added ZDICT_finalizeDictionary()

NEWS

@@ -1,7 +1,8 @@
 v1.1.3
-cli : new : commands for advanced parameters, by Przemyslaw Skibinski
+cli : new : advanced commands for detailed parameters, by Przemyslaw Skibinski
 API : fix : all symbols properly exposed in libzstd, by Nick Terrell
 API : new : ZSTD_create?Dict_byReference(), requested by Bartosz Taudul
+API : new : ZDICT_finalizeDictionary()
 
 v1.1.2
 API : streaming : decompression : changed : automatic implicit reset when chain-decoding new frames without init

lib/dictBuilder/zdict.c

@@ -824,6 +824,55 @@ _cleanup:
 }
 
 
+
+size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
+                          const void* customDictContent, size_t dictContentSize,
+                          const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                          ZDICT_params_t params)
+{
+    size_t hSize;
+#define HBUFFSIZE 256
+    BYTE header[HBUFFSIZE];
+    int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel;
+    U32 const notificationLevel = params.notificationLevel;
+
+    /* check conditions */
+    if (dictBufferCapacity <= dictContentSize) return ERROR(dstSize_tooSmall);
+    if (dictContentSize < ZDICT_CONTENTSIZE_MIN) return ERROR(srcSize_wrong);
+    if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall);
+
+    /* dictionary header */
+    MEM_writeLE32(header, ZSTD_DICT_MAGIC);
+    {   U64 const randomID = XXH64(customDictContent, dictContentSize, 0);
+        U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
+        U32 const dictID = params.dictID ? params.dictID : compliantID;
+        MEM_writeLE32(header+4, dictID);
+    }
+    hSize = 8;
+
+    /* entropy tables */
+    DISPLAYLEVEL(2, "\r%70s\r", "");   /* clean display line */
+    DISPLAYLEVEL(2, "statistics ... \n");
+    {   size_t const eSize = ZDICT_analyzeEntropy(header+hSize, HBUFFSIZE-hSize,
+                                  compressionLevel,
+                                  samplesBuffer, samplesSizes, nbSamples,
+                                  customDictContent, dictContentSize,
+                                  notificationLevel);
+        if (ZDICT_isError(eSize)) return eSize;
+        hSize += eSize;
+    }
+
+    /* copy elements in final buffer ; note : src and dst buffer can overlap */
+    if (hSize + dictContentSize < dictBufferCapacity) dictContentSize = dictBufferCapacity - hSize;
+    {   size_t const dictSize = hSize + dictContentSize;
+        char* dictEnd = (char*)dictBuffer + dictSize;
+        memmove(dictEnd - dictContentSize, customDictContent, dictContentSize);
+        memcpy(dictBuffer, header, hSize);
+        return dictSize;
+    }
+}
+
+
 size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
                                                  const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
                                                  ZDICT_params_t params)

lib/dictBuilder/zdict.h

@@ -87,22 +87,57 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dict
                                 ZDICT_params_t parameters);
 
 
-/*! ZDICT_addEntropyTablesFromBuffer() :
+/*! ZDICT_finalizeDictionary() :
+
+    Given a custom content as a basis for dictionary, and a set of samples,
+    finalize dictionary by adding headers and statistics.
 
-    Given a content-only dictionary (built using any 3rd party algorithm),
-    add entropy tables computed from an array of samples.
     Samples must be stored concatenated in a flat buffer `samplesBuffer`,
     supplied with an array of sizes `samplesSizes`, providing the size of each sample in order.
 
-    The input dictionary content must be stored *at the end* of `dictBuffer`.
+    dictContentSize must be > ZDICT_CONTENTSIZE_MIN bytes.
-    Its size is `dictContentSize`.
+    maxDictSize must be > dictContentSize, and must be > ZDICT_DICTSIZE_MIN bytes.
-    The resulting dictionary with added entropy tables will be *written back to `dictBuffer`*,
-    starting from its beginning.
-    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`).
-*/
-ZDICTLIB_API size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
-                                        const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
 
+    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
+              or an error code, which can be tested by ZDICT_isError().
+    note : ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0.
+    note 2 : dictBuffer and customDictContent can overlap
+*/
+#define ZDICT_CONTENTSIZE_MIN 256
+#define ZDICT_DICTSIZE_MIN    512
+ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
+                                const void* customDictContent, size_t dictContentSize,
+                                const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                                ZDICT_params_t parameters);
+
+
+
+/* Deprecation warnings */
+/* It is generally possible to disable deprecation warnings from compiler,
+   for example with -Wno-deprecated-declarations for gcc
+   or _CRT_SECURE_NO_WARNINGS in Visual.
+   Otherwise, it's also possible to manually define ZDICT_DISABLE_DEPRECATE_WARNINGS */
+#ifdef ZDICT_DISABLE_DEPRECATE_WARNINGS
+#  define ZDICT_DEPRECATED(message)   /* disable deprecation warnings */
+#else
+#  define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+#  if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
+#    define ZDICT_DEPRECATED(message) [[deprecated(message)]]
+#  elif (ZDICT_GCC_VERSION >= 405) || defined(__clang__)
+#    define ZDICT_DEPRECATED(message) __attribute__((deprecated(message)))
+#  elif (ZDICT_GCC_VERSION >= 301)
+#    define ZDICT_DEPRECATED(message) __attribute__((deprecated))
+#  elif defined(_MSC_VER)
+#    define ZDICT_DEPRECATED(message) __declspec(deprecated(message))
+#  else
+#    pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler")
+#    define ZDICT_DEPRECATED(message)
+#  endif
+#endif /* ZDICT_DISABLE_DEPRECATE_WARNINGS */
+
+ZDICT_DEPRECATED("use ZDICT_finalizeDictionary() instead")
+size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
+                                  const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
 
 
 #endif   /* ZDICT_STATIC_LINKING_ONLY */