void MainWindow::textBagOfWords(std::set<std::string> &featureDic, std::map<std::string, int> &text,int &textSize)
{
if(!ICTCLAS_Init()) //初始化分词组件。
{
QMessageBox::warning(this,"Warnning","Init fails",QMessageBox::Yes);
return;
}
else
{
printf("Init ok\n");
}
ICTCLAS_SetPOSmap(2);
QString myStr = ui->text->toPlainText();
QByteArray ba = myStr.toLocal8Bit();
char* sText;
char* sSentence = (char*)malloc(ba.size()+10);
sText = ba.data();
int len = 0;
//这样读入为了将换行符去掉，ASCII码10、13
for(int i = 0; sText[i] != '\0'; i++)
{
if(sText[i] == '\n' || sText[i] == '\r')continue;
sSentence[len++] = sText[i];
}
sSentence[len] = '\0';
unsigned int nPaLen=strlen(sSentence); // 需要分词的长度
char* sRst=0; //用户自行分配空间，用于保存结果；
sRst=(char*)malloc(nPaLen*6); //建议长度为字符串长度的6倍。
int nRstLen=0; //分词结果的长度
nRstLen = ICTCLAS_ParagraphProcess(sSentence,nPaLen,sRst,CODE_TYPE_UNKNOWN,0); //字符串处理
//free(sText);
free(sSentence);
//收集单词，形成字典
std::string words;
std::istringstream istream(sRst);
std::set<std::string> txtWords;
while(istream>>words)
{
txtWords.insert(words);
if(featureDic.count(words))
{
text[words]++;
}
}
textSize = txtWords.size();
free(sRst);
txtWords.clear();
istream.clear();
ICTCLAS_Exit(); //释放资源退出
return;
}
void SplitUTF8()
{
//初始化分词组件
if(!ICTCLAS_Init("",UTF8_CODE))//数据在当前路径下，设置为UTF8编码的分词
{
printf("ICTCLAS INIT FAILED!\n");
return ;
}
ICTCLAS_FileProcess("testUTF.txt","testUTF_result.txt");
ICTCLAS_Exit();
}
void SplitBIG5()
{
//初始化分词组件
if(!ICTCLAS_Init("",BIG5_CODE))//数据在当前路径下，设置为BIG5编码的分词
{
printf("ICTCLAS INIT FAILED!\n");
return ;
}
ICTCLAS_FileProcess("testBIG.txt","testBIG_result.txt");
ICTCLAS_Exit();
}
void FingerPrint(const char *sInput)
{
//初始化分词组件
if(!ICTCLAS_Init())
{
printf("ICTCLAS INIT FAILED!\n");
return ;
}
//释放分词组件资源
ICTCLAS_Exit();
}
int main(int argc, char* argv[])
{
//Sample1: Sentence or paragraph lexical analysis with only one result
char sSentence[2000],sSentenceResult[5000];
ICTCLAS_Init();
printf("Input sentence now!\n");
scanf("%s",sSentence);
while(_stricmp(sSentence,"q")!=0)
{
ICTCLAS_ParagraphProcess(sSentence,sSentenceResult);
printf("%s\nInput string now!\n",sSentenceResult);
scanf("%s",sSentence);
}
ICTCLAS_Exit();
//Sample2: File segmentation and POS tagging
/*
ICTCLAS_Init();
ICTCLAS_FileProcess("E:\\Sample\\Corpus_NewPOS\\199802_Org.txt","E:\\Sample\\Corpus_NewPOS\\199802_Org_cla.txt");
ICTCLAS_Exit();
*/
//Sample3: Sentence segmentation and POS tagging with multiple result
/*
char sSentence[2000],**sSentenceResult;
int i;
sSentenceResult=new char*[5];
for(i=0;i<5;i++)
sSentenceResult[i]=new char[5000];
ICTCLAS_Init();
printf("Input sentence now!\n");
scanf("%s",sSentence);
while(_stricmp(sSentence,"q")!=0)
{
ICTCLAS_SentenceProcess(sSentence,5,sSentenceResult);
for(i=0;i<5;i++)
printf("Result%d:%s\n",i+1,sSentenceResult[i]);
printf("Input string now!\n");
scanf("%s",sSentence);
}
ICTCLAS_Exit();
for(i=0;i<5;i++)
delete[] sSentenceResult[i];
delete [] sSentenceResult;
*/
return 0;
}
void KeyExtract(const char *sInput)
{
//初始化分词组件
if(!ICTCLAS_Init())
{
printf("ICTCLAS INIT FAILED!\n");
return ;
}
int nCount = ICTCLAS_GetParagraphProcessAWordCount(sInput);
//分词。提取关键词
result_t *result =(result_t*)malloc(sizeof(result_t)*nCount);
ICTCLAS_ParagraphProcessAW(nCount,result);//获取结果存到客户的内存中
//指纹提取，须在ICTCLAS_ParagraphProcessAW函数执行完后执行
unsigned long lFinger = ICTCLAS_FingerPrint();
char buf[100];
memset(buf, 0, 100);
sprintf(buf, "%x", lFinger);
printf("%s\n", buf);
//关键词提取，须在ICTCLAS_ParagraphProcessAW函数执行完后执行
result_t *resultKey = (result_t*)malloc(sizeof(result_t)*nCount);
int nCountKey;
ICTCLAS_KeyWord(resultKey, nCountKey);
for (int i=0; i<nCountKey; i++)
{
char buf[100];
memset(buf, 0, 100);
int index = resultKey[i].start;
if( resultKey[i].weight>0)
{
memcpy(buf,(void *)(sInput+index), resultKey[i].length);
printf("%s\t%d\n", buf, resultKey[i].weight);
}
}
free(resultKey);
free(result);
//释放分词组件资源
ICTCLAS_Exit();
}
int main(int argc, char** argv)
{
//testNewWord(GBK_CODE);
//testNewWord(UTF8_CODE);
//初始化分词组件
char* inputFile = argv[1];
char* outputFile = argv[2];
printf("%s\n", inputFile);
printf("%s\n", outputFile);
if(!ICTCLAS_Init("..",UTF8_CODE))//数据在当前路径下，设置为UTF8编码的分词
{
printf("ICTCLAS INIT FAILED!\n");
return NULL;
}
ICTCLAS_FileProcess(inputFile, outputFile, 0);
ICTCLAS_Exit();
return 0;
}
void SplitGBK(const char *sInput)
{//分词演示
//初始化分词组件
if(!ICTCLAS_Init())//数据在当前路径下，默认为GBK编码的分词
{
printf("ICTCLAS INIT FAILED!\n");
return ;
}
ICTCLAS_SetPOSmap(ICT_POS_MAP_SECOND);
char sSentence[2000]="三枪拍案惊奇的主创人员包括孙红雷、小沈阳、闫妮等，导演为张艺谋";
const char * sResult;
int nCount;
ICTCLAS_ParagraphProcessA(sSentence,&nCount);
printf("nCount=%d\n",nCount);
ICTCLAS_AddUserWord("孙红雷 yym");//添加孙红雷，作为演员名称
sResult = ICTCLAS_ParagraphProcess(sSentence,1);
printf("%s\n", sResult);
ICTCLAS_AddUserWord("小沈阳 yym");//添加小沈阳，作为演员名称
sResult = ICTCLAS_ParagraphProcess(sSentence,1);
printf("%s\n", sResult);
ICTCLAS_AddUserWord("闫妮 yym");//添加闫妮，作为演员名称
sResult = ICTCLAS_ParagraphProcess(sSentence,1);
printf("%s\n", sResult);
ICTCLAS_AddUserWord("三枪拍案惊奇 dym");//添加三枪拍案惊奇，作为电影名称
sResult = ICTCLAS_ParagraphProcess(sSentence,1);
printf("%s\n", sResult);
while(_stricmp(sSentence,"q")!=0)
{
sResult = ICTCLAS_ParagraphProcess(sSentence,0);
printf("%s\nInput string now('q' to quit)!\n", sResult);
scanf("%s",sSentence);
}
//导入用户词典前
printf("未导入用户词典：\n");
sResult = ICTCLAS_ParagraphProcess(sInput, 0);
printf("%s\n", sResult);
//导入用户词典后
printf("\n导入用户词典后：\n");
nCount = ICTCLAS_ImportUserDict("userdic.txt");//userdic.txt覆盖以前的用户词典
//保存用户词典
ICTCLAS_SaveTheUsrDic();
printf("导入%d个用户词。\n", nCount);
sResult = ICTCLAS_ParagraphProcess(sInput, 1);
printf("%s\n", sResult);
//动态添加用户词
printf("\n动态添加用户词后：\n");
ICTCLAS_AddUserWord("计算机学院 xueyuan");
ICTCLAS_SaveTheUsrDic();
sResult = ICTCLAS_ParagraphProcess(sInput, 1);
printf("%s\n", sResult);
//对文件进行分词
ICTCLAS_FileProcess("testGBK.txt","testGBK_result.txt",1);
//释放分词组件资源
ICTCLAS_Exit();
}
