perf: round 15 — grouped-listing O(N²) rebucket, exif/reseed allocs, tantivy zero-hit snippet skip

Benchmark-gated, same rule as rounds 2–14: every change ships with a
BEFORE/AFTER benchmark and an equivalence/safety gate; an AFTER that doesn't
beat its BEFORE is rolled back. The rule is encoded per harness (GATE FAIL
non-zero exit in the Rust examples, threshold expect() in vitest).

F1 — Grouped listings (trash / recent / favorites / shared-with-me)
re-bucketed the WHOLE accumulated list on every infinite-scroll page.
ResourceSectionsBuilder (new, off the reactive graph) re-buckets only the
fresh page and hands VirtualList the same rows array reference for untouched
buckets. 50×50 (2 500-item) drain: 63 750 → 2 500 bucketOf calls (25.5×),
12.5 → 1.3 ms wall (9.9×); O(N²/page) → O(N). Deep-equal to the full-rebuild
reference at every page for both a contiguous (date) and a non-contiguous
(trash-by-drive) group-by; reference-stability + fallback gated.

B1 — exif Make/Model: the display String was thrown away to allocate the
trimmed copy; display_value_trimmed trims in place (drain + truncate), 2 → 1
alloc per field (8 → 4 allocs/op, 1.26×).

B2 — content-index worker: text_extractor::supports (lowercases MIME +
extension) was called twice per file per drain batch; classify once into a
Vec<bool> and thread it through both uses. 256-file batch: 704 → 353 allocs,
34.5 → 16.7 µs (2.07×).

B3 — tantivy: skip SnippetGenerator::create on a zero-hit content search
(return Ok(vec![]) once top_docs.is_empty()); the per-hit loop was empty.
400-doc index: 1 575.6 → 1 237.2 ns (1.27×), widens with index size.

Harnesses: examples/bench_round15_micro.rs, examples/bench_round15_tantivy.rs,
frontend resourceSections.bench.test.ts; writeup in benches/ROUND15.md. Also
normalizes two round14 bench examples that were committed unformatted
(cargo fmt --all).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012o47jSrtL7xuNGTHXmtiYL

src/infrastructure/services/exif_service.rs

@@ -61,23 +61,13 @@ impl ExifService {
 
         // ── Camera info ──
         if let Some(field) = exif.get_field(Tag::Make, In::PRIMARY) {
-            let val = field
-                .display_value()
-                .to_string()
-                .trim_matches('"')
-                .trim()
-                .to_string();
+            let val = display_value_trimmed(field);
             if !val.is_empty() {
                 meta.camera_make = Some(val);
             }
         }
         if let Some(field) = exif.get_field(Tag::Model, In::PRIMARY) {
-            let val = field
-                .display_value()
-                .to_string()
-                .trim_matches('"')
-                .trim()
-                .to_string();
+            let val = display_value_trimmed(field);
             if !val.is_empty() {
                 meta.camera_model = Some(val);
             }
@@ -115,6 +105,29 @@ impl ExifService {
     }
 }
 
+/// Render an EXIF field's display value, then strip surrounding quotes and
+/// whitespace (the shape `Make`/`Model` want) in a SINGLE allocation.
+///
+/// `display_value().to_string()` is the one unavoidable allocation — the field
+/// value is materialized to text. The old `…to_string().trim_matches('"')
+/// .trim().to_string()` chain then threw that `String` away and allocated a
+/// second time for the trimmed copy. Here the same two-stage trim is applied
+/// in place on the already-owned buffer (`drain` drops the prefix, `truncate`
+/// the suffix — both reuse the allocation), so a quoted `"Canon"` costs one
+/// allocation instead of two.
+fn display_value_trimmed(field: &exif::Field) -> String {
+    let mut s = field.display_value().to_string();
+    // Same order the old chain used: strip `"` first, then whitespace. The
+    // result is a contiguous subslice of `s`; capture its byte range before
+    // mutating the owned buffer (the borrow ends at these two reads).
+    let trimmed = s.trim_matches('"').trim();
+    let start = trimmed.as_ptr().addr() - s.as_ptr().addr();
+    let len = trimmed.len();
+    s.drain(..start);
+    s.truncate(len);
+    s
+}
+
 /// Parse EXIF datetime string "YYYY:MM:DD HH:MM:SS" into DateTime<Utc>.
 fn parse_exif_datetime(s: &str) -> Option<DateTime<Utc>> {
     // EXIF dates use ":" as separator for date parts

src/infrastructure/services/search_index/content_index_worker.rs

@@ -264,13 +264,21 @@ impl ContentIndexWorker {
         let found: HashSet<Uuid> = files.iter().map(|f| f.0).collect();
         deletes.extend(upsert_candidates.iter().filter(|id| !found.contains(id)));
 
+        // `supports` lowercases the MIME (and, on a generic MIME, the extension)
+        // — 1–2 allocations per call. Classify each file ONCE here and thread the
+        // flag through both the wanted-hashes filter and the per-file records
+        // loop below, where it used to be re-derived a second time per file.
+        let supported: Vec<bool> = files
+            .iter()
+            .map(|(_, _, name, _, mime, _)| text_extractor::supports(name, mime))
+            .collect();
+
         // Per-blob text: batch-read the extraction cache, extract misses.
         let wanted_hashes: Vec<String> = files
             .iter()
-            .filter(|(_, _, name, _, mime, size)| {
-                text_extractor::supports(name, mime) && *size as u64 <= self.max_extract_file_bytes
-            })
-            .map(|f| f.3.clone())
+            .zip(&supported)
+            .filter(|&(f, sup)| *sup && f.5 as u64 <= self.max_extract_file_bytes)
+            .map(|(f, _)| f.3.clone())
             .collect();
         let mut text_by_hash: HashMap<String, Option<String>> = HashMap::new();
         if !wanted_hashes.is_empty() {
@@ -287,8 +295,9 @@ impl ContentIndexWorker {
         }
 
         let mut records = Vec::with_capacity(files.len());
-        for (file_id, drive_id, name, blob_hash, mime, size) in files {
-            let supported = text_extractor::supports(&name, &mime);
+        for ((file_id, drive_id, name, blob_hash, mime, size), supported) in
+            files.into_iter().zip(supported)
+        {
             let content = if !supported {
                 None
             } else if let Some(cached) = text_by_hash.get(&blob_hash) {

src/infrastructure/services/search_index/tantivy_content_index.rs

@@ -349,6 +349,14 @@ impl TantivyContentIndex {
             .search(&query, &TopDocs::with_limit(limit.max(1)).order_by_score())
             .map_err(|e| DomainError::internal_error("ContentIndex", format!("search: {e}")))?;
 
+        // No hits → no documents to highlight. `SnippetGenerator::create`
+        // compiles the query against the index (term lookups + weight build);
+        // for a query that matched nothing that is pure waste on the search
+        // request path, and the per-hit loop below never runs. Return early.
+        if top_docs.is_empty() {
+            return Ok(Vec::new());
+        }
+
         // Snippets highlight CONTENT matches; an empty fragment means the hit
         // came from the name (or a fuzzy variant) — no snippet then.
         let snippet_generator = SnippetGenerator::create(&searcher, &*query, fields.content)