diff options
author | mrsdizzie <info@mrsdizzie.com> | 2020-05-29 12:08:36 -0400 |
---|---|---|
committer | GitHub <noreply@github.com> | 2020-05-29 17:08:36 +0100 |
commit | 4c1ff57f1a41197bb6f6797d33461c76378e354c (patch) | |
tree | 5f1fc2fa51ccfefe937353c036b76566712f0fd5 /modules/emoji | |
parent | 02fa329a7c2190d947cd5e02ea90d2d4406653be (diff) | |
download | gitea-4c1ff57f1a41197bb6f6797d33461c76378e354c.tar.gz gitea-4c1ff57f1a41197bb6f6797d33461c76378e354c.zip |
Update emoji regex (#11584)
When matching emoji, use a regex built from the data we have instead of something generic using unicode ranges. A generic regex can't tell the difference between two separate emoji next to each other or one emoji that is built out of two separate emoji next to each other.
This means that emoji that are next to each other without space in between will be now accurately spanned individually with proper title etc...
Diffstat (limited to 'modules/emoji')
-rw-r--r-- | modules/emoji/emoji.go | 27 |
1 files changed, 27 insertions, 0 deletions
diff --git a/modules/emoji/emoji.go b/modules/emoji/emoji.go index 2a51e61fcf..e4b9e5631d 100644 --- a/modules/emoji/emoji.go +++ b/modules/emoji/emoji.go @@ -6,8 +6,10 @@ package emoji import ( + "sort" "strings" "sync" + "unicode/utf8" ) // Gemoji is a set of emoji data. @@ -48,6 +50,12 @@ func loadMap() { // process emoji codes and aliases codePairs := make([]string, 0) aliasPairs := make([]string, 0) + + // sort from largest to small so we match combined emoji first + sort.Slice(GemojiData, func(i, j int) bool { + return len(GemojiData[i].Emoji) > len(GemojiData[j].Emoji) + }) + for i, e := range GemojiData { if e.Emoji == "" || len(e.Aliases) == 0 { continue @@ -72,6 +80,7 @@ func loadMap() { codeReplacer = strings.NewReplacer(codePairs...) aliasReplacer = strings.NewReplacer(aliasPairs...) }) + } // FromCode retrieves the emoji data based on the provided unicode code (ie, @@ -117,3 +126,21 @@ func ReplaceAliases(s string) string { loadMap() return aliasReplacer.Replace(s) } + +// FindEmojiSubmatchIndex returns index pair of longest emoji in a string +func FindEmojiSubmatchIndex(s string) []int { + loadMap() + + // if rune and string length are the same then no emoji will be present + // similar performance when there is unicode present but almost 200% faster when not + if utf8.RuneCountInString(s) == len(s) { + return nil + } + for j := range GemojiData { + i := strings.Index(s, GemojiData[j].Emoji) + if i != -1 { + return []int{i, i + len(GemojiData[j].Emoji)} + } + } + return nil +} |