MCPcopy Create free account
hub / github.com/catboost/catboost / Tokenize

Method Tokenize

library/cpp/text_processing/tokenizer/tokenizer.cpp:286–303  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

284}
285
286void NTokenizer::TTokenizer::Tokenize(
287 TStringBuf inputString,
288 TVector<TString>* tokens,
289 TVector<NTokenizer::ETokenType>* tokenTypes
290) const {
291 Y_ASSERT(tokens);
292 tokens->clear();
293 if (tokenTypes) {
294 tokenTypes->clear();
295 }
296
297 if (Options.SeparatorType == NTokenizer::ESeparatorType::BySense) {
298 SplitBySense(inputString, Options, Lemmer.Get(), tokens, tokenTypes);
299 } else {
300 Y_ENSURE(Options.SeparatorType == NTokenizer::ESeparatorType::ByDelimiter, "Unsupported SeparatorType");
301 SplitByDelimiter(inputString, Options, Lemmer.Get(), tokens, tokenTypes);
302 }
303}
304
305TVector<TString> NTokenizer::TTokenizer::Tokenize(TStringBuf inputString) const {
306 TVector<TString> tokens;

Callers 2

ApplyFuncTotokenizedTextFunction · 0.45
SplitBySenseFunction · 0.45

Calls 5

SplitBySenseFunction · 0.85
SplitByDelimiterFunction · 0.85
TokenizeFunction · 0.85
clearMethod · 0.45
GetMethod · 0.45

Tested by

no test coverage detected