解析文件去标点

本文介绍了一个Java程序,该程序用于读取TXT文件内容,并通过正则表达式移除数字和特定符号,最后将处理后的文本写入新的TXT文件。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >


import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintStream;
import java.io.PrintWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ReadTxtFile {

public static void main(String[] args){
String raw = ReadTxtFile.readTxtFile("/Users/yourname/Downloads/a.txt");
String noNumRaw = raw.replaceAll("\\d+", "").replaceAll(",", "");
//String noRaw = noNumRaw.replaceAll("[,|\\\"]", "\t").replace("[\t|\n]", "\r\n");
//String result = noRaw.replaceAll("[\\n]", "").replaceAll("\\s", "\n").replaceAll("(?m)^\\s+", "");

//String result = noRaw.replaceAll("^\\n", "").replaceAll("\\t", "");
//System.out.println(result);
String regex = "\\\"([^\\\"]+)\\\"\\b";
Matcher m = Pattern.compile(regex).matcher(noNumRaw);
String result = m.replaceAll("$1\r\n");
result = result.replaceAll("\\\"\\\"", "\r\n");
result = result.replaceAll("\\\"", "");
//m = Pattern.compile("^[\u4E00-\u9FFF]+").matcher(result);
//result = m.replaceAll("");

System.out.println(result);

try {
ReadTxtFile.writeFromBuffer(result, "/Users/yourname/Downloads/b.txt");
} catch (IOException e) {

e.printStackTrace();
}
}

public static void writeFromBuffer(String str, String outFileName) throws IOException {
OutputStream os = new FileOutputStream(outFileName);
PrintStream ps = new PrintStream(os);
ps.print(str);

PrintWriter writer = new PrintWriter(new OutputStreamWriter(os));
writer.flush();
os.close();
}

@SuppressWarnings("finally")
public static String readTxtFile(String filePath) {
StringBuilder sb = new StringBuilder();

try {
//String encoding = "GBK";
File file = new File(filePath);
if (file.isFile() && file.exists()) { // 判断文件是否存在
InputStreamReader read = new InputStreamReader(
new FileInputStream(file));// 考虑到汉字编码格式
BufferedReader bufferedReader = new BufferedReader(read);
String lineTxt = null;
while ((lineTxt = bufferedReader.readLine()) != null) {
System.out.println(lineTxt);
sb.append(lineTxt);
}
read.close();
} else {
System.out.println("找不到指定的文件");
}
} catch (Exception e) {
System.out.println("读取文件内容出错");
e.printStackTrace();
} finally {
return sb.toString();
}

}
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值