From c95a9842a4a264dd14710077988a735e557f1e7e Mon Sep 17 00:00:00 2001 From: Vitor Pamplona Date: Wed, 4 Mar 2026 15:09:26 -0500 Subject: [PATCH] Adds the latin1 characters to the ascii block to avoid splitting words --- .../vitorpamplona/amethyst/commons/richtext/RichTextParser.kt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt index ab98ee8cb..103da1204 100644 --- a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt +++ b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt @@ -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]+)?(/[^?#]*)?(\?[^#]*)?(#.*)?"""