diff --git a/src/com/twitter/Regex.java b/src/com/twitter/Regex.java index 14b853f..8b21bc6 100644 --- a/src/com/twitter/Regex.java +++ b/src/com/twitter/Regex.java @@ -80,7 +80,8 @@ private static String join(Collection col, String delim) { "\\uff21-\\uff3a\\uff41-\\uff5a" + // full width Alphabet "\\uff66-\\uff9f" + // half width Katakana "\\uffa1-\\uffdc"; // half width Hangul (Korean) - private static final String HASHTAG_ALPHA_NUMERIC_CHARS = "0-9\\uff10-\\uff19_" + HASHTAG_ALPHA_CHARS; + private static final String SPECIAL_CHARS_INCLUDED = "\\u00b7\\u2022\\u30fb\\uff65"; + private static final String HASHTAG_ALPHA_NUMERIC_CHARS = "0-9\\uff10-\\uff19_" + HASHTAG_ALPHA_CHARS + SPECIAL_CHARS_INCLUDED; private static final String HASHTAG_ALPHA = "[" + HASHTAG_ALPHA_CHARS +"]"; private static final String HASHTAG_ALPHA_NUMERIC = "[" + HASHTAG_ALPHA_NUMERIC_CHARS +"]"; diff --git a/test-data/twitter-text-conformance b/test-data/twitter-text-conformance index be88d01..34b2fd8 160000 --- a/test-data/twitter-text-conformance +++ b/test-data/twitter-text-conformance @@ -1 +1 @@ -Subproject commit be88d01a567c82bc625f8991cd825dc100e01321 +Subproject commit 34b2fd833cca52aedcf08e03fa60c4210facfd32