1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257
|
/***********************************************************************
* © 2016 and later: Unicode, Inc. and others.
* License & terms of use: http://www.unicode.org/copyright.html
*
***********************************************************************
***********************************************************************
* COPYRIGHT:
* Copyright (C) 2001-2016 International Business Machines Corporation
* and others. All Rights Reserved.
*
***********************************************************************/
/********************************************************************************
*
* File ubrkperf.cpp
*
* Modification History:
* Name Description
* Vladimir Weinstein First Version, based on collperf
*
*********************************************************************************
*/
#include "cmemory.h"
#include "ubrkperf.h"
#include "uoptions.h"
#include <stdio.h>
#if 0
#if U_PLATFORM_IS_DARWIN_BASED
#include <ApplicationServices/ApplicationServices.h>
enum{
kUCTextBreakAllMask = (kUCTextBreakClusterMask | kUCTextBreakWordMask | kUCTextBreakLineMask)
};
UCTextBreakType breakTypes[4] = {kUCTextBreakCharMask, kUCTextBreakClusterMask, kUCTextBreakWordMask, kUCTextBreakLineMask};
TextBreakLocatorRef breakRef;
UCTextBreakType macBreakType;
void createMACBrkIt() {
OSStatus status = noErr;
LocaleRef lref;
status = LocaleRefFromLocaleString(opt_locale, &lref);
status = UCCreateTextBreakLocator(lref, 0, kUCTextBreakAllMask, (TextBreakLocatorRef*)&breakRef);
if(opt_char == true) {
macBreakType = kUCTextBreakClusterMask;
} else if(opt_word == true) {
macBreakType = kUCTextBreakWordMask;
} else if(opt_line == true) {
macBreakType = kUCTextBreakLineMask;
} else if(opt_sentence == true) {
// error
// brkit = BreakIterator::createSentenceInstance(opt_locale, status);
} else {
// default is character iterator
macBreakType = kUCTextBreakClusterMask;
}
}
#endif
void doForwardTest() {
if (opt_terse == false) {
printf("Doing the forward test\n");
}
int32_t noBreaks = 0;
int32_t i = 0;
unsigned long startTime = timeGetTime();
unsigned long elapsedTime = 0;
if(opt_icu) {
createICUBrkIt();
brkit->setText(text);
brkit->first();
if (opt_terse == false) {
printf("Warmup\n");
}
while(brkit->next() != BreakIterator::DONE) {
noBreaks++;
}
if (opt_terse == false) {
printf("Measure\n");
}
startTime = timeGetTime();
for(i = 0; i < opt_loopCount; i++) {
brkit->first();
while(brkit->next() != BreakIterator::DONE) {
}
}
elapsedTime = timeGetTime()-startTime;
} else if(opt_mac) {
#if U_PLATFORM_IS_DARWIN_BASED
createMACBrkIt();
UniChar* filePtr = text;
OSStatus status = noErr;
UniCharCount startOffset = 0, breakOffset = 0, numUniChars = textSize;
startOffset = 0;
//printf("\t---Search forward--\n");
while (startOffset < numUniChars)
{
status = UCFindTextBreak(breakRef, macBreakType, kUCTextBreakLeadingEdgeMask, filePtr, numUniChars,
startOffset, &breakOffset);
//require_action(status == noErr, EXIT, printf( "**UCFindTextBreak failed: startOffset %d, status %d\n", (int)startOffset, (int)status));
//require_action((breakOffset <= numUniChars),EXIT, printf("**UCFindTextBreak breakOffset too big: startOffset %d, breakOffset %d\n", (int)startOffset, (int)breakOffset));
// Output break
//printf("\t%d\n", (int)breakOffset);
// Increment counters
noBreaks++;
startOffset = breakOffset;
}
startTime = timeGetTime();
for(i = 0; i < opt_loopCount; i++) {
startOffset = 0;
while (startOffset < numUniChars)
{
status = UCFindTextBreak(breakRef, macBreakType, kUCTextBreakLeadingEdgeMask, filePtr, numUniChars,
startOffset, &breakOffset);
// Increment counters
startOffset = breakOffset;
}
}
elapsedTime = timeGetTime()-startTime;
UCDisposeTextBreakLocator(&breakRef);
#endif
}
if (opt_terse == false) {
int32_t loopTime = (int)(float(1000) * ((float)elapsedTime/(float)opt_loopCount));
int32_t timePerCU = (int)(float(1000) * ((float)loopTime/(float)textSize));
int32_t timePerBreak = (int)(float(1000) * ((float)loopTime/(float)noBreaks));
printf("forward break iteration average loop time %d\n", loopTime);
printf("number of code units %d average time per code unit %d\n", textSize, timePerCU);
printf("number of breaks %d average time per break %d\n", noBreaks, timePerBreak);
} else {
printf("time=%d\nevents=%d\nsize=%d\n", elapsedTime, noBreaks, textSize);
}
}
#endif
UPerfFunction* BreakIteratorPerformanceTest::TestICUForward()
{
return new ICUForward(locale, m_mode_, m_file_, m_fileLen_);
}
UPerfFunction* BreakIteratorPerformanceTest::TestICUIsBound()
{
return new ICUIsBound(locale, m_mode_, m_file_, m_fileLen_);
}
UPerfFunction* BreakIteratorPerformanceTest::TestDarwinForward()
{
return nullptr;
}
UPerfFunction* BreakIteratorPerformanceTest::TestDarwinIsBound()
{
return nullptr;
}
UPerfFunction* BreakIteratorPerformanceTest::runIndexedTest(int32_t index, UBool exec,
const char *&name,
char* par)
{
switch (index) {
TESTCASE(0, TestICUForward);
TESTCASE(1, TestICUIsBound);
TESTCASE(2, TestDarwinForward);
TESTCASE(3, TestDarwinIsBound);
default:
name = "";
return nullptr;
}
return nullptr;
}
UOption options[]={
UOPTION_DEF( "mode", 'm', UOPT_REQUIRES_ARG)
};
BreakIteratorPerformanceTest::BreakIteratorPerformanceTest(int32_t argc, const char* argv[], UErrorCode& status)
: UPerfTest(argc,argv,status),
m_mode_(nullptr),
m_file_(nullptr),
m_fileLen_(0)
{
_remainingArgc = u_parseArgs(_remainingArgc, const_cast<char**>(argv), UPRV_LENGTHOF(options), options);
if(options[0].doesOccur) {
m_mode_ = options[0].value;
switch(options[0].value[0]) {
case 'w' :
case 'c' :
case 's' :
case 'l' :
break;
default:
status = U_ILLEGAL_ARGUMENT_ERROR;
break;
}
} else {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
m_file_ = getBuffer(m_fileLen_, status);
if(status== U_ILLEGAL_ARGUMENT_ERROR){
fprintf(stderr, gUsageString, "ubrkperf");
fprintf(stderr, "\t-m or --mode Required mode for breakiterator: char, word, line or sentence\n");
return;
}
if(U_FAILURE(status)){
fprintf(stderr, "FAILED to create UPerfTest object. Error: %s\n", u_errorName(status));
return;
}
}
BreakIteratorPerformanceTest::~BreakIteratorPerformanceTest()
{
}
//----------------------------------------------------------------------------------------
//
// Main -- process command line, read in and pre-process the test file,
// call other functions to do the actual tests.
//
//----------------------------------------------------------------------------------------
int main(int argc, const char** argv) {
UErrorCode status = U_ZERO_ERROR;
BreakIteratorPerformanceTest test(argc, argv, status);
if(U_FAILURE(status)){
return status;
}
if(test.run()==false){
fprintf(stderr,"FAILED: Tests could not be run please check the arguments.\n");
return -1;
}
return 0;
}
|