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

2026-03-04 14:38:48 -05:00
parent be5c1f4832
commit 2f94b3cb15
2 changed files with 16 additions and 1 deletions
@@ -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]+)?(/[^?#]*)?(\?[^#]*)?(#.*)?"""