swift - Swift 中最快的逐字符读取器是什么

Question

我必须用 swift 中的字符读取器编写一个真正的快速字符。这是我到目前为止的解决方案。

对于 1.4mb 的文件，我在 0m0.932s 内得到它。对于 150mb 的文件，需要 1m42.931s

您知道更快的解决方案吗？

import Foundation
class CharReader {

let encoding : String.Encoding
let chunkSize : Int
var fileHandle : FileHandle!
let buffer : NSMutableData!
var atEof : Bool = false
var characterPointer: UnsafeMutablePointer<Character>
var startPointer: UnsafeMutablePointer<Character>

var stored_cnt: Int = 0;
var stored_idx: Int = 0;

init?(path: String, encoding: String.Encoding = String.Encoding.utf8, chunkSize : Int = 1024) {
    self.chunkSize = chunkSize
    self.encoding = encoding
    characterPointer = UnsafeMutablePointer<Character>.allocate(capacity: chunkSize)
    startPointer = characterPointer
    if let fileHandle = FileHandle(forReadingAtPath: path),
        let buffer = NSMutableData(capacity: chunkSize){
        self.fileHandle = fileHandle
        self.buffer = buffer
    } else {
        self.fileHandle = nil
        self.buffer = nil
        return nil
    }
}

deinit {
    self.close()
}

func nextChar() -> Character? {

    if atEof {
        return nil
    }

    if stored_cnt > (stored_idx + 1) {
        stored_idx += 1
        let char = characterPointer.pointee
        characterPointer = characterPointer.successor()
        return char
    }

    let tmpData = fileHandle.readData(ofLength: (chunkSize))
    if tmpData.count == 0 {
        atEof = true
        return nil
    }

    if let s = NSString(data: tmpData, encoding: encoding.rawValue) as String! {
        stored_idx = 0
        let characters = s.characters
        stored_cnt = characters.count

        characterPointer = startPointer
        characterPointer.initialize(from: characters)

        let char = characterPointer.pointee
        characterPointer = characterPointer.successor()
        return char
    }
    return nil;
}


/// Close the underlying file. No reading must be done after calling this method.
func close() -> Void {
    fileHandle?.closeFile()
    fileHandle = nil
}

}

请告诉我。

我用这个 main.swfit 测试这个类:

import Foundation

if CommandLine.arguments.count < 2 {
    print("Too less arguments.")
    exit(0)
}
let file = CommandLine.arguments[1]

if let aCharReader = CharReader(path: file) {
defer {
    aCharReader.close()
}
while let char = aCharReader.nextChar() {
    continue
}
}

该项目位于 GitHub 上:https://github.com/petershaw/charsinfile

非常感谢，附:

Answer 1

我更新了存储库，其中包含两个版本:https://github.com/petershaw/charsinfile

在 Martin 的帮助下，我修复了 Rob 代码中的错误。

我测试了一堆不同的文件，两个版本都工作正常。 Rob Napier 的代码效率更高!非常感谢，罗布。

感谢你们所有人帮助我找到最快的解决方案。很高兴这里有一个如此精彩和礼貌的社区，提供与 swift 和 cocoa 相关的东西。

祝你度过愉快的一周!

ps