Unicode flags are single tokens

tsproisl · Jul 2, 2019 · f28bf7c · f28bf7c
1 parent 1ba3fc1
commit f28bf7c
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/someweta/tagger.py b/someweta/tagger.py
@@ -66,7 +66,7 @@ def __init__(self, beam_size=5, iterations=10, lexicon=None, mapping=None, brown
                                    r"|".join([re.escape(_) for _ in emoticon_list]) +
                                    r"$", re.VERBOSE)
         # Unicode emoticons and other symbols
-        self.unicode_flags = re.compile(r"\p{Regional_Indicator}{2}")
+        self.unicode_flags = re.compile(r"^\p{Regional_Indicator}{2}$")
         # self.emoji = re.compile(r"^[\u2600-\u27BF\uFE0E\uFE0F\U0001F300-\U0001f64f\U0001F680-\U0001F6FF\U0001F900-\U0001F9FF]$")
         self.emoji = re.compile(r"[\p{Extended_Pictographic}\p{Emoji_Presentation}\uFE0F]")