这是一个非常快的 C 解决方案，使用位移操作。它假设您知道解码字符串的长度应该是多少。字符串是每个字母表的 0..maximum 范围内的整数向量。用户可以在字符范围受限的字符串之间进行转换。至于题名中的“in-place”，源向量和目的向量可以重叠，但前提是源字母表不大于目的字母表。
/*
recode version 1.0, 22 August 2015
Copyright (C) 2015 Mark Adler
This software is provided 'as-is', without any express or implied
warranty. In no event will the authors be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not
claim that you wrote the original software. If you use this software
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
Mark Adler
madler@alumni.caltech.edu
*/
/* Recode a vector from one alphabet to another using intermediate
variable-length bit codes. */
/* The approach is to use a Huffman code over equiprobable alphabets in two
directions. First to encode the source alphabet to a string of bits, and
second to encode the string of bits to the destination alphabet. This will
be reasonably close to the efficiency of base-encoding with arbitrary
precision arithmetic. */
#include <stddef.h> // size_t
#include <limits.h> // UINT_MAX, ULLONG_MAX
#if UINT_MAX == ULLONG_MAX
# error recode() assumes that long long has more bits than int
#endif
/* Take a list of integers source[0..slen-1], all in the range 0..smax, and
code them into dest[0..*dlen-1], where each value is in the range 0..dmax.
*dlen returns the length of the result, which will not exceed the value of
*dlen when called. If the original *dlen is not large enough to hold the
full result, then recode() will return non-zero to indicate failure.
Otherwise recode() will return 0. recode() will also return non-zero if
either of the smax or dmax parameters are less than one. The non-zero
return codes are 1 if *dlen is not long enough, 2 for invalid parameters,
and 3 if any of the elements of source are greater than smax.
Using this same operation on the result with smax and dmax reversed reverses
the operation, restoring the original vector. However there may be more
symbols returned than the original, so the number of symbols expected needs
to be known for decoding. (An end symbol could be appended to the source
alphabet to include the length in the coding, but then encoding and decoding
would no longer be symmetric, and the coding efficiency would be reduced.
This is left as an exercise for the reader if that is desired.) */
int recode(unsigned *dest, size_t *dlen, unsigned dmax,
const unsigned *source, size_t slen, unsigned smax)
{
// compute sbits and scut, with which we will recode the source with
// sbits-1 bits for symbols < scut, otherwise with sbits bits (adding scut)
if (smax < 1)
return 2;
unsigned sbits = 0;
unsigned scut = 1; // 2**sbits
while (scut && scut <= smax) {
scut <<= 1;
sbits++;
}
scut -= smax + 1;
// same thing for dbits and dcut
if (dmax < 1)
return 2;
unsigned dbits = 0;
unsigned dcut = 1; // 2**dbits
while (dcut && dcut <= dmax) {
dcut <<= 1;
dbits++;
}
dcut -= dmax + 1;
// recode a base smax+1 vector to a base dmax+1 vector using an
// intermediate bit vector (a sliding window of that bit vector is kept in
// a bit buffer)
unsigned long long buf = 0; // bit buffer
unsigned have = 0; // number of bits in bit buffer
size_t i = 0, n = 0; // source and dest indices
unsigned sym; // symbol being encoded
for (;;) {
// encode enough of source into bits to encode that to dest
while (have < dbits && i < slen) {
sym = source[i++];
if (sym > smax) {
*dlen = n;
return 3;
}
if (sym < scut) {
buf = (buf << (sbits - 1)) + sym;
have += sbits - 1;
}
else {
buf = (buf << sbits) + sym + scut;
have += sbits;
}
}
// if not enough bits to assure one symbol, then break out to a special
// case for coding the final symbol
if (have < dbits)
break;
// encode one symbol to dest
if (n == *dlen)
return 1;
sym = buf >> (have - dbits + 1);
if (sym < dcut) {
dest[n++] = sym;
have -= dbits - 1;
}
else {
sym = buf >> (have - dbits);
dest[n++] = sym - dcut;
have -= dbits;
}
buf &= ((unsigned long long)1 << have) - 1;
}
// if any bits are left in the bit buffer, encode one last symbol to dest
if (have) {
if (n == *dlen)
return 1;
sym = buf;
sym <<= dbits - 1 - have;
if (sym >= dcut)
sym = (sym << 1) - dcut;
dest[n++] = sym;
}
// return recoded vector
*dlen = n;
return 0;
}
/* Test recode(). */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <assert.h>
// Return a random vector of len unsigned values in the range 0..max.
static void ranvec(unsigned *vec, size_t len, unsigned max) {
unsigned bits = 0;
unsigned long long mask = 1;
while (mask <= max) {
mask <<= 1;
bits++;
}
mask--;
unsigned long long ran = 0;
unsigned have = 0;
size_t n = 0;
while (n < len) {
while (have < bits) {
ran = (ran << 31) + random();
have += 31;
}
if ((ran & mask) <= max)
vec[n++] = ran & mask;
ran >>= bits;
have -= bits;
}
}
// Get a valid number from str and assign it to var
#define NUM(var, str) \
do { \
char *end; \
unsigned long val = strtoul(str, &end, 0); \
var = val; \
if (*end || var != val) { \
fprintf(stderr, \
"invalid or out of range numeric argument: %s\n", str); \
return 1; \
} \
} while (0)
/* "bet n m len count" generates count test vectors of length len, where each
entry is in the range 0..n. Each vector is recoded to another vector using
only symbols in the range 0..m. That vector is recoded back to a vector
using only symbols in 0..n, and that result is compared with the original
random vector. Report on the average ratio of input and output symbols, as
compared to the optimal ratio for arbitrary precision base encoding. */
int main(int argc, char **argv)
{
// get sizes of alphabets and length of test vector, compute maximum sizes
// of recoded vectors
unsigned smax, dmax, runs;
size_t slen, dsize, bsize;
if (argc != 5) { fputs("need four arguments\n", stderr); return 1; }
NUM(smax, argv[1]);
NUM(dmax, argv[2]);
NUM(slen, argv[3]);
NUM(runs, argv[4]);
dsize = ceil(slen * ceil(log2(smax + 1.)) / floor(log2(dmax + 1.)));
bsize = ceil(dsize * ceil(log2(dmax + 1.)) / floor(log2(smax + 1.)));
// generate random test vectors, encode, decode, and compare
srandomdev();
unsigned source[slen], dest[dsize], back[bsize];
unsigned mis = 0, i;
unsigned long long dtot = 0;
int ret;
for (i = 0; i < runs; i++) {
ranvec(source, slen, smax);
size_t dlen = dsize;
ret = recode(dest, &dlen, dmax, source, slen, smax);
if (ret) {
fprintf(stderr, "encode error %d\n", ret);
break;
}
dtot += dlen;
size_t blen = bsize;
ret = recode(back, &blen, smax, dest, dlen, dmax);
if (ret) {
fprintf(stderr, "decode error %d\n", ret);
break;
}
if (blen < slen || memcmp(source, back, slen)) // blen > slen is ok
mis++;
}
if (mis)
fprintf(stderr, "%u/%u mismatches!\n", mis, i);
if (ret == 0)
printf("mean dest/source symbols = %.4f (optimal = %.4f)\n",
dtot / (i * (double)slen), log(smax + 1.) / log(dmax + 1.));
return 0;
}