Spark 中文分词

Posted 2021-02-08

Spark 中文分词

一、导入需要的分词包

import org.ansj.domain.Term
import org.ansj.recognition.impl.StopRecognition
import org.ansj.splitWord.analysis.ToAnalysis

二、停用词过滤

def filter(stopWords: Array[String]): StopRecognition = {
    // add stop words 
    val filter = new StopRecognition
    filter.insertStopNatures("w") // filter punctuation
    filter.insertStopNatures("m") // filter m pattern
    filter.insertStopNatures("null") // filter null
    filter.insertStopNatures("<br />") // filter <br />
    filter.insertStopRegexes("^[a-zA-Z]{1,}") //filter English alphabet
    filter.insertStopRegexes("^[0-9]+") //filter number
    filter.insertStopRegexes("[^a-zA-Z0-9\u4e00-\u9fa5]+")
    filter.insertStopRegexes("	")
    for (x <- stopWords) {
      filter.insertStopWords(x)
    }
    filter
  }

三、分词

def getWords(text: String, filter: StopRecognition): ArrayBuffer[String] = {
    val words = new mutable.ArrayBuffer[String]()
    val terms: java.util.List[Term] =  ToAnalysis.parse(text).recognition(filter).getTerms
    for (i <- 0 until terms.size()) {
        val word = terms.get(i).getName
        if (word.length >= MIN_WORD_LENGTH) {
            words += word
        }
    }
    words
}