Make liblzma produce the same output on both endiannesses.

Seems that it is a problem in some cases if the same
version of XZ Utils produces different output on different
endiannesses, so this commit fixes that problem. The output
will still vary between different XZ Utils versions, but I
cannot avoid that for now.

This commit bloatens the code on big endian systems by 1 KiB,
which should be OK since liblzma is bloated already. ;-)

diff --git a/src/liblzma/check/crc32_tablegen.c b/src/liblzma/check/crc32_tablegen.c
index 0cbfecd89dde2a661bde9a73a1c9e6e967675746..56bc5c7f42b58ebde656a4b94d74712510d9cae0 100644 (file)
--- a/src/liblzma/check/crc32_tablegen.c
+++ b/src/liblzma/check/crc32_tablegen.c
@@ -5,6 +5,7 @@
 ///
 /// Compiling: gcc -std=c99 -o crc32_tablegen crc32_tablegen.c
 /// Add -DWORDS_BIGENDIAN to generate big endian table.
+/// Add -DLZ_HASH_TABLE to generate lz_encoder_hash_table.h (little endian).
 //
 //  Author:     Lasse Collin
 //
@@ -82,10 +83,39 @@ print_crc32_table(void)
 }
 
 
+static void
+print_lz_table(void)
+{
+       printf("/* This file has been automatically generated by "
+                       "crc32_tablegen.c. */\n\n"
+                       "const uint32_t lzma_lz_hash_table[256] = {");
+
+       for (size_t b = 0; b < 256; ++b) {
+               if ((b % 4) == 0)
+                       printf("\n\t");
+
+               printf("0x%08" PRIX32, crc32_table[0][b]);
+
+               if (b != 255)
+                       printf(",%s", (b+1) % 4 == 0 ? "" : " ");
+       }
+
+       printf("\n};\n");
+
+       return;
+}
+
+
 int
 main(void)
 {
        init_crc32_table();
+
+#ifdef LZ_HASH_TABLE
+       print_lz_table();
+#else
        print_crc32_table();
+#endif
+
        return 0;
 }

diff --git a/src/liblzma/lz/Makefile.inc b/src/liblzma/lz/Makefile.inc
index 470d59c09d36b03673e1c1ac89b7ea452bf80f8e..75742a84bf88b0fb90387f86bbaedd45153184e4 100644 (file)
--- a/src/liblzma/lz/Makefile.inc
+++ b/src/liblzma/lz/Makefile.inc
@@ -10,6 +10,7 @@ liblzma_la_SOURCES += \
        lz/lz_encoder.c \
        lz/lz_encoder.h \
        lz/lz_encoder_hash.h \
+       lz/lz_encoder_hash_table.h \
        lz/lz_encoder_mf.c
 endif
 

diff --git a/src/liblzma/lz/lz_encoder.c b/src/liblzma/lz/lz_encoder.c
index 5fd03e8422aa2e0f7bdb10888e6222fbeabba8f5..0e7b7d1dd024e27db023a9f21975fcd1e2be44c4 100644 (file)
--- a/src/liblzma/lz/lz_encoder.c
+++ b/src/liblzma/lz/lz_encoder.c
@@ -13,7 +13,12 @@
 
 #include "lz_encoder.h"
 #include "lz_encoder_hash.h"
-#include "check.h"
+
+// See lz_encoder_hash.h. This is a bit hackish but avoids making
+// endianness a conditional in makefiles.
+#if defined(WORDS_BIGENDIAN) && !defined(HAVE_SMALL)
+#      include "lz_encoder_hash_table.h"
+#endif
 
 
 struct lzma_coder_s {

diff --git a/src/liblzma/lz/lz_encoder_hash.h b/src/liblzma/lz/lz_encoder_hash.h
index dd4b1f1906bf81f2f7bcfde1e0ce426b01c9a970..e92251d25366420f641c17984f15f3ce6abd5666 100644 (file)
--- a/src/liblzma/lz/lz_encoder_hash.h
+++ b/src/liblzma/lz/lz_encoder_hash.h
@@ -13,6 +13,17 @@
 #ifndef LZMA_LZ_ENCODER_HASH_H
 #define LZMA_LZ_ENCODER_HASH_H
 
+#if defined(WORDS_BIGENDIAN) && !defined(HAVE_SMALL)
+       // This is to make liblzma produce the same output on big endian
+       // systems that it does on little endian systems. lz_encoder.c
+       // takes care of including the actual table.
+       extern const uint32_t lzma_lz_hash_table[256];
+#      define hash_table lzma_lz_hash_table
+#else
+#      include "check.h"
+#      define hash_table lzma_crc32_table[0]
+#endif
+
 #define HASH_2_SIZE (UINT32_C(1) << 10)
 #define HASH_3_SIZE (UINT32_C(1) << 16)
 #define HASH_4_SIZE (UINT32_C(1) << 20)
@@ -36,31 +47,31 @@
 #endif
 
 #define hash_3_calc() \
-       const uint32_t temp = lzma_crc32_table[0][cur[0]] ^ cur[1]; \
+       const uint32_t temp = hash_table[cur[0]] ^ cur[1]; \
        const uint32_t hash_2_value = temp & HASH_2_MASK; \
        const uint32_t hash_value \
                        = (temp ^ ((uint32_t)(cur[2]) << 8)) & mf->hash_mask
 
 #define hash_4_calc() \
-       const uint32_t temp = lzma_crc32_table[0][cur[0]] ^ cur[1]; \
+       const uint32_t temp = hash_table[cur[0]] ^ cur[1]; \
        const uint32_t hash_2_value = temp & HASH_2_MASK; \
        const uint32_t hash_3_value \
                        = (temp ^ ((uint32_t)(cur[2]) << 8)) & HASH_3_MASK; \
        const uint32_t hash_value = (temp ^ ((uint32_t)(cur[2]) << 8) \
-                       ^ (lzma_crc32_table[0][cur[3]] << 5)) & mf->hash_mask
+                       ^ (hash_table[cur[3]] << 5)) & mf->hash_mask
 
 
 // The following are not currently used.
 
 #define hash_5_calc() \
-       const uint32_t temp = lzma_crc32_table[0][cur[0]] ^ cur[1]; \
+       const uint32_t temp = hash_table[cur[0]] ^ cur[1]; \
        const uint32_t hash_2_value = temp & HASH_2_MASK; \
        const uint32_t hash_3_value \
                        = (temp ^ ((uint32_t)(cur[2]) << 8)) & HASH_3_MASK; \
        uint32_t hash_4_value = (temp ^ ((uint32_t)(cur[2]) << 8) ^ \
-                       ^ lzma_crc32_table[0][cur[3]] << 5); \
+                       ^ hash_table[cur[3]] << 5); \
        const uint32_t hash_value \
-                       = (hash_4_value ^ (lzma_crc32_table[0][cur[4]] << 3)) \
+                       = (hash_4_value ^ (hash_table[cur[4]] << 3)) \
                                & mf->hash_mask; \
        hash_4_value &= HASH_4_MASK
 
@@ -68,30 +79,30 @@
 #define hash_zip_calc() \
        const uint32_t hash_value \
                        = (((uint32_t)(cur[0]) | ((uint32_t)(cur[1]) << 8)) \
-                               ^ lzma_crc32_table[0][cur[2]]) & 0xFFFF
+                               ^ hash_table[cur[2]]) & 0xFFFF
 */
 
 #define hash_zip_calc() \
        const uint32_t hash_value \
                        = (((uint32_t)(cur[2]) | ((uint32_t)(cur[0]) << 8)) \
-                               ^ lzma_crc32_table[0][cur[1]]) & 0xFFFF
+                               ^ hash_table[cur[1]]) & 0xFFFF
 
 #define mt_hash_2_calc() \
        const uint32_t hash_2_value \
-                       = (lzma_crc32_table[0][cur[0]] ^ cur[1]) & HASH_2_MASK
+                       = (hash_table[cur[0]] ^ cur[1]) & HASH_2_MASK
 
 #define mt_hash_3_calc() \
-       const uint32_t temp = lzma_crc32_table[0][cur[0]] ^ cur[1]; \
+       const uint32_t temp = hash_table[cur[0]] ^ cur[1]; \
        const uint32_t hash_2_value = temp & HASH_2_MASK; \
        const uint32_t hash_3_value \
                        = (temp ^ ((uint32_t)(cur[2]) << 8)) & HASH_3_MASK
 
 #define mt_hash_4_calc() \
-       const uint32_t temp = lzma_crc32_table[0][cur[0]] ^ cur[1]; \
+       const uint32_t temp = hash_table[cur[0]] ^ cur[1]; \
        const uint32_t hash_2_value = temp & HASH_2_MASK; \
        const uint32_t hash_3_value \
                        = (temp ^ ((uint32_t)(cur[2]) << 8)) & HASH_3_MASK; \
        const uint32_t hash_4_value = (temp ^ ((uint32_t)(cur[2]) << 8) ^ \
-                       (lzma_crc32_table[0][cur[3]] << 5)) & HASH_4_MASK
+                       (hash_table[cur[3]] << 5)) & HASH_4_MASK
 
 #endif

diff --git a/src/liblzma/lz/lz_encoder_hash_table.h b/src/liblzma/lz/lz_encoder_hash_table.h
new file mode 100644 (file)
index 0000000..8c51717
--- /dev/null
+++ b/src/liblzma/lz/lz_encoder_hash_table.h
@@ -0,0 +1,68 @@
+/* This file has been automatically generated by crc32_tablegen.c. */
+
+const uint32_t lzma_lz_hash_table[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
+};

diff --git a/src/liblzma/lz/lz_encoder_mf.c b/src/liblzma/lz/lz_encoder_mf.c
index e48de4fee936f21d0ad2aa8ce65abeb069c5352e..b31b08578d4513a4229aeacb8be5a8e9cd4551ec 100644 (file)
--- a/src/liblzma/lz/lz_encoder_mf.c
+++ b/src/liblzma/lz/lz_encoder_mf.c
@@ -13,7 +13,6 @@
 
 #include "lz_encoder.h"
 #include "lz_encoder_hash.h"
-#include "check.h"
 
 
 /// \brief      Find matches starting from the current byte