {
+      result.entries = start.files.length
+      result.names = largestFirst(start.files)
+      result.passworded = start.encrypted
+    }
+  }
+  // 7z keeps its listing at the end: the last segment of the last volume (a 7z-tail), or a small archive whole.
+  if ((kind === '7z-tail' || result.type === '7z') && segment.offset + segment.data.length === result.size) {
+    const listing = parseSevenZipTail(segment.data)
+    if (listing) {
+      result.entries = listing.files.length
+      if (listing.files.length > 0) result.names = largestFirst(listing.files)
+      result.passworded = listing.encrypted
+    }
+  }
   return result
 }
 
@@ -97,7 +119,7 @@ export function inspect(body: Buffer): Inspection {
 export function innerName(inspections: { kind: string; result: Inspection }[], releaseName = ''): string | null {
   const of = (kind: string) => inspections.filter((i) => i.kind === kind).map((i) => i.result)
   const content = (kind: string) => of(kind).flatMap((i) => i.names ?? []).find((n) => !PACKAGING.test(n))
-  const pick = content('archive') ?? content('par2') ?? of('lone').find((i) => i.yencName && !PACKAGING.test(i.yencName))?.yencName
+  const pick = content('archive') ?? content('7z-tail') ?? content('par2') ?? of('lone').find((i) => i.yencName && !PACKAGING.test(i.yencName))?.yencName
   const name = pick?.replace(/^.*[\\/]/, '').slice(0, 255)
   // The release's own name with an extension says nothing new (a random-named file's yEnc name is mostly its random name).
   return name && !name.toLowerCase().startsWith(releaseName.toLowerCase() || '\0') ? name : null

lib/sevenzip/index.ts

@@ -0,0 +1,2 @@
+export { parseSevenZipTail, type SevenZipListing } from '#lib/sevenzip/parse'
+export { lzmaDecode, LzmaError } from '#lib/sevenzip/lzma'

lib/sevenzip/lzma.ts

@@ -0,0 +1,221 @@
+/**
+ * An LZMA decoder (raw stream, as a 7z coder stores it: the properties apart, the unpacked size known), after the
+ * LZMA SDK's reference decoder (LzmaSpec.cpp). For 7z headers: those are small, so the whole output is one buffer.
+ */
+
+const MODEL_BITS = 11
+const BIT_MODEL_TOTAL = 1 << MODEL_BITS
+const MOVE_BITS = 5
+const TOP = 1 << 24
+const POS_BITS_MAX = 4
+const STATES = 12
+const LEN_TO_POS_STATES = 4
+const ALIGN_BITS = 4
+const END_POS_MODEL_INDEX = 14
+const FULL_DISTANCES = 1 << (END_POS_MODEL_INDEX >> 1)
+const MATCH_MIN_LEN = 2
+
+export class LzmaError extends Error {}
+
+const probs = (n: number) => new Uint16Array(n).fill(BIT_MODEL_TOTAL >>> 1)
+
+class RangeDecoder {
+  private range = 0xffffffff
+  private code = 0
+
+  constructor(
+    private input: Uint8Array,
+    private pos: number
+  ) {
+    if (this.byte() !== 0) throw new LzmaError('LZMA: bad stream start')
+    for (let i = 0; i < 4; i++) this.code = ((this.code << 8) | this.byte()) >>> 0
+    if (this.code === this.range) throw new LzmaError('LZMA: corrupt stream')
+  }
+
+  private byte(): number {
+    if (this.pos >= this.input.length) throw new LzmaError('LZMA: input ended')
+    return this.input[this.pos++]
+  }
+
+  private normalize() {
+    if (this.range < TOP) {
+      this.range = (this.range << 8) >>> 0
+      this.code = ((this.code << 8) | this.byte()) >>> 0
+    }
+  }
+
+  direct(bits: number): number {
+    let result = 0
+    do {
+      this.range >>>= 1
+      this.code = (this.code - this.range) >>> 0
+      const t = this.code >>> 31 ? 0xffffffff : 0
+      this.code = (this.code + (this.range & t)) >>> 0
+      this.normalize()
+      result = ((result << 1) | (t ? 0 : 1)) >>> 0
+    } while (--bits)
+    return result
+  }
+
+  bit(p: Uint16Array, i: number): number {
+    const v = p[i]
+    const bound = ((this.range >>> MODEL_BITS) * v) >>> 0
+    let symbol: number
+    if (this.code < bound) {
+      p[i] = v + ((BIT_MODEL_TOTAL - v) >>> MOVE_BITS)
+      this.range = bound
+      symbol = 0
+    } else {
+      p[i] = v - (v >>> MOVE_BITS)
+      this.code = (this.code - bound) >>> 0
+      this.range = (this.range - bound) >>> 0
+      symbol = 1
+    }
+    this.normalize()
+    return symbol
+  }
+
+  tree(p: Uint16Array, offset: number, bits: number): number {
+    let m = 1
+    for (let i = 0; i < bits; i++) m = (m << 1) + this.bit(p, offset + m)
+    return m - (1 << bits)
+  }
+
+  reverseTree(p: Uint16Array, offset: number, bits: number): number {
+    let m = 1
+    let symbol = 0
+    for (let i = 0; i < bits; i++) {
+      const bit = this.bit(p, offset + m)
+      m = (m << 1) + bit
+      symbol |= bit << i
+    }
+    return symbol
+  }
+}
+
+class LenDecoder {
+  private choice = probs(2)
+  private low = probs((1 << POS_BITS_MAX) << 3)
+  private mid = probs((1 << POS_BITS_MAX) << 3)
+  private high = probs(1 << 8)
+
+  decode(rc: RangeDecoder, posState: number): number {
+    if (rc.bit(this.choice, 0) === 0) return rc.tree(this.low, posState << 3, 3)
+    if (rc.bit(this.choice, 1) === 0) return 8 + rc.tree(this.mid, posState << 3, 3)
+    return 16 + rc.tree(this.high, 0, 8)
+  }
+}
+
+/** Decodes `size` bytes of a raw LZMA stream with its 5 property bytes (lc/lp/pb, dictionary size). */
+export function lzmaDecode(properties: Uint8Array, input: Uint8Array, size: number): Buffer {
+  if (properties.length < 5) throw new LzmaError('LZMA: short properties')
+  let d = properties[0]
+  if (d >= 9 * 5 * 5) throw new LzmaError('LZMA: bad properties')
+  const lc = d % 9
+  d = Math.floor(d / 9)
+  const lp = d % 5
+  const pb = Math.floor(d / 5)
+  const dictSize = Math.max(properties[1] | (properties[2] << 8) | (properties[3] << 16) | (properties[4] << 24), 1 << 12) >>> 0
+
+  const out = Buffer.alloc(size)
+  let pos = 0
+  const rc = new RangeDecoder(input, 0)
+  const literals = probs(0x300 << (lc + lp))
+  const posSlot = probs(LEN_TO_POS_STATES << 6)
+  const align = probs(1 << ALIGN_BITS)
+  const posDecoders = probs(1 + FULL_DISTANCES - END_POS_MODEL_INDEX)
+  const isMatch = probs(STATES << POS_BITS_MAX)
+  const isRep = probs(STATES)
+  const isRepG0 = probs(STATES)
+  const isRepG1 = probs(STATES)
+  const isRepG2 = probs(STATES)
+  const isRep0Long = probs(STATES << POS_BITS_MAX)
+  const lenDecoder = new LenDecoder()
+  const repLenDecoder = new LenDecoder()
+
+  const distance = (len: number): number => {
+    const lenState = Math.min(len, LEN_TO_POS_STATES - 1)
+    const slot = rc.tree(posSlot, lenState << 6, 6)
+    if (slot < 4) return slot
+    const directBits = (slot >>> 1) - 1
+    let dist = ((2 | (slot & 1)) * 2 ** directBits) >>> 0
+    if (slot < END_POS_MODEL_INDEX) {
+      dist = (dist + rc.reverseTree(posDecoders, dist - slot, directBits)) >>> 0
+    } else {
+      dist = (dist + rc.direct(directBits - ALIGN_BITS) * 2 ** ALIGN_BITS) >>> 0
+      dist = (dist + rc.reverseTree(align, 0, ALIGN_BITS)) >>> 0
+    }
+    return dist
+  }
+
+  let state = 0
+  let rep0 = 0
+  let rep1 = 0
+  let rep2 = 0
+  let rep3 = 0
+  while (pos < size) {
+    const posState = pos & ((1 << pb) - 1)
+    if (rc.bit(isMatch, (state << POS_BITS_MAX) + posState) === 0) {
+      const prev = pos > 0 ? out[pos - 1] : 0
+      const base = 0x300 * (((pos & ((1 << lp) - 1)) << lc) + (prev >>> (8 - lc)))
+      let symbol = 1
+      if (state >= 7) {
+        let match = out[pos - rep0 - 1]
+        do {
+          const matchBit = (match >>> 7) & 1
+          match <<= 1
+          const bit = rc.bit(literals, base + ((1 + matchBit) << 8) + symbol)
+          symbol = (symbol << 1) | bit
+          if (matchBit !== bit) break
+        } while (symbol < 0x100)
+      }
+      while (symbol < 0x100) symbol = (symbol << 1) | rc.bit(literals, base + symbol)
+      out[pos++] = symbol - 0x100
+      state = state < 4 ? 0 : state < 10 ? state - 3 : state - 6
+      continue
+    }
+    let len: number
+    if (rc.bit(isRep, state) !== 0) {
+      if (pos === 0) throw new LzmaError('LZMA: repeat before any output')
+      if (rc.bit(isRepG0, state) === 0) {
+        if (rc.bit(isRep0Long, (state << POS_BITS_MAX) + posState) === 0) {
+          state = state < 7 ? 9 : 11
+          out[pos] = out[pos - rep0 - 1]
+          pos++
+          continue
+        }
+      } else {
+        let dist: number
+        if (rc.bit(isRepG1, state) === 0) {
+          dist = rep1
+        } else {
+          if (rc.bit(isRepG2, state) === 0) {
+            dist = rep2
+          } else {
+            dist = rep3
+            rep3 = rep2
+          }
+          rep2 = rep1
+        }
+        rep1 = rep0
+        rep0 = dist
+      }
+      len = repLenDecoder.decode(rc, posState)
+      state = state < 7 ? 8 : 11
+    } else {
+      rep3 = rep2
+      rep2 = rep1
+      rep1 = rep0
+      len = lenDecoder.decode(rc, posState)
+      state = state < 7 ? 7 : 10
+      rep0 = distance(len)
+      // The end marker: allowed only where the output is complete, which the loop already ended at.
+      if (rep0 === 0xffffffff) throw new LzmaError('LZMA: end marker before the end')
+      if (rep0 >= dictSize || rep0 >= pos) throw new LzmaError('LZMA: distance out of range')
+    }
+    len += MATCH_MIN_LEN
+    if (len > size - pos) throw new LzmaError('LZMA: match past the end')
+    for (let i = 0; i < len; i++, pos++) out[pos] = out[pos - rep0 - 1]
+  }
+  return out
+}

lib/sevenzip/parse.ts

@@ -0,0 +1,350 @@
+import { crc32 } from 'node:zlib'
+import { lzmaDecode } from '#lib/sevenzip/lzma'
+
+/**
+ * What a 7z archive's header says (its listing): read from the archive's end, where 7z keeps it, so the last
+ * segment of the last volume is enough (the `7z-tail` probe; REBUILD.md, phase 2). The header there is mostly
+ * an encoded one: a pointer to the real header, LZMA-packed just before it, or AES-encrypted (`7z -mhe`), which
+ * hides the names and means a password.
+ */
+export interface SevenZipListing {
+  /** Files, not directories, with their unpacked size (0 for an empty one). */
+  files: { name: string; size: number }[]
+  /** Entries or the header encrypted (AES). */
+  encrypted: boolean
+  /** The header itself encrypted: no names known. */
+  headerEncrypted: boolean
+}
+
+const AES = '06f10701'
+const LZMA = '030101'
+/** A header bigger than this isn't unpacked (headers list names; 64 MiB is ~a million files). */
+const MAX_HEADER = 64 * 1024 * 1024
+
+const ID = {
+  end: 0x00,
+  header: 0x01,
+  archiveProperties: 0x02,
+  additionalStreamsInfo: 0x03,
+  mainStreamsInfo: 0x04,
+  filesInfo: 0x05,
+  packInfo: 0x06,
+  unpackInfo: 0x07,
+  subStreamsInfo: 0x08,
+  size: 0x09,
+  crc: 0x0a,
+  folder: 0x0b,
+  codersUnpackSize: 0x0c,
+  numUnpackStream: 0x0d,
+  emptyStream: 0x0e,
+  emptyFile: 0x0f,
+  name: 0x11,
+  encodedHeader: 0x17,
+  dummy: 0x19,
+}
+
+class Malformed extends Error {}
+
+interface Coder {
+  id: string
+  properties: Uint8Array
+  inStreams: number
+  outStreams: number
+}
+interface Folder {
+  coders: Coder[]
+  bindOut: Set<number>
+  unpackSizes: number[]
+  crc?: number
+}
+interface StreamsInfo {
+  packPos: number
+  packSizes: number[]
+  folders: Folder[]
+  /** Per folder, how many files' streams it holds, and every stream's size in order. */
+  streamsPerFolder: number[]
+  streamSizes: number[]
+}
+
+class Reader {
+  constructor(
+    private buf: Uint8Array,
+    public pos = 0
+  ) {}
+
+  get done() {
+    return this.pos >= this.buf.length
+  }
+
+  byte(): number {
+    if (this.pos >= this.buf.length) throw new Malformed('7z: header ended')
+    return this.buf[this.pos++]
+  }
+
+  bytes(n: number): Uint8Array {
+    if (n < 0 || this.pos + n > this.buf.length) throw new Malformed('7z: header ended')
+    const out = this.buf.subarray(this.pos, this.pos + n)
+    this.pos += n
+    return out
+  }
+
+  /** 7z's variable-length number: the first byte's high bits say how many bytes follow. */
+  number(): number {
+    const first = this.byte()
+    let mask = 0x80
+    let value = 0
+    for (let i = 0; i < 8; i++) {
+      if ((first & mask) === 0) {
+        value += (first & (mask - 1)) * 2 ** (8 * i)
+        break
+      }
+      value += this.byte() * 2 ** (8 * i)
+      mask >>>= 1
+    }
+    if (value > Number.MAX_SAFE_INTEGER) throw new Malformed('7z: number too large')
+    return value
+  }
+
+  uint32(): number {
+    const b = this.bytes(4)
+    return (b[0] | (b[1] << 8) | (b[2] << 16) | (b[3] << 24)) >>> 0
+  }
+
+  bits(n: number): boolean[] {
+    const out: boolean[] = []
+    let byte = 0
+    for (let i = 0; i < n; i++) {
+      if (i % 8 === 0) byte = this.byte()
+      out.push((byte & (0x80 >>> i % 8)) !== 0)
+    }
+    return out
+  }
+
+  /** "All defined" or a bit vector, then a CRC per defined item. */
+  digests(n: number): (number | undefined)[] {
+    const allDefined = this.byte() !== 0
+    const defined = allDefined ? Array(n).fill(true) : this.bits(n)
+    return defined.map((d) => (d ? this.uint32() : undefined))
+  }
+
+  expect(id: number) {
+    if (this.byte() !== id) throw new Malformed(`7z: expected property ${id}`)
+  }
+}
+
+/** Counts that come from the data: a garbage position makes huge ones, which shouldn't allocate. */
+function count(n: number, max = 1_000_000): number {
+  if (n > max) throw new Malformed('7z: implausible count')
+  return n
+}
+
+function readFolder(r: Reader): Folder {
+  const coders: Coder[] = []
+  const numCoders = count(r.number(), 64)
+  if (numCoders === 0) throw new Malformed('7z: folder without coders')
+  for (let i = 0; i < numCoders; i++) {
+    const flags = r.byte()
+    if (flags & 0x80) throw new Malformed('7z: alternative coder methods')
+    const id = Buffer.from(r.bytes(flags & 0x0f)).toString('hex')
+    const complex = (flags & 0x10) !== 0
+    const inStreams = complex ? count(r.number(), 64) : 1
+    const outStreams = complex ? count(r.number(), 64) : 1
+    const properties = flags & 0x20 ? r.bytes(count(r.number(), 1 << 16)) : new Uint8Array(0)
+    coders.push({ id, properties, inStreams, outStreams })
+  }
+  const totalOut = coders.reduce((n, c) => n + c.outStreams, 0)
+  const totalIn = coders.reduce((n, c) => n + c.inStreams, 0)
+  const bindOut = new Set<number>()
+  for (let i = 0; i < totalOut - 1; i++) {
+    r.number()
+    bindOut.add(r.number())
+  }
+  const packed = totalIn - (totalOut - 1)
+  if (packed < 1) throw new Malformed('7z: folder without packed streams')
+  if (packed > 1) for (let i = 0; i < packed; i++) r.number()
+  return { coders, bindOut, unpackSizes: [] }
+}
+
+/** The folder's output: the one out stream no bind pair consumes. */
+function unpackSize(folder: Folder): number {
+  for (let i = folder.unpackSizes.length - 1; i >= 0; i--) if (!folder.bindOut.has(i)) return folder.unpackSizes[i]
+  return 0
+}
+
+function readStreamsInfo(r: Reader): StreamsInfo {
+  const info: StreamsInfo = { packPos: 0, packSizes: [], folders: [], streamsPerFolder: [], streamSizes: [] }
+  let id = r.byte()
+  if (id === ID.packInfo) {
+    info.packPos = r.number()
+    const n = count(r.number())
+    for (id = r.byte(); id !== ID.end; id = r.byte()) {
+      if (id === ID.size) for (let i = 0; i < n; i++) info.packSizes.push(r.number())
+      else if (id === ID.crc) r.digests(n)
+      else throw new Malformed('7z: unexpected property in pack info')
+    }
+    id = r.byte()
+  }
+  if (id === ID.unpackInfo) {
+    r.expect(ID.folder)
+    const n = count(r.number())
+    if (r.byte() !== 0) throw new Malformed('7z: external folders')
+    for (let i = 0; i < n; i++) info.folders.push(readFolder(r))
+    r.expect(ID.codersUnpackSize)
+    for (const f of info.folders) for (const c of f.coders) for (let i = 0; i < c.outStreams; i++) f.unpackSizes.push(r.number())
+    for (id = r.byte(); id !== ID.end; id = r.byte()) {
+      if (id === ID.crc) r.digests(n).forEach((crc, i) => (info.folders[i].crc = crc))
+      else throw new Malformed('7z: unexpected property in unpack info')
+    }
+    id = r.byte()
+  }
+  info.streamsPerFolder = info.folders.map(() => 1)
+  if (id === ID.subStreamsInfo) {
+    id = r.byte()
+    if (id === ID.numUnpackStream) {
+      info.streamsPerFolder = info.folders.map(() => count(r.number()))
+      id = r.byte()
+    }
+    const hasSizes = id === ID.size
+    info.folders.forEach((f, i) => {
+      const n = info.streamsPerFolder[i]
+      if (n === 0) return
+      let sum = 0
+      for (let j = 0; j < n - 1 && hasSizes; j++) {
+        const size = r.number()
+        info.streamSizes.push(size)
+        sum += size
+      }
+      info.streamSizes.push(unpackSize(f) - sum)
+    })
+    if (hasSizes) id = r.byte()
+    while (id !== ID.end) {
+      if (id === ID.crc) {
+        // CRCs for the streams whose folder had none (a folder of one stream with a CRC has its own).
+        const unknown = info.folders.reduce((n, f, i) => n + (info.streamsPerFolder[i] === 1 && f.crc !== undefined ? 0 : info.streamsPerFolder[i]), 0)
+        r.digests(unknown)
+      } else {
+        throw new Malformed('7z: unexpected property in substreams info')
+      }
+      id = r.byte()
+    }
+    id = r.byte()
+  } else {
+    info.streamSizes = info.folders.map(unpackSize)
+  }
+  if (id !== ID.end) throw new Malformed('7z: streams info not ended')
+  return info
+}
+
+function readFilesInfo(r: Reader, streams: StreamsInfo | null): { name: string; size: number }[] {
+  const n = count(r.number())
+  let emptyStream: boolean[] = Array(n).fill(false)
+  let emptyFile: boolean[] = []
+  let names: string[] = []
+  for (let id = r.byte(); id !== ID.end; id = r.byte()) {
+    const size = r.number()
+    const end = r.pos + size
+    if (id === ID.emptyStream) {
+      emptyStream = r.bits(n)
+    } else if (id === ID.emptyFile) {
+      emptyFile = r.bits(emptyStream.filter(Boolean).length)
+    } else if (id === ID.name) {
+      if (r.byte() !== 0) throw new Malformed('7z: external names')
+      const text = Buffer.from(r.bytes(size - 1)).toString('utf16le')
+      names = text.split('\0').slice(0, n)
+    } else if (id !== ID.dummy && id > 0x19) {
+      throw new Malformed('7z: unknown file property')
+    }
+    r.pos = end
+  }
+  if (names.length !== n) throw new Malformed('7z: names missing')
+  const out: { name: string; size: number }[] = []
+  let stream = 0
+  let empty = 0
+  for (let i = 0; i < n; i++) {
+    if (!emptyStream[i]) {
+      out.push({ name: names[i], size: streams?.streamSizes[stream++] ?? 0 })
+      continue
+    }
+    // An empty stream is a directory unless it's marked an empty file.
+    if (emptyFile[empty++]) out.push({ name: names[i], size: 0 })
+  }
+  return out
+}
+
+function readHeader(r: Reader): SevenZipListing {
+  let id = r.byte()
+  if (id === ID.archiveProperties) {
+    for (let type = r.byte(); type !== 0; type = r.byte()) r.bytes(r.number())
+    id = r.byte()
+  }
+  if (id === ID.additionalStreamsInfo) {
+    readStreamsInfo(r)
+    id = r.byte()
+  }
+  let streams: StreamsInfo | null = null
+  if (id === ID.mainStreamsInfo) {
+    streams = readStreamsInfo(r)
+    id = r.byte()
+  }
+  let files: { name: string; size: number }[] = []
+  if (id === ID.filesInfo) {
+    files = readFilesInfo(r, streams)
+    id = r.byte()
+  }
+  if (id !== ID.end) throw new Malformed('7z: header not ended')
+  const encrypted = (streams?.folders ?? []).some((f) => f.coders.some((c) => c.id === AES))
+  return { files, encrypted, headerEncrypted: false }
+}
+
+/**
+ * The header that ends exactly at `end` in `data`, starting at `start`: a plain one, or an encoded one whose packed
+ * data lies just before it (where 7z writes it). Throws when it isn't one.
+ */
+function headerAt(data: Uint8Array, start: number, end: number): SevenZipListing {
+  const r = new Reader(data.subarray(0, end), start)
+  const id = r.byte()
+  if (id === ID.header) {
+    const listing = readHeader(r)
+    if (!r.done) throw new Malformed('7z: bytes after the header')
+    return listing
+  }
+  if (id !== ID.encodedHeader) throw new Malformed('7z: not a header')
+  const info = readStreamsInfo(r)
+  if (!r.done) throw new Malformed('7z: bytes after the encoded header')
+  if (info.folders.length !== 1 || info.packSizes.length < 1) throw new Malformed('7z: unexpected encoded header')
+  const folder = info.folders[0]
+  if (folder.coders.some((c) => c.id === AES)) return { files: [], encrypted: true, headerEncrypted: true }
+  if (folder.coders.length !== 1 || folder.coders[0].id !== LZMA) throw new Malformed(`7z: header coder ${folder.coders[0].id} not supported`)
+  const packSize = info.packSizes[0]
+  const size = unpackSize(folder)
+  if (packSize > start || size > MAX_HEADER) throw new Malformed('7z: packed header not in the data')
+  const header = lzmaDecode(folder.coders[0].properties, data.subarray(start - packSize, start), size)
+  if (folder.crc !== undefined && crc32(header) >>> 0 !== folder.crc) throw new Malformed('7z: header CRC mismatch')
+  return headerAt(header, 0, header.length)
+}
+
+/**
+ * The listing of the 7z archive that `data` is the end of (the last segment of its last volume, or a whole small
+ * archive); null when no header ends there.
+ */
+export function parseSevenZipTail(data: Uint8Array): SevenZipListing | null {
+  const end = data.length
+  // An encoded header is a few dozen bytes; a plain one (7z -mhc=off) can be large.
+  for (let start = end - 2; start >= Math.max(0, end - 1024); start--) {
+    if (data[start] !== ID.encodedHeader || data[start + 1] !== ID.packInfo) continue
+    try {
+      return headerAt(data, start, end)
+    } catch {
+      // Not a header here (any byte can look like the start of one): the next position.
+    }
+  }
+  for (let start = end - 2; start >= 0; start--) {
+    if (data[start] !== ID.header || ![ID.archiveProperties, ID.additionalStreamsInfo, ID.mainStreamsInfo, ID.filesInfo, ID.end].includes(data[start + 1])) continue
+    try {
+      return headerAt(data, start, end)
+    } catch {
+      // Not a header here (any byte can look like the start of one): the next position.
+    }
+  }
+  return null
+}

lib/zip/index.ts

@@ -0,0 +1 @@
+export { parseZipStart, type ZipStart } from '#lib/zip/parse'

lib/zip/parse.ts

@@ -0,0 +1,50 @@
+/**
+ * The entries a ZIP's start shows: its local file headers, one before each entry's data, as far as the data
+ * holds them (the first segment of a .zip; REBUILD.md, phase 2). The full list is in the central directory at
+ * the end; the start names the first entries and says whether they're encrypted, as a RAR's first volume does.
+ */
+export interface ZipStart {
+  files: { name: string; size: number }[]
+  encrypted: boolean
+}
+
+const LOCAL = 0x04034b50
+/** Traditional PKWARE encryption (bit 0 of the flags), or WinZip AES (method 99). */
+const ENCRYPTED_FLAG = 0x1
+const DATA_DESCRIPTOR_FLAG = 0x8
+const AES_METHOD = 99
+const MAX_ENTRIES = 10_000
+
+export function parseZipStart(data: Buffer): ZipStart | null {
+  if (data.length < 30 || data.readUInt32LE(0) !== LOCAL) return null
+  const result: ZipStart = { files: [], encrypted: false }
+  let pos = 0
+  while (pos + 30 <= data.length && data.readUInt32LE(pos) === LOCAL && result.files.length < MAX_ENTRIES) {
+    const flags = data.readUInt16LE(pos + 6)
+    const method = data.readUInt16LE(pos + 8)
+    let compressed = data.readUInt32LE(pos + 18)
+    let size = data.readUInt32LE(pos + 22)
+    const nameLength = data.readUInt16LE(pos + 26)
+    const extraLength = data.readUInt16LE(pos + 28)
+    const nameEnd = pos + 30 + nameLength
+    if (nameEnd > data.length) break
+    // Bit 11: UTF-8 names; others are mostly CP437, read as latin1.
+    const name = data.toString(flags & 0x800 ? 'utf8' : 'latin1', pos + 30, nameEnd)
+    // Zip64: the real sizes in extra field 0x0001.
+    for (let e = nameEnd; e + 4 <= Math.min(nameEnd + extraLength, data.length); ) {
+      const id = data.readUInt16LE(e)
+      const length = data.readUInt16LE(e + 2)
+      if (id === 0x0001 && e + 4 + length <= data.length && length >= 16) {
+        size = Number(data.readBigUInt64LE(e + 4))
+        compressed = Number(data.readBigUInt64LE(e + 12))
+      }
+      e += 4 + length
+    }
+    if (flags & ENCRYPTED_FLAG || method === AES_METHOD) result.encrypted = true
+    if (!name.endsWith('/')) result.files.push({ name, size })
+    // Sizes after the data (a streamed zip): where the next header starts isn't known.
+    if (flags & DATA_DESCRIPTOR_FLAG) break
+    pos = nameEnd + extraLength + compressed
+  }
+  return result.files.length > 0 || result.encrypted ? result : null
+}

tests/unit/edge/range_indexer.spec.ts

@@ -55,6 +55,20 @@ test.group('edge / RangeIndexer', () => {
     assert.equal(batch.next, 1_000_001)
   })
 
+  test("archive candidates: a split 7z's start and its highest volume's end, an unsplit 7z's start and end, a ZIP's start", ({ assert }) => {
+    const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1_000_000, rules, edgeArticles: 10 })
+    indexer.add([
+      ...post(100, 'Split.Seven.7z.001', 2, { counter: 'Split.Seven [1/3]' }),
+      ...post(110, 'Split.Seven.7z.003', 2, { counter: 'Split.Seven [3/3]' }),
+      ...post(120, 'Split.Seven.7z.002', 2, { counter: 'Split.Seven [2/3]' }),
+      ...post(200, 'Whole.Seven.7z', 3, { counter: 'Whole.Seven [1/1]' }),
+      ...post(300, 'Some.Zip.zip', 2, { counter: 'Some.Zip [1/1]' }),
+    ], 200_000)
+    indexer.finish()
+    const got = indexer.take().candidates.map((c) => `${c.kind} ${c.file}`).sort()
+    assert.deepEqual(got, ['7z-tail Split.Seven.7z.003', '7z-tail Whole.Seven.7z', 'archive Some.Zip.zip', 'archive Split.Seven.7z.001', 'archive Whole.Seven.7z'])
+  })
+
   test('files the edges cut leave as fragments; one missing parts in the middle is only counted', ({ assert }) => {
     const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1_000_000, rules, edgeArticles: 1000 })
     indexer.add([

tests/unit/probe/inspect.spec.ts

@@ -1,5 +1,6 @@
 import { test } from '@japa/runner'
 import { createHash } from 'node:crypto'
+import { readFileSync } from 'node:fs'
 import { crc32 } from 'node:zlib'
 import yencode from 'yencode'
 import { crc32Hex } from '#lib/yenc/index'
@@ -148,4 +149,45 @@ test.group('probe / innerName', () => {
     // Nor does packaging: a lone par2 volume.
     assert.isNull(innerName([{ kind: 'lone', result: { yencName: 'a1b2.vol007+08.par2', size: 1, type: 'par2' } }], 'x9y8'))
   })
+
+  test("a 7z-tail: the listing from the last segment of the last volume; one that isn't the last segment: none", ({ assert }) => {
+    const tail = readFileSync(new URL('../../fixtures/sevenzip/split-last-volume.tail', import.meta.url))
+    // The volume's last 8,000 bytes as its third part, of a volume 1,000,000 bytes long.
+    const last = tail.subarray(tail.length - 8000)
+    const part = (data: Buffer, begin: number) =>
+      Buffer.from(
+        [`=ybegin part=3 total=3 line=128 size=1000000 name=x.7z.004`, `=ypart begin=${begin} end=${begin + data.length - 1}`, yencode.encode(data).toString('latin1'), `=yend size=${data.length} part=3 pcrc32=${crc32Hex(data)}`].join('\r\n'),
+        'latin1'
+      )
+    const result = inspect(part(last, 1_000_000 - 8000 + 1), '7z-tail')
+    assert.equal(result.entries, 4)
+    assert.deepEqual(result.names?.[0], 'Some.Movie.2020.1080p.BluRay.x264-GRP/some.movie.2020.1080p.bluray.x264-grp.mkv')
+    assert.isFalse(result.passworded)
+    assert.isUndefined(inspect(part(last, 1), '7z-tail').names)
+    const encrypted = readFileSync(new URL('../../fixtures/sevenzip/header-encrypted.tail', import.meta.url))
+    const hidden = inspect(part(encrypted.subarray(encrypted.length - 8000), 1_000_000 - 8000 + 1), '7z-tail')
+    assert.isTrue(hidden.passworded)
+    assert.equal(hidden.entries, 0)
+    assert.isUndefined(hidden.names)
+    // A small 7z whole in one article, probed as an archive start.
+    assert.deepEqual(inspect(article(readFileSync(new URL('../../fixtures/sevenzip/tiny.7z', import.meta.url)), 'x.7z'), 'archive').names, ['b.nfo', 'a.txt'])
+  })
+
+  test('a ZIP start: the names of its first entries, and whether they are encrypted', ({ assert }) => {
+    const local = (name: string, data: Buffer, flags = 0) => {
+      const header = Buffer.alloc(30)
+      header.writeUInt32LE(0x04034b50, 0)
+      header.writeUInt16LE(flags, 6)
+      header.writeUInt32LE(data.length, 18)
+      header.writeUInt32LE(data.length, 22)
+      header.writeUInt16LE(Buffer.byteLength(name), 26)
+      return Buffer.concat([header, Buffer.from(name), data])
+    }
+    const zip = Buffer.concat([local('Album/', Buffer.alloc(0)), local('Album/01 - Track.flac', Buffer.alloc(3000, 1)), local('Album/cover.jpg', Buffer.alloc(500, 2))])
+    const plain = inspect(article(zip, 'album.zip'))
+    assert.equal(plain.type, 'zip')
+    assert.deepEqual(plain.names, ['Album/01 - Track.flac', 'Album/cover.jpg'])
+    assert.isFalse(plain.passworded)
+    assert.isTrue(inspect(article(local('secret.mkv', Buffer.alloc(100), 0x1), 'x.zip')).passworded)
+  })
 })

tests/unit/probe/lzma.spec.ts

@@ -0,0 +1,20 @@
+import { test } from '@japa/runner'
+import { readFileSync } from 'node:fs'
+import { lzmaDecode, LzmaError } from '#lib/sevenzip/lzma'
+
+const fixture = (name: string) => readFileSync(new URL(`../../fixtures/sevenzip/${name}`, import.meta.url))
+
+test.group('probe / LZMA', () => {
+  test('decodes a stream Python made (.lzma: 5 property bytes, the size, the raw stream)', ({ assert }) => {
+    const alone = fixture('sample.lzma')
+    const expected = fixture('sample.bin')
+    const decoded = lzmaDecode(alone.subarray(0, 5), alone.subarray(13), expected.length)
+    assert.isTrue(decoded.equals(expected))
+  })
+
+  test('a cut-off or damaged stream throws LzmaError', ({ assert }) => {
+    const alone = fixture('sample.lzma')
+    const size = fixture('sample.bin').length
+    assert.throws(() => lzmaDecode(alone.subarray(0, 5), alone.subarray(13, 200), size), LzmaError)
+  })
+})

tests/unit/probe/sevenzip.spec.ts

@@ -0,0 +1,45 @@
+import { test } from '@japa/runner'
+import { readFileSync } from 'node:fs'
+import { parseSevenZipTail } from '#lib/sevenzip/index'
+
+const fixture = (name: string) => readFileSync(new URL(`../../fixtures/sevenzip/${name}`, import.meta.url))
+const DIR = 'Some.Movie.2020.1080p.BluRay.x264-GRP'
+
+test.group('probe / 7z listing from the archive end', () => {
+  test('an LZMA-packed header (7z default): files with sizes, directories left out', ({ assert }) => {
+    const listing = parseSevenZipTail(fixture('plain.tail'))
+    assert.deepEqual(listing, {
+      files: [
+        { name: `${DIR}/empty.txt`, size: 0 },
+        { name: `${DIR}/Sample/sample.mkv`, size: 20000 },
+        { name: `${DIR}/grp.nfo`, size: 4 },
+        { name: `${DIR}/some.movie.2020.1080p.bluray.x264-grp.mkv`, size: 300000 },
+      ],
+      encrypted: false,
+      headerEncrypted: false,
+    })
+  })
+
+  test('an uncompressed header (7z -mhc=off) and the last volume of a split archive', ({ assert }) => {
+    for (const name of ['uncompressed-header.tail', 'split-last-volume.tail']) {
+      const listing = parseSevenZipTail(fixture(name))!
+      assert.lengthOf(listing.files, 4, name)
+      assert.isFalse(listing.encrypted, name)
+    }
+  })
+
+  test('encrypted entries: names listed, encrypted; an encrypted header (7z -mhe): no names, encrypted', ({ assert }) => {
+    const files = parseSevenZipTail(fixture('files-encrypted.tail'))!
+    assert.lengthOf(files.files, 4)
+    assert.isTrue(files.encrypted)
+    assert.isFalse(files.headerEncrypted)
+    assert.deepEqual(parseSevenZipTail(fixture('header-encrypted.tail')), { files: [], encrypted: true, headerEncrypted: true })
+  })
+
+  test('a whole small archive; not the end of an archive: null', ({ assert }) => {
+    assert.deepEqual(parseSevenZipTail(fixture('tiny.7z'))?.files.map((f) => f.name), ['a.txt', 'b.nfo'])
+    // The end cut off, or data that isn't 7z at all.
+    assert.isNull(parseSevenZipTail(fixture('plain.tail').subarray(0, 30000)))
+    assert.isNull(parseSevenZipTail(fixture('sample.bin')))
+  })
+})