Fix deallocation problem and add documentation
This commit is contained in:
parent
e6fe405838
commit
896ff0644a
@ -241,3 +241,10 @@ sampleInfo* getSampleInfo(const char** fileNamesTable, unsigned nbFiles, size_t
|
||||
|
||||
return info;
|
||||
}
|
||||
|
||||
|
||||
void freeSampleInfo(sampleInfo *info) {
|
||||
if (info->samplesSizes) free((void*)(info->samplesSizes));
|
||||
if (info->srcBuffer) free((void*)(info->srcBuffer));
|
||||
free(info);
|
||||
}
|
||||
|
@ -26,8 +26,25 @@ typedef struct {
|
||||
}sampleInfo;
|
||||
|
||||
|
||||
|
||||
/*! getSampleInfo():
|
||||
* Load from input files and add samples to buffer
|
||||
* @return: a sampleInfo struct containing infomation about buffer where samples are stored,
|
||||
* size of each sample, and total number of samples
|
||||
*/
|
||||
sampleInfo* getSampleInfo(const char** fileNamesTable, unsigned nbFiles, size_t chunkSize,
|
||||
unsigned maxDictSize, const unsigned displayLevel);
|
||||
|
||||
|
||||
|
||||
/*! freeSampleInfo():
|
||||
* Free memory allocated for info
|
||||
*/
|
||||
void freeSampleInfo(sampleInfo *info);
|
||||
|
||||
|
||||
|
||||
/*! saveDict():
|
||||
* Save data stored on buff to dictFileName
|
||||
*/
|
||||
void saveDict(const char* dictFileName, const void* buff, size_t buffSize);
|
||||
|
@ -46,7 +46,6 @@ static UTIL_time_t g_displayClock = UTIL_TIME_INITIALIZER;
|
||||
***************************************/
|
||||
static const unsigned g_defaultMaxDictSize = 110 KB;
|
||||
#define DEFAULT_CLEVEL 3
|
||||
#define DEFAULT_INPUTFILE ""
|
||||
#define DEFAULT_k 200
|
||||
#define DEFAULT_OUTPUTFILE "defaultDict"
|
||||
#define DEFAULT_DICTID 0
|
||||
@ -135,30 +134,29 @@ int main(int argCount, const char* argv[])
|
||||
const char* programName = argv[0];
|
||||
int operationResult = 0;
|
||||
|
||||
char* inputFile = DEFAULT_INPUTFILE;
|
||||
/* Initialize arguments to default values */
|
||||
unsigned k = DEFAULT_k;
|
||||
char* outputFile = DEFAULT_OUTPUTFILE;
|
||||
const char* outputFile = DEFAULT_OUTPUTFILE;
|
||||
unsigned dictID = DEFAULT_DICTID;
|
||||
unsigned maxDictSize = g_defaultMaxDictSize;
|
||||
|
||||
/* Initialize table to store input files */
|
||||
const char** filenameTable = (const char**)malloc(argCount * sizeof(const char*));
|
||||
unsigned filenameIdx = 0;
|
||||
|
||||
/* Parse arguments */
|
||||
for (int i = 1; i < argCount; i++) {
|
||||
const char* argument = argv[i];
|
||||
if (longCommandWArg(&argument, "k=")) { k = readU32FromChar(&argument); continue; }
|
||||
if (longCommandWArg(&argument, "dictID=")) { dictID = readU32FromChar(&argument); continue; }
|
||||
if (longCommandWArg(&argument, "maxdict=")) { maxDictSize = readU32FromChar(&argument); continue; }
|
||||
if (longCommandWArg(&argument, "in=")) {
|
||||
inputFile = malloc(strlen(argument) + 1);
|
||||
strcpy(inputFile, argument);
|
||||
filenameTable[filenameIdx] = inputFile;
|
||||
filenameTable[filenameIdx] = argument;
|
||||
filenameIdx++;
|
||||
continue;
|
||||
}
|
||||
if (longCommandWArg(&argument, "out=")) {
|
||||
outputFile = malloc(strlen(argument) + 1);
|
||||
strcpy(outputFile, argument);
|
||||
outputFile = argument;
|
||||
continue;
|
||||
}
|
||||
DISPLAYLEVEL(1, "Incorrect parameters\n");
|
||||
@ -168,7 +166,7 @@ int main(int argCount, const char* argv[])
|
||||
|
||||
char* fileNamesBuf = NULL;
|
||||
unsigned fileNamesNb = filenameIdx;
|
||||
int followLinks = 0;
|
||||
int followLinks = 0; /* follow directory recursively */
|
||||
const char** extendedFileList = NULL;
|
||||
extendedFileList = UTIL_createFileList(filenameTable, filenameIdx, &fileNamesBuf,
|
||||
&fileNamesNb, followLinks);
|
||||
@ -194,5 +192,9 @@ int main(int argCount, const char* argv[])
|
||||
filenameIdx, blockSize, maxDictSize, zParams.notificationLevel);
|
||||
operationResult = RANDOM_trainFromFiles(outputFile, info, maxDictSize, ¶ms);
|
||||
|
||||
/* Free allocated memory */
|
||||
UTIL_freeFileList(extendedFileList, fileNamesBuf);
|
||||
freeSampleInfo(info);
|
||||
|
||||
return operationResult;
|
||||
}
|
||||
|
@ -113,15 +113,8 @@ static size_t RANDOM_buildDictionary(const size_t totalSamplesSize, const BYTE *
|
||||
}
|
||||
|
||||
|
||||
/*! ZDICT_trainFromBuffer_random():
|
||||
* Train a dictionary from an array of samples using the RANDOM 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().
|
||||
*/
|
||||
|
||||
|
||||
ZDICTLIB_API size_t ZDICT_trainFromBuffer_random(
|
||||
void *dictBuffer, size_t dictBufferCapacity,
|
||||
const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
|
||||
|
@ -23,7 +23,14 @@ typedef struct {
|
||||
} ZDICT_random_params_t;
|
||||
|
||||
|
||||
|
||||
/*! ZDICT_trainFromBuffer_random():
|
||||
* 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().
|
||||
*/
|
||||
ZDICTLIB_API size_t ZDICT_trainFromBuffer_random( void *dictBuffer, size_t dictBufferCapacity,
|
||||
const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
|
||||
ZDICT_random_params_t parameters);
|
||||
|
Loading…
Reference in New Issue
Block a user