extzstd 0.2 → 0.3

data/contrib/zstd/lib/dictBuilder/zdict.h

@@ -38,21 +38,28 @@ extern "C" {
 
 
 /*! ZDICT_trainFromBuffer():
- * Train a dictionary from an array of samples.
- * Uses ZDICT_optimizeTrainFromBuffer_cover() single-threaded, with d=8 and steps=4.
- * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
- * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
- * The resulting dictionary will be saved into `dictBuffer`.
+ *  Train a dictionary from an array of samples.
+ *  Redirect towards ZDICT_optimizeTrainFromBuffer_fastCover() single-threaded, with d=8, steps=4,
+ *  f=20, and accel=1.
+ *  Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ *  supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ *  The resulting dictionary will be saved into `dictBuffer`.
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- * Note: ZDICT_trainFromBuffer() requires about 9 bytes of memory for each input byte.
- * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
- *        It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
- *        In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *  Note:  Dictionary training will fail if there are not enough samples to construct a
+ *         dictionary, or if most of the samples are too small (< 8 bytes being the lower limit).
+ *         If dictionary training fails, you should use zstd without a dictionary, as the dictionary
+ *         would've been ineffective anyways. If you believe your samples would benefit from a dictionary
+ *         please open an issue with details, and we can look into it.
+ *  Note: ZDICT_trainFromBuffer()'s memory usage is about 6 MB.
+ *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
+ *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
  *        It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
  */
 ZDICTLIB_API size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
-                       const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
+                                    const void* samplesBuffer,
+                                    const size_t* samplesSizes, unsigned nbSamples);
 
 
 /*======   Helper functions   ======*/
@@ -72,62 +79,119 @@ ZDICTLIB_API const char* ZDICT_getErrorName(size_t errorCode);
  * ==================================================================================== */
 
 typedef struct {
-    int      compressionLevel;   /* 0 means default; target a specific zstd compression level */
-    unsigned notificationLevel;  /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
-    unsigned dictID;             /* 0 means auto mode (32-bits random value); other : force dictID value */
+    int      compressionLevel;   /* optimize for a specific zstd compression level; 0 means default */
+    unsigned notificationLevel;  /* Write log to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
+    unsigned dictID;             /* force dictID value; 0 means auto mode (32-bits random value) */
 } ZDICT_params_t;
 
 /*! ZDICT_cover_params_t:
- *  For all values 0 means default.
  *  k and d are the only required parameters.
+ *  For others, value 0 means default.
  */
 typedef struct {
     unsigned k;                  /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */
     unsigned d;                  /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
-    unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */
+    unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (40) : Higher means more parameters checked */
     unsigned nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
+    double splitPoint;           /* Percentage of samples used for training: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (1.0), 1.0 when all samples are used for both training and testing */
     ZDICT_params_t zParams;
 } ZDICT_cover_params_t;
 
+typedef struct {
+    unsigned k;                  /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */
+    unsigned d;                  /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
+    unsigned f;                  /* log of size of frequency array : constraint: 0 < f <= 31 : 1 means default(20)*/
+    unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (40) : Higher means more parameters checked */
+    unsigned nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
+    double splitPoint;           /* Percentage of samples used for training: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (0.75), 1.0 when all samples are used for both training and testing */
+    unsigned accel;              /* Acceleration level: constraint: 0 < accel <= 10, higher means faster and less accurate, 0 means default(1) */
+    ZDICT_params_t zParams;
+} ZDICT_fastCover_params_t;
 
 /*! ZDICT_trainFromBuffer_cover():
- * Train a dictionary from an array of samples using the COVER algorithm.
- * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
- * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
- * The resulting dictionary will be saved into `dictBuffer`.
+ *  Train a dictionary from an array of samples using the COVER algorithm.
+ *  Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ *  supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ *  The resulting dictionary will be saved into `dictBuffer`.
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte.
- * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
- *        It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
- *        In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ *  Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte.
+ *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
+ *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
  *        It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
  */
 ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
-    void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
-    const size_t *samplesSizes, unsigned nbSamples,
-    ZDICT_cover_params_t parameters);
+          void *dictBuffer, size_t dictBufferCapacity,
+    const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
+          ZDICT_cover_params_t parameters);
 
 /*! ZDICT_optimizeTrainFromBuffer_cover():
  * The same requirements as above hold for all the parameters except `parameters`.
  * This function tries many parameter combinations and picks the best parameters.
- * `*parameters` is filled with the best parameters found, and the dictionary
- * constructed with those parameters is stored in `dictBuffer`.
+ * `*parameters` is filled with the best parameters found,
+ * dictionary constructed with those parameters is stored in `dictBuffer`.
  *
  * All of the parameters d, k, steps are optional.
- * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}.
+ * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8}.
  * if steps is zero it defaults to its default value.
- * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048].
+ * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000].
  *
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- *           On success `*parameters` contains the parameters selected.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          On success `*parameters` contains the parameters selected.
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
  * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread.
  */
 ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
-    void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
-    const size_t *samplesSizes, unsigned nbSamples,
-    ZDICT_cover_params_t *parameters);
+          void* dictBuffer, size_t dictBufferCapacity,
+    const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+          ZDICT_cover_params_t* parameters);
+
+/*! ZDICT_trainFromBuffer_fastCover():
+ *  Train a dictionary from an array of samples using a modified version of COVER algorithm.
+ *  Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ *  supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ *  d and k are required.
+ *  All other parameters are optional, will use default values if not provided
+ *  The resulting dictionary will be saved into `dictBuffer`.
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ *  Note: ZDICT_trainFromBuffer_fastCover() requires 6 * 2^f bytes of memory.
+ *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
+ *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
+ *        It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+ */
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_fastCover(void *dictBuffer,
+                    size_t dictBufferCapacity, const void *samplesBuffer,
+                    const size_t *samplesSizes, unsigned nbSamples,
+                    ZDICT_fastCover_params_t parameters);
+
+/*! ZDICT_optimizeTrainFromBuffer_fastCover():
+ * The same requirements as above hold for all the parameters except `parameters`.
+ * This function tries many parameter combinations (specifically, k and d combinations)
+ * and picks the best parameters. `*parameters` is filled with the best parameters found,
+ * dictionary constructed with those parameters is stored in `dictBuffer`.
+ * All of the parameters d, k, steps, f, and accel are optional.
+ * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8}.
+ * if steps is zero it defaults to its default value.
+ * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000].
+ * If f is zero, default value of 20 is used.
+ * If accel is zero, default value of 1 is used.
+ *
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          On success `*parameters` contains the parameters selected.
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ * Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 6 * 2^f bytes of memory for each thread.
+ */
+ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer,
+                    size_t dictBufferCapacity, const void* samplesBuffer,
+                    const size_t* samplesSizes, unsigned nbSamples,
+                    ZDICT_fastCover_params_t* parameters);
 
 /*! ZDICT_finalizeDictionary():
  * Given a custom content as a basis for dictionary, and a set of samples,
@@ -140,7 +204,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
  * maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes.
  *
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
- *           or an error code, which can be tested by ZDICT_isError().
+ *          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 dictContent can overlap
  */
@@ -157,22 +221,24 @@ typedef struct {
 } ZDICT_legacy_params_t;
 
 /*! ZDICT_trainFromBuffer_legacy():
- * Train a dictionary from an array of samples.
- * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
- * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
- * The resulting dictionary will be saved into `dictBuffer`.
+ *  Train a dictionary from an array of samples.
+ *  Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ *  supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ *  The resulting dictionary will be saved into `dictBuffer`.
  * `parameters` is optional and can be provided with values set to 0 to mean "default".
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- *           or an error code, which can be tested with ZDICT_isError().
- * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
- *        It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
- *        In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ *          or an error code, which can be tested with ZDICT_isError().
+ *          See ZDICT_trainFromBuffer() for details on failure modes.
+ *  Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ *        It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
+ *        In general, it's recommended to provide a few thousands samples, though this can vary a lot.
  *        It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
- * Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0.
+ *  Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0.
  */
 ZDICTLIB_API size_t ZDICT_trainFromBuffer_legacy(
-    void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
-    const size_t *samplesSizes, unsigned nbSamples, ZDICT_legacy_params_t parameters);
+    void *dictBuffer, size_t dictBufferCapacity,
+    const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
+    ZDICT_legacy_params_t parameters);
 
 /* Deprecation warnings */
 /* It is generally possible to disable deprecation warnings from compiler,

data/contrib/zstd/lib/legacy/zstd_legacy.h

@@ -20,7 +20,7 @@ extern "C" {
 ***************************************/
 #include "mem.h"            /* MEM_STATIC */
 #include "error_private.h"  /* ERROR */
-#include "zstd.h"           /* ZSTD_inBuffer, ZSTD_outBuffer */
+#include "zstd_internal.h"  /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTD_frameSizeInfo */
 
 #if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0)
 #  undef ZSTD_LEGACY_SUPPORT
@@ -178,43 +178,73 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
     }
 }
 
-MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src,
-                                             size_t compressedSize)
+MEM_STATIC ZSTD_frameSizeInfo ZSTD_findFrameSizeInfoLegacy(const void *src, size_t srcSize)
 {
-    U32 const version = ZSTD_isLegacy(src, compressedSize);
+    ZSTD_frameSizeInfo frameSizeInfo;
+    U32 const version = ZSTD_isLegacy(src, srcSize);
     switch(version)
     {
 #if (ZSTD_LEGACY_SUPPORT <= 1)
         case 1 :
-            return ZSTDv01_findFrameCompressedSize(src, compressedSize);
+            ZSTDv01_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 2)
         case 2 :
-            return ZSTDv02_findFrameCompressedSize(src, compressedSize);
+            ZSTDv02_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 3)
         case 3 :
-            return ZSTDv03_findFrameCompressedSize(src, compressedSize);
+            ZSTDv03_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 4)
         case 4 :
-            return ZSTDv04_findFrameCompressedSize(src, compressedSize);
+            ZSTDv04_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 5)
         case 5 :
-            return ZSTDv05_findFrameCompressedSize(src, compressedSize);
+            ZSTDv05_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 6)
         case 6 :
-            return ZSTDv06_findFrameCompressedSize(src, compressedSize);
+            ZSTDv06_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
 #if (ZSTD_LEGACY_SUPPORT <= 7)
         case 7 :
-            return ZSTDv07_findFrameCompressedSize(src, compressedSize);
+            ZSTDv07_findFrameSizeInfoLegacy(src, srcSize,
+                &frameSizeInfo.compressedSize,
+                &frameSizeInfo.decompressedBound);
+            break;
 #endif
         default :
-            return ERROR(prefix_unknown);
+            frameSizeInfo.compressedSize = ERROR(prefix_unknown);
+            frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+            break;
     }
+    return frameSizeInfo;
+}
+
+MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo frameSizeInfo = ZSTD_findFrameSizeInfoLegacy(src, srcSize);
+    return frameSizeInfo.compressedSize;
 }
 
 MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
@@ -246,6 +276,7 @@ MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
 MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U32 newVersion,
                                         const void* dict, size_t dictSize)
 {
+    DEBUGLOG(5, "ZSTD_initLegacyStream for v0.%u", newVersion);
     if (prevVersion != newVersion) ZSTD_freeLegacyStreamContext(*legacyContext, prevVersion);
     switch(newVersion)
     {
@@ -304,6 +335,7 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
 MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
                                               ZSTD_outBuffer* output, ZSTD_inBuffer* input)
 {
+    DEBUGLOG(5, "ZSTD_decompressLegacyStream for v0.%u", version);
     switch(version)
     {
         default :

data/contrib/zstd/lib/legacy/zstd_v01.c

@@ -668,11 +668,17 @@ static size_t FSE_initDStream(FSE_DStream_t* bitD, const void* srcBuffer, size_t
         switch(srcSize)
         {
             case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);
+                    /* fallthrough */
             case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);
+                    /* fallthrough */
             case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);
+                    /* fallthrough */
             case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24;
+                    /* fallthrough */
             case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16;
+                    /* fallthrough */
             case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) <<  8;
+                    /* fallthrough */
             default:;
         }
         contain32 = ((const BYTE*)srcBuffer)[srcSize-1];
@@ -1330,6 +1336,8 @@ static const U32 ZSTD_magicNumber = 0xFD2FB51E;   /* 3rd version : seqNb header
 #define LITERAL_NOENTROPY 63
 #define COMMAND_NOENTROPY 7   /* to remove */
 
+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+
 static const size_t ZSTD_blockHeaderSize = 3;
 static const size_t ZSTD_frameHeaderSize = 4;
 
@@ -1458,7 +1466,7 @@ unsigned ZSTDv01_isError(size_t code) { return ERR_isError(code); }
 *   Decompression code
 **************************************************************/
 
-size_t ZSTDv01_getcBlockSize(const void* src, size_t srcSize, blockProperties_t* bpPtr)
+static size_t ZSTDv01_getcBlockSize(const void* src, size_t srcSize, blockProperties_t* bpPtr)
 {
     const BYTE* const in = (const BYTE* const)src;
     BYTE headerFlags;
@@ -1511,7 +1519,7 @@ static size_t ZSTD_decompressLiterals(void* ctx,
 }
 
 
-size_t ZSTDv01_decodeLiteralsBlock(void* ctx,
+static size_t ZSTDv01_decodeLiteralsBlock(void* ctx,
                                 void* dst, size_t maxDstSize,
                           const BYTE** litStart, size_t* litSize,
                           const void* src, size_t srcSize)
@@ -1563,7 +1571,7 @@ size_t ZSTDv01_decodeLiteralsBlock(void* ctx,
 }
 
 
-size_t ZSTDv01_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumpsLengthPtr,
+static size_t ZSTDv01_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumpsLengthPtr,
                          FSE_DTable* DTableLL, FSE_DTable* DTableML, FSE_DTable* DTableOffb,
                          const void* src, size_t srcSize)
 {
@@ -1751,7 +1759,7 @@ static size_t ZSTD_execSequence(BYTE* op,
                                 BYTE* const base, BYTE* const oend)
 {
     static const int dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* substracted */
+    static const int dec64table[] = {8, 8, 8, 7, 8, 9,10,11};   /* subtracted */
     const BYTE* const ostart = op;
     const size_t litLength = sequence.litLength;
     BYTE* const endMatch = op + litLength + sequence.matchLength;    /* risk : address space overflow (32-bits) */
@@ -1993,36 +2001,59 @@ size_t ZSTDv01_decompress(void* dst, size_t maxDstSize, const void* src, size_t
     return ZSTDv01_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
 }
 
-size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t srcSize)
+/* ZSTD_errorFrameSizeInfoLegacy() :
+   assumes `cSize` and `dBound` are _not_ NULL */
+static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
+{
+    *cSize = ret;
+    *dBound = ZSTD_CONTENTSIZE_ERROR;
+}
+
+void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
 {
     const BYTE* ip = (const BYTE*)src;
     size_t remainingSize = srcSize;
+    size_t nbBlocks = 0;
     U32 magicNumber;
     blockProperties_t blockProperties;
 
     /* Frame Header */
-    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+        return;
+    }
     magicNumber = ZSTD_readBE32(src);
-    if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
+    if (magicNumber != ZSTD_magicNumber) {
+        ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
+        return;
+    }
     ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;
 
     /* Loop on each block */
     while (1)
     {
         size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties);
-        if (ZSTDv01_isError(blockSize)) return blockSize;
+        if (ZSTDv01_isError(blockSize)) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, blockSize);
+            return;
+        }
 
         ip += ZSTD_blockHeaderSize;
         remainingSize -= ZSTD_blockHeaderSize;
-        if (blockSize > remainingSize) return ERROR(srcSize_wrong);
+        if (blockSize > remainingSize) {
+            ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
+            return;
+        }
 
         if (blockSize == 0) break;   /* bt_end */
 
         ip += blockSize;
         remainingSize -= blockSize;
+        nbBlocks++;
     }
 
-    return ip - (const BYTE*)src;
+    *cSize = ip - (const BYTE*)src;
+    *dBound = nbBlocks * BLOCKSIZE;
 }
 
 /*******************************