《精通正则表达式》第2章Java例子

最新推荐文章于 2024-08-13 20:49:07 发布

无无90

最新推荐文章于 2024-08-13 20:49:07 发布

阅读量291

点赞数

文章标签：正则表达式 regex Java

本文链接：https://blog.csdn.net/wlwh90/article/details/89684131

版权

Text-to-HTML转换例子（76页）

package zcw.com.lib_regex.master;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Created by zcw on 2019/4/28.<br><br>
 */
public class P72 {
    public static void main(String[] args) {
        String filePath = "lib_regex\\text.txt";
        StringBuilder builder = new StringBuilder();
        try {
            FileReader fileReader = new FileReader(filePath);
            BufferedReader bufferedReader = new BufferedReader(fileReader);

            // 从文件一行一行读取字符串到builder，每行以\n结束
            String content;
            while ((content = bufferedReader.readLine()) != null) {
                builder.append(content + "\n");
            }

            // 关闭文件
            fileReader.close();
            bufferedReader.close();
        }
        catch (IOException e) {
            System.err.println("Open " + filePath + "failed.\n" + e.getMessage());
            System.exit(0);
        }

        transfer(builder.toString());
    }

    /**
     * 把文本文件转换成html内容。
     * @param content 需要转换的内容
     */
    private static void transfer(String content) {
        // 匹配主机号正则表达式
        String hostName = "[-a-z0-9]+(\\.[-a-z0-9]+)*\\.(com|edu|info)";

        /**
         * 下标为[3]的正则表达式与书中不同；书中为"^\s*$",用此表达式，一直未能匹配成功，所以参考了书中81页内容，在每行开头插入<p>
         */
        String[] regex = {
                "&",        // 处理&字符
                "<",        // 处理<
                ">",        // 处理>
                "^([^\\n]+)",
                "\\b(\\w[-.\\w]*@" + hostName + ")\\b",
                "\\b(http://" + hostName + "\\b(/[-a-z0-9_:@&?=+,.!/~*'%$]*(?<![.,?!]))?)"
        };

        String[] replaceText = {
                "&amp;",
                "&lt;",
                "&gt;",
                "<p>",
        };

        for(int i = 0; i < 3; i++) {
            content = content.replaceAll(regex[i], replaceText[i]);
        }

        // 划分段落
        Pattern pattern = Pattern.compile(regex[3], Pattern.MULTILINE);
        Matcher matcher = pattern.matcher(content);
        while (matcher.find()) {
            content = matcher.replaceAll(replaceText[3] + "$1");
        }

        // 把E-mail地址转换为连接形式
        pattern = Pattern.compile(regex[4], Pattern.CASE_INSENSITIVE);
        matcher = pattern.matcher(content);
        while (matcher.find()) {
            content = matcher.replaceAll("<a href=\"mailto:$1\">$1</a>");
        }

        // 把HTTP URL地址转换为连接形式
        pattern = Pattern.compile(regex[5], Pattern.CASE_INSENSITIVE);
        matcher = pattern.matcher(content);
        while (matcher.find()) {
            content = matcher.replaceAll("<a href=\"$1\">$1</a>");
        }
        System.out.println(content);

        createHtml(content);
    }

    /**
     * 创建html文件
     * @param content
     */
    private static void createHtml(String content) {
        try {
            // 创建文件
            String filePath = "lib_regex\\test.html";
            File file = new File(filePath);
            if(!file.exists()) {
                file.createNewFile();
            }

            FileWriter fileWriter = new FileWriter(file);
            BufferedWriter bufferedWriter = new BufferedWriter(fileWriter);

            String[] html = {
                    "<!DOCTYPE html>\n",
                    "<html lang=\"en\">\n",
                    "<head>\n",
                    "<meta charset=\"UTF-8\">\n",
                    "<title>正则表达式测试</title>\n",
                    "</head>\n",
                    "<body>\n",
                    content,
                    "</body>\n",
                    "</html>\n",
            };

            // 把内容写入html文件
            for(String string : html) {
                bufferedWriter.write(string);
            }
            bufferedWriter.flush();

            fileWriter.close();
            bufferedWriter.close();
        }
        catch (IOException e) {
            System.err.println("Create html file failed.\n" + e.getMessage());
            return ;
        }
    }
}

text.txt文本内容如下：

This is a <TAG Test> sample file.
It has three lines.
That’s all
This is & test.
jfriedl@oreilly.com
http://www.baidu.com

Copy It has three lines.
Copy That’s <TAG Test> all
Copy jfriedl@oreilly.com
Copy http://www.baidu.com

代码运行结果如图所示：在这里插入图片描述
代码运行成功之后，会生成一个可直接在浏览器中打开的test.html页面，页面效果如图所示：

重复单词例子（77页）

package zcw.com.lib_regex.master;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.regex.Pattern;

/**
 * Created by zcw on 2019/4/29.<br><br>
 * main方法传入参数：lib_regex\\text2.txt
 */
public class TwoWord {
    public static void main(String[] args) {
        Pattern regex1 = Pattern.compile(
                "\\b" +              // 单词边界
                "([a-z]+)" +                // 匹配单词
                "((?:\\s|<[^>]+>)+)" +      // 匹配空格或者<tag>
                "(\\1\\b)",                 // \\1为反向引用，\\b为单词边界符
                Pattern.CASE_INSENSITIVE);

        /** \033[7m为控制台输出高亮起始符，\033[m为控制台高亮结束符<br />
         *  $1用于引用捕获组
         */
        String replace1 = "\033[7m$1\033[m$2\033[7m$3\033[m";

        /** 去掉所有未标记的行，如果没有\e转义符，既为未标记的行。<br>
         * {@link Pattern#MULTILINE}处理多行，对于书中所讲m模式。
         */
        Pattern regex2 = Pattern.compile("^(?:[^\\e]*\\n)+", Pattern.MULTILINE);

        /** 匹配每一行的开头 */
        Pattern regex3 = Pattern.compile("^([^\\n]+)", Pattern.MULTILINE);

        // 对于命令行的每个参数进行如下处理
        for(int i = 0; i < args.length; i++) {
            try {
                BufferedReader in = new BufferedReader(new FileReader(args[i]));
                String text;

                while ((text = Util.getPara(in)) != null) {
                    // 应用3条规则替换
                    text = regex1.matcher(text).replaceAll(replace1);
                    text = regex2.matcher(text).replaceAll("");
                    text = regex3.matcher(text).replaceAll(args[i] + ": $1");

                    // 显示结果
                    System.out.println(text);
                }
				
				in.close();
            }
            catch (IOException e) {
                System.err.println("can't read [" + args[i] + "]: " + e.getMessage());
            }
        }

        System.out.println("\033[7m一句用于测试高亮的话\033[m");
    }
}

package zcw.com.lib_regex.master;

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

/**
 * Created by zcw on 2019/4/29.<br><br>
 */
public class Util {

    /**
     * 用于读入“一段”文本
     * @param in 字符流
     * @return 返回一段文字，直到遇到空行
     * @throws IOException
     */
    public static String getPara(BufferedReader in) throws IOException {
        StringBuffer buffer = new StringBuffer();
        String line;

        // 如果遇到空行，则结束
        while ((line = in.readLine()) != null && (buffer.length() == 0 || line.length() != 0)) {
            buffer.append(line + "\n");
        }

        return buffer.length() == 0 ? null : buffer.toString();
    }
}

例子测试文本内容如下：

This is a sample file
File three lines pattern.
It has three three lines.
That’s all all
check for doubled words (such as thisthis thisthis), a common problem with
of this chapter. If you knew thethe <afsdf> thethe specific doubled word to find (such
jfriedl@oreilly.com
http://www.baidu.com

check for doubled words (such as thisthis thisthis), a common problem with
of this chapter. If you knew thethe <afsdf> thethe specific doubled word to find (such
jfriedl@oreilly.com
http://www.baidu.com