Merge pull request #215 from cvzi/fix_delimiters

Fix delimiters
carpedm20 · Jul 11, 2022 · c398e0c · c398e0c
2 parents cf923b2 + dbda4a8
commit c398e0c
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 9 deletions.
diff --git a/emoji/core.py b/emoji/core.py
@@ -38,15 +38,16 @@ def emojize(
         Python is fun 👍
         >>> print(emoji.emojize("Python is fun :thumbs_up:"))
         Python is fun 👍
-        >>> print(emoji.emojize("Python is fun __thumbs_up__", delimiters = ("__", "__")))
+        >>> print(emoji.emojize("Python is fun {thumbs_up}", delimiters = ("{", "}")))
         Python is fun 👍
         >>> print(emoji.emojize("Python is fun :red_heart:", variant="text_type"))
         Python is fun ❤
         >>> print(emoji.emojize("Python is fun :red_heart:", variant="emoji_type"))
         Python is fun ❤️ # red heart, not black heart
 
     :param string: String contains emoji names.
-    :param delimiters: (optional) Use delimiters other than _DEFAULT_DELIMITER
+    :param delimiters: (optional) Use delimiters other than _DEFAULT_DELIMITER. Each delimiter
+        should contain at least one character that is not part of a-zA-Z0-9 and ``_-–&.’”“()!?#*+,/\``
     :param variant: (optional) Choose variation selector between "base"(None), VS-15 ("text_type") and VS-16 ("emoji_type")
     :param language: Choose language of emoji name: language code 'es', 'de', etc. or 'alias'
         to use English aliases
@@ -78,7 +79,7 @@ def emojize(
         language_pack = unicode_codes.get_emoji_unicode_dict(language)
 
     pattern = re.compile(u'(%s[\\w\\-&.’”“()!#*+?–,/]+%s)' %
-                         delimiters, flags=re.UNICODE)
+                         (re.escape(delimiters[0]), re.escape(delimiters[1])), flags=re.UNICODE)
 
     def replace(match):
         mg = match.group(1)[len(delimiters[0]):-len(delimiters[1])]

diff --git a/tests/test_core.py b/tests/test_core.py
@@ -222,20 +222,22 @@ def test_demojize_complicated_string():
 
 def test_demojize_delimiters():
     for e in [u'\U000026BD', u'\U0001f44d', u'\U0001F3C8']:
-        for d in [(":", ":"), ("a", "b"), ("!", "!!"), ("123", "456"), (u"😁", u"👌")]:
+        for d in [(":", ":"), ("}", "}"), ("!$", "!!$"), ("[123", "456]"), (u"😁", u"👌"), ("[", "]")]:
             s = emoji.demojize(e, delimiters=d)
             assert s.startswith(d[0])
             assert s.endswith(d[1])
 
-    text = u"Example of a text with an emoji%sin a sentence"
+    text = u"Example with an emoji%sin a sentence and %s %s %s %s multiple emoji %s%s%s%s%s in a row"
     for e in [u'\U000026BD', u'\U0001f44d', u'\U0001F3C8']:
-        for d in [(":", ":"), ("!", "-!-"), ("-", "-"), (":", "::"), ("::", "::"), (u"😁", u"👌")]:
-            text_with_unicode = text % e
+        for d in [(":", ":"), ("{", "}"), ("!$", "$!"), (":", "::"), ("::", "::"), (u"😁", u"👌"), ("[", "]")]:
+            print("delimiter: %s" % (d, ))
+            text_with_unicode = text % ((e, ) * 10)
             demojized_text = emoji.demojize(text_with_unicode, delimiters=d)
-            assert text_with_unicode != demojized_text
+            assert text_with_unicode != demojized_text, (text_with_unicode, demojized_text)
             assert e not in demojized_text
             assert emoji.emojize(demojized_text, delimiters=d) == text_with_unicode
-            text_with_emoji = text % emoji.demojize(e, delimiters=d)
+            de = emoji.demojize(e, delimiters=d)
+            text_with_emoji = text % ((de, ) * 10)
             assert demojized_text == text_with_emoji
             assert emoji.emojize(text_with_emoji, delimiters=d) == text_with_unicode