在Kotlin中解析webp文件头获取其高度和宽度，但得到意想不到的结果

Question

我正在尝试根据扩展文件格式的WebP容器规范读取WebP图像标题。

fun get24bit(data: ByteArray, index: Int): Int {
    return ((data[0 + index].toInt()) or (data[1 + index].toInt() shl 8) or (data[2 + index].toInt() shl 16))
}

fun get32bit(data: ByteArray, index: Int): Int {
    return get24bit(data, index) or (data[3 + index].toInt() shl 24)
}

// data -> File(fileName).readBytes() for testing purpose
fun webpExtract(data: ByteArray) {
    println(String(data.copyOfRange(0, 4)))
    println("Size: ${get32bit(data, 4)}")
    println(String(data.copyOfRange(8, 12)))
    println(String(data.copyOfRange(12, 16)))
    // 16, 17, 18, 19 reserved

    val width = 1 + get24bit(data, 20)
    val height = 1 + get24bit(data, 23)

    println("Width: $width, Height: $height")
}

输出为：

RIFF
Size: -52
WEBP
VP8X
Width: 17, Height: 32513

字符串输出没问题，但大小变为负值，宽度和高度错误，即它们应该分别为 128 和 128（对于我使用的测试图像）。

代码有问题吗？我无法弄清楚问题出在哪里。

我还在 github 验证了实际的 C++ 实现。我的代码执行相同的位移，但结果不正确。据我所知，左移与无符号和有符号右移没有任何关系？

Answer 1

不知道

Spec不完整或其他什么，我记录了字节值并以某种方式找到了模式。发现尺寸为 24-26 和 27-29 索引。

val width = 1 + (get24bit(data, 24))
val height = 1 + (get24bit(data, 27))

这个就可以了！希望只要文档未更新，注意这一点会有所帮助。

Answer 2

接受的答案仅适用于某些 WebP 文件（扩展格式 VP8X），但还有其他两种格式（有损 VP8 和无损 VP8L）不适用于该答案。

这 3 种格式有不同的获取尺寸的方法。

fun getWebPDimensions(imgFile: File) {
    val stream = FileInputStream(imgFile)
    val data = stream.readNBytes(30)
    // All formats consist of a file header (12 bytes) and a ChunkHeader (8 bytes)
    // The first four ChunkHeader bytes contain the 4 characters of the format (12 to 15):
    val imageFormat = String(Arrays.copyOfRange(data, 12, 16)) // exclusive range
    val width: Int
    val height: Int
    when(imageFormat) {
        "VP8 " -> { // last character is a space
            // Simple File Format (Lossy)
            // The data is in the VP8 specification and the decoding guide explains how to get the dimensions: https://datatracker.ietf.org/doc/html/rfc6386#section-19.1
            // The format consists of the frame_tag (3 bytes), start code (3 bytes), horizontal_size_code (2 bytes) and vertical_size_code (2 bytes)
            // The size is 14 bits, use a mask to remove the last two digits
            width = get16bit(data, 26) and 0x3FFF
            height = get16bit(data, 28) and 0x3FFF
        }
        "VP8X" -> {
            // Extended File Format, size position specified here: https://developers.google.com/speed/webp/docs/riff_container#extended_file_format
            // The width starts 4 bytes after the ChunkHeader with a size of 3 bytes, the height comes after.
            width = 1 + (get24bit(data, 24))
            height = 1 + (get24bit(data, 27))
        }
        "VP8L" -> {
            // Simple File Format (Lossless), specification here: https://developers.google.com/speed/webp/docs/webp_lossless_bitstream_specification#3_riff_header
            // The format consists of a signature (1 byte), 14 bit width (2 bytes) and 14 bit height (2 bytes)
            // The width and height are in consecutive bits
            val firstBytes = get16bit(data, 21)
            width = 1 + (firstBytes and 0x3FFF)
            val lastTwoDigits =  (firstBytes and 0xC000) shr 14 // the last 2 bits correspond to the first 2 bits of the height
            // Extract the remaining 12 bits and shift them to add space for the two digits
            height = 1 + ((get16bit(data, 23) and 0xFFF shl 2) or lastTwoDigits)
        }
    }
}

private fun get16bit(data: ByteArray, index: Int): Int {
    // The mask (0xFF) converts the byte from signed (this is how Java originally reads the byte) to unsigned
    return data[index].toInt() and 0xFF or (data[index + 1].toInt() and 0xFF shl 8)
}

private fun get24bit(data: ByteArray, index: Int): Int {
    return get16bit(data, index) or (data[index + 2].toInt() and 0xFF shl 16)
}