查看分词器分词结果

2019独角兽企业重金招聘Python工程师标准>>>

Analyzer analyzer = new WhitespaceAnalyzer();

try {

// 第一个参数只是标识性没有实际作用

TokenStream stream = analyzer.tokenStream("", new StringReader("我爱 北京 天安门"));

// 获取词与词之间的位置增量

PositionIncrementAttribute postiona = stream.addAttribute(PositionIncrementAttribute.class);

// 获取各个单词之间的偏移量

OffsetAttribute offseta = stream.addAttribute(OffsetAttribute.class);

// 获取每个单词信息

CharTermAttribute chara = stream.addAttribute(CharTermAttribute.class);

// 获取当前分词的类型

TypeAttribute typea = stream.addAttribute(TypeAttribute.class);

stream.reset();

while (stream.incrementToken()) {

System.out.print("位置增量" + postiona.getPositionIncrement() + ":\t");

System.out.println(

chara + "\t[" + offseta.startOffset() + " - " + offseta.endOffset() + "]\t<" + typea + ">");

}

System.out.println();

} catch (Exception e) {

e.printStackTrace();

}

转载于:https://my.oschina.net/payzheng/blog/645605