def hello(a,b):
# ret = ''.join([chr(c) for c in range(a,a+min(b-a, 500))])
segments = cut([
classify(chr(c))
for c in range(a,b)], 30)
# ret = '<br/>'.join([''.join(a) for a in segments])
ret = '<br/>'.join([''.join(a) for a in segments])
# js_map = {chr(c): uname(chr(c)) for c in range(a,b)}
js_map = {}
for c in range(a,b):
try:
name = uname(chr(c))
except ValueError:
name = "no value found"
js_map[chr(c)] = "u+"+hex(c)+" "+name
js_map_str = "char_names = %s"%repr(js_map)
return html(
head(style)
+body(
div('','id="tooltip"')
+ret
+script2(js_map_str)
+script("tooltip.js")
+script("post_char.js")
+script("simple-ajax.js")
)
)
def __init__(self, codepoint):
self.char = unichr(codepoint)
self.hex = '%04x' % codepoint
self.dec = codepoint
self.entity = '&#x%x;' % codepoint
try:
self.name = uname(self.char)
self.category = category(self.char)
except ValueError:
pass
def fds():
print(uniblock[0])
intervals = {(i[0], i[1]):i[2] for i in uniblock}
chars = ''
# chars = open("unicode-favchars.txt", encoding="utf-8").read()+additions
chars += open("unicode-favchars2.txt", encoding="utf-8").read()
chars = list(set(chars))
# f = open("unicode-sorted.txt", encoding="utf-8")
things = {}
for c in chars:
# cat = unicodedata.category(c)
# dig = unicodedata.digit(c)
categ, categ_name = interval_find(ord(c),intervals)
cat = categ_name
if not cat in things: things[cat]=[]
things[cat].append(c)
# return '<br/>'.join(
# [cat+' '.join(
# [c for c in things[cat]]
# ) for cat in things]
# )
js_map={}
for c in chars:
try:
name = uname(c)
except ValueError:
name = "no value found"
js_map[c] = "u+"+hex(ord(c))+" "+name
js_map_str = "char_names = %s"%repr(js_map)
made = table(''.join(
[tr([cat,' '.join([classify(c) for c in things[cat]])])
for cat in things])
)
return html(
head(style)
+body(
div('','id="tooltip"')
# +tag3(' '.join(chars), div)
+tag3(multiline(sorted(chars), 20), 'div', 'style="font-size:3em"')
+made
+script2(js_map_str)
+script("tooltip.js")
+script("post_char.js")
+script("simple-ajax.js")
)
)
def units_of_filename(fn):
unit = ''
for char in fn:
if char not in okay:
if unit:
yield unit
unit = ''
yield uname(char).replace(' ', '-')
else:
unit += char
if unit:
yield unit
from argparse import ArgumentParser
parser = ArgumentParser()
parser.add_argument('-w', '--width', type=int, default=1)
parser.add_argument('files', nargs='*')
args = parser.parse_args()
files = args.files
if not files:
files.append('-')
w=args.width
CC = Counter()
for fn in files:
if fn=='-':
f = stdin
else:
f = open(fn)
for line in f:
if w==1:
CC.update(line)
else:
for i in range(len(line)-w):
CC[line[i:i+w]] += 1
for (char, count) in CC.most_common():
if w==1:
print("<%c>: %s[%d]: %d" % (char, uname(char,"***UNKNOWN***"), ord(char), count))
else:
print("<%s>: %d" % (char, count))
def isMeemOrYeh(x):
nm = uname(x)
return MEEM in nm or YEH in x
def uName(c):
try:
un = uname(c)
except Exception:
un = "NO NAME"
return un
