Merge branch 'dev' of github.com:facebook/zstd into dev

lib/dictBuilder/zdict.c

@@ -361,21 +361,35 @@ static dictItem ZDICT_analyzePos(
 }
 
 
-/*! ZDICT_tryMerge() :
+static int isIncluded(const void* in, const void* container, size_t length)
- *  check if dictItem can be merged, do it if possible
+{
- *  @return : id of destination elt, 0 if not merged
+    const char* const ip = (const char*) in;
- */
+    const char* const into = (const char*) container;
-static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip)
+    size_t u;
+
+    for (u=0; u<length; u++) {  /* works because end of buffer is a noisy guard band */
+        if (ip[u] != into[u]) break;
+    }
+
+    return u==length;
+}
+
+/*! ZDICT_checkMerge
+    check if dictItem can be merged, do it if possible
+    @return : id of destination elt, 0 if not merged
+*/
+static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip, const void* buffer)
 {
     const U32 tableSize = table->pos;
     const U32 eltEnd = elt.pos + elt.length;
+    const char* const buf = (const char*) buffer;
 
     /* tail overlap */
     U32 u; for (u=1; u<tableSize; u++) {
         if (u==eltNbToSkip) continue;
         if ((table[u].pos > elt.pos) && (table[u].pos <= eltEnd)) {  /* overlap, existing > new */
             /* append */
-            U32 addedLength = table[u].pos - elt.pos;
+            U32 const addedLength = table[u].pos - elt.pos;
             table[u].length += addedLength;
             table[u].pos = elt.pos;
             table[u].savings += elt.savings * addedLength / elt.length;   /* rough approx */
@@ -391,9 +405,10 @@ static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip)
     /* front overlap */
     for (u=1; u<tableSize; u++) {
         if (u==eltNbToSkip) continue;
+
         if ((table[u].pos + table[u].length >= elt.pos) && (table[u].pos < elt.pos)) {  /* overlap, existing < new */
             /* append */
-            int addedLength = (int)eltEnd - (table[u].pos + table[u].length);
+            int const addedLength = (int)eltEnd - (table[u].pos + table[u].length);
             table[u].savings += elt.length / 8;    /* rough approx bonus */
             if (addedLength > 0) {   /* otherwise, elt fully included into existing */
                 table[u].length += addedLength;
@@ -405,7 +420,18 @@ static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip)
                 table[u] = table[u-1], u--;
             table[u] = elt;
             return u;
-    }   }
+        }
+
+        if (MEM_read64(buf + table[u].pos) == MEM_read64(buf + elt.pos + 1)) {
+            if (isIncluded(buf + table[u].pos, buf + elt.pos + 1, table[u].length)) {
+                size_t const addedLength = MAX( (int)elt.length - (int)table[u].length , 1 );
+                table[u].pos = elt.pos;
+                table[u].savings += (U32)(elt.savings * addedLength / elt.length);
+                table[u].length = MIN(elt.length, table[u].length + 1);
+                return u;
+            }
+        }
+    }
 
     return 0;
 }
@@ -423,14 +449,14 @@ static void ZDICT_removeDictItem(dictItem* table, U32 id)
 }
 
 
-static void ZDICT_insertDictItem(dictItem* table, U32 maxSize, dictItem elt)
+static void ZDICT_insertDictItem(dictItem* table, U32 maxSize, dictItem elt, const void* buffer)
 {
     /* merge if possible */
-    U32 mergeId = ZDICT_tryMerge(table, elt, 0);
+    U32 mergeId = ZDICT_tryMerge(table, elt, 0, buffer);
-    if (mergeId) {  /* recursive : re-merge the newly merged elt */
+    if (mergeId) {
         U32 newMerge = 1;
         while (newMerge) {
-            newMerge = ZDICT_tryMerge(table, table[mergeId], mergeId);  /* merge existing elt */
+            newMerge = ZDICT_tryMerge(table, table[mergeId], mergeId, buffer);
             if (newMerge) ZDICT_removeDictItem(table, mergeId);
             mergeId = newMerge;
         }
@@ -519,7 +545,7 @@ static size_t ZDICT_trainBuffer(dictItem* dictList, U32 dictListSize,
             if (doneMarks[cursor]) { cursor++; continue; }
             solution = ZDICT_analyzePos(doneMarks, suffix, reverseSuffix[cursor], buffer, minRatio, notificationLevel);
             if (solution.length==0) { cursor++; continue; }
-            ZDICT_insertDictItem(dictList, dictListSize, solution);
+            ZDICT_insertDictItem(dictList, dictListSize, solution, buffer);
             cursor += solution.length;
             DISPLAYUPDATE(2, "\r%4.2f %% \r", (double)cursor / bufferSize * 100);
     }   }
@@ -681,19 +707,19 @@ static size_t ZDICT_analyzeEntropy(void*  dstBuffer, size_t maxDstSize,
         goto _cleanup;
     }
     if (offcodeMax>OFFCODE_MAX) { eSize = ERROR(dictionary_wrong); goto _cleanup; }   /* too large dictionary */
-    for (u=0; u<256; u++) countLit[u]=1;   /* any character must be described */
+    for (u=0; u<256; u++) countLit[u] = 1;   /* any character must be described */
-    for (u=0; u<=offcodeMax; u++) offcodeCount[u]=1;
+    for (u=0; u<=offcodeMax; u++) offcodeCount[u] = 1;
-    for (u=0; u<=MaxML; u++) matchLengthCount[u]=1;
+    for (u=0; u<=MaxML; u++) matchLengthCount[u] = 1;
-    for (u=0; u<=MaxLL; u++) litLengthCount[u]=1;
+    for (u=0; u<=MaxLL; u++) litLengthCount[u] = 1;
     memset(repOffset, 0, sizeof(repOffset));
     repOffset[1] = repOffset[4] = repOffset[8] = 1;
     memset(bestRepOffset, 0, sizeof(bestRepOffset));
-    if (compressionLevel==0) compressionLevel=g_compressionLevel_default;
+    if (compressionLevel==0) compressionLevel = g_compressionLevel_default;
     params = ZSTD_getParams(compressionLevel, averageSampleSize, dictBufferSize);
     {   size_t const beginResult = ZSTD_compressBegin_advanced(esr.ref, dictBuffer, dictBufferSize, params, 0);
-            if (ZSTD_isError(beginResult)) {
+        if (ZSTD_isError(beginResult)) {
+            DISPLAYLEVEL(1, "error : ZSTD_compressBegin_advanced() failed : %s \n", ZSTD_getErrorName(beginResult));
             eSize = ERROR(GENERIC);
-            DISPLAYLEVEL(1, "error : ZSTD_compressBegin_advanced failed \n");
             goto _cleanup;
     }   }
 
@@ -874,20 +900,11 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
                                                  const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
                                                  ZDICT_params_t params)
 {
-    size_t hSize;
     int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel;
     U32 const notificationLevel = params.notificationLevel;
+    size_t hSize = 8;
 
-    /* dictionary header */
+    /* calculate entropy tables */
-    MEM_writeLE32(dictBuffer, ZSTD_DICT_MAGIC);
-    {   U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0);
-        U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
-        U32 const dictID = params.dictID ? params.dictID : compliantID;
-        MEM_writeLE32((char*)dictBuffer+4, dictID);
-    }
-    hSize = 8;
-
-    /* entropy tables */
     DISPLAYLEVEL(2, "\r%70s\r", "");   /* clean display line */
     DISPLAYLEVEL(2, "statistics ... \n");
     {   size_t const eSize = ZDICT_analyzeEntropy((char*)dictBuffer+hSize, dictBufferCapacity-hSize,
@@ -899,6 +916,13 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
         hSize += eSize;
     }
 
+    /* add dictionary header (after entropy tables) */
+    MEM_writeLE32(dictBuffer, ZSTD_DICT_MAGIC);
+    {   U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0);
+        U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
+        U32 const dictID = params.dictID ? params.dictID : compliantID;
+        MEM_writeLE32((char*)dictBuffer+4, dictID);
+    }
 
     if (hSize + dictContentSize < dictBufferCapacity)
         memmove((char*)dictBuffer + hSize, (char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize);

programs/platform.h

@@ -100,9 +100,18 @@ extern "C" {
 #if (defined(__linux__) && (PLATFORM_POSIX_VERSION >= 1)) || (PLATFORM_POSIX_VERSION >= 200112L) || defined(__DJGPP__)
 #  include <unistd.h>   /* isatty */
 #  define IS_CONSOLE(stdStream) isatty(fileno(stdStream))
-#elif defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
+#elif defined(MSDOS) || defined(OS2) || defined(__CYGWIN__)
 #  include <io.h>       /* _isatty */
 #  define IS_CONSOLE(stdStream) _isatty(_fileno(stdStream))
+#elif defined(WIN32) || defined(_WIN32)
+#  include <io.h>      /* _isatty */
+#  include <windows.h> /* DeviceIoControl, HANDLE, FSCTL_SET_SPARSE */
+#  include <stdio.h>   /* FILE */
+static __inline int IS_CONSOLE(FILE* stdStream)
+{
+    DWORD dummy;
+    return _isatty(_fileno(stdStream)) && GetConsoleMode((HANDLE)_get_osfhandle(_fileno(stdStream)), &dummy);
+}
 #else
 #  define IS_CONSOLE(stdStream) 0
 #endif