在C#中验证HTML5

Question

我们目前正在C#中构建一个绿色领域的应用程序.我们有广泛的UI测试,使用Selenium Web Driver.这些测试(以及单元测试)由我们的CI服务器运行.

Selenium公开了一个.PageSource属性,对我来说,通过HTML5验证器运行该源作为每个UI测试的另一部分是有意义的.

我想了解http://validator.w3.org/所采用的相同类型的东西.作为奖励,我还想了解508个问题.

我的问题是我找不到任何可以在本地执行此操作的内容,并且很容易集成到我的UI测试中.W3C站点公开了一个SOAP api,但是我不想在CI过程中访问他们的站点.它们似乎也不支持获取SOAP响应.我想避免在本地安装完整的W3C服务器.

我看到的最接近的是http://www.totalvalidator.com/,使用它需要编写临时文件和解析报告.

在我走下这条赛道之前,我以为我会看到是否有人知道另一种方式.最好是我可以调用的DotNet组件.

C

Answer 1

在花了整个周末解决这个问题之后，我能看到的唯一解决方案是一个名为 CSE HTML Validator 的商业库

它位于此处http://www.htmlvalidator.com/htmldownload.html

我为它写了一个简单的包装。这是代码

using Newtonsoft.Json;
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.Linq;

[assembly: CLSCompliant(true)]
namespace HtmlValidator
{

public class Validator
{
    #region Constructors...

    public Validator(string htmlToValidate)
    {
        HtmlToValidate = htmlToValidate;
        HasExecuted = false;
        Errors = new List<ValidationResult>();
        Warnings = new List<ValidationResult>();
        OtherMessages = new List<ValidationResult>();

    }

    #endregion



    #region Properties...
    public IList<ValidationResult> Errors { get; private set; }
    public bool HasExecuted { get; private set; }
    public string HtmlToValidate { get; private set; }
    public IList<ValidationResult> OtherMessages { get; private set; }
    public string ResultsString { get; private set; }
    public string TempFilePath { get; private set; }
    public IList<ValidationResult> Warnings { get; private set; }
    #endregion



    #region Public methods...
    public void ValidateHtmlFile()
    {

        WriteTempFile();

        ExecuteValidator();

        DeleteTempFile();

        ParseResults();

        HasExecuted = true;
    }

    #endregion



    #region Private methods...
    private void DeleteTempFile()
    {
        TempFilePath = Path.GetTempFileName();
        File.Delete(TempFilePath);
    }


    private void ExecuteValidator()
    {
        var psi = new ProcessStartInfo(GetHTMLValidatorPath())
        {
            RedirectStandardInput = false,
            RedirectStandardOutput = true,
            RedirectStandardError = false,
            UseShellExecute = false,
            Arguments = String.Format(@"-e,(stdout),0,16 ""{0}""", TempFilePath)
        };

        var p = new Process
        {
            StartInfo = psi
        };
        p.Start();

        var stdOut = p.StandardOutput;

        ResultsString = stdOut.ReadToEnd();
    }


    private static string GetHTMLValidatorPath()
    {
        return @"C:\Program Files (x86)\HTMLValidator120\cmdlineprocessor.exe";
    }


    private void ParseResults()
    {
        var results = JsonConvert.DeserializeObject<dynamic>(ResultsString);
        IList<InternalValidationResult> messages = results.messages.ToObject<List<InternalValidationResult>>();


        foreach (InternalValidationResult internalValidationResult in messages)
        {
            ValidationResult result = new ValidationResult()
            {
                Message = internalValidationResult.message,
                LineNumber = internalValidationResult.linenumber,
                MessageCategory = internalValidationResult.messagecategory,
                MessageType = internalValidationResult.messagetype,
                CharLocation = internalValidationResult.charlocation
            };

            switch (internalValidationResult.messagetype)
            {
                case "ERROR":
                    Errors.Add(result);
                    break;

                case "WARNING":
                    Warnings.Add(result);
                    break;

                default:
                    OtherMessages.Add(result);
                    break;
            }
        }
    }


    private void WriteTempFile()
    {
        TempFilePath = Path.GetTempFileName();
        StreamWriter streamWriter = File.AppendText(TempFilePath);
        streamWriter.WriteLine(HtmlToValidate);
        streamWriter.Flush();
        streamWriter.Close();
    }
    #endregion
}
}




public class ValidationResult
{
    public string MessageType { get; set; }
    public string MessageCategory { get; set; }
    public string Message { get; set; }
    public int LineNumber { get; set; }
    public int CharLocation { get; set; }


    public override string ToString()
    {
        return String.Format("{0} Line {1} Char {2}:: {3}", this.MessageType, this.LineNumber, this.CharLocation, this.Message);

    }

}


public class InternalValidationResult
{
    /*
     * DA: this class is used as in intermediate store of messages that come back from the underlying validator. The fields must be cased as per the underlying Json object.
     * That is why they are ignored.
     */
    #region Properties...
    [System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1709:IdentifiersShouldBeCasedCorrectly", MessageId = "charlocation"), System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1704:IdentifiersShouldBeSpelledCorrectly", MessageId = "charlocation")]
    public int charlocation { get; set; }
    [System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1709:IdentifiersShouldBeCasedCorrectly", MessageId = "linenumber"), System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1704:IdentifiersShouldBeSpelledCorrectly", MessageId = "linenumber")]

    public int linenumber { get; set; }
    [System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1709:IdentifiersShouldBeCasedCorrectly", MessageId = "message"), System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1704:IdentifiersShouldBeSpelledCorrectly", MessageId = "message")]

    public string message { get; set; }
    [System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1704:IdentifiersShouldBeSpelledCorrectly", MessageId = "messagecategory"), System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1709:IdentifiersShouldBeCasedCorrectly", MessageId = "messagecategory")]
    public string messagecategory { get; set; }
    [System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1709:IdentifiersShouldBeCasedCorrectly", MessageId = "messagetype"), System.Diagnostics.CodeAnalysis.SuppressMessage("Microsoft.Naming", "CA1704:IdentifiersShouldBeSpelledCorrectly", MessageId = "messagetype")]

    public string messagetype { get; set; }
    #endregion
}

使用/测试

   private const string ValidHtml = "<!DOCType html><html><head></head><body><p>Hello World</p></body></html>";
    private const string BrokenHtml = "<!DOCType html><html><head></head><body><p>Hello World</p></body>";

    [TestMethod]
    public void CanValidHtmlStringReturnNoErrors()
    {
        Validator subject = new Validator(ValidHtml);
        subject.ValidateHtmlFile();
        Assert.IsTrue(subject.HasExecuted);
        Assert.IsTrue(subject.Errors.Count == 0);
    }


    [TestMethod]
    public void CanInvalidHtmlStringReturnErrors()
    {
        Validator subject = new Validator(BrokenHtml);
        subject.ValidateHtmlFile();
        Assert.IsTrue(subject.HasExecuted);
        Assert.IsTrue(subject.Errors.Count > 0);
        Assert.IsTrue(subject.Errors[0].ToString().Contains("ERROR"));
    }