def index(self, corpus_reader: CorpusReader): update = self.__index.update for pmid, document in corpus_reader.items(): update(pmid, document) self.__documents.setdefault(pmid, 0) if self.__process.memory_percent() >= self.__max_memory_usage: self.__dispatch()
def index(self, corpus_reader : CorpusReader): for pmid, document in corpus_reader.items(): self.update(pmid, document) self.documents.add(pmid) if self.process.memory_percent() >= self.max_memory_usage: self.dispatch()