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

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"]
-        private val wordBoundaryRegex = Regex("(?<=[\\u0000-\\u007F])(?=[\\u0080-\\uFFFF])|(?<=[\\u0080-\\uFFFF])(?=[\\u0000-\\u007F])| +")
+        val wordBoundaryRegex = Regex("(?<=[\\u0000-\\u007F])(?=[\\u0080-\\uFFFF])|(?<=[\\u0080-\\uFFFF])(?=[\\u0000-\\u007F])| +")
 
         val additionalUrlSchema =
             """^([A-Za-z0-9-_]+(\.[A-Za-z0-9-_]+)+)(:[0-9]+)?(/[^?#]*)?(\?[^#]*)?(#.*)?"""

commons/src/commonTest/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParserMultibyteTest.kt

@@ -23,6 +23,7 @@ package com.vitorpamplona.amethyst.commons.richtext
 import com.vitorpamplona.amethyst.commons.model.EmptyTagList
 import org.junit.Assert.assertTrue
 import org.junit.Test
+import kotlin.test.assertEquals
 
 class RichTextParserMultibyteTest {
     @Test
@@ -58,6 +59,20 @@ class RichTextParserMultibyteTest {
         )
     }
 
+    @Test
+    fun testFullTextWithMultibyteAndLatinAccents() {
+        // Multibyte characters around an email address should not produce URL/Link segments
+        val text =
+            "Vitor, você tem como colocar alguma forma de aviso se o link vai carregar uma imagem ou um vídeo? \uD83E\uDD7A"
+
+        val regex = Regex("(?<=[\\u0000-\\u00FF])(?=[\\u0100-\\uFFFF])|(?<=[\\u0100-\\uFFFF])(?=[\\u0000-\\u00FF])| +")
+
+        assertEquals(
+            "Vitor,-você-tem-como-colocar-alguma-forma-de-aviso-se-o-link-vai-carregar-uma-imagem-ou-um-vídeo?-\uD83E\uDD7A",
+            text.split(regex).joinToString("-"),
+        )
+    }
+
     @Test
     fun testEmailSegmentStandalone() {
         val text = "user@example.com"