introduced ext_wksp variants of count to reduce stack memory usage

lib/common/fse.h

@@ -294,8 +294,31 @@ If there is an error, the function will return an error code, which can be teste
 /* *****************************************
 *  FSE advanced API
 *******************************************/
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned
+ */
+size_t FSE_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                 const void* source, size_t sourceSize, unsigned* workSpace);
+
+/** FSE_countFast() :
+ *  same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr
+ */
 size_t FSE_countFast(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
-/**< same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr  */
+
+/* FSE_countFast_wksp() :
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` must be a table of minimum `1024` unsigned
+ */
+size_t FSE_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned* workSpace);
+
+/*! FSE_count_simple
+ * Same as FSE_countFast(), but does not use any additional memory (not even on stack).
+ * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`).
+*/
+size_t FSE_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
+
+
 
 unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
 /**< same as FSE_optimalTableLog(), which used `minus==2` */
@@ -334,13 +357,9 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 *******************************************/
 /*!
    This API consists of small unitary functions, which highly benefit from being inlined.
-   You will want to enable link-time-optimization to ensure these functions are properly inlined in your binary.
-   Visual seems to do it automatically.
-   For gcc or clang, you'll need to add -flto flag at compilation and linking stages.
-   If none of these solutions is applicable, include "fse.c" directly.
+   Hence their body are included in next section.
 */
-typedef struct
-{
+typedef struct {
     ptrdiff_t   value;
     const void* stateTable;
     const void* symbolTT;
@@ -400,8 +419,7 @@ If there is an error, it returns an errorCode (which can be tested using FSE_isE
 /* *****************************************
 *  FSE symbol decompression API
 *******************************************/
-typedef struct
-{
+typedef struct {
     size_t      state;
     const void* table;   /* precise table may vary, depending on U16 */
 } FSE_DState_t;

lib/common/huf.h

@@ -90,6 +90,11 @@ const char* HUF_getErrorName(size_t code);   /**< provides error code string (us
 *   Same as HUF_compress(), but offers direct control over `maxSymbolValue` and `tableLog` */
 size_t HUF_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
 
+/** HUF_compress4X_wksp() :
+*   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of <= 1024 unsigned */
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, unsigned* workSpace);
+
+
 
 #ifdef HUF_STATIC_LINKING_ONLY
 
@@ -208,12 +213,13 @@ size_t HUF_decompress4X4_usingDTable(void* dst, size_t maxDstSize, const void* c
 /* single stream variants */
 
 size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, unsigned* workSpace);  /**< `workSpace` must be a table of at least 1024 unsigned */
 size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
 
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
 
-size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /**< automatic selection of sing or double symbol decoder, based on DTable */
 size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
 size_t HUF_decompress1X4_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);