c# - XPath 查询中的撇号 (')

Question

我使用以下 XPATH 查询 列出站点下的对象。 ListObject[@Title='SomeValue']。 SomeValue 是动态的。只要 SomeValue 没有撇号 (')，此查询就有效。也尝试使用转义序列。没用。

我做错了什么？

Answer 1

这很难做到。

看看XPath Recommendation ，你会看到它定义了一个文字:

Literal ::=   '"' [^"]* '"' 
            | "'" [^']* "'"

也就是说，XPath 表达式中的字符串文字可以包含撇号或双引号，但不能同时包含两者。

你不能使用转义来解决这个问题。像这样的文字:

'Some'Value'

将匹配此 XML 文本:

Some'Value

这确实意味着可能有一段 XML 文本无法生成 XPath 文字来匹配，例如:

<elm att="&quot;&apos"/>

但这并不意味着不可能用 XPath 匹配该文本，它只是很棘手。在您尝试匹配的值包含单引号和双引号的任何情况下，您都可以构造一个表达式，使用 concat 来生成它将匹配的文本:

elm[@att=concat('"', "'")]

所以这导致我们这样做，这比我想要的要复杂得多:

/// <summary>
/// Produce an XPath literal equal to the value if possible; if not, produce
/// an XPath expression that will match the value.
/// 
/// Note that this function will produce very long XPath expressions if a value
/// contains a long run of double quotes.
/// </summary>
/// <param name="value">The value to match.</param>
/// <returns>If the value contains only single or double quotes, an XPath
/// literal equal to the value.  If it contains both, an XPath expression,
/// using concat(), that evaluates to the value.</returns>
static string XPathLiteral(string value)
{
    // if the value contains only single or double quotes, construct
    // an XPath literal
    if (!value.Contains("\""))
    {
        return "\"" + value + "\"";
    }
    if (!value.Contains("'"))
    {
        return "'" + value + "'";
    }

    // if the value contains both single and double quotes, construct an
    // expression that concatenates all non-double-quote substrings with
    // the quotes, e.g.:
    //
    //    concat("foo", '"', "bar")
    StringBuilder sb = new StringBuilder();
    sb.Append("concat(");
    string[] substrings = value.Split('\"');
    for (int i = 0; i < substrings.Length; i++ )
    {
        bool needComma = (i>0);
        if (substrings[i] != "")
        {
            if (i > 0)
            {
                sb.Append(", ");
            }
            sb.Append("\"");
            sb.Append(substrings[i]);
            sb.Append("\"");
            needComma = true;
        }
        if (i < substrings.Length - 1)
        {
            if (needComma)
            {
                sb.Append(", ");                    
            }
            sb.Append("'\"'");
        }

    }
    sb.Append(")");
    return sb.ToString();
}

是的，我在所有边缘情况下都对其进行了测试。这就是为什么逻辑如此复杂的原因:

    foreach (string s in new[]
    {
        "foo",              // no quotes
        "\"foo",            // double quotes only
        "'foo",             // single quotes only
        "'foo\"bar",        // both; double quotes in mid-string
        "'foo\"bar\"baz",   // multiple double quotes in mid-string
        "'foo\"",           // string ends with double quotes
        "'foo\"\"",         // string ends with run of double quotes
        "\"'foo",           // string begins with double quotes
        "\"\"'foo",         // string begins with run of double quotes
        "'foo\"\"bar"       // run of double quotes in mid-string
    })
    {
        Console.Write(s);
        Console.Write(" = ");
        Console.WriteLine(XPathLiteral(s));
        XmlElement elm = d.CreateElement("test");
        d.DocumentElement.AppendChild(elm);
        elm.SetAttribute("value", s);

        string xpath = "/root/test[@value = " + XPathLiteral(s) + "]";
        if (d.SelectSingleNode(xpath) == elm)
        {
            Console.WriteLine("OK");
        }
        else
        {
            Console.WriteLine("Should have found a match for {0}, and didn't.", s);
        }
    }
    Console.ReadKey();
}