From 5ea900cb5ad862bca81316729f92357c1fc040ce Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Sat, 23 Mar 2013 22:25:15 +0200 Subject: [PATCH] liblzma: Be less picky in lzma_alone_decoder(). To avoid false positives when detecting .lzma files, rare values in dictionary size and uncompressed size fields were rejected. They will still be rejected if .lzma files are decoded with lzma_auto_decoder(), but when using lzma_alone_decoder() directly, such files will now be accepted. Hopefully this is an OK compromise. This doesn't affect xz because xz still has its own file format detection code. This does affect lzmadec though. So after this commit lzmadec will accept files that xz or xz-emulating-lzma doesn't. NOTE: lzma_alone_decoder() still won't decode all .lzma files because liblzma's LZMA decoder doesn't support lc + lp > 4. Reported here: http://sourceforge.net/projects/lzmautils/forums/forum/708858/topic/7068827 --- src/liblzma/common/alone_decoder.c | 22 ++++++++++++++-------- src/liblzma/common/alone_decoder.h | 5 +++-- src/liblzma/common/auto_decoder.c | 2 +- 3 files changed, 18 insertions(+), 11 deletions(-) diff --git a/src/liblzma/common/alone_decoder.c b/src/liblzma/common/alone_decoder.c index d35aff67..c1360ca1 100644 --- a/src/liblzma/common/alone_decoder.c +++ b/src/liblzma/common/alone_decoder.c @@ -26,6 +26,11 @@ struct lzma_coder_s { SEQ_CODE, } sequence; + /// If true, reject files that are unlikely to be .lzma files. + /// If false, more non-.lzma files get accepted and will give + /// LZMA_DATA_ERROR either immediately or after a few output bytes. + bool picky; + /// Position in the header fields size_t pos; @@ -68,13 +73,13 @@ alone_decode(lzma_coder *coder, |= (size_t)(in[*in_pos]) << (coder->pos * 8); if (++coder->pos == 4) { - if (coder->options.dict_size != UINT32_MAX) { + if (coder->picky && coder->options.dict_size + != UINT32_MAX) { // A hack to ditch tons of false positives: // We allow only dictionary sizes that are // 2^n or 2^n + 2^(n-1). LZMA_Alone created // only files with 2^n, but accepts any - // dictionary size. If someone complains, this - // will be reconsidered. + // dictionary size. uint32_t d = coder->options.dict_size - 1; d |= d >> 2; d |= d >> 3; @@ -103,9 +108,9 @@ alone_decode(lzma_coder *coder, // Another hack to ditch false positives: Assume that // if the uncompressed size is known, it must be less - // than 256 GiB. Again, if someone complains, this - // will be reconsidered. - if (coder->uncompressed_size != LZMA_VLI_UNKNOWN + // than 256 GiB. + if (coder->picky + && coder->uncompressed_size != LZMA_VLI_UNKNOWN && coder->uncompressed_size >= (LZMA_VLI_C(1) << 38)) return LZMA_FORMAT_ERROR; @@ -189,7 +194,7 @@ alone_decoder_memconfig(lzma_coder *coder, uint64_t *memusage, extern lzma_ret lzma_alone_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator, - uint64_t memlimit) + uint64_t memlimit, bool picky) { lzma_next_coder_init(&lzma_alone_decoder_init, next, allocator); @@ -208,6 +213,7 @@ lzma_alone_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator, } next->coder->sequence = SEQ_PROPERTIES; + next->coder->picky = picky; next->coder->pos = 0; next->coder->options.dict_size = 0; next->coder->options.preset_dict = NULL; @@ -223,7 +229,7 @@ lzma_alone_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator, extern LZMA_API(lzma_ret) lzma_alone_decoder(lzma_stream *strm, uint64_t memlimit) { - lzma_next_strm_init(lzma_alone_decoder_init, strm, memlimit); + lzma_next_strm_init(lzma_alone_decoder_init, strm, memlimit, false); strm->internal->supported_actions[LZMA_RUN] = true; strm->internal->supported_actions[LZMA_FINISH] = true; diff --git a/src/liblzma/common/alone_decoder.h b/src/liblzma/common/alone_decoder.h index d819b3fb..dfa031aa 100644 --- a/src/liblzma/common/alone_decoder.h +++ b/src/liblzma/common/alone_decoder.h @@ -16,7 +16,8 @@ #include "common.h" -extern lzma_ret lzma_alone_decoder_init(lzma_next_coder *next, - const lzma_allocator *allocator, uint64_t memlimit); +extern lzma_ret lzma_alone_decoder_init( + lzma_next_coder *next, const lzma_allocator *allocator, + uint64_t memlimit, bool picky); #endif diff --git a/src/liblzma/common/auto_decoder.c b/src/liblzma/common/auto_decoder.c index 22e45189..bf355070 100644 --- a/src/liblzma/common/auto_decoder.c +++ b/src/liblzma/common/auto_decoder.c @@ -54,7 +54,7 @@ auto_decode(lzma_coder *coder, const lzma_allocator *allocator, coder->memlimit, coder->flags)); } else { return_if_error(lzma_alone_decoder_init(&coder->next, - allocator, coder->memlimit)); + allocator, coder->memlimit, true)); // If the application wants to know about missing // integrity check or about the check in general, we