Java实现统计文件夹下所有文件的字数

import java.io.*;
import java.nio.charset.StandardCharsets;
import java.nio.file.*;
import java.nio.file.attribute.BasicFileAttributes;
import java.util.regex.Pattern;

public class WordCounter {
    private static final Pattern WORD_PATTERN = Pattern.compile("[a-zA-Z]+|[\u4e00-\u9fa5]");
    private static long totalWords = 0;

    public static void main(String[] args) throws IOException {
        Path startPath = Paths.get("path/to/your/directory"); // replace with your directory
        Files.walkFileTree(startPath, new SimpleFileVisitor<Path>() {

            @Override
            public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
                if (file.toString().endsWith(".md")) {
                    totalWords += countWords(file);
                }
                return FileVisitResult.CONTINUE;
            }

            private long countWords(Path file) throws IOException {
                long count = 0;
                try (BufferedReader reader = Files.newBufferedReader(file, StandardCharsets.UTF_8)) {
                    String line;
                    while ((line = reader.readLine()) != null) {
                        count += WORD_PATTERN.split(line).length;
                    }
                }
                return count;
            }

            @Override
            public FileVisitResult postVisitDirectory(Path dir, IOException exc) {
                System.out.println("Visited directory: " + dir + ", total words: " + totalWords);
                return FileVisitResult.CONTINUE;
            }
        });
        System.out.println("Total words in all .md files: " + totalWords);
    }
}

import java.io.File;
import java.io.FileNotFoundException;
import java.util.Scanner;

public class WordCount {
    public static void main(String[] args) {
        // 读取文档路径
        String filePath = "path/to/your/document.txt";
        
        try {
            // 创建文件对象
            File file = new File(filePath);
            
            // 创建Scanner对象，用于读取文件内容
            Scanner scanner = new Scanner(file);
            
            // 统计字符个数的变量
            int count = 0;
            
            // 逐行读取文件内容，并统计字符个数
            while (scanner.hasNextLine()) {
                String line = scanner.nextLine();
                count += line.replaceAll("\\s+", "").length();
            }
            
            // 输出统计结果
            System.out.println("文档的字数是：" + count);
            
            // 关闭Scanner对象
            scanner.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    }
}

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;

public class WordCount {
    public static void main(String[] args) {
        String filename = "example.txt"; // 替换为要统计字数的文件路径

        int wordCount = 0;
        int spaceCount = 0;
        int punctuationCount = 0;

        try (BufferedReader reader = new BufferedReader(new FileReader(filename))) {
            String line;
            while ((line = reader.readLine()) != null) {
                String[] words = line.split("\\s+");
                wordCount += words.length;
                spaceCount += words.length - 1;
                
                for (char c : line.toCharArray()) {
                    if (Character.isWhitespace(c)) {
                        spaceCount++;
                    } else if (Character.isLetterOrDigit(c) || Character.isSpaceChar(c)) {
                        // do nothing
                    } else {
                        punctuationCount++;
                    }
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }

        System.out.println("字数: " + wordCount);
        System.out.println("空格数: " + spaceCount);
        System.out.println("标点符号数: " + punctuationCount);
    }
}

import os

DirPath = 'D:/下载/docs'
resultArray = []
listCount = 0
content = ''
resultCount = 0


def check_contain_chinese(check_str, fileName):
    countResult = 0
    for ch in check_str:
        if u'\u4e00' <= ch <= u'\u9fff':
            countResult += 1
    resultArray.append(countResult)
    print(str(fileName) + "文件的中文字数是：" + str(countResult) + '\n')


if __name__ == "__main__":
    for item in os.listdir(DirPath):
        print(DirPath + '/' + item)
        listCount += 1
        f = open(DirPath + '/' + item, 'r', encoding='utf-8')
        content = f.read()
        check_contain_chinese(content, item)

    for num in resultArray:
        resultCount += num
    print("累计文件个数：" + str(listCount) + "个")
    print("累计中文字符：" + str(resultCount) + "个")