sheepit-shadow-nabber/src/main/java/com/sheepit/client/Utils.java

/*
 * Copyright (C) 2010-2014 Laurent CLOUET
 * Author Laurent CLOUET <laurent.clouet@nopnop.net>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; version 2
 * of the License.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

package com.sheepit.client;

import net.lingala.zip4j.ZipFile;
import net.lingala.zip4j.exception.ZipException;
import net.lingala.zip4j.io.inputstream.ZipInputStream;
import net.lingala.zip4j.model.LocalFileHeader;

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintWriter;
import java.io.StringWriter;
import java.net.URLConnection;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Calendar;
import java.util.Date;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.TimeZone;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

/**
 * Provides various general utility methods for the SheepIt client codebase
 */
public class Utils {
	
	/**
	 * This is a hashmap of media types currently consisting of two image formats, tga and exr
	 * The first string is the filename extension.
	 * The second string is the media/MIME type
	 */
	private static Map<String, String> mimeTypes = new HashMap<>();
	
	static {
		mimeTypes.put(".tga", "image/tga");
		mimeTypes.put(".exr", "image/x-exr");
	}
	
	/**
	 * Extracts (and optionally decrypts) contents of a given zip file to a target directory
	 *
	 * @param zipFileName_ Path to the zipfiles
	 * @param destinationDirectory Path to the target directory where files will be extracted to
	 * @param password Optional password for decrypting the zip archive which will only be used if it's not null and if the zip is truly encrypted
	 * @param log The SheepIt Debug log where log messages might be logged into
	 * @return A status code as an integer, -1 if it encounters a ZipException, 0 otherwise
	 */
	public static int unzipFileIntoDirectory(String zipFileName_, String destinationDirectory, char[] password, Log log) {
		try {
			ZipFile zipFile = new ZipFile(zipFileName_);
//			unzipParameters.setIgnoreDateTimeAttributes(true);
			
			if (password != null && zipFile.isEncrypted()) {
				zipFile.setPassword(password);
			}
//			zipFile.extractAll(destinationDirectory, unzipParameters);
			zipFile.extractAll(destinationDirectory);
		}
		catch (ZipException e) {
			StringWriter sw = new StringWriter();
			PrintWriter pw = new PrintWriter(sw);
			e.printStackTrace(pw);
			log.debug("Utils::unzipFileIntoDirectory(" + zipFileName_ + "," + destinationDirectory + ") exception " + e + " stacktrace: " + sw.toString());
			return -1;
		}
		return 0;
	}
	
	/**
	 * Takes the list of zip file chunks and combines them to a zip archive in memory to
	 * extract (and optionally decrypt) the contents to the target directory
	 *
	 * @param full_path_chunks List of paths to the chunks of which a zip file will be constructed from
	 * @param destinationDirectory Path to the target directory where files will be extracted to
	 * @param password Optional password for decrypting the zip archive which will only be used if it's not null
	 * @param log The SheepIt Debug log where log messages might be logged into
	 * @return A status code as an integer, -1 if it encounters a IOException, 0 otherwise
	 */
	public static int unzipChunksIntoDirectory(List<String> full_path_chunks, String destinationDirectory, char[] password, Log log) {
		try {
			// STEP 1: Create a ChunkInputStream, which will read the chunks' contents in order
			ChunkInputStream chunkInputStream = new ChunkInputStream(full_path_chunks.stream().map(Paths::get).collect(Collectors.toList()));
			
			// STEP 2: unzip the zip like before
			ZipInputStream zipInputStream = new ZipInputStream(chunkInputStream);
			if (password != null) {
				zipInputStream.setPassword(password);
			}
			LocalFileHeader fileHeader = null;
			while ((fileHeader = zipInputStream.getNextEntry()) != null) {
				String outFilePath = destinationDirectory + File.separator + fileHeader.getFileName();
				File outFile = new File(outFilePath);
				
				//Checks if the file is a directory
				if (fileHeader.isDirectory()) {
					outFile.mkdirs();
					continue;
				}
				
				File parentDir = outFile.getParentFile();
				if (parentDir.exists() == false) {
					parentDir.mkdirs();
				}
				
				FileOutputStream os = new FileOutputStream(outFile);
				
				int readLen = -1;
				byte[] buff = new byte[1024];
				
				//Loop until End of File and write the contents to the output stream
				while ((readLen = zipInputStream.read(buff)) != -1) {
					os.write(buff, 0, readLen);
				}
				
				os.close();
			}
			zipInputStream.close();
		}
		catch (IOException e) {
			StringWriter sw = new StringWriter();
			PrintWriter pw = new PrintWriter(sw);
			e.printStackTrace(pw);
			log.debug("Utils::unzipChunksIntoDirectory exception " + e + " stacktrace: " + sw.toString());
			return -1;
		}
		
		return 0;
	}
	
	/**
	 * Gets a MD5 checksum either from the cache or computes it and puts it into the cache
	 *
	 * @param path_of_file_ Path of the file to get the MD5 checksum for
	 * @return the string The MD5 checksum
	 */
	public static String md5(String path_of_file_) {
		Md5 md5 = new Md5();
		return md5.get(path_of_file_);
	}
	
	/**
	 * Takes an array of bytes and encodes them as a string of hexadecimal digits
	 * @param bytes An array of bytes to be encoded, the order of which dictates the output in big-endian
	 * @return A string of hexadecimal digits, two digits for a byte each. Constructed from left to right.
	 */
	public static String convertBinaryToHex(byte[] bytes) {
		StringBuilder hexStringBuilder = new StringBuilder();
		for (byte aByte : bytes) {
			char[] hex = new char[2];
			hex[0] = Character.forDigit((aByte >> 4) & 0xF, 16);
			hex[1] = Character.forDigit((aByte & 0xF), 16);
			hexStringBuilder.append(new String(hex));
		}
		return hexStringBuilder.toString();
	}
	
	/**
	 * Returns the latest (highest) of a modification time of a file in the directory recursively
	 * @param directory_ The root directory from which to search from
	 * @return The latest (highest) modification time in milliseconds since epoch or 0 if no files exist in the target directory tree
	 */
	public static double lastModificationTime(File directory_) {
		double max = 0.0;
		if (directory_.isDirectory()) {
			File[] list = directory_.listFiles();
			if (list != null) {
				for (File aFile : list) {
					double max1 = lastModificationTime(aFile);
					if (max1 > max) {
						max = max1;
					}
				}
			}
		}
		else if (directory_.isFile()) {
			return directory_.lastModified();
		}
		
		return max;
	}
	
	/**
	 * Deletes a file or directory recursively
	 * @param file The filesystem element to be deleted
	 */
	public static void delete(File file) {
		if (file == null) {
			return;
		}
		if (file.isDirectory()) {
			String[] files = file.list();
			if (files != null) {
				if (files.length != 0) {
					for (String temp : files) {
						File fileDelete = new File(file, temp);
						delete(fileDelete);
					}
				}
			}
		}
		file.delete();
	}
	
	/**
	 * Converts a number string to a number.
	 * @param in The number string with an ending up to Tera (10^12)
	 * Example inputs: "32", "10k", "100K", "100G", "1.3G", "0.4T"
	 * @return A numerical representation of the number string
	 */
	public static long parseNumber(String in) {
		in = in.trim();
		in = in.replaceAll(",", ".");
		try {
			return Long.parseLong(in);
		}
		catch (NumberFormatException e) {
		}
		final Matcher m = Pattern.compile("([\\d.,]+)\\s*(\\w)").matcher(in);
		m.find();
		long scale = 1;
		switch (Character.toUpperCase(m.group(2).charAt(0))) {
			case 'T':
				scale *= 1000; //Multiply by 1000 each time the higher the metric prefix
			case 'G': //Note the lack of break statements, thus it executes through
				scale *= 1000;
			case 'M':
				scale *= 1000;
			case 'K':
				scale *= 1000;
				break;
		}
		return Math.round(Double.parseDouble(m.group(1)) * scale);
	}
	
	/**
	 * Gives a human-readable representation in hours, minutes and seconds when a given date will be reached
	 * @param date The target time
	 * @return A string in the format of Xh Ymin Ys as long as none of them are zero
	 * Examples: 69h 42min 13s, 20min, 1h 23s
	 */
	public static String humanDuration(Date date) {
		Calendar calendar = Calendar.getInstance(TimeZone.getTimeZone("GMT"));
		calendar.setTime(date);
		
		int hours = (calendar.get(Calendar.DAY_OF_MONTH) - 1) * 24 + calendar.get(Calendar.HOUR_OF_DAY);
		int minutes = calendar.get(Calendar.MINUTE);
		int seconds = calendar.get(Calendar.SECOND);
		
		String output = "";
		if (hours > 0) {
			output += hours + "h ";
		}
		if (minutes > 0) {
			output += minutes + "min ";
		}
		if (seconds > 0) {
			output += seconds + "s";
		}
		return output;
	}
	
	/**
	 * Checks for a given path if there is enough free space i.e. at-least over half a megabyte.
	 * If the first check fails, it polls again for up to 3 times with increasing delay
	 * to work around a Java limitation where getUsableSpace might just return 0 on a busy disk
	 * @param destination_ The path to check the for enough free space for
	 * @param log The SheepIt Debug log where log messages might be logged into
	 * @return True if there is not enough free space, false otherwise
	 */
	public static boolean noFreeSpaceOnDisk(String destination_, Log log) {
		try {
			File file = new File(destination_);
			for (int i = 0; i < 5; i++) { //We poll repeatedly because getUsableSpace() might just return 0 on busy disk IO
				long space = file.getUsableSpace();
				if (space > 512 * 1024) { // at least the same amount as Server.HTTPGetFile
					return false; // If we are not "full", we are done, no need for additional polling
				} else if (i < 4) {
					long time = (long) (
						Math.random() * (100 - 50 + 1) + 50 + //Wait between 50 and 100 milliseconds,
						(i * 500) //add 500 ms on each failed poll
					);
					log.debug("Utils::Not enough free disk space(" + space + ") encountered on try " + i + ", waiting " + time + "ms");
					Thread.sleep(time);
				}
			}
			return true;
		}
		catch (SecurityException | InterruptedException e) {
		}
		
		return false;
	}
	
	/**
	 * Tries to detect media/MIME type of given file based on characteristics like the file contents or file extension
	 * @param file Path to the file for which to detect the MIME type for
	 * @return The MIME type of the file
	 * @throws IOException If an I/O error occurs
	 */
	public static String findMimeType(String file) throws IOException {
		String mimeType = Files.probeContentType(Paths.get(file));
		if (mimeType == null) {
			InputStream stream = new BufferedInputStream(new FileInputStream(file));
			mimeType = URLConnection.guessContentTypeFromStream(stream);
		}
		if (mimeType == null) {
			mimeType = URLConnection.guessContentTypeFromName(file);
		}
		
		if (mimeType == null || (mimeType.equals("image/aces") && file.toLowerCase().endsWith(".exr"))) {
			try {
				String extension = file.substring(file.lastIndexOf('.'));
				mimeType = mimeTypes.get(extension);
			}
			catch (IndexOutOfBoundsException e) {
				e.printStackTrace();
			}
		}

		return mimeType;
	}
	
	/**
	 * Format a number of bytes into a human-readable format with metric prefixes (base 1024)
	 * @param bytes The amount of bytes to convert
	 * @return Human-readable formatted string (respecting locale of the machine)
	 * representing the amount of bytes
	 * Examples: 4.20GB, 20.00TB, 3.69MB
	 * In a different locale (here for German):
	 * Examples: 4,20GB, 20,00TB, 3,69MB
	 */
	public static String formatDataConsumption(long bytes) {
		float divider = 0;
		String suffix = "";
		
		if (bytes > 1099511627776f) {    // 1TB
			divider = 1099511627776f;
			suffix = "TB";
		}
		else if (bytes > 1073741824) {    // 1GB
			divider = 1073741824;
			suffix = "GB";
		}
		else {    // 1MB
			divider = 1048576;
			suffix = "MB";
		}
		
		return String.format("%.2f%s", (bytes / divider), suffix);
	}
	
	/**
	 * Sometimes on Windows, delete of file return false for no obvious reason.
	 * Wait a bit and try again
	 */
	public static boolean deleteFile(File file) {
		if (file.delete() == false) {
			// maybe the system was busy
			try {
				Thread.sleep(4000);
			}
			catch (InterruptedException e) {
			}
			System.gc();
			if (file.delete() == false) {
				file.deleteOnExit(); // nothing more can be done...
				return false;
			}
		}
		return true;
	}
}