java8--项目--词频统计

package stream;

import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.List;
import java.util.regex.Pattern;
import java.util.stream.Stream;

public class CountLongWords0320250103 {
    public static void main(String[] args) throws IOException {
        long count;
        count = Listcount();  //for each遍历数组
        System.out.println(count);
        count = ListToStreamcount();//转换成流后用filter方法lambda表达式传入条件过滤出
        System.out.println(count);
        count = ListToParallelStreamcount();  //上一个的多线程版
        System.out.println(count);
        count = Streamcount();  //以非字母分隔符分割后立刻转换成流，用filter过滤
        System.out.println(count);
    }

    public static long Streamcount(){
        String contents = null;
        try {
            contents = new String(
                    Files.readAllBytes(
                            Paths.get("C:\\Users\\Administrator\\IdeaProjects\\untitled2\\src\\gutenberg\\alice30.txt")),
                    StandardCharsets.UTF_8
            );
        } catch (IOException e) {
            e.printStackTrace();
        }
        Stream<String> words = Pattern.compile("\\PL+").splitAsStream(contents);
        long count = 0;
        count = words.filter(w->w.length() > 12).count();
        return count;
    }

    public static long ListToParallelStreamcount(){
        String contents = null;
        try {
            contents = new String(
                    Files.readAllBytes(
                            Paths.get("C:\\Users\\Administrator\\IdeaProjects\\untitled2\\src\\gutenberg\\alice30.txt")),
                    StandardCharsets.UTF_8
            );
        } catch (IOException e) {
            e.printStackTrace();
        }
        List<String> words = Arrays.asList(contents.split("\\PL+"));
        long count = 0;
        count = words.parallelStream().filter(w -> w.length() > 12).count();
        return  count;
    }

    public static long ListToStreamcount(){
        String contents = null;
        try {
            contents = new String(
                    Files.readAllBytes(
                            Paths.get("C:\\Users\\Administrator\\IdeaProjects\\untitled2\\src\\gutenberg\\alice30.txt")),
                    StandardCharsets.UTF_8
            );
        } catch (IOException e) {
            e.printStackTrace();
        }
        List<String> words = Arrays.asList(contents.split("\\PL+"));
        long count = 0;
        count = words.stream().filter(w -> w.length() > 12).count();
        return  count;
    }

    
    public static long Listcount(){
        String contents = null;
        try {
            contents = new String(
                    Files.readAllBytes(
                            Paths.get("C:\\Users\\Administrator\\IdeaProjects\\untitled2\\src\\gutenberg\\alice30.txt")),
                    StandardCharsets.UTF_8
            );
        } catch (IOException e) {
            e.printStackTrace();
        }
        List<String> words = Arrays.asList(contents.split("\\PL+"));
        long count = 0;
        for (String w:
                words) {
            if (w.length()>12) count++;
        }
        return count;
    }
}

ps：
1.java虚拟机在项目根目录下启动
2.路径还可以用.\\src\\gutenberg\\alice30.txt或./src/gutenberg/alice30.txt，也可以反斜杠和斜杠混用，比如./src/gutenberg\\alice30.txt,路径里的反斜杠需要用反斜杠转义，这里已经转义了
20250104第一次追加pps：
补充方法--统计行：

public static long LinesStreamcount(){
    long count = 0;
    Path path = Paths.get("./src/gutenberg/alice30.txt");
    try {
        try(Stream<String> lines = Files.lines(path)){
            count = lines.filter(w -> w.length() > 12).count();
        }
    } catch (IOException e) {
        e.printStackTrace();
    }
    System.out.println(count);
    return count;
}