import java.io.DataInputStream; 
import java.io.FileInputStream; 
import java.io.IOException; 
import java.io.InputStream; 
import java.util.zip.ZipFile; 

public class DISBugReport {
	/** 
	 * This method is written to illustrate a bug 
	 * in which DataInputStream.read(byte[]) fails while DataInputStream.read() 
	 * succeeds in reading the same file. 
	 * 
	 * The failure only seems to happen when the DataInputStream is derived 
	 * from from a zipped archive entry. To illustrate this, t 
	 * the argument to the method determine whether a zipped entry generates 
	 * the input stream or a regular file (FileInputStream) does. 
	 * 
	 * @param fromZipped if set to true the DataInputStream will sit on top of a zipped entry 
	 * @throws IOException 
	 */ 
	public static void checkBytes(boolean fromZipped) throws IOException{ 

		System.out.println("\nComparing dis.read(byte[]) with dis.read() with "+ (fromZipped?"Zipped":"Uncompressed") +"file"); 

		// Path and file size information for a file that reveals the bug 
		// to test on another file replace directory and fileName 
		// and make sure fileSize is equal to at most the size (measured in bytes) 
		// of the file to be tested in bytes. 

		// publicly available file from the Census here: 
		// ftp://ftp2.census.gov/geo/tiger/TIGER2017/TABBLOCK/tl_2017_09_tabblock10.zip	
		String entryName = "tl_2017_09_tabblock10.dbf"; // publicly available file from the Census 
		String zipFilePath ="D:\\tl_2017_09_tabblock10.zip"; 
		int fileSize = 7096203; 
		String uncompressedFilePath = "D:\\tl_2017_09_tabblock10.dbf"; 

		// get data input stream either from zipped or uncompressed version 
		// of the same file depending on "fromZipped" flag. 
		// Note bug is ONLY revealed on data stream 
		// derived from a zipped entry. 
		DataInputStream dis; 
		if(fromZipped) dis = getDataStreamFromZippedEntry(zipFilePath, entryName); 
		else dis = new DataInputStream(new FileInputStream(uncompressedFilePath)); 

		// we will attempt to populate two byte[] arrays 
		// with the entire contents of the file 
		// the first ("allBytesAtOnce") will be populated using DataInputStream.read(byte[]) 
		// the second ("allBytesOneAtATime") will be populated using DataInputStream.read() 

		// USING DataInputStream.read(byte[]) 
		// download the whole file into a byte array 
		// and close streams 
		byte[] allBytesAtOnce = new byte[fileSize]; 
		int numRead = dis.read(allBytesAtOnce); 
		System.out.println("num read: " + numRead);	
		dis.close(); 

		// USING DataInputStream.read() 
		// do it again, reading one byte at a time 
		if(fromZipped) dis = getDataStreamFromZippedEntry(zipFilePath, entryName); 
		else dis = new DataInputStream(new FileInputStream(uncompressedFilePath));	
		byte[] allBytesOneAtATime = new byte[fileSize];	
		for(int i = 0; i < fileSize; i++) { 
			allBytesOneAtATime[i] = (byte)dis.read(); 
		} 
		dis.close(); 

		// Compare the two byte arrays: 
		// allBytesAtOnce was populated with a call to DataInputStream.read(byte[]) 
		// allBytesOneAtATime was populated with successive calls to DataInputStream.read() 
		boolean totalAgreement = true; 
		for(int i = 0; i < fileSize; i++) { 
			if(allBytesAtOnce[i] != allBytesOneAtATime[i]) { 
				System.out.println("Disagreement at : " + i); 
				System.out.println("allBytesAtOnce["+i+"]: "+ allBytesAtOnce[i]); 
				System.out.println("allBytesOneAtATime["+i+"]: "+ allBytesOneAtATime[i]); 
				totalAgreement = false; 
				break;	
			}	
		} 
		System.out.println("total agreement: " + totalAgreement); 
	} 

	public static DataInputStream getDataStreamFromZippedEntry(String zipFilePath, String entryName) throws IOException { 
		// get data input stream from zip file	
		ZipFile zf = new ZipFile(zipFilePath); 
		InputStream is = zf.getInputStream(zf.getEntry(entryName));	
		return new DataInputStream(is); 
	} 

	public static void main(String[] args) throws IOException { 

		// in this test the DataInputStream will derive from a zipped file entry 
		checkBytes(true); 

		// in this test the DataInputStream will derive from an uncompressed file 
		checkBytes(false); 
	} 
}