通过Java实现Linux系统下grep指令的功能

在Linux系统下grep指令常见的使用方式有如下两种：

1. grep pattern files – 搜索 files 中匹配 pattern 的内容
2. grep -r pattern dir – 递归搜索 dir 中匹配 pattern 的内容

现有如下方法可实现在Windows系统下通过Java代码实现与第一种使用方法相同的功能：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.nio.CharBuffer;
import java.nio.MappedByteBuffer;
import java.nio.channels.FileChannel;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;

public class Grep {

	private static Charset charset = Charset.forName("utf-8");
	private static CharsetDecoder decoder = charset.newDecoder();

	private static Pattern linePattern = Pattern.compile(".*\r?\n");
	private static Pattern pattern;

	public static void main(String[] args) {
		if (args.length < 2) {
			System.err.println("Usage : java Grep pattern file...");
			return ;
		}
		compile(args[0]);
		for (int i = 1; i < args.length; i++) {
			File f = new File(args[i]);
			try {
				grep(f);
			} catch (IOException e) {
				System.err.println(f + ":" + e);
			}
		}
	}

	private static void grep(File f) throws IOException {
		//取得 FileChannel
		FileInputStream fis = new FileInputStream(f);
		FileChannel fc = fis.getChannel();
		// Get the file's size and then map it into memory
		int size = (int) fc.size();
		MappedByteBuffer bb = fc.map(FileChannel.MapMode.READ_ONLY, 0, size);
		//把 字节buffer decode 成 charBuffer
		CharBuffer cb = decoder.decode(bb);
		grep(f, cb);
		fc.close();
	}

	private static void grep(File f, CharBuffer cb) {
		Matcher lm = linePattern.matcher(cb); //line matcher
		Matcher pm = null; //pattern matcher
		int lines = 0;
		while (lm.find()) {
			lines++;
			CharSequence curLineCs = lm.group();//the current line
			if (pm == null) {
				pm = pattern.matcher(curLineCs);
			} else {
				pm.reset(curLineCs);
			}
			if (pm.find()) {
				System.out.println(f + "→" + lines + ":" + curLineCs);
			}
			if (lm.end() == cb.limit()) { //文件最后
				break;
			}
		}
	}

	private static void compile(String pat) {
		try {
			pattern = Pattern.compile(pat);
		} catch (PatternSyntaxException e) {
			System.err.println(e.getMessage());
			System.exit(1);
		}
	}
}

执行java Grep abcd 1.txt 运行效果图如下：

也可以同时搜索多个文件，执行java Grep abcd 1.txt 2.txt 3.txt 4.txt 运行效果如下：

至此，在Windows系统下通过Java代码实现了与Linux系统写grep命令第一种使用方法相同的功能