commit 5b0749cf7d62047d604fd5b8bfd5b96063d153c0 Author: Zack Weinberg zackw@cmu.edu Date: Mon Apr 30 11:21:47 2012 -0700

Use zlib's crc32c. Add tests for crc32c. --- Makefile.am | 4 +- src/crc32.cc | 86 ------------------------ src/crc32.h | 10 --- src/test/unittest_zlib.cc | 158 +++++++++++++++++++++++++++++++++++++++++++++ src/zpack.cc | 24 ++++++- src/zpack.h | 2 + 6 files changed, 184 insertions(+), 100 deletions(-)

diff --git a/Makefile.am b/Makefile.am index 11f8ac3..3ded164 100644 --- a/Makefile.am +++ b/Makefile.am @@ -30,7 +30,6 @@ STEGANOGRAPHERS = \

libstegotorus_a_SOURCES = \ src/base64.cc \ - src/crc32.cc \ src/connections.cc \ src/crypt.cc \ src/network.cc \ @@ -52,7 +51,8 @@ UTGROUPS = \ src/test/unittest_pdfsteg.cc \ src/test/unittest_socks.cc \ src/test/unittest_config.cc \ - src/test/unittest_transfer.cc + src/test/unittest_transfer.cc \ + src/test/unittest_zlib.cc

unittests_SOURCES = \ src/test/tinytest.cc \ diff --git a/src/crc32.cc b/src/crc32.cc deleted file mode 100644 index 151eae1..0000000 --- a/src/crc32.cc +++ /dev/null @@ -1,86 +0,0 @@ -/* Copyright 2011, 2012 SRI International - * See LICENSE for other credits and copying information - */ -#include "util.h" -#include "crc32.h" - -#define CRC32C(c,d) (c=(c>>8)^crc_c[(c^(d))&0xFF]) - -static const unsigned int crc_c[256] = { - 0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, - 0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3, - 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988, - 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, - 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de, - 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, - 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, - 0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5, - 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172, - 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, - 0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, - 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59, - 0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, - 0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f, - 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924, - 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, - 0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a, - 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433, - 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, - 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01, - 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, - 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, - 0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c, - 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65, - 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, - 0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, - 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0, - 0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, - 0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086, - 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f, - 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, - 0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, - 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a, - 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, - 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8, - 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, - 0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, - 0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7, - 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc, - 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, - 0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, - 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b, - 0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, - 0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79, - 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236, - 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, - 0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, - 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d, - 0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, - 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713, - 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, - 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, - 0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e, - 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777, - 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, - 0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, - 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2, - 0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, - 0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0, - 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9, - 0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, - 0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf, - 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94, - 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d, -}; - -unsigned int -generate_crc32c(const char *buffer, size_t length) -{ - size_t i; - unsigned int crc32 = ~0L; - - for (i = 0; i < length; i++){ - CRC32C(crc32, (unsigned char)buffer[i]); - } - return ~crc32; -} diff --git a/src/crc32.h b/src/crc32.h deleted file mode 100644 index 67bb48a..0000000 --- a/src/crc32.h +++ /dev/null @@ -1,10 +0,0 @@ -/* Copyright 2011, 2012 SRI International - * See LICENSE for other credits and copying information - */ - -#ifndef _CRC32_H -#define _CRC32_H - -unsigned int generate_crc32c(const char *string, size_t length); - -#endif diff --git a/src/test/unittest_zlib.cc b/src/test/unittest_zlib.cc new file mode 100644 index 0000000..fa447dd --- /dev/null +++ b/src/test/unittest_zlib.cc @@ -0,0 +1,158 @@ +/* Copyright 2012 SRI International + * See LICENSE for other credits and copying information + */ + +#include "util.h" +#include "unittest.h" + +#include "zlib.h" +#include "zpack.h" + +/* Smoke tests for zlib. */ + +static void +test_zlib_crc32(void *) +{ + // Test vectors generated using a standalone crc32 implementation + // of unknown provenance, and then validated with the implementation + // built into zlib. If anyone knows a reliable source for "official" + // test vectors for the 0x04C11DB7 polynomial, please let us know. + + struct hash_testvec + { + const uint8_t *text; + size_t tlen; + uint32_t digest; + }; + static const struct hash_testvec tests[] = { +#define T(s, d) { (const uint8_t *)s, sizeof s - 1, 0x##d } + + // the empty string + T("", 00000000), + + // 4-byte messages + T("\x00\x00\x00\x00", 2144df1c), + T("\x11\x11\x11\x11", ed6c2543), + T("\x22\x22\x22\x22", 62642de3), + T("\x33\x33\x33\x33", ae4cd7bc), + T("\x44\x44\x44\x44", a7053ae2), + T("\x55\x55\x55\x55", 6b2dc0bd), + T("\x66\x66\x66\x66", e425c81d), + T("\x77\x77\x77\x77", 280d3242), + T("\x88\x88\x88\x88", f6b612a1), + T("\x99\x99\x99\x99", 3a9ee8fe), + T("\xaa\xaa\xaa\xaa", b596e05e), + T("\xbb\xbb\xbb\xbb", 79be1a01), + T("\xcc\xcc\xcc\xcc", 70f7f75f), + T("\xdd\xdd\xdd\xdd", bcdf0d00), + T("\xee\xee\xee\xee", 33d705a0), + T("\xff\xff\xff\xff", ffffffff), + T("\x40\x49\x0f\xdb", 538226fd), // pi (IEEE single) + + // 8-byte messages + T("\x00\x00\x00\x00\x00\x00\x00\x00", 6522df69), + T("\x00\x00\x00\x00\xff\xff\xff\xff", bb99ff8a), + T("\xff\xff\xff\xff\x00\x00\x00\x00", ffffffff), + T("\xff\xff\xff\xff\xff\xff\xff\xff", 2144df1c), + T("\x55\x55\x55\x55\x55\x55\x55\x55", efd02285), + T("\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa", abb622f0), + T("\x40\x09\x21\xfb\x54\x44\x2d\x18", 2a8990d8), // pi (IEEE double) + + // 32-byte messages: all possible bytes occur once + T("\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" + "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f", + 91267e8a), + T("\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" + "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f", + f6a606e3), + T("\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f" + "\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f", + 5e268e58), + T("\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" + "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f", + 39a6f631), + T("\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" + "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f", + d456996f), + T("\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf" + "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf", + b3d6e106), + T("\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" + "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf", + 1b5669bd), + T("\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" + "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff", + 7cd611d4), + + // 26- to 40-letter pangrams from Wikipedia, all nonletters removed, + // all lowercase + T("cwmfjordbankglyphsvextquiz", 81308910), + T("nymphsblitzquickvexdwarfjog", c9b201ae), + T("brickquizwhangsjumpyveldtfox", c17836eb), + T("vexednymphsgoforquickwaltzjob", ea8c2360), + T("bothfickledwarvesjinxmypigquiz", 3c7c5f5f), + T("ficklejinxbogdwarvesspymathquiz", 75862807), + T("averybadquackmightjinxzippyfowls", 563373aa), + T("aquickbrownfoxjumpsoverthelazydog", 56df6600), + T("quizzicaltwinsprovedmyhijackbugfix", b7140701), + T("whenzombiesarrivequicklyfaxjudgepat", c398efae), + T("heavyboxesperformquickwaltzesandjigs", bb60c571), + T("fakebugsputinwaxjonquilsdrivehimcrazy", a1c524f0), + T("wovensilkpyjamasexchangedforbluequartz", 9a7f064e), + T("thequickonyxgoblinjumpsoverthelazydwarf", 3b478712), + T("amazinglyfewdiscothequesprovidejukeboxes", 7ddde4a3), + + // self-describing pangram by Lee Sallows (SciAm, 1984) + T("This Pangram contains four as, one b, two cs, one d, thirty es, " + "six fs, five gs, seven hs, eleven is, one j, one k, two ls, two ms, " + "eighteen ns, fifteen os, two ps, one q, five rs, twenty-seven ss, " + "eighteen ts, two us, seven vs, eight ws, two xs, three ys, & one z.", + 3ab5b411), + + // "Lion-Eating Poet in the Stone Den" by Chao Yuen Ren, + // Simplified Chinese text in UTF-8 + T("\xe3\x80\x8a\xe6\x96\xbd\xe6\xb0\x8f\xe9\xa3\x9f\xe7\x8b\xae\xe5\x8f" + "\xb2\xe3\x80\x8b \xe7\x9f\xb3\xe5\xae\xa4\xe8\xaf\x97\xe5\xa3\xab\xe6" + "\x96\xbd\xe6\xb0\x8f\xef\xbc\x8c\xe5\x97\x9c\xe7\x8b\xae\xef\xbc\x8c" + "\xe8\xaa\x93\xe9\xa3\x9f\xe5\x8d\x81\xe7\x8b\xae\xe3\x80\x82 \xe6\xb0" + "\x8f\xe6\x97\xb6\xe6\x97\xb6\xe9\x80\x82\xe5\xb8\x82\xe8\xa7\x86\xe7" + "\x8b\xae\xe3\x80\x82 \xe5\x8d\x81\xe6\x97\xb6\xef\xbc\x8c\xe9\x80\x82" + "\xe5\x8d\x81\xe7\x8b\xae\xe9\x80\x82\xe5\xb8\x82\xe3\x80\x82 \xe6\x98" + "\xaf\xe6\x97\xb6\xef\xbc\x8c\xe9\x80\x82\xe6\x96\xbd\xe6\xb0\x8f\xe9" + "\x80\x82\xe5\xb8\x82\xe3\x80\x82 \xe6\xb0\x8f\xe8\xa7\x86\xe6\x98\xaf" + "\xe5\x8d\x81\xe7\x8b\xae\xef\xbc\x8c\xe6\x81\x83\xe7\x9f\xa2\xe5\x8a" + "\xbf\xef\xbc\x8c\xe4\xbd\xbf\xe6\x98\xaf\xe5\x8d\x81\xe7\x8b\xae\xe9" + "\x80\x9d\xe4\xb8\x96\xe3\x80\x82 \xe6\xb0\x8f\xe6\x8b\xbe\xe6\x98\xaf" + "\xe5\x8d\x81\xe7\x8b\xae\xe5\xb0\xb8\xef\xbc\x8c\xe9\x80\x82\xe7\x9f" + "\xb3\xe5\xae\xa4\xe3\x80\x82 \xe7\x9f\xb3\xe5\xae\xa4\xe6\xb9\xbf\xef" + "\xbc\x8c\xe6\xb0\x8f\xe4\xbd\xbf\xe4\xbe\x8d\xe6\x8b\xad\xe7\x9f\xb3" + "\xe5\xae\xa4\xe3\x80\x82 \xe7\x9f\xb3\xe5\xae\xa4\xe6\x8b\xad\xef\xbc" + "\x8c\xe6\xb0\x8f\xe5\xa7\x8b\xe8\xaf\x95\xe9\xa3\x9f\xe6\x98\xaf\xe5" + "\x8d\x81\xe7\x8b\xae\xe3\x80\x82 \xe9\xa3\x9f\xe6\x97\xb6\xef\xbc\x8c" + "\xe5\xa7\x8b\xe8\xaf\x86\xe6\x98\xaf\xe5\x8d\x81\xe7\x8b\xae\xe5\xb0" + "\xb8\xef\xbc\x8c\xe5\xae\x9e\xe5\x8d\x81\xe7\x9f\xb3\xe7\x8b\xae\xe5" + "\xb0\xb8\xe3\x80\x82 \xe8\xaf\x95\xe9\x87\x8a\xe6\x98\xaf\xe4\xba\x8b" + "\xe3\x80\x82", + 1fa606e5), + + { 0, 0, 0 } +#undef T + }; + + int i; + uint32_t h; + for (i = 0; tests[i].text; i++) { + h = generate_crc32c(tests[i].text, tests[i].tlen); + tt_assert_op_type(h,==,tests[i].digest, unsigned int, "%08x"); + } + + end:; +} + +#define T(name) \ + { #name, test_zlib_##name, 0, 0, 0 } + +struct testcase_t zlib_tests[] = { + T(crc32), + END_OF_TESTCASES +}; diff --git a/src/zpack.cc b/src/zpack.cc index 751c96e..2a7adfc 100644 --- a/src/zpack.cc +++ b/src/zpack.cc @@ -4,7 +4,8 @@ #include "util.h" #include "zpack.h" #include "zlib.h" -#include "crc32.h" + +#include <limits>

#define CHUNK 16384

@@ -296,7 +297,7 @@ gzDeflate(const char *source, size_t slen, char *dest, size_t dlen, return -1; }

- crc = generate_crc32c(source, slen); + crc = generate_crc32c((const uint8_t *)source, slen);

c = (unsigned char *)dest + 10 + z.total_out; c[0] = (crc >> 0) & 0xff; @@ -312,3 +313,22 @@ gzDeflate(const char *source, size_t slen, char *dest, size_t dlen, return -1; return 10 + z.total_out + 8; } + +uint32_t +generate_crc32c(const uint8_t *string, size_t length) +{ + // zlib doesn't believe in size_t. When size_t is bigger than uInt, + // we theoretically could break the operation up into uInt-sized + // chunks to support the full range of size_t, but I doubt we will + // ever need to crc32 more than 2^32 bytes, so I'm not bothering. + // -- zw, 2012 + log_assert(length <= std::numeric_limits<uInt>::max()); + + uLong crc = crc32(crc32(0, 0, 0), string, length); + + // zlib also doesn't believe 'long' can be more than 32 bits wide. + // This shouldn't ever fire unless there is a bug in zlib. + log_assert(crc <= std::numeric_limits<uint32_t>::max()); + + return crc; +} diff --git a/src/zpack.h b/src/zpack.h index 18bb531..e1e1c2c 100644 --- a/src/zpack.h +++ b/src/zpack.h @@ -12,4 +12,6 @@ ssize_t gzInflate(const char *source, size_t slen, char *dest, size_t dlen); ssize_t gzDeflate(const char *source, size_t slen, char *dest, size_t dlen, time_t mtime);

+uint32_t generate_crc32c(const uint8_t *string, size_t length); + #endif