close
Skip to content

zstd: BuildDict fails with RLE table #951

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
klauspost merged 2 commits into from
Jun 12, 2024
Merged

zstd: BuildDict fails with RLE table #951

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f500298
zstd: BuildDict fails with RLE table
klauspost Apr 12, 2024
11a80c8
Prevent offsets longer than dict to be selected.
klauspost Apr 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions zstd/dict.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,9 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
enc.Encode(&block, b)
addValues(&remain, block.literals)
litTotal += len(block.literals)
if len(block.sequences) == 0 {
continue
}
seqs += len(block.sequences)
block.genCodes()
addHist(&ll, block.coders.llEnc.Histogram())
Expand All @@ -286,6 +289,9 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
if offset == 0 {
continue
}
if int(offset) >= len(o.History) {
continue
}
if offset > 3 {
newOffsets[offset-3]++
} else {
Expand Down Expand Up @@ -336,6 +342,9 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
if seqs/nUsed < 512 {
// Use 512 as minimum.
nUsed = seqs / 512
if nUsed == 0 {
nUsed = 1
}
}
copyHist := func(dst *fseEncoder, src *[256]int) ([]byte, error) {
hist := dst.Histogram()
Expand All @@ -358,6 +367,28 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
fakeLength += v
hist[i] = uint32(v)
}

// Ensure we aren't trying to represent RLE.
if maxCount == fakeLength {
for i := range hist {
if uint8(i) == maxSym {
fakeLength++
maxSym++
hist[i+1] = 1
if maxSym > 1 {
break
}
}
if hist[0] == 0 {
fakeLength++
hist[i] = 1
if maxSym > 1 {
break
}
}
}
}

dst.HistogramFinished(maxSym, maxCount)
dst.reUsed = false
dst.useRLE = false
Expand Down