//读取中文文本,要设置gbk格式
//该格式中文可以识别,英文也可以
reader = new InputStreamReader(new FileInputStream(filename),"gbk");
//拓展----分词
//分词时候,读取中文文本
TokenStream stream=a.tokenStream("content",new StringReader(str));
//注意分词时候的包的导入,jdk中也有一个TokenStream 类
org.apache.lucene.analysis.TokenStream stream=a.tokenStream("content",new StringReader(str));
注意:写入换行时,一定要\r\n,否则无效
String line = "";
while((line = in.readLine())!=null){
System.out.println(line);
out.write(line+"\r\n");
}
注意:流一定要在finally中关闭
if(null!=in){
try {
in.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(null!=out){
try {
out.close();
} catch (IOException e) {
e.printStackTrace();
}
}