zstd: Fix incorrect encoding in best mode (#415)

Fix incorrect intermediate when testing current value for repeat+3 offsets. Fixes #414
klauspost · Aug 12, 2021 · bf4861f · bf4861f
1 parent 2ad8e19
commit bf4861f
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 9 deletions.
diff --git a/zstd/enc_best.go b/zstd/enc_best.go
@@ -5,6 +5,7 @@
 package zstd
 
 import (
+ "bytes"
  "fmt"
 
  "github.com/klauspost/compress"
@@ -208,6 +209,11 @@ encodeLoop:
  if s-offset >= e.maxMatchOff || load3232(src, offset) != first {
  return match{s: s, est: highScore}
  }
+ if debugAsserts {
+ if !bytes.Equal(src[s:s+4], src[offset:offset+4]) {
+ panic(fmt.Sprintf("first match mismatch: %v != %v, first: %08x", src[s:s+4], src[offset:offset+4], first))
+ }
+ }
  m := match{offset: offset, s: s, length: 4 + e.matchlen(s+4, offset+4, src), rep: rep}
  m.estBits(bitsPerByte)
  return m
@@ -218,17 +224,17 @@ encodeLoop:
  best = bestOf(best, matchAt(candidateS.prev-e.cur, s, uint32(cv), -1))
 
  if canRepeat && best.length < goodEnough {
- cv := uint32(cv >> 8)
+ cv32 := uint32(cv >> 8)
  spp := s + 1
- best = bestOf(best, matchAt(spp-offset1, spp, cv, 1))
- best = bestOf(best, matchAt(spp-offset2, spp, cv, 2))
- best = bestOf(best, matchAt(spp-offset3, spp, cv, 3))
+ best = bestOf(best, matchAt(spp-offset1, spp, cv32, 1))
+ best = bestOf(best, matchAt(spp-offset2, spp, cv32, 2))
+ best = bestOf(best, matchAt(spp-offset3, spp, cv32, 3))
  if best.length > 0 {
- cv >>= 16
+ cv32 = uint32(cv >> 24)
  spp += 2
- best = bestOf(best, matchAt(spp-offset1, spp, cv, 1))
- best = bestOf(best, matchAt(spp-offset2, spp, cv, 2))
- best = bestOf(best, matchAt(spp-offset3, spp, cv, 3))
+ best = bestOf(best, matchAt(spp-offset1, spp, cv32, 1))
+ best = bestOf(best, matchAt(spp-offset2, spp, cv32, 2))
+ best = bestOf(best, matchAt(spp-offset3, spp, cv32, 3))
  }
  }
  // Load next and check...
@@ -281,6 +287,12 @@ encodeLoop:
  }
  }
 
+ if debugAsserts {
+ if !bytes.Equal(src[best.s:best.s+best.length], src[best.offset:best.offset+best.length]) {
+ panic(fmt.Sprintf("match mismatch: %v != %v", src[best.s:best.s+best.length], src[best.offset:best.offset+best.length]))
+ }
+ }
+
  // We have a match, we can store the forward value
  if best.rep > 0 {
  s = best.s
@@ -356,7 +368,7 @@ encodeLoop:
  panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
  }
 
- if debugAsserts && canRepeat && int(offset1) > len(src) {
+ if debugAsserts && int(offset1) > len(src) {
  panic("invalid offset")
  }
 

diff --git a/zstd/testdata/regression.zip b/zstd/testdata/regression.zip