Question

我有一个大文本文件（15000行）。每行以/ txt结尾我想更改每5行以txt5结尾。我已经搜索了Internet，但没有找到适合我的解决方案。

import java.io.*;
import java.util.*;
import java.util.concurrent.TimeUnit;

public class Main {


private static String fileToString(String filename) throws IOException {
    FileInputStream inputStream = null;
    Scanner reader = null;
    inputStream = new FileInputStream(filename);
    reader = new Scanner(inputStream, "UTF-8");

    /*BufferedReader reader = new BufferedReader(new FileReader(filename));*/
    StringBuilder builder = new StringBuilder();


    // For every line in the file, append it to the string builder
    while (reader.hasNextLine()) {
        String line = reader.nextLine();
        builder.append(line);
    }

    reader.close();
    return builder.toString();
}

public static final String UTF8_BOM = "\uFEFF";

private static String removeUTF8BOM(String s) {
    if (s.startsWith(UTF8_BOM)) {
        s = s.substring(1);
    }
    return s;
}

public static void main(String[] args) throws IOException {

    long startTime = System.nanoTime();
    System.out.println("-------------- Start Contents of file: ---------------------");
    FileInputStream inputStream = null;
    Scanner sc = null;
    String path = "C:/xampp/htdocs/thesis_freqeuncy_2/nahidd_filtered.txt";
    try {
        inputStream = new FileInputStream(path);
        sc = new Scanner(inputStream, "UTF-8");
        int countWord = 0;
        BufferedWriter writer = null;
        while (sc.hasNextLine()) {
            String word = null;
            String line = sc.nextLine();
            String[] wordList = line.split("\\s+");

            for (int i = 0; i < wordList.length; i++) {
                word = wordList[i].replace("।", "");
                word = word.replace(",", "").trim();
                ArrayList<String> freqword = new ArrayList<>();
                String freq = fileToString("C:/xampp/htdocs/thesis_freqeuncy_2/freq3.txt");
                /*freqword = freq.split("\\r?\\n");*/
                Collections.addAll(freqword, freq.split("\\r?\\n"));
                int flag = 0;
                String[] freqwordsp = null;
                int k;
                for (k = 0; k < freqword.size(); k++) {
                    freqwordsp = freqword.get(k).split("\\s+");
                    String word2 = freqwordsp[0];
                    word = removeUTF8BOM(word);
                    word2 = removeUTF8BOM(word2);
                    word.replaceAll("\\P{Print}", "");
                    word2.replaceAll("\\P{Print}", "");
                    if (word2.toString().equals(word.toString())) {

                        flag = 1;
                        break;
                    }
                }

                int count = 0;
                if (flag == 1) {
                    count = Integer.parseInt(freqwordsp[1]);
                }
                count = count + 1;
                word = word + " " + count + "\n";
                freqword.add(word);

                System.out.println(freqword);
                writer = new BufferedWriter(new FileWriter("C:/xampp/htdocs/thesis_freqeuncy_2/freq3.txt"));
                writer.write(String.valueOf(freqword));
            }
        }
        // writer.close();
        System.out.println(countWord);
        System.out.println("-------------- End Contents of file: ---------------------");
        long endTime = System.nanoTime();
        long totalTime = (endTime - startTime);
        System.out.println(TimeUnit.MINUTES.convert(totalTime, TimeUnit.NANOSECONDS));

        // note that Scanner suppresses exceptions
        if (sc.ioException() != null) {
            throw sc.ioException();
        }
    } finally {
        if (inputStream != null) {
            inputStream.close();
        }
        if (sc != null) {
            sc.close();
        }
    }

}

收件人：

somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt
somethingDifferent/txt

Answer 1

使用EditPadPro进行了测试，但这也可以在Notepad ++中工作：

搜索

((?:^.*/txt\r\n){4}^.*/txt$)

并替换为

\15

说明：

(           # Start capturing group no. 1, referenced by \1 in the replacement expression
 (?:        # Start a non-capturing group that matches...
  ^.*/txt   # a complete line ending in /txt
  \r\n      # and a (Windows-style) carriage return
 ){4}       # four times in a row.
 ^.*/txt$   # Then match a fifth line just like that, but without the CR
)           # End of capturing group

正则表达式查找并替换记事本中的每n个事件

1 个答案: