def analyze(filename, printCode=False, writeDot=False):
with open(filename, 'rb') as fi:
s = fi.read()
freq = Counter(s)
tree = huffTree(freq)
if writeDot:
write_dot(tree, 'tree.dot', is_binary(s))
code = huffCode(tree)
if printCode:
print_code(freq, code)
def analyze(filename, printCode=False, writeDot=False):
with open(filename, 'rb') as fi:
s = fi.read()
freq = Counter(s)
tree = huffTree(freq)
if writeDot:
write_dot(tree, 'tree.dot', is_binary(s))
code = huffCode(tree)
if printCode:
print_code(freq, code)
def encode(filename):
with open(filename, 'rb') as fi:
s = fi.read()
code = huffCode(huffTree(Counter(s)))
with open(filename + '.huff', 'wb') as fo:
for c in sorted(code):
fo.write(('%02x %s\n' % (c if is_py3k else ord(c),
code[c].to01())).encode())
a = bitarray(endian='little')
a.encode(code, s)
# write unused bits
fo.write(b'unused %s\n' % str(a.buffer_info()[3]).encode())
a.tofile(fo)
print('%d / %d' % (len(a), 8 * len(s)))
print('Ratio =%6.2f%%' % (100.0 * a.buffer_info()[1] / len(s)))
def encode(filename):
with open(filename, 'rb') as fi:
s = fi.read()
code = huffCode(huffTree(Counter(s)))
with open(filename + '.huff', 'wb') as fo:
for c in sorted(code):
fo.write(('%02x %s\n' %
(c if is_py3k else ord(c), code[c].to01())).encode())
a = bitarray(endian='little')
a.encode(code, s)
# write unused bits
fo.write(b'unused %s\n' % str(a.buffer_info()[3]).encode())
a.tofile(fo)
print('%d / %d' % (len(a), 8 * len(s)))
print('Ratio =%6.2f%%' % (100.0 * a.buffer_info()[1] / len(s)))
def main():
txt = 1000 * open('README').read()
t0 = time()
freq = Counter(txt)
print('count: %9.6f sec' % (time() - t0))
t0 = time()
tree = huffTree(freq)
print('tree: %9.6f sec' % (time() - t0))
write_dot(tree, 'tree.dot')
code = huffCode(tree)
# create tree from code (no frequencies)
write_dot(make_tree(code), 'tree_raw.dot')
a = bitarray()
t0 = time()
a.encode(code, txt)
print('C encode: %9.6f sec' % (time() - t0))
# Time the decode function above
t0 = time()
res = decode(tree, a)
Py_time = time() - t0
assert ''.join(res) == txt
print('Py decode: %9.6f sec' % Py_time)
# Time the decode method which is implemented in C
t0 = time()
res = a.decode(code)
assert ''.join(res) == txt
C_time = time() - t0
print('C decode: %9.6f sec' % C_time)
print('Ratio: %f' % (Py_time / C_time))
def main():
txt = open('README').read()
code = huffCode(freq_string(txt))
sample = 2000 * txt
a = bitarray()
a.encode(code, sample)
# Time the decode function above
start_time = time.time()
res = decode(code, a)
Py_time = time.time() - start_time
assert ''.join(res) == sample
print('Py_time: %.6f sec' % Py_time)
# Time the decode method which is implemented in C
start_time = time.time()
res = a.decode(code)
C_time = time.time() - start_time
assert ''.join(res) == sample
print('C_time: %.6f sec' % C_time)
print('Ratio: %f' % (Py_time / C_time))
def main():
txt = open('README').read()
code = huffCode(freq_string(txt))
sample = 2000 * txt
a = bitarray()
a.encode(code, sample)
# Time the decode function above
start_time = time.time()
res = decode(code, a)
Py_time = time.time() - start_time
assert ''.join(res) == sample
print('Py_time: %.6f sec' % Py_time)
# Time the decode method which is implemented in C
start_time = time.time()
res = a.decode(code)
C_time = time.time() - start_time
assert ''.join(res) == sample
print('C_time: %.6f sec' % C_time)
print('Ratio: %f' % (Py_time / C_time))
res = []
it = iter(bitsequence)
while True:
r = traverse(it, tree)
if r is False:
break
else:
if r == []:
raise ValueError("prefix code does not match data")
res.append(r)
return res
txt = open('README').read()
code = huffCode(freq_string(txt))
sample = 1000*txt
a = bitarray()
a.encode(code, sample)
# Time the decode function above
start_time = time.time()
res = decode(code, a)
Py_time = time.time() - start_time
assert ''.join(res) == sample
print('Py_time: %.6f sec' % Py_time)
# Time the decode method which is implemented in C
start_time = time.time()
res = []
it = iter(bitsequence)
while True:
r = traverse(it, tree)
if r is False:
break
else:
if r == []:
raise ValueError("prefix code does not match data")
res.append(r)
return res
txt = open('README').read()
code = huffCode(freq_string(txt))
sample = 1000 * txt
a = bitarray()
a.encode(code, sample)
# Time the decode function above
start_time = time.time()
res = decode(code, a)
Py_time = time.time() - start_time
assert ''.join(res) == sample
print('Py_time: %.6f sec' % Py_time)
# Time the decode method which is implemented in C
start_time = time.time()
