Question

我正在为大型视频文件创建MD5校验和。我目前正在使用代码：

extension NSData {
func MD5() -> NSString {
    let digestLength = Int(CC_MD5_DIGEST_LENGTH)
    let md5Buffer = UnsafeMutablePointer<CUnsignedChar>.allocate(capacity: digestLength)

    CC_MD5(bytes, CC_LONG(length), md5Buffer)
    let output = NSMutableString(capacity: Int(CC_MD5_DIGEST_LENGTH * 2))
    for i in 0..<digestLength {
        output.appendFormat("%02x", md5Buffer[i])
    }

    return NSString(format: output)
    }
}

但这会产生一个内存缓冲区，对于大型视频文件来说并不理想。在Swift中有没有办法计算读取文件流的MD5校验和，因此内存占用量最小？

Answer 1

如图所示，您可以以块的形式计算MD5校验和例如在Is there a MD5 library that doesn't require the whole input at the same time?。

以下是使用Swift的可能实现：

|Browser|
|Chrome|
|FireFox|
|Edge|
|IE11|

需要自动释放池来释放返回的内存 func md5File(url: URL) -> Data? { let bufferSize = 1024 * 1024 do { // Open file for reading: let file = try FileHandle(forReadingFrom: url) defer { file.closeFile() } // Create and initialize MD5 context: var context = CC_MD5_CTX() CC_MD5_Init(&context) // Read up to `bufferSize` bytes, until EOF is reached, and update MD5 context: while autoreleasepool(invoking: { let data = file.readData(ofLength: bufferSize) if data.count > 0 { data.withUnsafeBytes { _ = CC_MD5_Update(&context, $0, numericCast(data.count)) } return true // Continue } else { return false // End of file } }) { } // Compute the MD5 digest: var digest = Data(count: Int(CC_MD5_DIGEST_LENGTH)) digest.withUnsafeMutableBytes { _ = CC_MD5_Final($0, &context) } return digest } catch { print("Cannot open file:", error.localizedDescription) return nil } }，没有它的整个（可能是巨大的）文件将被加载到内存中。感谢Abhi Beckert注意到这一点并提供实施。

如果您需要将摘要作为十六进制编码的字符串，请更改将类型返回到file.readData()并替换

String?

通过

return digest

Answer 2

针对SHA256哈希的解决方案（基于Martin R的答案）：

func sha256(url: URL) -> Data? {
    do {
        let bufferSize = 1024 * 1024
        // Open file for reading:
        let file = try FileHandle(forReadingFrom: url)
        defer {
            file.closeFile()
        }

        // Create and initialize SHA256 context:
        var context = CC_SHA256_CTX()
        CC_SHA256_Init(&context)

        // Read up to `bufferSize` bytes, until EOF is reached, and update SHA256 context:
        while autoreleasepool(invoking: {
            // Read up to `bufferSize` bytes
            let data = file.readData(ofLength: bufferSize)
            if data.count > 0 {
                data.withUnsafeBytes {
                    _ = CC_SHA256_Update(&context, $0, numericCast(data.count))
                }
                // Continue
                return true
            } else {
                // End of file
                return false
            }
        }) { }

        // Compute the SHA256 digest:
        var digest = Data(count: Int(CC_SHA256_DIGEST_LENGTH))
        digest.withUnsafeMutableBytes {
            _ = CC_SHA256_Final($0, &context)
        }

        return digest
    } catch {
        print(error)
        return nil
    }
}

使用先前创建名称为URL的{{1}}类型的实例：

fileURL

Swift计算大文件的MD5校验和

2 个答案: