nick/amethyst
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Adds the latin1 characters to the ascii block to avoid splitting words

Browse Source
This commit is contained in:
Vitor Pamplona
2026-03-04 15:09:26 -05:00
parent 2f94b3cb15
commit c95a9842a4
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt
+1 -1
View File
@@ -348,7 +348,7 @@ class RichTextParser {
// Splits at spaces AND at ASCII/multibyte character boundaries
// e.g. "ああexample.com" -> ["ああ", "example.com"]
val wordBoundaryRegex = Regex("(?<=[\\u0000-\\u007F])(?=[\\u0080-\\uFFFF])|(?<=[\\u0080-\\uFFFF])(?=[\\u0000-\\u007F])| +")
val wordBoundaryRegex = Regex("(?<=[\\u0000-\\u00FF])(?=[\\u0100-\\uFFFF])|(?<=[\\u0100-\\uFFFF])(?=[\\u0000-\\u00FF])| +")
val additionalUrlSchema =
"""^([A-Za-z0-9-_]+(\.[A-Za-z0-9-_]+)+)(:[0-9]+)?(/[^?#]*)?(\?[^#]*)?(#.*)?"""