Split string in square brackets from Google translator

Question

I am receiving a data from a Google Language Translator service and need help splitting the data.

void Start()
{
    translateText("Hello, This is a test!", "en", "fr");
}

void translateText(string text, string fromLanguage, string toLanguage)
{
    string url = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=" + fromLanguage + "&tl=" + toLanguage + "&dt=t&q=" + Uri.EscapeUriString(text);
    StartCoroutine(startTranslator(url));
}

IEnumerator startTranslator(string url)
{
    UnityWebRequest www = UnityWebRequest.Get(url);
    yield return www.Send();

    Debug.Log("Raw string Received: " + www.downloadHandler.text);

    LanguageResult tempResult = decodeResult(www.downloadHandler.text);

    Debug.Log("Original Text: " + tempResult.originalText);
    Debug.Log("Translated Text: " + tempResult.translatedText);
    Debug.Log("LanguageIso: " + tempResult.languageIso);

    yield return null;
}

LanguageResult decodeResult(string result)
{
    char[] delims = { '[', '\"', ']', ',' };
    string[] arr = result.Split(delims, StringSplitOptions.RemoveEmptyEntries);

    LanguageResult tempLang = null;
    if (arr.Length >= 4)
    {
        tempLang = new LanguageResult();
        tempLang.translatedText = arr[0];
        tempLang.originalText = arr[1];
        tempLang.unknowValue = arr[2];
        tempLang.languageIso = arr[3];
    }
    return tempLang;
}

public class LanguageResult
{
    public string translatedText;
    public string originalText;
    public string unknowValue;
    public string languageIso;
}

then calling it with translateText("Hello, This is a test!", "en", "fr"); from the Start() function which converts the English sentence to French with ISO 639-1 Code.

The received data looks like this:

[[["Bonjour, Ceci est un test!","Hello, This is a test!",,,0]],,"en"]

I want to split it like this:

• Bonjour, Ceci est un test!
• Hello, This is a test!
• 0
• en

and put them into a string array in order.

I currently use this:

char[] delims = { '[', '\"', ']', ',' };
        string[] arr = result.Split(delims, StringSplitOptions.RemoveEmptyEntries);

This works if there is no comma in the received string. If there is a comma, the splitted values are messed up. What's the best way of splitting this?

EDIT:

With Blorgbeard's solution, the final working code is as below. Hopefully, this will help somebody else. This shouldn't be used for commercial purposes but for personal or school project.

void Start()
{
    //translateText("Hello, This is \" / \\ a test !", "en", "fr");
    //translateText("Hello, This is , \\ \" a test !", "en", "fr");
    translateText("Hello, This is a test!", "en", "fr");
}

void translateText(string text, string fromLanguage, string toLanguage)
{
    string url = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=" + fromLanguage + "&tl=" + toLanguage + "&dt=t&q=" + Uri.EscapeUriString(text);
    StartCoroutine(startTranslator(url));
}

IEnumerator startTranslator(string url)
{
    UnityWebRequest www = UnityWebRequest.Get(url);
    yield return www.Send();

    Debug.Log("Raw string Received: " + www.downloadHandler.text);

    LanguageResult tempResult = decodeResult(www.downloadHandler.text);
    displayResult(tempResult);
    yield return null;
}

void displayResult(LanguageResult translationResult)
{
    Debug.Log("Original Text: " + translationResult.originalText);
    Debug.Log("Translated Text: " + translationResult.translatedText);
    Debug.Log("LanguageIso: " + translationResult.languageIso);
}

LanguageResult decodeResult(string result)
{
    string[] arr = Decode(result);

    LanguageResult tempLang = null;
    if (arr.Length >= 4)
    {
        tempLang = new LanguageResult();
        tempLang.translatedText = arr[0];
        tempLang.originalText = arr[1];
        tempLang.unknowValue = arr[2];
        tempLang.languageIso = arr[3];
    }
    return tempLang;
}

public class LanguageResult
{
    public string translatedText;
    public string originalText;
    public string unknowValue;
    public string languageIso;
}

private string[] Decode(string input)
{
    List<string> finalResult = new List<string>();

    bool inToken = false;
    bool inString = false;
    bool escaped = false;
    var seps = ",[]\"".ToArray();
    var current = "";
    foreach (var chr in input)
    {
        if (!inString && chr == '"')
        {
            current = "";
            inString = true;
            continue;
        }
        if (inString && !escaped && chr == '"')
        {
            finalResult.Add(current);
            current = "";
            inString = false;
            continue;
        }
        if (inString && !escaped && chr == '\\')
        {
            escaped = true;
            continue;
        }
        if (inString && (chr != '"' || escaped))
        {
            escaped = false;
            current += chr;
            continue;
        }
        if (inToken && seps.Contains(chr))
        {
            finalResult.Add(current);
            current = "";
            inToken = false;
            continue;
        }
        if (!inString && chr == '"')
        {
            inString = true;
            current = "";
            continue;
        }
        if (!inToken && !seps.Contains(chr))
        {
            inToken = true;
            current = "";
        }
        current += chr;
    }
    return finalResult.ToArray();
}

Answer 1

You could code up a simple parser yourself. Here's one I threw together (could use some cleaning up, but demonstrates the idea):

private static IEnumerable<string> Parse(string input) {
    bool inToken = false;
    bool inString = false;
    bool escaped = false;
    var seps = ",[]\"".ToArray();
    var current = "";
    foreach (var chr in input) {
        if (!inString && chr == '"') {
            current = "";
            inString = true;
            continue;
        }
        if (inString && !escaped && chr == '"') {
            yield return current;
            current = "";
            inString = false;
            continue;
        }
        if (inString && !escaped && chr == '\\') {
            escaped = true;
            continue;
        }
        if (inString && (chr != '"' || escaped)) {
            escaped = false;
            current += chr;
            continue;
        }
        if (inToken && seps.Contains(chr)) {
            yield return current;
            current = "";
            inToken = false;
            continue;
        }
        if (!inString && chr == '"') {
            inString = true;
            current = "";
            continue;
        }
        if (!inToken && !seps.Contains(chr)) {
            inToken = true;
            current = "";
        }
        current += chr;
    }
}

Here's a jsfiddle demo.

Answer 2

Using Regex.Split you could do something like this for example:

using System;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
        var input ="[[[\"Bonjour, Ceci est un test!\",\"Hello, This is a test!\",,,0]],,\"en\"]";
        var parse = Regex.Split(input, "\\[|\\]|[^a-zA-Z ],|\",\"|\"|\"");
        foreach(var item in parse) {
            bool result = !String.IsNullOrEmpty(item) && (Char.IsLetter(item[0]) || Char.IsDigit(item[0]));
            if (result) {
                Console.WriteLine(item);
            }
        }
   }
}

Output:

Bonjour, Ceci est un test!
Hello, This is a test!
0
en

If you want everything that was split you can simply remove the bool check for alphacharacters.

Answer 3

Here is a crazy idea - split by " and then by the rest (but won't work if there is " between the "'s)

var s = @"[[[""Bonjour, Ceci est un test!"",""Hello, This is a test!"",,,0]],,""en""]";

var a = s.Split('"').Select((x, i) => (i & 1) > 0 ? new[] { x } : x.Split("[],".ToArray(),  
                     StringSplitOptions.RemoveEmptyEntries)).SelectMany(x => x).ToArray();

Debug.Print(string.Join("|", a)); // "Bonjour, Ceci est un test!|Hello, This is a test!|0|en"

Answer 4

You can try regex for splitting. I tested with the sample you provided. It results like this.

    var str="[[[\"Bonjour, Ceci est un test!\",\"Hello, This is a test!\",,,0]],,\"en\"]";
    var splitted=Regex.Split(str,@"\[|\]|\,");
    foreach(var split in splitted){
       Console.WriteLine(split );
    }

   "Bonjour Ceci est un test!"
   "Hello This is a test!"
    0
   "en"