added : dictID retrieval functions.

added : unit tests for dictID retrieval functions

diff --git a/NEWS b/NEWS
index 5808895424a5f75ebeea626fe819507093f26095..127d1ac8fdc00cf8bc20b0b25d7b20850a42dcd5 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -7,6 +7,8 @@ cli : fixed : status displays total amount decoded, even for file consisting of
 cli : fixed : zstdcat
 API : changed : zbuff prototypes now generate deprecation warnings
 API : changed : streaming decompression implicit reset on starting new frame
+API : added experimental : dictID retrieval functions
+zlib_wrapper : added support for gz* functions, by Przemyslaw Skibinski
 Changed : reduced stack memory use
 
 v1.1.1

diff --git a/lib/decompress/zstd_decompress.c b/lib/decompress/zstd_decompress.c
index 7c4f54bd31ca75bf52824a00ff4c9b77f70f7258..1b235ed6d2c21087df805d66ba1300b5ff316282 100644 (file)
--- a/lib/decompress/zstd_decompress.c
+++ b/lib/decompress/zstd_decompress.c
@@ -1778,6 +1778,45 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
     return sizeof(*ddict) + sizeof(ddict->refContext) + ddict->dictSize;
 }
 
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
+{
+    if (dictSize < 8) return 0;
+    if (MEM_readLE32(dict) != ZSTD_DICT_MAGIC) return 0;
+    return MEM_readLE32((const char*)dict + 4);
+}
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;
+    return ZSTD_getDictID_fromDict(ddict->dict, ddict->dictSize);
+}
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompressed the frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary to be decoded (most common case).
+ *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */
+unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize)
+{
+    ZSTD_frameParams zfp;
+    size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize);
+    if (ZSTD_isError(hError)) return 0;
+    return zfp.dictID;
+}
+
 
 /*! ZSTD_decompress_usingDDict() :
 *   Decompression using a pre-digested Dictionary

diff --git a/lib/zstd.h b/lib/zstd.h
index b7a8bb989df4fd9891e67d5ff470ed23e82e780b..a1b0e62bcd39155ff767f0f856fdd461e1e146ec 100644 (file)
--- a/lib/zstd.h
+++ b/lib/zstd.h
@@ -462,6 +462,30 @@ ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
  *  Gives the amount of memory used by a given ZSTD_DDict */
 ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompressed the frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary to be decoded (most common case).
+ *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */
+unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+
 
 /********************************************************************
 *  Advanced streaming functions

diff --git a/tests/fuzzer.c b/tests/fuzzer.c
index f8110498d4a2e8e6ea33605ee02180f91f52c7c8..1c1ae470ae07432f915020d2b222a4baa82bd2fa 100644 (file)
--- a/tests/fuzzer.c
+++ b/tests/fuzzer.c
@@ -27,7 +27,7 @@
 #include <time.h>         /* clock_t */
 #define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_compressContinue, ZSTD_compressBlock */
 #include "zstd.h"         /* ZSTD_VERSION_STRING */
-#include "zstd_errors.h" /* ZSTD_getErrorCode */
+#include "zstd_errors.h"  /* ZSTD_getErrorCode */
 #include "zdict.h"        /* ZDICT_trainFromBuffer */
 #include "datagen.h"      /* RDG_genBuffer */
 #include "mem.h"
@@ -273,6 +273,18 @@ static int basicUnitTests(U32 seed, double compressibility)
         if (ZSTD_isError(cSize)) goto _output_error;
         DISPLAYLEVEL(4, "OK (%u bytes : %.2f%%)\n", (U32)cSize, (double)cSize/CNBuffSize*100);
 
+        DISPLAYLEVEL(4, "test%3i : retrieve dictID from dictionary : ", testNb++);
+        {   U32 const dictID = ZSTD_getDictID_fromDict(dictBuffer, dictSize);
+            if (dictID != 0) goto _output_error;   /* non-conformant (content-only) dictionary */
+        }
+        DISPLAYLEVEL(4, "OK \n");
+
+        DISPLAYLEVEL(4, "test%3i : retrieve dictID from frame : ", testNb++);
+        {   U32 const dictID = ZSTD_getDictID_fromFrame(compressedBuffer, cSize);
+            if (dictID != 0) goto _output_error;   /* non-conformant (content-only) dictionary */
+        }
+        DISPLAYLEVEL(4, "OK \n");
+
         DISPLAYLEVEL(4, "test%3i : frame built with dictionary should be decompressible : ", testNb++);
         CHECKPLUS(r, ZSTD_decompress_usingDict(dctx,
                                        decodedBuffer, CNBuffSize,