Created
September 28, 2014 01:03
-
-
Save pleonex/c5b04eb9dcecd93628d7 to your computer and use it in GitHub Desktop.
Encode / Decode a string with the Ninokuni default encoding table.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/python | |
""" | |
ninostring.py: Encode / Decode a string with the Ninokuni default table. | |
Copyright (C) 2014 pleonex | |
This program is free software: you can redistribute it and/or modify | |
it under the terms of the GNU General Public License as published by | |
the Free Software Foundation, either version 2 of the License, or | |
(at your option) any later version. | |
This program is distributed in the hope that it will be useful, | |
but WITHOUT ANY WARRANTY; without even the implied warranty of | |
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
GNU General Public License for more details. | |
You should have received a copy of the GNU General Public License | |
along with this program. If not, see <http://www.gnu.org/licenses/>. | |
""" | |
class TableEntry: | |
""" Reperesent an entry in the table encoding. """ | |
def __init__(self, first_char, idx_start, num_chars): | |
""" Create a new instance of the class. | |
Args: | |
first_char (int list): First shift-jis char in the range. | |
idx_start (int): First encoding byte in the range. | |
num_chars (int): Number of chars in this range. | |
""" | |
self.first_char = unicode(first_char, 'shift-jis') | |
self.idx_start = idx_start | |
self.num_chars = num_chars | |
def sum_char(self, c, i): | |
""" Increments a char with a number. | |
Args: | |
c (char): Char to increment. | |
i (int): Increment. | |
Returns: | |
char: The char with the increment. | |
""" | |
return unichr(ord(c) + i) | |
def get_first_char(self): | |
""" Gets the first shift-jis char in the range. | |
Returns: | |
char: The first char in the range. | |
""" | |
return self.first_char | |
def get_last_char(self): | |
""" Gets the last shift-jis char in the range. | |
Returns: | |
char: The last char in the range. | |
""" | |
return self.sum_char(self.get_first_char(), self.get_num_chars()) | |
def get_idx_start(self): | |
""" Gets the first encoding byte in the range. | |
Returns: | |
int: The first encoding byte in the range. | |
""" | |
return self.idx_start | |
def get_idx_end(self): | |
""" Gets the last encoding byte in the range. | |
Returns: | |
int: The last encoding byte in the range. | |
""" | |
return self.get_idx_start() + self.get_num_chars() | |
def get_num_chars(self): | |
""" Gets the number of chars in the range. | |
Returns: | |
int: The number of chars in the range. | |
""" | |
return self.num_chars | |
def contains_char(self, c): | |
""" Checks if the decoded char it's in this encoding entry range. | |
Args: | |
c (unicode): Char to check. | |
Returns: | |
bool: If the char is in the range. | |
""" | |
return c >= self.get_first_char() and c <= self.get_last_char() | |
def contains_idx(self, b): | |
""" Checks if the encoded integer it's in this encoding entry range. | |
Args: | |
b (int): Encoded integer to check. | |
Returns: | |
bool: If the encoded integer is in the range. | |
""" | |
return b >= self.get_idx_start() and b <= self.get_idx_end() | |
def decode_char(self, b): | |
""" Decode a encoded integer to a char using this range. | |
Args: | |
b (int): Encoded integer to decode. | |
Returns: | |
unicode: Decoded unicode char. | |
""" | |
return self.sum_char(self.get_first_char(), (b - self.get_idx_start())) | |
def encode_char(self, c): | |
""" Encode a char to a encoded integer using this range. | |
Args: | |
c (unicode): Char to encode. | |
Returns: | |
int: Encoded intenger. | |
""" | |
return self.get_idx_start() + (ord(c) - ord(self.get_first_char())) | |
def decode(bs, entries): | |
""" Decode a list of encoded integers to a string. | |
Args: | |
bs (int list): Encoded integer list. | |
entries (TableEntry list): Table to use to decode. | |
Returns: | |
unicode: Decoded unicode string. | |
""" | |
newS = unicode() | |
for b in bs: | |
# print str(b) + " ->", | |
# Search the table | |
table = None | |
for t in entries: | |
if (t.contains_idx(b)): | |
table = t | |
# Decode the integer | |
# print str(table.get_idx_start()) | |
newS += table.decode_char(b) | |
return newS | |
def encode(ss, entries): | |
""" Encode a string to a list of encoded integers. | |
Args: | |
ss (unicode): Unico string to encode. | |
entries (TableEntry list): Table to use to encode. | |
Returns: | |
int list: Encoded integer list. | |
""" | |
newS = [] | |
for c in ss: | |
# print c.encode('utf-8') + " ->", | |
# Search the table | |
table = None | |
for t in entries: | |
if (t.contains_char(c)): | |
table = t | |
# Encode the char | |
# print table.get_first_char().encode('utf-8') | |
newS.append(table.encode_char(c)) | |
return newS | |
if __name__ == "__main__": | |
# Create the encoding table | |
entries = [] | |
entries.append(TableEntry('\x81\x40', 0x01, 0x01)) | |
entries.append(TableEntry('\x82\x4F', 0x02, 0x0A)) | |
entries.append(TableEntry('\x82\x9F', 0x0C, 0x53)) | |
entries.append(TableEntry('\x83\x40', 0x5F, 0x57)) | |
entries.append(TableEntry('\x81\x5B', 0xB6, 0x01)) | |
entries.append(TableEntry('\x81\x60', 0xB7, 0x01)) | |
entries.append(TableEntry('\x81\x48', 0xB8, 0x02)) | |
entries.append(TableEntry('\x81\x41', 0xBA, 0x01)) | |
entries.append(TableEntry('\x81\x42', 0xBB, 0x01)) | |
# Gets the string to encode in unicode format | |
s = unicode(u'\u30ce\u30fc\u30b3\u30e1\u30f3\u30c8') | |
print s.encode('utf-8') | |
# Encode it | |
enc = encode(s, entries) | |
print "[", | |
for e in enc: | |
print hex(e), | |
print "]" | |
# Decode it | |
dec = decode(enc, entries) | |
print dec.encode('utf-8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment