chore: release v0.0.21

[sw-release-bot]

🤖 New release

• structured-zstd: 0.0.20 -> 0.0.21

Changelog

0.0.21 - 2026-05-16

Added

• (encoding) feat: block splitting for improved compression ratio #23 add donor _fromBorders pre-split heuristic + broaden level coverage (#140)

Fixed

• (bench) restore sample_size=10, raise measurement_time to clear criterion floor (#144)

Performance

• (encoding) feat: long distance matching (LDM) for compression #18 Phase 5 — LDM producer (gear hash + bucket table + search/emit) (#139)
• (encoding) feat(encoding): #111 Phase 4 — donor fast paths + Matcher trait #124 Phase 4 — HC speculative tail check + MatcherStorage enum dispatch (#125)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 3 — const-generic Strategy dispatch (#123)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 2 — saturating_* cleanup on hot path (#121)

Refactored

• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 1e — migrate methods off HcMatchGenerator (Stages A–D) (#119)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 1d — split HcMatchGenerator into MatchTable / HcMatcher / BtMatcher (#118)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 1c — extract Simple matcher into simple/ (#117)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 1b — extract shared match-finder helpers (#116)
• (encoding) feat: encoder architecture rewrite (split monolith, const-generic Strategy, arena allocator) #111 Phase 1 — structural split of match_generator monolith (#113)

Bench

• add real peak-alloc metric for full encode/decode/memory baseline (#143)

---

This PR was generated with release-plz.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[sw-release-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'structured-zstd vs C FFI (x86_64-gnu)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.30.

Benchmark suite	Current: 9d084e9	Previous: 1e0f695	Ratio
compress/level_22_btultra2/small-4k-log-lines/matrix/pure_rust	0.287 ms	0.219 ms	1.31
compress/level_22_btultra2/small-4k-log-lines/matrix/c_ffi	0.112 ms	0.067 ms	1.67
compress/level_22_btultra2/decodecorpus-z000033/matrix/c_ffi	242.066 ms	171.961 ms	1.41
compress/level_22_btultra2/low-entropy-1m/matrix/pure_rust	1.763 ms	1.293 ms	1.36
compress/level_22_btultra2/low-entropy-1m/matrix/c_ffi	1.701 ms	1.184 ms	1.44

This comment was automatically generated by workflow using github-action-benchmark.

CC: @polaz