omnizip 0.3.16 → 0.3.17

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4417d9e90649e837f75b25bcee26c0721283e360d015eaf0c4194fa2957be053
-  data.tar.gz: 8c5fc8e793ea023d21abd9b044c3ddfb3786ee90225fe57fb322fa8cc60c5f4a
+  metadata.gz: 26bb587688afe9104a60ed3db30bd0b4d4a0ad909d1f02d0afaf3c8b67343119
+  data.tar.gz: 674f6bdf6fa36ec488ad06aa3f0a98ba792945fff3d244e9913ee06ff64402a6
 SHA512:
-  metadata.gz: 2de569d977b1b47bc476efd9eb17e8f00c5b803e96451592964ee0f43bfa04caf52fd6462d02fbcaf9bd914b32436a210b1b935d24d6c1ad96a61acf119c7ca4
-  data.tar.gz: c070c98a67fef377cf8710f89ed922bb0a6ff5cf8edd0ac7307113f4973d07a85c5eb8dfce48210f7d570687d361f68cc61f947d4dc739588f9aee1662126269
+  metadata.gz: ed59928f26cec56627b12304d9cf55d3ed04a7ee07f0a3bf2ef6f71b44a0e21d76d4246746db8f5dd0751139f68208a5a5a53c81ce9959f4433f883d3648adfc
+  data.tar.gz: 311d21ef3715257f1db58f9c1238200d04dce604022337fa53adf7a2c95d1a2d1272ba75bbcae55aaaf5d5b97a16ef954e7ab1b423e9f6875abb1f1036653a6b

data/lib/omnizip/algorithms/zstandard/match_finder.rb

@@ -177,7 +177,12 @@ module Omnizip
           limit = block_end - mm
 
           while ip < limit
-            match = find_best_match(src, ip, ms, mm, limit)
+            match = if lazy.zero?
+                      find_greedy_match(src, ip, ms, mm, limit, anchor,
+                                        seq_store.rep_offsets[0])
+                    else
+                      find_best_match(src, ip, ms, mm, limit)
+                    end
             if match
               dist, len = match
               defer = false
@@ -198,6 +203,7 @@ module Omnizip
                 next
               end
 
+              ip = match[2] if match.length == 3
               seq_store.literals << src.byteslice(anchor, ip - anchor)
               seq_store.sequences <<
                 RawSequence.new(ip - anchor, len, dist)
@@ -218,6 +224,55 @@ module Omnizip
         # rubocop:enable Metrics/AbcSize
         # rubocop:enable Metrics/MethodLength
 
+        # Greedy-path match search (port of the Rust
+        # compress_block_with_min_match): the rep0 fast-path first
+        # (cheapest offset to encode), then the hash table — both
+        # with backward extension into the pending literals. Returns
+        # [offset, length, start] or nil.
+        def find_greedy_match(src, ip, ms, min_match, limit, anchor, rep0)
+          m = rep0_match(src, ip, rep0, min_match, limit, anchor)
+          return m if m
+
+          dist, len = find_best_match(src, ip, ms, min_match, limit)
+          return nil unless dist
+
+          back = backward_extension(src, ip, anchor, ip - dist)
+          [dist, len + back, ip - back]
+        end
+
+        # Match at distance rep0 (the decoder's most recent offset)
+        # with forward and backward extension. [rep0, length, start]
+        # or nil.
+        #
+        # rubocop:disable-next Metrics/AbcSize
+        def rep0_match(src, ip, rep0, min_match, limit, anchor)
+          return nil if rep0 <= 0 || ip <= rep0
+          return nil if src.byteslice(ip, MIN_MATCH) !=
+            src.byteslice(ip - rep0, MIN_MATCH)
+
+          m_len = MIN_MATCH + count_match(
+            src, ip + MIN_MATCH, src, ip + MIN_MATCH - rep0,
+            [limit + MIN_MATCH_ECONOMICAL - ip - MIN_MATCH, 0].max
+          )
+          back = backward_extension(src, ip, anchor, ip - rep0)
+          m_len += back
+          return nil if m_len < min_match
+
+          [rep0, m_len, ip - back]
+        end
+
+        # Bytes before `ip` (and before the match candidate) that
+        # extend the match backward, bounded by the pending literal
+        # run so the previous sequence is never overlapped.
+        def backward_extension(src, ip, anchor, candidate)
+          back = 0
+          while ip > anchor + back && candidate > back &&
+              src.getbyte(ip - 1 - back) == src.getbyte(candidate - 1 - back)
+            back += 1
+          end
+          back
+        end
+
         # Find the best match at `ip` (single probe, or a chain walk
         # when enabled). Updates the hash table. Returns
         # [distance, length] or nil.

data/lib/omnizip/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Omnizip
-  VERSION = "0.3.16"
+  VERSION = "0.3.17"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: omnizip
 version: !ruby/object:Gem::Version
-  version: 0.3.16
+  version: 0.3.17
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-08-24 00:00:00.000000000 Z
+date: 2026-08-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: base64