You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-commits@hadoop.apache.org by cm...@apache.org on 2014/10/10 02:12:38 UTC
[2/2] git commit: HADOOP-11184. Update Hadoop's lz4 to r123 (cmccabe)
(cherry picked from commit d8d628d1e0c42a32e2079ed430e8817996bbe4c4)
HADOOP-11184. Update Hadoop's lz4 to r123 (cmccabe)
(cherry picked from commit d8d628d1e0c42a32e2079ed430e8817996bbe4c4)
Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo
Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/8addbe2b
Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/8addbe2b
Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/8addbe2b
Branch: refs/heads/branch-2
Commit: 8addbe2b8eaf9fabbb0b6dc0dd3351a0145e0cae
Parents: d3125f3
Author: Colin Patrick Mccabe <cm...@cloudera.com>
Authored: Thu Oct 9 17:05:35 2014 -0700
Committer: Colin Patrick Mccabe <cm...@cloudera.com>
Committed: Thu Oct 9 17:12:24 2014 -0700
----------------------------------------------------------------------
LICENSE.txt | 7 +-
hadoop-common-project/hadoop-common/CHANGES.txt | 2 +
hadoop-common-project/hadoop-common/pom.xml | 1 -
.../src/org/apache/hadoop/io/compress/lz4/lz4.c | 1243 +++++++++++++-----
.../src/org/apache/hadoop/io/compress/lz4/lz4.h | 296 +++--
.../apache/hadoop/io/compress/lz4/lz4_encoder.h | 258 ----
.../org/apache/hadoop/io/compress/lz4/lz4hc.c | 591 +++++++--
.../org/apache/hadoop/io/compress/lz4/lz4hc.h | 84 +-
.../hadoop/io/compress/lz4/lz4hc_encoder.h | 349 -----
9 files changed, 1657 insertions(+), 1174 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hadoop/blob/8addbe2b/LICENSE.txt
----------------------------------------------------------------------
diff --git a/LICENSE.txt b/LICENSE.txt
index 946a6df..8a4b175 100644
--- a/LICENSE.txt
+++ b/LICENSE.txt
@@ -252,13 +252,12 @@ in src/main/native/src/org/apache/hadoop/util:
* BSD-style license that can be found in the LICENSE file.
*/
-For src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,
-lz4_encoder.h,lz4hc.h,lz4hc.c,lz4hc_encoder.h},
+For src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,lz4hc.h,lz4hc.c},
/*
LZ4 - Fast LZ compression algorithm
Header File
- Copyright (C) 2011-2013, Yann Collet.
+ Copyright (C) 2011-2014, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
@@ -285,6 +284,6 @@ lz4_encoder.h,lz4hc.h,lz4hc.c,lz4hc_encoder.h},
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- LZ4 source repository : http://code.google.com/p/lz4/
+ - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/
http://git-wip-us.apache.org/repos/asf/hadoop/blob/8addbe2b/hadoop-common-project/hadoop-common/CHANGES.txt
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/CHANGES.txt b/hadoop-common-project/hadoop-common/CHANGES.txt
index 876a977..9230394 100644
--- a/hadoop-common-project/hadoop-common/CHANGES.txt
+++ b/hadoop-common-project/hadoop-common/CHANGES.txt
@@ -247,6 +247,8 @@ Release 2.6.0 - UNRELEASED
HADOOP-11174. Delegation token for KMS should only be got once if it
already exists. (Yi Liu via wang)
+ HADOOP-11184. Update Hadoop's lz4 to version r123. (cmccabe)
+
OPTIMIZATIONS
HADOOP-10838. Byte array native checksumming. (James Thomas via todd)
http://git-wip-us.apache.org/repos/asf/hadoop/blob/8addbe2b/hadoop-common-project/hadoop-common/pom.xml
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/pom.xml b/hadoop-common-project/hadoop-common/pom.xml
index d745f71..6cdced2 100644
--- a/hadoop-common-project/hadoop-common/pom.xml
+++ b/hadoop-common-project/hadoop-common/pom.xml
@@ -499,7 +499,6 @@
<exclude>src/test/resources/kdc/ldif/users.ldif</exclude>
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h</exclude>
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c</exclude>
- <exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4_encoder.h</exclude>
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.h</exclude>
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc.c</exclude>
<exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4hc_encoder.h</exclude>
http://git-wip-us.apache.org/repos/asf/hadoop/blob/8addbe2b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c
index 8eda7ae..39f176f 100644
--- a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c
+++ b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c
@@ -1,6 +1,6 @@
/*
LZ4 - Fast LZ compression algorithm
- Copyright (C) 2011-2013, Yann Collet.
+ Copyright (C) 2011-2014, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
@@ -27,47 +27,44 @@
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- LZ4 source repository : http://code.google.com/p/lz4/
+ - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/
+/**************************************
+ Tuning parameters
+**************************************/
/*
-Note : this source file requires "lz4_encoder.h"
-*/
-
-//**************************************
-// Tuning parameters
-//**************************************
-// MEMORY_USAGE :
-// Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
-// Increasing memory usage improves compression ratio
-// Reduced memory usage can improve speed, due to cache effect
-// Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
-#define MEMORY_USAGE 14
-
-// HEAPMODE :
-// Select how default compression function will allocate memory for its hash table,
-// in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)).
-// Default allocation strategy is to use stack (HEAPMODE 0)
-// Note : explicit functions *_stack* and *_heap* are unaffected by this setting
+ * HEAPMODE :
+ * Select how default compression functions will allocate memory for their hash table,
+ * in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)).
+ */
#define HEAPMODE 0
-//**************************************
-// CPU Feature Detection
-//**************************************
-// 32 or 64 bits ?
+/**************************************
+ CPU Feature Detection
+**************************************/
+/* 32 or 64 bits ? */
#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \
- || defined(__powerpc64__) || defined(__ppc64__) || defined(__PPC64__) \
- || defined(__64BIT__) || defined(_LP64) || defined(__LP64__) \
- || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) // Detects 64 bits mode
+ || defined(__64BIT__) || defined(__mips64) \
+ || defined(__powerpc64__) || defined(__powerpc64le__) \
+ || defined(__ppc64__) || defined(__ppc64le__) \
+ || defined(__PPC64__) || defined(__PPC64LE__) \
+ || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) \
+ || defined(__s390x__) ) /* Detects 64 bits mode */
# define LZ4_ARCH64 1
#else
# define LZ4_ARCH64 0
#endif
+#define LZ4_32BITS (sizeof(void*)==4)
+#define LZ4_64BITS (sizeof(void*)==8)
-// Little Endian or Big Endian ?
-// Overwrite the #define below if you know your architecture endianess
+/*
+ * Little Endian or Big Endian ?
+ * Overwrite the #define below if you know your architecture endianess
+ */
+#include <stdlib.h> /* Apparently required to detect endianess */
#if defined (__GLIBC__)
# include <endian.h>
# if (__BYTE_ORDER == __BIG_ENDIAN)
@@ -81,57 +78,62 @@ Note : this source file requires "lz4_encoder.h"
|| defined(_MIPSEB) || defined(__s390__)
# define LZ4_BIG_ENDIAN 1
#else
-// Little Endian assumed. PDP Endian and other very rare endian format are unsupported.
+/* Little Endian assumed. PDP Endian and other very rare endian format are unsupported. */
#endif
-// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
-// For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property
-// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance
+/*
+ * Unaligned memory access is automatically enabled for "common" CPU, such as x86.
+ * For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property
+ * If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance
+ */
#if defined(__ARM_FEATURE_UNALIGNED)
# define LZ4_FORCE_UNALIGNED_ACCESS 1
#endif
-// Define this parameter if your target system or compiler does not support hardware bit count
-#if defined(_MSC_VER) && defined(_WIN32_WCE) // Visual Studio for Windows CE does not support Hardware bit count
+/* Define this parameter if your target system or compiler does not support hardware bit count */
+#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for Windows CE does not support Hardware bit count */
# define LZ4_FORCE_SW_BITCOUNT
#endif
-// BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :
-// This option may provide a small boost to performance for some big endian cpu, although probably modest.
-// You may set this option to 1 if data will remain within closed environment.
-// This option is useless on Little_Endian CPU (such as x86)
-//#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1
+/*
+ * BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :
+ * This option may provide a small boost to performance for some big endian cpu, although probably modest.
+ * You may set this option to 1 if data will remain within closed environment.
+ * This option is useless on Little_Endian CPU (such as x86)
+ */
+
+/* #define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 */
-//**************************************
-// Compiler Options
-//**************************************
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) // C99
+/**************************************
+ Compiler Options
+**************************************/
+#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */
/* "restrict" is a known keyword */
#else
-# define restrict // Disable restrict
+# define restrict /* Disable restrict */
#endif
-#ifdef _MSC_VER // Visual Studio
-# define forceinline static __forceinline
-# include <intrin.h> // For Visual 2005
-# if LZ4_ARCH64 // 64-bits
-# pragma intrinsic(_BitScanForward64) // For Visual 2005
-# pragma intrinsic(_BitScanReverse64) // For Visual 2005
-# else // 32-bits
-# pragma intrinsic(_BitScanForward) // For Visual 2005
-# pragma intrinsic(_BitScanReverse) // For Visual 2005
+#ifdef _MSC_VER /* Visual Studio */
+# define FORCE_INLINE static __forceinline
+# include <intrin.h> /* For Visual 2005 */
+# if LZ4_ARCH64 /* 64-bits */
+# pragma intrinsic(_BitScanForward64) /* For Visual 2005 */
+# pragma intrinsic(_BitScanReverse64) /* For Visual 2005 */
+# else /* 32-bits */
+# pragma intrinsic(_BitScanForward) /* For Visual 2005 */
+# pragma intrinsic(_BitScanReverse) /* For Visual 2005 */
# endif
-# pragma warning(disable : 4127) // disable: C4127: conditional expression is constant
-#else
+# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
+#else
# ifdef __GNUC__
-# define forceinline static inline __attribute__((always_inline))
+# define FORCE_INLINE static inline __attribute__((always_inline))
# else
-# define forceinline static inline
+# define FORCE_INLINE static inline
# endif
#endif
-#ifdef _MSC_VER
+#ifdef _MSC_VER /* Visual Studio */
# define lz4_bswap16(x) _byteswap_ushort(x)
#else
# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))
@@ -149,18 +151,26 @@ Note : this source file requires "lz4_encoder.h"
#define unlikely(expr) expect((expr) != 0, 0)
-//**************************************
-// Includes
-//**************************************
-#include <stdlib.h> // for malloc
-#include <string.h> // for memset
+/**************************************
+ Memory routines
+**************************************/
+#include <stdlib.h> /* malloc, calloc, free */
+#define ALLOCATOR(n,s) calloc(n,s)
+#define FREEMEM free
+#include <string.h> /* memset, memcpy */
+#define MEM_INIT memset
+
+
+/**************************************
+ Includes
+**************************************/
#include "lz4.h"
-//**************************************
-// Basic Types
-//**************************************
-#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L // C99
+/**************************************
+ Basic Types
+**************************************/
+#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */
# include <stdint.h>
typedef uint8_t BYTE;
typedef uint16_t U16;
@@ -182,7 +192,7 @@ Note : this source file requires "lz4_encoder.h"
#endif
#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-# ifdef __IBMC__
+# if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC)
# pragma pack(1)
# else
# pragma pack(push, 1)
@@ -195,7 +205,11 @@ typedef struct { U64 v; } _PACKED U64_S;
typedef struct {size_t v;} _PACKED size_t_S;
#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-# pragma pack(pop)
+# if defined(__SUNPRO_C) || defined(__SUNPRO_CC)
+# pragma pack(0)
+# else
+# pragma pack(pop)
+# endif
#endif
#define A16(x) (((U16_S *)(x))->v)
@@ -204,20 +218,26 @@ typedef struct {size_t v;} _PACKED size_t_S;
#define AARCH(x) (((size_t_S *)(x))->v)
-//**************************************
-// Constants
-//**************************************
-#define HASHTABLESIZE (1 << MEMORY_USAGE)
+/**************************************
+ Constants
+**************************************/
+#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
+#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define HASH_SIZE_U32 (1 << LZ4_HASHLOG)
#define MINMATCH 4
#define COPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (COPYLENGTH+MINMATCH)
-#define MINLENGTH (MFLIMIT+1)
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1U<<10)
+#define MB *(1U<<20)
+#define GB *(1U<<30)
-#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT-1))
-#define SKIPSTRENGTH 6 // Increasing this value will make the compression run slower on incompressible data
+#define LZ4_64KLIMIT ((64 KB) + (MFLIMIT-1))
+#define SKIPSTRENGTH 6 /* Increasing this value will make the compression run slower on incompressible data */
#define MAXD_LOG 16
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
@@ -228,44 +248,61 @@ typedef struct {size_t v;} _PACKED size_t_S;
#define RUN_MASK ((1U<<RUN_BITS)-1)
-//**************************************
-// Architecture-specific macros
-//**************************************
+/**************************************
+ Structures and local types
+**************************************/
+typedef struct {
+ U32 hashTable[HASH_SIZE_U32];
+ U32 currentOffset;
+ U32 initCheck;
+ const BYTE* dictionary;
+ const BYTE* bufferStart;
+ U32 dictSize;
+} LZ4_stream_t_internal;
+
+typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
+
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+
+
+/**************************************
+ Architecture-specific macros
+**************************************/
#define STEPSIZE sizeof(size_t)
-#define LZ4_COPYSTEP(s,d) { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; }
-#define LZ4_COPY8(s,d) { LZ4_COPYSTEP(s,d); if (STEPSIZE<8) LZ4_COPYSTEP(s,d); }
-#define LZ4_SECURECOPY(s,d,e) { if ((STEPSIZE==8)&&(d<e)) LZ4_WILDCOPY(s,d,e); }
-
-#if LZ4_ARCH64 // 64-bit
-# define HTYPE U32
-# define INITBASE(base) const BYTE* const base = ip
-#else // 32-bit
-# define HTYPE const BYTE*
-# define INITBASE(base) const int base = 0
-#endif
+#define LZ4_COPYSTEP(d,s) { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; }
+#define LZ4_COPY8(d,s) { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); }
#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE))
# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
# define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }
-#else // Little Endian
+#else /* Little Endian */
# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }
# define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; }
#endif
-//**************************************
-// Macros
-//**************************************
-#define LZ4_WILDCOPY(s,d,e) { do { LZ4_COPY8(s,d) } while (d<e); }
-#define LZ4_BLINDCOPY(s,d,l) { BYTE* e=(d)+(l); LZ4_WILDCOPY(s,d,e); d=e; }
+/**************************************
+ Macros
+**************************************/
+#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(!!(c)) }; } /* use only *after* variable declarations */
+#if LZ4_ARCH64 || !defined(__GNUC__)
+# define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (d<e); } /* at the end, d>=e; */
+#else
+# define LZ4_WILDCOPY(d,s,e) { if (likely(e-d <= 8)) LZ4_COPY8(d,s) else do { LZ4_COPY8(d,s) } while (d<e); }
+#endif
-//****************************
-// Private functions
-//****************************
+/****************************
+ Private local functions
+****************************/
#if LZ4_ARCH64
-forceinline int LZ4_NbCommonBytes (register U64 val)
+static int LZ4_NbCommonBytes (register U64 val)
{
# if defined(LZ4_BIG_ENDIAN)
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
@@ -297,7 +334,7 @@ forceinline int LZ4_NbCommonBytes (register U64 val)
#else
-forceinline int LZ4_NbCommonBytes (register U32 val)
+static int LZ4_NbCommonBytes (register U32 val)
{
# if defined(LZ4_BIG_ENDIAN)
# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
@@ -329,227 +366,530 @@ forceinline int LZ4_NbCommonBytes (register U32 val)
#endif
+/********************************
+ Compression functions
+********************************/
+int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
+int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); }
-//******************************
-// Compression functions
-//******************************
+static int LZ4_hashSequence(U32 sequence, tableType_t tableType)
+{
+ if (tableType == byU16)
+ return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
+ else
+ return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
+}
-/*
-int LZ4_compress_stack(
- const char* source,
- char* dest,
- int inputSize)
+static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); }
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest'.
-Destination buffer must be already allocated, and sized at a minimum of LZ4_compressBound(inputSize).
-return : the number of bytes written in buffer 'dest'
-*/
-#define FUNCTION_NAME LZ4_compress_stack
-#include "lz4_encoder.h"
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ switch (tableType)
+ {
+ case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; }
+ case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; }
+ case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; }
+ }
+}
+static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ U32 h = LZ4_hashPosition(p, tableType);
+ LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
+}
-/*
-int LZ4_compress_stack_limitedOutput(
- const char* source,
- char* dest,
- int inputSize,
- int maxOutputSize)
+static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
+ if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
+ { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */
+}
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
-If it cannot achieve it, compression will stop, and result of the function will be zero.
-return : the number of bytes written in buffer 'dest', or 0 if the compression fails
-*/
-#define FUNCTION_NAME LZ4_compress_stack_limitedOutput
-#define LIMITED_OUTPUT
-#include "lz4_encoder.h"
+static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ U32 h = LZ4_hashPosition(p, tableType);
+ return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
+}
+static unsigned LZ4_count(const BYTE* pIn, const BYTE* pRef, const BYTE* pInLimit)
+{
+ const BYTE* const pStart = pIn;
-/*
-int LZ4_compress64k_stack(
- const char* source,
- char* dest,
- int inputSize)
+ while (likely(pIn<pInLimit-(STEPSIZE-1)))
+ {
+ size_t diff = AARCH(pRef) ^ AARCH(pIn);
+ if (!diff) { pIn+=STEPSIZE; pRef+=STEPSIZE; continue; }
+ pIn += LZ4_NbCommonBytes(diff);
+ return (unsigned)(pIn - pStart);
+ }
+ if (LZ4_64BITS) if ((pIn<(pInLimit-3)) && (A32(pRef) == A32(pIn))) { pIn+=4; pRef+=4; }
+ if ((pIn<(pInLimit-1)) && (A16(pRef) == A16(pIn))) { pIn+=2; pRef+=2; }
+ if ((pIn<pInLimit) && (*pRef == *pIn)) pIn++;
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest'.
-This function compresses better than LZ4_compress_stack(), on the condition that
-'inputSize' must be < to LZ4_64KLIMIT, or the function will fail.
-Destination buffer must be already allocated, and sized at a minimum of LZ4_compressBound(inputSize).
-return : the number of bytes written in buffer 'dest', or 0 if compression fails
-*/
-#define FUNCTION_NAME LZ4_compress64k_stack
-#define COMPRESS_64K
-#include "lz4_encoder.h"
+ return (unsigned)(pIn - pStart);
+}
-/*
-int LZ4_compress64k_stack_limitedOutput(
+static int LZ4_compress_generic(
+ void* ctx,
const char* source,
char* dest,
int inputSize,
- int maxOutputSize)
+ int maxOutputSize,
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
-This function compresses better than LZ4_compress_stack_limitedOutput(), on the condition that
-'inputSize' must be < to LZ4_64KLIMIT, or the function will fail.
-If it cannot achieve it, compression will stop, and result of the function will be zero.
-return : the number of bytes written in buffer 'dest', or 0 if the compression fails
-*/
-#define FUNCTION_NAME LZ4_compress64k_stack_limitedOutput
-#define COMPRESS_64K
-#define LIMITED_OUTPUT
-#include "lz4_encoder.h"
+ limitedOutput_directive outputLimited,
+ tableType_t tableType,
+ dict_directive dict,
+ dictIssue_directive dictIssue)
+{
+ LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx;
+
+ const BYTE* ip = (const BYTE*) source;
+ const BYTE* base;
+ const BYTE* lowLimit;
+ const BYTE* const lowRefLimit = ip - dictPtr->dictSize;
+ const BYTE* const dictionary = dictPtr->dictionary;
+ const BYTE* const dictEnd = dictionary + dictPtr->dictSize;
+ const size_t dictDelta = dictEnd - (const BYTE*)source;
+ const BYTE* anchor = (const BYTE*) source;
+ const BYTE* const iend = ip + inputSize;
+ const BYTE* const mflimit = iend - MFLIMIT;
+ const BYTE* const matchlimit = iend - LASTLITERALS;
+ BYTE* op = (BYTE*) dest;
+ BYTE* const olimit = op + maxOutputSize;
-/*
-void* LZ4_createHeapMemory();
-int LZ4_freeHeapMemory(void* ctx);
+ const int skipStrength = SKIPSTRENGTH;
+ U32 forwardH;
+ size_t refDelta=0;
-Used to allocate and free hashTable memory
-to be used by the LZ4_compress_heap* family of functions.
-LZ4_createHeapMemory() returns NULL is memory allocation fails.
-*/
-void* LZ4_create() { return malloc(HASHTABLESIZE); }
-int LZ4_free(void* ctx) { free(ctx); return 0; }
+ /* Init conditions */
+ if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */
+ switch(dict)
+ {
+ case noDict:
+ default:
+ base = (const BYTE*)source;
+ lowLimit = (const BYTE*)source;
+ break;
+ case withPrefix64k:
+ base = (const BYTE*)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE*)source - dictPtr->dictSize;
+ break;
+ case usingExtDict:
+ base = (const BYTE*)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE*)source;
+ break;
+ }
+ if ((tableType == byU16) && (inputSize>=(int)LZ4_64KLIMIT)) return 0; /* Size too large (not within 64K limit) */
+ if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */
+ /* First Byte */
+ LZ4_putPosition(ip, ctx, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
-/*
-int LZ4_compress_heap(
- void* ctx,
- const char* source,
- char* dest,
- int inputSize)
+ /* Main Loop */
+ for ( ; ; )
+ {
+ const BYTE* ref;
+ BYTE* token;
+ {
+ const BYTE* forwardIp = ip;
+ unsigned step=1;
+ unsigned searchMatchNb = (1U << skipStrength);
+
+ /* Find a match */
+ do {
+ U32 h = forwardH;
+ ip = forwardIp;
+ forwardIp += step;
+ step = searchMatchNb++ >> skipStrength;
+
+ if (unlikely(forwardIp > mflimit)) goto _last_literals;
+
+ ref = LZ4_getPositionOnHash(h, ctx, tableType, base);
+ if (dict==usingExtDict)
+ {
+ if (ref<(const BYTE*)source)
+ {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ }
+ else
+ {
+ refDelta = 0;
+ lowLimit = (const BYTE*)source;
+ }
+ }
+ forwardH = LZ4_hashPosition(forwardIp, tableType);
+ LZ4_putPositionOnHash(ip, h, ctx, tableType, base);
+
+ } while ( ((dictIssue==dictSmall) ? (ref < lowRefLimit) : 0)
+ || ((tableType==byU16) ? 0 : (ref + MAX_DISTANCE < ip))
+ || (A32(ref+refDelta) != A32(ip)) );
+ }
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest'.
-The memory used for compression must be created by LZ4_createHeapMemory() and provided by pointer 'ctx'.
-Destination buffer must be already allocated, and sized at a minimum of LZ4_compressBound(inputSize).
-return : the number of bytes written in buffer 'dest'
-*/
-#define FUNCTION_NAME LZ4_compress_heap
-#define USE_HEAPMEMORY
-#include "lz4_encoder.h"
+ /* Catch up */
+ while ((ip>anchor) && (ref+refDelta > lowLimit) && (unlikely(ip[-1]==ref[refDelta-1]))) { ip--; ref--; }
+ {
+ /* Encode Literal length */
+ unsigned litLength = (unsigned)(ip - anchor);
+ token = op++;
+ if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
+ return 0; /* Check output limit */
+ if (litLength>=RUN_MASK)
+ {
+ int len = (int)litLength-RUN_MASK;
+ *token=(RUN_MASK<<ML_BITS);
+ for(; len >= 255 ; len-=255) *op++ = 255;
+ *op++ = (BYTE)len;
+ }
+ else *token = (BYTE)(litLength<<ML_BITS);
-/*
-int LZ4_compress_heap_limitedOutput(
- void* ctx,
- const char* source,
- char* dest,
- int inputSize,
- int maxOutputSize)
+ /* Copy Literals */
+ { BYTE* end = op+litLength; LZ4_WILDCOPY(op,anchor,end); op=end; }
+ }
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
-If it cannot achieve it, compression will stop, and result of the function will be zero.
-The memory used for compression must be created by LZ4_createHeapMemory() and provided by pointer 'ctx'.
-return : the number of bytes written in buffer 'dest', or 0 if the compression fails
-*/
-#define FUNCTION_NAME LZ4_compress_heap_limitedOutput
-#define LIMITED_OUTPUT
-#define USE_HEAPMEMORY
-#include "lz4_encoder.h"
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (U16)(ip-ref));
+ /* Encode MatchLength */
+ {
+ unsigned matchLength;
-/*
-int LZ4_compress64k_heap(
- void* ctx,
- const char* source,
- char* dest,
- int inputSize)
+ if ((dict==usingExtDict) && (lowLimit==dictionary))
+ {
+ const BYTE* limit;
+ ref += refDelta;
+ limit = ip + (dictEnd-ref);
+ if (limit > matchlimit) limit = matchlimit;
+ matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit);
+ ip += MINMATCH + matchLength;
+ if (ip==limit)
+ {
+ unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+ matchLength += more;
+ ip += more;
+ }
+ }
+ else
+ {
+ matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit);
+ ip += MINMATCH + matchLength;
+ }
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest'.
-The memory used for compression must be created by LZ4_createHeapMemory() and provided by pointer 'ctx'.
-'inputSize' must be < to LZ4_64KLIMIT, or the function will fail.
-Destination buffer must be already allocated, and sized at a minimum of LZ4_compressBound(inputSize).
-return : the number of bytes written in buffer 'dest'
-*/
-#define FUNCTION_NAME LZ4_compress64k_heap
-#define COMPRESS_64K
-#define USE_HEAPMEMORY
-#include "lz4_encoder.h"
+ if (matchLength>=ML_MASK)
+ {
+ if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit)))
+ return 0; /* Check output limit */
+ *token += ML_MASK;
+ matchLength -= ML_MASK;
+ for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; }
+ if (matchLength >= 255) { matchLength-=255; *op++ = 255; }
+ *op++ = (BYTE)matchLength;
+ }
+ else *token += (BYTE)(matchLength);
+ }
+ anchor = ip;
-/*
-int LZ4_compress64k_heap_limitedOutput(
- void* ctx,
- const char* source,
- char* dest,
- int inputSize,
- int maxOutputSize)
+ /* Test end of chunk */
+ if (ip > mflimit) break;
-Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
-If it cannot achieve it, compression will stop, and result of the function will be zero.
-The memory used for compression must be created by LZ4_createHeapMemory() and provided by pointer 'ctx'.
-'inputSize' must be < to LZ4_64KLIMIT, or the function will fail.
-return : the number of bytes written in buffer 'dest', or 0 if the compression fails
-*/
-#define FUNCTION_NAME LZ4_compress64k_heap_limitedOutput
-#define COMPRESS_64K
-#define LIMITED_OUTPUT
-#define USE_HEAPMEMORY
-#include "lz4_encoder.h"
+ /* Fill table */
+ LZ4_putPosition(ip-2, ctx, tableType, base);
+
+ /* Test next position */
+ ref = LZ4_getPosition(ip, ctx, tableType, base);
+ if (dict==usingExtDict)
+ {
+ if (ref<(const BYTE*)source)
+ {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ }
+ else
+ {
+ refDelta = 0;
+ lowLimit = (const BYTE*)source;
+ }
+ }
+ LZ4_putPosition(ip, ctx, tableType, base);
+ if ( ((dictIssue==dictSmall) ? (ref>=lowRefLimit) : 1)
+ && (ref+MAX_DISTANCE>=ip)
+ && (A32(ref+refDelta)==A32(ip)) )
+ { token=op++; *token=0; goto _next_match; }
+
+ /* Prepare next loop */
+ forwardH = LZ4_hashPosition(++ip, tableType);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ {
+ int lastRun = (int)(iend - anchor);
+ if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize))
+ return 0; /* Check output limit */
+ if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
+ else *op++ = (BYTE)(lastRun<<ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend-anchor;
+ }
+
+ /* End */
+ return (int) (((char*)op)-dest);
+}
int LZ4_compress(const char* source, char* dest, int inputSize)
{
-#if HEAPMODE
- void* ctx = LZ4_create();
+#if (HEAPMODE)
+ void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */
+#else
+ U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */
+#endif
int result;
- if (ctx == NULL) return 0; // Failed allocation => compression not done
- if (inputSize < LZ4_64KLIMIT)
- result = LZ4_compress64k_heap(ctx, source, dest, inputSize);
- else result = LZ4_compress_heap(ctx, source, dest, inputSize);
- LZ4_free(ctx);
+
+ if (inputSize < (int)LZ4_64KLIMIT)
+ result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue);
+ else
+ result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue);
+
+#if (HEAPMODE)
+ FREEMEM(ctx);
+#endif
return result;
+}
+
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+#if (HEAPMODE)
+ void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */
#else
- if (inputSize < (int)LZ4_64KLIMIT) return LZ4_compress64k_stack(source, dest, inputSize);
- return LZ4_compress_stack(source, dest, inputSize);
+ U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */
+#endif
+ int result;
+
+ if (inputSize < (int)LZ4_64KLIMIT)
+ result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue);
+ else
+ result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue);
+
+#if (HEAPMODE)
+ FREEMEM(ctx);
#endif
+ return result;
}
-int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+/*****************************************
+ Experimental : Streaming functions
+*****************************************/
+
+/*
+ * LZ4_initStream
+ * Use this function once, to init a newly allocated LZ4_stream_t structure
+ * Return : 1 if OK, 0 if error
+ */
+void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
+{
+ MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
+LZ4_stream_t* LZ4_createStream(void)
+{
+ LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(4, LZ4_STREAMSIZE_U32);
+ LZ4_resetStream(lz4s);
+ return lz4s;
+}
+
+int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
+{
+ FREEMEM(LZ4_stream);
+ return (0);
+}
+
+
+int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
+{
+ LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
+ const BYTE* p = (const BYTE*)dictionary;
+ const BYTE* const dictEnd = p + dictSize;
+ const BYTE* base;
+
+ LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */
+ if (dict->initCheck) LZ4_resetStream(LZ4_dict); /* Uninitialized structure detected */
+
+ if (dictSize < MINMATCH)
+ {
+ dict->dictionary = NULL;
+ dict->dictSize = 0;
+ return 1;
+ }
+
+ if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB;
+ base = p - dict->currentOffset;
+ dict->dictionary = p;
+ dict->dictSize = (U32)(dictEnd - p);
+ dict->currentOffset += dict->dictSize;
+
+ while (p <= dictEnd-MINMATCH)
+ {
+ LZ4_putPosition(p, dict, byU32, base);
+ p+=3;
+ }
+
+ return 1;
+}
+
+
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
{
-#if HEAPMODE
- void* ctx = LZ4_create();
+ if ((LZ4_dict->currentOffset > 0x80000000) ||
+ ((size_t)LZ4_dict->currentOffset > (size_t)src)) /* address space overflow */
+ {
+ /* rescale hash table */
+ U32 delta = LZ4_dict->currentOffset - 64 KB;
+ const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
+ int i;
+ for (i=0; i<HASH_SIZE_U32; i++)
+ {
+ if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
+ else LZ4_dict->hashTable[i] -= delta;
+ }
+ LZ4_dict->currentOffset = 64 KB;
+ if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
+ LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
+ }
+}
+
+
+FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* source, char* dest, int inputSize,
+ int maxOutputSize, limitedOutput_directive limit)
+{
+ LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream;
+ const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+ const BYTE* smallest = (const BYTE*) source;
+ if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */
+ if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
+ LZ4_renormDictT(streamPtr, smallest);
+
+ /* Check overlapping input/dictionary space */
+ {
+ const BYTE* sourceEnd = (const BYTE*) source + inputSize;
+ if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd))
+ {
+ streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
+ if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
+ if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
+ streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+ }
+ }
+
+ /* prefix mode : source data follows dictionary */
+ if (dictEnd == (const BYTE*)source)
+ {
+ int result;
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, dictSmall);
+ else
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, noDictIssue);
+ streamPtr->dictSize += (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+
+ /* external dictionary mode */
+ {
+ int result;
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, dictSmall);
+ else
+ result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, noDictIssue);
+ streamPtr->dictionary = (const BYTE*)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+}
+
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize)
+{
+ return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, 0, notLimited);
+}
+
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+ return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput);
+}
+
+
+/* Hidden debug function, to force separate dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+{
+ LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict;
int result;
- if (ctx == NULL) return 0; // Failed allocation => compression not done
- if (inputSize < LZ4_64KLIMIT)
- result = LZ4_compress64k_heap_limitedOutput(ctx, source, dest, inputSize, maxOutputSize);
- else result = LZ4_compress_heap_limitedOutput(ctx, source, dest, inputSize, maxOutputSize);
- LZ4_free(ctx);
+ const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+ const BYTE* smallest = dictEnd;
+ if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
+ LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest);
+
+ result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue);
+
+ streamPtr->dictionary = (const BYTE*)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+
return result;
-#else
- if (inputSize < (int)LZ4_64KLIMIT) return LZ4_compress64k_stack_limitedOutput(source, dest, inputSize, maxOutputSize);
- return LZ4_compress_stack_limitedOutput(source, dest, inputSize, maxOutputSize);
-#endif
}
-//****************************
-// Decompression functions
-//****************************
+int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
+{
+ LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
+ const BYTE* previousDictEnd = dict->dictionary + dict->dictSize;
-typedef enum { noPrefix = 0, withPrefix = 1 } prefix64k_directive;
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
-typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+ if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */
+ if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;
+ memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
-// This generic decompression function cover all use cases.
-// It shall be instanciated several times, using different sets of directives
-// Note that it is essential this generic function is really inlined,
-// in order to remove useless branches during compilation optimisation.
-forceinline int LZ4_decompress_generic(
+ dict->dictionary = (const BYTE*)safeBuffer;
+ dict->dictSize = (U32)dictSize;
+
+ return dictSize;
+}
+
+
+
+/****************************
+ Decompression functions
+****************************/
+/*
+ * This generic decompression function cover all use cases.
+ * It shall be instantiated several times, using different sets of directives
+ * Note that it is essential this generic function is really inlined,
+ * in order to remove useless branches during compilation optimization.
+ */
+FORCE_INLINE int LZ4_decompress_generic(
const char* source,
char* dest,
- int inputSize, //
- int outputSize, // OutputSize must be != 0; if endOnInput==endOnInputSize, this value is the max size of Output Buffer.
-
- int endOnInput, // endOnOutputSize, endOnInputSize
- int prefix64k, // noPrefix, withPrefix
- int partialDecoding, // full, partial
- int targetOutputSize // only used if partialDecoding==partial
+ int inputSize,
+ int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
+
+ int endOnInput, /* endOnOutputSize, endOnInputSize */
+ int partialDecoding, /* full, partial */
+ int targetOutputSize, /* only used if partialDecoding==partial */
+ int dict, /* noDict, withPrefix64k, usingExtDict */
+ const char* dictStart, /* only if dict==usingExtDict */
+ int dictSize /* note : = 0 if noDict */
)
{
- // Local Variables
+ /* Local Variables */
const BYTE* restrict ip = (const BYTE*) source;
const BYTE* ref;
const BYTE* const iend = ip + inputSize;
@@ -558,139 +898,370 @@ forceinline int LZ4_decompress_generic(
BYTE* const oend = op + outputSize;
BYTE* cpy;
BYTE* oexit = op + targetOutputSize;
+ const BYTE* const lowLimit = (const BYTE*)dest - dictSize;
- size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
-#if LZ4_ARCH64
- size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};
-#endif
+ const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
+ const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4};
+ const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};
+ const int safeDecode = (endOnInput==endOnInputSize);
+ const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
- // Special cases
- if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; // targetOutputSize too high => decode everything
- if ((endOnInput) && unlikely(outputSize==0)) return ((inputSize==1) && (*ip==0)) ? 0 : -1; // Empty output buffer
- if ((!endOnInput) && unlikely(outputSize==0)) return (*ip==0?1:-1);
+ /* Special cases */
+ if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */
+ if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */
+ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
- // Main Loop
+
+ /* Main Loop */
while (1)
{
unsigned token;
size_t length;
- // get runlength
+ /* get runlength */
token = *ip++;
if ((length=(token>>ML_BITS)) == RUN_MASK)
- {
- unsigned s=255;
- while (((endOnInput)?ip<iend:1) && (s==255))
- {
- s = *ip++;
- length += s;
- }
+ {
+ unsigned s;
+ do
+ {
+ s = *ip++;
+ length += s;
+ }
+ while (likely((endOnInput)?ip<iend-RUN_MASK:1) && (s==255));
+ if ((safeDecode) && LZ4_32BITS && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error; /* overflow detection */
+ if ((safeDecode) && LZ4_32BITS && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error; /* overflow detection */
}
- // copy literals
+ /* copy literals */
cpy = op+length;
if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
|| ((!endOnInput) && (cpy>oend-COPYLENGTH)))
{
if (partialDecoding)
{
- if (cpy > oend) goto _output_error; // Error : write attempt beyond end of output buffer
- if ((endOnInput) && (ip+length > iend)) goto _output_error; // Error : read attempt beyond end of input buffer
+ if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */
+ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */
}
else
{
- if ((!endOnInput) && (cpy != oend)) goto _output_error; // Error : block decoding must stop exactly there
- if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; // Error : input must be consumed
+ if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */
+ if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */
}
memcpy(op, ip, length);
ip += length;
op += length;
- break; // Necessarily EOF, due to parsing restrictions
+ break; /* Necessarily EOF, due to parsing restrictions */
}
- LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy;
+ LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy;
- // get offset
+ /* get offset */
LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;
- if ((prefix64k==noPrefix) && unlikely(ref < (BYTE* const)dest)) goto _output_error; // Error : offset outside destination buffer
+ if ((checkOffset) && (unlikely(ref < lowLimit))) goto _output_error; /* Error : offset outside destination buffer */
+
+ /* get matchlength */
+ if ((length=(token&ML_MASK)) == ML_MASK)
+ {
+ unsigned s;
+ do
+ {
+ if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
+ s = *ip++;
+ length += s;
+ } while (s==255);
+ if ((safeDecode) && LZ4_32BITS && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */
+ }
+ length += MINMATCH;
+
+ /* check external dictionary */
+ if ((dict==usingExtDict) && (ref < (BYTE* const)dest))
+ {
+ if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;
- // get matchlength
- if ((length=(token&ML_MASK)) == ML_MASK)
- {
- for ( ; (!endOnInput) || (ip<iend-(LASTLITERALS+1)) ; ) // Ensure enough bytes remain for LASTLITERALS + token
+ if (length <= (size_t)(dest-(char*)ref))
{
- unsigned s = *ip++;
- length += s;
- if (s==255) continue;
- break;
+ ref = dictEnd - (dest-(char*)ref);
+ memcpy(op, ref, length);
+ op += length;
}
+ else
+ {
+ size_t copySize = (size_t)(dest-(char*)ref);
+ memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+ copySize = length - copySize;
+ if (copySize > (size_t)((char*)op-dest)) /* overlap */
+ {
+ BYTE* const endOfMatch = op + copySize;
+ const BYTE* copyFrom = (BYTE*)dest;
+ while (op < endOfMatch) *op++ = *copyFrom++;
+ }
+ else
+ {
+ memcpy(op, dest, copySize);
+ op += copySize;
+ }
+ }
+ continue;
}
- // copy repeated sequence
- if unlikely((op-ref)<(int)STEPSIZE)
+ /* copy repeated sequence */
+ cpy = op + length;
+ if (unlikely((op-ref)<(int)STEPSIZE))
{
-#if LZ4_ARCH64
- size_t dec64 = dec64table[op-ref];
-#else
- const size_t dec64 = 0;
-#endif
+ const size_t dec64 = dec64table[op-ref];
op[0] = ref[0];
op[1] = ref[1];
op[2] = ref[2];
op[3] = ref[3];
- op += 4, ref += 4; ref -= dec32table[op-ref];
- A32(op) = A32(ref);
- op += STEPSIZE-4; ref -= dec64;
- } else { LZ4_COPYSTEP(ref,op); }
- cpy = op + length - (STEPSIZE-4);
+ ref += dec32table[op-ref];
+ A32(op+4) = A32(ref);
+ op += 8; ref -= dec64;
+ } else { LZ4_COPY8(op,ref); }
- if unlikely(cpy>oend-(COPYLENGTH)-(STEPSIZE-4))
+ if (unlikely(cpy>oend-12))
{
- if (cpy > oend-LASTLITERALS) goto _output_error; // Error : last 5 bytes must be literals
- LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH));
+ if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last 5 bytes must be literals */
+ if (op<oend-COPYLENGTH) LZ4_WILDCOPY(op, ref, (oend-COPYLENGTH));
while(op<cpy) *op++=*ref++;
- op=cpy;
- continue;
}
- LZ4_WILDCOPY(ref, op, cpy);
- op=cpy; // correction
+ else LZ4_WILDCOPY(op, ref, cpy);
+ op=cpy; /* correction */
}
- // end of decoding
+ /* end of decoding */
if (endOnInput)
- return (int) (((char*)op)-dest); // Nb of output bytes decoded
+ return (int) (((char*)op)-dest); /* Nb of output bytes decoded */
else
- return (int) (((char*)ip)-source); // Nb of input bytes read
+ return (int) (((char*)ip)-source); /* Nb of input bytes read */
- // Overflow error detected
+ /* Overflow error detected */
_output_error:
return (int) (-(((char*)ip)-source))-1;
}
-int LZ4_decompress_safe(const char* source, char* dest, int inputSize, int maxOutputSize)
+int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, NULL, 0);
+}
+
+int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, NULL, 0);
+}
+
+int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, NULL, 64 KB);
+}
+
+/* streaming decompression functions */
+
+typedef struct
+{
+ const char* dictionary;
+ int dictSize;
+} LZ4_streamDecode_t_internal;
+
+/*
+ * If you prefer dynamic allocation methods,
+ * LZ4_createStreamDecode()
+ * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure.
+ */
+LZ4_streamDecode_t* LZ4_createStreamDecode(void)
+{
+ LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(sizeof(U32), LZ4_STREAMDECODESIZE_U32);
+ MEM_INIT(lz4s, 0, LZ4_STREAMDECODESIZE);
+ return lz4s;
+}
+
+int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
+{
+ FREEMEM(LZ4_stream);
+ return 0;
+}
+
+/*
+ * LZ4_setStreamDecode
+ * Use this function to instruct where to find the dictionary
+ * This function is not necessary if previous data is still available where it was decoded.
+ * Loading a size of 0 is allowed (same effect as no dictionary).
+ * Return : 1 if OK, 0 if error
+ */
+int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ lz4sd->dictionary = dictionary;
+ lz4sd->dictSize = dictSize;
+ return 1;
+}
+
+/*
+*_continue() :
+ These decoding functions allow decompression of multiple blocks in "streaming" mode.
+ Previously decoded blocks must still be available at the memory position where they were decoded.
+ If it's not possible, save the relevant part of decoded data into a safe buffer,
+ and indicate where it stands using LZ4_setDictDecode()
+*/
+int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ int result;
+
+ result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize);
+ if (result <= 0) return result;
+ if (lz4sd->dictionary + lz4sd->dictSize == dest)
+ {
+ lz4sd->dictSize += result;
+ }
+ else
+ {
+ lz4sd->dictionary = dest;
+ lz4sd->dictSize = result;
+ }
+
+ return result;
+}
+
+int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
+{
+ LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+ int result;
+
+ result = LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize);
+ if (result <= 0) return result;
+ if (lz4sd->dictionary + lz4sd->dictSize == dest)
+ {
+ lz4sd->dictSize += result;
+ }
+ else
+ {
+ lz4sd->dictionary = dest;
+ lz4sd->dictSize = result;
+ }
+
+ return result;
+}
+
+
+/*
+Advanced decoding functions :
+*_usingDict() :
+ These decoding functions work the same as "_continue" ones,
+ the dictionary must be explicitly provided within parameters
+*/
+
+FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
+{
+ if (dictSize==0)
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, NULL, 64 KB);
+ if ((dictStart+dictSize == dest) && (dictSize >= (int)(64 KB - 1)))
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, NULL, 64 KB);
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, dictStart, dictSize);
+}
+
+int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
- return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, full, 0);
+ //return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize);
+ return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
}
-int LZ4_decompress_fast(const char* source, char* dest, int outputSize)
+int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
- return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, noPrefix, full, 0);
+ //return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, dictStart, dictSize);
+ return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
}
-int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int inputSize, int maxOutputSize)
+/* debug function */
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize);
+}
+
+
+/***************************************************
+ Obsolete Functions
+***************************************************/
+/*
+These function names are deprecated and should no longer be used.
+They are only provided here for compatibility with older user programs.
+- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
+- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
+*/
+int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
+int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
+
+
+/* Obsolete Streaming functions */
+
+int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
+
+static void LZ4_init(LZ4_stream_t_internal* lz4ds, const BYTE* base)
{
- return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, withPrefix, full, 0);
+ MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE);
+ lz4ds->bufferStart = base;
}
-int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int outputSize)
+int LZ4_resetStreamState(void* state, const char* inputBuffer)
{
- return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, withPrefix, full, 0);
+ if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */
+ LZ4_init((LZ4_stream_t_internal*)state, (const BYTE*)inputBuffer);
+ return 0;
}
-int LZ4_decompress_safe_partial(const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize)
+void* LZ4_create (const char* inputBuffer)
{
- return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, partial, targetOutputSize);
+ void* lz4ds = ALLOCATOR(4, LZ4_STREAMSIZE_U32);
+ LZ4_init ((LZ4_stream_t_internal*)lz4ds, (const BYTE*)inputBuffer);
+ return lz4ds;
}
+char* LZ4_slideInputBuffer (void* LZ4_Data)
+{
+ LZ4_stream_t_internal* lz4ds = (LZ4_stream_t_internal*)LZ4_Data;
+
+ LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)lz4ds->bufferStart, 64 KB);
+
+ return (char*)(lz4ds->bufferStart + 64 KB);
+}
+
+/* Obsolete compresson functions using User-allocated state */
+
+int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
+
+int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize)
+{
+ if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */
+ MEM_INIT(state, 0, LZ4_STREAMSIZE);
+
+ if (inputSize < (int)LZ4_64KLIMIT)
+ return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue);
+ else
+ return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue);
+}
+
+int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+ if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */
+ MEM_INIT(state, 0, LZ4_STREAMSIZE);
+
+ if (inputSize < (int)LZ4_64KLIMIT)
+ return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue);
+ else
+ return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue);
+}
+
+/* Obsolete streaming decompression functions */
+
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, NULL, 64 KB);
+}
+
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, NULL, 64 KB);
+}
http://git-wip-us.apache.org/repos/asf/hadoop/blob/8addbe2b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h
index d866234..44ada14 100644
--- a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h
+++ b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.h
@@ -1,7 +1,7 @@
/*
LZ4 - Fast LZ compression algorithm
Header File
- Copyright (C) 2011-2013, Yann Collet.
+ Copyright (C) 2011-2014, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
@@ -28,151 +28,295 @@
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- LZ4 source repository : http://code.google.com/p/lz4/
+ - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/
-
-/*
- Copied from:
- URL: http://lz4.googlecode.com/svn/trunk
- Repository Root: http://lz4.googlecode.com/svn
- Repository UUID: 650e7d94-2a16-8b24-b05c-7c0b3f6821cd
- Revision: 99
- Node Kind: directory
- Schedule: normal
- Last Changed Author: yann.collet.73@gmail.com
- Last Changed Rev: 99
- Last Changed Date: 2013-07-27 19:19:31 +0800 (Sat, 27 Jul 2013)
- */
-
#pragma once
#if defined (__cplusplus)
extern "C" {
#endif
+/*
+ * lz4.h provides raw compression format functions, for optimal performance and integration into programs.
+ * If you need to generate data using an inter-operable format (respecting the framing specification),
+ * please use lz4frame.h instead.
+*/
-//**************************************
-// Compiler Options
-//**************************************
-#if defined(_MSC_VER) && !defined(__cplusplus) // Visual Studio
-# define inline __inline // Visual C is not C99, but supports some kind of inline
-#endif
+/**************************************
+ Version
+**************************************/
+#define LZ4_VERSION_MAJOR 1 /* for major interface/format changes */
+#define LZ4_VERSION_MINOR 3 /* for minor interface/format changes */
+#define LZ4_VERSION_RELEASE 1 /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
+int LZ4_versionNumber (void);
+
+/**************************************
+ Tuning parameter
+**************************************/
+/*
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio
+ * Reduced memory usage can improve speed, due to cache effect
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ */
+#define LZ4_MEMORY_USAGE 14
-//****************************
-// Simple Functions
-//****************************
+/**************************************
+ Simple Functions
+**************************************/
-int LZ4_compress (const char* source, char* dest, int inputSize);
-int LZ4_decompress_safe (const char* source, char* dest, int inputSize, int maxOutputSize);
+int LZ4_compress (const char* source, char* dest, int sourceSize);
+int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize);
/*
LZ4_compress() :
- Compresses 'inputSize' bytes from 'source' into 'dest'.
+ Compresses 'sourceSize' bytes from 'source' into 'dest'.
Destination buffer must be already allocated,
and must be sized to handle worst cases situations (input data not compressible)
Worst case size evaluation is provided by function LZ4_compressBound()
- inputSize : Max supported value is ~1.9GB
+ inputSize : Max supported value is LZ4_MAX_INPUT_SIZE
return : the number of bytes written in buffer dest
or 0 if the compression fails
LZ4_decompress_safe() :
- maxOutputSize : is the size of the destination buffer (which must be already allocated)
- return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
+ compressedSize : is obviously the source size
+ maxDecompressedSize : is the size of the destination buffer, which must be already allocated.
+ return : the number of bytes decompressed into the destination buffer (necessarily <= maxDecompressedSize)
+ If the destination buffer is not large enough, decoding will stop and output an error code (<0).
If the source stream is detected malformed, the function will stop decoding and return a negative result.
- This function is protected against buffer overflow exploits (never writes outside of output buffer, and never reads outside of input buffer). Therefore, it is protected against malicious data packets
+ This function is protected against buffer overflow exploits,
+ and never writes outside of output buffer, nor reads outside of input buffer.
+ It is also protected against malicious data packets.
*/
-//****************************
-// Advanced Functions
-//****************************
-
-static inline int LZ4_compressBound(int isize) { return ((isize) + ((isize)/255) + 16); }
-#define LZ4_COMPRESSBOUND( isize) ((isize) + ((isize)/255) + 16)
+/**************************************
+ Advanced Functions
+**************************************/
+#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize) ((unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
/*
LZ4_compressBound() :
- Provides the maximum size that LZ4 may output in a "worst case" scenario (input data not compressible)
- primarily useful for memory allocation of output buffer.
- inline function is recommended for the general case,
- macro is also provided when result needs to be evaluated at compilation (such as table size allocation).
+ Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
+ This function is primarily useful for memory allocation purposes (output buffer size).
+ Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
- isize : is the input size. Max supported value is ~1.9GB
+ isize : is the input size. Max supported value is LZ4_MAX_INPUT_SIZE
return : maximum output size in a "worst case" scenario
- note : this function is limited by "int" range (2^31-1)
+ or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE)
*/
+int LZ4_compressBound(int isize);
-int LZ4_compress_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize);
-
/*
LZ4_compress_limitedOutput() :
- Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
+ Compress 'sourceSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.
If it cannot achieve it, compression will stop, and result of the function will be zero.
+ This saves time and memory on detecting non-compressible (or barely compressible) data.
This function never writes outside of provided output buffer.
- inputSize : Max supported value is ~1.9GB
+ sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE
maxOutputSize : is the size of the destination buffer (which must be already allocated)
return : the number of bytes written in buffer 'dest'
- or 0 if the compression fails
+ or 0 if compression fails
*/
+int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize);
+
+/*
+LZ4_compress_withState() :
+ Same compression functions, but using an externally allocated memory space to store compression state.
+ Use LZ4_sizeofState() to know how much memory must be allocated,
+ and then, provide it as 'void* state' to compression functions.
+*/
+int LZ4_sizeofState(void);
+int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
+int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
-int LZ4_decompress_fast (const char* source, char* dest, int outputSize);
/*
LZ4_decompress_fast() :
- outputSize : is the original (uncompressed) size
+ originalSize : is the original and therefore uncompressed size
return : the number of bytes read from the source buffer (in other words, the compressed size)
- If the source stream is malformed, the function will stop decoding and return a negative result.
- note : This function is a bit faster than LZ4_decompress_safe()
- This function never writes outside of output buffers, and never read before input buffer, but may read beyond input buffer (since it doesn't know its size) in case of malicious data packet.
- Use this function preferably into a trusted environment (data to decode comes from a trusted source).
- Destination buffer must be already allocated. Its size must be a minimum of 'outputSize' bytes.
+ If the source stream is detected malformed, the function will stop decoding and return a negative result.
+ Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes.
+ note : This function fully respect memory boundaries for properly formed compressed data.
+ It is a bit faster than LZ4_decompress_safe().
+ However, it does not provide any protection against intentionally modified data stream (malicious input).
+ Use this function in trusted environment only (data to decode comes from a trusted source).
*/
+int LZ4_decompress_fast (const char* source, char* dest, int originalSize);
-int LZ4_decompress_safe_partial (const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize);
/*
LZ4_decompress_safe_partial() :
- This function decompress a compressed block of size 'inputSize' at position 'source'
- into output buffer 'dest' of size 'maxOutputSize'.
- The function stops decompressing operation as soon as 'targetOutputSize' has been reached,
+ This function decompress a compressed block of size 'compressedSize' at position 'source'
+ into destination buffer 'dest' of size 'maxDecompressedSize'.
+ The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached,
reducing decompression time.
- return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
+ return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize)
Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller.
Always control how many bytes were decoded.
- If the source stream is malformed, the function will stop decoding and return a negative result.
+ If the source stream is detected malformed, the function will stop decoding and return a negative result.
This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets
*/
+int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize);
-int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int inputSize, int maxOutputSize);
-int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int outputSize);
+/***********************************************
+ Experimental Streaming Compression Functions
+***********************************************/
+#define LZ4_STREAMSIZE_U32 ((1 << (LZ4_MEMORY_USAGE-2)) + 8)
+#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U32 * sizeof(unsigned int))
/*
-*_withPrefix64k() :
- These decoding functions work the same as their "normal name" versions,
- but will potentially use up to 64KB of data in front of 'char* dest'.
- These functions are used for decoding inter-dependant blocks.
-*/
+ * LZ4_stream_t
+ * information structure to track an LZ4 stream.
+ * important : init this structure content before first use !
+ */
+typedef struct { unsigned int table[LZ4_STREAMSIZE_U32]; } LZ4_stream_t;
+
+/*
+ * LZ4_resetStream
+ * Use this function to init an allocated LZ4_stream_t structure
+ */
+void LZ4_resetStream (LZ4_stream_t* LZ4_streamPtr);
+
+/*
+ * If you prefer dynamic allocation methods,
+ * LZ4_createStream will allocate and initialize an LZ4_stream_t structure
+ * LZ4_freeStream releases its memory.
+ */
+LZ4_stream_t* LZ4_createStream(void);
+int LZ4_freeStream (LZ4_stream_t* LZ4_stream);
+
+/*
+ * LZ4_loadDict
+ * Use this function to load a static dictionary into LZ4_stream.
+ * Any previous data will be forgotten, only 'dictionary' will remain in memory.
+ * Loading a size of 0 is allowed.
+ * Return : 1 if OK, 0 if error
+ */
+int LZ4_loadDict (LZ4_stream_t* LZ4_stream, const char* dictionary, int dictSize);
+
+/*
+ * LZ4_compress_continue
+ * Compress data block 'source', using blocks compressed before as dictionary to improve compression ratio
+ * Previous data blocks are assumed to still be present at their previous location.
+ */
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize);
+
+/*
+ * LZ4_compress_limitedOutput_continue
+ * Same as before, but also specify a maximum target compressed size (maxOutputSize)
+ * If objective cannot be met, compression exits, and returns a zero.
+ */
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize);
+
+/*
+ * LZ4_saveDict
+ * If previously compressed data block is not guaranteed to remain available at its memory location
+ * save it into a safer place (char* safeBuffer)
+ * Note : you don't need to call LZ4_loadDict() afterwards,
+ * dictionary is immediately usable, you can therefore call again LZ4_compress_continue()
+ * Return : dictionary size in bytes, or 0 if error
+ * Note : any dictSize > 64 KB will be interpreted as 64KB.
+ */
+int LZ4_saveDict (LZ4_stream_t* LZ4_stream, char* safeBuffer, int dictSize);
+
+
+/************************************************
+ Experimental Streaming Decompression Functions
+************************************************/
+
+#define LZ4_STREAMDECODESIZE_U32 4
+#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U32 * sizeof(unsigned int))
+/*
+ * LZ4_streamDecode_t
+ * information structure to track an LZ4 stream.
+ * important : init this structure content using LZ4_setStreamDecode or memset() before first use !
+ */
+typedef struct { unsigned int table[LZ4_STREAMDECODESIZE_U32]; } LZ4_streamDecode_t;
+/*
+ * LZ4_setStreamDecode
+ * Use this function to instruct where to find the dictionary.
+ * This function can be used to specify a static dictionary,
+ * or to instruct where to find some previously decoded data saved into a different memory space.
+ * Setting a size of 0 is allowed (same effect as no dictionary).
+ * Return : 1 if OK, 0 if error
+ */
+int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
-//****************************
-// Obsolete Functions
-//****************************
+/*
+ * If you prefer dynamic allocation methods,
+ * LZ4_createStreamDecode will allocate and initialize an LZ4_streamDecode_t structure
+ * LZ4_freeStreamDecode releases its memory.
+ */
+LZ4_streamDecode_t* LZ4_createStreamDecode(void);
+int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
+
+/*
+*_continue() :
+ These decoding functions allow decompression of multiple blocks in "streaming" mode.
+ Previously decoded blocks must still be available at the memory position where they were decoded.
+ If it's not possible, save the relevant part of decoded data into a safe buffer,
+ and indicate where its new address using LZ4_setStreamDecode()
+*/
+int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize);
+int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize);
-static inline int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
-static inline int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
/*
-These functions are deprecated and should no longer be used.
-They are provided here for compatibility with existing user programs.
+Advanced decoding functions :
+*_usingDict() :
+ These decoding functions work the same as
+ a combination of LZ4_setDictDecode() followed by LZ4_decompress_x_continue()
+ They don't use nor update an LZ4_streamDecode_t structure.
*/
+int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize);
+int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize);
+
+/**************************************
+ Obsolete Functions
+**************************************/
+/*
+Obsolete decompression functions
+These function names are deprecated and should no longer be used.
+They are only provided here for compatibility with older user programs.
+- LZ4_uncompress is the same as LZ4_decompress_fast
+- LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe
+These function prototypes are now disabled; uncomment them if you really need them.
+It is highly recommended to stop using these functions and migrated to newer ones */
+/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */
+/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */
+
+/*
+ * If you prefer dynamic allocation methods,
+ * LZ4_createStreamDecode()
+ * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure.
+ * LZ4_free just frees it.
+ */
+/* void* LZ4_createStreamDecode(void); */
+/*int LZ4_free (void* LZ4_stream); yes, it's the same one as for compression */
+
+/* Obsolete streaming functions; use new streaming interface whenever possible */
+void* LZ4_create (const char* inputBuffer);
+int LZ4_sizeofStreamState(void);
+int LZ4_resetStreamState(void* state, const char* inputBuffer);
+char* LZ4_slideInputBuffer (void* state);
+
+/* Obsolete streaming decoding functions */
+int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int compressedSize, int maxOutputSize);
+int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int originalSize);
+
#if defined (__cplusplus)
}