Instance* PostaggerReader::next() {
if (is.eof()) {
return 0;
}
cursor ++;
if (trace && cursor % interval == 0) {
INFO_LOG("reading: read %d0%% instances.", (cursor/ interval));
}
Instance* inst = new Instance;
std::string line;
std::getline(is, line);
trim(line);
if (line.size() == 0) {
delete inst;
return 0;
}
std::vector<std::string> words = split(line);
for (size_t i = 0; i < words.size(); ++ i) {
if (with_tag) {
std::vector<std::string> sep = rsplit_by_sep(words[i], delimiter, 1);
if (sep.size() == 2) {
inst->raw_forms.push_back(sep[0]);
inst->forms.push_back(sbc2dbc_x(sep[0]));
inst->tags.push_back(sep[1]);
} else {
std::cerr << words[i] << std::endl;
delete inst;
return 0;
}
} else {
inst->raw_forms.push_back(words[i]);
inst->forms.push_back(sbc2dbc_x(words[i]));
}
}
return inst;
}
Instance* CoNLLReader::next() {
if (is.eof()) { return NULL;}
Instance* inst = new Instance;
std::string line;
inst->raw_forms.push_back( SpecialOption::ROOT );
inst->forms.push_back( SpecialOption::ROOT );
inst->lemmas.push_back( SpecialOption::ROOT );
inst->postags.push_back( SpecialOption::ROOT );
inst->heads.push_back( -1 );
inst->deprels.push_back( SpecialOption::ROOT );
while (!is.eof()) {
getline(is, line);
trim(line);
if (line.size() == 0) { break; }
std::vector<std::string> items = split(line);
if (items.size() < 8) {
WARNING_LOG("Unknown conll format file");
}
inst->raw_forms.push_back( items[1] ); // items[1]: form
inst->forms.push_back( sbc2dbc(items[1]) );
inst->lemmas.push_back( items[2] ); // items[2]: lemma
inst->postags.push_back( items[3] ); // items[4]: postag
inst->heads.push_back( to_int(items[6]) );
inst->deprels.push_back( items[7] );
}
if (inst->forms.size() == 1) {
delete inst;
inst = NULL;
}
return inst;
}
Instance* SegmentReader::next() {
if (is.eof()) {
return 0;
}
cursor ++;
if (trace && cursor % interval == 0) {
INFO_LOG("reading: read %d0%% instances.", (cursor/ interval));
}
Instance* inst = new Instance;
std::string line;
std::getline(is, line);
trim(line);
if (line.size() == 0) {
delete inst;
return 0;
}
if (segmented) {
std::vector<std::string> words = strutils::split(line);
inst->words = words;
for (size_t i = 0; i < words.size(); ++ i) {
// std::vector<std::string> chars;
// int num_chars = codecs::decode(words[i], chars);
int num_chars = preprocessor.preprocess(words[i], inst->raw_forms,
inst->forms, inst->chartypes);
if (num_chars < 0) {
delete inst;
return 0;
}
for (size_t j = 0; j < num_chars; ++ j) {
// inst->forms.push_back(chars[j]);
if (1 == num_chars) {
inst->tags.push_back( __s__ );
} else {
if (0 == j) {
inst->tags.push_back( __b__ );
} else if (num_chars - 1 == j) {
inst->tags.push_back( __e__ );
} else {
inst->tags.push_back( __i__ );
}
}
}
}
} else {
int ret = preprocessor.preprocess(line, inst->raw_forms,
inst->forms, inst->chartypes);
if (ret < 0) {
delete inst;
return 0;
}
}
return inst;
}
