From b1cfb87e71b8252dfd086274c54e347c4b49e662 Mon Sep 17 00:00:00 2001
From: James Lu <james@overdrivenetworks.com>
Date: Wed, 5 Oct 2022 18:40:03 -0700
Subject: [PATCH] String: allow multi-character inputs in "ord" and
 "unicodename"

This allows them to support emoji ZWJ sequences, which render like one character but are actually multiple.
---
 plugins/String/plugin.py | 33 ++++++++++++++++++---------------
 plugins/String/test.py   | 14 +++++++++++---
 2 files changed, 29 insertions(+), 18 deletions(-)

diff --git a/plugins/String/plugin.py b/plugins/String/plugin.py
index 495d33387..20cae111d 100644
--- a/plugins/String/plugin.py
+++ b/plugins/String/plugin.py
@@ -51,13 +51,13 @@ import multiprocessing
 
 class String(callbacks.Plugin):
     """Provides useful commands for manipulating characters and strings."""
-    def ord(self, irc, msg, args, letter):
-        """<letter>
+    def ord(self, irc, msg, args, s):
+        """<string>
 
-        Returns the unicode codepoint of <letter>.
+        Returns the unicode codepoint of characters in <string>.
         """
-        irc.reply(str(ord(letter)))
-    ord = wrap(ord, ['letter'])
+        irc.replies([str(ord(char)) for char in s])
+    ord = wrap(ord, ['text'])
 
     def chr(self, irc, msg, args, i):
         """<number>
@@ -70,17 +70,20 @@ class String(callbacks.Plugin):
             irc.error(_('That number doesn\'t map to a unicode character.'))
     chr = wrap(chr, ['int'])
 
-    def unicodename(self, irc, msg, args, character):
-        """<character>
+    def unicodename(self, irc, msg, args, s):
+        """<string>
 
-        Returns the name of the given unicode <character>."""
-        if len(character) != 1:
-            irc.errorInvalid('character', character)
-        try:
-            irc.reply(unicodedata.name(character))
-        except ValueError:
-            irc.error(_('No name found for this character.'))
-    unicodename = wrap(unicodename, ['something'])
+        Returns the name of characters in <string>.
+        This will error if any character is not a valid Unicode character."""
+        replies = []
+        for idx, char in enumerate(s):
+            try:
+                replies.append(unicodedata.name(char))
+            except ValueError:
+                irc.error(_('No name found for character %r at position %d.') %
+                          (char, idx), Raise=True)
+        irc.replies(replies)
+    unicodename = wrap(unicodename, ['text'])
 
     def unicodesearch(self, irc, msg, args, name):
         """<name>
diff --git a/plugins/String/test.py b/plugins/String/test.py
index 4f21d4e70..766a2c4a0 100644
--- a/plugins/String/test.py
+++ b/plugins/String/test.py
@@ -103,13 +103,21 @@ class StringTestCase(PluginTestCase):
         for c in map(chr, range(256)):
             i = ord(c)
             self.assertResponse('ord %s' % utils.str.dqrepr(c), str(i))
-
+        self.assertResponse('ord é', '233')
+        self.assertResponse('ord 🆒', '127378')
+        self.assertResponse('ord 🇦🇶', '127462 and 127478')
 
     def testUnicode(self):
         self.assertResponse('unicodename ☃', 'SNOWMAN')
         self.assertResponse('unicodesearch SNOWMAN', '☃')
-        #self.assertResponse('unicodename ?',
-        #    'No name found for this character.')
+        self.assertResponse('unicodename ?', 'QUESTION MARK')
+
+        # multi-char strings and ZWJ sequences
+        self.assertResponse('unicodename :O', 'COLON and LATIN CAPITAL LETTER O')
+        self.assertResponse('unicodename 🤷‍♂️', 'SHRUG, ZERO WIDTH JOINER, MALE SIGN, and VARIATION SELECTOR-16')
+
+        self.assertError('unicodename "\\uFFFF"')
+        self.assertError('unicodename "!@#\\uFFFF$"')
         self.assertResponse('unicodesearch FOO',
             'Error: No character found with this name.')