int PartialSegmentationUtils::split_by_partial_tag(
const std::string& line,
std::vector<std::string>& words) {
size_t offset1 = line.find(__partial_start__);
size_t offset2 = line.find(__word_start__);
if (offset1 == std::string::npos && offset2 == std::string::npos) {
// 0 representing no partial tags. split with the original tags.
words = split(line);
return 0;
}
size_t offset = 0;
size_t prelude = 0, coda = 0, len_start_tag = 0, len_end_tag = 0;
while (offset < line.length()) {
prelude = (offset1 < offset2 ? offset1 : offset2);
std::string word = line.substr(offset, prelude - offset);
if (word.length() > 0) { words.push_back( word ); }
if (offset1 < offset2) {
coda = line.find(__partial_end__, prelude);
len_start_tag = __partial_start__.length();
len_end_tag = __partial_end__.length();
} else {
coda = line.find(__word_end__, prelude);
len_start_tag = __word_start__.length();
len_end_tag = __word_end__.length();
}
word = line.substr(prelude + len_start_tag, coda - prelude - len_start_tag);
if ((word.find(__partial_start__) != std::string::npos) ||
(word.find(__partial_end__) != std::string::npos) ||
(word.find(__word_start__) != std::string::npos) ||
(word.find(__word_end__) != std::string::npos)) {
return -1;
}
words.push_back( line.substr(prelude, coda - prelude + len_end_tag) );
offset = coda + len_end_tag;
offset1 = line.find(__partial_start__, offset);
offset2 = line.find(__word_start__, offset);
if (offset1 == std::string::npos && offset2 == std::string::npos) {
// 0 representing no partial tags.
word = line.substr(offset);
if (word.length() > 0) { words.push_back( word ); }
break;
}
}
return 1;
}
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;
}