Skip to content

fix: avoid frequent string2bytes conversions #20940

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
merged 2 commits into from
Aug 24, 2022
Merged

fix: avoid frequent string2bytes conversions #20940

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eb51998
fix: avoid frequent string2bytes conversions
wolfogre Aug 24, 2022
c0c36ad
Merge branch 'main' into bugfix/escape-streamer
lunny Aug 24, 2022
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
15 changes: 8 additions & 7 deletions modules/charset/escape_stream.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@ func (e *escapeStreamer) Text(data string) error {
_, _ = sb.WriteString(data[:len(UTF8BOM)])
pos = len(UTF8BOM)
}
dataBytes := []byte(data)
for pos < len(data) {
nextIdxs := defaultWordRegexp.FindStringIndex(data[pos:])
if nextIdxs == nil {
Expand All @@ -64,30 +65,30 @@ func (e *escapeStreamer) Text(data string) error {
positions := make([]int, 0, next-until+1)

for pos < until {
r, sz := utf8.DecodeRune([]byte(data)[pos:])
r, sz := utf8.DecodeRune(dataBytes[pos:])
positions = positions[:0]
positions = append(positions, pos, pos+sz)
types, confusables, _ := e.runeTypes(r)
if err := e.handleRunes(data, []rune{r}, positions, types, confusables, sb); err != nil {
if err := e.handleRunes(dataBytes, []rune{r}, positions, types, confusables, sb); err != nil {
return err
}
pos += sz
}

for i := pos; i < next; {
r, sz := utf8.DecodeRune([]byte(data)[i:])
r, sz := utf8.DecodeRune(dataBytes[i:])
runes = append(runes, r)
positions = append(positions, i)
i += sz
}
positions = append(positions, next)
types, confusables, runeCounts := e.runeTypes(runes...)
if runeCounts.needsEscape() {
if err := e.handleRunes(data, runes, positions, types, confusables, sb); err != nil {
if err := e.handleRunes(dataBytes, runes, positions, types, confusables, sb); err != nil {
return err
}
} else {
_, _ = sb.Write([]byte(data)[pos:next])
_, _ = sb.Write(dataBytes[pos:next])
}
pos = next
}
Expand All @@ -99,7 +100,7 @@ func (e *escapeStreamer) Text(data string) error {
return nil
}

func (e *escapeStreamer) handleRunes(data string, runes []rune, positions []int, types []runeType, confusables []rune, sb *strings.Builder) error {
func (e *escapeStreamer) handleRunes(data []byte, runes []rune, positions []int, types []runeType, confusables []rune, sb *strings.Builder) error {
for i, r := range runes {
switch types[i] {
case brokenRuneType:
Expand All @@ -111,7 +112,7 @@ func (e *escapeStreamer) handleRunes(data string, runes []rune, positions []int,
}
end := positions[i+1]
start := positions[i]
if err := e.brokenRune([]byte(data)[start:end]); err != nil {
if err := e.brokenRune(data[start:end]); err != nil {
return err
}
case ambiguousRuneType:
Expand Down