public void Verify_sanitize_of_single_mhtml_file()
{
var tempFile = Path.ChangeExtension(Path.GetTempFileName(), ".mht");
File.Copy(TestConfig.PathToMht, tempFile);
string mhtml = File.ReadAllText(tempFile);
MHTMLParser parser = new MHTMLParser(mhtml)
{
OutputDirectory = Path.GetDirectoryName(tempFile),
DecodeImageData = true
};
var outFile = Path.ChangeExtension(tempFile, ".html");
File.WriteAllText(outFile, parser.getHTMLText());
_sanitizer = new SafeHtmlConverter(outFile)
{
Logger = NullLogger.Instance
};
var result = _sanitizer.Run("jobtest");
Assert.That(File.Exists(result), "Output pdf file not created");
File.Delete(result);
}
protected async override Task <ProcessResult> OnPolling(PollerJobParameters parameters, string workingFolder)
{
string pathToFile = await DownloadBlob(parameters.TenantId, parameters.JobId, parameters.FileName, workingFolder).ConfigureAwait(false);
//String fileName = Path.Combine(Path.GetDirectoryName(pathToFile), parameters.All[JobKeys.FileName]);
//Logger.DebugFormat("Move blob id {0} to real filename {1}", pathToFile, fileName);
//if (File.Exists(fileName)) File.Delete(fileName);
//File.Copy(pathToFile, fileName);
if (Logger.IsDebugEnabled)
{
Logger.DebugFormat("Conversion of HtmlZip to PDF: file {0}", pathToFile);
}
var file = pathToFile;
if (pathToFile.EndsWith(".mht", StringComparison.OrdinalIgnoreCase) || pathToFile.EndsWith(".mhtml", StringComparison.OrdinalIgnoreCase))
{
string mhtml = File.ReadAllText(pathToFile);
MHTMLParser parser = new MHTMLParser(mhtml)
{
OutputDirectory = workingFolder,
DecodeImageData = true
};
var outFile = Path.ChangeExtension(pathToFile, ".html");
File.WriteAllText(outFile, parser.getHTMLText());
file = outFile;
}
var sanitizer = new SafeHtmlConverter(file)
{
Logger = Logger
};
file = sanitizer.Run(parameters.JobId);
var converter = new HtmlToPdfConverterFromDiskFile(file, base.JobsHostConfiguration)
{
Logger = Logger
};
var pdfConvertedFileName = converter.Run(parameters.TenantId, parameters.JobId);
await AddFormatToDocumentFromFile(
parameters.TenantId,
parameters.JobId,
new DocumentFormat(DocumentFormats.Pdf),
pdfConvertedFileName,
new Dictionary <string, object>()).ConfigureAwait(false);
return(ProcessResult.Ok);
}
static void Main(string[] args)
{
Console.Title = "QQMht To Html";
string outdir = ".";
string hFile = Path.GetFileNameWithoutExtension(args[0]);
string d = $@"{outdir}\{hFile}_images";
string mht, html = string.Empty;
try
{
mht = File.ReadAllText(args[0]);
}
catch
{
return;
}
MHTMLParser parser = new MHTMLParser(mht);
List <string[]> nodes;
Console.WriteLine("Processing data...");
nodes = parser.DecompressString();
if (nodes.Count > 0)
{
int c = nodes.Count - 1;
if (nodes.Count > 1)
{
Console.WriteLine($"{c} image(s) found.");
Directory.CreateDirectory(d);
Console.WriteLine($"create dir {d}");
}
html = nodes[0][2];
for (int i = 1; i < nodes.Count; i++)
{
string ext = nodes[i][0].Split("/".ToArray())[1],
name = nodes[i][1].Split(".".ToArray())[0];
if (ext == "jpeg")
{
ext = "jpg";
}
string iFile = $@"{d}\{name}.{ext}";
byte[] bytes = Convert.FromBase64String(nodes[i][2]);
File.WriteAllBytes(iFile, bytes);
html = html.Replace($"{name}.dat", $@"{iFile}");
Console.WriteLine($"Processing image...({i}/{c}): {iFile}");
}
hFile = $@"{outdir}\{hFile}.html";
File.WriteAllText(hFile, html);
Console.Write("All done.");
}
}
private string ProcessFile(string pathToFile, string workingFolder)
{
var extension = Path.GetExtension(pathToFile).ToLower();
if (extension == ".htmlzip" || extension == ".htmzip")
{
ZipFile.ExtractToDirectory(pathToFile, workingFolder);
Logger.DebugFormat("Extracted zip to {0}", workingFolder);
var htmlFile = Path.ChangeExtension(pathToFile, "html");
if (File.Exists(htmlFile))
{
Logger.DebugFormat("Html file is {0}", htmlFile);
return(htmlFile);
}
htmlFile = Path.ChangeExtension(pathToFile, "htm");
if (File.Exists(htmlFile))
{
Logger.DebugFormat("Html file is {0}", htmlFile);
return(htmlFile);
}
Logger.ErrorFormat("Invalid HTMLZIP file, name is {0} but corresponding html file not found after decompression", Path.GetFileName(pathToFile));
}
else if (extension == ".mht" || extension == ".mhtml")
{
MHTMLParser parser = new MHTMLParser(File.ReadAllText(pathToFile));
parser.OutputDirectory = workingFolder;
parser.DecodeImageData = false;
var html = parser.getHTMLText();
pathToFile = pathToFile + ".html";
File.WriteAllText(pathToFile, html);
}
return(pathToFile);
}
