Kotlin gzip uncompress fail - java

I try to simplify my java gzip uncompress code to kotlin. But after I changed, it sames broken.
Here is the java code
public static byte[] uncompress(byte[] compressedBytes) {
if (null == compressedBytes || compressedBytes.length == 0) {
return null;
}
ByteArrayOutputStream out = null;
ByteArrayInputStream in = null;
GZIPInputStream gzipInputStream = null;
try {
out = new ByteArrayOutputStream();
in = new ByteArrayInputStream(compressedBytes);
gzipInputStream = new GZIPInputStream(in);
byte[] buffer = new byte[256];
int n = 0;
while ((n = gzipInputStream.read(buffer)) >= 0) {
out.write(buffer, 0, n);
}
return out.toByteArray();
} catch (IOException ignore) {
} finally {
CloseableUtils.closeQuietly(gzipInputStream);
CloseableUtils.closeQuietly(in);
CloseableUtils.closeQuietly(out);
}
return null;
}
This is my kotlin code.
payload = GZIPInputStream(payload.inputStream())
.bufferedReader()
.use { it.readText() }
.toByteArray()
And I got this error.
com.google.protobuf.nano.InvalidProtocolBufferNanoException: While parsing a protocol message, the input ended unexpectedly in the middle of a field. This could mean either than the input has been truncated or that an embedded message misreported its own length.
It seems that the decompression process was interrupted by reader?

The readText(charset: Charset = Charsets.UTF_8) decodes the bytes into UTF-8 character set, which is why it says "This could mean either than the input has been truncated" it probably have tried to convert 8-bits into a Char and build a String out of it.
Use the readBytes() to get ByteArray which is represented same as byte[] in JVM platform.
Example:
GZIPInputStream(payload.inputStream())
.bufferedReader()
.use { it.readBytes() }
Edit:
For reading bytes, you shouldn't be using the Reader, it is meant for reading the Text in UTF-8 format as defined in the Kotlin's InputStream.bufferedReader:
public inline fun InputStream.bufferedReader(charset: Charset = Charsets.UTF_8): BufferedReader = reader(charset).buffered()
The InputStream.readBytes() will read the bytes at a buffer of 8KB itself.
public fun InputStream.readBytes(): ByteArray {
val buffer = ByteArrayOutputStream(maxOf(DEFAULT_BUFFER_SIZE, this.available()))
copyTo(buffer)
return buffer.toByteArray()
}
// This copies with 8KB buffer automatically
// DEFAULT_BUFFER_SIZE = 8 * 1024
public fun InputStream.copyTo(out: OutputStream, bufferSize: Int = DEFAULT_BUFFER_SIZE): Long {
var bytesCopied: Long = 0
val buffer = ByteArray(bufferSize)
var bytes = read(buffer)
while (bytes >= 0) {
out.write(buffer, 0, bytes)
bytesCopied += bytes
bytes = read(buffer)
}
return bytesCopied
}
So you just have to do:
GZIPInputStream(payload.inputStream()).use { it.readBytes() }

use the following function:
fun File.unzip(unzipLocationRoot: File? = null) {
val rootFolder = unzipLocationRoot
?: File(parentFile.absolutePath + File.separator + nameWithoutExtension)
if (!rootFolder.exists()) {
rootFolder.mkdirs()
}
ZipFile(this).use { zip ->
zip
.entries()
.asSequence()
.map {
val outputFile = File(rootFolder.absolutePath + File.separator + it.name)
ZipIO(it, outputFile)
}
.map {
it.output.parentFile?.run {
if (!exists()) mkdirs()
}
it
}
.filter { !it.entry.isDirectory }
.forEach { (entry, output) ->
zip.getInputStream(entry).use { input ->
output.outputStream().use { output ->
input.copyTo(output)
}
}
}
}
}
Pass the file as a parameter as follow:
val zipFile = File(your file directory, your file name)
zipFile.unzip()
Hope this would help 🙏🏼

Related

Unable to create checkSum value using SHA-256

As per my requirement I want to create checksum value using SHA-256, from InputStream,
As below:
private InputStream createZipInput(List<ResponsePack> aList, byte[] manifestData)
{
final int bufferSize = 2048;
byte buffer[] = new byte[bufferSize];
ByteArrayOutputStream byteStream = new ByteArrayOutputStream();
ZipOutputStream zipFileToSend = new ZipOutputStream(byteStream);
LOG.trace("Compressing the file {}");
try
{
for (ResponsePack info : aList)
{
ByteArrayOutputStream byteStreamCheckSum = new ByteArrayOutputStream();
ZipOutputStream zipFileToSendCheckSum = new ZipOutputStream(byteStreamCheckSum);
zipFileToSend.putNextEntry(new ZipEntry(info.getFileName()));
zipFileToSendCheckSum.putNextEntry(new ZipEntry(info.getFileName()));
InputStream in = info.getFileContentStream();
int length;
while ((length = in.read(buffer)) >= 0)
{
zipFileToSend.write(buffer, 0, length);
zipFileToSendCheckSum.write(buffer, 0, length);
}
zipFileToSend.closeEntry();
zipFileToSendCheckSum.closeEntry();
String checksum = validChecksum(byteStreamCheckSum.toByteArray());
LOG.error("Checksum {}", checksum);
zipFileToSendCheckSum.flush();
zipFileToSendCheckSum.close();
}
zipFileToSend.close();
}
catch (IOException e)
{
return e;
}
return new ByteArrayInputStream(byteStream.toByteArray());
}
private static String validChecksum(byte[] dataCopy)
{
printLOG("Byte Array Size {}", dataCopy.length);
try (ZipInputStream zipInputStream = new ZipInputStream(new ByteArrayInputStream(dataCopy)))
{
ZipEntry zipEntry;
MessageDigest digest = DigestUtils.getSha256Digest();
DWriter writer = new DWriter(digest);
while ((zipEntry = zipInputStream.getNextEntry()) != null)
{
org.apache.commons.io.output.ByteArrayOutputStream dest = StreamUtils.extractFileAsByteArrayStream(zipInputStream);
LOG.error("CheckSum Entity creating");
if(zipEntry != null)
{
printLOG("CheckSum Entity file Name {}", zipEntry.getName());
}
LOG.error("Byte array size {}", dest.toByteArray().length);
writer.write(dest.toByteArray());
dest.flush();
dest.close();
}
if (writer.getChecksum() != null)
{
return writer.getChecksum();
}
else
{
return "";
}
}
catch (Exception e)
{
printLOG("Exception encountered while creating checksum: {}", e.getMessage());
return "";
}
}
static class DWriter
{
private final MessageDigest myDigest;
DWriter(MessageDigest digest)
{
myDigest = digest;
}
public void write(byte[] data)
{
myDigest.update(data);
}
public String getChecksum()
{
return new String(Hex.encodeHex(myDigest.digest()));
}
}
But the problem is when I checked the log, found byte array contains value but still checksum always creating for empty string, as below
Byte Array Size 3948
CheckSum Entity creating
CheckSum Entity file Name 20200911104812526.json
Byte array size 20854
Checksum e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
Help me where I am doing wrong, due to which I am getting checksum for an empty string
I'm not sure what's wrong with the code but it seems overly complicated: you're writing the input into a zipped stream and the dezip it in memory to read it again.
You don't need to do that: storing the input in a (non-zipped) byte array should be enough.
I think you need to make sure that in.read() works as intended (and that there's actually some data to read).
You get the checksum for a null input and your zip entry is also empty, so it looks like the input was empty. Add some logs or use a debugger to investigate what's happening.
private InputStream createZipInput(List<ResponsePack> aList, byte[] manifestData) {
final int bufferSize = 2048;
byte buffer[] = new byte[bufferSize];
ByteArrayOutputStream byteStream = new ByteArrayOutputStream();
ZipOutputStream zipFileToSend = new ZipOutputStream(byteStream);
LOG.trace("Compressing the file {}");
try {
for (ResponsePack info : aList) {
ByteArrayOutputStream byteStreamCheckSum = new ByteArrayOutputStream();
zipFileToSend.putNextEntry(new ZipEntry(info.getFileName()));
InputStream in = info.getFileContentStream();
int length;
while ((length = in.read(buffer)) != -1) {
zipFileToSend.write(buffer, 0, length);
byteStreamCheckSum.write(buffer, 0, length);
}
zipFileToSend.closeEntry();
MessageDigest digest = DigestUtils.getSha256Digest();
digest.update(byteStreamCheckSum.toByteArray());
String checksum = new String(Hex.encodeHex(digest.digest()));
LOG.error("Checksum {}", checksum);
}
zipFileToSend.close();
} catch (IOException e) {
throw e;
}
return new ByteArrayInputStream(byteStream.toByteArray());

Android Socket TCP Dataloss

I am unable to transmit an entire file using WiFi-Direct. The file sender is indicating that the entire file has been copied over to the socket output stream. The file receiver is only receiving roughly half of the file.
I looked at the contents of both the original file and the contents of the file storing the received data, and found the receiver is only receiving pieces of the original file. For example, it would receive bytes 0-100, and then it would jump to byte 245-350.
Why is the receiver only receiving bits and pieces of the file, rather than the entire file?
File Receiving Logic
private class FileReceiveThread(val channel: Channel) : TransmissionThread() {
private var mFileName: String = ""
private var mFileSize: Long = 0L
private var mBytesReceivedTotal = 0L
override fun run() {
try {
Timber.d("File receive thread running: fileSize=$mFileSize, fileName=$mFileName")
val outputFile = File.createTempFile("file", "")
val fileOutput = outputFile.outputStream()
val channelInput = channel.getInputStream().unwrap()
val inputBuffer = ByteArray(FILE_TX_BUFFER_SIZE)
var bytesReceived = channelInput.read(inputBuffer)
while (bytesReceived > 0) {
fileOutput.write(inputBuffer)
mBytesReceivedTotal += bytesReceived
Timber.d("Received $mBytesReceivedTotal total bytes")
bytesReceived = channelInput.read(inputBuffer)
}
onTransmitComplete?.invoke()
} catch (e: Exception) {
e.printStackTrace()
}
}
fun start(filename: String, size: Long) {
mFileName = filename
mFileSize = size
start()
}
}
File Sending Logic
private class FileSendThread : TransmissionThread() {
var mFile: File? = null
var mOutputStream: OutputStream? = null
override fun run() {
if (mFile != null && mOutputStream != null) {
val inputStream = mFile!!.inputStream()
val channelStream = mOutputStream!!
val buffer = ByteArray(FILE_TX_BUFFER_SIZE)
var bytesRead = inputStream.read(buffer)
var totalBytesRead = 0L + bytesRead
while (bytesRead > 0) {
Timber.v("Read $bytesRead, total $totalBytesRead")
channelStream.write(buffer)
bytesRead = inputStream.read(buffer)
totalBytesRead += bytesRead
}
Timber.d("Wrote file to output stream")
inputStream.close()
Timber.d("No more data to send")
onTransmitComplete?.invoke()
} else Timber.d("Parameters null: file=$mFile")
}
fun start(file: File, stream: OutputStream) {
mFile = file
mOutputStream = stream
start()
}
}
while (inputStream.read(buffer) > 0) {
channelStream.write(buffer)
}
The read() will often not fill the complete buffer. Hence if you write the buffer then only as far as it is filled.
var totalbytesread = 0;
var nread;
while ((nread = inputStream.read(buffer)) > 0) {
channelStream.write(buffer, 0, nread)
totalbytesread += nread;
}
channelStream.close()';
Log the totalbytesread.
Your original code would have caused a bigger received file so there is something else to be discovered..

How to read a file using ByteArrayInputStream in java? [duplicate]

How do I convert a java.io.File to a byte[]?
From JDK 7 you can use Files.readAllBytes(Path).
Example:
import java.io.File;
import java.nio.file.Files;
File file;
// ...(file is initialised)...
byte[] fileContent = Files.readAllBytes(file.toPath());
It depends on what best means for you. Productivity wise, don't reinvent the wheel and use Apache Commons. Which is here FileUtils.readFileToByteArray(File input).
Since JDK 7 - one liner:
byte[] array = Files.readAllBytes(Paths.get("/path/to/file"));
No external dependencies needed.
import java.io.RandomAccessFile;
RandomAccessFile f = new RandomAccessFile(fileName, "r");
byte[] b = new byte[(int)f.length()];
f.readFully(b);
Documentation for Java 8: http://docs.oracle.com/javase/8/docs/api/java/io/RandomAccessFile.html
Basically you have to read it in memory. Open the file, allocate the array, and read the contents from the file into the array.
The simplest way is something similar to this:
public byte[] read(File file) throws IOException, FileTooBigException {
if (file.length() > MAX_FILE_SIZE) {
throw new FileTooBigException(file);
}
ByteArrayOutputStream ous = null;
InputStream ios = null;
try {
byte[] buffer = new byte[4096];
ous = new ByteArrayOutputStream();
ios = new FileInputStream(file);
int read = 0;
while ((read = ios.read(buffer)) != -1) {
ous.write(buffer, 0, read);
}
}finally {
try {
if (ous != null)
ous.close();
} catch (IOException e) {
}
try {
if (ios != null)
ios.close();
} catch (IOException e) {
}
}
return ous.toByteArray();
}
This has some unnecessary copying of the file content (actually the data is copied three times: from file to buffer, from buffer to ByteArrayOutputStream, from ByteArrayOutputStream to the actual resulting array).
You also need to make sure you read in memory only files up to a certain size (this is usually application dependent) :-).
You also need to treat the IOException outside the function.
Another way is this:
public byte[] read(File file) throws IOException, FileTooBigException {
if (file.length() > MAX_FILE_SIZE) {
throw new FileTooBigException(file);
}
byte[] buffer = new byte[(int) file.length()];
InputStream ios = null;
try {
ios = new FileInputStream(file);
if (ios.read(buffer) == -1) {
throw new IOException(
"EOF reached while trying to read the whole file");
}
} finally {
try {
if (ios != null)
ios.close();
} catch (IOException e) {
}
}
return buffer;
}
This has no unnecessary copying.
FileTooBigException is a custom application exception.
The MAX_FILE_SIZE constant is an application parameters.
For big files you should probably think a stream processing algorithm or use memory mapping (see java.nio).
As someone said, Apache Commons File Utils might have what you are looking for
public static byte[] readFileToByteArray(File file) throws IOException
Example use (Program.java):
import org.apache.commons.io.FileUtils;
public class Program {
public static void main(String[] args) throws IOException {
File file = new File(args[0]); // assume args[0] is the path to file
byte[] data = FileUtils.readFileToByteArray(file);
...
}
}
If you don't have Java 8, and agree with me that including a massive library to avoid writing a few lines of code is a bad idea:
public static byte[] readBytes(InputStream inputStream) throws IOException {
byte[] b = new byte[1024];
ByteArrayOutputStream os = new ByteArrayOutputStream();
int c;
while ((c = inputStream.read(b)) != -1) {
os.write(b, 0, c);
}
return os.toByteArray();
}
Caller is responsible for closing the stream.
// Returns the contents of the file in a byte array.
public static byte[] getBytesFromFile(File file) throws IOException {
// Get the size of the file
long length = file.length();
// You cannot create an array using a long type.
// It needs to be an int type.
// Before converting to an int type, check
// to ensure that file is not larger than Integer.MAX_VALUE.
if (length > Integer.MAX_VALUE) {
// File is too large
throw new IOException("File is too large!");
}
// Create the byte array to hold the data
byte[] bytes = new byte[(int)length];
// Read in the bytes
int offset = 0;
int numRead = 0;
InputStream is = new FileInputStream(file);
try {
while (offset < bytes.length
&& (numRead=is.read(bytes, offset, bytes.length-offset)) >= 0) {
offset += numRead;
}
} finally {
is.close();
}
// Ensure all the bytes have been read in
if (offset < bytes.length) {
throw new IOException("Could not completely read file "+file.getName());
}
return bytes;
}
You can use the NIO api as well to do it. I could do this with this code as long as the total file size (in bytes) would fit in an int.
File f = new File("c:\\wscp.script");
FileInputStream fin = null;
FileChannel ch = null;
try {
fin = new FileInputStream(f);
ch = fin.getChannel();
int size = (int) ch.size();
MappedByteBuffer buf = ch.map(MapMode.READ_ONLY, 0, size);
byte[] bytes = new byte[size];
buf.get(bytes);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
try {
if (fin != null) {
fin.close();
}
if (ch != null) {
ch.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
I think its very fast since its using MappedByteBuffer.
Simple way to do it:
File fff = new File("/path/to/file");
FileInputStream fileInputStream = new FileInputStream(fff);
// int byteLength = fff.length();
// In android the result of file.length() is long
long byteLength = fff.length(); // byte count of the file-content
byte[] filecontent = new byte[(int) byteLength];
fileInputStream.read(filecontent, 0, (int) byteLength);
Simplest Way for reading bytes from file
import java.io.*;
class ReadBytesFromFile {
public static void main(String args[]) throws Exception {
// getBytes from anyWhere
// I'm getting byte array from File
File file = null;
FileInputStream fileStream = new FileInputStream(file = new File("ByteArrayInputStreamClass.java"));
// Instantiate array
byte[] arr = new byte[(int) file.length()];
// read All bytes of File stream
fileStream.read(arr, 0, arr.length);
for (int X : arr) {
System.out.print((char) X);
}
}
}
Guava has Files.toByteArray() to offer you. It has several advantages:
It covers the corner case where files report a length of 0 but still have content
It's highly optimized, you get a OutOfMemoryException if trying to read in a big file before even trying to load the file. (Through clever use of file.length())
You don't have to reinvent the wheel.
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Path;
File file = getYourFile();
Path path = file.toPath();
byte[] data = Files.readAllBytes(path);
Using the same approach as the community wiki answer, but cleaner and compiling out of the box (preferred approach if you don't want to import Apache Commons libs, e.g. on Android):
public static byte[] getFileBytes(File file) throws IOException {
ByteArrayOutputStream ous = null;
InputStream ios = null;
try {
byte[] buffer = new byte[4096];
ous = new ByteArrayOutputStream();
ios = new FileInputStream(file);
int read = 0;
while ((read = ios.read(buffer)) != -1)
ous.write(buffer, 0, read);
} finally {
try {
if (ous != null)
ous.close();
} catch (IOException e) {
// swallow, since not that important
}
try {
if (ios != null)
ios.close();
} catch (IOException e) {
// swallow, since not that important
}
}
return ous.toByteArray();
}
This is one of the simplest way
String pathFile = "/path/to/file";
byte[] bytes = Files.readAllBytes(Paths.get(pathFile ));
I belive this is the easiest way:
org.apache.commons.io.FileUtils.readFileToByteArray(file);
ReadFully Reads b.length bytes from this file into the byte array, starting at the current file pointer. This method reads repeatedly from the file until the requested number of bytes are read. This method blocks until the requested number of bytes are read, the end of the stream is detected, or an exception is thrown.
RandomAccessFile f = new RandomAccessFile(fileName, "r");
byte[] b = new byte[(int)f.length()];
f.readFully(b);
If you want to read bytes into a pre-allocated byte buffer, this answer may help.
Your first guess would probably be to use InputStream read(byte[]). However, this method has a flaw that makes it unreasonably hard to use: there is no guarantee that the array will actually be completely filled, even if no EOF is encountered.
Instead, take a look at DataInputStream readFully(byte[]). This is a wrapper for input streams, and does not have the above mentioned issue. Additionally, this method throws when EOF is encountered. Much nicer.
Not only does the following way convert a java.io.File to a byte[], I also found it to be the fastest way to read in a file, when testing many different Java file reading methods against each other:
java.nio.file.Files.readAllBytes()
import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
public class ReadFile_Files_ReadAllBytes {
public static void main(String [] pArgs) throws IOException {
String fileName = "c:\\temp\\sample-10KB.txt";
File file = new File(fileName);
byte [] fileBytes = Files.readAllBytes(file.toPath());
char singleChar;
for(byte b : fileBytes) {
singleChar = (char) b;
System.out.print(singleChar);
}
}
}
//The file that you wanna convert into byte[]
File file=new File("/storage/0CE2-EA3D/DCIM/Camera/VID_20190822_205931.mp4");
FileInputStream fileInputStream=new FileInputStream(file);
byte[] data=new byte[(int) file.length()];
BufferedInputStream bufferedInputStream=new BufferedInputStream(fileInputStream);
bufferedInputStream.read(data,0,data.length);
//Now the bytes of the file are contain in the "byte[] data"
Let me add another solution without using third-party libraries. It re-uses an exception handling pattern that was proposed by Scott (link). And I moved the ugly part into a separate message (I would hide in some FileUtils class ;) )
public void someMethod() {
final byte[] buffer = read(new File("test.txt"));
}
private byte[] read(final File file) {
if (file.isDirectory())
throw new RuntimeException("Unsupported operation, file "
+ file.getAbsolutePath() + " is a directory");
if (file.length() > Integer.MAX_VALUE)
throw new RuntimeException("Unsupported operation, file "
+ file.getAbsolutePath() + " is too big");
Throwable pending = null;
FileInputStream in = null;
final byte buffer[] = new byte[(int) file.length()];
try {
in = new FileInputStream(file);
in.read(buffer);
} catch (Exception e) {
pending = new RuntimeException("Exception occured on reading file "
+ file.getAbsolutePath(), e);
} finally {
if (in != null) {
try {
in.close();
} catch (Exception e) {
if (pending == null) {
pending = new RuntimeException(
"Exception occured on closing file"
+ file.getAbsolutePath(), e);
}
}
}
if (pending != null) {
throw new RuntimeException(pending);
}
}
return buffer;
}
public static byte[] readBytes(InputStream inputStream) throws IOException {
byte[] buffer = new byte[32 * 1024];
int bufferSize = 0;
for (;;) {
int read = inputStream.read(buffer, bufferSize, buffer.length - bufferSize);
if (read == -1) {
return Arrays.copyOf(buffer, bufferSize);
}
bufferSize += read;
if (bufferSize == buffer.length) {
buffer = Arrays.copyOf(buffer, bufferSize * 2);
}
}
}
Another Way for reading bytes from file
Reader reader = null;
try {
reader = new FileReader(file);
char buf[] = new char[8192];
int len;
StringBuilder s = new StringBuilder();
while ((len = reader.read(buf)) >= 0) {
s.append(buf, 0, len);
byte[] byteArray = s.toString().getBytes();
}
} catch(FileNotFoundException ex) {
} catch(IOException e) {
}
finally {
if (reader != null) {
reader.close();
}
}
Try this :
import sun.misc.IOUtils;
import java.io.IOException;
try {
String path="";
InputStream inputStream=new FileInputStream(path);
byte[] data=IOUtils.readFully(inputStream,-1,false);
}
catch (IOException e) {
System.out.println(e);
}
Can be done as simple as this (Kotlin version)
val byteArray = File(path).inputStream().readBytes()
EDIT:
I've read docs of readBytes method. It says:
Reads this stream completely into a byte array.
Note: It is the caller's responsibility to close this stream.
So to be able to close the stream, while keeping everything clean, use the following code:
val byteArray = File(path).inputStream().use { it.readBytes() }
Thanks to #user2768856 for pointing this out.
try this if you have target version less than 26 API
private static byte[] readFileToBytes(String filePath) {
File file = new File(filePath);
byte[] bytes = new byte[(int) file.length()];
// funny, if can use Java 7, please uses Files.readAllBytes(path)
try(FileInputStream fis = new FileInputStream(file)){
fis.read(bytes);
return bytes;
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return null;
}
In JDK8
Stream<String> lines = Files.lines(path);
String data = lines.collect(Collectors.joining("\n"));
lines.close();

Servlet getContentLength() returns > 0 but getInputStream().available() returns 0 [duplicate]

How do I read an entire InputStream into a byte array?
You can use Apache Commons IO to handle this and similar tasks.
The IOUtils type has a static method to read an InputStream and return a byte[].
InputStream is;
byte[] bytes = IOUtils.toByteArray(is);
Internally this creates a ByteArrayOutputStream and copies the bytes to the output, then calls toByteArray(). It handles large files by copying the bytes in blocks of 4KiB.
You need to read each byte from your InputStream and write it to a ByteArrayOutputStream.
You can then retrieve the underlying byte array by calling toByteArray():
InputStream is = ...
ByteArrayOutputStream buffer = new ByteArrayOutputStream();
int nRead;
byte[] data = new byte[16384];
while ((nRead = is.read(data, 0, data.length)) != -1) {
buffer.write(data, 0, nRead);
}
return buffer.toByteArray();
Finally, after twenty years, there’s a simple solution without the need for a 3rd party library, thanks to Java 9:
InputStream is;
…
byte[] array = is.readAllBytes();
Note also the convenience methods readNBytes(byte[] b, int off, int len) and transferTo(OutputStream) addressing recurring needs.
Use vanilla Java's DataInputStream and its readFully Method (exists since at least Java 1.4):
...
byte[] bytes = new byte[(int) file.length()];
DataInputStream dis = new DataInputStream(new FileInputStream(file));
dis.readFully(bytes);
...
There are some other flavors of this method, but I use this all the time for this use case.
If you happen to use Google Guava, it'll be as simple as using ByteStreams:
byte[] bytes = ByteStreams.toByteArray(inputStream);
Safe solution (close streams correctly):
Java 9 and newer:
final byte[] bytes;
try (inputStream) {
bytes = inputStream.readAllBytes();
}
Java 8 and older:
public static byte[] readAllBytes(InputStream inputStream) throws IOException {
final int bufLen = 4 * 0x400; // 4KB
byte[] buf = new byte[bufLen];
int readLen;
IOException exception = null;
try {
try (ByteArrayOutputStream outputStream = new ByteArrayOutputStream()) {
while ((readLen = inputStream.read(buf, 0, bufLen)) != -1)
outputStream.write(buf, 0, readLen);
return outputStream.toByteArray();
}
} catch (IOException e) {
exception = e;
throw e;
} finally {
if (exception == null) inputStream.close();
else try {
inputStream.close();
} catch (IOException e) {
exception.addSuppressed(e);
}
}
}
Kotlin (when Java 9+ isn't accessible):
#Throws(IOException::class)
fun InputStream.readAllBytes(): ByteArray {
val bufLen = 4 * 0x400 // 4KB
val buf = ByteArray(bufLen)
var readLen: Int = 0
ByteArrayOutputStream().use { o ->
this.use { i ->
while (i.read(buf, 0, bufLen).also { readLen = it } != -1)
o.write(buf, 0, readLen)
}
return o.toByteArray()
}
}
To avoid nested use see here.
Scala (when Java 9+ isn't accessible) (By #Joan. Thx):
def readAllBytes(inputStream: InputStream): Array[Byte] =
Stream.continually(inputStream.read).takeWhile(_ != -1).map(_.toByte).toArray
As always, also Spring framework (spring-core since 3.2.2) has something for you: StreamUtils.copyToByteArray()
public static byte[] getBytesFromInputStream(InputStream is) throws IOException {
ByteArrayOutputStream os = new ByteArrayOutputStream();
byte[] buffer = new byte[0xFFFF];
for (int len = is.read(buffer); len != -1; len = is.read(buffer)) {
os.write(buffer, 0, len);
}
return os.toByteArray();
}
In-case someone is still looking for a solution without dependency and If you have a file.
DataInputStream
byte[] data = new byte[(int) file.length()];
DataInputStream dis = new DataInputStream(new FileInputStream(file));
dis.readFully(data);
dis.close();
ByteArrayOutputStream
InputStream is = new FileInputStream(file);
ByteArrayOutputStream buffer = new ByteArrayOutputStream();
int nRead;
byte[] data = new byte[(int) file.length()];
while ((nRead = is.read(data, 0, data.length)) != -1) {
buffer.write(data, 0, nRead);
}
RandomAccessFile
RandomAccessFile raf = new RandomAccessFile(file, "r");
byte[] data = new byte[(int) raf.length()];
raf.readFully(data);
Do you really need the image as a byte[]? What exactly do you expect in the byte[] - the complete content of an image file, encoded in whatever format the image file is in, or RGB pixel values?
Other answers here show you how to read a file into a byte[]. Your byte[] will contain the exact contents of the file, and you'd need to decode that to do anything with the image data.
Java's standard API for reading (and writing) images is the ImageIO API, which you can find in the package javax.imageio. You can read in an image from a file with just a single line of code:
BufferedImage image = ImageIO.read(new File("image.jpg"));
This will give you a BufferedImage, not a byte[]. To get at the image data, you can call getRaster() on the BufferedImage. This will give you a Raster object, which has methods to access the pixel data (it has several getPixel() / getPixels() methods).
Lookup the API documentation for javax.imageio.ImageIO, java.awt.image.BufferedImage, java.awt.image.Raster etc.
ImageIO supports a number of image formats by default: JPEG, PNG, BMP, WBMP and GIF. It's possible to add support for more formats (you'd need a plug-in that implements the ImageIO service provider interface).
See also the following tutorial: Working with Images
If you don't want to use the Apache commons-io library, this snippet is taken from the sun.misc.IOUtils class. It's nearly twice as fast as the common implementation using ByteBuffers:
public static byte[] readFully(InputStream is, int length, boolean readAll)
throws IOException {
byte[] output = {};
if (length == -1) length = Integer.MAX_VALUE;
int pos = 0;
while (pos < length) {
int bytesToRead;
if (pos >= output.length) { // Only expand when there's no room
bytesToRead = Math.min(length - pos, output.length + 1024);
if (output.length < pos + bytesToRead) {
output = Arrays.copyOf(output, pos + bytesToRead);
}
} else {
bytesToRead = output.length - pos;
}
int cc = is.read(output, pos, bytesToRead);
if (cc < 0) {
if (readAll && length != Integer.MAX_VALUE) {
throw new EOFException("Detect premature EOF");
} else {
if (output.length != pos) {
output = Arrays.copyOf(output, pos);
}
break;
}
}
pos += cc;
}
return output;
}
ByteArrayOutputStream out = new ByteArrayOutputStream();
byte[] buffer = new byte[1024];
while (true) {
int r = in.read(buffer);
if (r == -1) break;
out.write(buffer, 0, r);
}
byte[] ret = out.toByteArray();
#Adamski: You can avoid buffer entirely.
Code copied from http://www.exampledepot.com/egs/java.io/File2ByteArray.html (Yes, it is very verbose, but needs half the size of memory as the other solution.)
// Returns the contents of the file in a byte array.
public static byte[] getBytesFromFile(File file) throws IOException {
InputStream is = new FileInputStream(file);
// Get the size of the file
long length = file.length();
// You cannot create an array using a long type.
// It needs to be an int type.
// Before converting to an int type, check
// to ensure that file is not larger than Integer.MAX_VALUE.
if (length > Integer.MAX_VALUE) {
// File is too large
}
// Create the byte array to hold the data
byte[] bytes = new byte[(int)length];
// Read in the bytes
int offset = 0;
int numRead = 0;
while (offset < bytes.length
&& (numRead=is.read(bytes, offset, bytes.length-offset)) >= 0) {
offset += numRead;
}
// Ensure all the bytes have been read in
if (offset < bytes.length) {
throw new IOException("Could not completely read file "+file.getName());
}
// Close the input stream and return bytes
is.close();
return bytes;
}
Input Stream is ...
ByteArrayOutputStream bos = new ByteArrayOutputStream();
int next = in.read();
while (next > -1) {
bos.write(next);
next = in.read();
}
bos.flush();
byte[] result = bos.toByteArray();
bos.close();
Java 9 will give you finally a nice method:
InputStream in = ...;
ByteArrayOutputStream bos = new ByteArrayOutputStream();
in.transferTo( bos );
byte[] bytes = bos.toByteArray();
We are seeing some delay for few AWS transaction, while converting S3 object to ByteArray.
Note: S3 Object is PDF document (max size is 3 mb).
We are using the option #1 (org.apache.commons.io.IOUtils) to convert the S3 object to ByteArray. We have noticed S3 provide the inbuild IOUtils method to convert the S3 object to ByteArray, we are request you to confirm what is the best way to convert the S3 object to ByteArray to avoid the delay.
Option #1:
import org.apache.commons.io.IOUtils;
is = s3object.getObjectContent();
content =IOUtils.toByteArray(is);
Option #2:
import com.amazonaws.util.IOUtils;
is = s3object.getObjectContent();
content =IOUtils.toByteArray(is);
Also let me know if we have any other better way to convert the s3 object to bytearray
I know it's too late but here I think is cleaner solution that's more readable...
/**
* method converts {#link InputStream} Object into byte[] array.
*
* #param stream the {#link InputStream} Object.
* #return the byte[] array representation of received {#link InputStream} Object.
* #throws IOException if an error occurs.
*/
public static byte[] streamToByteArray(InputStream stream) throws IOException {
byte[] buffer = new byte[1024];
ByteArrayOutputStream os = new ByteArrayOutputStream();
int line = 0;
// read bytes from stream, and store them in buffer
while ((line = stream.read(buffer)) != -1) {
// Writes bytes from byte array (buffer) into output stream.
os.write(buffer, 0, line);
}
stream.close();
os.flush();
os.close();
return os.toByteArray();
}
I tried to edit #numan's answer with a fix for writing garbage data but edit was rejected. While this short piece of code is nothing brilliant I can't see any other better answer. Here's what makes most sense to me:
ByteArrayOutputStream out = new ByteArrayOutputStream();
byte[] buffer = new byte[1024]; // you can configure the buffer size
int length;
while ((length = in.read(buffer)) != -1) out.write(buffer, 0, length); //copy streams
in.close(); // call this in a finally block
byte[] result = out.toByteArray();
btw ByteArrayOutputStream need not be closed. try/finally constructs omitted for readability
See the InputStream.available() documentation:
It is particularly important to realize that you must not use this
method to size a container and assume that you can read the entirety
of the stream without needing to resize the container. Such callers
should probably write everything they read to a ByteArrayOutputStream
and convert that to a byte array. Alternatively, if you're reading
from a file, File.length returns the current length of the file
(though assuming the file's length can't change may be incorrect,
reading a file is inherently racy).
Wrap it in a DataInputStream if that is off the table for some reason, just use read to hammer on it until it gives you a -1 or the entire block you asked for.
public int readFully(InputStream in, byte[] data) throws IOException {
int offset = 0;
int bytesRead;
boolean read = false;
while ((bytesRead = in.read(data, offset, data.length - offset)) != -1) {
read = true;
offset += bytesRead;
if (offset >= data.length) {
break;
}
}
return (read) ? offset : -1;
}
Java 8 way (thanks to BufferedReader and Adam Bien)
private static byte[] readFully(InputStream input) throws IOException {
try (BufferedReader buffer = new BufferedReader(new InputStreamReader(input))) {
return buffer.lines().collect(Collectors.joining("\n")).getBytes(<charset_can_be_specified>);
}
}
Note that this solution wipes carriage return ('\r') and can be inappropriate.
The other case to get correct byte array via stream, after send request to server and waiting for the response.
/**
* Begin setup TCP connection to PC app
* to open integrate connection between mobile app and pc app (or mobile app)
*/
mSocket = new Socket(IP, port);
// mSocket.setSoTimeout(30000);
DataOutputStream mDos = new DataOutputStream(mSocket.getOutputStream());
String str = "MobileRequest#" + params[0] + "#<EOF>";
mDos.write(str.getBytes());
try {
Thread.sleep(1000);
} catch (InterruptedException e) {
e.printStackTrace();
}
/* Since data are accepted as byte, all of them will be collected in the
following byte array which initialised with accepted data length. */
DataInputStream mDis = new DataInputStream(mSocket.getInputStream());
byte[] data = new byte[mDis.available()];
// Collecting data into byte array
for (int i = 0; i < data.length; i++)
data[i] = mDis.readByte();
// Converting collected data in byte array into String.
String RESPONSE = new String(data);
You're doing an extra copy if you use ByteArrayOutputStream. If you know the length of the stream before you start reading it (e.g. the InputStream is actually a FileInputStream, and you can call file.length() on the file, or the InputStream is a zipfile entry InputStream, and you can call zipEntry.length()), then it's far better to write directly into the byte[] array -- it uses half the memory, and saves time.
// Read the file contents into a byte[] array
byte[] buf = new byte[inputStreamLength];
int bytesRead = Math.max(0, inputStream.read(buf));
// If needed: for safety, truncate the array if the file may somehow get
// truncated during the read operation
byte[] contents = bytesRead == inputStreamLength ? buf
: Arrays.copyOf(buf, bytesRead);
N.B. the last line above deals with files getting truncated while the stream is being read, if you need to handle that possibility, but if the file gets longer while the stream is being read, the contents in the byte[] array will not be lengthened to include the new file content, the array will simply be truncated to the old length inputStreamLength.
I use this.
public static byte[] toByteArray(InputStream is) throws IOException {
ByteArrayOutputStream output = new ByteArrayOutputStream();
try {
byte[] b = new byte[4096];
int n = 0;
while ((n = is.read(b)) != -1) {
output.write(b, 0, n);
}
return output.toByteArray();
} finally {
output.close();
}
}
This is my copy-paste version:
#SuppressWarnings("empty-statement")
public static byte[] inputStreamToByte(InputStream is) throws IOException {
if (is == null) {
return null;
}
// Define a size if you have an idea of it.
ByteArrayOutputStream r = new ByteArrayOutputStream(2048);
byte[] read = new byte[512]; // Your buffer size.
for (int i; -1 != (i = is.read(read)); r.write(read, 0, i));
is.close();
return r.toByteArray();
}
Java 7 and later:
import sun.misc.IOUtils;
...
InputStream in = ...;
byte[] buf = IOUtils.readFully(in, -1, false);
You can try Cactoos:
byte[] array = new BytesOf(stream).bytes();
Here is an optimized version, that tries to avoid copying data bytes as much as possible:
private static byte[] loadStream (InputStream stream) throws IOException {
int available = stream.available();
int expectedSize = available > 0 ? available : -1;
return loadStream(stream, expectedSize);
}
private static byte[] loadStream (InputStream stream, int expectedSize) throws IOException {
int basicBufferSize = 0x4000;
int initialBufferSize = (expectedSize >= 0) ? expectedSize : basicBufferSize;
byte[] buf = new byte[initialBufferSize];
int pos = 0;
while (true) {
if (pos == buf.length) {
int readAhead = -1;
if (pos == expectedSize) {
readAhead = stream.read(); // test whether EOF is at expectedSize
if (readAhead == -1) {
return buf;
}
}
int newBufferSize = Math.max(2 * buf.length, basicBufferSize);
buf = Arrays.copyOf(buf, newBufferSize);
if (readAhead != -1) {
buf[pos++] = (byte)readAhead;
}
}
int len = stream.read(buf, pos, buf.length - pos);
if (len < 0) {
return Arrays.copyOf(buf, pos);
}
pos += len;
}
}
Solution in Kotlin (will work in Java too, of course), which includes both cases of when you know the size or not:
fun InputStream.readBytesWithSize(size: Long): ByteArray? {
return when {
size < 0L -> this.readBytes()
size == 0L -> ByteArray(0)
size > Int.MAX_VALUE -> null
else -> {
val sizeInt = size.toInt()
val result = ByteArray(sizeInt)
readBytesIntoByteArray(result, sizeInt)
result
}
}
}
fun InputStream.readBytesIntoByteArray(byteArray: ByteArray,bytesToRead:Int=byteArray.size) {
var offset = 0
while (true) {
val read = this.read(byteArray, offset, bytesToRead - offset)
if (read == -1)
break
offset += read
if (offset >= bytesToRead)
break
}
}
If you know the size, it saves you on having double the memory used compared to the other solutions (in a brief moment, but still could be useful). That's because you have to read the entire stream to the end, and then convert it to a byte array (similar to ArrayList which you convert to just an array).
So, if you are on Android, for example, and you got some Uri to handle, you can try to get the size using this:
fun getStreamLengthFromUri(context: Context, uri: Uri): Long {
context.contentResolver.query(uri, arrayOf(MediaStore.MediaColumns.SIZE), null, null, null)?.use {
if (!it.moveToNext())
return#use
val fileSize = it.getLong(it.getColumnIndex(MediaStore.MediaColumns.SIZE))
if (fileSize > 0)
return fileSize
}
//if you wish, you can also get the file-path from the uri here, and then try to get its size, using this: https://stackoverflow.com/a/61835665/878126
FileUtilEx.getFilePathFromUri(context, uri, false)?.use {
val file = it.file
val fileSize = file.length()
if (fileSize > 0)
return fileSize
}
context.contentResolver.openInputStream(uri)?.use { inputStream ->
if (inputStream is FileInputStream)
return inputStream.channel.size()
else {
var bytesCount = 0L
while (true) {
val available = inputStream.available()
if (available == 0)
break
val skip = inputStream.skip(available.toLong())
if (skip < 0)
break
bytesCount += skip
}
if (bytesCount > 0L)
return bytesCount
}
}
return -1L
}
You can use cactoos library with provides reusable object-oriented Java components.
OOP is emphasized by this library, so no static methods, NULLs, and so on, only real objects and their contracts (interfaces).
A simple operation like reading InputStream, can be performed like that
final InputStream input = ...;
final Bytes bytes = new BytesOf(input);
final byte[] array = bytes.asBytes();
Assert.assertArrayEquals(
array,
new byte[]{65, 66, 67}
);
Having a dedicated type Bytes for working with data structure byte[] enables us to use OOP tactics for solving tasks at hand.
Something that a procedural "utility" method will forbid us to do.
For example, you need to enconde bytes you've read from this InputStream to Base64.
In this case you will use Decorator pattern and wrap Bytes object within implementation for Base64.
cactoos already provides such implementation:
final Bytes encoded = new BytesBase64(
new BytesOf(
new InputStreamOf("XYZ")
)
);
Assert.assertEquals(new TextOf(encoded).asString(), "WFla");
You can decode them in the same manner, by using Decorator pattern
final Bytes decoded = new Base64Bytes(
new BytesBase64(
new BytesOf(
new InputStreamOf("XYZ")
)
)
);
Assert.assertEquals(new TextOf(decoded).asString(), "XYZ");
Whatever your task is you will be able to create own implementation of Bytes to solve it.

java zip to binary format and then decompress

I have a task that
read a zip file from local into binary message
transfer binary message through EMS as String (done by java API)
receive transferred binary message as String (done by java API)
decompress the binary message and then print it out
The problem I am facing is DataFormatException while decompress the message.
I have no idea which part went wrong.
I use this to read file into binary message:
static String readFile_Stream(String fileName) throws IOException {
File file = new File(fileName);
byte[] fileData = new byte[(int) file.length()];
FileInputStream in = new FileInputStream(file);
in.read(fileData);
String content = "";
System.out.print("Sent message: ");
for(byte b : fileData)
{
System.out.print(getBits(b));
content += getBits(b);
}
in.close();
return content;
}
static String getBits(byte b)
{
String result = "";
for(int i = 0; i < 8; i++)
result = ((b & (1 << i)) == 0 ? "0" : "1") + result;
return result;
}
I use this to decompress message:
private static byte[] toByteArray(String input)
{
byte[] byteArray = new byte[input.length()/8];
for (int i=0;i<input.length()/8;i++)
{
String read_data = input.substring(i*8, i*8+8);
short a = Short.parseShort(read_data, 2);
byteArray[i] = (byte) a;
}
return byteArray;
}
public static byte[] unzipByteArray(byte[] file) throws IOException {
byte[] byReturn = null;
Inflater oInflate = new Inflater(false);
oInflate.setInput(file);
ByteArrayOutputStream oZipStream = new ByteArrayOutputStream();
try {
while (! oInflate.finished() ){
byte[] byRead = new byte[4 * 1024];
int iBytesRead = oInflate.inflate(byRead);
if (iBytesRead == byRead.length){
oZipStream.write(byRead);
}
else {
oZipStream.write(byRead, 0, iBytesRead);
}
}
byReturn = oZipStream.toByteArray();
}
catch (DataFormatException ex){
throw new IOException("Attempting to unzip file that is not zipped.");
}
finally {
oZipStream.close();
}
return byReturn;
}
The message I got is
java.io.IOException: Attempting to unzip file that is not zipped.
at com.sourcefreak.example.test.TibcoEMSQueueReceiver.unzipByteArray(TibcoEMSQueueReceiver.java:144)
at com.sourcefreak.example.test.TibcoEMSQueueReceiver.main(TibcoEMSQueueReceiver.java:54)
After check, the binary message does not corrupted after transmission.
Please help to figure out the problem.
Have you tried using InflaterInputStream? Based on my experience, using Inflater directly is rather tricky. You can use this to get started:
public static byte[] unzipByteArray(byte[] file) throws IOException {
InflaterInputStream iis = new InflaterInputStream(new ByteArrayInputStream(file));
ByteArrayOutputStream baos = new ByteArrayOutputStream();
byte[] buffer = new byte[512];
int length = 0;
while ((length = iis.read(buffer, 0, buffer.length) != 0) {
baos.write(buffer, 0, length);
}
iis.close();
baos.close();
return baos.toByteArray();
}
I finally figure out the problem.
The problem is the original file is a .zip file, so I should use zipInputStream to unzip the file before further processing.
public static byte[] unzipByteArray(byte[] file) throws IOException {
// create a buffer to improve copy performance later.
byte[] buffer = new byte[2048];
byte[] content ;
// open the zip file stream
InputStream theFile = new ByteArrayInputStream(file);
ZipInputStream stream = new ZipInputStream(theFile);
ByteArrayOutputStream output = new ByteArrayOutputStream();
try
{
ZipEntry entry;
while((entry = stream.getNextEntry())!=null)
{
//String s = String.format("Entry: %s len %d added %TD", entry.getName(), entry.getSize(), new Date(entry.getTime()));
//System.out.println(s);
// Once we get the entry from the stream, the stream is
// positioned read to read the raw data, and we keep
// reading until read returns 0 or less.
//String outpath = outdir + "/" + entry.getName();
try
{
//output = new FileOutputStream(outpath);
int len = 0;
while ((len = stream.read(buffer)) > 0)
{
output.write(buffer, 0, len);
}
}
finally
{
// we must always close the output file
if(output!=null) output.close();
}
}
}
finally
{
// we must always close the zip file.
stream.close();
}
content = output.toByteArray();
return content;
}
This code work for zip file containing single file inside.

Categories