public Boolean Convert(String inputFileName, String outputFileName)
{
try
{
var text = File.ReadAllText(inputFileName);
// Create a MigraDoc document
Document document = new Document();
var section = document.AddSection();
var paragraph = section.AddParagraph();
paragraph.Format.Font.Size = 12;
paragraph.AddFormattedText(text);
PdfDocumentRenderer pdfRenderer = new PdfDocumentRenderer(unicode, embedding);
pdfRenderer.Document = document;
pdfRenderer.RenderDocument();
pdfRenderer.PdfDocument.Save(outputFileName);
return(true);
}
catch (Exception ex)
{
Logger.WarnFormat(ex, "Error converting file {0} to Pdf.", inputFileName);
return(false);
}
}
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);
}
public void Upload_list_files_in_temp()
{
var fileList = File.ReadAllText(@"c:\temp\filelist.txt");
foreach (var line in fileList.Split('\n'))
{
FileInfo finfo = new FileInfo(line);
_docs.UploadAsync(finfo.FullName, DocumentHandle.FromString(finfo.Name)).Wait();
}
}
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);
}
protected async override Task <ProcessResult> OnPolling(PollerJobParameters parameters, string workingFolder)
{
string pathToFile = await DownloadBlob(parameters.TenantId, parameters.JobId, parameters.FileName, workingFolder);
if (Logger.IsDebugEnabled)
{
Logger.DebugFormat("Conversion of HtmlZip to PDF: file {0}", pathToFile);
}
var file = pathToFile;
if (pathToFile.ToLower().EndsWith(".mht") || pathToFile.ToLower().EndsWith(".mhtml"))
{
string mhtml = File.ReadAllText(pathToFile);
MHTMLParser parser = new MHTMLParser(mhtml);
parser.OutputDirectory = workingFolder;
parser.DecodeImageData = true;
var outFile = Path.ChangeExtension(pathToFile, ".html");
File.WriteAllText(outFile, parser.getHTMLText());
file = outFile;
}
var converter = new HtmlToPdfConverterFromDiskFileOld(file, base.JobsHostConfiguration)
{
Logger = Logger
};
var pdfConvertedFileName = converter.Run(parameters.JobId);
await AddFormatToDocumentFromFile(
parameters.TenantId,
parameters.JobId,
new DocumentFormat(DocumentFormats.Pdf),
pdfConvertedFileName,
new Dictionary <string, object>());
return(ProcessResult.Ok);
}
public void should_serialize_document_import_data()
{
var fname = Path.Combine(TestConfig.TempFolder, "a_file_to_import");
var client = new DocumentStoreServiceClient(new Uri("http://ds"), "test");
var did = client.CreateDocumentImportData(TaskId, "c:\\temp\\a file.docx", "a file.docx", Doc);
client.QueueDocumentImport(did, fname);
Assert.IsTrue(File.Exists(fname + ".dsimport"));
const string expected =
@"{
""TaskId"": ""9a29d730-f57a-41e4-92ba-55b7d99712a2"",
""Uri"": ""c:\\temp\\a file.docx"",
""FileName"": ""a file.docx"",
""Handle"": ""doc"",
""Format"": ""original"",
""Tenant"": ""test"",
""CustomData"": null,
""DeleteAfterImport"": false
}";
Assert.AreEqual(expected, File.ReadAllText(fname + ".dsimport"));
}
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);
}
public static string ReadLangFile(string lang)
{
return(File.ReadAllText(PathToLangFile(lang)));
}
public string Convert(String jobId, string pathToEml, string workingFolder)
{
Logger.DebugFormat("Coverting {0} in working folder {1}", pathToEml, workingFolder);
var reader = new Reader();
var outFolder = Path.Combine(workingFolder, jobId);
Logger.DebugFormat("Creating message working folder is {0}", outFolder);
Directory.CreateDirectory(outFolder);
Logger.Debug("Extracting files");
var files = reader.ExtractToFolder(pathToEml, outFolder);
if (Logger.IsDebugEnabled)
{
foreach (var file in files)
{
Logger.DebugFormat("\t{0}", Path.GetFileName(file));
}
Logger.DebugFormat("Total files {0}", files.Length);
}
var htmlFileName = files.FirstOrDefault(x => x.EndsWith(".htm", StringComparison.OrdinalIgnoreCase)) ??
files.FirstOrDefault(x => x.EndsWith(".html", StringComparison.OrdinalIgnoreCase));
if (htmlFileName == null)
{
var textFile = files.FirstOrDefault(x => x.EndsWith(".txt", StringComparison.OrdinalIgnoreCase));
if (textFile != null)
{
htmlFileName = textFile + ".html";
var textcontent = File.ReadAllText(textFile);
File.WriteAllText(htmlFileName, String.Format("<html><body><pre>{0}</pre></body></html>", textcontent));
}
else
{
htmlFileName = "contentmissing.html";
File.WriteAllText(htmlFileName, "<html>No content found in mail.</html>");
}
}
var htmlNameWithoutExtension = Path.GetFileNameWithoutExtension(htmlFileName);
var htmlContent = File.ReadAllText(htmlFileName);
var dirInfoFullName = new DirectoryInfo(outFolder).FullName;
htmlContent = Regex.Replace(
htmlContent,
@"src=""(?<src>.+?)""",
new MatchEvaluator((m) => NormalizeImgEvaluator(m, dirInfoFullName)),
RegexOptions.IgnoreCase);
File.WriteAllText(htmlFileName, htmlContent);
var pathToZip = Path.Combine(workingFolder, htmlNameWithoutExtension + ".ezip");
Logger.DebugFormat("New zip file is {0}", pathToZip);
if (File.Exists(pathToZip))
{
Logger.DebugFormat("Deleting previous file: {0}", pathToZip);
File.Delete(pathToZip);
}
Logger.DebugFormat("Creating new file: {0}", pathToZip);
ZipFile.CreateFromDirectory(outFolder, pathToZip);
Logger.DebugFormat("Deleting message working folder", outFolder);
Directory.Delete(outFolder, true);
Logger.DebugFormat(
"Convesion done {0} => {1}",
pathToEml,
pathToZip
);
return(pathToZip);
}
public FileSystemBlobDescriptor FindOneById(BlobId blobId)
{
if (blobId == null)
{
throw new ArgumentNullException(nameof(blobId));
}
var descriptorLocalFileName = _directoryManager.GetDescriptorFileNameFromBlobId(blobId);
if (!File.Exists(descriptorLocalFileName))
{
return(null);
}
var descriptor = JsonConvert.DeserializeObject <FileSystemBlobDescriptor>(File.ReadAllText(descriptorLocalFileName));
descriptor.SetLocalFileName(_directoryManager.GetFileNameFromBlobId(blobId, descriptor.FileNameWithExtension));
return(descriptor);
}
