如何将整个输入流读到字节数组?


当前回答

如果您不想使用Apache common -io库,则此代码片段取自sun.misc.IOUtils类。它的速度几乎是使用ByteBuffers的普通实现的两倍:

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;
}

其他回答

您需要从InputStream中读取每个字节,并将其写入ByteArrayOutputStream。

然后你可以通过调用toByteArray()来检索底层的字节数组:

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();

Kotlin中的解决方案(当然也可以在Java中工作),其中包括当你知道大小时的两种情况:

    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
        }
    }

如果您知道大小,那么与其他解决方案相比,它可以节省两倍的内存(在很短的时间内,但仍然可能有用)。这是因为您必须将整个流读到末尾,然后将其转换为字节数组(类似于将数组转换为数组的ArrayList)。

例如,如果你在Android上,你有一些Uri要处理,你可以尝试用这个来获取大小:

    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
    }

下面是一个优化的版本,尽量避免复制数据字节:

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;
   }
}

如果您不想使用Apache common -io库,则此代码片段取自sun.misc.IOUtils类。它的速度几乎是使用ByteBuffers的普通实现的两倍:

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;
}

我用这个。

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();
        }
    }