Java文件分割与合并_文本多样化分割与合并_MT管理器插件

用Java实现二进制文件的分割与合并，大小文本文件的多样化分割与合并，文件排序算法：按自然语言排序

https://pan.baidu.com/s/1Lhzb6dwZOJ1Yy5Lu0ELQTg&pwd=9qze

#1. 代码
Main.java

import android.support.annotation.NonNull;
import java.util.Arrays;
import java.util.List;

import bin.mt.plugin.api.translation.BaseTranslationEngine;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.FileReader;
import java.io.BufferedReader;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.json.JSONArray;
import org.json.JSONObject;
import android.content.SharedPreferences;
import java.io.*;

public class Main extends BaseTranslationEngine {

	public Main() {
		super(new ConfigurationBuilder()
				// 关闭「跳过已翻译词条」
				.setForceNotToSkipTranslated(true).build());
	}

	//分割，参数说明：需分割文件的全路径（输入），切割的文件大小（设置），切割后的文件单位默认为MB（设置），分割后文件存放的文件夹全路径，待分割文件格式
	public void Split(String SrcFilePath, long SingleGoalFileSize, String SingleFileUnit, String GoalFileDirectory,
			int format) {
		//SingleGoalFileSize 文件大小    SingleFileUnit 文件单位默认单位：MB  ，分割后文件路径和目录（省略时为当前文件夹）， 默认各类文件有自己的分割方式

		SharedPreferences preferences = getContext().getPreferences();
		String op = preferences.getString("operate", "");//分割方式
		String name_flag = preferences.getString("name_flag", "-🆎标识");
		String[] nf = new String[] { "", "" };//批处理文件在该字符数组之间嵌入序号为标识符
		int ab = name_flag.lastIndexOf("🆎");//根据最后一个🆎来识别
		if (ab == -1) {
			if (name_flag.equals("")) {
				nf[0] = "-";
				nf[1] = "标识";
			} else {
				nf[0] = name_flag;
			}
		} else {
			nf[0] = name_flag.substring(0, ab);
			nf[1] = name_flag.substring(ab).replace("🆎", "");
		}

		if (SrcFilePath.equals("") || SrcFilePath == null) {
			System.out.println("分割失败!");
			return;
		}

		File SrcFile = new File(SrcFilePath); //新建文件
		long SrcFileSize = SrcFile.length();//源文件的大小
		long SingleFileSize = 1;//分割后的单个文件大小(以字节为单位)
		int unit = 1;//分割后的单个文件单位
		//SingleFileUnit=SingleFileUnit.toUpperCase();
		switch (SingleFileUnit) {
		case "B":
			SingleFileSize = SingleGoalFileSize;
			unit = (int) SingleGoalFileSize;
			break;
		case "KB":
			SingleFileSize = 1024 * SingleGoalFileSize;
			if (SingleGoalFileSize > 2048)
				unit = 1024 * 1024;
			else
				unit = (int) SingleFileSize;
			break;
		case "GB":
			unit = 1024 * 1024;
			SingleFileSize = unit * 1024 * SingleGoalFileSize;
			unit *= 10;
			break;
		default:
			unit = 1024 * 1024;
			SingleFileSize = unit * SingleGoalFileSize;//默认单位MB
		}

		int GoalFileNum = (int) (SrcFileSize / SingleFileSize); //获取分割后文件的数量
		GoalFileNum = SrcFileSize % SingleFileSize == 0 ? GoalFileNum : GoalFileNum + 1; //计算总的文件大小

		int x1 = SrcFilePath.lastIndexOf("/"); //获取文件路径的分隔符位置
		int x2 = SrcFilePath.lastIndexOf("."); //获取文件的后缀位置
		String SrcFileName, fc = "";

		if (x2 < x1)
			SrcFileName = SrcFilePath.substring(x1 + 1);
		else {
			fc = SrcFilePath.substring(x2);
			SrcFileName = SrcFilePath.substring(x1 + 1, x2); //截取文件名，如果要分割的文件没有后缀，则GoalFileDirectory参数不能为空，因为在文件位置无法新建同名文件夹
		}
		if (GoalFileDirectory == null || GoalFileDirectory.equals("")) {
			GoalFileDirectory = SrcFilePath.substring(0, x1);
		}
		File goalDirectory = new File(GoalFileDirectory + File.separator + SrcFileName + File.separator);
		if (!goalDirectory.exists()) {
			goalDirectory.mkdirs();
		}
		GoalFileDirectory = GoalFileDirectory + File.separator + SrcFileName + File.separator + SrcFileName + nf[0];//File.separator 的作用相当于 ' \  '所以用 File.separator 保证了在任何系统下不会出错。
		try {
			FileInputStream fis = new FileInputStream(SrcFilePath); //新建输入流对象
			//String bm = fc.matches("\\.apk|\\.zip|\\.rar|\\.7z|\\.tar|\\.gz|\\.exe|\\.dll|\\.so|\\.dex|\\.mp3|\\.mp4|\\.jpg") ? "ISO-8859-1" : "UTF-8";
			//注意根据文件编码格式指定InputStreamReader的编码
			InputStreamReader reader = null;//new InputStreamReader(fis,"UTF-8");//默认UTF-8 GBK ASCII  ISO-8859-1  Windows-1252
			BufferedReader bufferedReader = null;//new BufferedReader(reader);
			//FileOutputStream fos = null;//new FileOutputStream(CompleteSingleGoalFilePath);
			//BufferedOutputStream bos = null;//new BufferedOutputStream(fos);  //包装
			String tem = null, line = null, CompleteSingleGoalFilePath;
			StringBuilder textbatch = new StringBuilder();//.delete(0,sb.length());
			byte bytes[];

			if (op.equals("file") || (op.equals("fit") && format == 0)) {
				bytes = new byte[unit];//每次读取文件的大小
				int len = -1;
				BufferedInputStream bis = new BufferedInputStream(fis);
				FileOutputStream fos = null;
				BufferedOutputStream bos = null;
				for (int i = 0; i < GoalFileNum; i++) {
					//分割后的单个文件完整路径名
					CompleteSingleGoalFilePath = GoalFileDirectory + String.valueOf(i) + nf[1] + fc;

					fos = new FileOutputStream(CompleteSingleGoalFilePath);
					bos = new BufferedOutputStream(fos); //包装
					long count = 0;
					while ((len = bis.read(bytes)) != -1) {
						bos.write(bytes, 0, len);//从源文件读取规定大小的字节数写入到单个目标文件中
						count += len;
						if (count >= SingleFileSize)
							break;
					}
					bos.flush();
					bos.close();
					fos.close();
				}
				bis.close();
				fis.close();
			} else if (op.equals("json") || (op.equals("fit") && format == 3)) {
				reader = new InputStreamReader(fis, "UTF-8");//默认UTF-8 GBK ASCII ISO-8859-1  Windows-1252
				bufferedReader = new BufferedReader(reader);
				FileWriter fw = null;
				BufferedWriter bufw = null;
				while ((line = bufferedReader.readLine()) != null) {
					textbatch.append(line).append(System.getProperty("line.separator"));
				}
				JSONArray jsonArray = new JSONArray(textbatch.toString());
				textbatch.delete(0, textbatch.length());
				for (int i = 0; i < jsonArray.length(); i++) {
					JSONObject jsonObject = jsonArray.getJSONObject(i);
					CompleteSingleGoalFilePath = GoalFileDirectory + String.valueOf(i) + nf[1] + fc;
					fw = new FileWriter(CompleteSingleGoalFilePath, false); //创建FileWriter类对象, true从尾部不覆盖
					bufw = new BufferedWriter(fw); //创建BufferedWriter对象
					bufw.write(jsonObject.toString());
					bufw.flush(); //清空流
					bufw.close(); //关闭BufferedWriter流
					fw.close(); //关闭FileWriter流
				}
				bufferedReader.close();
				reader.close();
			} else {
				reader = new InputStreamReader(fis, "UTF-8");//默认UTF-8 GBK ASCII ISO-8859-1  Windows-1252
				bufferedReader = new BufferedReader(reader);
				String remove = preferences.getString("Remover_regular", "");//正则查找🆎正则替换
				String spliter = preferences.getString("spliter", "");//分割🈹0指令 换行符：\r|\n
				//String[] rp = remove.indexOf("🆎")>0 ? remove.split("🆎", 2) : remove.split("$", 5);//split不可靠，空字符串不被解析,,,，即使大参数也不行
				String[] rp = new String[] { "", "" };
				ab = remove.lastIndexOf("🆎");//根据最后一个🆎来识别
				if (ab != -1) {
					if (ab == 0)
						rp[0] = remove.replace("🆎", "");
					else {
						rp[0] = remove.substring(0, ab);
						rp[1] = remove.substring(ab).replace("🆎", "");
						//replaceAll()的参数是正则表达式，replaceAll("[\\t\\n\\r]", "");替换换行符，要替换成换行符String.replace("@","\t\n")，,前后参数不同！！！
						rp[1] = rp[1].replaceAll("\\\\n", "\n").replaceAll("\\\\t", "\t");//将储存的\\n变成换行符
					}
				} else
					rp[0] = remove;
				//boolean flagsp = false;
				//if(!spliter.equals("")) flagsp = true;
				Pattern prp = Pattern.compile(spliter, Pattern.MULTILINE);//多行匹配^ $
				Matcher mrp;
				//如果文本匹配分割框输入了任意字符串，将开启匹配分割模式
				if (spliter.equals("")) {
					//文本文件按自定义字符串长度分割粗略