Python:可逆地将字母数字字符串编码为整数

以下是我目前掌握的情况:

字符串-->字节

mBytes = m.encode("utf-8")

字节-->int

mInt = int.from_bytes(mBytes, byteorder="big")

int-->字节

mBytes = mInt.to_bytes(((mInt.bit_length() + 7) // 8), byteorder="big")

字节-->一串

m = mBytes.decode("utf-8")

m = "test123"
mBytes = m.encode("utf-8")
mInt = int.from_bytes(mBytes, byteorder="big")
mBytes2 = mInt.to_bytes(((mInt.bit_length() + 7) // 8), byteorder="big")
m2 = mBytes2.decode("utf-8")
print(m == m2)

以下是与上述相同的可重复使用版本:

class BytesIntEncoder:

    @staticmethod
    def encode(b: bytes) -> int:
        return int.from_bytes(b, byteorder='big')

    @staticmethod
    def decode(i: int) -> bytes:
        return i.to_bytes(((i.bit_length() + 7) // 8), byteorder='big')

如果您使用的是Python<3.6,删除可选类型注释。

>>> s = 'Test123'
>>> b = s.encode()
>>> b
b'Test123'

>>> BytesIntEncoder.encode(b)
23755444588720691
>>> BytesIntEncoder.decode(_)
b'Test123'
>>> _.decode()
'Test123'

回想一下,字符串可以编码为字节,然后可以编码为整数。然后可以反转编码,以获得后跟原始字符串的字节。

binascii 产生 同整数编码 和Charle-f回答中的那个。我相信它是相同的,因为我对它进行了广泛的测试。

学分: this answer .

from binascii import hexlify, unhexlify

class BytesIntEncoder:

    @staticmethod
    def encode(b: bytes) -> int:
        return int(hexlify(b), 16) if b != b'' else 0

    @staticmethod
    def decode(i: int) -> int:
        return unhexlify('%x' % i) if i != 0 else b''

快速测试:

>>> s = 'Test123'
>>> b = s.encode()
>>> b
b'Test123'

>>> BytesIntEncoder.encode(b)
23755444588720691
>>> BytesIntEncoder.decode(_)
b'Test123'
>>> _.decode()
'Test123'

假设字符集仅为字母数字,即a-z a-z 0-9,则每个字符需要6位。因此,使用8位字节编码在理论上是对内存的低效使用。

sys.getsizeof ,并且更可能用于较大的字符串。

string.ascii_lowercase string.ascii_uppercase + string.digits

import string


class BytesIntEncoder:

    def __init__(self, chars: bytes = (string.ascii_letters + string.digits).encode()):
        num_chars = len(chars)
        translation = ''.join(chr(i) for i in range(1, num_chars + 1)).encode()
        self._translation_table = bytes.maketrans(chars, translation)
        self._reverse_translation_table = bytes.maketrans(translation, chars)
        self._num_bits_per_char = (num_chars + 1).bit_length()

    def encode(self, chars: bytes) -> int:
        num_bits_per_char = self._num_bits_per_char
        output, bit_idx = 0, 0
        for chr_idx in chars.translate(self._translation_table):
            output |= (chr_idx << bit_idx)
            bit_idx += num_bits_per_char
        return output

    def decode(self, i: int) -> bytes:
        maxint = (2 ** self._num_bits_per_char) - 1
        output = bytes(((i >> offset) & maxint) for offset in range(0, i.bit_length(), self._num_bits_per_char))
        return output.translate(self._reverse_translation_table)


# Test
import itertools
import random
import unittest


class TestBytesIntEncoder(unittest.TestCase):

    chars = string.ascii_letters + string.digits
    encoder = BytesIntEncoder(chars.encode())

    def _test_encoding(self, b_in: bytes):
        i = self.encoder.encode(b_in)
        self.assertIsInstance(i, int)
        b_out = self.encoder.decode(i)
        self.assertIsInstance(b_out, bytes)
        self.assertEqual(b_in, b_out)
        # print(b_in, i)

    def test_thoroughly_with_small_str(self):
        for s_len in range(4):
            for s in itertools.combinations_with_replacement(self.chars, s_len):
                s = ''.join(s)
                b_in = s.encode()
                self._test_encoding(b_in)

    def test_randomly_with_large_str(self):
        for s_len in range(256):
            num_samples = {s_len <= 16: 2 ** s_len,
                           16 < s_len <= 32: s_len ** 2,
                           s_len > 32: s_len * 2,
                           s_len > 64: s_len,
                           s_len > 128: 2}[True]
            # print(s_len, num_samples)
            for _ in range(num_samples):
                b_in = ''.join(random.choices(self.chars, k=s_len)).encode()
                self._test_encoding(b_in)


if __name__ == '__main__':
    unittest.main()

用法示例:

>>> encoder = BytesIntEncoder()
>>> s = 'Test123'
>>> b = s.encode()
>>> b
b'Test123'

>>> encoder.encode(b)
3908257788270
>>> encoder.decode(_)
b'Test123'

所以我需要一本数字字典, 它可能看起来有点难看,但它的效率很高,因为每个字符(英文字母)正好是2个数字,但它可以传输任何类型的unicode字符

import json

myDict = {
    "le key": "le Valueue",
    2 : {
        "heya": 1234569,
        "3": 4
    },
    'Α α, Β β, Γ γ' : 'שלום'
}
def convertDictToNum(toBeConverted):
    return int(''.join([(lambda c: c if len(c) ==2 else '0'+c )(str(ord(c) - 26)) for c in str(json.dumps(toBeConverted))]))

def loadDictFromNum(toBeDecoded):
    toBeDecoded = str(toBeDecoded)
    return json.loads(''.join([chr(int(toBeDecoded[cut:cut + 2]) + 26) for cut in range(0, len(toBeDecoded), 2)]))

numbersDict = convertDictToNum(myDict)
print(numbersDict)
# 9708827506817595083206088....
recoveredDict = loadDictFromNum(numbersDict)
print(recoveredDict)
# {'le key': 'le Valueue', '2': {'heya': 1234569, '3': 4}, 'Α α, Β β, Γ γ': 'שלום'}