Single-archive rules: stub archives and nonsense pieces dropped at the edge

The judge gets each file's articles seen and bytes, and whether the window
closed on the release. A settled release of one unsplit archive posted to 2+
groups is dropped as a stub archive when its articles are <= 256 KiB with the
release >= 1 MB, or it is in 4+ groups, or by a webmail poster (those two
under 100 MB); releases touching music, e-book, comics, tabs or fonts groups
are exempt. A one-article archive of 100 kB-1 MB under a release-like,
unscrambled name without spaces or an e-book format is dropped as a nonsense
piece. Both switched by the rule set (dropStubArchives, dropNonsensePieces),
mirrored in lib/rules, sampled like every drop (LOG.md (123)-(127)).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

tests/unit/rules/rule_set.spec.ts

@@ -9,6 +9,18 @@ const file = (name: string, totalParts: number, firstMessageId: string, group =
   groups: [group],
   firstMessageId,
   poster,
+  segments: totalParts,
+  bytes: totalParts * 700_000,
+})
+/** A single archive of `segments` articles and `bytes` in all, posted to `groups` groups. */
+const archive = (name: string, poster: string, groups: number, segments: number, bytes: number, firstMessageId = NYUU) => ({
+  name,
+  totalParts: segments,
+  groups: Array.from({ length: groups }, (_, i) => `alt.binaries.g${i}`),
+  firstMessageId,
+  poster,
+  segments,
+  bytes,
 })
 const NGPOST = 'b94268bc702040f7b811d5318f727e4f@ngPost'
 const NYUU = 'FmFwIaTpGgUiSfYcMwFlMeRo-1790637260478@nyuu'
@@ -50,6 +62,48 @@ test.group('rules / verdicts', () => {
     assert.include(rules.judge('k', [file('Hs7dKq2LmZ9xWv3RtYp1Qa.part01.rar', 50, NYUU, 'alt.binaries.misc')]), { rule: 'garbage', key: 'nyuu alt.binaries.misc' })
     assert.deepEqual(rules.judge('k', [file('Hs7dKq2LmZ9xWv3RtYp1Qa.part01.rar', 50, NYUU)]), { rule: null })
   })
+
+  test('stub archives: a settled single archive in 2+ groups with 250 kB articles, or 4+ groups, or a webmail poster', ({ assert }) => {
+    // Power-Post's 250 kB articles, two groups, 12 MB: the 2016 wave; the article-size leg alone without webmail.
+    assert.include(rules.judge('k', [archive('Chat Watch 1.2.1.zip', 'jahnunsinos007@gmail.com (Jahnunsinos007)', 2, 48, 12_000_000)]), { rule: 'stub-archive', key: 'AW' })
+    assert.include(rules.judge('k', [archive('Some.Movie.2014.720p.BluRay-GRP.rar', 'Yenc@power-post.org (Yenc-PP-A&A)', 2, 48, 12_000_000)]), { rule: 'stub-archive', key: 'A' })
+    // Five groups, 319 kB in two articles: the 2015 a.b.cracks wave (under 1 MB, so the groups leg alone).
+    assert.include(rules.judge('k', [archive('Big Hero 6 (2014) 720p BDRip [COMPRESSED].rar', 'Yenc@power-post.org', 5, 2, 319_000)]), { rule: 'stub-archive', key: 'X' })
+    // A webmail poster with 650 kB articles: the 2014 "leaked Sex Video" wave, but only under 100 MB without the article-size leg.
+    assert.include(rules.judge('k', [archive('Leaked Sex Video.rar', 'first.last88@gmail.com', 2, 100, 65_000_000)]), { rule: 'stub-archive', key: 'W' })
+    assert.deepEqual(rules.judge('k', [archive('Leaked Sex Video.rar', 'first.last88@gmail.com', 2, 400, 260_000_000)]), { rule: null })
+    // Not settled: a par2 can still join.
+    assert.deepEqual(rules.judge('k', [archive('Chat Watch 1.2.1.zip', 'jahnunsinos007@gmail.com', 2, 48, 12_000_000)], false), { rule: null })
+  })
+
+  test('stub archives: small, single-group, split and large hash-named archives are kept', ({ assert }) => {
+    // An e-book: a one- or two-article release always has small articles (LOG.md (126)).
+    assert.deepEqual(rules.judge('k', [archive('Maeve Binchy - Tara Road (epub).rar', 'kie@home.now (KiE)', 2, 2, 521_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Chat Watch 1.2.1.zip', 'jahnunsinos007@gmail.com', 1, 48, 12_000_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Some.Movie.2014.720p.BluRay-GRP.rar', 'poster@example.org', 2, 100, 70_000_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Some.Movie.2014.part01.rar', 'a@gmail.com', 2, 48, 12_000_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('cbcd32359460df1fa9b7d01d8720.rar', 'b648de0d1c0f7a9a77be273d@gmail.com', 2, 3163, 2_340_000_000)]), { rule: null })
+    // A karaoke zip crossposted to a.b.test with Power-Post's articles: its group exempts it (LOG.md (127)).
+    assert.deepEqual(rules.judge('k', [{ ...archive('KV-1055806 - Walker Hayes - U Gurl.zip', 'home@home.com (TexasDj)', 2, 13, 3_300_000), groups: ['alt.binaries.sounds.karaoke', 'alt.binaries.test'] }]), { rule: null })
+    // A rar with its par2 is no single archive.
+    assert.deepEqual(rules.judge('k', [archive('Chat Watch 1.2.1.zip', 'a@gmail.com', 2, 48, 12_000_000), file('Chat Watch 1.2.1.par2', 1, NYUU)]), { rule: null })
+    const off = new RuleSet({ ...DEFAULT_RULES, dropStubArchives: false, samplePercent: 0, priorities: {}, droppedSignatures: [] })
+    assert.deepEqual(off.judge('k', [archive('Chat Watch 1.2.1.zip', 'jahnunsinos007@gmail.com', 2, 48, 12_000_000)]), { rule: null })
+  })
+
+  test('nonsense pieces: one article of 100 kB to 1 MB under a release-like name', ({ assert }) => {
+    assert.include(rules.judge('k', [archive('Some.Show.S01E01.1080p.WEB-DL.rar', 'poster@example.org', 1, 1, 790_000)]), { rule: 'nonsense-piece', key: 'nyuu' })
+    // A 3 kB cue/log sidecar rar with a year in its name: under the floor. A book (spaces, a format). Two articles, a plain name, a scrambled one: not this rule.
+    assert.deepEqual(rules.judge('k', [archive('The Smiths-the queen is dead(Remaster)(2011).rar', 'Yenc@power-post.org (Sir Cedrik)', 1, 1, 3_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Kevin Ashman - [Roman 02] - The Rise of Caratacus (2020) (epub).rar', 'fake@address.com (Psychopath)', 2, 1, 303_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('One.Wrong.Turn.Deanna.Lynn.Sletten.epub.rar', 'fake@address.com (Psychopath)', 1, 1, 382_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Vieweg.Teubner.Verlag.-.Numerische.Mathematik.2011.German.RETAIL.eBook-BitBook.rar', 'saggir@domain.com', 1, 1, 113_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('Some.Show.S01E01.1080p.WEB-DL.rar', 'poster@example.org', 1, 2, 790_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('holiday snaps.rar', 'poster@example.org', 1, 1, 790_000)]), { rule: null })
+    assert.deepEqual(rules.judge('k', [archive('nYDeXeF49dieZ1J7flK-JFzZ3j.rar', 'poster@example.org', 1, 1, 790_000)]), { rule: null })
+    const off = new RuleSet({ ...DEFAULT_RULES, dropNonsensePieces: false, samplePercent: 0, priorities: {}, droppedSignatures: [] })
+    assert.deepEqual(off.judge('k', [archive('Some.Show.S01E01.1080p.WEB-DL.rar', 'poster@example.org', 1, 1, 790_000)]), { rule: null })
+  })
 })
 
 test.group('rules / upload tools', () => {