extzstd 0.1 → 0.1.1

data/contrib/zstd/{dictBuilder → lib/dictBuilder}/zdict.c

@@ -36,12 +36,11 @@
 #include <time.h>          /* clock */
 
 #include "mem.h"           /* read */
-#include "error_private.h"
 #include "fse.h"           /* FSE_normalizeCount, FSE_writeNCount */
 #define HUF_STATIC_LINKING_ONLY
-#include "huf.h"
+#include "huf.h"           /* HUF_buildCTable, HUF_writeCTable */
 #include "zstd_internal.h" /* includes zstd.h */
-#include "xxhash.h"
+#include "xxhash.h"        /* XXH64 */
 #include "divsufsort.h"
 #ifndef ZDICT_STATIC_LINKING_ONLY
 #  define ZDICT_STATIC_LINKING_ONLY
@@ -61,7 +60,7 @@
 #define NOISELENGTH 32
 
 #define MINRATIO 4
-static const int g_compressionLevel_default = 5;
+static const int g_compressionLevel_default = 6;
 static const U32 g_selectivity_default = 9;
 static const size_t g_provision_entropySize = 200;
 static const size_t g_min_fast_dictContent = 192;
@@ -307,13 +306,13 @@ static dictItem ZDICT_analyzePos(
         } while (length >=MINMATCHLENGTH);
 
         /* look backward */
-		length = MINMATCHLENGTH;
-		while ((length >= MINMATCHLENGTH) & (start > 0)) {
-			length = ZDICT_count(b + pos, b + suffix[start - 1]);
-			if (length >= LLIMIT) length = LLIMIT - 1;
-			lengthList[length]++;
-			if (length >= MINMATCHLENGTH) start--;
-		}
+        length = MINMATCHLENGTH;
+        while ((length >= MINMATCHLENGTH) & (start > 0)) {
+        	length = ZDICT_count(b + pos, b + suffix[start - 1]);
+        	if (length >= LLIMIT) length = LLIMIT - 1;
+        	lengthList[length]++;
+        	if (length >= MINMATCHLENGTH) start--;
+        }
 
         /* largest useful length */
         memset(cumulLength, 0, sizeof(cumulLength));
@@ -570,7 +569,7 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
             if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
     }
     cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize);
-    if (ZSTD_isError(cSize)) { DISPLAYLEVEL(1, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
+    if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
 
     if (cSize) {  /* if == 0; block is not compressible */
         const seqStore_t* seqStorePtr = ZSTD_getSeqStore(esr.zc);
@@ -825,6 +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)
@@ -898,12 +946,14 @@ size_t ZDICT_trainFromBuffer_unsafe(
         U32 const nb = MIN(25, dictList[0].pos);
         U32 const dictContentSize = ZDICT_dictSize(dictList);
         U32 u;
-        DISPLAYLEVEL(3, "\n %u segments found, of total size %u \n", dictList[0].pos, dictContentSize);
-        DISPLAYLEVEL(3, "list %u best segments \n", nb);
-        for (u=1; u<=nb; u++) {
-            U32 pos = dictList[u].pos;
-            U32 length = dictList[u].length;
-            U32 printedLength = MIN(40, length);
+        DISPLAYLEVEL(3, "\n %u segments found, of total size %u \n", dictList[0].pos-1, dictContentSize);
+        DISPLAYLEVEL(3, "list %u best segments \n", nb-1);
+        for (u=1; u<nb; u++) {
+            U32 const pos = dictList[u].pos;
+            U32 const length = dictList[u].length;
+            U32 const printedLength = MIN(40, length);
+            if ((pos > samplesBuffSize) || ((pos + length) > samplesBuffSize))
+                return ERROR(GENERIC);   /* should never happen */
             DISPLAYLEVEL(3, "%3u:%3u bytes at pos %8u, savings %7u bytes |",
                          u, length, pos, dictList[u].savings);
             ZDICT_printHex((const char*)samplesBuffer+pos, printedLength);

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

@@ -0,0 +1,201 @@
+/**
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of this source tree. An additional grant
+ * of patent rights can be found in the PATENTS file in the same directory.
+ */
+
+#ifndef DICTBUILDER_H_001
+#define DICTBUILDER_H_001
+
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+
+/*======  Dependencies  ======*/
+#include <stddef.h>  /* size_t */
+
+
+/* =====   ZDICTLIB_API : control library symbols visibility   ===== */
+#if defined(__GNUC__) && (__GNUC__ >= 4)
+#  define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default")))
+#else
+#  define ZDICTLIB_VISIBILITY
+#endif
+#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
+#  define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY
+#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1)
+#  define ZDICTLIB_API __declspec(dllimport) ZDICTLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+#  define ZDICTLIB_API ZDICTLIB_VISIBILITY
+#endif
+
+
+/*! ZDICT_trainFromBuffer() :
+    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`.
+    @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.
+           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);
+
+
+/*======   Helper functions   ======*/
+ZDICTLIB_API unsigned ZDICT_getDictID(const void* dictBuffer, size_t dictSize);  /**< extracts dictID; @return zero if error (not a valid dictionary) */
+ZDICTLIB_API unsigned ZDICT_isError(size_t errorCode);
+ZDICTLIB_API const char* ZDICT_getErrorName(size_t errorCode);
+
+
+
+#ifdef ZDICT_STATIC_LINKING_ONLY
+
+/* ====================================================================================
+ * The definitions in this section are considered experimental.
+ * They should never be used with a dynamic library, as they may change in the future.
+ * They are provided for advanced usages.
+ * Use them only in association with static linking.
+ * ==================================================================================== */
+
+typedef struct {
+    unsigned selectivityLevel;   /* 0 means default; larger => select more => larger dictionary */
+    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 */
+    unsigned reserved[2];        /* reserved space for future parameters */
+} ZDICT_params_t;
+
+
+/*! ZDICT_trainFromBuffer_advanced() :
+    Same as ZDICT_trainFromBuffer() with control over more parameters.
+    `parameters` is optional and can be provided with values set to 0 to mean "default".
+    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferSize`),
+              or an error code, which can be tested by ZDICT_isError().
+    note : ZDICT_trainFromBuffer_advanced() will send notifications into stderr if instructed to, using notificationLevel>0.
+*/
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
+                                const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                                ZDICT_params_t parameters);
+
+/*! COVER_params_t :
+    For all values 0 means default.
+    kMin and d are the only required parameters.
+*/
+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 nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
+    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;   /* 0 means default; target a specific zstd compression level */
+} COVER_params_t;
+
+
+/*! COVER_trainFromBuffer() :
+    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 : COVER_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.
+           It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+*/
+ZDICTLIB_API size_t COVER_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
+                              const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                              COVER_params_t parameters);
+
+/*! COVER_optimizeTrainFromBuffer() :
+    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`.
+
+    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 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].
+
+    @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.
+    Note : COVER_optimizeTrainFromBuffer() 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 COVER_optimizeTrainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
+                                     const void* samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
+                                     COVER_params_t *parameters);
+
+/*! ZDICT_finalizeDictionary() :
+
+    Given a custom content as a basis for dictionary, and a set of samples,
+    finalize dictionary by adding headers and statistics.
+
+    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.
+
+    dictContentSize must be > ZDICT_CONTENTSIZE_MIN bytes.
+    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().
+    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) ZDICTLIB_API   /* 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)]] ZDICTLIB_API
+#  elif (ZDICT_GCC_VERSION >= 405) || defined(__clang__)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message)))
+#  elif (ZDICT_GCC_VERSION >= 301)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated))
+#  elif defined(_MSC_VER)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __declspec(deprecated(message))
+#  else
+#    pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler")
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API
+#  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 */
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif   /* DICTBUILDER_H_001 */

data/contrib/zstd/{legacy → lib/legacy}/zstd_legacy.h

@@ -20,14 +20,33 @@ extern "C" {
 #include "mem.h"            /* MEM_STATIC */
 #include "error_private.h"  /* ERROR */
 #include "zstd.h"           /* ZSTD_inBuffer, ZSTD_outBuffer */
-#include "zstd_v01.h"
-#include "zstd_v02.h"
-#include "zstd_v03.h"
-#include "zstd_v04.h"
-#include "zstd_v05.h"
-#include "zstd_v06.h"
-#include "zstd_v07.h"
 
+#if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0)
+#  undef ZSTD_LEGACY_SUPPORT
+#  define ZSTD_LEGACY_SUPPORT 8
+#endif
+
+#if (ZSTD_LEGACY_SUPPORT <= 1)
+#  include "zstd_v01.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 2)
+#  include "zstd_v02.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 3)
+#  include "zstd_v03.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 4)
+#  include "zstd_v04.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
+#  include "zstd_v05.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
+#  include "zstd_v06.h"
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
+#  include "zstd_v07.h"
+#endif
 
 /** ZSTD_isLegacy() :
     @return : > 0 if supported by legacy decoder. 0 otherwise.
@@ -40,13 +59,27 @@ MEM_STATIC unsigned ZSTD_isLegacy(const void* src, size_t srcSize)
     magicNumberLE = MEM_readLE32(src);
     switch(magicNumberLE)
     {
+#if (ZSTD_LEGACY_SUPPORT <= 1)
         case ZSTDv01_magicNumberLE:return 1;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 2)
         case ZSTDv02_magicNumber : return 2;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 3)
         case ZSTDv03_magicNumber : return 3;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 4)
         case ZSTDv04_magicNumber : return 4;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
         case ZSTDv05_MAGICNUMBER : return 5;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
         case ZSTDv06_MAGICNUMBER : return 6;
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
         case ZSTDv07_MAGICNUMBER : return 7;
+#endif
         default : return 0;
     }
 }
@@ -56,24 +89,30 @@ MEM_STATIC unsigned long long ZSTD_getDecompressedSize_legacy(const void* src, s
 {
     U32 const version = ZSTD_isLegacy(src, srcSize);
     if (version < 5) return 0;  /* no decompressed size in frame header, or not a legacy format */
+#if (ZSTD_LEGACY_SUPPORT <= 5)
     if (version==5) {
         ZSTDv05_parameters fParams;
         size_t const frResult = ZSTDv05_getFrameParams(&fParams, src, srcSize);
         if (frResult != 0) return 0;
         return fParams.srcSize;
     }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
     if (version==6) {
         ZSTDv06_frameParams fParams;
         size_t const frResult = ZSTDv06_getFrameParams(&fParams, src, srcSize);
         if (frResult != 0) return 0;
         return fParams.frameContentSize;
     }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
     if (version==7) {
         ZSTDv07_frameParams fParams;
         size_t const frResult = ZSTDv07_getFrameParams(&fParams, src, srcSize);
         if (frResult != 0) return 0;
         return fParams.frameContentSize;
     }
+#endif
     return 0;   /* should not be possible */
 }
 
@@ -86,14 +125,23 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
     U32 const version = ZSTD_isLegacy(src, compressedSize);
     switch(version)
     {
+#if (ZSTD_LEGACY_SUPPORT <= 1)
         case 1 :
             return ZSTDv01_decompress(dst, dstCapacity, src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 2)
         case 2 :
             return ZSTDv02_decompress(dst, dstCapacity, src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 3)
         case 3 :
             return ZSTDv03_decompress(dst, dstCapacity, src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 4)
         case 4 :
             return ZSTDv04_decompress(dst, dstCapacity, src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
         case 5 :
             {   size_t result;
                 ZSTDv05_DCtx* const zd = ZSTDv05_createDCtx();
@@ -102,6 +150,8 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
                 ZSTDv05_freeDCtx(zd);
                 return result;
             }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
         case 6 :
             {   size_t result;
                 ZSTDv06_DCtx* const zd = ZSTDv06_createDCtx();
@@ -110,6 +160,8 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
                 ZSTDv06_freeDCtx(zd);
                 return result;
             }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
         case 7 :
             {   size_t result;
                 ZSTDv07_DCtx* const zd = ZSTDv07_createDCtx();
@@ -118,11 +170,50 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
                 ZSTDv07_freeDCtx(zd);
                 return result;
             }
+#endif
         default :
             return ERROR(prefix_unknown);
     }
 }
 
+MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src,
+                                             size_t compressedSize)
+{
+    U32 const version = ZSTD_isLegacy(src, compressedSize);
+    switch(version)
+    {
+#if (ZSTD_LEGACY_SUPPORT <= 1)
+        case 1 :
+            return ZSTDv01_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 2)
+        case 2 :
+            return ZSTDv02_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 3)
+        case 3 :
+            return ZSTDv03_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 4)
+        case 4 :
+            return ZSTDv04_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
+        case 5 :
+            return ZSTDv05_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
+        case 6 :
+            return ZSTDv06_findFrameCompressedSize(src, compressedSize);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
+        case 7 :
+            return ZSTDv07_findFrameCompressedSize(src, compressedSize);
+#endif
+        default :
+            return ERROR(prefix_unknown);
+    }
+}
 
 MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
 {
@@ -133,10 +224,18 @@ MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
         case 2 :
         case 3 :
             return ERROR(version_unsupported);
+#if (ZSTD_LEGACY_SUPPORT <= 4)
         case 4 : return ZBUFFv04_freeDCtx((ZBUFFv04_DCtx*)legacyContext);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
         case 5 : return ZBUFFv05_freeDCtx((ZBUFFv05_DCtx*)legacyContext);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
         case 6 : return ZBUFFv06_freeDCtx((ZBUFFv06_DCtx*)legacyContext);
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
         case 7 : return ZBUFFv07_freeDCtx((ZBUFFv07_DCtx*)legacyContext);
+#endif
     }
 }
 
@@ -152,6 +251,7 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
         case 2 :
         case 3 :
             return 0;
+#if (ZSTD_LEGACY_SUPPORT <= 4)
         case 4 :
         {
             ZBUFFv04_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv04_createDCtx() : (ZBUFFv04_DCtx*)*legacyContext;
@@ -161,6 +261,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
             *legacyContext = dctx;
             return 0;
         }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
         case 5 :
         {
             ZBUFFv05_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv05_createDCtx() : (ZBUFFv05_DCtx*)*legacyContext;
@@ -169,6 +271,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
             *legacyContext = dctx;
             return 0;
         }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
         case 6 :
         {
             ZBUFFv06_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv06_createDCtx() : (ZBUFFv06_DCtx*)*legacyContext;
@@ -177,6 +281,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
             *legacyContext = dctx;
             return 0;
         }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
         case 7 :
         {
             ZBUFFv07_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv07_createDCtx() : (ZBUFFv07_DCtx*)*legacyContext;
@@ -185,6 +291,7 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U
             *legacyContext = dctx;
             return 0;
         }
+#endif
     }
 }
 
@@ -200,6 +307,7 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
         case 2 :
         case 3 :
             return ERROR(version_unsupported);
+#if (ZSTD_LEGACY_SUPPORT <= 4)
         case 4 :
             {
                 ZBUFFv04_DCtx* dctx = (ZBUFFv04_DCtx*) legacyContext;
@@ -212,6 +320,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
                 input->pos += readSize;
                 return hintSize;
             }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 5)
         case 5 :
             {
                 ZBUFFv05_DCtx* dctx = (ZBUFFv05_DCtx*) legacyContext;
@@ -224,6 +334,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
                 input->pos += readSize;
                 return hintSize;
             }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 6)
         case 6 :
             {
                 ZBUFFv06_DCtx* dctx = (ZBUFFv06_DCtx*) legacyContext;
@@ -236,6 +348,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
                 input->pos += readSize;
                 return hintSize;
             }
+#endif
+#if (ZSTD_LEGACY_SUPPORT <= 7)
         case 7 :
             {
                 ZBUFFv07_DCtx* dctx = (ZBUFFv07_DCtx*) legacyContext;
@@ -248,6 +362,7 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version,
                 input->pos += readSize;
                 return hintSize;
             }
+#endif
     }
 }
 

data/contrib/zstd/{legacy → lib/legacy}/zstd_v01.c

@@ -1354,7 +1354,7 @@ static void   ZSTD_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
 
 #define COPY8(d,s)    { ZSTD_copy8(d,s); d+=8; s+=8; }
 
-static void ZSTD_wildcopy(void* dst, const void* src, size_t length)
+static void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length)
 {
     const BYTE* ip = (const BYTE*)src;
     BYTE* op = (BYTE*)dst;
@@ -1803,7 +1803,7 @@ static size_t ZSTD_execSequence(BYTE* op,
         } else { ZSTD_copy8(op, match); }
         op += 8; match += 8;
 
-        if (endMatch > oend-12)
+        if (endMatch > oend-(16-MINMATCH))
         {
             if (op < oend-8)
             {
@@ -1814,7 +1814,7 @@ static size_t ZSTD_execSequence(BYTE* op,
             while (op<endMatch) *op++ = *match++;
         }
         else
-            ZSTD_wildcopy(op, match, sequence.matchLength-8);   /* works even if matchLength < 8 */
+            ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8);   /* works even if matchLength < 8 */
 
         /* restore, in case of overlap */
         if (overlapRisk) memcpy(endMatch, saved, qutt);
@@ -1992,6 +1992,37 @@ 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)
+{
+    const BYTE* ip = (const BYTE*)src;
+    size_t remainingSize = srcSize;
+    U32 magicNumber;
+    blockProperties_t blockProperties;
+
+    /* Frame Header */
+    if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    magicNumber = ZSTD_readBE32(src);
+    if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
+    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;
+
+        ip += ZSTD_blockHeaderSize;
+        remainingSize -= ZSTD_blockHeaderSize;
+        if (blockSize > remainingSize) return ERROR(srcSize_wrong);
+
+        if (blockSize == 0) break;   /* bt_end */
+
+        ip += blockSize;
+        remainingSize -= blockSize;
+    }
+
+    return ip - (const BYTE*)src;
+}
 
 /*******************************
 *  Streaming Decompression API