Get character names of control characters

1 files changed, 14 insertions, 6 deletions

diff --git a/misc.py b/misc.py
index ffd0ed4..0447829 100644
--- a/misc.py
+++ b/misc.py
@@ -192,17 +192,25 @@ def coinflip_cmd(irc, hostmask, is_admin, args):
     reply(irc, hostmask, args, msg)
 
 
+def get_char_name(char):
+    # Hack to get the name of control characters. U+2400 is "SYMBOL FOR NULL"
+    # and this function will remove the leading "SYMBOL FOR " prefix when a
+    # null byte is passed to it.
+    if char <= '\x1f':
+        char = chr(ord(char) + 0x2400)
+        return unicodedata.name(char)[11:]
+    return unicodedata.name(char, 'Unknown')
+
+
 @register_command('chr', 'unicode', 'u')
 def unicode_cmd(irc, hostmask, is_admin, args):
     chars = args[1]
-    if len(chars) > 5:
-        msg = f'You must provide 1-5 characters, not {len(chars)}.'
+    if len(chars) > 10:
+        msg = f'You must provide 1-10 characters, not {len(chars)}.'
     elif not chars:
         msg = 'Usage: .unicode <character>'
     else:
-        msg = ', '.join(
-            f'U+{ord(char):04X} - {unicodedata.name(char, "Unknown")}'
-            for char in chars
-        )
+        msg = ', '.join(f'U+{ord(char):04X} - {get_char_name(char)}'
+                        for char in chars)
 
     reply(irc, hostmask, args, msg)