如何转义JSON字符串?

我用 System.Web.HttpUtility.JavaScriptStringEncode

string quoted = HttpUtility.JavaScriptStringEncode(input);

建立在 the answer by Dejan ,你能做的就是 import System.Web.Helpers .NET Framework assembly ,然后使用以下函数:

static string EscapeForJson(string s) {
  string quoted = System.Web.Helpers.Json.Encode(s);
  return quoted.Substring(1, quoted.Length - 2);
}

这个 Substring 需要呼叫,因为 Encode 自动用双引号括住字符串。

对于那些使用Newtonsoft非常流行的Json.Net项目的用户来说,这项任务很简单:

using Newtonsoft.Json;

....
var s = JsonConvert.ToString(@"a\b");
Console.WriteLine(s);
....

此代码打印:

“a\\b”

也就是说,结果字符串值包含引号和转义反斜杠。

是的,只需将以下函数添加到Utils类或其他内容:

    public static string cleanForJSON(string s)
    {
        if (s == null || s.Length == 0) {
            return "";
        }

        char         c = '\0';
        int          i;
        int          len = s.Length;
        StringBuilder sb = new StringBuilder(len + 4);
        String       t;

        for (i = 0; i < len; i += 1) {
            c = s[i];
            switch (c) {
                case '\\':
                case '"':
                    sb.Append('\\');
                    sb.Append(c);
                    break;
                case '/':
                    sb.Append('\\');
                    sb.Append(c);
                    break;
                case '\b':
                    sb.Append("\\b");
                    break;
                case '\t':
                    sb.Append("\\t");
                    break;
                case '\n':
                    sb.Append("\\n");
                    break;
                case '\f':
                    sb.Append("\\f");
                    break;
                case '\r':
                    sb.Append("\\r");
                    break;
                default:
                    if (c < ' ') {
                        t = "000" + String.Format("X", c);
                        sb.Append("\\u" + t.Substring(t.Length - 4));
                    } else {
                        sb.Append(c);
                    }
                    break;
            }
        }
        return sb.ToString();
    }

我使用了以下代码来转义json的字符串值。 您需要将“”添加到以下代码的输出中:

public static string EscapeStringValue(string value)
{
    const char BACK_SLASH = '\\';
    const char SLASH = '/';
    const char DBL_QUOTE = '"';

    var output = new StringBuilder(value.Length);
    foreach (char c in value)
    {
        switch (c)
        {
            case SLASH:
                output.AppendFormat("{0}{1}", BACK_SLASH, SLASH);
                break;

            case BACK_SLASH:
                output.AppendFormat("{0}{0}", BACK_SLASH);
                break;

            case DBL_QUOTE:
                output.AppendFormat("{0}{1}",BACK_SLASH,DBL_QUOTE);
                break;

            default:
                output.Append(c);
                break;
        }
    }

    return output.ToString();
}

这里提供的方法是错误的。
既然可以使用System.Web.HttpUtility.JavaScriptEncode,为什么还要冒险这么远呢?

如果你在一个较低的框架上,你可以直接从mono复制过去

由mono项目提供@ https://github.com/mono/mono/blob/master/mcs/class/System.Web/System.Web/HttpUtility.cs

    public static string JavaScriptStringEncode(string value, bool addDoubleQuotes)
    {
        if (string.IsNullOrEmpty(value))
            return addDoubleQuotes ? "\"\"" : string.Empty;

        int len = value.Length;
        bool needEncode = false;
        char c;
        for (int i = 0; i < len; i++)
        {
            c = value[i];

            if (c >= 0 && c <= 31 || c == 34 || c == 39 || c == 60 || c == 62 || c == 92)
            {
                needEncode = true;
                break;
            }
        }

        if (!needEncode)
            return addDoubleQuotes ? "\"" + value + "\"" : value;

        var sb = new System.Text.StringBuilder();
        if (addDoubleQuotes)
            sb.Append('"');

        for (int i = 0; i < len; i++)
        {
            c = value[i];
            if (c >= 0 && c <= 7 || c == 11 || c >= 14 && c <= 31 || c == 39 || c == 60 || c == 62)
                sb.AppendFormat("\\u{0:x4}", (int)c);
            else switch ((int)c)
                {
                    case 8:
                        sb.Append("\\b");
                        break;

                    case 9:
                        sb.Append("\\t");
                        break;

                    case 10:
                        sb.Append("\\n");
                        break;

                    case 12:
                        sb.Append("\\f");
                        break;

                    case 13:
                        sb.Append("\\r");
                        break;

                    case 34:
                        sb.Append("\\\"");
                        break;

                    case 92:
                        sb.Append("\\\\");
                        break;

                    default:
                        sb.Append(c);
                        break;
                }
        }

        if (addDoubleQuotes)
            sb.Append('"');

        return sb.ToString();
    }

这可以压缩成

// https://github.com/mono/mono/blob/master/mcs/class/System.Json/System.Json/JsonValue.cs
public class SimpleJSON
{

    private static  bool NeedEscape(string src, int i)
    {
        char c = src[i];
        return c < 32 || c == '"' || c == '\\'
            // Broken lead surrogate
            || (c >= '\uD800' && c <= '\uDBFF' &&
                (i == src.Length - 1 || src[i + 1] < '\uDC00' || src[i + 1] > '\uDFFF'))
            // Broken tail surrogate
            || (c >= '\uDC00' && c <= '\uDFFF' &&
                (i == 0 || src[i - 1] < '\uD800' || src[i - 1] > '\uDBFF'))
            // To produce valid JavaScript
            || c == '\u2028' || c == '\u2029'
            // Escape "</" for <script> tags
            || (c == '/' && i > 0 && src[i - 1] == '<');
    }



    public static string EscapeString(string src)
    {
        System.Text.StringBuilder sb = new System.Text.StringBuilder();

        int start = 0;
        for (int i = 0; i < src.Length; i++)
            if (NeedEscape(src, i))
            {
                sb.Append(src, start, i - start);
                switch (src[i])
                {
                    case '\b': sb.Append("\\b"); break;
                    case '\f': sb.Append("\\f"); break;
                    case '\n': sb.Append("\\n"); break;
                    case '\r': sb.Append("\\r"); break;
                    case '\t': sb.Append("\\t"); break;
                    case '\"': sb.Append("\\\""); break;
                    case '\\': sb.Append("\\\\"); break;
                    case '/': sb.Append("\\/"); break;
                    default:
                        sb.Append("\\u");
                        sb.Append(((int)src[i]).ToString("x04"));
                        break;
                }
                start = i + 1;
            }
        sb.Append(src, start, src.Length - start);
        return sb.ToString();
    }
}

我也建议使用 JSON.NET 提到了库,但如果必须在生成的JSON字符串中转义unicode字符(例如,uxxx格式),则可能必须自己转义。看一看 Converting Unicode strings to escaped ascii string 举个例子。

我对其中一些答案进行了长串和短串的速度测试。克莱夫帕特森的 code 赢了一点,大概是因为其他人考虑了序列化选项。以下是我的结果:

Apple Banana
System.Web.HttpUtility.JavaScriptStringEncode: 140ms
System.Web.Helpers.Json.Encode: 326ms
Newtonsoft.Json.JsonConvert.ToString: 230ms
Clive Paterson: 108ms

\\some\long\path\with\lots\of\things\to\escape\some\long\path\t\with\lots\of\n\things\to\escape\some\long\path\with\lots\of\"things\to\escape\some\long\path\with\lots"\of\things\to\escape
System.Web.HttpUtility.JavaScriptStringEncode: 2849ms
System.Web.Helpers.Json.Encode: 3300ms
Newtonsoft.Json.JsonConvert.ToString: 2827ms
Clive Paterson: 1173ms

下面是测试代码:

public static void Main(string[] args)
{
    var testStr1 = "Apple Banana";
    var testStr2 = @"\\some\long\path\with\lots\of\things\to\escape\some\long\path\t\with\lots\of\n\things\to\escape\some\long\path\with\lots\of\""things\to\escape\some\long\path\with\lots""\of\things\to\escape";

    foreach (var testStr in new[] { testStr1, testStr2 })
    {
        var results = new Dictionary<string,List<long>>();

        for (var n = 0; n < 10; n++)
        {
            var count = 1000 * 1000;

            var sw = Stopwatch.StartNew();
            for (var i = 0; i < count; i++)
            {
                var s = System.Web.HttpUtility.JavaScriptStringEncode(testStr);
            }
            var t = sw.ElapsedMilliseconds;
            results.GetOrCreate("System.Web.HttpUtility.JavaScriptStringEncode").Add(t);

            sw = Stopwatch.StartNew();
            for (var i = 0; i < count; i++)
            {
                var s = System.Web.Helpers.Json.Encode(testStr);
            }
            t = sw.ElapsedMilliseconds;
            results.GetOrCreate("System.Web.Helpers.Json.Encode").Add(t);

            sw = Stopwatch.StartNew();
            for (var i = 0; i < count; i++)
            {
                var s = Newtonsoft.Json.JsonConvert.ToString(testStr);
            }
            t = sw.ElapsedMilliseconds;
            results.GetOrCreate("Newtonsoft.Json.JsonConvert.ToString").Add(t);

            sw = Stopwatch.StartNew();
            for (var i = 0; i < count; i++)
            {
                var s = cleanForJSON(testStr);
            }
            t = sw.ElapsedMilliseconds;
            results.GetOrCreate("Clive Paterson").Add(t);
        }

        Console.WriteLine(testStr);
        foreach (var result in results)
        {
            Console.WriteLine(result.Key + ": " + Math.Round(result.Value.Skip(1).Average()) + "ms");
        }
        Console.WriteLine();
    }

    Console.ReadLine();
}

那么System.Web.Helpers.Json.Encode(…)呢(请参见 http://msdn.microsoft.com/en-us/library/system.web.helpers.json.encode(v=vs.111).aspx )?

String.Format("X", c);

只输出:X

请改为:

string t = ((int)c).ToString("X");

sb.Append("\\u" + t.PadLeft(4, '0'));

我很好的一行,使用了JsonConvert,就像其他人一样,但是添加了子字符串来删除添加的引号和反斜杠。

 var escapedJsonString = JsonConvert.ToString(JsonString).Substring(1, JsonString.Length - 2);

有一个Json库在 Codeplex