I would like to use swift 5 to programmatically split a sentence into words as well as punctuations including spaces.

1. input: "Hello, I am Albert Einstein."
2. output: ["Hello", ",", " ", "I", " ", "am", " ", "Albert", " ", "Einstein", "."]

I adopted the code provided by @Duyen-Hoa (Split text into array while maintaining the punctuation in Swift) and slightly modified it into the following code (I basically just deleted the parts deleting the space). But, I cannot get arraies for including just a space. Instead, I am somehow getting space included at the beginning of the array with each word.

func sentenceSplitter(text_input: String) ->  [String]  {
                    
        var list = [String]()
        var currentSubString = "";
        text.enumerateSubstrings(in: text.startIndex..<text.endIndex, options: String.EnumerationOptions.byComposedCharacterSequences) { (substring, substringRange, enclosingRange, value) in
            if let _subString = substring {
                if (!currentSubString.isEmpty &&
                    (_subString.compare(" ") == .orderedSame
                     || _subString.compare(",") == .orderedSame
                     || _subString.compare(".") == .orderedSame
                     || _subString.compare(";") == .orderedSame
                     || _subString.compare("!") == .orderedSame
                     || _subString.compare("?") == .orderedSame
                    )
                ) {
                    //create word if see any of those character and currentSubString is not empty
                    list.append(currentSubString)
                    currentSubString = _subString
                } else {
                        currentSubString  = _subString
                    
                }
            }
        }
        
        //last word
        if (!currentSubString.isEmpty) {
            list.append(currentSubString)
        }
        
        
        return list
    }

Could you let me know what I am doing wrong?

Original code from: Duyen-Hoa

var str = "Hello, I am Albert Einstein."
var list = [String]()
var currentSubString = "";
//enumerate to get all characters including ".", ",", ";", " "
str.enumerateSubstrings(in: str.startIndex..<str.endIndex, options: String.EnumerationOptions.byComposedCharacterSequences) { (substring, substringRange, enclosingRange, value) in
    if let _subString = substring {
        if (!currentSubString.isEmpty &&
            (_subString.compare(" ") == .orderedSame
                || _subString.compare(",") == .orderedSame
                || _subString.compare(".") == .orderedSame
                || _subString.compare(";") == .orderedSame
            )
            ) {
            //create word if see any of those character and currentSubString is not empty
            list.append(currentSubString)
            currentSubString = _subString.trimmingCharacters(in: CharacterSet.whitespaces )
        } else {
            //add to current sub string if current character is not space.
            if (_subString.compare(" ") != .orderedSame) {
                currentSubString  = _subString
            }
        }
    }
} 


//last word
if (!currentSubString.isEmpty) {
    list.append(currentSubString)
}

CodePudding user response：

Here you don't need to remove

.trimmingCharacters(in: CharacterSet.whitespaces)

Instead you need to detect where it's ignoring space from the _subString and there you need to add

if _subString == " " {
    list.append(_subString)
}

And your code will look like below:

let str = "Hello, I am Albert Einstein."
var list = [String]()


var currentSubString = "";

    str.enumerateSubstrings(in: str.startIndex..<str.endIndex, options: String.EnumerationOptions.byComposedCharacterSequences) { (substring, substringRange, enclosingRange, value) in
        
        if let _subString = substring {
            if (!currentSubString.isEmpty &&
                (_subString.compare(" ") == .orderedSame
                    || _subString.compare(",") == .orderedSame
                    || _subString.compare(".") == .orderedSame
                    || _subString.compare(";") == .orderedSame
                )
            ) {
                list.append(currentSubString)
                //If _subString is a space
                if _subString == " " {
                    list.append(_subString)
                }
                currentSubString = _subString.trimmingCharacters(in: CharacterSet.whitespaces)
            } else {
                if (_subString.compare(" ") != .orderedSame) {
                    currentSubString  = _subString
                } else {
                    //If _subString is a space at start
                    if _subString == " " {
                        list.append(_subString)
                    }
                }
            }
        }
    }

    if (!currentSubString.isEmpty) {
        list.append(currentSubString)
    }

    print(list)

Here input is "Hello, I am Albert Einstein." And output will be:

["Hello", ",", " ", "I", " ", "am", " ", "Albert", " ", "Einstein", "."]

Hope it will help.