在Swift 3中使用LibXML2下载时从服务器解析大型XML

Ele*_*gyD 7 c xml libxml2 ios swift

我在Swift 3中遇到了来自LibXML2的SAX解析器的问题.
我想XMLPullParser在iOS中使用类似Android的东西.从服务器下载XML并在下载时解析Stream.

我的XML看起来像这样:

<?xml version="1.0" encoding="UTF-8" ?>
<ResultList id="12345678-0" platforms="A;B;C;D;E">
    <Book id="1111111111" author="Author A" title="Title A" price="9.95" ... />
    <Book id="1111111112" author="Author B" title="Title B" price="2.00" ... />
    <Book id="1111111113" author="Author C" title="Title C" price="5.00" ... />
    <ResultInfo bookcount="3" />
</ResultList>
Run Code Online (Sandbox Code Playgroud)

因此,所有数据都存储在属性而不是子节点中.

我自己创建了以下类,主要基于以下示例:
XMLPerformance,XMLPerformance-SwiftiOS-XML-Streaming

import Foundation

class LibXMLParser: NSObject, URLSessionDataDelegate {

    var url: URL?
    var delegate: LibXMLParserDelegate?
    var done = false
    var context: xmlParserCtxtPtr?

    var simpleSAXHandlerStruct: xmlSAXHandler = {
        var handler = xmlSAXHandler()

        handler.initialized = XML_SAX2_MAGIC
        handler.startElementNs = startElementSAX
        handler.endElementNs = endElementSAX
        handler.characters = charactersFoundSAX
        //handler.error = errorEncounteredSAX

        return handler
    }()

    init(url: URL) {
        super.init()

        self.url = url
    }

    func parse() {
        self.done = false
        let session = URLSession(configuration: .default, delegate: self, delegateQueue: OperationQueue.main)
        let dataTask = session.dataTask(with: URLRequest(url: url!))
        dataTask.resume()

        self.context = xmlCreatePushParserCtxt(&simpleSAXHandlerStruct, Unmanaged.passUnretained(self).toOpaque(), nil, 0, nil)
        self.delegate?.parserDidStartDocument()

        repeat {
            RunLoop.current.run(mode: .defaultRunLoopMode, before: Date.distantFuture)
        } while !self.done

        xmlFreeParserCtxt(self.context)
        self.delegate?.parserDidEndDocument()
    }

    func urlSession(_ session: URLSession, dataTask: URLSessionDataTask, didReceive data: Data) {
        print("Did receive data")
        data.withUnsafeBytes { (bytes: UnsafePointer<CChar>) -> Void in
            xmlParseChunk(self.context, bytes, CInt(data.count), 0)
        }
    }

    func urlSessionDidFinishEvents(forBackgroundURLSession session: URLSession) {
        xmlParseChunk(self.context, nil, 0, 1)
        self.done = true
    }

    func urlSession(_ session: URLSession, didBecomeInvalidWithError error: Error?) {
        self.done = true
        //self.delegate?.parserErrorOccurred(error)
    }

    func urlSession(_ session: URLSession, task: URLSessionTask, didCompleteWithError error: Error?) {
        self.done = true
        //self.delegate?.parserErrorOccurred(error)
    }
}

private func startElementSAX(_ ctx: UnsafeMutableRawPointer?, name: UnsafePointer<xmlChar>?, prefix: UnsafePointer<xmlChar>?, URI: UnsafePointer<xmlChar>?, nb_namespaces: CInt, namespaces: UnsafeMutablePointer<UnsafePointer<xmlChar>?>?, nb_attributes: CInt, nb_defaulted: CInt, attributes: UnsafeMutablePointer<UnsafePointer<xmlChar>?>?) {
    let parser = Unmanaged<LibXMLParser>.fromOpaque(ctx!).takeUnretainedValue()
    parser.delegate?.parserDidStartElement(String(cString: name!), nb_attributes: nb_attributes, attributes: attributes)
}

private func endElementSAX(_ ctx: UnsafeMutableRawPointer?, name: UnsafePointer<xmlChar>?,
                           prefix: UnsafePointer<xmlChar>?,
                           URI: UnsafePointer<xmlChar>?) {
    let parser = Unmanaged<LibXMLParser>.fromOpaque(ctx!).takeUnretainedValue()
    parser.delegate?.parserDidEndElement(String(cString: name!))
}

private func charactersFoundSAX(_ ctx: UnsafeMutableRawPointer?, ch: UnsafePointer<xmlChar>?, len: CInt) {
    let parser = Unmanaged<LibXMLParser>.fromOpaque(ctx!).takeUnretainedValue()
    parser.delegate?.parserFoundCharacters(String(cString: ch!))
}
Run Code Online (Sandbox Code Playgroud)

我用一个初始化这个类URL.当我调用parse()它创建一个URLSession和一个URLSessionDataTask委托自己来覆盖该方法didReceive data: Data.之后我创建一个xmlParserCtxtPtr循环,直到dataTask完成.

当它接收数据时,我用xmlParseChunk方法解析它并startElementSAX调用我从ViewController类设置的委托.(我只需要元素名称,属性和属性的数量.)
到目前为止一切顺利.

在我的ViewController(UITableViewController)中,我有以下代码:

func downloadBooksLibXML() {
    print("Downloading…")
    UIApplication.shared.isNetworkActivityIndicatorVisible = true

    DispatchQueue.global().async {
        print("Setting up parser")
        let parser = LibXMLParser(url: URL(string: self.baseUrl + self.parameters!)!)
        parser.delegate = self
        parser.parse()
    }
}

func parserDidStartDocument() {

}

func parserDidEndDocument() {
    DispatchQueue.main.sync {
        UIApplication.shared.isNetworkActivityIndicatorVisible = false
        self.isDone = true
        print("Finished")
    }
}

func parserDidStartElement(_ elementName: String, nb_attributes: CInt, attributes: UnsafeMutablePointer<UnsafePointer<xmlChar>?>?) {
    print(elementName)
    switch elementName {
    case "Book":
        DispatchQueue.main.async {
            let book = self.buildBook(nb_attributes: nb_attributes, attributes: attributes)
            self.books.append(book)

            self.tableView.beginUpdates()
            self.tableView.insertRows(at: [IndexPath(row: self.books.count - 1, section: 0)], with: .automatic)
            self.tableView.endUpdates()
            self.navigationItem.title = String(format: NSLocalizedString("books_found", comment: "Books found"), "\(self.books.count)")
        }
    case "ResultList":
        break
    case "ResultInfo":
        break
    default:
        break
    }
}

func buildBook(nb_attributes: CInt, attributes: UnsafeMutablePointer<UnsafePointer<xmlChar>?>?) -> Book {
    let fields = 5 /* (localname/prefix/URI/value/end) */
    let book = Book()
    for i in 0..<Int(nb_attributes) {
        if let localname = attributes?[i * fields + 0],
            //let prefix = attributes?[i * fields + 1],
            //let URI = attributes?[i * fields + 2],
            let value_start = attributes?[i * fields + 3],
            let value_end = attributes?[i * fields + 4] {

            let localnameString = String(cString: localname)
            let string_start = String(cString: value_start)
            let string_end = String(cString: value_end)
            let diff = string_start.characters.count - string_end.characters.count
            if diff > 0 {
                let value = string_start.substring(to: string_start.index(string_start.startIndex, offsetBy: diff))
                book.setValue(value, forKey: localnameString)
            }
        }
    }
    return book
}

func parserDidEndElement(_ elementName: String) {

}

func parserFoundCharacters(_ string: String) {

}

func parserErrorOccurred(_ parseError: Error?) {

}
Run Code Online (Sandbox Code Playgroud)

------

更新

因此,获得属性值的问题已由nwellnhof的答案修正.我已将上面的代码更新为更好的代码.它现在不再遍历所有属性.现在我的新问题:

我已经创建了buildBook获取BookXML属性对象的方法.我主要是从这里翻译方法在libXML sax解析器(C++)中获取属性值的正确方法是什么?到Swift并用于setValue(value: Any?, forKey: String)设置我的书对象的属性.

但现在我的问题是它不会更新tableView.我尝试buildBook在后台线程中执行同步方法,DispatchQueue.global().sync并使用异步主线程中的tableView更新DispatchQueue.main.async.但是它崩溃了tableView.endUpdates()虽然它在主线程中.

------

任何帮助将受到高度赞赏.

nwe*_*hof 0

看起来像是一个简单的相差一错误。要在 C 中迭代属性数组,我会编写如下内容:

for (int i = 0; i < nb_attributes; i++)
Run Code Online (Sandbox Code Playgroud)

但是您使用的是包含上限的闭范围运算符:

for i in 0...Int(nb_attributes)
Run Code Online (Sandbox Code Playgroud)

因此,您应该使用半开范围运算符:

for i in 0..<Int(nb_attributes)
Run Code Online (Sandbox Code Playgroud)

顺便说一下,libxml2还有一个模仿 C# 的拉解析器接口XmlTextReader,它比 SAX 解析器更容易使用。