def do(self):
self.write_byte(self.__in[self.__offset])
self.__offset += 1
while self.__offset < self.__length:
offset, length = find_longest_match(self.__in[:self.__offset],
self.__in[self.__offset:])
if offset >= 1 and length >= 4:
self.__dictcopy(offset, length)
else:
self.__literal()
return self.getdata()
def do(self):
self.write_byte(self.__in[self.__offset])
self.__offset += 1
while self.__offset < self.__length:
offset, length = find_longest_match(self.__in[:self.__offset],
self.__in[self.__offset:])
if offset >= 1 and length >= 4:
self.__dictcopy(offset, length)
else:
self.__literal()
return self.getdata()
def compress(data_to_compress):
offset = 0
compressed_data = []
length = len(data_to_compress)
while offset < length:
#find the longest match for the next word to encode
match_offset, match_length = find_longest_match(data_to_compress[:offset],
data_to_compress[offset:])
#get the next symbol, if there is something else to compress
symbol = data_to_compress[offset + match_length] if offset + match_length < length else ''
compressed_data.append({"offset": match_offset, "length":match_length, "symbol":symbol})
offset += match_length + 1 # +1 since the next char is included in symbol
return compressed_data
def compress(data_to_compress):
offset = 0
compressed_data = []
length = len(data_to_compress)
while offset < length:
match_offset, match_length = find_longest_match(data_to_compress[:offset],
data_to_compress[offset:])
if match_length == 0:
symbol = data_to_compress[offset]
compressed_data.append({"literal":True, "symbol":symbol})
offset += 1
else:
compressed_data.append({"literal":False, "offset":match_offset, "length":match_length})
offset += match_length
return compressed_data
def do(self):
self.__literal(False)
while self.__offset < self.__length:
offset, length = find_longest_match(self.__in[: self.__offset], self.__in[self.__offset :])
if length == 0:
c = self.__in[self.__offset]
if c == "\x00":
self.__singlebyte(0)
else:
self.__literal()
elif length == 1 and 0 <= offset < 16:
self.__singlebyte(offset)
elif 2 <= length <= 3 and 0 < offset <= 127:
self.__shortblock(offset, length)
elif 3 <= length and 2 <= offset:
self.__block(offset, length)
else:
self.__literal()
# raise ValueError("no parsing found", offset, length)
self.__end()
return self.getdata()
def do(self):
self.__literal(False)
while self.__offset < self.__length:
offset, length = find_longest_match(self.__in[:self.__offset],
self.__in[self.__offset:])
if length == 0:
c = self.__in[self.__offset]
if c == "\x00":
self.__singlebyte(0)
else:
self.__literal()
elif length == 1 and 0 <= offset < 16:
self.__singlebyte(offset)
elif 2 <= length <= 3 and 0 < offset <= 127:
self.__shortblock(offset, length)
elif 3 <= length and 2 <= offset:
self.__block(offset, length)
else:
self.__literal()
#raise ValueError("no parsing found", offset, length)
self.__end()
return self.getdata()
def compress(data_to_compress):
offset = 0
compressed_data = []
length = len(data_to_compress)
while offset < length:
match_offset, match_length = find_longest_match(
data_to_compress[:offset], data_to_compress[offset:])
if match_length == 0:
symbol = data_to_compress[offset]
compressed_data.append({"literal": True, "symbol": symbol})
offset += 1
else:
compressed_data.append({
"literal": False,
"offset": match_offset,
"length": match_length
})
offset += match_length
return compressed_data
#
#Kabopan - Readable Algorithms. Public Domain, 2007-2009
from kbp.comp._lz77 import find_longest_match, back_copy
assert find_longest_match("abc","a") == (3, 1)
assert find_longest_match("abc","d") == (0, 0)
assert find_longest_match("abcab","ab") == (2, 2)
assert back_copy("a", 1, 1) == "aa"
assert back_copy("ab", 2, 2) == "abab"
assert back_copy("duplicate me please", 9, 19) == "duplicate me pleaseduplicate"