mirrors/gotosocial
1
0
Fork 0
mirror of https://github.com/superseriousbusiness/gotosocial.git synced 2025-10-29 21:02:26 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

[bugfix] Extend parser to handle more non-Latin hashtags (#3700)

Browse source 
* Allow marks after NFC normalization

Includes regression test for the Tamil example from #3618

* Disallow just numbers + marks + underscore as hashtag
This commit is contained in:
Vyr Cossont 2025-01-31 02:42:55 -08:00 • committed by GitHub
commit b9e0689359
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 48 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

17
internal/text/normalize.go
View file

@ -50,17 +50,16 @@ func NormalizeHashtag(text string) (string, bool) {
// Validate normalized result.
var (
notJustUnderscores = false
onlyPermittedChars = true
lengthOK = true
atLeastOneRequiredChar = false
onlyPermittedChars = true
lengthOK = true
)
for i, r := range normalized {
if r != '_' {
// This isn't an underscore,
// so the whole hashtag isn't
// just underscores.
notJustUnderscores = true
if !isPermittedIfNotEntireHashtag(r) {
// This isn't an underscore, mark, etc,
// so the hashtag contains at least one
atLeastOneRequiredChar = true
}
if i >= maximumHashtagLength {
@ -74,5 +73,5 @@ func NormalizeHashtag(text string) (string, bool) {
}
}
return normalized, (lengthOK && onlyPermittedChars && notJustUnderscores)
return normalized, lengthOK && onlyPermittedChars && atLeastOneRequiredChar
}