[1] | 1 | ''' |
---|
| 2 | A collection of tools to assist in analyzing encrypted blobs of data |
---|
| 3 | |
---|
[66] | 4 | Copyright (C) 2011-2013 Virtual Security Research, LLC |
---|
[1] | 5 | Author: Timothy D. Morgan, Jason A. Donenfeld |
---|
| 6 | |
---|
| 7 | This program is free software: you can redistribute it and/or modify |
---|
| 8 | it under the terms of the GNU Lesser General Public License, version 3, |
---|
| 9 | as published by the Free Software Foundation. |
---|
| 10 | |
---|
| 11 | This program is distributed in the hope that it will be useful, |
---|
| 12 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 13 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 14 | GNU General Public License for more details. |
---|
| 15 | |
---|
| 16 | You should have received a copy of the GNU General Public License |
---|
| 17 | along with this program. If not, see <http://www.gnu.org/licenses/>. |
---|
| 18 | ''' |
---|
| 19 | |
---|
| 20 | import sys |
---|
| 21 | import base64 |
---|
| 22 | import binascii |
---|
[44] | 23 | import traceback |
---|
[1] | 24 | import fractions |
---|
| 25 | import operator |
---|
| 26 | import functools |
---|
[40] | 27 | from . import buffertools |
---|
[1] | 28 | |
---|
[40] | 29 | |
---|
| 30 | # urllib.parse's functions are not well suited for encoding/decoding |
---|
| 31 | # bytes or managing encoded case |
---|
| 32 | def _percentEncode(binary, plus=False, upper=True): |
---|
[82] | 33 | fmt = "%%%.2x" |
---|
[40] | 34 | if upper: |
---|
[82] | 35 | fmt = "%%%.2X" |
---|
[40] | 36 | |
---|
[45] | 37 | ret_val = bytearray(b'') |
---|
[40] | 38 | for c in binary: |
---|
| 39 | if c not in b'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789': |
---|
[45] | 40 | ret_val.extend((fmt % c).encode('ascii')) |
---|
[40] | 41 | elif plus and (c == 20): |
---|
[45] | 42 | ret_val.extend(b'+') |
---|
[40] | 43 | else: |
---|
[45] | 44 | ret_val.append(c) |
---|
[40] | 45 | |
---|
| 46 | return ret_val |
---|
| 47 | |
---|
| 48 | |
---|
| 49 | def _percentDecode(binary, plus=False): |
---|
| 50 | if plus: |
---|
| 51 | binary = binary.replace(b'+', b' ') |
---|
| 52 | if binary == b'': |
---|
| 53 | return b'' |
---|
| 54 | chunks = binary.split(b'%') |
---|
| 55 | |
---|
[44] | 56 | ret_val = chunks[0] |
---|
| 57 | for chunk in chunks[1:]: |
---|
[40] | 58 | if len(chunk) < 2: |
---|
| 59 | return None |
---|
| 60 | try: |
---|
| 61 | ret_val += bytes([int(chunk[0:2], 16)]) + chunk[2:] |
---|
| 62 | except: |
---|
[44] | 63 | #traceback.print_exc() |
---|
| 64 | #print(repr(chunk), repr(binary)) |
---|
[40] | 65 | return None |
---|
| 66 | |
---|
| 67 | return ret_val |
---|
| 68 | |
---|
| 69 | |
---|
[1] | 70 | # abstract class |
---|
| 71 | class DataEncoding(object): |
---|
[40] | 72 | charset = frozenset(b'') |
---|
| 73 | extraneous_chars = b'' |
---|
[1] | 74 | dialect = None |
---|
| 75 | name = None |
---|
| 76 | priority = None |
---|
| 77 | |
---|
| 78 | def __init__(self, dialect=''): |
---|
| 79 | self.dialect = dialect |
---|
| 80 | |
---|
| 81 | def isExample(self, blob): |
---|
| 82 | sblob = frozenset(blob) |
---|
[20] | 83 | if self.charset != None and not sblob.issubset(self.charset): |
---|
| 84 | return False |
---|
| 85 | return self.extraTests(blob) |
---|
[1] | 86 | |
---|
| 87 | def extraTests(self, blob): |
---|
[20] | 88 | """May return True, False, or None, for is an example, isn't an |
---|
| 89 | example, or unknown, respectively. |
---|
| 90 | |
---|
| 91 | """ |
---|
[1] | 92 | return True |
---|
| 93 | |
---|
| 94 | def decode(self, blob): |
---|
| 95 | return None |
---|
| 96 | |
---|
| 97 | def encode(self, blob): |
---|
| 98 | return None |
---|
| 99 | |
---|
| 100 | |
---|
| 101 | class base64Encoding(DataEncoding): |
---|
| 102 | name = 'base64' |
---|
| 103 | def __init__(self, dialect='rfc3548'): |
---|
| 104 | super(base64Encoding, self).__init__(dialect) |
---|
| 105 | if dialect.startswith('rfc3548'): |
---|
[40] | 106 | self.c62 = b'+' |
---|
| 107 | self.c63 = b'/' |
---|
| 108 | self.pad = b'=' |
---|
[1] | 109 | elif dialect.startswith('filename'): |
---|
[40] | 110 | self.c62 = b'+' |
---|
| 111 | self.c63 = b'-' |
---|
| 112 | self.pad = b'=' |
---|
[1] | 113 | elif dialect.startswith('url1'): |
---|
[40] | 114 | self.c62 = b'-' |
---|
| 115 | self.c63 = b'_' |
---|
| 116 | self.pad = b'=' |
---|
[1] | 117 | elif dialect.startswith('url2'): |
---|
[40] | 118 | self.c62 = b'-' |
---|
| 119 | self.c63 = b'_' |
---|
| 120 | self.pad = b'.' |
---|
[1] | 121 | elif dialect.startswith('url3'): |
---|
[40] | 122 | self.c62 = b'_' |
---|
| 123 | self.c63 = b'-' |
---|
| 124 | self.pad = b'.' |
---|
[1] | 125 | elif dialect.startswith('url4'): |
---|
[40] | 126 | self.c62 = b'-' |
---|
| 127 | self.c63 = b'_' |
---|
| 128 | self.pad = b'!' |
---|
[1] | 129 | elif dialect.startswith('url5'): |
---|
[40] | 130 | self.c62 = b'+' |
---|
| 131 | self.c63 = b'/' |
---|
| 132 | self.pad = b'$' |
---|
[53] | 133 | elif dialect.startswith('url6'): |
---|
| 134 | self.c62 = b'*' |
---|
| 135 | self.c63 = b'/' |
---|
| 136 | self.pad = b'=' |
---|
[1] | 137 | elif dialect.startswith('otkurl'): |
---|
[40] | 138 | self.c62 = b'-' |
---|
| 139 | self.c63 = b'_' |
---|
| 140 | self.pad = b'*' |
---|
[1] | 141 | elif dialect.startswith('xmlnmtoken'): |
---|
[40] | 142 | self.c62 = b'.' |
---|
| 143 | self.c63 = b'-' |
---|
| 144 | self.pad = b'=' |
---|
[1] | 145 | elif dialect.startswith('xmlname'): |
---|
[40] | 146 | self.c62 = b'_' |
---|
| 147 | self.c63 = b':' |
---|
| 148 | self.pad = b'=' |
---|
[1] | 149 | |
---|
[34] | 150 | if 'newline' in dialect: |
---|
[40] | 151 | self.extraneous_chars = b'\r\n' |
---|
[34] | 152 | |
---|
[40] | 153 | self.charset = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ' |
---|
| 154 | +b'abcdefghijklmnopqrstuvwxyz0123456789' |
---|
[34] | 155 | +self.c62+self.c63+self.pad+self.extraneous_chars) |
---|
[1] | 156 | |
---|
| 157 | def _guessPadLength(self, nopad_len): |
---|
| 158 | length = ((4 - nopad_len % 4) % 4) |
---|
| 159 | if length != 3: |
---|
| 160 | return length |
---|
| 161 | return None |
---|
| 162 | |
---|
| 163 | def extraTests(self, blob): |
---|
[34] | 164 | for c in self.extraneous_chars: |
---|
[40] | 165 | blob = blob.replace(bytes([c]), b'') |
---|
[34] | 166 | |
---|
[66] | 167 | if self.dialect.endswith('intpad'): |
---|
| 168 | if blob[-1] not in b'012': |
---|
| 169 | return False |
---|
| 170 | nopad = blob[:-1] |
---|
| 171 | padlen = blob[-1] - 48 # see the ascii table |
---|
| 172 | else: |
---|
| 173 | nopad = blob.rstrip(self.pad) |
---|
| 174 | padlen = len(blob) - len(nopad) |
---|
| 175 | |
---|
| 176 | # what the pad length ought to be |
---|
[1] | 177 | padlen_guess = self._guessPadLength(len(nopad)) |
---|
| 178 | if padlen_guess == None: |
---|
| 179 | return False |
---|
| 180 | |
---|
| 181 | # we don't accept bad pads, only missing pads |
---|
| 182 | if self.dialect.endswith('nopad'): |
---|
| 183 | return self.pad not in blob |
---|
| 184 | |
---|
| 185 | # pad must not appear in the middle of the |
---|
| 186 | # string and must be the correct length at the end |
---|
[66] | 187 | return (self.pad not in nopad) and (padlen == padlen_guess) |
---|
[1] | 188 | |
---|
| 189 | def decode(self, blob): |
---|
[34] | 190 | for c in self.extraneous_chars: |
---|
[40] | 191 | blob = blob.replace(bytes(c), b'') |
---|
[34] | 192 | |
---|
[66] | 193 | if self.dialect.endswith('intpad'): |
---|
| 194 | padlen = blob[-1] - 48 # see the ascii table |
---|
| 195 | padlen_guess = self._guessPadLength(len(blob[:-1])) |
---|
| 196 | if padlen != padlen_guess: |
---|
| 197 | raise Exception("Invalid length for int-padded base64 string. (%d != %d)" |
---|
| 198 | % (padlen, padlen_guess)) |
---|
| 199 | |
---|
| 200 | blob = blob[:-1] + (self.pad*padlen) |
---|
| 201 | |
---|
[1] | 202 | if self.dialect.endswith('nopad'): |
---|
| 203 | if self.pad in blob: |
---|
| 204 | raise Exception("Unpadded base64 string contains pad character") |
---|
| 205 | |
---|
| 206 | padlen = self._guessPadLength(len(blob)) |
---|
| 207 | if padlen == None: |
---|
| 208 | raise Exception("Invalid length for unpadded base64 string.") |
---|
| 209 | |
---|
| 210 | blob = blob+(self.pad*padlen) |
---|
| 211 | |
---|
| 212 | if not self.dialect.startswith('rfc3548'): |
---|
[42] | 213 | table = bytes.maketrans(self.c62+self.c63+self.pad, b'+/=') |
---|
[1] | 214 | blob = blob.translate(table) |
---|
| 215 | |
---|
| 216 | return base64.standard_b64decode(blob) |
---|
| 217 | |
---|
| 218 | |
---|
| 219 | def encode(self, blob): |
---|
| 220 | ret_val = base64.standard_b64encode(blob) |
---|
| 221 | |
---|
| 222 | if not self.dialect.startswith('rfc3548'): |
---|
[42] | 223 | table = bytes.maketrans(b'+/=', self.c62+self.c63+self.pad) |
---|
[1] | 224 | ret_val = ret_val.translate(table) |
---|
| 225 | |
---|
| 226 | if ret_val != None and self.dialect.endswith('nopad'): |
---|
| 227 | ret_val = ret_val.rstrip(self.pad) |
---|
| 228 | |
---|
[66] | 229 | if ret_val != None and self.dialect.endswith('intpad'): |
---|
| 230 | stripped = ret_val.rstrip(self.pad) |
---|
| 231 | ret_val = stripped + ("%d" % (len(ret_val) - len(stripped))).encode('utf-8') |
---|
| 232 | |
---|
[1] | 233 | return ret_val |
---|
| 234 | |
---|
| 235 | |
---|
| 236 | class base32Encoding(DataEncoding): |
---|
| 237 | name = 'base32' |
---|
| 238 | def __init__(self, dialect='rfc3548upper'): |
---|
| 239 | super(base32Encoding, self).__init__(dialect) |
---|
| 240 | if dialect.startswith('rfc3548upper'): |
---|
[40] | 241 | self.pad = b'=' |
---|
| 242 | self.charset = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ234567'+self.pad) |
---|
[1] | 243 | |
---|
| 244 | elif dialect.startswith('rfc3548lower'): |
---|
[40] | 245 | self.pad = b'=' |
---|
| 246 | self.charset = frozenset(b'abcdefghijklmnopqrstuvwxyz234567'+self.pad) |
---|
[1] | 247 | |
---|
| 248 | def _guessPadLength(self, nopad_len): |
---|
| 249 | pad_lengths = {0:0, 7:1, 5:3, 4:4, 2:6} |
---|
| 250 | return pad_lengths.get(nopad_len%8, None) |
---|
| 251 | |
---|
| 252 | def extraTests(self, blob): |
---|
| 253 | nopad = blob.rstrip(self.pad) |
---|
| 254 | padlen_guess = self._guessPadLength(len(nopad)) |
---|
| 255 | if padlen_guess == None: |
---|
| 256 | return False |
---|
| 257 | |
---|
| 258 | # we don't accept bad pads, only missing pads |
---|
| 259 | if self.dialect.endswith('nopad'): |
---|
| 260 | return self.pad not in blob |
---|
| 261 | |
---|
| 262 | # pad must not appear in the middle of the |
---|
| 263 | # string and must be the correct length at the end |
---|
| 264 | return (self.pad not in nopad) and (len(blob) == len(nopad)+padlen_guess) |
---|
| 265 | |
---|
| 266 | |
---|
| 267 | def decode(self, blob): |
---|
| 268 | if self.dialect.endswith('nopad'): |
---|
| 269 | if self.pad in blob: |
---|
[40] | 270 | raise Exception("Unpadded base32 string contains pad character") |
---|
[1] | 271 | |
---|
| 272 | padlen = self._guessPadLength(len(blob)) |
---|
| 273 | if padlen == None: |
---|
| 274 | raise Exception("Invalid length for unpadded base64 string.") |
---|
| 275 | |
---|
| 276 | blob = blob+(self.pad*padlen) |
---|
| 277 | |
---|
| 278 | return base64.b32decode(blob.upper()) |
---|
| 279 | |
---|
| 280 | |
---|
| 281 | def encode(self, blob): |
---|
| 282 | ret_val = base64.b32encode(blob) |
---|
| 283 | |
---|
| 284 | if ret_val != None and self.dialect.endswith('nopad'): |
---|
| 285 | ret_val = ret_val.rstrip(self.pad) |
---|
| 286 | |
---|
| 287 | if 'lower' in self.dialect: |
---|
| 288 | ret_val = ret_val.lower() |
---|
| 289 | else: |
---|
| 290 | ret_val = ret_val.upper() |
---|
| 291 | |
---|
| 292 | return ret_val |
---|
| 293 | |
---|
| 294 | |
---|
| 295 | class hexEncoding(DataEncoding): |
---|
| 296 | name = 'hex' |
---|
| 297 | def __init__(self, dialect='mixed'): |
---|
| 298 | super(hexEncoding, self).__init__(dialect) |
---|
| 299 | if 'mixed' in dialect: |
---|
[40] | 300 | self.charset = frozenset(b'ABCDEFabcdef0123456789') |
---|
[1] | 301 | elif 'upper' in dialect: |
---|
[40] | 302 | self.charset = frozenset(b'ABCDEF0123456789') |
---|
[1] | 303 | elif 'lower' in dialect: |
---|
[40] | 304 | self.charset = frozenset(b'abcdef0123456789') |
---|
[1] | 305 | |
---|
| 306 | |
---|
| 307 | def extraTests(self, blob): |
---|
| 308 | return (len(blob) % 2 == 0) |
---|
| 309 | |
---|
| 310 | def decode(self, blob): |
---|
| 311 | return binascii.a2b_hex(blob) |
---|
| 312 | |
---|
| 313 | def encode(self, blob): |
---|
| 314 | if 'upper' in self.dialect: |
---|
| 315 | return binascii.b2a_hex(blob).upper() |
---|
| 316 | if 'lower' in self.dialect: |
---|
| 317 | return binascii.b2a_hex(blob).lower() |
---|
| 318 | else: |
---|
| 319 | return binascii.b2a_hex(blob) |
---|
| 320 | |
---|
| 321 | |
---|
| 322 | class percentEncoding(DataEncoding): |
---|
| 323 | name = 'percent' |
---|
| 324 | def __init__(self, dialect='mixed'): |
---|
| 325 | super(percentEncoding, self).__init__(dialect) |
---|
| 326 | self.charset = None |
---|
| 327 | if 'mixed' in dialect: |
---|
[40] | 328 | self.hexchars = frozenset(b'ABCDEFabcdef0123456789') |
---|
[1] | 329 | elif 'upper' in dialect: |
---|
[40] | 330 | self.hexchars = frozenset(b'ABCDEF0123456789') |
---|
[1] | 331 | elif 'lower' in dialect: |
---|
[40] | 332 | self.hexchars = frozenset(b'abcdef0123456789') |
---|
[1] | 333 | |
---|
| 334 | def extraTests(self, blob): |
---|
[40] | 335 | chunks = blob.split(b'%') |
---|
[1] | 336 | if len(chunks) < 2: |
---|
[20] | 337 | return None |
---|
[1] | 338 | for c in chunks[1:]: |
---|
| 339 | if len(c) < 2: |
---|
| 340 | return False |
---|
| 341 | if (c[0] not in self.hexchars) or (c[1] not in self.hexchars): |
---|
| 342 | return False |
---|
| 343 | return True |
---|
| 344 | |
---|
| 345 | def decode(self, blob): |
---|
[40] | 346 | plus = False |
---|
[1] | 347 | if 'plus' in self.dialect: |
---|
[40] | 348 | plus = True |
---|
| 349 | return _percentDecode(blob, plus=plus) |
---|
[1] | 350 | |
---|
| 351 | def encode(self, blob): |
---|
[40] | 352 | upper = True |
---|
| 353 | plus = False |
---|
[1] | 354 | if 'plus' in self.dialect: |
---|
[40] | 355 | plus = True |
---|
| 356 | if 'lower' in self.dialect: |
---|
| 357 | upper = False |
---|
[1] | 358 | |
---|
[40] | 359 | return _percentEncode(blob, plus=plus, upper=upper) |
---|
[1] | 360 | |
---|
[66] | 361 | # XXX: need a better way to organize these with the possible combinations of dialects, padding, etc |
---|
| 362 | # for instance, can we have rfc3548-newline-nopad ? |
---|
[1] | 363 | priorities = [ |
---|
| 364 | (hexEncoding, 'upper', 100), |
---|
| 365 | (hexEncoding, 'lower', 101), |
---|
| 366 | (hexEncoding, 'mixed', 102), |
---|
| 367 | (base32Encoding, 'rfc3548upper', 150), |
---|
| 368 | (base32Encoding, 'rfc3548lower', 151), |
---|
| 369 | (base32Encoding, 'rfc3548upper-nopad', 160), |
---|
| 370 | (base32Encoding, 'rfc3548lower-nopad', 161), |
---|
| 371 | (base64Encoding, 'rfc3548', 200), |
---|
| 372 | (base64Encoding, 'rfc3548-nopad', 201), |
---|
[34] | 373 | (base64Encoding, 'rfc3548-newline', 202), |
---|
[66] | 374 | (base64Encoding, 'rfc3548-intpad', 203), |
---|
[1] | 375 | (base64Encoding, 'filename', 210), |
---|
| 376 | (base64Encoding, 'filename-nopad', 211), |
---|
[66] | 377 | (base64Encoding, 'filename-intpad', 212), |
---|
[1] | 378 | (base64Encoding, 'url1', 230), |
---|
| 379 | (base64Encoding, 'url1-nopad', 231), |
---|
[66] | 380 | (base64Encoding, 'url1-intpad', 232), |
---|
[1] | 381 | (base64Encoding, 'otkurl', 235), |
---|
| 382 | (base64Encoding, 'otkurl-nopad', 236), |
---|
[66] | 383 | (base64Encoding, 'otkurl-intpad', 237), |
---|
[1] | 384 | (base64Encoding, 'url2', 240), |
---|
| 385 | (base64Encoding, 'url2-nopad', 241), |
---|
[66] | 386 | (base64Encoding, 'url2-intpad', 242), |
---|
[1] | 387 | (base64Encoding, 'url3', 250), |
---|
| 388 | (base64Encoding, 'url3-nopad', 251), |
---|
[66] | 389 | (base64Encoding, 'url3-intpad', 252), |
---|
[1] | 390 | (base64Encoding, 'url4', 260), |
---|
| 391 | (base64Encoding, 'url4-nopad', 261), |
---|
[66] | 392 | (base64Encoding, 'url4-intpad', 262), |
---|
[1] | 393 | (base64Encoding, 'url5', 265), |
---|
| 394 | (base64Encoding, 'url5-nopad', 266), |
---|
[66] | 395 | (base64Encoding, 'url5-intpad', 267), |
---|
[53] | 396 | (base64Encoding, 'url6', 267), |
---|
| 397 | (base64Encoding, 'url6-nopad', 268), |
---|
[66] | 398 | (base64Encoding, 'url6-intpad', 269), |
---|
[1] | 399 | (base64Encoding, 'xmlnmtoken', 270), |
---|
| 400 | (base64Encoding, 'xmlnmtoken-nopad', 271), |
---|
[66] | 401 | (base64Encoding, 'xmlnmtoken-intpad', 272), |
---|
[1] | 402 | (base64Encoding, 'xmlname', 280), |
---|
| 403 | (base64Encoding, 'xmlname-nopad', 281), |
---|
[66] | 404 | (base64Encoding, 'xmlname-intpad', 282), |
---|
[1] | 405 | (percentEncoding, 'upper-plus', 400), |
---|
| 406 | (percentEncoding, 'upper', 401), |
---|
| 407 | (percentEncoding, 'lower-plus', 410), |
---|
| 408 | (percentEncoding, 'lower', 411), |
---|
| 409 | (percentEncoding, 'mixed-plus', 420), |
---|
| 410 | (percentEncoding, 'mixed', 421), |
---|
| 411 | ] |
---|
| 412 | |
---|
| 413 | encodings = {} |
---|
| 414 | for enc,d,p in priorities: |
---|
| 415 | e = enc(d) |
---|
| 416 | e.priority = p |
---|
| 417 | encodings["%s/%s" % (enc.name, d)] = e |
---|
| 418 | |
---|
[67] | 419 | |
---|
[28] | 420 | def supportedEncodings(): |
---|
[40] | 421 | e = list(encodings.keys()) |
---|
[28] | 422 | e.sort() |
---|
| 423 | return e |
---|
[1] | 424 | |
---|
[28] | 425 | |
---|
[1] | 426 | def possibleEncodings(blob): |
---|
[20] | 427 | likely = set() |
---|
| 428 | possible = set() |
---|
[1] | 429 | for name,encoding in encodings.items(): |
---|
[20] | 430 | result = encoding.isExample(blob) |
---|
| 431 | if result == True: |
---|
| 432 | likely.add(name) |
---|
| 433 | elif result == None: |
---|
| 434 | possible.add(name) |
---|
| 435 | return likely,possible |
---|
[1] | 436 | |
---|
| 437 | |
---|
| 438 | def encodingIntersection(blobs): |
---|
| 439 | ret_val = set(encodings.keys()) |
---|
[20] | 440 | p = set(encodings.keys()) |
---|
[1] | 441 | for b in blobs: |
---|
[20] | 442 | likely,possible = possibleEncodings(b) |
---|
| 443 | ret_val &= likely | possible |
---|
| 444 | p &= possible |
---|
| 445 | return ret_val - p |
---|
[1] | 446 | |
---|
| 447 | |
---|
| 448 | def bestEncoding(encs): |
---|
| 449 | priority = 999999999 |
---|
| 450 | best = None |
---|
| 451 | for e in encs: |
---|
| 452 | if encodings[e].priority < priority: |
---|
| 453 | best = e |
---|
| 454 | priority = encodings[e].priority |
---|
| 455 | return best |
---|
| 456 | |
---|
| 457 | |
---|
| 458 | def decode(encoding, blob): |
---|
[67] | 459 | """Given an encoding name and a blob, decodes the blob and returns it. |
---|
| 460 | |
---|
| 461 | encoding -- A string representation of the encoding and dialect. |
---|
| 462 | For a list of valid encoding names, run: |
---|
| 463 | bletchley-analyze -e ? |
---|
| 464 | |
---|
| 465 | blob -- A bytes or bytearray object to be decoded. If a string |
---|
| 466 | is provided instead, it will be converted to a bytes |
---|
| 467 | object using 'utf-8'. |
---|
| 468 | |
---|
| 469 | Returns a bytes object containing the decoded representation of |
---|
| 470 | blob. Will throw various types of exceptions if a problem is |
---|
| 471 | encountered. |
---|
| 472 | """ |
---|
| 473 | if isinstance(blob, str): |
---|
| 474 | blob = blob.encode('utf-8') |
---|
[1] | 475 | return encodings[encoding].decode(blob) |
---|
| 476 | |
---|
| 477 | def encode(encoding, blob): |
---|
[67] | 478 | """Given an encoding name and a blob, encodes the blob and returns it. |
---|
| 479 | |
---|
| 480 | encoding -- A string representation of the encoding and dialect. |
---|
| 481 | For a list of valid encoding names, run: |
---|
| 482 | bletchley-analyze -e ? |
---|
| 483 | |
---|
| 484 | blob -- A bytes or bytearray object to be encoded. |
---|
| 485 | |
---|
| 486 | Returns a bytes object containing the encoded representation of |
---|
| 487 | blob. Will throw various types of exceptions if a problem is |
---|
| 488 | encountered.""" |
---|
[1] | 489 | return encodings[encoding].encode(blob) |
---|
| 490 | |
---|
[67] | 491 | |
---|
[1] | 492 | def decodeAll(encoding, blobs): |
---|
[40] | 493 | return [encodings[encoding].decode(b) for b in blobs] |
---|
[1] | 494 | |
---|
[67] | 495 | |
---|
[1] | 496 | def encodeAll(encoding, blobs): |
---|
[40] | 497 | return [encodings[encoding].encode(b) for b in blobs] |
---|
[1] | 498 | |
---|
[67] | 499 | |
---|
[1] | 500 | def decodeChain(decoding_chain, blob): |
---|
[67] | 501 | """Given a sequence of encoding names (decoding_chain) and a blob, |
---|
| 502 | decodes the blob once for each element of the decoding_chain. For |
---|
| 503 | instance, if the decoding_chain were |
---|
| 504 | ['percent/lower', 'base64/rfc3548'] |
---|
| 505 | then blob would first be decoded as 'percent/lower', followed by |
---|
| 506 | 'base64/rfc3548'. |
---|
| 507 | |
---|
| 508 | decoding_chain -- A sequence (list,tuple,...) of string |
---|
| 509 | representations of the encoding and dialect. For a |
---|
| 510 | list of valid encoding names, run: |
---|
| 511 | bletchley-analyze -e ? |
---|
| 512 | |
---|
| 513 | blob -- A bytes or bytearray object to be decoded. If a string |
---|
| 514 | is provided instead, it will be converted to a bytes |
---|
| 515 | object using 'utf-8'. |
---|
| 516 | |
---|
| 517 | Returns a bytes object containing the decoded representation of |
---|
| 518 | blob. Will throw various types of exceptions if a problem is |
---|
| 519 | encountered. |
---|
| 520 | """ |
---|
[1] | 521 | for decoding in decoding_chain: |
---|
| 522 | blob = decode(decoding, blob) |
---|
| 523 | return blob |
---|
| 524 | |
---|
[67] | 525 | |
---|
[1] | 526 | def encodeChain(encoding_chain, blob): |
---|
[67] | 527 | """Given a sequence of encoding names (encoding_chain) and a blob, |
---|
| 528 | encodes the blob once for each element of the encoding_chain. For |
---|
| 529 | instance, if the encoding_chain were |
---|
| 530 | ['base64/rfc3548', 'percent/lower',] |
---|
| 531 | then blob would first be encoded as 'base64/rfc3548', followed by |
---|
| 532 | 'percent/lower'. |
---|
| 533 | |
---|
| 534 | encoding_chain -- A sequence (list,tuple,...) of string |
---|
| 535 | representations of the encoding and dialect. For a |
---|
| 536 | list of valid encoding names, run: |
---|
| 537 | bletchley-analyze -e ? |
---|
| 538 | |
---|
| 539 | blob -- A bytes or bytearray object to be encoded. |
---|
| 540 | |
---|
| 541 | Returns a bytes object containing the encoded representation of |
---|
| 542 | blob. Will throw various types of exceptions if a problem is |
---|
| 543 | encountered. |
---|
| 544 | """ |
---|
[1] | 545 | for encoding in encoding_chain: |
---|
| 546 | blob = encode(encoding, blob) |
---|
| 547 | return blob |
---|
| 548 | |
---|
[67] | 549 | |
---|
[1] | 550 | def getLengths(s): |
---|
| 551 | lengths = set() |
---|
| 552 | for bin in s: |
---|
| 553 | lengths.add(len(bin)) |
---|
| 554 | lengths = list(lengths) |
---|
| 555 | lengths.sort() |
---|
| 556 | return lengths |
---|
| 557 | |
---|
| 558 | |
---|
| 559 | def maxBlockSize(blob_lengths): |
---|
| 560 | divisor = 0 |
---|
| 561 | for bl in blob_lengths: |
---|
| 562 | divisor = fractions.gcd(divisor, bl) |
---|
| 563 | |
---|
| 564 | return divisor |
---|
| 565 | |
---|
| 566 | |
---|
[40] | 567 | allTrue = functools.partial(functools.reduce, (lambda x,y: x and y)) |
---|
[1] | 568 | |
---|
| 569 | def checkCommonBlocksizes(lengths): |
---|
| 570 | common_block_sizes = (8,16,20) |
---|
| 571 | ret_val = [] |
---|
| 572 | for cbs in common_block_sizes: |
---|
| 573 | gcdIsCBS = (lambda x: fractions.gcd(x,cbs)==cbs) |
---|
| 574 | if allTrue(map(gcdIsCBS, lengths)): |
---|
| 575 | ret_val.append(cbs) |
---|
| 576 | return ret_val |
---|
| 577 | |
---|
| 578 | |
---|
| 579 | def int2binary(x, bits=8): |
---|
| 580 | """ |
---|
| 581 | Integer to binary |
---|
| 582 | Count is number of bits |
---|
| 583 | """ |
---|
| 584 | return "".join(map(lambda y:str((x>>y)&1), range(bits-1, -1, -1))) |
---|