Search: a word with a leading ^ matches at a word's start only

"^zed" finds "Zed Dead", "The_Zed_Files", not "Facialized": a regex on
release_texts, (^|[^[:alnum:]]) before the word, which the trigram index
serves (homelab: 551 texts for ^zed against 6,606 for zed, 35 ms warm).
Words without ^ match anywhere as before; the search box says so.

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

app/services/search_service.ts

@@ -85,6 +85,19 @@ function contains(word: string): string {
   return `%${word.replace(/[\\%_]/g, (c) => `\\${c}`)}%`
 }
 
+/**
+ * A search word's condition on release_texts: anywhere in a text (ILIKE), or with a leading "^" at a word's start, the
+ * text's or after a character that's no letter or digit ("^zed" finds "Zed.Dead", "The_Zed", not "Facialized"). Both
+ * use the trigram index.
+ */
+function wordMatch(word: string): { sql: string; binding: string } {
+  if (word.startsWith('^') && word.length > 1) {
+    const rest = word.slice(1).replace(/[\\^$.|?*+()[\]{}]/g, (c) => `\\${c}`)
+    return { sql: 't.text ~* ?', binding: `(^|[^[:alnum:]])${rest}` }
+  }
+  return { sql: 't.text ILIKE ?', binding: contains(word) }
+}
+
 /** Searching and browsing the catalog, for the web interface and Newznab. */
 class SearchService {
   async search(params: SearchParams) {
@@ -93,10 +106,12 @@ class SearchService {
     if (!params.judged) where.push('NOT EXISTS (SELECT 1 FROM release_verdicts v WHERE v.release_id = r.id)')
     const bindings: unknown[] = []
     // Every word in one of the release's texts (its name, the names the prober found inside; release_texts, by its
-    // trigram index, which yields ids: never an OR across the two tables); "The.Block.AU" and "the block au" alike.
+    // trigram index, which yields ids: never an OR across the two tables); "The.Block.AU" and "the block au" alike;
+    // "^zed" only at a word's start.
     for (const word of (params.q ?? '').split(/[\s._-]+/).filter(Boolean).slice(0, 8)) {
-      where.push('r.id IN (SELECT t.release_id FROM release_texts t WHERE t.text ILIKE ?)')
-      bindings.push(contains(word))
+      const match = wordMatch(word)
+      where.push(`r.id IN (SELECT t.release_id FROM release_texts t WHERE ${match.sql})`)
+      bindings.push(match.binding)
     }
     if (params.readable) where.push('(r.readable OR r.inner_name IS NOT NULL)')
     if (params.complete) where.push('r.complete')

public/index.html

@@ -22,7 +22,7 @@
           <label class="search-box">
             <svg aria-hidden="true" viewBox="0 0 24 24"><circle cx="11" cy="11" r="7" /><path d="m20 20-3.5-3.5" /></svg>
             <input id="q" type="search" autocomplete="off" spellcheck="false"
-                   placeholder="Search release names…" aria-label="Search" />
+                   placeholder="Search release names… (^word: at a word's start)" aria-label="Search" />
             <kbd aria-hidden="true">/</kbd>
           </label>
           <label class="select">

tests/functional/releases_api.spec.ts

@@ -138,4 +138,26 @@ test.group('Releases API', (group) => {
     const list = (await client.get('/api/v1/releases?q=locked movie')).body() as { releases: { passwordKnown: boolean }[] }
     assert.isTrue(list.releases[0].passwordKnown)
   })
+
+  test('a word with a leading ^ matches at a word start only; without it anywhere', async ({ client, assert }) => {
+    const [g] = await db.table('groups').insert({ name: GROUP, priority: 1 }).returning('id')
+    const [n] = await db.table('nodes').insert({ name: 'api-node' }).returning('id')
+    const [r] = await db.table('ranges').insert({ group_id: g.id, start_id: 1, end_id: 1000, next_id: 1, status: 'leased', node_id: n.id }).returning('id')
+    const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1000, rules: { ...DEFAULT_RULES, samplePercent: 0, droppedSignatures: [], priorities: { [GROUP]: 1 } } })
+    indexer.add([
+      ...file('Zed.Dead.2019.1080p.mkv', 'Zed.Dead.2019 [1/1]', 2, 100),
+      ...file('The_Zed_Files.S01E01.mkv', 'The_Zed_Files.S01E01 [1/1]', 2, 200),
+      ...file('Babe.Facialized.2017.mkv', 'Babe.Facialized.2017 [1/1]', 2, 300),
+    ], 1001)
+    indexer.finish()
+    await BatchStore.store(Number(r.id), Number(n.id), indexer.take())
+
+    const names = async (q: string) =>
+      ((await client.get(`/api/v1/releases?q=${encodeURIComponent(q)}`)).body() as { releases: { name: string }[] }).releases.map((x) => x.name).sort()
+    assert.lengthOf(await names('zed'), 3)
+    assert.deepEqual(await names('^zed'), ['The_Zed_Files S01E01', 'Zed Dead 2019'])
+    assert.deepEqual(await names('^zed dead'), ['Zed Dead 2019'])
+    // Regex characters in the word are literal.
+    assert.deepEqual(await names('^ze+d'), [])
+  })
 })