void StringUtilTest::testConvertStringToNumber(){
StringUtil sUtil;
//check passing in null returns -1
CPPUNIT_ASSERT(sUtil.convertStringToNumber(NULL) == -1);
//check passing string with a number in it
CPPUNIT_ASSERT(sUtil.convertStringToNumber("2343") == 2343);
//check passing string with % at end
CPPUNIT_ASSERT(sUtil.convertStringToNumber("1233%") == 1233);
CPPUNIT_ASSERT(sUtil.convertStringToNumber("1233 %") == 1233);
//check passing string with % at front
CPPUNIT_ASSERT(sUtil.convertStringToNumber("%22") == 0);
//check passing non numeric string
CPPUNIT_ASSERT(sUtil.convertStringToNumber("apple") == 0);
//check passing in NA
CPPUNIT_ASSERT(sUtil.convertStringToNumber("NA") == -2);
//check passing in number with characters in it
CPPUNIT_ASSERT(sUtil.convertStringToNumber("234A234") == 234);
//check passing in number too large
CPPUNIT_ASSERT(sUtil.convertStringToNumber("99999999999999999999999999999999999999999999") == -3);
}
void StringUtilTest::testSplitNullArgs(){
StringUtil sUtil;
//test null arguments
std::list<std::string> sList = sUtil.split(NULL,NULL);
CPPUNIT_ASSERT(sList.empty() == true);
sList = sUtil.split("blah",NULL);
CPPUNIT_ASSERT(sList.empty() == true);
sList = sUtil.split(NULL,"sdf");
CPPUNIT_ASSERT(sList.empty() == true);
}
int main(int argc, char** argv) {
// Create an instance of the Kytea program
Kytea kytea;
// Load a KyTea model from a model file
// this can be a binary or text model in any character encoding,
// it will be detected automatically
kytea.readModel("../../data/model.bin");
// Get the string utility class. This allows you to convert from
// the appropriate string encoding to Kytea's internal format
StringUtil* util = kytea.getStringUtil();
// Get the configuration class, this allows you to read or set the
// configuration for the analysis
KyteaConfig* config = kytea.getConfig();
// Map a plain text string to a KyteaString, and create a sentence object
KyteaString surface_string = util->mapString("これはテストです。");
KyteaSentence sentence(surface_string, util->normalize(surface_string));
// Find the word boundaries
kytea.calculateWS(sentence);
// Find the pronunciations for each tag level
for(int i = 0; i < config->getNumTags(); i++)
kytea.calculateTags(sentence,i);
// For each word in the sentence
const KyteaSentence::Words & words = sentence.words;
for(int i = 0; i < (int)words.size(); i++) {
// Print the word
cout << util->showString(words[i].surface);
// For each tag level
for(int j = 0; j < (int)words[i].tags.size(); j++) {
cout << "\t";
// Print each of its tags
for(int k = 0; k < (int)words[i].tags[j].size(); k++) {
cout << " " << util->showString(words[i].tags[j][k].first) <<
"/" << words[i].tags[j][k].second;
}
}
cout << endl;
}
cout << endl;
}
static void handing_text(std::string &line, std::map<std::string, std::size_t> &word_count) //文本处理，将大写转换成小写，去除标点符号
{
std::string word ;
std::istringstream sin(line);
StringUtil stringutil ;
while(sin >> word) //构成词库
{
stringutil.upperTolower(word); //大写转小写，去除标点符号
//统计单词的词频，去除重复词的存储
std::pair<std::map<std::string, std::size_t>::iterator, bool> ret =
word_count.insert(std::make_pair(word, 1));
if (!ret.second)
{
++ret.first->second;
}
}
sin.clear();
}
void CsvUtil::addFileData(const std::string &rSCsvFilePath)
{
if(std::string("") == rSCsvFilePath) return;
FileLoadUtil tFileLoadUtil;
auto linesVec = tFileLoadUtil.getDataLines(rSCsvFilePath);
StrVec strsVec;
StrDict dict;
StringUtil tStringUtil;
for(const auto &linesVecIter : linesVec)
{
strsVec = tStringUtil.split(linesVecIter.c_str(), ",");
dict.push_back(strsVec);
}
_pCsvMap->insert(std::make_pair(std::string(rSCsvFilePath), dict));
}
void StringUtilTest::testGetIntAsPaddedString() {
int cmp;
StringUtil sUtil;
//check that 0 or negative size string will return empty string
for (int i = 0; i > -2; i--) {
const char *val = sUtil.getIntAsPaddedString(0, 123, i);
CPPUNIT_ASSERT(val != NULL);
CPPUNIT_ASSERT(strcmp(val, "") == 0);
}
//check that value is larger the 10 width is set to width of 10.
cmp = strcmp(sUtil.getIntAsPaddedString(4, 3, 20), "##########");
CPPUNIT_ASSERT(cmp == 0);
//check that value is 10 width its set to width 10
cmp = strcmp(sUtil.getIntAsPaddedString(4, 3, 10), "##########");
CPPUNIT_ASSERT(cmp == 0);
//check that value of 9 width is set to 9
cmp = strcmp(sUtil.getIntAsPaddedString(4, 3, 9), "#########");
CPPUNIT_ASSERT(cmp == 0);
//check a negative value
cmp = strcmp(sUtil.getIntAsPaddedString(-1, 3, 9), " -1");
CPPUNIT_ASSERT(cmp == 0);
//check a 2 digit number no padding
cmp = strcmp(sUtil.getIntAsPaddedString(32, 32, 2), "32");
CPPUNIT_ASSERT(cmp == 0);
//check a 2 digit number 1 padding
cmp = strcmp(sUtil.getIntAsPaddedString(32, 32, 3), " 32");
CPPUNIT_ASSERT(cmp == 0);
//check a 2 digit number beyond threshold
cmp = strcmp(sUtil.getIntAsPaddedString(32, 4, 2), "##");
CPPUNIT_ASSERT(cmp == 0);
}
void StringUtilTest::testSplitValidArgs(){
StringUtil sUtil;
//test 3 in list
std::list<std::string> sList = sUtil.split("codonis,trestles,steele",",");
CPPUNIT_ASSERT(sList.empty() == false);
CPPUNIT_ASSERT(sList.size() == 3);
CPPUNIT_ASSERT(sList.front() == "codonis");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "trestles");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "steele");
//test 2 in list
sList = sUtil.split("codonis,steele",",");
CPPUNIT_ASSERT(sList.empty() == false);
CPPUNIT_ASSERT(sList.size() == 2);
CPPUNIT_ASSERT(sList.front() == "codonis");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "steele");
//test 1 in list
sList = sUtil.split("codonis",",");
CPPUNIT_ASSERT(sList.empty() == false);
CPPUNIT_ASSERT(sList.size() == 1);
CPPUNIT_ASSERT(sList.front() == "codonis");
//test 7 in list
sList = sUtil.split("codonis,trestles,steele,a,b,c,d",",");
CPPUNIT_ASSERT(sList.empty() == false);
CPPUNIT_ASSERT(sList.size() == 7);
CPPUNIT_ASSERT(sList.front() == "codonis");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "trestles");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "steele");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "a");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "b");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "c");
sList.pop_front();
CPPUNIT_ASSERT(sList.front() == "d");
sList.pop_front();
}
