hadoop-common-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From whe...@apache.org
Subject [2/2] hadoop git commit: HADOOP-12572. Update Hadoop's lz4 to r131. Contributed by Kevin Bowling.
Date Sun, 22 Nov 2015 23:44:21 GMT
HADOOP-12572. Update Hadoop's lz4 to r131. Contributed by Kevin Bowling.


Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo
Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/4c061e60
Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/4c061e60
Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/4c061e60

Branch: refs/heads/trunk
Commit: 4c061e607ef62f81000aebdb04efbd1aa403c76d
Parents: 6039059
Author: Haohui Mai <wheat9@apache.org>
Authored: Sun Nov 22 15:18:24 2015 -0800
Committer: Haohui Mai <wheat9@apache.org>
Committed: Sun Nov 22 15:18:24 2015 -0800

----------------------------------------------------------------------
 LICENSE.txt                                     |    6 +-
 hadoop-common-project/hadoop-common/CHANGES.txt |    2 +
 .../hadoop/io/compress/lz4/Lz4Compressor.c      |    4 +-
 .../hadoop/io/compress/lz4/Lz4Decompressor.c    |    2 +-
 .../src/org/apache/hadoop/io/compress/lz4/lz4.c | 1184 +++++++++++-------
 .../src/org/apache/hadoop/io/compress/lz4/lz4.h |  281 +++--
 .../org/apache/hadoop/io/compress/lz4/lz4hc.c   |  906 ++++++--------
 .../org/apache/hadoop/io/compress/lz4/lz4hc.h   |  220 ++--
 .../src/main/native/src/codec/Lz4Codec.cc       |    2 +-
 .../src/main/native/test/TestCompressions.cc    |    2 +-
 10 files changed, 1373 insertions(+), 1236 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hadoop/blob/4c061e60/LICENSE.txt
----------------------------------------------------------------------
diff --git a/LICENSE.txt b/LICENSE.txt
index 46da0f8..de98394 100644
--- a/LICENSE.txt
+++ b/LICENSE.txt
@@ -257,7 +257,8 @@ For src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,lz4hc.h,l
 /*
    LZ4 - Fast LZ compression algorithm
    Header File
-   Copyright (C) 2011-2014, Yann Collet.
+   Copyright (C) 2011-2015, 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
@@ -284,11 +285,10 @@ For src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,lz4hc.h,l
    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
    You can contact the author at :
-   - LZ4 source repository : http://code.google.com/p/lz4/
+   - LZ4 source repository : https://github.com/Cyan4973/lz4
    - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
 */
 
-
 For hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-nativetask/src/main/native/gtest
 ---------------------------------------------------------------------
 Copyright 2008, Google Inc.

http://git-wip-us.apache.org/repos/asf/hadoop/blob/4c061e60/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 3058799..bc6a44d 100644
--- a/hadoop-common-project/hadoop-common/CHANGES.txt
+++ b/hadoop-common-project/hadoop-common/CHANGES.txt
@@ -968,6 +968,8 @@ Release 2.8.0 - UNRELEASED
     HADOOP-12575. Add build instruction for docker toolbox instead of
     boot2docker(Kai Sasaki via ozawa)
 
+    HADOOP-12572. Update Hadoop's lz4 to r131. (Kevin Bowling via wheat9)
+
   OPTIMIZATIONS
 
     HADOOP-11785. Reduce the number of listStatus operation in distcp

http://git-wip-us.apache.org/repos/asf/hadoop/blob/4c061e60/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c
index f742384..26b43d6 100644
--- a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c
+++ b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Compressor.c
@@ -73,7 +73,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
     return (jint)0;
   }
 
-  compressed_direct_buf_len = LZ4_compress(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len);
+  compressed_direct_buf_len = LZ4_compress_default(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len, LZ4_compressBound(uncompressed_direct_buf_len));
   if (compressed_direct_buf_len < 0){
     THROW(env, "java/lang/InternalError", "LZ4_compress failed");
   }
@@ -115,7 +115,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Compressor_comp
     return (jint)0;
   }
 
-  compressed_direct_buf_len = LZ4_compressHC(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len);
+  compressed_direct_buf_len = LZ4_compress_HC(uncompressed_bytes, compressed_bytes, uncompressed_direct_buf_len, LZ4_compressBound(uncompressed_direct_buf_len), 0);
   if (compressed_direct_buf_len < 0){
     THROW(env, "java/lang/InternalError", "LZ4_compressHC failed");
   }

http://git-wip-us.apache.org/repos/asf/hadoop/blob/4c061e60/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Decompressor.c
----------------------------------------------------------------------
diff --git a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Decompressor.c b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Decompressor.c
index cdeaa31..1803543 100644
--- a/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Decompressor.c
+++ b/hadoop-common-project/hadoop-common/src/main/native/src/org/apache/hadoop/io/compress/lz4/Lz4Decompressor.c
@@ -72,7 +72,7 @@ JNIEXPORT jint JNICALL Java_org_apache_hadoop_io_compress_lz4_Lz4Decompressor_de
 
   uncompressed_direct_buf_len = LZ4_decompress_safe(compressed_bytes, uncompressed_bytes, compressed_direct_buf_len, uncompressed_direct_buf_len);
   if (uncompressed_direct_buf_len < 0) {
-    THROW(env, "java/lang/InternalError", "LZ4_uncompress_unknownOutputSize failed.");
+    THROW(env, "java/lang/InternalError", "LZ4_decompress_safe failed.");
   }
 
   (*env)->SetIntField(env, thisj, Lz4Decompressor_compressedDirectBufLen, 0);

http://git-wip-us.apache.org/repos/asf/hadoop/blob/4c061e60/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 39f176f..1b5194c 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 +1,7 @@
 /*
    LZ4 - Fast LZ compression algorithm
-   Copyright (C) 2011-2014, Yann Collet.
+   Copyright (C) 2011-2015, 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
@@ -27,121 +28,68 @@
    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
    You can contact the author at :
-   - LZ4 source repository : http://code.google.com/p/lz4/
+   - LZ4 source repository : https://github.com/Cyan4973/lz4
    - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
 */
 
+
 /**************************************
-   Tuning parameters
+*  Tuning parameters
 **************************************/
 /*
  * 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)).
+ * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
  */
 #define HEAPMODE 0
 
-
-/**************************************
-   CPU Feature Detection
-**************************************/
-/* 32 or 64 bits ? */
-#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \
-  || 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
+ * ACCELERATION_DEFAULT :
+ * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
  */
-#include <stdlib.h>   /* Apparently required to detect endianess */
-#if defined (__GLIBC__)
-#  include <endian.h>
-#  if (__BYTE_ORDER == __BIG_ENDIAN)
-#     define LZ4_BIG_ENDIAN 1
-#  endif
-#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))
-#  define LZ4_BIG_ENDIAN 1
-#elif defined(__sparc) || defined(__sparc__) \
-   || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \
-   || defined(__hpux)  || defined(__hppa) \
-   || defined(_MIPSEB) || defined(__s390__)
-#  define LZ4_BIG_ENDIAN 1
-#else
-/* Little Endian assumed. PDP Endian and other very rare endian format are unsupported. */
-#endif
+#define ACCELERATION_DEFAULT 1
+
 
+/**************************************
+*  CPU Feature Detection
+**************************************/
 /*
- * 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
+ * LZ4_FORCE_SW_BITCOUNT
+ * Define this parameter if your target system or compiler does not support hardware bit count
  */
-#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 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 */
+/**************************************
+*  Includes
+**************************************/
+#include "lz4.h"
 
 
 /**************************************
- Compiler Options
+*  Compiler Options
 **************************************/
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
-/* "restrict" is a known keyword */
-#else
-#  define restrict /* Disable restrict */
-#endif
-
 #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
+#  include <intrin.h>
 #  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
+#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
 #else
-#  ifdef __GNUC__
-#    define FORCE_INLINE static inline __attribute__((always_inline))
+#  if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
+#    if defined(__GNUC__) || defined(__clang__)
+#      define FORCE_INLINE static inline __attribute__((always_inline))
+#    else
+#      define FORCE_INLINE static inline
+#    endif
 #  else
-#    define FORCE_INLINE static inline
-#  endif
-#endif
-
-#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)))
-#endif
-
-#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+#    define FORCE_INLINE static
+#  endif   /* __STDC_VERSION__ */
+#endif  /* _MSC_VER */
 
-#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
+/* LZ4_GCC_VERSION is defined into lz4.h */
+#if (LZ4_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
 #  define expect(expr,value)    (__builtin_expect ((expr),(value)) )
 #else
 #  define expect(expr,value)    (expr)
@@ -152,7 +100,7 @@
 
 
 /**************************************
-   Memory routines
+*  Memory routines
 **************************************/
 #include <stdlib.h>   /* malloc, calloc, free */
 #define ALLOCATOR(n,s) calloc(n,s)
@@ -162,13 +110,7 @@
 
 
 /**************************************
-   Includes
-**************************************/
-#include "lz4.h"
-
-
-/**************************************
-   Basic Types
+*  Basic Types
 **************************************/
 #if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
 # include <stdint.h>
@@ -185,46 +127,95 @@
   typedef unsigned long long  U64;
 #endif
 
-#if defined(__GNUC__)  && !defined(LZ4_FORCE_UNALIGNED_ACCESS)
-#  define _PACKED __attribute__ ((packed))
-#else
-#  define _PACKED
-#endif
 
-#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC)
-#    pragma pack(1)
-#  else
-#    pragma pack(push, 1)
-#  endif
-#endif
+/**************************************
+*  Reading and writing into memory
+**************************************/
+#define STEPSIZE sizeof(size_t)
 
-typedef struct { U16 v; }  _PACKED U16_S;
-typedef struct { U32 v; }  _PACKED U32_S;
-typedef struct { U64 v; }  _PACKED U64_S;
-typedef struct {size_t v;} _PACKED size_t_S;
+static unsigned LZ4_64bits(void) { return sizeof(void*)==8; }
 
-#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  if defined(__SUNPRO_C) || defined(__SUNPRO_CC)
-#    pragma pack(0)
-#  else
-#    pragma pack(pop)
-#  endif
-#endif
+static unsigned LZ4_isLittleEndian(void)
+{
+    const union { U32 i; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental  */
+    return one.c[0];
+}
+
+
+static U16 LZ4_read16(const void* memPtr)
+{
+    U16 val16;
+    memcpy(&val16, memPtr, 2);
+    return val16;
+}
+
+static U16 LZ4_readLE16(const void* memPtr)
+{
+    if (LZ4_isLittleEndian())
+    {
+        return LZ4_read16(memPtr);
+    }
+    else
+    {
+        const BYTE* p = (const BYTE*)memPtr;
+        return (U16)((U16)p[0] + (p[1]<<8));
+    }
+}
+
+static void LZ4_writeLE16(void* memPtr, U16 value)
+{
+    if (LZ4_isLittleEndian())
+    {
+        memcpy(memPtr, &value, 2);
+    }
+    else
+    {
+        BYTE* p = (BYTE*)memPtr;
+        p[0] = (BYTE) value;
+        p[1] = (BYTE)(value>>8);
+    }
+}
+
+static U32 LZ4_read32(const void* memPtr)
+{
+    U32 val32;
+    memcpy(&val32, memPtr, 4);
+    return val32;
+}
+
+static U64 LZ4_read64(const void* memPtr)
+{
+    U64 val64;
+    memcpy(&val64, memPtr, 8);
+    return val64;
+}
 
-#define A16(x)   (((U16_S *)(x))->v)
-#define A32(x)   (((U32_S *)(x))->v)
-#define A64(x)   (((U64_S *)(x))->v)
-#define AARCH(x) (((size_t_S *)(x))->v)
+static size_t LZ4_read_ARCH(const void* p)
+{
+    if (LZ4_64bits())
+        return (size_t)LZ4_read64(p);
+    else
+        return (size_t)LZ4_read32(p);
+}
+
+
+static void LZ4_copy4(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 4); }
+
+static void LZ4_copy8(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 8); }
+
+/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */
+static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+    BYTE* d = (BYTE*)dstPtr;
+    const BYTE* s = (const BYTE*)srcPtr;
+    BYTE* e = (BYTE*)dstEnd;
+    do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
+}
 
 
 /**************************************
-   Constants
+*  Common 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
@@ -232,13 +223,10 @@ typedef struct {size_t v;} _PACKED size_t_S;
 #define MFLIMIT (COPYLENGTH+MINMATCH)
 static const int LZ4_minLength = (MFLIMIT+1);
 
-#define KB *(1U<<10)
-#define MB *(1U<<20)
+#define KB *(1 <<10)
+#define MB *(1 <<20)
 #define GB *(1U<<30)
 
-#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)
 
@@ -249,130 +237,148 @@ static const int LZ4_minLength = (MFLIMIT+1);
 
 
 /**************************************
-   Structures and local types
+*  Common Utils
 **************************************/
-typedef struct {
-    U32  hashTable[HASH_SIZE_U32];
-    U32  currentOffset;
-    U32  initCheck;
-    const BYTE* dictionary;
-    const BYTE* bufferStart;
-    U32  dictSize;
-} LZ4_stream_t_internal;
+#define LZ4_STATIC_ASSERT(c)    { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
 
-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;
+/**************************************
+*  Common functions
+**************************************/
+static unsigned LZ4_NbCommonBytes (register size_t val)
+{
+    if (LZ4_isLittleEndian())
+    {
+        if (LZ4_64bits())
+        {
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanForward64( &r, (U64)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (__builtin_ctzll((U64)val) >> 3);
+#       else
+            static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
+            return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+#       endif
+        }
+        else /* 32 bits */
+        {
+#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r;
+            _BitScanForward( &r, (U32)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (__builtin_ctz((U32)val) >> 3);
+#       else
+            static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
+            return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+#       endif
+        }
+    }
+    else   /* Big Endian CPU */
+    {
+        if (LZ4_64bits())
+        {
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse64( &r, val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (__builtin_clzll((U64)val) >> 3);
+#       else
+            unsigned r;
+            if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
+            if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        }
+        else /* 32 bits */
+        {
+#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse( &r, (unsigned long)val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (__builtin_clz((U32)val) >> 3);
+#       else
+            unsigned r;
+            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        }
+    }
+}
 
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
-typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
+{
+    const BYTE* const pStart = pIn;
+
+    while (likely(pIn<pInLimit-(STEPSIZE-1)))
+    {
+        size_t diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+        if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
+        pIn += LZ4_NbCommonBytes(diff);
+        return (unsigned)(pIn - pStart);
+    }
+
+    if (LZ4_64bits()) if ((pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
+    if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
+    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
+    return (unsigned)(pIn - pStart);
+}
 
 
+#ifndef LZ4_COMMONDEFS_ONLY
 /**************************************
-   Architecture-specific macros
+*  Local Constants
 **************************************/
-#define STEPSIZE                  sizeof(size_t)
-#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 */
-#  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
+#define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
+#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */
+
+static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
+static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */
 
 
 /**************************************
-   Macros
+*  Local Structures and types
 **************************************/
-#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
+typedef struct {
+    U32 hashTable[HASH_SIZE_U32];
+    U32 currentOffset;
+    U32 initCheck;
+    const BYTE* dictionary;
+    BYTE* bufferStart;   /* obsolete, used for slideInputBuffer */
+    U32 dictSize;
+} LZ4_stream_t_internal;
 
+typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
 
-/****************************
-   Private local functions
-****************************/
-#if LZ4_ARCH64
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
 
-static int LZ4_NbCommonBytes (register U64 val)
-{
-# if defined(LZ4_BIG_ENDIAN)
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanReverse64( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_clzll(val) >> 3);
-#   else
-    int r;
-    if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
-    if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
-    r += (!val);
-    return r;
-#   endif
-# else
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanForward64( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_ctzll(val) >> 3);
-#   else
-    static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
-    return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
-#   endif
-# endif
-}
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { full = 0, partial = 1 } earlyEnd_directive;
 
-#else
 
-static int LZ4_NbCommonBytes (register U32 val)
-{
-# if defined(LZ4_BIG_ENDIAN)
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanReverse( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_clz(val) >> 3);
-#   else
-    int r;
-    if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
-    r += (!val);
-    return r;
-#   endif
-# else
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r;
-    _BitScanForward( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_ctz(val) >> 3);
-#   else
-    static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
-    return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
-#   endif
-# endif
-}
+/**************************************
+*  Local Utils
+**************************************/
+int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
+int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
+int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
 
-#endif
 
 
 /********************************
-   Compression functions
+*  Compression functions
 ********************************/
-int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
-int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
 
-static int LZ4_hashSequence(U32 sequence, tableType_t tableType)
+static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType)
 {
     if (tableType == byU16)
         return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
@@ -380,15 +386,30 @@ static int LZ4_hashSequence(U32 sequence, tableType_t tableType)
         return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
 }
 
-static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); }
+static const U64 prime5bytes = 889523592379ULL;
+static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType)
+{
+    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
+    const U32 hashMask = (1<<hashLog) - 1;
+    return ((sequence * prime5bytes) >> (40 - hashLog)) & hashMask;
+}
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType)
+{
+    if (LZ4_64bits())
+        return LZ4_hashSequence64(sequence, tableType);
+    return LZ4_hashSequence((U32)sequence, tableType);
+}
+
+static U32 LZ4_hashPosition(const void* p, tableType_t tableType) { return LZ4_hashSequenceT(LZ4_read_ARCH(p), tableType); }
+
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const 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; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
     }
 }
 
@@ -411,36 +432,17 @@ static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t t
     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;
-
-    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++;
-
-    return (unsigned)(pIn - pStart);
-}
-
-
-static int LZ4_compress_generic(
-                 void* ctx,
-                 const char* source,
-                 char* dest,
-                 int inputSize,
-                 int maxOutputSize,
-
-                 limitedOutput_directive outputLimited,
-                 tableType_t tableType,
-                 dict_directive dict,
-                 dictIssue_directive dictIssue)
+FORCE_INLINE int LZ4_compress_generic(
+                 void* const ctx,
+                 const char* const source,
+                 char* const dest,
+                 const int inputSize,
+                 const int maxOutputSize,
+                 const limitedOutput_directive outputLimited,
+                 const tableType_t tableType,
+                 const dict_directive dict,
+                 const dictIssue_directive dictIssue,
+                 const U32 acceleration)
 {
     LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx;
 
@@ -459,12 +461,11 @@ static int LZ4_compress_generic(
     BYTE* op = (BYTE*) dest;
     BYTE* const olimit = op + maxOutputSize;
 
-    const int skipStrength = SKIPSTRENGTH;
     U32 forwardH;
     size_t refDelta=0;
 
     /* Init conditions */
-    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;          /* Unsupported input size, too large (or negative) */
+    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported input size, too large (or negative) */
     switch(dict)
     {
     case noDict:
@@ -481,8 +482,8 @@ static int LZ4_compress_generic(
         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) */
+    if ((tableType == byU16) && (inputSize>=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);
@@ -491,26 +492,26 @@ static int LZ4_compress_generic(
     /* Main Loop */
     for ( ; ; )
     {
-        const BYTE* ref;
+        const BYTE* match;
         BYTE* token;
         {
             const BYTE* forwardIp = ip;
-            unsigned step=1;
-            unsigned searchMatchNb = (1U << skipStrength);
+            unsigned step = 1;
+            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
 
             /* Find a match */
             do {
                 U32 h = forwardH;
                 ip = forwardIp;
                 forwardIp += step;
-                step = searchMatchNb++ >> skipStrength;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
 
                 if (unlikely(forwardIp > mflimit)) goto _last_literals;
 
-                ref = LZ4_getPositionOnHash(h, ctx, tableType, base);
+                match = LZ4_getPositionOnHash(h, ctx, tableType, base);
                 if (dict==usingExtDict)
                 {
-                    if (ref<(const BYTE*)source)
+                    if (match<(const BYTE*)source)
                     {
                         refDelta = dictDelta;
                         lowLimit = dictionary;
@@ -524,13 +525,13 @@ static int LZ4_compress_generic(
                 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)) );
+            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
+                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
         }
 
         /* Catch up */
-        while ((ip>anchor) && (ref+refDelta > lowLimit) && (unlikely(ip[-1]==ref[refDelta-1]))) { ip--; ref--; }
+        while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
 
         {
             /* Encode Literal length */
@@ -548,12 +549,13 @@ static int LZ4_compress_generic(
             else *token = (BYTE)(litLength<<ML_BITS);
 
             /* Copy Literals */
-            { BYTE* end = op+litLength; LZ4_WILDCOPY(op,anchor,end); op=end; }
+            LZ4_wildCopy(op, anchor, op+litLength);
+            op+=litLength;
         }
 
 _next_match:
         /* Encode Offset */
-        LZ4_WRITE_LITTLEENDIAN_16(op, (U16)(ip-ref));
+        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
 
         /* Encode MatchLength */
         {
@@ -562,10 +564,10 @@ _next_match:
             if ((dict==usingExtDict) && (lowLimit==dictionary))
             {
                 const BYTE* limit;
-                ref += refDelta;
-                limit = ip + (dictEnd-ref);
+                match += refDelta;
+                limit = ip + (dictEnd-match);
                 if (limit > matchlimit) limit = matchlimit;
-                matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit);
+                matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
                 ip += MINMATCH + matchLength;
                 if (ip==limit)
                 {
@@ -576,14 +578,14 @@ _next_match:
             }
             else
             {
-                matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit);
+                matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
                 ip += MINMATCH + matchLength;
             }
 
+            if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit)))
+                return 0;    /* Check output limit */
             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; }
@@ -602,10 +604,10 @@ _next_match:
         LZ4_putPosition(ip-2, ctx, tableType, base);
 
         /* Test next position */
-        ref = LZ4_getPosition(ip, ctx, tableType, base);
+        match = LZ4_getPosition(ip, ctx, tableType, base);
         if (dict==usingExtDict)
         {
-            if (ref<(const BYTE*)source)
+            if (match<(const BYTE*)source)
             {
                 refDelta = dictDelta;
                 lowLimit = dictionary;
@@ -617,9 +619,9 @@ _next_match:
             }
         }
         LZ4_putPosition(ip, ctx, tableType, base);
-        if ( ((dictIssue==dictSmall) ? (ref>=lowRefLimit) : 1)
-            && (ref+MAX_DISTANCE>=ip)
-            && (A32(ref+refDelta)==A32(ip)) )
+        if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
+            && (match+MAX_DISTANCE>=ip)
+            && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
         { token=op++; *token=0; goto _next_match; }
 
         /* Prepare next loop */
@@ -629,13 +631,22 @@ _next_match:
 _last_literals:
     /* Encode Last Literals */
     {
-        int lastRun = (int)(iend - anchor);
-        if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize))
+        const size_t lastRun = (size_t)(iend - anchor);
+        if ((outputLimited) && ((op - (BYTE*)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;
+        if (lastRun >= RUN_MASK)
+        {
+            size_t accumulator = lastRun - RUN_MASK;
+            *op++ = RUN_MASK << ML_BITS;
+            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        }
+        else
+        {
+            *op++ = (BYTE)(lastRun<<ML_BITS);
+        }
+        memcpy(op, anchor, lastRun);
+        op += lastRun;
     }
 
     /* End */
@@ -643,39 +654,271 @@ _last_literals:
 }
 
 
-int LZ4_compress(const char* source, char* dest, int inputSize)
+int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    LZ4_resetStream((LZ4_stream_t*)state);
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+
+    if (maxOutputSize >= LZ4_compressBound(inputSize))
+    {
+        if (inputSize < LZ4_64Klimit)
+            return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16,                        noDict, noDictIssue, acceleration);
+        else
+            return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+    }
+    else
+    {
+        if (inputSize < LZ4_64Klimit)
+            return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
+        else
+            return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+    }
+}
+
+
+int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
 #if (HEAPMODE)
-    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4);   /* Aligned on 4-bytes boundaries */
+    void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
 #else
-    U32 ctx[LZ4_STREAMSIZE_U32] = {0};      /* Ensure data is aligned on 4-bytes boundaries */
+    LZ4_stream_t ctx;
+    void* ctxPtr = &ctx;
 #endif
-    int result;
 
-    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);
+    int result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
 
 #if (HEAPMODE)
-    FREEMEM(ctx);
+    FREEMEM(ctxPtr);
 #endif
     return result;
 }
 
-int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+
+int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+    return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
+}
+
+
+/* hidden debug function */
+/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
+int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    LZ4_stream_t ctx;
+
+    LZ4_resetStream(&ctx);
+
+    if (inputSize < LZ4_64Klimit)
+        return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
+    else
+        return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+}
+
+
+/********************************
+*  destSize variant
+********************************/
+
+static int LZ4_compress_destSize_generic(
+                       void* const ctx,
+                 const char* const src,
+                       char* const dst,
+                       int*  const srcSizePtr,
+                 const int targetDstSize,
+                 const tableType_t tableType)
+{
+    const BYTE* ip = (const BYTE*) src;
+    const BYTE* base = (const BYTE*) src;
+    const BYTE* lowLimit = (const BYTE*) src;
+    const BYTE* anchor = ip;
+    const BYTE* const iend = ip + *srcSizePtr;
+    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const matchlimit = iend - LASTLITERALS;
+
+    BYTE* op = (BYTE*) dst;
+    BYTE* const oend = op + targetDstSize;
+    BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
+    BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
+    BYTE* const oMaxSeq = oMaxLit - 1 /* token */;
+
+    U32 forwardH;
+
+
+    /* Init conditions */
+    if (targetDstSize < 1) return 0;                                     /* Impossible to store anything */
+    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;            /* Unsupported input size, too large (or negative) */
+    if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
+    if (*srcSizePtr<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
+
+    /* First Byte */
+    *srcSizePtr = 0;
+    LZ4_putPosition(ip, ctx, tableType, base);
+    ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+    /* Main Loop */
+    for ( ; ; )
+    {
+        const BYTE* match;
+        BYTE* token;
+        {
+            const BYTE* forwardIp = ip;
+            unsigned step = 1;
+            unsigned searchMatchNb = 1 << LZ4_skipTrigger;
+
+            /* Find a match */
+            do {
+                U32 h = forwardH;
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimit))
+                    goto _last_literals;
+
+                match = LZ4_getPositionOnHash(h, ctx, tableType, base);
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putPositionOnHash(ip, h, ctx, tableType, base);
+
+            } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+                || (LZ4_read32(match) != LZ4_read32(ip)) );
+        }
+
+        /* Catch up */
+        while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
+
+        {
+            /* Encode Literal length */
+            unsigned litLength = (unsigned)(ip - anchor);
+            token = op++;
+            if (op + ((litLength+240)/255) + litLength > oMaxLit)
+            {
+                /* Not enough space for a last match */
+                op--;
+                goto _last_literals;
+            }
+            if (litLength>=RUN_MASK)
+            {
+                unsigned len = litLength - RUN_MASK;
+                *token=(RUN_MASK<<ML_BITS);
+                for(; len >= 255 ; len-=255) *op++ = 255;
+                *op++ = (BYTE)len;
+            }
+            else *token = (BYTE)(litLength<<ML_BITS);
+
+            /* Copy Literals */
+            LZ4_wildCopy(op, anchor, op+litLength);
+            op += litLength;
+        }
+
+_next_match:
+        /* Encode Offset */
+        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+
+        /* Encode MatchLength */
+        {
+            size_t matchLength;
+
+            matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+
+            if (op + ((matchLength+240)/255) > oMaxMatch)
+            {
+                /* Match description too long : reduce it */
+                matchLength = (15-1) + (oMaxMatch-op) * 255;
+            }
+            //printf("offset %5i, matchLength%5i \n", (int)(ip-match), matchLength + MINMATCH);
+            ip += MINMATCH + matchLength;
+
+            if (matchLength>=ML_MASK)
+            {
+                *token += ML_MASK;
+                matchLength -= ML_MASK;
+                while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
+                *op++ = (BYTE)matchLength;
+            }
+            else *token += (BYTE)(matchLength);
+        }
+
+        anchor = ip;
+
+        /* Test end of block */
+        if (ip > mflimit) break;
+        if (op > oMaxSeq) break;
+
+        /* Fill table */
+        LZ4_putPosition(ip-2, ctx, tableType, base);
+
+        /* Test next position */
+        match = LZ4_getPosition(ip, ctx, tableType, base);
+        LZ4_putPosition(ip, ctx, tableType, base);
+        if ( (match+MAX_DISTANCE>=ip)
+            && (LZ4_read32(match)==LZ4_read32(ip)) )
+        { token=op++; *token=0; goto _next_match; }
+
+        /* Prepare next loop */
+        forwardH = LZ4_hashPosition(++ip, tableType);
+    }
+
+_last_literals:
+    /* Encode Last Literals */
+    {
+        size_t lastRunSize = (size_t)(iend - anchor);
+        if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend)
+        {
+            /* adapt lastRunSize to fill 'dst' */
+            lastRunSize  = (oend-op) - 1;
+            lastRunSize -= (lastRunSize+240)/255;
+        }
+        ip = anchor + lastRunSize;
+
+        if (lastRunSize >= RUN_MASK)
+        {
+            size_t accumulator = lastRunSize - RUN_MASK;
+            *op++ = RUN_MASK << ML_BITS;
+            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        }
+        else
+        {
+            *op++ = (BYTE)(lastRunSize<<ML_BITS);
+        }
+        memcpy(op, anchor, lastRunSize);
+        op += lastRunSize;
+    }
+
+    /* End */
+    *srcSizePtr = (int) (((const char*)ip)-src);
+    return (int) (((char*)op)-dst);
+}
+
+
+static int LZ4_compress_destSize_extState (void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+{
+    LZ4_resetStream((LZ4_stream_t*)state);
+
+    if (targetDstSize >= LZ4_compressBound(*srcSizePtr))   /* compression success is guaranteed */
+    {
+        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
+    }
+    else
+    {
+        if (*srcSizePtr < LZ4_64Klimit)
+            return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, byU16);
+        else
+            return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr);
+    }
+}
+
+
+int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
 {
 #if (HEAPMODE)
-    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4);   /* Aligned on 4-bytes boundaries */
+    void* ctx = ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
 #else
-    U32 ctx[LZ4_STREAMSIZE_U32] = {0};      /* Ensure data is aligned on 4-bytes boundaries */
+    LZ4_stream_t ctxBody;
+    void* ctx = &ctxBody;
 #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);
+    int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);
 
 #if (HEAPMODE)
     FREEMEM(ctx);
@@ -684,27 +927,24 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in
 }
 
 
-/*****************************************
-   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));
-}
+/********************************
+*  Streaming functions
+********************************/
 
 LZ4_stream_t* LZ4_createStream(void)
 {
-    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(4, LZ4_STREAMSIZE_U32);
+    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
     LZ4_resetStream(lz4s);
     return lz4s;
 }
 
+void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
+{
+    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
 int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 {
     FREEMEM(LZ4_stream);
@@ -712,6 +952,7 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 }
 
 
+#define HASH_UNIT sizeof(size_t)
 int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
 {
     LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
@@ -719,29 +960,30 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
     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 ((dict->initCheck) || (dict->currentOffset > 1 GB))  /* Uninitialized structure, or reuse overflow */
+        LZ4_resetStream(LZ4_dict);
 
-    if (dictSize < MINMATCH)
+    if (dictSize < (int)HASH_UNIT)
     {
         dict->dictionary = NULL;
         dict->dictSize = 0;
-        return 1;
+        return 0;
     }
 
-    if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB;
+    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
+    dict->currentOffset += 64 KB;
     base = p - dict->currentOffset;
     dict->dictionary = p;
     dict->dictSize = (U32)(dictEnd - p);
     dict->currentOffset += dict->dictSize;
 
-    while (p <= dictEnd-MINMATCH)
+    while (p <= dictEnd-HASH_UNIT)
     {
-        LZ4_putPosition(p, dict, byU32, base);
+        LZ4_putPosition(p, dict->hashTable, byU32, base);
         p+=3;
     }
 
-    return 1;
+    return dict->dictSize;
 }
 
 
@@ -766,8 +1008,7 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
 }
 
 
-FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* source, char* dest, int inputSize,
-                                                int maxOutputSize, limitedOutput_directive limit)
+int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
     LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream;
     const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
@@ -776,6 +1017,7 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
     if (streamPtr->initCheck) return 0;   /* Uninitialized structure detected */
     if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
     LZ4_renormDictT(streamPtr, smallest);
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
     /* Check overlapping input/dictionary space */
     {
@@ -794,9 +1036,9 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
     {
         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);
+            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, noDictIssue);
+            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
         streamPtr->dictSize += (U32)inputSize;
         streamPtr->currentOffset += (U32)inputSize;
         return result;
@@ -806,9 +1048,9 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
     {
         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);
+            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, noDictIssue);
+            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
         streamPtr->dictionary = (const BYTE*)source;
         streamPtr->dictSize = (U32)inputSize;
         streamPtr->currentOffset += (U32)inputSize;
@@ -816,18 +1058,8 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
     }
 }
 
-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 */
+/* Hidden debug function, to force external 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;
@@ -838,7 +1070,7 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char*
     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);
+    result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
 
     streamPtr->dictionary = (const BYTE*)source;
     streamPtr->dictSize = (U32)inputSize;
@@ -866,9 +1098,9 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
 
 
 
-/****************************
-   Decompression functions
-****************************/
+/*******************************
+*  Decompression functions
+*******************************/
 /*
  * This generic decompression function cover all use cases.
  * It shall be instantiated several times, using different sets of directives
@@ -876,8 +1108,8 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
  * in order to remove useless branches during compilation optimization.
  */
 FORCE_INLINE int LZ4_decompress_generic(
-                 const char* source,
-                 char* dest,
+                 const char* const source,
+                 char* const dest,
                  int inputSize,
                  int outputSize,         /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
 
@@ -885,20 +1117,20 @@ FORCE_INLINE int LZ4_decompress_generic(
                  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 */
+                 const BYTE* const lowPrefix,  /* == dest if dict == noDict */
+                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
+                 const size_t dictSize         /* note : = 0 if noDict */
                  )
 {
     /* Local Variables */
-    const BYTE* restrict ip = (const BYTE*) source;
-    const BYTE* ref;
+    const BYTE* ip = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
 
     BYTE* op = (BYTE*) dest;
     BYTE* const oend = op + outputSize;
     BYTE* cpy;
     BYTE* oexit = op + targetOutputSize;
-    const BYTE* const lowLimit = (const BYTE*)dest - dictSize;
+    const BYTE* const lowLimit = lowPrefix - dictSize;
 
     const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
     const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4};
@@ -919,8 +1151,9 @@ FORCE_INLINE int LZ4_decompress_generic(
     {
         unsigned token;
         size_t length;
+        const BYTE* match;
 
-        /* get runlength */
+        /* get literal length */
         token = *ip++;
         if ((length=(token>>ML_BITS)) == RUN_MASK)
         {
@@ -931,8 +1164,8 @@ FORCE_INLINE int LZ4_decompress_generic(
                 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 */
+            if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error;   /* overflow detection */
+            if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error;   /* overflow detection */
         }
 
         /* copy literals */
@@ -955,14 +1188,16 @@ FORCE_INLINE int LZ4_decompress_generic(
             op += length;
             break;     /* Necessarily EOF, due to parsing restrictions */
         }
-        LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy;
+        LZ4_wildCopy(op, ip, cpy);
+        ip += length; op = cpy;
 
         /* get offset */
-        LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;
-        if ((checkOffset) && (unlikely(ref < lowLimit))) goto _output_error;   /* Error : offset outside destination buffer */
+        match = cpy - LZ4_readLE16(ip); ip+=2;
+        if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside destination buffer */
 
         /* get matchlength */
-        if ((length=(token&ML_MASK)) == ML_MASK)
+        length = token & ML_MASK;
+        if (length == ML_MASK)
         {
             unsigned s;
             do
@@ -971,36 +1206,37 @@ FORCE_INLINE int LZ4_decompress_generic(
                 s = *ip++;
                 length += s;
             } while (s==255);
-            if ((safeDecode) && LZ4_32BITS && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error;   /* overflow detection */
+            if ((safeDecode) && 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 ((dict==usingExtDict) && (match < lowPrefix))
         {
-            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;
+            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */
 
-            if (length <= (size_t)(dest-(char*)ref))
+            if (length <= (size_t)(lowPrefix-match))
             {
-                ref = dictEnd - (dest-(char*)ref);
-                memcpy(op, ref, length);
-                op += length;
+                /* match can be copied as a single segment from external dictionary */
+                match = dictEnd - (lowPrefix-match);
+                memmove(op, match, length); op += length;
             }
             else
             {
-                size_t copySize = (size_t)(dest-(char*)ref);
+                /* match encompass external dictionary and current segment */
+                size_t copySize = (size_t)(lowPrefix-match);
                 memcpy(op, dictEnd - copySize, copySize);
                 op += copySize;
                 copySize = length - copySize;
-                if (copySize > (size_t)((char*)op-dest))   /* overlap */
+                if (copySize > (size_t)(op-lowPrefix))   /* overlap within current segment */
                 {
                     BYTE* const endOfMatch = op + copySize;
-                    const BYTE* copyFrom = (BYTE*)dest;
+                    const BYTE* copyFrom = lowPrefix;
                     while (op < endOfMatch) *op++ = *copyFrom++;
                 }
                 else
                 {
-                    memcpy(op, dest, copySize);
+                    memcpy(op, lowPrefix, copySize);
                     op += copySize;
                 }
             }
@@ -1009,25 +1245,31 @@ FORCE_INLINE int LZ4_decompress_generic(
 
         /* copy repeated sequence */
         cpy = op + length;
-        if (unlikely((op-ref)<(int)STEPSIZE))
+        if (unlikely((op-match)<8))
         {
-            const size_t dec64 = dec64table[op-ref];
-            op[0] = ref[0];
-            op[1] = ref[1];
-            op[2] = ref[2];
-            op[3] = ref[3];
-            ref += dec32table[op-ref];
-            A32(op+4) = A32(ref);
-            op += 8; ref -= dec64;
-        } else { LZ4_COPY8(op,ref); }
+            const size_t dec64 = dec64table[op-match];
+            op[0] = match[0];
+            op[1] = match[1];
+            op[2] = match[2];
+            op[3] = match[3];
+            match += dec32table[op-match];
+            LZ4_copy4(op+4, match);
+            op += 8; match -= dec64;
+        } else { LZ4_copy8(op, match); op+=8; match+=8; }
 
         if (unlikely(cpy>oend-12))
         {
-            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++;
+            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals */
+            if (op < oend-8)
+            {
+                LZ4_wildCopy(op, match, oend-8);
+                match += (oend-8) - op;
+                op = oend-8;
+            }
+            while (op<cpy) *op++ = *match++;
         }
-        else LZ4_WILDCOPY(op, ref, cpy);
+        else
+            LZ4_wildCopy(op, match, cpy);
         op=cpy;   /* correction */
     }
 
@@ -1035,35 +1277,38 @@ FORCE_INLINE int LZ4_decompress_generic(
     if (endOnInput)
        return (int) (((char*)op)-dest);     /* Nb of output bytes decoded */
     else
-       return (int) (((char*)ip)-source);   /* Nb of input bytes read */
+       return (int) (((const char*)ip)-source);   /* Nb of input bytes read */
 
     /* Overflow error detected */
 _output_error:
-    return (int) (-(((char*)ip)-source))-1;
+    return (int) (-(((const char*)ip)-source))-1;
 }
 
 
 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);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, 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);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, 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);
+    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
 }
 
+
 /* streaming decompression functions */
 
 typedef struct
 {
-    const char* dictionary;
-    int dictSize;
+    const BYTE* externalDict;
+    size_t extDictSize;
+    const BYTE* prefixEnd;
+    size_t prefixSize;
 } LZ4_streamDecode_t_internal;
 
 /*
@@ -1073,8 +1318,7 @@ typedef struct
  */
 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);
+    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
     return lz4s;
 }
 
@@ -1094,8 +1338,10 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
 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;
+    lz4sd->prefixSize = (size_t) dictSize;
+    lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+    lz4sd->externalDict = NULL;
+    lz4sd->extDictSize  = 0;
     return 1;
 }
 
@@ -1104,23 +1350,32 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti
     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()
+    and indicate where it stands using LZ4_setStreamDecode()
 */
 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)
+    if (lz4sd->prefixEnd == (BYTE*)dest)
     {
-        lz4sd->dictSize += result;
+        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                        endOnInputSize, full, 0,
+                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize += result;
+        lz4sd->prefixEnd  += result;
     }
     else
     {
-        lz4sd->dictionary = dest;
-        lz4sd->dictSize = result;
+        lz4sd->extDictSize = lz4sd->prefixSize;
+        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                        endOnInputSize, full, 0,
+                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = result;
+        lz4sd->prefixEnd  = (BYTE*)dest + result;
     }
 
     return result;
@@ -1131,16 +1386,25 @@ int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch
     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)
+    if (lz4sd->prefixEnd == (BYTE*)dest)
     {
-        lz4sd->dictSize += result;
+        result = LZ4_decompress_generic(source, dest, 0, originalSize,
+                                        endOnOutputSize, full, 0,
+                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize += originalSize;
+        lz4sd->prefixEnd  += originalSize;
     }
     else
     {
-        lz4sd->dictionary = dest;
-        lz4sd->dictSize = result;
+        lz4sd->extDictSize = lz4sd->prefixSize;
+        lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize;
+        result = LZ4_decompress_generic(source, dest, 0, originalSize,
+                                        endOnOutputSize, full, 0,
+                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = originalSize;
+        lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
     }
 
     return result;
@@ -1157,34 +1421,44 @@ Advanced decoding functions :
 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);
+        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
+    if (dictStart+dictSize == dest)
+    {
+        if (dictSize >= (int)(64 KB - 1))
+            return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
+        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
+    }
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)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, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize);
     return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
 }
 
 int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
 {
-    //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);
 }
 
 /* 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);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
 }
 
 
 /***************************************************
-    Obsolete Functions
+*  Obsolete Functions
 ***************************************************/
+/* obsolete compression functions */
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
+int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
+int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
+int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }
+
 /*
 These function names are deprecated and should no longer be used.
 They are only provided here for compatibility with older user programs.
@@ -1199,69 +1473,43 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize,
 
 int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
 
-static void LZ4_init(LZ4_stream_t_internal* lz4ds, const BYTE* base)
+static void LZ4_init(LZ4_stream_t_internal* lz4ds, BYTE* base)
 {
     MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE);
     lz4ds->bufferStart = base;
 }
 
-int LZ4_resetStreamState(void* state, const char* inputBuffer)
+int LZ4_resetStreamState(void* state, char* inputBuffer)
 {
     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);
+    LZ4_init((LZ4_stream_t_internal*)state, (BYTE*)inputBuffer);
     return 0;
 }
 
-void* LZ4_create (const char* inputBuffer)
+void* LZ4_create (char* inputBuffer)
 {
-    void* lz4ds = ALLOCATOR(4, LZ4_STREAMSIZE_U32);
-    LZ4_init ((LZ4_stream_t_internal*)lz4ds, (const BYTE*)inputBuffer);
+    void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+    LZ4_init ((LZ4_stream_t_internal*)lz4ds, (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);
+    LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data;
+    int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB);
+    return (char*)(ctx->bufferStart + dictSize);
 }
 
 /* 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);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, 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);
+    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
 }
+
+#endif   /* LZ4_COMMONDEFS_ONLY */


Mime
View raw message