使用 NSRegularExpression 匹配的奇怪字符串范围行为

Question

我正在尝试解析原始 HTTP 响应，但在尝试将 NSRange 转换为范围时得到的范围不正确。这是来自 playground 的相关代码：

public extension NSRange {
    public func toStringRange(_ str: String) -> Range<String.Index>? {
        guard str.characters.count >= length - location  && location < str.characters.count else { return nil }
        let fromIdx = str.characters.index(str.startIndex, offsetBy: self.location)
        print("from: \(self.location) = \(fromIdx)")
        let toIdx = str.characters.index(fromIdx, offsetBy: self.length)
        return fromIdx..<toIdx
    }
}

let responseString = "HTTP/1.0 200 OK\r\nContent-Length: 193\r\nContent-Type: application/json\r\n"
let responseRange = NSRange(location: 0, length: responseString.characters.count)
let responseRegex = try! NSRegularExpression(pattern: "^(HTTP/1.\d) (\d+) (.*?\r\n)(.*)", options: [.anchorsMatchLines])
guard let matchResult = responseRegex.firstMatch(in: responseString, options: [], range: responseRange),
    matchResult.numberOfRanges == 5,
    let versionRange = matchResult.rangeAt(1).toStringRange(responseString),
    let statusRange = matchResult.rangeAt(2).toStringRange(responseString),
    let headersRange = matchResult.rangeAt(4).toStringRange(responseString)
    else { fatalError() }

toStringRange() 中打印的输出是

from: 0 = Index(_base: Swift.String.UnicodeScalarView.Index(_position: 0), _countUTF16: 1)
from: 9 = Index(_base: Swift.String.UnicodeScalarView.Index(_position: 9), _countUTF16: 1)
from: 17 = Index(_base: Swift.String.UnicodeScalarView.Index(_position: 18), _countUTF16: 1)

为什么第 3 次 toStringRange() 调用返回的字符串范围从 18 而不是 17 开始？

Answer 1

你的从NSRange到Range<String.Index>的转换方法不对于外部的扩展字素簇和字符可以正常工作 "basic multilingual plane"（表情符号、旗帜等）。

NSRange 计算 UTF-16 代码点（对应于 unichar NSString 中的表示）。 Range<String.Index> 计数 Swift Characters 表示扩展字素簇。

在您的具体情况下，"\r\n" 算作两个 UTF-16 代码点，但是作为单个 Character，这会导致不需要的 "shift".

这是一个简化的例子：

let responseString = "OK\r\nContent-Length"

let nsRange = (responseString as NSString).range(of: "Content")
print(nsRange.location, nsRange.length) // 4 7

if let sRange1 = nsRange.toStringRange(responseString) {
    print(responseString.substring(with: sRange1)) // "ontent-"
}

使用方法

extension String {
    func range(from nsRange: NSRange) -> Range<String.Index>? {
        guard
            let from16 = utf16.index(utf16.startIndex, offsetBy: nsRange.location, limitedBy: utf16.endIndex),
            let to16 = utf16.index(from16, offsetBy: nsRange.length, limitedBy: utf16.endIndex),
            let from = String.Index(from16, within: self),
            let to = String.Index(to16, within: self)
            else { return nil }
        return from ..< to
    }
}

从 NSRange to Range<String.Index> 你会得到预期的结果：

if let sRange2 = responseString.range(from: nsRange) {
    print(responseString.substring(with: sRange2)) // "Content"
}

使用 NSRegularExpression 匹配的奇怪字符串范围行为

strange string range behavior using NSRegularExpression matches

regex

swift

nsregularexpression