Question

I have an HTML document with unclosed <LI> elements. I need to append </LI> to the end of each </OBJECT> that follows the opening <LI> tag.
Note: Objects that aren’t preceded by <LI> should not have an </LI> tag appended to </OBJECT>

<OBJECT value="example">
    <param name="Joe">

    </OBJECT>
<UL>
    <LI> <OBJECT type="example">
        <param name="Pat">
        <param name="State" value="Arizona">
        </OBJECT>
    <UL>
        <LI> <OBJECT type="example">
            <param name="Steve">
            <param name="State" value="California">
            </OBJECT>

<OBJECT type="text/sitemap">
    <param name="Carol">

    </OBJECT>

This is what I’ve got so far with no luck

private void closeListItems(string doc)
{
    StringBuilder sb = new StringBuilder();
    Regex rx = new Regex("(<LI>.(.+?)</OBJECT>)", RegexOptions.Multiline | RegexOptions.IgnoreCase);
    string[] hhcFile = File.ReadAllLines(doc);
    string temp = "";
    foreach (string line in hhcFile)
    {
        temp += line + "\n";
    }
    temp = rx.Replace(temp, "<LI>");
    StreamWriter sw = new StreamWriter(Application.StartupPath + "\\liFix.txt");
    sw.Write(temp);
    sw.Close();

}

UPDATE: I also tried this with no luck:

private void closeListItems(string doc)
{
    StringBuilder sb = new StringBuilder();
    string[] hhcFile = File.ReadAllLines(doc);
    string temp = "";
    bool liOpen = false;
    foreach (string line in hhcFile)
    {
        temp = line;
        if (line.Contains("<LI>"))
        {
            liOpen = true;
        }
        if (line.Contains("</OBJECT>") && liOpen == true)
        {
            temp.Replace(temp, temp + "</LI>");
            liOpen = false;
        }
        sb.Append("\n" + temp);
    }
    File.WriteAllText("fixLi.txt", sb.ToString());

}

Answer 1

This answer is just in terms of your update:

string.Replace returns a string. Strings are immutable in C# which means you can’t directly change the string. Any operation that appears to change the string actually returns one.

Therefore, this line:

temp.Replace(temp, temp + "</LI>");

..does nothing. It should be:

temp = temp.Replace(temp, temp + "</LI>");