changed API comments to invite using macro ZSTD_CONTENTSIZE_UNKNOWN

to mean "pledgedSrcSize is not known at init time" instead of `0`.
Note that, a few prototypes created and documented with `0` to mean "unknown" still interpret "0" as unknown,
to avoid breaking 3rd party applications which depend on this behavior.
But this value is no longer recommended to mean "unknown".

In some future version, it might be possible to switch "0" to mean "empty",
as is already the case for several prototypes.
The advantage is that pledgedSrcSize field would have same behavior accross entire API,
making it easier to reason about.

Note that all concerned prototypes belong to the "experimental" API section.

srcSize is controlled at end of compression,
so if someone uses "0" to mean "unknown" while it effectively means "empty",
this is immediately caught by the compression function, which generates an error code : ZSTD_ERROR_srcSize_wrong

diff --git a/doc/zstd_manual.html b/doc/zstd_manual.html
index b4720adac2638256c90b323dc26c9329ea652a4b..7ef86a23dba16b172f80ed5f98229d93e3253373 100644 (file)
--- a/doc/zstd_manual.html
+++ b/doc/zstd_manual.html
@@ -631,10 +631,10 @@ size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMet
 
 <h3>Advanced Streaming compression functions</h3><pre></pre><b><pre>ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
 ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize);    </b>/**< same as ZSTD_initStaticCCtx() */<b>
-size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   </b>/**< pledgedSrcSize must be correct, a size of 0 means unknown.  for a frame size of 0 use initCStream_advanced */<b>
+size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   </b>/**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, a size of 0 is interepreted as "unknown". But it may change in some future version to mean "empty". */<b>
 size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); </b>/**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/<b>
 size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
-                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  </b>/**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */<b>
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  </b>/**< pledgedSrcSize : If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */<b>
 size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  </b>/**< note : cdict will just be referenced, and must outlive compression session */<b>
 size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  </b>/**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */<b>
 </pre></b><BR>
@@ -642,9 +642,11 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict*
 </b><p>  start a new compression job, using same parameters from previous job.
   This is typically useful to skip dictionary loading stage, since it will re-use it in-place..
   Note that zcs must be init at least once before using ZSTD_resetCStream().
-  pledgedSrcSize==0 means "srcSize unknown".
+  If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN.
   If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end.
-  @return : 0, or an error code (which can be tested using ZSTD_isError()) 
+  For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs,
+  but it may change to mean "empty" in some future version, so prefer using macro ZSTD_CONTENTSIZE_UNKNOWN.
+ @return : 0, or an error code (which can be tested using ZSTD_isError()) 
 </p></pre><BR>
 
 <h3>Advanced Streaming decompression functions</h3><pre></pre><b><pre>ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem);
@@ -693,10 +695,10 @@ size_t ZSTD_resetDStream(ZSTD_DStream* zds);  </b>/**< re-use decompression para
 
 <h3>Buffer-less streaming compression functions</h3><pre></pre><b><pre>size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
 size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
-size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); </b>/**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */<b>
+size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); </b>/**< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */<b>
 size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); </b>/**< note: fails if cdict==NULL */<b>
-size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize);   </b>/* compression parameters are already set within cdict. pledgedSrcSize=0 means null-size */<b>
-size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); </b>/**<  note: if pledgedSrcSize can be 0, indicating unknown size.  if it is non-zero, it must be accurate.  for 0 size frames, use compressBegin_advanced */<b>
+size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize);   </b>/* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */<b>
+size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); </b>/**<  note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */<b>
 </pre></b><BR>
 <a name="Chapter19"></a><h2>Buffer-less streaming decompression (synchronous mode)</h2><pre>
   A ZSTD_DCtx object is required to track streaming operations.
@@ -848,11 +850,11 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long
                               * Special: value 0 means "do not change strategy". */
 
     </b>/* frame parameters */<b>
-    ZSTD_p_contentSizeFlag=200, </b>/* Content size is written into frame header _whenever known_ (default:1)<b>
-                              * note that content size must be known at the beginning,
-                              * it is sent using ZSTD_CCtx_setPledgedSrcSize() */
+    ZSTD_p_contentSizeFlag=200, </b>/* Content size will be written into frame header _whenever known_ (default:1)<b>
+                              * Content size must be known at the beginning of compression,
+                              * it is provided using ZSTD_CCtx_setPledgedSrcSize() */
     ZSTD_p_checksumFlag,     </b>/* A 32-bits checksum of content is written at end of frame (default:0) */<b>
-    ZSTD_p_dictIDFlag,       </b>/* When applicable, dictID of dictionary is provided in frame header (default:1) */<b>
+    ZSTD_p_dictIDFlag,       </b>/* When applicable, dictionary's ID is written into frame header (default:1) */<b>
 
     </b>/* multi-threading parameters */<b>
     ZSTD_p_nbThreads=400,    </b>/* Select how many threads a compression job can spawn (default:1)<b>
@@ -913,7 +915,7 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long
  @result : 0, or an error code (which can be tested with ZSTD_isError()).
   Note 1 : 0 means zero, empty.
            In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
-           Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
+           ZSTD_CONTENTSIZE_UNKNOWN is default value for any new compression job.
   Note 2 : If all data is provided and consumed in a single round,
            this value is overriden by srcSize instead. 
 </p></pre><BR>

diff --git a/lib/zstd.h b/lib/zstd.h
index 2866866be043037a8a0be5ef0a2ce2a651931cce..e9c4ff9d4f8601eaa7033d9919e6a5ac092cd724 100644 (file)
--- a/lib/zstd.h
+++ b/lib/zstd.h
@@ -731,10 +731,10 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
 /*=====   Advanced Streaming compression functions  =====*/
 ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
 ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize);    /**< same as ZSTD_initStaticCCtx() */
-ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct, a size of 0 means unknown.  for a frame size of 0 use initCStream_advanced */
+ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, a size of 0 is interepreted as "unknown". But it may change in some future version to mean "empty". */
 ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/
 ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
-                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize is optional: it can be 0, which means "unknown" if contentSizeFlag is set, or "unknown" if contentSizeFlag is not set. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize : If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */
 ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  /**< note : cdict will just be referenced, and must outlive compression session */
 ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
 
@@ -742,9 +742,11 @@ ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const
  *  start a new compression job, using same parameters from previous job.
  *  This is typically useful to skip dictionary loading stage, since it will re-use it in-place..
  *  Note that zcs must be init at least once before using ZSTD_resetCStream().
- *  pledgedSrcSize==0 means "srcSize unknown".
+ *  If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN.
  *  If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end.
- *  @return : 0, or an error code (which can be tested using ZSTD_isError()) */
+ *  For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs,
+ *  but it may change to mean "empty" in some future version, so prefer using macro ZSTD_CONTENTSIZE_UNKNOWN.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
 ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
 
 
@@ -800,10 +802,10 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);  /**< re-use decompress
 /*=====   Buffer-less streaming compression functions  =====*/
 ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
 ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
-ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */
+ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */
 ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /**< note: fails if cdict==NULL */
-ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize);   /* compression parameters are already set within cdict. pledgedSrcSize=0 means null-size */
-ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**<  note: if pledgedSrcSize can be 0, indicating unknown size.  if it is non-zero, it must be accurate.  for 0 size frames, use compressBegin_advanced */
+ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize);   /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */
+ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**<  note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */
 
 ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
@@ -1066,7 +1068,7 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param
  * @result : 0, or an error code (which can be tested with ZSTD_isError()).
  *  Note 1 : 0 means zero, empty.
  *           In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
- *           Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
+ *           ZSTD_CONTENTSIZE_UNKNOWN is default value for any new compression job.
  *  Note 2 : If all data is provided and consumed in a single round,
  *           this value is overriden by srcSize instead. */
 ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);