Skip to content

refactor(internal): compile regex once while clearing text #1430

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
LinkinStars merged 1 commit into from
Nov 24, 2025
Merged

refactor(internal): compile regex once while clearing text #1430

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
48 changes: 22 additions & 26 deletions pkg/htmltext/htmltext.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,38 +34,34 @@ import (
"github.com/mozillazg/go-pinyin"
)

var (
reCode = regexp.MustCompile(`(?ism)<(pre)>.*<\/pre>`)
reCodeReplace = "{code...}"
reLink = regexp.MustCompile(`(?ism)<a.*?[^<]>(.*)?<\/a>`)
reLinkReplace = " [$1] "
reSpace = regexp.MustCompile(` +`)
reSpaceReplace = " "

spaceReplacer = strings.NewReplacer(
"\n", " ",
"\r", " ",
"\t", " ",
)
)

// ClearText clear HTML, get the clear text
func ClearText(html string) (text string) {
if len(html) == 0 {
text = html
return
func ClearText(html string) string {
if html == "" {
return html
}

var (
re *regexp.Regexp
codeReg = `(?ism)<(pre)>.*<\/pre>`
codeRepl = "{code...}"
linkReg = `(?ism)<a.*?[^<]>(.*)?<\/a>`
linkRepl = " [$1] "
spaceReg = ` +`
spaceRepl = " "
)
re = regexp.MustCompile(codeReg)
html = re.ReplaceAllString(html, codeRepl)
html = reCode.ReplaceAllString(html, reCodeReplace)
html = reLink.ReplaceAllString(html, reLinkReplace)

re = regexp.MustCompile(linkReg)
html = re.ReplaceAllString(html, linkRepl)

text = strings.NewReplacer(
"\n", " ",
"\r", " ",
"\t", " ",
).Replace(strip.StripTags(html))
text := spaceReplacer.Replace(strip.StripTags(html))

// replace multiple spaces to one space
re = regexp.MustCompile(spaceReg)
text = strings.TrimSpace(re.ReplaceAllString(text, spaceRepl))
return
return strings.TrimSpace(reSpace.ReplaceAllString(text, reSpaceReplace))
}

func UrlTitle(title string) (text string) {
Expand Down