cosmopolitan/libc/str/lz4len.c
tkchia 0ffc0dd461
Let lz4toasm accept LZ4 files that lack extracted-size field (#858)
lz4toasm should now more easily accept LZ4 files output by
compressor programs that do not support the extracted-size
field, such as Stephan Brumme's smallz4.

This patch also proposes to add a new lz4len() function to
the libc: it parses an LZ4 compressed block to compute the
unpacked content size, without really unpacking the block.

Co-authored-by: tkchia <tkchia-cosmo@gmx.com>
2023-07-23 11:12:22 -07:00

57 lines
2.7 KiB
C

/*-*- mode:c;indent-tabs-mode:nil;c-basic-offset:2;tab-width:8;coding:utf-8 -*-│
│vi: set net ft=c ts=2 sts=2 sw=2 fenc=utf-8 :vi│
╞══════════════════════════════════════════════════════════════════════════════╡
│ Copyright 2020 Justine Alexandra Roberts Tunney │
│ │
│ Permission to use, copy, modify, and/or distribute this software for │
│ any purpose with or without fee is hereby granted, provided that the │
│ above copyright notice and this permission notice appear in all copies. │
│ │
│ THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL │
│ WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED │
│ WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE │
│ AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL │
│ DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR │
│ PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER │
│ TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR │
│ PERFORMANCE OF THIS SOFTWARE. │
╚─────────────────────────────────────────────────────────────────────────────*/
#include "libc/intrin/bits.h"
#include "libc/intrin/pushpop.internal.h"
#include "libc/nexgen32e/kompressor.h"
#include "libc/str/str.h"
/**
* Returns the uncompressed content size for a compressed LZ4 block, without
* actually decompressing it.
*
* @see lz4cpy()
*/
size_t lz4len(const void *blockdata, size_t blocksize) {
unsigned char *ip, *ipe;
unsigned token, length, fifteen, offset, matchlen;
size_t unpacklen = 0;
for (ip = blockdata, ipe = ip + blocksize;;) {
token = *ip++;
length = token >> 4;
fifteen = pushpop(15);
if (length == fifteen) {
do {
length += *ip;
} while (*ip++ == 255);
}
ip += length;
unpacklen += length;
if (ip >= ipe) break;
offset = READ16LE(ip);
matchlen = token & fifteen;
ip += 2;
if (matchlen == fifteen) {
do {
matchlen += *ip;
} while (*ip++ == 255);
}
unpacklen += matchlen + 4;
}
return unpacklen;
}