CTRunGetGlyphs返回的CGGlyph不存在时，如何手动合并字符？

背景 #

我正在使用CTRunGetGlyphs处理NSAttributedString，目标是获取字符串"ffifion 🇬🇧"的字形并逐个传入其他函数。注意：ff应作为连字，字符串末尾包含Unicode旗帜表情，但当前使用的字体中没有ff连字。

返回的字形如下：

1st CTRun
  - 0 : 398 (ff)
  - 1 : 257
  - 2 : 399 (fi)
  - 3 : 295
  - 4 : 287
  - 5 : 1

2nd CTRun
  - 0 : 428 

当前遍历字形的代码 #

extension NSMutableAttributedString {
func readGlyphs(size: CGSize) {

        var output: [Glyph] = []
        var characterCounter: Int = 0

        let attributedString = self

        let string = attributedString.string

        let framesetter = CTFramesetterCreateWithAttributedString(attributedString)
        let bounds = CGRect(x: 0, y: 0, width: size.width, height: size.height)

        let frame = CTFramesetterCreateFrame(framesetter, CFRange(), CGPath(rect: bounds, transform: nil), nil)

        let lines = CTFrameGetLines(frame) as? [CTLine] ?? []

        let linesCount = lines.count

        let lineOrigins: [CGPoint] = [CGPoint](unsafeUninitializedCapacity: linesCount) { (bufferPointer, count) in
            if let baseAddress = bufferPointer.baseAddress {
                CTFrameGetLineOrigins(frame, CFRange(), baseAddress)
                count = linesCount
            }
        }

        for i in 0..<lineOrigins.count {
            let line = lines[i]
            guard let runs = CTLineGetGlyphRuns(line) as? [CTRun] else {
                continue
            }

            for run in runs {

                let runGlyphsCount = CTRunGetGlyphCount(run)
                let glyphPositions = [CGPoint](unsafeUninitializedCapacity: runGlyphsCount) { (bufferPointer, count) in
                    if let baseAddress = bufferPointer.baseAddress {
                        CTRunGetPositions(run, CFRange(), baseAddress)
                        count = runGlyphsCount
                    }
                }

                let glyphs = [CGGlyph](unsafeUninitializedCapacity: runGlyphsCount) { (bufferPointer, count) in
                    if let baseAddress = bufferPointer.baseAddress {
                        CTRunGetGlyphs(run, CFRange(), baseAddress)
                        count = runGlyphsCount
                    }
                }

                guard var attributes: [String: Any] = (CTRunGetAttributes(run) as NSDictionary as? [String: Any]) else { return }
                   attributes = attributes
                    .reduce([:]) { (partialResult: [String: Any], tuple: (key: String, value: Any)) in
                       var result = partialResult
                       result[tuple.key] = tuple.value
                       return result
                   }

                // swiftlint:disable force_cast
                let font = attributes["NSFont"] as! CTFont
                // swiftlint:enable force_cast

                let map = createUnicodeFontMap(ctFont: font)

                var indices = Array(repeating: CFIndex(), count: runGlyphsCount)
                CTRunGetStringIndices(run, CFRange(), &indices)

                for k in 0..<glyphs.count {

                    let char: Character = Array(string)[k]
                    let scalar: UnicodeScalar? = map[glyphs[k]]
                    let indicie = indices[k]

                    let charValue: String
                    if let scalar {
                        charValue = String(scalar)
                    } else {
                        charValue = String(char)
                    }


                    //processCharacter(char: ?????)

                    characterCounter += 1
                }
            }
        }

    }
}

调用方式：

let _ = NSAttributedString("ffifion 🇬🇧").readGlyphs(size: CGSize(width: 380, height: 10_000))

核心问题 #

第一个CGGlyph无法找到对应的Unicode标量，如何将第一个字符与下一个合并为"ff"，同时确保表情符号和其他有效Glyph正常工作？尝试过循环合并字符直到获取有效标量，但方法不够通用，需要能适配任意字符串的解决方案。

用于建立CGGlyph到UnicodeScalar映射的函数 #

func createUnicodeFontMap(ctFont: CTFont) -> [CGGlyph: UnicodeScalar] {

    let charset = CTFontCopyCharacterSet(ctFont) as CharacterSet

    var glyphToUnicode = [CGGlyph: UnicodeScalar]() // Start with empty map.

    // Enumerate all Unicode scalar values from the character set:
    for plane: UInt8 in 0...16 where charset.hasMember(inPlane: plane) {
        for unicode in UTF32Char(plane) << 16 ..< UTF32Char(plane + 1) << 16 {
            if let uniChar = UnicodeScalar(unicode), charset.contains(uniChar) {

                // Get glyph for this `uniChar` ...
                let utf16 = Array(uniChar.utf16)
                var glyphs = [CGGlyph](repeating: 0, count: utf16.count)
                if CTFontGetGlyphsForCharacters(ctFont, utf16, &glyphs, utf16.count) {
                    // ... and add it to the map.
                    glyphToUnicode[glyphs[0]] = uniChar
                }
            }
        }
    }

    return glyphToUnicode
}

可行的解决方案（更新） #

以下代码可满足需求，通过CTRunGetStringIndices返回的索引范围来获取每个Glyph对应的原字符串片段：

var char: String = "" 
let firstIndex = indices[k]
if indices.indices.contains(k+1) {
    let slice = firstIndex..<indices[k+1]
    char = String(Array(string)[slice])
} else {
    if Array(string).indices.contains(firstIndex) {
        char = String(Array(string)[firstIndex])
    }
}

字体与Unicode的对应关系确实是一个复杂的领域，需要结合CoreText提供的索引映射来准确关联Glyph和原字符串内容。

内容的提问来源于stack exchange，提问作者Chris