Java 以最快的方式读取 200 万行的文本文件

file java

2022-09-01 03:00:34

目前我正在使用扫描仪/文件阅读器，并使用while hasnextline。我认为这种方法效率不高。有没有其他方法可以读取具有类似功能的文件？

public void Read(String file) {
        Scanner sc = null;


        try {
            sc = new Scanner(new FileReader(file));

            while (sc.hasNextLine()) {
                String text = sc.nextLine();
                String[] file_Array = text.split(" ", 3);

                if (file_Array[0].equalsIgnoreCase("case")) {
                    //do something
                } else if (file_Array[0].equalsIgnoreCase("object")) {
                    //do something
                } else if (file_Array[0].equalsIgnoreCase("classes")) {
                    //do something
                } else if (file_Array[0].equalsIgnoreCase("function")) {
                    //do something
                } 
                else if (file_Array[0].equalsIgnoreCase("ignore")) {
                    //do something
                }
                else if (file_Array[0].equalsIgnoreCase("display")) {
                    //do something
                }
            }

        } catch (FileNotFoundException e) {
            System.out.println("Input file " + file + " not found");
            System.exit(1);
        } finally {
            sc.close();
        }
    }

答案 1

你会发现 BufferedReader.readLine（） 和你需要的一样快：你可以用它每秒读取数百万行。更有可能的是，字符串拆分和处理会导致您遇到的任何性能问题。

答案 2

我做了一个比较不同方法的要点：

import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
import java.util.Scanner;
import java.util.function.Function;

public class Main {

    public static void main(String[] args) {

        String path = "resources/testfile.txt";
        measureTime("BufferedReader.readLine() into LinkedList", Main::bufferReaderToLinkedList, path);
        measureTime("BufferedReader.readLine() into ArrayList", Main::bufferReaderToArrayList, path);
        measureTime("Files.readAllLines()", Main::readAllLines, path);
        measureTime("Scanner.nextLine() into ArrayList", Main::scannerArrayList, path);
        measureTime("Scanner.nextLine() into LinkedList", Main::scannerLinkedList, path);
        measureTime("RandomAccessFile.readLine() into ArrayList", Main::randomAccessFileArrayList, path);
        measureTime("RandomAccessFile.readLine() into LinkedList", Main::randomAccessFileLinkedList, path);
        System.out.println("-----------------------------------------------------------");
    }

    private static void measureTime(String name, Function<String, List<String>> fn, String path) {
        System.out.println("-----------------------------------------------------------");
        System.out.println("run: " + name);
        long startTime = System.nanoTime();
        List<String> l = fn.apply(path);
        long estimatedTime = System.nanoTime() - startTime;
        System.out.println("lines: " + l.size());
        System.out.println("estimatedTime: " + estimatedTime / 1_000_000_000.);
    }

    private static List<String> bufferReaderToLinkedList(String path) {
        return bufferReaderToList(path, new LinkedList<>());
    }

    private static List<String> bufferReaderToArrayList(String path) {
        return bufferReaderToList(path, new ArrayList<>());
    }

    private static List<String> bufferReaderToList(String path, List<String> list) {
        try {
            final BufferedReader in = new BufferedReader(
                new InputStreamReader(new FileInputStream(path), StandardCharsets.UTF_8));
            String line;
            while ((line = in.readLine()) != null) {
                list.add(line);
            }
            in.close();
        } catch (final IOException e) {
            e.printStackTrace();
        }
        return list;
    }

    private static List<String> readAllLines(String path) {
        try {
            return Files.readAllLines(Paths.get(path));
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    private static List<String> randomAccessFileLinkedList(String path) {
        return randomAccessFile(path, new LinkedList<>());
    }

    private static List<String> randomAccessFileArrayList(String path) {
        return randomAccessFile(path, new ArrayList<>());
    }

    private static List<String> randomAccessFile(String path, List<String> list) {
        try {
            RandomAccessFile file = new RandomAccessFile(path, "r");
            String str;
            while ((str = file.readLine()) != null) {
                list.add(str);
            }
            file.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return list;
    }

    private static List<String> scannerLinkedList(String path) {
        return scanner(path, new LinkedList<>());
    }

    private static List<String> scannerArrayList(String path) {
        return scanner(path, new ArrayList<>());
    }

    private static List<String> scanner(String path, List<String> list) {
        try {
            Scanner scanner = new Scanner(new File(path));
            while (scanner.hasNextLine()) {
                list.add(scanner.nextLine());
            }
            scanner.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
        return list;
    }


}

run： BufferedReader.readLine（） into LinkedList， lines： 1000000， estimateTime： 0.105118655

run： BufferedReader.readLine（） into ArrayList，行： 1000000，估计时间： 0.072696934

run： Files.readAllLines（），行： 1000000，估计时间： 0.087753316

run： Scanner.nextLine（） into ArrayList， lines： 1000000， estimateTime： 0.743121734

run： Scanner.nextLine（）到 LinkedList 中，行数： 1000000，估计时间： 0.867049885

run： RandomAccessFile.readLine（） into ArrayList， lines： 1000000， estimateTime： 11.413323046

run： RandomAccessFile.readLine（） into LinkedList， lines： 1000000， estimateTime： 11.423862897

BufferedReader是最快的，也是可以接受的，由于正则表达式很慢，是不可接受的Files.readAllLines()ScannerRandomAccessFile