VOL-1967 move api-server to separate repository
Change-Id: I21b85be74205805be15f8a85e53a903d16785671
diff --git a/vendor/github.com/DataDog/zstd/zdict.h b/vendor/github.com/DataDog/zstd/zdict.h
index ad459c2..37978ec 100644
--- a/vendor/github.com/DataDog/zstd/zdict.h
+++ b/vendor/github.com/DataDog/zstd/zdict.h
@@ -39,20 +39,27 @@
/*! ZDICT_trainFromBuffer():
* Train a dictionary from an array of samples.
- * Redirect towards ZDICT_optimizeTrainFromBuffer_cover() single-threaded, with d=8 and steps=4.
+ * 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.
+ * 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 ======*/
@@ -84,11 +91,27 @@
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 */
+ unsigned shrinkDict; /* Train dictionaries to shrink in size starting from the minimum size and selects the smallest dictionary that is shrinkDictMaxRegression% worse than the largest dictionary. 0 means no shrinking and 1 means shrinking */
+ unsigned shrinkDictMaxRegression; /* Sets shrinkDictMaxRegression so that a smaller dictionary can be at worse shrinkDictMaxRegression% worse than the max dict size dictionary. */
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) */
+ unsigned shrinkDict; /* Train dictionaries to shrink in size starting from the minimum size and selects the smallest dictionary that is shrinkDictMaxRegression% worse than the largest dictionary. 0 means no shrinking and 1 means shrinking */
+ unsigned shrinkDictMaxRegression; /* Sets shrinkDictMaxRegression so that a smaller dictionary can be at worse shrinkDictMaxRegression% worse than the max dict size dictionary. */
+
+ ZDICT_params_t zParams;
+} ZDICT_fastCover_params_t;
/*! ZDICT_trainFromBuffer_cover():
* Train a dictionary from an array of samples using the COVER algorithm.
@@ -97,6 +120,7 @@
* 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_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`.
@@ -115,13 +139,14 @@
* 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(
@@ -129,6 +154,50 @@
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,
* finalize dictionary by adding headers and statistics.
@@ -140,7 +209,7 @@
* 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
*/
@@ -164,6 +233,7 @@
* `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().
+ * 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.