Swift 3 如何解析数据

Question

我的 Swift 3 代码有一个 Foundation Data 字节集合（从 SQlite BLOB 读取）。数据的内部内容有多个具有这种结构的块：

 {
     UINT32  count;  // number of points in this trkseg
     UINT32  colour; // RGB colour of the line drawn for this trkseq
     Double lat;  // latitude of 1st point
     Double long; // longitude of 1st point
     Coord  point[count-1] // array of points (2nd to last points)
}

typedef struct {
     Float lat   // difference in latitude of this point from the lat of the 1st point
     Float long  // difference in longitude of this point from the lat of the 1st point
 } Coord;

这在 C 和 Java 中很容易解析。不幸的是，我无法找到用 Swift 3 解析这个的最佳方法。我不是在问你如何解析这个确切的数据布局，而只是为了用 Swift 3 解析这些原始数据的建议和最佳实践。来自网络搜索和 Apple文档我很困惑！

***ANSWER - 感谢 Martin R 让我走上正轨。我在这里添加一些代码来展示我是如何解决这个问题的，以防它帮助其他人。正如马丁所说，有很多方法可以解决这个问题。我的解决方案确保无论主机字节序如何，始终正确解析网络字节序（大字节序）的 blob 数据。

/// Parse the SQLite data blob to add GPS track segments
///
/// - Parameter data: GPS track information
private func addTracks(_ data: Data) {

    // The data holds compressed GPX data. It has multiple track segments.
    // It has a block of binary data per track segment with this structure:
    //     {
    //         UINT32  count;  // number of points in this trkseg
    //         UINT32  colour; // RGB colour of the line drawn for this trkseq
    //         Double lat;  // latitude of 1st point
    //         Double long; // longitude of 1st point
    //         Coord  point[count-1] // array of points (2nd to last points)
    //    }
    //
    //    typedef struct {
    //         Float lat   // difference in latitude of this point from the lat of the 1st point
    //         Float long  // difference in longitude of this point from the lat of the 1st point
    //     } Coord;

    var dataCount = data.count // number of data bytes

    var pointCount = 0     // counts coordinates per trkseg
    var colour:UInt = 0
    var lat:Double = 0.0
    var long:Double = 0.0
    var bigEndian = true
    var i = 0

    // From http://codereview.stackexchange.com/questions/114730/type-to-byte-array-conversion-in-swift
    if (NSHostByteOrder() == NS_LittleEndian) {
        bigEndian = false
    }

    while (dataCount >= 40) {
        pointCount = Int(self.uint32Value(data: data.subdata(in: i..<i+4), isBigEndian: bigEndian))
        i = i+4

        if (pointCount < 2 || ((pointCount-1)*8 + 24 > dataCount)) {
            print("ERROR, pointCount=\(pointCount)")
            break
        }
        colour = UInt(self.uint32Value(data: data.subdata(in: i..<i+4), isBigEndian: bigEndian))
        i = i+4
        let firstLat = self.doubleValue(data: data.subdata(in: i..<i+8), isBigEndian: bigEndian)
        i = i+8
        let firstLong = self.doubleValue(data: data.subdata(in: i..<i+8), isBigEndian: bigEndian)
        i = i+8
        print("pointCount=\(pointCount) colour=\(colour) firstLat=\(firstLat) firstLong=\(firstLong)")

        for _ in 1..<pointCount {
            lat = firstLat - Double(self.floatValue(data: data.subdata(in: i..<i+4), isBigEndian: bigEndian))
            i = i+4
            long = firstLong - Double(self.floatValue(data: data.subdata(in: i..<i+4), isBigEndian: bigEndian))
            i = i+4
            print("lat=\(lat) long=\(long)")
        }
        dataCount = dataCount - 24 - (pointCount-1)*8;
    }
}

private func floatValue(data: Data, isBigEndian: Bool) -> Float {
    if (isBigEndian) {
        return Float(bitPattern: UInt32(littleEndian: data.withUnsafeBytes { $0.pointee } ))
    }
    else {
        return Float(bitPattern: UInt32(bigEndian: data.withUnsafeBytes { $0.pointee }))
    }
}

private func doubleValue(data: Data, isBigEndian: Bool) -> Double {

    if (isBigEndian) {
        return Double(bitPattern: UInt64(littleEndian: data.withUnsafeBytes { $0.pointee } ))
    }
    else {
        return Double(bitPattern: UInt64(bigEndian: data.withUnsafeBytes { $0.pointee } ))
    }
}

private func uint32Value(data: Data, isBigEndian: Bool) -> UInt32 {

    if (isBigEndian) {
        return data.withUnsafeBytes{ $0.pointee }
    }
    else {
        let temp: UInt32 = data.withUnsafeBytes{ $0.pointee }
        return temp.bigEndian
    }
}

Answer 1

一种可能的方法是使用

public func withUnsafeBytes<ResultType, ContentType>(_ body: (UnsafePointer<ContentType>) throws -> ResultType) rethrows -> ResultType

访问和取消引用数据中字节的方法。 占位符类型ContentType可以从上下文中推断出来：

let color: UInt32 = data.subdata(in: 0..<4).withUnsafeBytes { $0.pointee }
// ...
let lat: Double = data.subdata(in: 8..<16).withUnsafeBytes { $0.pointee }
// ...

从 Swift 4 开始，您可以使用下标来提取数据：

let color: UInt32 = data[0..<4].withUnsafeBytes { $0.pointee }
// ...
let lat: Double = data[8..<16].withUnsafeBytes { $0.pointee }
// ...

如果所有字段都针对其类型正确对齐，那么您可以 使用

public func load<T>(fromByteOffset offset: Int = default, as type: T.Type) -> T

来自UnsafeRawPointer：

data.withUnsafeBytes { (bytes: UnsafePointer<UInt8>) -> Void in
    let rawPointer = UnsafeRawPointer(bytes)
    let color = rawPointer.load(fromByteOffset: 0, as: UInt32.self)
    // ...
    let lat = rawPointer.load(fromByteOffset: 8, as: Double.self)
    // ...
}

在较低级别上，您可以使用 memcpy 再次与 任意对齐的数据：

var color: UInt32 = 0
var lat: Double = 0
data.withUnsafeBytes { (bytes: UnsafePointer<UInt8>) -> Void in
    memcpy(&color, bytes, 4)
    // ...
    memcpy(&lat, bytes + 8, 8)
    // ...
}

我可能会使用第一种方法，除非性能是 问题在哪里可以使用第二个或第三个，这取决于是否 所有字段都保证按照它们的类型对齐。