string Mykytea::getTagsToString(string str)
{
KyteaString surface_string = util->mapString(str);
KyteaSentence sentence(surface_string, util->normalize(surface_string));
kytea->calculateWS(sentence);
for(int i = 0; i < config->getNumTags(); i++)
kytea->calculateTags(sentence,i);
const KyteaSentence::Words & words = sentence.words;
string ret_str;
for(int i = 0; i < (int)words.size(); i++) {
ret_str += util->showString(words[i].surface);
for(int j = 0; j < (int)words[i].tags.size(); j++) {
for(int k = 0; k < 1; k++) {
ret_str += "/";
ret_str += util->showString(words[i].tags[j][k].first);
}
}
ret_str += " ";
}
return ret_str;
}
vector<Tags>* Mykytea::getAllTags(string str){
vector<Tags>* ret_words = new vector<Tags>;
KyteaString surface_string = util->mapString(str);
KyteaSentence sentence(surface_string, util->normalize(surface_string));
kytea->calculateWS(sentence);
for(int i = 0; i < config->getNumTags(); i++)
kytea->calculateTags(sentence,i);
const KyteaSentence::Words & words = sentence.words;
for(int i = 0; i < (int)words.size(); i++) {
tags vec_tag;
for(int j = 0; j < (int)words[i].tags.size(); j++) {
vector< pair<string, double> > vec_tmp;
for(int k = 0; k < (int)words[i].tags[j].size(); k++) {
vec_tmp.push_back( make_pair(util->showString(words[i].tags[j][k].first), words[i].tags[j][k].second) );
}
vec_tag.push_back( vec_tmp );
}
struct Tags t = { util->showString(words[i].surface), vec_tag };
(*ret_words).push_back( t );
}
return ret_words;
}
void blf2xml(const string & file_name, const string & result_name, const string & ext)
{
ifstream in(file_name.c_str());
if(!in) {
cerr << "Warning: Can't open file " << file_name << " ignoring." << endl;
return;
}
ofstream out(result_name.c_str());
if(!out) {
cerr << "Warning: Can't open file " << result_name << " ignoring." << endl;
return;
}
c_SentenceEntry sentence(basename(file_name, ext), "#", "#.");
string tmp;
vector< c_LabelEntry > label;
while(getline(in, tmp)) {
if(!isComment(tmp)) {
c_LabelEntry tmplabel;
stringstream ins(tmp.c_str());
ins >> tmplabel.first >> tmplabel.phon >> tmplabel.pros;
label.push_back(tmplabel);
}
}
sp<String> Eliza::talk(sp<String> s) {
sp<String> reply;
// Do some input transformations.
s = Strings::translate(s, "ABCDEFGHIJKLMNOPQRSTUVWXYZ",
"abcdefghijklmnopqrstuvwxyz");
s = Strings::translate(s, "@#$%^&*()_-+=~`{[}]|:;<>\\\"",
" " );
s = Strings::translate(s, ",?!", "...");
// Remove multiple spaces.
s = Strings::compress(s);
sp<StringArray> lines = new StringArray(2);
// Break apart sentences, and do each separately.
while (Strings::match(s, "*.*", lines)) {
reply = sentence(lines->get(0));
if (reply != nullptr) {
return reply;
}
s = Strings::trim(lines->get(1));
}
if (s->length() != 0) {
reply = sentence(s);
if (reply != nullptr) {
return reply;
}
}
// Nothing matched, so try memory.
sp<String> m = memory->get();
if (m != nullptr) {
return m;
}
// No memory, reply with xnone.
sp<Key> key = keys->getKey(String::valueOf("xnone"));
if (key != nullptr) {
sp<Key> dummy = nullptr;
reply = decompose(key, s, dummy);
if (reply != nullptr) {
return reply;
}
}
// No xnone, just say anything.
return String::valueOf("I am at a loss for words.");
}
int
main()
{
// declare a new Sentence object and pass "What time is it?" to the
// constructor
Sentence sentence("What time is it???");
// Call class Sentence's member function print
sentence.print();
return 0; // everything executed ok
}
vector<string>* Mykytea::getWS(string str){
vector<string>* vec = new vector<string>;
KyteaString surface_string = util->mapString(str);
KyteaSentence sentence(surface_string, util->normalize(surface_string));
kytea->calculateWS(sentence);
const KyteaSentence::Words & words = sentence.words;
for(int i = 0; i < (int)words.size(); i++) {
(*vec).push_back(util->showString(words[i].surface));
}
return vec;
}
/**
* Finds the sentence annotation containing the given token.
*
* \param token the token
* \return the sentence or an invalid sentence if not found
*/
SentenceAnnotation SentenceAnnotation::findSentenceContainingToken(TokenAnnotation& token)
{
FSIterator iterator = token.getView().getAnnotationIndex(tSentenceAnnotation).iterator();
if (iterator.isValid()) {
iterator.moveToFirst();
while (iterator.isValid()) {
AnnotationFS annotation(iterator.get());
SentenceAnnotation sentence(annotation);
if ((sentence.getFirstToken().getIndex() <= token.getIndex()) && (sentence.getLastToken().getIndex() >= token.getIndex()))
return sentence;
iterator.moveToNext();
}
}
return SentenceAnnotation();
}
Window::Window()
: QGraphicsWidget(0, Qt::Window)
{
FlowLayout *lay = new FlowLayout;
QLatin1String wiseWords("I am not bothered by the fact that I am unknown."
" I am bothered when I do not know others. (Confucius)");
QString sentence(wiseWords);
QStringList words = sentence.split(QLatin1Char(' '), QString::SkipEmptyParts);
for (int i = 0; i < words.count(); ++i) {
QGraphicsProxyWidget *proxy = new QGraphicsProxyWidget(this);
QLabel *label = new QLabel(words.at(i));
label->setFrameStyle(QFrame::Box | QFrame::Plain);
proxy->setWidget(label);
lay->addItem(proxy);
}
setLayout(lay);
}
int main()
{
char ans ;
/*乱数の初期化*/
srand(65535) ;
/*文の生成*/
while(1){
sentence() ;
printf("\n") ;
printf("これで良いですか？(y/n)\n") ;
scanf("%c",&ans) ;
if(ans=='y') break ;
}
return 0 ;
}
JNIEXPORT jint JNICALL Java_edu_hit_ir_ltp4j_Segmentor_segment
(JNIEnv* env, jobject obj, jstring sent, jobject array_words) {
jclass array_list = env->GetObjectClass(array_words);
jmethodID list_add = env->GetMethodID(array_list, "add", "(Ljava/lang/Object;)Z");
const char* str_sent = env->GetStringUTFChars( sent , 0);
std::string sentence(str_sent);
std::vector<std::string> words;
int len = segmentor_segment(segmentor, sentence, words);
for(int i = 0; i < len; i++) {
jobject tmp = stringToJstring(env,words[i].c_str());
env->CallBooleanMethod(array_words,list_add,tmp);
}
env->ReleaseStringUTFChars(sent, str_sent);
return len;
}
void GPSWindow::timeout()
{
engine::Latitude lat;
if (!engine::Latitude::parse(lat, latitude->text().toStdString()))
return;
engine::Longitude lon;
if (!engine::Longitude::parse(lon, longitude->text().toStdString()))
return;
engine::Date t;
if (!engine::Date::parse(t, datetime_utc->text().toStdString()))
return;
nmea::RMC rmc;
rmc.set(t);
rmc.set(lat);
rmc.set(lon);
emit sentence(rmc.str());
}
int main()
{
char nlist[NMAX][CHMAX] ;//名詞リスト
char vlist[NMAX][CHMAX] ;//動詞リスト
int nnum,vnum ;//リストの項目数
int i ;
/*乱数の初期化*/
srand(65535) ;
/*名詞リストと動詞リストの読み込み*/
nnum=setlist(nlist,NFILE) ;
vnum=setlist(vlist,VFILE) ;
for(i=0;i<50;++i){
/*文の生成*/
sentence(nlist,nnum,vlist,vnum) ;
printf("．\n") ;
}
return 0 ;
}
static void couchStoreAndRetrieveAttachment(PrintTextA &a) {
CouchDB db(getTestCouch());
db.use(DATABASENAME);
Document doc = db.newDocument(".data");
db.uploadAttachment(doc,"testAttachment","text/plain",[](SeqFileOutput wr) {
SeqTextOutA txtwr(wr);
ConstStrA sentence("The quick brown fox jumps over the lazy dog");
txtwr.blockWrite(sentence,true);
});
Document doc2 = db.retrieveDocument(doc.getID());
AttachmentData data = db.downloadAttachment(doc2,"testAttachment");
a("%1-%2") << data.contentType << ConstStrA(reinterpret_cast<const char *>(data.data()),data.length());
}
void HunspellDialog::goToNextWord(int i)
{
if (m_returnToDefaultLang)
{
bool b=languagesComboBox->blockSignals(true);
languagesComboBox->setCurrentIndex(m_primaryLangIndex);
languagesComboBox->blockSignals(b);
}
if (i>=0)
m_wfListIndex=i;
else
{
do {
++m_wfListIndex;
} while (m_wfListIndex<m_wfList->count() && (m_wfList->at(m_wfListIndex).changed || m_wfList->at(m_wfListIndex).ignore));
//qDebug()<<"selected word index"<<m_wfListIndex;
}
if (m_wfListIndex>=m_wfList->count())
{
statusLabel->setText(tr("Spelling check complete"));
suggestionsListWidget->clear();
sentenceTextEdit->clear();
changePushButton->setEnabled(false);
changeAllPushButton->setEnabled(false);
ignoreOncePushButton->setEnabled(false);
ignoreAllPushButton->setEnabled(false);
return;
}
else
statusLabel->setText("");
currWF=m_wfList->at(m_wfListIndex);
setLanguageCombo(currWF.lang);
updateSuggestions(currWF.replacements);
int sentencePos=0;
QString sentence(m_iText->sentence(currWF.start, sentencePos));
sentence.insert(currWF.end-sentencePos+currWF.changeOffset,"</b></font>");
sentence.insert(currWF.start-sentencePos+currWF.changeOffset,"<font color=red><b>");
sentenceTextEdit->setText(sentence);
}
ISpRecoGrammar* SpeechRecognition::InitGrammar()
{
HRESULT hr;
SPSTATEHANDLE sate;
ISpRecoGrammar* recoGrammar;
hr = recoContext->CreateGrammar(GRAMMARID, &recoGrammar);
CheckReturn(hr);
WORD langID = MAKELANGID(LANG_ENGLISH, SUBLANG_ENGLISH_US);
hr = recoGrammar->ResetGrammar(langID);
CheckReturn(hr);
//create rules
hr = recoGrammar->GetRule(RULENAME, 0, SPRAF_TopLevel | SPRAF_Active, true, &sate);
CheckReturn(hr);
//add words
const std::wstring commandWstr = std::wstring(L"Mocha");
hr = recoGrammar->AddWordTransition(sate, NULL, commandWstr.c_str(), L" ", SPWT_LEXICAL, 1, nullptr);
CheckReturn(hr);
for (std::wstring& ws : wordList)
{
std::string sentence(ws.begin(), ws.end());
std::vector<std::string> words = split(sentence, ' ');
for (std::string& w : words)
{
std::wstring wsword(w.begin(), w.end());
hr = recoGrammar->AddWordTransition(sate, NULL, wsword.c_str(), L" ", SPWT_LEXICAL, 1, nullptr);
}
CheckReturn(hr);
}
hr = recoGrammar->Commit(0);
CheckReturn(hr);
return recoGrammar;
}
void MainWindow::updateNavInfoEvent()
{
QString buff;
port->receiveLine(buff);
GpSentence sentence(buff);
ui->textBrowser->append("GPXXX:" + sentence.code);
if(sentence.code.contains("$GPRMC")) {
if(sentence.data.size() >=8 ) {
infoA->text = sentence.data[6];
infoD->text = sentence.data[7];
}
}
if(sentence.code.contains("$GPGGA")) {
if(sentence.data.size() >=9 ) {
infoB->text = sentence.data[8];
QString lat = sentence.data[1]+ " " +sentence.data[2];
QString lon = sentence.data[3]+ " " +sentence.data[4];
ui->lineEdit->setText("LAT: " + lat + " LON:" + lon);
}
}
// ui->textBrowser->append(buff);
// ui->textBrowser->ensureCursorVisible();
// infoA->text = NavInfo::Instance()->getSpeedString();
repaint();
}
void Samu::FamilyCaregiverShell ( void )
{
std::string cmd_prefix = "cmd";
fd_set rfds;
struct timeval tmo;
int sleep {0};
if ( sleep_ )
sleep = sleep_after_ + 1;
int prev_sec {0};
for ( ; run_ ; )
{
try
{
disp.cg_read();
if ( ++sleep > sleep_after_ )
{
if ( !sleep_ )
{
std::cerr << "Isaac went to sleep." << std::endl;
disp.log ( "I went to sleep." );
}
sleep_ = true;
}
else
{
std::cerr << sleep << " " << std::flush;
int sec = ( sleep * read_usec_ ) / ( 1000*1000 );
if ( sec != prev_sec )
{
int after = ( sleep_after_ * read_usec_ ) / ( 1000*1000 );
std::stringstream sleep_after;
sleep_after << "I will go to sleep after ";
sleep_after << ( after-sec );
sleep_after << " seconds";
disp.log ( sleep_after.str() );
prev_sec = sec;
}
}
}
catch ( std::string line )
{
if ( sleep_ )
{
std::cerr << "Isaac is awake now." << std::endl;
disp.log ( "I am awake now." );
}
sleep_ = false;
sleep = 0;
if ( !line.compare ( 0, cmd_prefix.length(), cmd_prefix ) )
{
std::string readCmd {"cmd read"};
size_t f = line.find ( readCmd );
if ( f != std::string::npos )
{
f = f+readCmd.length() +1;
if ( f < line.length() )
{
std::string fname = line.substr ( f );
set_training_file ( fname );
}
}
else
NextCaregiver();
}
else
{
try
{
sentence ( -1, line );
}
catch ( const char* err )
{
std::cerr << err << std::endl;
disp.log ( err );
}
}
}
usleep ( read_usec_ );
}
run_ = false;
}
void DataBlock::Add(int *head, int sentence_length, int64_t word_count, uint64_t next_random)
{
Sentence sentence(head, sentence_length, word_count, next_random);
m_sentences.push_back(sentence);
}
int main(int argc, char *argv[]) /*{{{*/
{
int usage=0,c;
char *userPhrases=(char*)0,*e;
char defaultPhrases[_POSIX_PATH_MAX];
static struct option lopts[]=
{
{ "beginner", no_argument, 0, 'b', },
{ "ignore-double-words", no_argument, 0, 'd' },
{ "suggest", no_argument, 0, 's' },
{ "file", required_argument, 0, 'f' },
{ "help", no_argument, 0, 'h' },
{ "version", no_argument, 0, 'v' },
{ "language", required_argument, 0, 'L' },
{ "quiet", no_argument, 0, 'q' },
{ "no-default-file", no_argument, 0, 'n' },
{ (const char*)0, 0, 0, '\0' }
};
/* init locale */ /*{{{*/
setlocale(LC_ALL,"");
#ifdef HAVE_GETTEXT
bindtextdomain("diction",LOCALEDIR);
textdomain("diction");
#endif
e=getenv("LC_MESSAGES");
if (e==(char*)0) e=getenv("LC_ALL");
if (e==(char*)0) e=getenv("LANG");
if (e)
{
strncpy(phraseLanguage,e,sizeof(phraseLanguage)-1);
phraseLanguage[sizeof(phraseLanguage)-1]='\0';
if (strstr(phraseLanguage,".."))
{
fprintf(stderr,_("diction: Invalid string `..' in default phrase language `%s'.\n"),phraseLanguage);
exit(2);
}
else
{
snprintf(defaultPhrases,sizeof(defaultPhrases), "/diction/%s",e);
if (access(defaultPhrases,R_OK)!=0)
{
phraseLanguage[5]='\0';
snprintf(defaultPhrases,sizeof(defaultPhrases), "/diction/%s",phraseLanguage);
if (access(defaultPhrases,R_OK)!=0)
{
phraseLanguage[2]='\0';
snprintf(defaultPhrases,sizeof(defaultPhrases), "/diction/%s",phraseLanguage);
if (access(defaultPhrases,R_OK)!=0)
{
strcpy(phraseLanguage,"C");
}
}
}
}
}
else strcpy(phraseLanguage,"C");
/*}}}*/
/* parse options */ /*{{{*/
strcpy(defaultPhrases, "/diction/");
while ((c=getopt_long(argc,argv,"bdsf:nL:qh",lopts,(int*)0))!=EOF) switch(c)
{
case 'b': beginner=1; break;
case 'd': doubleWords=0; break;
case 's': suggest=1; break;
case 'f': userPhrases=optarg; break;
case 'n': defaultPhrases[0]='\0'; break;
case 'L': strncpy(phraseLanguage,optarg,sizeof(phraseLanguage)-1); phraseLanguage[sizeof(phraseLanguage)-1]='\0'; break;
case 'q': quiet=1; break;
case 'v': printf("GNU diction\n"); exit(0);
case 'h': usage=2; break;
default: usage=1; break;
}
if (defaultPhrases[0]) strcat(defaultPhrases,phraseLanguage);
if (usage==1 || (userPhrases==(char*)0 && defaultPhrases[0]=='\0'))
{
print_usage(stderr);
fputs("\n",stderr);
fputs(_("Try `diction -h' or `diction --help' for more information.\n"),stderr);
exit(1);
}
if (usage==2)
{
print_usage(stdout);
fputs("\n",stdout);
fputs(_("Print wordy and commonly misused phrases in sentences.\n\n"),stdout);
fputs(_("-b, --beginner complain about typical mistakes of beginners\n"),stdout);
fputs(_("-d, --ignore-double-words do not complain about double words\n"),stdout);
fputs(_("-s, --suggest suggest better wording\n"),stdout);
fputs(_("-f, --file also read the specified database\n"),stdout);
fputs(_("-n, --no-default-file do not read the default phrase file\n"),stdout);
fputs(_("-L, --language set document language\n"),stdout);
fputs(_("-q, --quiet do not print input file name\n"),stdout);
fputs(_("-h, --help print this message\n"),stdout);
fputs(_(" --version print the version\n"),stdout);
fputs("\n",stdout);
fputs(_("Report bugs to <*****@*****.**>.\n"),stdout);
exit(0);
}
/*}}}*/
if (defaultPhrases[0]) loadPhrases(defaultPhrases);
if (userPhrases) loadPhrases(userPhrases);
sentences=0;
hits=0;
if (optind==argc) sentence("diction",stdin,"(stdin)",diction,phraseLanguage);
else while (optind<argc)
{
FILE *fp;
if ((fp=fopen(argv[optind],"r"))==(FILE*)0)
{
fprintf(stderr,_("diction: Opening `%s' failed (%s).\n"),argv[optind],strerror(errno));
}
else
{
sentence("diction",fp,argv[optind],diction,phraseLanguage);
fclose(fp);
}
++optind;
}
if (sentences==0)
{
printf(_("No sentences found.\n"));
}
else
{
if (hits==0) printf(_("No phrases "));
else if (hits==1) printf(_("1 phrase "));
else printf(_("%d phrases "),hits);
if (sentences==1) printf(_("in 1 sentence found.\n"));
else printf(_("in %d sentences found.\n"),sentences);
}
exit(0);
}
TranslationHypothesis::TranslationHypothesis(const string& source)
{
const StaticData &staticData = StaticData::Instance();
const TranslationSystem& system =
staticData.GetTranslationSystem(TranslationSystem::DEFAULT);
//clean up previous sentence
if (m_cleanup) {
system.CleanUpAfterSentenceProcessing();
} else {
m_cleanup = true;
}
//the sentence
Sentence sentence(Input);
stringstream in(source + "\n");
const std::vector<FactorType> &inputFactorOrder = staticData.GetInputFactorOrder();
sentence.Read(in,inputFactorOrder);
for (size_t i=0; i<sentence.GetSize(); ++i){ m_words.push_back(sentence.GetWord(i)); }
//translation options
m_manager.reset(new Manager(sentence, Normal, &system));
m_manager->ResetSentenceStats(sentence);
system.InitializeBeforeSentenceProcessing(sentence);
m_toc.reset(sentence.CreateTranslationOptionCollection(&system));
//const vector <DecodeGraph*>
// &decodeStepVL = staticData.GetDecodeGraphs();
m_toc->CreateTranslationOptions();
//sort the options
size_t maxPhraseSize = staticData.GetMaxPhraseLength();
for (size_t start = 0; start < m_words.size(); ++start) {
for (size_t end = start; end < start + maxPhraseSize && end < m_words.size(); ++end) {
TranslationOptionList& options =
m_toc->GetTranslationOptionList(start,end);
sort(options.begin(), options.end(), TOptCompare());
/*
while (options.size() > ttableLimit) {
size_t pos = options.size() - 1;
delete options.Get(pos);
options.Remove(pos);
}*/
}
}
//hypothesis
m_hypothesis.reset(Hypothesis::Create(*m_manager,sentence, emptyTarget()));
for (size_t i = 0; i < m_words.size(); ++i) {
m_allHypos.push_back(m_hypothesis);
WordsRange segment(i,i);
const TranslationOptionList& options =
m_toc->GetTranslationOptionList(segment);
/*
cerr << "Options for " << *(options.Get(0)->GetSourcePhrase()) << endl;
for (size_t j = 0; j < options.size(); ++j) {
cerr << *(options.Get(j)) << endl;
}*/
assert(options.size());
m_hypothesis.reset(
Hypothesis::Create(*m_hypothesis, *(options.Get(0)), NULL));
}
}
