Merge pull request #505 from lz4/dev

update to `dev`

7 files changed, 453 insertions, 228 deletions

diff --git a/lib/Makefile b/lib/Makefile
index dd33f50..7b31239 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -116,6 +116,10 @@ clean:
 #-----------------------------------------------------------------------------
 ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS))
 
+.PHONY: listL120
+listL120:  # extract lines >= 120 characters in *.{c,h}, by Takayuki Matsuoka (note : $$, for Makefile compatibility)
+	find . -type f -name '*.c' -o -name '*.h' | while read -r filename; do awk 'length > 120 {print FILENAME "(" FNR "): " $$0}' $$filename; done
+
 DESTDIR     ?=
 # directory variables : GNU conventions prefer lowercase
 # see https://www.gnu.org/prep/standards/html_node/Makefile-Conventions.html
diff --git a/lib/lz4.c b/lib/lz4.c
index 0fdbe5e..bb6b619 100644
--- a/lib/lz4.c
+++ b/lib/lz4.c
@@ -69,7 +69,9 @@
  * Prefer these methods in priority order (0 > 1 > 2)
  */
 #ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */
-#  if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
+#  if defined(__GNUC__) && \
+  ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \
+  || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
 #    define LZ4_FORCE_MEMORY_ACCESS 2
 #  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
 #    define LZ4_FORCE_MEMORY_ACCESS 1
@@ -80,7 +82,7 @@
  * LZ4_FORCE_SW_BITCOUNT
  * 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 */
+#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for WinCE doesn't support Hardware bit count */
 #  define LZ4_FORCE_SW_BITCOUNT
 #endif
 
@@ -89,6 +91,7 @@
 /*-************************************
 *  Dependency
 **************************************/
+#define LZ4_STATIC_LINKING_ONLY
 #include "lz4.h"
 /* see also "memory routines" below */
 
@@ -146,8 +149,12 @@
 #  define expect(expr,value)    (expr)
 #endif
 
+#ifndef likely
 #define likely(expr)     expect((expr) != 0, 1)
+#endif
+#ifndef unlikely
 #define unlikely(expr)   expect((expr) != 0, 0)
+#endif
 
 
 /*-************************************
@@ -317,7 +324,7 @@ static const int LZ4_minLength = (MFLIMIT+1);
 #  endif
 #endif
 
-#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
+#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */
 
 #if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
 #  include <stdio.h>
@@ -516,7 +523,21 @@ LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tab
     return LZ4_hash4(LZ4_read32(p), tableType);
 }
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
+static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: /* fallthrough */
+    case byPtr: { /* illegal! */ assert(0); return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
+    }
+}
+
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+                                  void* tableBase, tableType_t const tableType,
+                            const BYTE* srcBase)
 {
     switch (tableType)
     {
@@ -533,6 +554,28 @@ LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_
     LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
 }
 
+/* LZ4_getIndexOnHash() :
+ * Index of match position registered in hash table.
+ * hash position must be calculated by using base+index, or dictBase+index.
+ * Assumption 1 : only valid if tableType == byU32 or byU16.
+ * Assumption 2 : h is presumed valid (within limits of hash table)
+ */
+static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
+{
+    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
+    if (tableType == byU32) {
+        const U32* const hashTable = (const U32*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
+        return hashTable[h];
+    }
+    if (tableType == byU16) {
+        const U16* const hashTable = (const U16*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
+        return hashTable[h];
+    }
+    assert(0); return 0;  /* forbidden case */
+}
+
 static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
     if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
@@ -540,18 +583,18 @@ static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType
     { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
 }
 
-LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
+LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p,
+                                             const void* tableBase, tableType_t tableType,
+                                             const BYTE* srcBase)
 {
     U32 const h = LZ4_hashPosition(p, tableType);
     return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
 }
 
-
 LZ4_FORCE_INLINE void LZ4_prepareTable(
         LZ4_stream_t_internal* const cctx,
         const int inputSize,
-        const tableType_t tableType,
-        const dict_directive dictDirective) {
+        const tableType_t tableType) {
     /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
      * therefore safe to use no matter what mode we're in. Otherwise, we figure
      * out if it's safe to leave as is or whether it needs to be reset.
@@ -563,23 +606,28 @@ LZ4_FORCE_INLINE void LZ4_prepareTable(
           || tableType == byPtr
           || inputSize >= 4 KB)
         {
-            DEBUGLOG(4, "Resetting table in %p", cctx);
+            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
             MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
             cctx->currentOffset = 0;
             cctx->tableType = clearedTable;
+        } else {
+            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
         }
     }
-    /* If the current offset is zero, we will never look in the external
-     * dictionary context, since there is no value a table entry can take that
-     * indicates a miss. In that case, we need to bump the offset to something
-     * non-zero.
+
+    /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster
+     * than compressing without a gap. However, compressing with
+     * currentOffset == 0 is faster still, so we preserve that case.
      */
-    if (dictDirective == usingDictCtx &&
-        tableType != byPtr &&
-        cctx->currentOffset == 0)
-    {
-        cctx->currentOffset = 1;
+    if (cctx->currentOffset != 0 && tableType == byU32) {
+        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
+        cctx->currentOffset += 64 KB;
     }
+
+    /* Finally, clear history */
+    cctx->dictCtx = NULL;
+    cctx->dictionary = NULL;
+    cctx->dictSize = 0;
 }
 
 /** LZ4_compress_generic() :
@@ -598,8 +646,8 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
 {
     const BYTE* ip = (const BYTE*) source;
 
-    size_t currentOffset = cctx->currentOffset;
-    const BYTE* base = (const BYTE*) source - currentOffset;
+    U32 const startIndex = cctx->currentOffset;
+    const BYTE* base = (const BYTE*) source - startIndex;
     const BYTE* lowLimit;
 
     const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
@@ -607,8 +655,10 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
         dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
     const U32 dictSize =
         dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
+    const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */
 
-    const BYTE* const lowRefLimit = (const BYTE*) source - dictSize;
+    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
+    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */
     const BYTE* const dictEnd = dictionary + dictSize;
     const BYTE* anchor = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
@@ -618,26 +668,38 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
     /* the dictCtx currentOffset is indexed on the start of the dictionary,
      * while a dictionary in the current context precedes the currentOffset */
     const BYTE* dictBase = dictDirective == usingDictCtx ?
-        (const BYTE*) source - dictCtx->currentOffset :
-        (const BYTE*) source - dictSize - currentOffset;
-    const ptrdiff_t dictDelta = dictionary ? dictEnd - (const BYTE*) source : 0;
-    const BYTE* dictLowLimit;
+        dictionary + dictSize - dictCtx->currentOffset :
+        dictionary + dictSize - startIndex;
 
     BYTE* op = (BYTE*) dest;
     BYTE* const olimit = op + maxOutputSize;
 
-    ptrdiff_t retval = 0;
-
+    U32 offset = 0;
     U32 forwardH;
 
+    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType);
     /* Init conditions */
     if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported inputSize, too large (or negative) */
+    if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */
+    assert(acceleration >= 1);
 
     lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
-    dictLowLimit = dictionary ? dictionary : lowLimit;
 
-    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) */
+    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;  /* Size too large (not within 64K limit) */
+
+    /* Update context state */
+    if (dictDirective == usingDictCtx) {
+        /* Subsequent linked blocks can't use the dictionary. */
+        /* Instead, they use the block we just compressed. */
+        cctx->dictCtx = NULL;
+        cctx->dictSize = (U32)inputSize;
+    } else {
+        cctx->dictSize += (U32)inputSize;
+    }
+    cctx->currentOffset += (U32)inputSize;
+    cctx->tableType = tableType;
+
+    if (inputSize<LZ4_minLength) goto _last_literals;        /* Input too small, no compression (all literals) */
 
     /* First Byte */
     LZ4_putPosition(ip, cctx->hashTable, tableType, base);
@@ -645,12 +707,12 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
 
     /* Main Loop */
     for ( ; ; ) {
-        ptrdiff_t refDelta = 0;
         const BYTE* match;
         BYTE* token;
 
         /* Find a match */
-        {   const BYTE* forwardIp = ip;
+        if (tableType == byPtr) {
+            const BYTE* forwardIp = ip;
             unsigned step = 1;
             unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
             do {
@@ -663,41 +725,78 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
                 assert(ip < mflimitPlusOne);
 
                 match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+
+            } while ( (match+MAX_DISTANCE < ip)
+                   || (LZ4_read32(match) != LZ4_read32(ip)) );
+
+        } else {   /* byU32, byU16 */
+
+            const BYTE* forwardIp = ip;
+            unsigned step = 1;
+            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+            do {
+                U32 const h = forwardH;
+                U32 const current = (U32)(forwardIp - base);
+                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+                assert(matchIndex <= current);
+                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
+
                 if (dictDirective == usingDictCtx) {
-                    if (match < (const BYTE*)source) {
+                    if (matchIndex < startIndex) {
                         /* there was no match, try the dictionary */
-                        match = LZ4_getPosition(ip, dictCtx->hashTable, byU32, dictBase);
-                        refDelta = dictDelta;
-                        lowLimit = dictLowLimit;
+                        assert(tableType == byU32);
+                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                        match = dictBase + matchIndex;
+                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */
+                        lowLimit = dictionary;
                     } else {
-                        refDelta = 0;
+                        match = base + matchIndex;
                         lowLimit = (const BYTE*)source;
                     }
                 } else if (dictDirective==usingExtDict) {
-                    if (match < (const BYTE*)source) {
-                        refDelta = dictDelta;
-                        lowLimit = dictLowLimit;
+                    if (matchIndex < startIndex) {
+                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);
+                        match = dictBase + matchIndex;
+                        lowLimit = dictionary;
                     } else {
-                        refDelta = 0;
+                        match = base + matchIndex;
                         lowLimit = (const BYTE*)source;
-                }   }
+                    }
+                } else {   /* single continuous memory segment */
+                    match = base + matchIndex;
+                }
                 forwardH = LZ4_hashPosition(forwardIp, tableType);
-                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+
+                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue;     /* match outside of valid area */
+                if ((tableType != byU16) && (current - matchIndex > MAX_DISTANCE)) continue; /* too far - note: works even if matchIndex overflows */
+                if (tableType == byU16) assert((current - matchIndex) <= MAX_DISTANCE);      /* too_far presumed impossible with byU16 */
+
+                if (LZ4_read32(match) == LZ4_read32(ip)) {
+                    if (maybe_extMem) offset = current - matchIndex;
+                    break;   /* match found */
+                }
 
-            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
-                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
-                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+            } while(1);
         }
 
         /* Catch up */
-        while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+        while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
 
         /* Encode Literals */
         {   unsigned const litLength = (unsigned)(ip - anchor);
             token = op++;
             if ((outputLimited) &&  /* Check output buffer overflow */
                 (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
-                goto _clean_up;
+                return 0;
             if (litLength >= RUN_MASK) {
                 int len = (int)litLength-RUN_MASK;
                 *token = (RUN_MASK<<ML_BITS);
@@ -709,35 +808,55 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
             /* Copy Literals */
             LZ4_wildCopy(op, anchor, op+litLength);
             op+=litLength;
+            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
         }
 
 _next_match:
+        /* at this stage, the following variables must be correctly set :
+         * - ip : at start of LZ operation
+         * - match : at start of previous pattern occurence; can be within current prefix, or within extDict
+         * - offset : if maybe_ext_memSegment==1 (constant)
+         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
+         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
+         */
+
         /* Encode Offset */
-        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+        if (maybe_extMem) {   /* static test */
+            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
+            assert(offset <= MAX_DISTANCE && offset > 0);
+            LZ4_writeLE16(op, (U16)offset); op+=2;
+        } else  {
+            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));
+            assert(ip-match <= MAX_DISTANCE);
+            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
+        }
 
         /* Encode MatchLength */
         {   unsigned matchCode;
 
-            if ((dictDirective==usingExtDict || dictDirective==usingDictCtx) && lowLimit==dictionary) {
-                const BYTE* limit;
-                match += refDelta;
-                limit = ip + (dictEnd-match);
+            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
+              && (lowLimit==dictionary) /* match within extDict */ ) {
+                const BYTE* limit = ip + (dictEnd-match);
+                assert(dictEnd > match);
                 if (limit > matchlimit) limit = matchlimit;
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
                 ip += MINMATCH + matchCode;
                 if (ip==limit) {
-                    unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
                     matchCode += more;
                     ip += more;
                 }
+                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);
             } else {
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
                 ip += MINMATCH + matchCode;
+                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);
             }
 
             if ( outputLimited &&    /* Check output buffer overflow */
                 (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
-                goto _clean_up;
+                return 0;
             if (matchCode >= ML_MASK) {
                 *token += ML_MASK;
                 matchCode -= ML_MASK;
@@ -762,33 +881,58 @@ _next_match:
         LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
 
         /* Test next position */
-        match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
-        if (dictDirective == usingDictCtx) {
-            if (match < (const BYTE*)source) {
-                /* there was no match, try the dictionary */
-                match = LZ4_getPosition(ip, dictCtx->hashTable, byU32, dictBase);
-                refDelta = dictDelta;
-                lowLimit = dictLowLimit;
-            } else {
-                refDelta = 0;
-                lowLimit = (const BYTE*)source;
+        if (tableType == byPtr) {
+
+            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+            LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+            if ( (match+MAX_DISTANCE >= ip)
+              && (LZ4_read32(match) == LZ4_read32(ip)) )
+            { token=op++; *token=0; goto _next_match; }
+
+        } else {   /* byU32, byU16 */
+
+            U32 const h = LZ4_hashPosition(ip, tableType);
+            U32 const current = (U32)(ip-base);
+            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if (dictDirective == usingDictCtx) {
+                if (matchIndex < startIndex) {
+                    /* there was no match, try the dictionary */
+                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                    matchIndex += dictDelta;
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;  /* required for match length counter */
+                }
+            } else if (dictDirective==usingExtDict) {
+                if (matchIndex < startIndex) {
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;   /* required for match length counter */
+                }
+            } else {   /* single memory segment */
+                match = base + matchIndex;
             }
-        } else if (dictDirective==usingExtDict) {
-            if (match < (const BYTE*)source) {
-                refDelta = dictDelta;
-                lowLimit = dictLowLimit;
-            } else {
-                refDelta = 0;
-                lowLimit = (const BYTE*)source;
-        }   }
-        LZ4_putPosition(ip, cctx->hashTable, tableType, base);
-        if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
-            && (match+MAX_DISTANCE>=ip)
-            && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
-        { token=op++; *token=0; goto _next_match; }
+            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
+              && ((tableType==byU16) ? 1 : (current - matchIndex <= MAX_DISTANCE))
+              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
+                token=op++;
+                *token=0;
+                if (maybe_extMem) offset = current - matchIndex;
+                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                            (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
+                goto _next_match;
+            }
+        }
 
         /* Prepare next loop */
         forwardH = LZ4_hashPosition(++ip, tableType);
+
     }
 
 _last_literals:
@@ -796,7 +940,7 @@ _last_literals:
     {   size_t const lastRun = (size_t)(iend - anchor);
         if ( (outputLimited) &&  /* Check output buffer overflow */
             ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
-            goto _clean_up;
+            return 0;
         if (lastRun >= RUN_MASK) {
             size_t accumulator = lastRun - RUN_MASK;
             *op++ = RUN_MASK << ML_BITS;
@@ -809,22 +953,7 @@ _last_literals:
         op += lastRun;
     }
 
-    retval = (((char*)op)-dest);
-
-_clean_up:
-    if (dictDirective == usingDictCtx) {
-        /* Subsequent linked blocks can't use the dictionary. */
-        /* Instead, they use the block we just compressed. */
-        cctx->dictCtx = NULL;
-        cctx->dictSize = (U32)inputSize;
-    } else {
-        cctx->dictSize += (U32)inputSize;
-    }
-    cctx->currentOffset += (U32)inputSize;
-    cctx->tableType = tableType;
-
-    /* End */
-    return (int)retval;
+    return (int)(((char*)op) - dest);
 }
 
 
@@ -837,68 +966,60 @@ int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int
         if (inputSize < LZ4_64Klimit) {
             return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
         } else {
-            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32;
             return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
         }
     } else {
         if (inputSize < LZ4_64Klimit) {;
             return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
         } else {
-            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32;
             return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
         }
     }
 }
 
 /**
- * LZ4_compress_fast_extState_noReset is a variant of LZ4_compress_fast_extState
- * that can be used when the state is known to have already been initialized
- * (via LZ4_resetStream or an earlier call to LZ4_compress_fast_extState /
- * LZ4_compress_fast_extState_noReset). This can provide significantly better
- * performance when the context reset would otherwise be a significant part of
- * the cost of the compression, e.g., when the data to be compressed is small.
+ * LZ4_compress_fast_extState_fastReset() :
+ * A variant of LZ4_compress_fast_extState().
+ *
+ * Using this variant avoids an expensive initialization step. It is only safe
+ * to call if the state buffer is known to be correctly initialized already
+ * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
+ * "correctly initialized").
  */
-int LZ4_compress_fast_extState_noReset(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
 {
     LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
     if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
-    ctx->dictionary = NULL;
-    ctx->dictSize = 0;
-    ctx->dictCtx = NULL;
 
-    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
-        if (inputSize < LZ4_64Klimit) {
+    if (dstCapacity >= LZ4_compressBound(srcSize)) {
+        if (srcSize < LZ4_64Klimit) {
             const tableType_t tableType = byU16;
-            LZ4_prepareTable(ctx, inputSize, tableType, noDict);
+            LZ4_prepareTable(ctx, srcSize, tableType);
             if (ctx->currentOffset) {
-                return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, dictSmall, acceleration);
+                return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, dictSmall, acceleration);
             } else {
-                return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+                return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
             }
         } else {
-            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
-            LZ4_prepareTable(ctx, inputSize, tableType, noDict);
-            if (ctx->currentOffset) {
-                ctx->currentOffset += 64 KB;
-            }
-            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
         }
     } else {
-        if (inputSize < LZ4_64Klimit) {
+        if (srcSize < LZ4_64Klimit) {
             const tableType_t tableType = byU16;
-            LZ4_prepareTable(ctx, inputSize, tableType, noDict);
+            LZ4_prepareTable(ctx, srcSize, tableType);
             if (ctx->currentOffset) {
-                return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, dictSmall, acceleration);
+                return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
             } else {
-                return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+                return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
             }
         } else {
-            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
-            LZ4_prepareTable(ctx, inputSize, tableType, noDict);
-            if (ctx->currentOffset) {
-                ctx->currentOffset += 64 KB;
-            }
-            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
         }
     }
 }
@@ -1110,11 +1231,12 @@ static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src,
     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)
+        if (*srcSizePtr < LZ4_64Klimit) {
             return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
-        else
-            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr);
-    }
+        } else {
+            tableType_t const tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, tableType);
+    }   }
 }
 
 
@@ -1154,9 +1276,12 @@ LZ4_stream_t* LZ4_createStream(void)
 
 void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
 {
-    DEBUGLOG(5, "LZ4_resetStream %p", LZ4_stream);
+    DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
     MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
-    LZ4_stream->internal_donotuse.tableType = clearedTable;
+}
+
+void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
+    LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
 }
 
 int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
@@ -1172,47 +1297,66 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
 {
     LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
+    const tableType_t tableType = byU32;
     const BYTE* p = (const BYTE*)dictionary;
     const BYTE* const dictEnd = p + dictSize;
     const BYTE* base;
 
-    DEBUGLOG(4, "LZ4_loadDict %p", LZ4_dict);
+    DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);
+
+    LZ4_prepareTable(dict, 0, tableType);
 
-    if ((dict->initCheck)
-      || (dict->tableType != byU32 && dict->tableType != clearedTable)
-      || (dict->currentOffset > 1 GB))  /* Uninitialized structure, or reuse overflow */
-        LZ4_resetStream(LZ4_dict);
+    /* We always increment the offset by 64 KB, since, if the dict is longer,
+     * we truncate it to the last 64k, and if it's shorter, we still want to
+     * advance by a whole window length so we can provide the guarantee that
+     * there are only valid offsets in the window, which allows an optimization
+     * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
+     * dictionary isn't a full 64k. */
 
     if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
-    dict->currentOffset += 64 KB;
-    base = p - dict->currentOffset;
+    base = dictEnd - 64 KB - dict->currentOffset;
     dict->dictionary = p;
     dict->dictSize = (U32)(dictEnd - p);
-    dict->currentOffset += dict->dictSize;
-    dict->tableType = byU32;
+    dict->currentOffset += 64 KB;
+    dict->tableType = tableType;
 
     if (dictSize < (int)HASH_UNIT) {
         return 0;
     }
 
     while (p <= dictEnd-HASH_UNIT) {
-        LZ4_putPosition(p, dict->hashTable, byU32, base);
+        LZ4_putPosition(p, dict->hashTable, tableType, base);
         p+=3;
     }
 
     return dict->dictSize;
 }
 
+void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) {
+    if (dictionary_stream != NULL) {
+        /* If the current offset is zero, we will never look in the
+         * external dictionary context, since there is no value a table
+         * entry can take that indicate a miss. In that case, we need
+         * to bump the offset to something non-zero.
+         */
+        if (working_stream->internal_donotuse.currentOffset == 0) {
+            working_stream->internal_donotuse.currentOffset = 64 KB;
+        }
+        working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse);
+    } else {
+        working_stream->internal_donotuse.dictCtx = NULL;
+    }
+}
 
-static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
 {
-    if ((LZ4_dict->currentOffset > 0x80000000) ||
-        ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {   /* address space overflow */
+    if (LZ4_dict->currentOffset + nextSize > 0x80000000) {   /* potential ptrdiff_t overflow (32-bits mode) */
         /* rescale hash table */
         U32 const delta = LZ4_dict->currentOffset - 64 KB;
         const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
         int i;
-        DEBUGLOG(4, "LZ4_renormDictT %p", LZ4_dict);
+        DEBUGLOG(4, "LZ4_renormDictT");
         for (i=0; i<LZ4_HASH_SIZE_U32; i++) {
             if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
             else LZ4_dict->hashTable[i] -= delta;
@@ -1230,10 +1374,8 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch
     LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
     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);
+    LZ4_renormDictT(streamPtr, inputSize);   /* avoid index overflow */
     if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
     /* Check overlapping input/dictionary space */
@@ -1248,7 +1390,6 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch
 
     /* prefix mode : source data follows dictionary */
     if (dictEnd == (const BYTE*)source) {
-        LZ4_prepareTable(streamPtr, inputSize, tableType, withPrefix64k);
         if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
             return LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
         else
@@ -1267,16 +1408,14 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch
             if (inputSize > 4 KB) {
                 /* For compressing large blobs, it is faster to pay the setup
                  * cost to copy the dictionary's tables into the active context,
-                 * so that the compression loop is only looking in one table.
+                 * so that the compression loop is only looking into one table.
                  */
                 memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t));
                 result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
             } else {
-                LZ4_prepareTable(streamPtr, inputSize, tableType, usingDictCtx);
                 result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
             }
         } else {
-            LZ4_prepareTable(streamPtr, inputSize, tableType, usingExtDict);
             if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
                 result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
             } else {
@@ -1290,25 +1429,22 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch
 }
 
 
-/* Hidden debug function, to force external dictionary mode */
-int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+/* Hidden debug function, to force-test external dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
 {
     LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
     int result;
-    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
 
-    const BYTE* smallest = dictEnd;
-    if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
-    LZ4_renormDictT(streamPtr, smallest);
+    LZ4_renormDictT(streamPtr, srcSize);
 
     if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
-        result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
     } else {
-        result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
     }
 
     streamPtr->dictionary = (const BYTE*)source;
-    streamPtr->dictSize = (U32)inputSize;
+    streamPtr->dictSize = (U32)srcSize;
 
     return result;
 }
@@ -1533,19 +1669,25 @@ _output_error:
 LZ4_FORCE_O2_GCC_PPC64LE
 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, (BYTE*)dest, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  endOnInputSize, full, 0, noDict,
+                                  (BYTE*)dest, NULL, 0);
 }
 
 LZ4_FORCE_O2_GCC_PPC64LE
 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, (BYTE*)dest, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  endOnInputSize, partial, targetOutputSize,
+                                  noDict, (BYTE*)dest, NULL, 0);
 }
 
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
 {
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
+    return LZ4_decompress_generic(source, dest, 0, originalSize,
+                                  endOnOutputSize, full, 0, withPrefix64k,
+                                  (BYTE*)(dest - 64 KB), NULL, 64 KB);
 }
 
 
@@ -1687,21 +1829,45 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres
 *  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); }
+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 dstCapacity)
+{
+    return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 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.
+These decompression functions 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); }
+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 */
 
diff --git a/lib/lz4.h b/lib/lz4.h
index 80f040f..0dfa19e 100644
--- a/lib/lz4.h
+++ b/lib/lz4.h
@@ -353,18 +353,69 @@ LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int or
  * Their signatures may change.
  **************************************/
 
-/*!
-LZ4_compress_fast_extState_noReset() :
-    A variant of LZ4_compress_fast_extState().
-
-    Use the _noReset variant if LZ4_resetStream() was called on the state
-    buffer before being used for the first time (calls to both extState
-    functions leave the state in a safe state, so zeroing is not required
-    between calls). Otherwise, using the plain _extState requires LZ4 to
-    reinitialize the state internally for every call.
-*/
-LZ4LIB_API int LZ4_compress_fast_extState_noReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+/*! LZ4_resetStream_fast() :
+ *  When an LZ4_stream_t is known to be in a internally coherent state,
+ *  it can often be prepared for a new compression with almost no work, only
+ *  sometimes falling back to the full, expensive reset that is always required
+ *  when the stream is in an indeterminate state (i.e., the reset performed by
+ *  LZ4_resetStream()).
+ *
+ *  LZ4_streams are guaranteed to be in a valid state when:
+ *  - returned from LZ4_createStream()
+ *  - reset by LZ4_resetStream()
+ *  - memset(stream, 0, sizeof(LZ4_stream_t))
+ *  - the stream was in a valid state and was reset by LZ4_resetStream_fast()
+ *  - the stream was in a valid state and was then used in any compression call
+ *    that returned success
+ *  - the stream was in an indeterminate state and was used in a compression
+ *    call that fully reset the state (LZ4_compress_fast_extState()) and that
+ *    returned success
+ */
+LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
 
+/*! LZ4_compress_fast_extState_fastReset() :
+ *  A variant of LZ4_compress_fast_extState().
+ *
+ *  Using this variant avoids an expensive initialization step. It is only safe
+ *  to call if the state buffer is known to be correctly initialized already
+ *  (see above comment on LZ4_resetStream_fast() for a definition of "correctly
+ *  initialized"). From a high level, the difference is that this function
+ *  initializes the provided state with a call to LZ4_resetStream_fast() while
+ *  LZ4_compress_fast_extState() starts with a call to LZ4_resetStream().
+ */
+LZ4LIB_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*! LZ4_attach_dictionary() :
+ *  This is an experimental API that allows for the efficient use of a
+ *  static dictionary many times.
+ *
+ *  Rather than re-loading the dictionary buffer into a working context before
+ *  each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
+ *  working LZ4_stream_t, this function introduces a no-copy setup mechanism,
+ *  in which the working stream references the dictionary stream in-place.
+ *
+ *  Several assumptions are made about the state of the dictionary stream.
+ *  Currently, only streams which have been prepared by LZ4_loadDict() should
+ *  be expected to work.
+ *
+ *  Alternatively, the provided dictionary stream pointer may be NULL, in which
+ *  case any existing dictionary stream is unset.
+ *
+ *  If a dictionary is provided, it replaces any pre-existing stream history.
+ *  The dictionary contents are the only history that can be referenced and
+ *  logically immediately precede the data compressed in the first subsequent
+ *  compression call.
+ *
+ *  The dictionary will only remain attached to the working stream through the
+ *  first compression call, at the end of which it is cleared. The dictionary
+ *  stream (and source buffer) must remain in-place / accessible / unchanged
+ *  through the completion of the first compression call on the stream.
+ */
+LZ4LIB_API void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream);
+
+#endif
 
 /*-************************************
  *  Private definitions
diff --git a/lib/lz4frame.c b/lib/lz4frame.c
index a080fa6..507e4fe 100644
--- a/lib/lz4frame.c
+++ b/lib/lz4frame.c
@@ -74,6 +74,7 @@ You can contact the author at :
 *  Includes
 **************************************/
 #include "lz4frame_static.h"
+#define LZ4_STATIC_LINKING_ONLY
 #include "lz4.h"
 #define LZ4_HC_STATIC_LINKING_ONLY
 #include "lz4hc.h"
@@ -530,13 +531,8 @@ static void LZ4F_applyCDict(void* ctx,
                             const LZ4F_CDict* cdict,
                             int level) {
     if (level < LZ4HC_CLEVEL_MIN) {
-        LZ4_stream_t_internal* internal_ctx = &((LZ4_stream_t *)ctx)->internal_donotuse;
-        assert(!internal_ctx->initCheck);
-        /* Clear any local dictionary */
-        internal_ctx->dictionary = NULL;
-        internal_ctx->dictSize = 0;
-        /* Point to the dictionary context */
-        internal_ctx->dictCtx = cdict ? &(cdict->fastCtx->internal_donotuse) : NULL;
+        LZ4_resetStream_fast((LZ4_stream_t *)ctx);
+        LZ4_attach_dictionary((LZ4_stream_t *)ctx, cdict ? cdict->fastCtx : NULL);
     } else {
         if (cdict) {
             memcpy(ctx, cdict->HCCtx, sizeof(*cdict->HCCtx));
@@ -716,7 +712,7 @@ static int LZ4F_compressBlock(void* ctx, const char* src, char* dst, int srcSize
     if (cdict) {
         return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, acceleration);
     } else {
-        return LZ4_compress_fast_extState_noReset(ctx, src, dst, srcSize, dstCapacity, acceleration);
+        return LZ4_compress_fast_extState_fastReset(ctx, src, dst, srcSize, dstCapacity, acceleration);
     }
 }
 
diff --git a/lib/lz4frame.h b/lib/lz4frame.h
index 9efaca0..e80b1a1 100644
--- a/lib/lz4frame.h
+++ b/lib/lz4frame.h
@@ -93,8 +93,8 @@ extern "C" {
  **************************************/
 typedef size_t LZ4F_errorCode_t;
 
-LZ4FLIB_API unsigned    LZ4F_isError(LZ4F_errorCode_t code);   /**< tells if a `LZ4F_errorCode_t` function result is an error code */
-LZ4FLIB_API const char* LZ4F_getErrorName(LZ4F_errorCode_t code);   /**< return error code string; useful for debugging */
+LZ4FLIB_API unsigned    LZ4F_isError(LZ4F_errorCode_t code);   /**< tells when a function result is an error code */
+LZ4FLIB_API const char* LZ4F_getErrorName(LZ4F_errorCode_t code);   /**< return error code string; for debugging */
 
 
 /*-************************************
@@ -162,13 +162,13 @@ typedef LZ4F_contentChecksum_t contentChecksum_t;
  *  It's not required to set all fields, as long as the structure was initially memset() to zero.
  *  For all fields, 0 sets it to default value */
 typedef struct {
-  LZ4F_blockSizeID_t     blockSizeID;          /* max64KB, max256KB, max1MB, max4MB ; 0 == default */
-  LZ4F_blockMode_t       blockMode;            /* LZ4F_blockLinked, LZ4F_blockIndependent ; 0 == default */
-  LZ4F_contentChecksum_t contentChecksumFlag;  /* if enabled, frame is terminated with a 32-bits checksum of decompressed data ; 0 == disabled (default)  */
-  LZ4F_frameType_t       frameType;            /* read-only field : LZ4F_frame or LZ4F_skippableFrame */
-  unsigned long long     contentSize;          /* Size of uncompressed content ; 0 == unknown */
-  unsigned               dictID;               /* Dictionary ID, sent by the compressor to help decoder select the correct dictionary; 0 == no dictID provided */
-  LZ4F_blockChecksum_t   blockChecksumFlag;    /* if enabled, each block is followed by a checksum of block's compressed data ; 0 == disabled (default)  */
+  LZ4F_blockSizeID_t     blockSizeID;         /* max64KB, max256KB, max1MB, max4MB; 0 == default */
+  LZ4F_blockMode_t       blockMode;           /* LZ4F_blockLinked, LZ4F_blockIndependent; 0 == default */
+  LZ4F_contentChecksum_t contentChecksumFlag; /* 1: frame terminated with 32-bit checksum of decompressed data; 0: disabled (default) */
+  LZ4F_frameType_t       frameType;           /* read-only field : LZ4F_frame or LZ4F_skippableFrame */
+  unsigned long long     contentSize;         /* Size of uncompressed content ; 0 == unknown */
+  unsigned               dictID;              /* Dictionary ID, sent by compressor to help decoder select correct dictionary; 0 == no dictID provided */
+  LZ4F_blockChecksum_t   blockChecksumFlag;   /* 1: each block followed by a checksum of block's compressed data; 0: disabled (default) */
 } LZ4F_frameInfo_t;
 
 /*! LZ4F_preferences_t :
@@ -177,7 +177,7 @@ typedef struct {
  *  All reserved fields must be set to zero. */
 typedef struct {
   LZ4F_frameInfo_t frameInfo;
-  int      compressionLevel;       /* 0 == default (fast mode); values above LZ4HC_CLEVEL_MAX count as LZ4HC_CLEVEL_MAX; values below 0 trigger "fast acceleration", proportional to value */
+  int      compressionLevel;       /* 0: default (fast mode); values > LZ4HC_CLEVEL_MAX count as LZ4HC_CLEVEL_MAX; values < 0 trigger "fast acceleration" */
   unsigned autoFlush;              /* 1 == always flush, to reduce usage of internal buffers */
   unsigned reserved[4];            /* must be zero for forward compatibility */
 } LZ4F_preferences_t;
@@ -264,36 +264,44 @@ LZ4FLIB_API size_t LZ4F_compressBound(size_t srcSize, const LZ4F_preferences_t*
 
 /*! LZ4F_compressUpdate() :
  *  LZ4F_compressUpdate() can be called repetitively to compress as much data as necessary.
- *  An important rule is that dstCapacity MUST be large enough to ensure operation success even in worst case situations.
+ *  Important rule: dstCapacity MUST be large enough to ensure operation success even in worst case situations.
  *  This value is provided by LZ4F_compressBound().
  *  If this condition is not respected, LZ4F_compress() will fail (result is an errorCode).
- *  LZ4F_compressUpdate() doesn't guarantee error recovery. When an error occurs, compression context must be freed or resized.
+ *  LZ4F_compressUpdate() doesn't guarantee error recovery.
+ *  When an error occurs, compression context must be freed or resized.
  * `cOptPtr` is optional : NULL can be provided, in which case all options are set to default.
  * @return : number of bytes written into `dstBuffer` (it can be zero, meaning input data was just buffered).
  *           or an error code if it fails (which can be tested using LZ4F_isError())
  */
-LZ4FLIB_API size_t LZ4F_compressUpdate(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const void* srcBuffer, size_t srcSize, const LZ4F_compressOptions_t* cOptPtr);
+LZ4FLIB_API size_t LZ4F_compressUpdate(LZ4F_cctx* cctx,
+                                       void* dstBuffer, size_t dstCapacity,
+                                 const void* srcBuffer, size_t srcSize,
+                                 const LZ4F_compressOptions_t* cOptPtr);
 
 /*! LZ4F_flush() :
  *  When data must be generated and sent immediately, without waiting for a block to be completely filled,
  *  it's possible to call LZ4_flush(). It will immediately compress any data buffered within cctx.
  * `dstCapacity` must be large enough to ensure the operation will be successful.
  * `cOptPtr` is optional : it's possible to provide NULL, all options will be set to default.
- * @return : number of bytes written into dstBuffer (it can be zero, which means there was no data stored within cctx)
+ * @return : nb of bytes written into dstBuffer (can be zero, when there is no data stored within cctx)
  *           or an error code if it fails (which can be tested using LZ4F_isError())
  */
-LZ4FLIB_API size_t LZ4F_flush(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const LZ4F_compressOptions_t* cOptPtr);
+LZ4FLIB_API size_t LZ4F_flush(LZ4F_cctx* cctx,
+                              void* dstBuffer, size_t dstCapacity,
+                        const LZ4F_compressOptions_t* cOptPtr);
 
 /*! LZ4F_compressEnd() :
  *  To properly finish an LZ4 frame, invoke LZ4F_compressEnd().
  *  It will flush whatever data remained within `cctx` (like LZ4_flush())
  *  and properly finalize the frame, with an endMark and a checksum.
  * `cOptPtr` is optional : NULL can be provided, in which case all options will be set to default.
- * @return : number of bytes written into dstBuffer (necessarily >= 4 (endMark), or 8 if optional frame checksum is enabled)
+ * @return : nb of bytes written into dstBuffer, necessarily >= 4 (endMark),
  *           or an error code if it fails (which can be tested using LZ4F_isError())
  *  A successful call to LZ4F_compressEnd() makes `cctx` available again for another compression task.
  */
-LZ4FLIB_API size_t LZ4F_compressEnd(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const LZ4F_compressOptions_t* cOptPtr);
+LZ4FLIB_API size_t LZ4F_compressEnd(LZ4F_cctx* cctx,
+                                    void* dstBuffer, size_t dstCapacity,
+                              const LZ4F_compressOptions_t* cOptPtr);
 
 
 /*-*********************************
@@ -303,7 +311,7 @@ typedef struct LZ4F_dctx_s LZ4F_dctx;   /* incomplete type */
 typedef LZ4F_dctx* LZ4F_decompressionContext_t;   /* compatibility with previous API versions */
 
 typedef struct {
-  unsigned stableDst;    /* pledge that at least 64KB+64Bytes of previously decompressed data remain unmodifed where it was decoded. This optimization skips storage operations in tmp buffers */
+  unsigned stableDst;    /* pledges that last 64KB decompressed data will remain available unmodified. This optimization skips storage operations in tmp buffers. */
   unsigned reserved[3];  /* must be set to zero for forward compatibility */
 } LZ4F_decompressOptions_t;
 
@@ -316,7 +324,7 @@ typedef struct {
  *  The function provides a pointer to an allocated and initialized LZ4F_dctx object.
  *  The result is an errorCode, which can be tested using LZ4F_isError().
  *  dctx memory can be released using LZ4F_freeDecompressionContext();
- *  The result of LZ4F_freeDecompressionContext() is indicative of the current state of decompressionContext when being released.
+ *  Result of LZ4F_freeDecompressionContext() indicates current state of decompressionContext when being released.
  *  That is, it should be == 0 if decompression has been completed fully and correctly.
  */
 LZ4FLIB_API LZ4F_errorCode_t LZ4F_createDecompressionContext(LZ4F_dctx** dctxPtr, unsigned version);
@@ -357,8 +365,8 @@ LZ4FLIB_API size_t LZ4F_getFrameInfo(LZ4F_dctx* dctx,
  *  The function will read up to *srcSizePtr bytes from srcBuffer,
  *  and decompress data into dstBuffer, of capacity *dstSizePtr.
  *
- *  The number of bytes consumed from srcBuffer will be written into *srcSizePtr (necessarily <= original value).
- *  The number of bytes decompressed into dstBuffer will be written into *dstSizePtr (necessarily <= original value).
+ *  The nb of bytes consumed from srcBuffer will be written into *srcSizePtr (necessarily <= original value).
+ *  The nb of bytes decompressed into dstBuffer will be written into *dstSizePtr (necessarily <= original value).
  *
  *  The function does not necessarily read all input bytes, so always check value in *srcSizePtr.
  *  Unconsumed source data must be presented again in subsequent invocations.
diff --git a/lib/lz4hc.c b/lib/lz4hc.c
index 0c1b20a..111a09b 100644
--- a/lib/lz4hc.c
+++ b/lib/lz4hc.c
@@ -336,7 +336,7 @@ LZ4_FORCE_INLINE int LZ4HC_encodeSequence (
     U32 const mlAdd = (matchLength>=19) ? ((matchLength-19) / 255) + 1 : 0;
     U32 const cost = 1 + llAdd + ll + 2 + mlAdd;
     if (start==NULL) start = *anchor;  /* only works for single segment */
-    //g_debuglog_enable = (pos >= 2228) & (pos <= 2262);
+    /* g_debuglog_enable = (pos >= 2228) & (pos <= 2262); */
     DEBUGLOG(6, "pos:%7u -- literals:%3u, match:%4i, offset:%5u, cost:%3u + %u",
                 pos,
                 (U32)(*ip - *anchor), matchLength, (U32)(*ip-match),
@@ -852,16 +852,17 @@ int LZ4_resetStreamStateHC(void* state, char* inputBuffer)
     LZ4HC_CCtx_internal *ctx = &((LZ4_streamHC_t*)state)->internal_donotuse;
     if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1;   /* Error : pointer is not aligned for pointer (32 or 64 bits) */
     LZ4HC_init(ctx, (const BYTE*)inputBuffer);
-    ctx->inputBuffer = (BYTE*)inputBuffer;
+    ctx->inputBuffer = inputBuffer;
     return 0;
 }
 
-void* LZ4_createHC (char* inputBuffer)
+void* LZ4_createHC (const char* inputBuffer)
 {
     LZ4_streamHC_t* hc4 = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t));
     if (hc4 == NULL) return NULL;   /* not enough memory */
     LZ4HC_init (&hc4->internal_donotuse, (const BYTE*)inputBuffer);
-    hc4->internal_donotuse.inputBuffer = (BYTE*)inputBuffer;
+    assert(sizeof(size_t) == sizeof(void*));
+    hc4->internal_donotuse.inputBuffer = (void*)(size_t)inputBuffer;   /* ugly hack, circumvent -Wcast-qual */
     return hc4;
 }
 
@@ -885,7 +886,7 @@ char* LZ4_slideInputBufferHC(void* LZ4HC_Data)
 {
     LZ4HC_CCtx_internal* const hc4 = &((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse;
     int const dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB);
-    return (char*)(hc4->inputBuffer + dictSize);
+    return (char*)(hc4->inputBuffer) + dictSize;
 }
 
 
@@ -1136,15 +1137,14 @@ static int LZ4HC_compress_optimal (
  encode: /* cur, last_match_pos, best_mlen, best_off must be set */
          assert(cur < LZ4_OPT_NUM);
          assert(last_match_pos >= 1);  /* == 1 when only one candidate */
-         DEBUGLOG(6, "reverse traversal, looking for shortest path")
-         DEBUGLOG(6, "last_match_pos = %i", last_match_pos);
+         DEBUGLOG(6, "reverse traversal, looking for shortest path (last_match_pos=%i)", last_match_pos);
          {   int candidate_pos = cur;
              int selected_matchLength = best_mlen;
              int selected_offset = best_off;
              while (1) {  /* from end to beginning */
                  int const next_matchLength = opt[candidate_pos].mlen;  /* can be 1, means literal */
                  int const next_offset = opt[candidate_pos].off;
-                 DEBUGLOG(6, "pos %i: sequence length %i", candidate_pos, selected_matchLength);
+                 DEBUGLOG(7, "pos %i: sequence length %i", candidate_pos, selected_matchLength);
                  opt[candidate_pos].mlen = selected_matchLength;
                  opt[candidate_pos].off = selected_offset;
                  selected_matchLength = next_matchLength;
diff --git a/lib/lz4hc.h b/lib/lz4hc.h
index a7f77f9..7a25bee 100644
--- a/lib/lz4hc.h
+++ b/lib/lz4hc.h
@@ -148,7 +148,7 @@ typedef struct
     const uint8_t* end;         /* next block here to continue on current prefix */
     const uint8_t* base;        /* All index relative to this position */
     const uint8_t* dictBase;    /* alternate base for extDict */
-    uint8_t* inputBuffer;       /* deprecated */
+    void*      inputBuffer;     /* deprecated */
     uint32_t   dictLimit;       /* below that point, need extDict */
     uint32_t   lowLimit;        /* below that point, no more dict */
     uint32_t   nextToUpdate;    /* index from which to continue dictionary update */
@@ -164,7 +164,7 @@ typedef struct
     const unsigned char* end;        /* next block here to continue on current prefix */
     const unsigned char* base;       /* All index relative to this position */
     const unsigned char* dictBase;   /* alternate base for extDict */
-    unsigned char* inputBuffer;      /* deprecated */
+    void*          inputBuffer;      /* deprecated */
     unsigned int   dictLimit;        /* below that point, need extDict */
     unsigned int   lowLimit;         /* below that point, no more dict */
     unsigned int   nextToUpdate;     /* index from which to continue dictionary update */
@@ -206,8 +206,8 @@ LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_co
 LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_continue               (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize);
 LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
 
-/* Deprecated Streaming functions using older model; should no longer be used */
-LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API void* LZ4_createHC (char* inputBuffer);
+/* Deprecated Streaming functions; should no longer be used */
+LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API void* LZ4_createHC (const char* inputBuffer);
 LZ4_DEPRECATED("use LZ4_saveDictHC() instead") LZ4LIB_API     char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
 LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") LZ4LIB_API   int   LZ4_freeHC (void* LZ4HC_Data);
 LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel);