private XElement GenerateToc(TableOfContentResult result)
{
XDocument doc = new XDocument(new XElement(nsItj + "tableOfContent"));
doc.Root.Add(GenerateList(result.Sections));
return(doc.Root);
}
private XElement GenerateHwTable(TableOfContentResult result)
{
XDocument doc = new XDocument(new XElement(nsItj + "headwordsTable"));
doc.Root.Add(GenerateTable(result.HeadwordsList));
return(doc.Root);
}
private static XElement GenerateHwList(TableOfContentResult result)
{
XDocument doc = new XDocument(new XElement(nsItj + "headwordsList"));
doc.Root.Add(GenerateList(result.HeadwordsList));
return(doc.Root);
}
private static void GenerateTocXml(TableOfContentResult result)
{
XElement toc = GenerateToc(result);
Console.WriteLine(toc);
Console.WriteLine();
}
private static void GenerateTocText(TableOfContentResult result)
{
Console.WriteLine("<tableOfContent>");
Console.WriteLine("<list>");
foreach (TableOfContentItem item in result.Sections)
{
//WriteTocInfo(item);
WriteTocInfoXml(item, 1);
}
Console.WriteLine("</list>");
Console.WriteLine("</tableOfContent>");
}
private static void TestDocument(string file)
{
ContentInfoBuilder builder = new ContentInfoBuilder();
builder.XmlFile = file;
builder.StartingElement = "body";
TableOfContentResult result = builder.MakeTableOfContent();
//GenerateTocXml(result);
SaveToc(result, Path.Combine(@"V:\Projekty\BitBucket\itjakub\UJCSystem\ITJakub.Xml.Conversion\Ujc.Ovj.Ooxml.Conversion.Test\Data\Metadata",
file.Substring(file.LastIndexOf('\\') + 1).Replace(".xml", ".cnt")));
//GenerateTocText(result);
}
//private void GenerateConversionMetadataFile(SplittingResult splittingResult,
// string documentType,
// string finalOutputFileFullPath)
//{
// GenerateConversionMetadataFile(splittingResult, new TableOfContentResult(), documentType, finalOutputFileFullPath);
//}
private void GenerateConversionMetadataFile(SplittingResult splittingResult, TableOfContentResult tableOfContentResult,
string documentType, string finalOutputFileFullPath, string finalOutputFileName, string finalOutputMetadataFileName)
{
XDocument metada = new XDocument();
XDocument teiDocument = XDocument.Load(finalOutputFileFullPath);
metada.Add(new XElement(nsItj + "document",
new XAttribute("doctype", documentType),
new XAttribute("versionId", _currentVersionInfoSkeleton.Id),
new XAttribute(nsXml + "lang", "cs"),
new XAttribute("n", _documentId),
new XAttribute("xmlns", nsTei),
new XAttribute(XNamespace.Xmlns + "itj", nsItj),
new XAttribute(XNamespace.Xmlns + "nlp", nsNlp),
new XAttribute(XNamespace.Xmlns + "xml", XNamespace.Xml)
)
);
XElement header = teiDocument.Descendants(nsTei + "teiHeader").FirstOrDefault();
metada.Root.Add(header);
XElement toc = GenerateToc(tableOfContentResult);
XElement hws = GenerateHwList(tableOfContentResult);
XElement hwt = GenerateHwTable(hws);
XElement accessories = new XElement(nsItj + "accessories",
new XElement(nsItj + "file", new XAttribute("type", "content"), new XAttribute("name", finalOutputFileName)));
if (splittingResult != null) //generovat pouze v případě, že k rozdělení na strany došlo
{
XElement pages = new XElement(nsItj + "pages",
from info in splittingResult.PageBreaksSplitInfo
select new XElement(nsItj + "page",
info.Number == null ? null : new XAttribute("n", info.Number),
info.Id == null ? null : new XAttribute(nsXml + "id", info.Id),
info.FileName == null ? null : new XAttribute("resource", info.FileName),
info.Facsimile == null ? null : new XAttribute("facs", info.Facsimile)
)
);
metada.Root.Add(pages);
}
metada.Root.Add(toc);
metada.Root.Add(hwt);
metada.Root.Add(hws);
metada.Root.Add(accessories);
metada.Save(finalOutputMetadataFileName);
}
private static void SaveToc(TableOfContentResult result, string filepath)
{
XDocument doc = new XDocument(new XElement(nsItj + "metadata"));
XElement toc = new XElement(nsItj + "tableOfContent");
toc.Add(GenerateList(result.Sections));
XElement hw = new XElement(nsItj + "headwordsList");
hw.Add(GenerateList(result.HeadwordsList));
doc.Root.Add(toc);
doc.Root.Add(hw);
doc.Save(filepath);
}
public ConversionResult Convert(DocxToTeiConverterSettings settings)
{
ConverterSettings = settings;
CheckIfDirectoryPathsExists(ConverterSettings);
_result = new ConversionResult();
string documentType = null;
//get metadata only for first (by alphabet) uploaded file
var inputFileName = ConverterSettings.InputFilesPath.Select(filePath => new FileInfo(filePath)).Select(fileInfo => fileInfo.Name).First();
ResolveDefaultSettingsValues(ConverterSettings);
var prepis = GetPrepisy(ConverterSettings, inputFileName);
if (prepis == null)
{
//dokument v evidenci neexistuje, nabídnout zanesení dokumentu do evidence
// mělo by stačit přiřazení typu dokumentu
_result.Errors.Add(new DocumentNotInEvidenceException(String.Format("Dokument s uvedeným jménem souboru '{0}' neexistuje v evidenci.", inputFileName)));
return(_result);
}
if (prepis.FazeZpracovani < FazeZpracovani.Exportovat)
{
_result.Errors.Add(new DocumentNotInRequredStateException("Dokument s uvedeným jménem souboru není připraven pro export."));
return(_result);
}
documentType = GetDocumentType(prepis.TypPrepisu);
_documentId = prepis.GUID;
if (documentType == null)
{
//dokument má v evidenci přiřazen typ dokumentu, který není podporován
_result.Errors.Add(new NotSupportedFileFormatException("Dokument má v evidenci přiřazen typ dokumentu, který není podporován."));
return(_result);
}
string tempDirectoryPath = ConverterSettings.TempDirectoryPath;
//vytvoří se adresářová struktura, pokud neexistuje, pro ukládání výsledných a dočasných souborů
AdresarovaStruktura ads = new AdresarovaStruktura(tempDirectoryPath, documentType);
ads.VytvorStrukturu();
string docxToXmlFilePath = Path.Combine(GetDataDirectoryPath(), "AllStylesConvert.2xml");
string xsltTemplatesPath = GetXsltTemplatesPath();
string xsltTransformationsPath = GetXsltTransformationsPath();
string fileNameWithoutExtension = prepis.Soubor.NazevBezPripony;
string xmlOutpuFileName = fileNameWithoutExtension + XmlExtension;
string finalOutputDirectory = ads.DejVystup; // Path.Combine(ads.DejVystup, fileNameWithoutExtension);
string finalOutputFileName = Path.Combine(finalOutputDirectory, xmlOutpuFileName);
//Zatím pouze konverze z DOCX do základního XML
IList <string> xmlOutputFiles = new List <string>();
try
{
var filePart = 0;
foreach (var inputFilePath in ConverterSettings.InputFilesPath)
{
xmlOutputFiles.Add(GetDocxToXmlOutput(ads, prepis.Soubor.NazevBezPripony, filePart, ConverterSettings.InputFilesPath.Length > 1));
ConvertDocxToXml(inputFilePath, docxToXmlFilePath, xmlOutputFiles.Last());
filePart++;
}
}
catch (Exception exception)
{
_result.Errors.Add(exception);
return(_result);
}
if (!Directory.Exists(finalOutputDirectory))
{
Directory.CreateDirectory(finalOutputDirectory);
}
IExportNastaveni exportSettings = GetExportSettings(documentType, ConverterSettings, xsltTransformationsPath, xsltTemplatesPath, ads, prepis);
ExportBase export = GetExportModule(documentType, exportSettings);
if (export == null || exportSettings == null)
{
//Objekt pro export se nepodažřilo vytvořit, není podporován.
return(_result);
}
try
{
export.Exportuj(exportSettings.Prepis, xmlOutputFiles, ConverterSettings.UploadedFilesPath);
_result.IsConverted = true;
}
catch (Exception exception)
{
_result.Errors.Add(exception);
return(_result);
}
if (!settings.Debug)
{
foreach (var xmlOutputFile in xmlOutputFiles.Where(File.Exists))
{
File.Delete(xmlOutputFile);
}
}
var versions = settings.GetVersionList(_documentId);
_currentVersionInfoSkeleton = versions.Last();
WriteListChange(finalOutputFileName, versions, _currentVersionInfoSkeleton);
var xmlFinalOutputPath = Path.Combine(settings.OutputDirectoryPath, xmlOutpuFileName);
File.Copy(finalOutputFileName, xmlFinalOutputPath, true);
_result.MetadataFilePath = settings.OutputMetadataFilePath;
//GetConversionMetadataFileFullPath(settings.OutputFilePath);
if (export.UsePersonalizedXmdGenerator)
{
export.GenerateConversionMetadataFile(documentType, xmlFinalOutputPath, xmlOutpuFileName, settings.OutputMetadataFilePath);
}
else
{
SplittingResult splittingResult = null;
if (settings.SplitDocumentByPageBreaks)
{
splittingResult = SplitDocumentByPageBreaks(xmlFinalOutputPath, fileNameWithoutExtension);
if (!splittingResult.IsSplitted)
{
_result.IsConverted = false;
_result.Errors.Add(new DocumentSplittingException("Vyskytla se chyba při rozdělení souboru podle hranice stran."));
}
}
TableOfContentResult tocResult = null;
ContentInfoBuilder tocBuilder = new ContentInfoBuilder();
tocResult = tocBuilder.MakeTableOfContent(xmlFinalOutputPath, "body");
GenerateConversionMetadataFile(splittingResult, tocResult, documentType, xmlFinalOutputPath, xmlOutpuFileName, settings.OutputMetadataFilePath);
}
if (!settings.Debug)
{
try
{
Directory.Delete(settings.TempDirectoryPath, true);
}
catch (IOException exception)
{
Directory.Delete(settings.TempDirectoryPath, true);
}
}
return(_result);
}
/// <summary>
/// The extract table of content.
/// </summary>
/// <returns>
/// The <see cref="TableOfContentResult"/>.
/// </returns>
public TableOfContentResult ExtractTableOfContent(string fileName)
{
var tableOfContentResult = new TableOfContentResult();
if (!File.Exists(fileName))
{
tableOfContentResult.Result = false;
tableOfContentResult.LastError = "File not found!";
return(tableOfContentResult);
}
Microsoft.Office.Interop.Word.Application wordApplication = null;
Microsoft.Office.Interop.Word.Document document = null;
bool breakPoint = false;
try
{
object templatePath = fileName;
object missingObj = Missing.Value;
wordApplication = new Microsoft.Office.Interop.Word.Application();
document = wordApplication.Documents.Open(ref templatePath, ref missingObj, ref missingObj, ref missingObj);
var content = string.Empty;
var hyperlinksCount = document.TablesOfContents[1].Range.Hyperlinks.Count;
int NextStart = 0;
for (var i = hyperlinksCount; i > 0; i--)
{
var tableOfContentData = new TableOfContentData();
var myRange = document.TablesOfContents[1].Range.Hyperlinks[i].Range;
if (myRange.Text.Contains("Защита оборудования ТСО от воздействия молниевых разрядов"))
{
var xxx = myRange.CharacterStyle;
var yyy = myRange.FormattedText;
breakPoint = true;
}
var splites = myRange.Text.Split('\t');
if (splites.Length > 1)
{
int page;
var result = int.TryParse(splites[splites.Length - 1], out page);
if (result)
{
for (var j = 0; j < splites.Length - 1; j++)
{
content += splites[j] + " ";
}
tableOfContentData.Page = page;
tableOfContentData.Content = content.Trim().Replace(" ", " ");
content = string.Empty;
}
else
{
content += myRange.Text;
}
}
else
{
content += myRange.Text;
}
var rd = new RangeDetails();
rd.HyperLinkStart = myRange.Start;
rd.HyperLinkEnd = myRange.End;
rd.LinkText = myRange.Text;
try
{
var sadd = document.TablesOfContents[1].Range.Hyperlinks[i].SubAddress;
var wb = document.Bookmarks[sadd];
if (wb != null)
{
Microsoft.Office.Interop.Word.Style style = wb.Range.get_Style();
tableOfContentData.StyleInfo = style.NameLocal;
if (breakPoint)
{
var ss = wb.Range.Text;
breakPoint = false;
}
rd.ContentRangeStart = wb.Range.End + 1; // content starts after the Heading so we take the end of heading
if (i == document.TablesOfContents[1].Range.Hyperlinks.Count)
{
// then it is the last Range and the "End" will be the endofDoc.
object oEndOfDoc = @"\endofdoc";
rd.ContentRangeEnd = document.Bookmarks.get_Item(ref oEndOfDoc).Range.End;
}
else
{
rd.ContentRangeEnd = NextStart - 1;
}
NextStart = rd.ContentRangeStart;
string text = document.Range(rd.ContentRangeStart, rd.ContentRangeEnd).Text;
var xxx = document.Range(rd.ContentRangeStart, rd.ContentRangeEnd).Fields;
tableOfContentResult.Items.Add(tableOfContentData);
}
}
catch (Exception ex)
{
return(null);
}
//contRange.Ranges.Add(rd);
}
document.Close();
document = null;
wordApplication.Quit();
wordApplication = null;
}
catch (Exception ex)
{
tableOfContentResult.Result = false;
tableOfContentResult.LastError = ex.Message;
}
finally
{
document?.Close();
wordApplication?.Quit();
}
tableOfContentResult.Items.Reverse();
return(tableOfContentResult);
}
