fix .u
mutantmonkey
parent
d9a8cb9a12
commit
7b41ea29bd
|
|
@ -11,124 +11,126 @@ import re, unicodedata
|
||||||
from itertools import islice
|
from itertools import islice
|
||||||
|
|
||||||
def about(u, cp=None, name=None):
|
def about(u, cp=None, name=None):
|
||||||
if cp is None:
|
if cp is None:
|
||||||
cp = ord(u)
|
cp = ord(u)
|
||||||
if name is None:
|
if name is None:
|
||||||
try: name = unicodedata.name(u)
|
try: name = unicodedata.name(u)
|
||||||
except ValueError:
|
except ValueError:
|
||||||
return 'U+%04X (No name found)' % cp
|
return 'U+%04X (No name found)' % cp
|
||||||
|
|
||||||
if not unicodedata.combining(u):
|
if not unicodedata.combining(u):
|
||||||
template = 'U+%04X %s (%s)'
|
template = 'U+%04X %s (%s)'
|
||||||
else: template = 'U+%04X %s (\xe2\x97\x8c%s)'
|
else: template = 'U+%04X %s (\xe2\x97\x8c%s)'
|
||||||
return template % (cp, name, u)
|
return template % (cp, name, u)
|
||||||
|
|
||||||
def codepoint_simple(arg):
|
def codepoint_simple(arg):
|
||||||
arg = arg.upper()
|
arg = arg.upper()
|
||||||
|
|
||||||
r_label = re.compile('\\b' + arg.replace(' ', '.*\\b') + '\\b')
|
r_label = re.compile('\\b' + arg.replace(' ', '.*\\b') + '\\b')
|
||||||
|
|
||||||
results = []
|
results = []
|
||||||
for cp in range(0xFFFF):
|
for cp in range(0xFFFF):
|
||||||
u = chr(cp)
|
u = chr(cp)
|
||||||
try: name = unicodedata.name(u)
|
try: name = unicodedata.name(u)
|
||||||
except ValueError: continue
|
except ValueError: continue
|
||||||
|
|
||||||
if r_label.search(name):
|
if r_label.search(name):
|
||||||
results.append((len(name), u, cp, name))
|
|
||||||
if not results:
|
|
||||||
r_label = re.compile('\\b' + arg.replace(' ', '.*\\b'))
|
|
||||||
for cp in range(0xFFFF):
|
|
||||||
u = chr(cp)
|
|
||||||
try: name = unicodedata.name(u)
|
|
||||||
except ValueError: continue
|
|
||||||
|
|
||||||
if r_label.search(name):
|
|
||||||
results.append((len(name), u, cp, name))
|
results.append((len(name), u, cp, name))
|
||||||
|
if not results:
|
||||||
|
r_label = re.compile('\\b' + arg.replace(' ', '.*\\b'))
|
||||||
|
for cp in range(0xFFFF):
|
||||||
|
u = chr(cp)
|
||||||
|
try: name = unicodedata.name(u)
|
||||||
|
except ValueError: continue
|
||||||
|
|
||||||
if not results:
|
if r_label.search(name):
|
||||||
return None
|
results.append((len(name), u, cp, name))
|
||||||
|
|
||||||
length, u, cp, name = sorted(results)[0]
|
if not results:
|
||||||
return about(u, cp, name)
|
return None
|
||||||
|
|
||||||
|
length, u, cp, name = sorted(results)[0]
|
||||||
|
return about(u, cp, name)
|
||||||
|
|
||||||
def codepoint_extended(arg):
|
def codepoint_extended(arg):
|
||||||
arg = arg.upper()
|
arg = arg.upper()
|
||||||
try: r_search = re.compile(arg)
|
try: r_search = re.compile(arg)
|
||||||
except: raise ValueError('Broken regexp: %r' % arg)
|
except: raise ValueError('Broken regexp: %r' % arg)
|
||||||
|
|
||||||
for cp in range(1, 0x10FFFF):
|
for cp in range(1, 0x10FFFF):
|
||||||
u = chr(cp)
|
u = chr(cp)
|
||||||
name = unicodedata.name(u, '-')
|
name = unicodedata.name(u, '-')
|
||||||
|
|
||||||
if r_search.search(name):
|
if r_search.search(name):
|
||||||
yield about(u, cp, name)
|
yield about(u, cp, name)
|
||||||
|
|
||||||
def u(phenny, input):
|
def u(phenny, input):
|
||||||
"""Look up unicode information."""
|
"""Look up unicode information."""
|
||||||
arg = input.bytes[3:]
|
arg = input.bytes[3:]
|
||||||
# phenny.msg('#inamidst', '%r' % arg)
|
# phenny.msg('#inamidst', '%r' % arg)
|
||||||
if not arg:
|
if not arg:
|
||||||
return phenny.reply('You gave me zero length input.')
|
return phenny.reply('You gave me zero length input.')
|
||||||
elif not arg.strip(' '):
|
elif not arg.strip(b' '):
|
||||||
if len(arg) > 1: return phenny.reply('%s SPACEs (U+0020)' % len(arg))
|
if len(arg) > 1: return phenny.reply('%s SPACEs (U+0020)' % len(arg))
|
||||||
return phenny.reply('1 SPACE (U+0020)')
|
return phenny.reply('1 SPACE (U+0020)')
|
||||||
|
|
||||||
# @@ space
|
# @@ space
|
||||||
if set(arg.upper()) - set(
|
if set(arg.upper()) - set(
|
||||||
'ABCDEFGHIJKLMNOPQRSTUVWYXYZ0123456789- .?+*{}[]\\/^$'):
|
b'ABCDEFGHIJKLMNOPQRSTUVWYXYZ0123456789- .?+*{}[]\\/^$'):
|
||||||
printable = False
|
printable = False
|
||||||
elif len(arg) > 1:
|
elif len(arg) > 1:
|
||||||
printable = True
|
printable = True
|
||||||
else: printable = False
|
else: printable = False
|
||||||
|
|
||||||
if printable:
|
if printable:
|
||||||
extended = False
|
extended = False
|
||||||
for c in '.?+*{}[]\\/^$':
|
for c in b'.?+*{}[]\\/^$':
|
||||||
if c in arg:
|
if c in arg:
|
||||||
extended = True
|
extended = True
|
||||||
break
|
break
|
||||||
|
|
||||||
if len(arg) == 4:
|
if len(arg) == 4:
|
||||||
try: u = chr(int(arg, 16))
|
try: u = chr(int(arg, 16))
|
||||||
except ValueError: pass
|
except ValueError: pass
|
||||||
else: return phenny.say(about(u))
|
else: return phenny.say(about(u))
|
||||||
|
|
||||||
if extended:
|
arg = arg.decode('utf-8')
|
||||||
# look up a codepoint with regexp
|
|
||||||
results = list(islice(codepoint_extended(arg), 4))
|
if extended:
|
||||||
for i, result in enumerate(results):
|
# look up a codepoint with regexp
|
||||||
if (i < 2) or ((i == 2) and (len(results) < 4)):
|
results = list(islice(codepoint_extended(arg), 4))
|
||||||
phenny.say(result)
|
for i, result in enumerate(results):
|
||||||
elif (i == 2) and (len(results) > 3):
|
if (i < 2) or ((i == 2) and (len(results) < 4)):
|
||||||
phenny.say(result + ' [...]')
|
phenny.say(result)
|
||||||
if not results:
|
elif (i == 2) and (len(results) > 3):
|
||||||
phenny.reply('Sorry, no results')
|
phenny.say(result + ' [...]')
|
||||||
else:
|
if not results:
|
||||||
# look up a codepoint freely
|
phenny.reply('Sorry, no results')
|
||||||
result = codepoint_simple(arg)
|
else:
|
||||||
if result is not None:
|
# look up a codepoint freely
|
||||||
phenny.say(result)
|
result = codepoint_simple(arg)
|
||||||
else: phenny.reply("Sorry, no results for %r." % arg)
|
if result is not None:
|
||||||
else:
|
phenny.say(result)
|
||||||
text = arg.decode('utf-8')
|
else: phenny.reply("Sorry, no results for %r." % arg)
|
||||||
# look up less than three podecoints
|
else:
|
||||||
if len(text) <= 3:
|
text = arg.decode('utf-8')
|
||||||
for u in text:
|
# look up less than three podecoints
|
||||||
phenny.say(about(u))
|
if len(text) <= 3:
|
||||||
# look up more than three podecoints
|
for u in text:
|
||||||
elif len(text) <= 10:
|
phenny.say(about(u))
|
||||||
phenny.reply(' '.join('U+%04X' % ord(c) for c in text))
|
# look up more than three podecoints
|
||||||
else: phenny.reply('Sorry, your input is too long!')
|
elif len(text) <= 10:
|
||||||
|
phenny.reply(' '.join('U+%04X' % ord(c) for c in text))
|
||||||
|
else: phenny.reply('Sorry, your input is too long!')
|
||||||
u.commands = ['u']
|
u.commands = ['u']
|
||||||
u.example = '.u 203D'
|
u.example = '.u 203D'
|
||||||
|
|
||||||
def bytes(phenny, input):
|
def bytes(phenny, input):
|
||||||
"""Show the input as pretty printed bytes."""
|
"""Show the input as pretty printed bytes."""
|
||||||
b = input.bytes
|
b = input.bytes
|
||||||
phenny.reply('%r' % b[b.find(' ') + 1:])
|
phenny.reply('%r' % b[b.find(' ') + 1:])
|
||||||
bytes.commands = ['bytes']
|
bytes.commands = ['bytes']
|
||||||
bytes.example = '.bytes \xe3\x8b\xa1'
|
bytes.example = '.bytes \xe3\x8b\xa1'
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
print(__doc__.strip())
|
print(__doc__.strip())
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue