public static Info ReadDocInfo(string fileName)
{
Info result = new Info();
try
{
PDDocument pDoc = PDDocument.load(fileName);
PDDocumentInformation docInfo = pDoc.getDocumentInformation();
if (docInfo != null)
{
var author = docInfo.getAuthor();
var title = docInfo.getTitle();
var summary = docInfo.getSubject();
var keywords = docInfo.getKeywords();
result.Author = author;
result.Title = title;
result.Summary = summary;
result.Keywords = keywords;
}
}
catch (Exception ex)
{
}
return(result);
}
internal PDFDocumentInformation GetDocumentInformation(PDDocument pdfDocument)
{
PDDocumentInformation documentInformation = pdfDocument.getDocumentInformation();
PDFDocumentInformation pDFDocumentInformation = new PDFDocumentInformation()
{
Author = documentInformation.getAuthor()
};
documentInformation.getCreationDate();
pDFDocumentInformation.CreationDate = this.ConvertJavaDateToCSharp(documentInformation.getCreationDate());
pDFDocumentInformation.Creator = documentInformation.getCreator();
pDFDocumentInformation.Keywords = documentInformation.getKeywords();
pDFDocumentInformation.ModifiedDate = this.ConvertJavaDateToCSharp(documentInformation.getModificationDate());
pDFDocumentInformation.Producer = documentInformation.getProducer();
pDFDocumentInformation.Subject = documentInformation.getSubject();
pDFDocumentInformation.Title = documentInformation.getTitle();
pDFDocumentInformation.Trapped = documentInformation.getTrapped();
return(pDFDocumentInformation);
}
private void DoMetadata()
{
java.util.TimeZone timeZone = java.util.TimeZone.getTimeZone("GMT");
Calendar instance = Calendar.getInstance();
instance.setTimeZone(timeZone);
PDDocumentInformation documentInformation = this.doc.getDocumentInformation();
documentInformation.setModificationDate(instance);
if (documentInformation.getAuthor() == null)
{
documentInformation.setAuthor("Aquaforest");
}
if ((string.IsNullOrEmpty(documentInformation.getProducer()) ? true : documentInformation.getProducer() == " "))
{
documentInformation.setProducer("Aquaforest PDFA - http://www.aquaforest.com");
}
if (documentInformation.getKeywords() == null)
{
documentInformation.setKeywords("");
}
documentInformation.getCreationDate();
instance.setTime(this.GetDate(documentInformation.getCreationDate()));
documentInformation.setCreationDate(instance);
this.doc.setDocumentInformation(documentInformation);
this.doc.save(this.tempFileName);
documentInformation = this.doc.getDocumentInformation();
PDDocumentCatalog documentCatalog = this.doc.getDocumentCatalog();
XMPMetadata xMPMetadatum = XMPMetadata.createXMPMetadata();
if (this.ConformanceLevel.Trim().ToLower() == "a")
{
PDMarkInfo pDMarkInfo = new PDMarkInfo();
pDMarkInfo.setMarked(true);
documentCatalog.setMarkInfo(pDMarkInfo);
}
PDFAIdentificationSchema pDFAIdentificationSchema = xMPMetadatum.createAndAddPFAIdentificationSchema();
pDFAIdentificationSchema.setConformance(this.ConformanceLevel);
pDFAIdentificationSchema.setPart(new Integer(this.pdfaversion));
DublinCoreSchema dublinCoreSchema = xMPMetadatum.createAndAddDublinCoreSchema();
string title = documentInformation.getTitle();
if (title != null)
{
dublinCoreSchema.setTitle(title);
}
title = documentInformation.getSubject();
if (title != null)
{
dublinCoreSchema.setDescription(title);
}
title = documentInformation.getAuthor();
if (title != null)
{
dublinCoreSchema.addCreator(title);
}
AdobePDFSchema adobePDFSchema = xMPMetadatum.createAndAddAdobePDFSchema();
title = documentInformation.getProducer();
if (title != null)
{
adobePDFSchema.setProducer(title);
}
title = documentInformation.getKeywords();
if (title != null)
{
adobePDFSchema.setKeywords(title);
}
XMPBasicSchema xMPBasicSchema = xMPMetadatum.createAndAddXMPBasicSchema();
title = documentInformation.getCreator();
if (title != null)
{
xMPBasicSchema.setCreatorTool(title);
}
if (documentInformation.getCreationDate() != null)
{
xMPBasicSchema.setCreateDate(documentInformation.getCreationDate());
}
if (documentInformation.getModificationDate() != null)
{
xMPBasicSchema.setModifyDate(documentInformation.getModificationDate());
}
xMPBasicSchema.setMetadataDate(new GregorianCalendar());
XmpSerializer xmpSerializer = new XmpSerializer();
ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
SAXParserFactoryImpl sAXParserFactoryImpl = new SAXParserFactoryImpl();
TransformerFactoryImpl transformerFactoryImpl = new TransformerFactoryImpl();
xmpSerializer.serialize(xMPMetadatum, byteArrayOutputStream, false);
PDMetadata pDMetadatum = new PDMetadata(this.doc);
pDMetadatum.importXMPMetadata(byteArrayOutputStream.toByteArray());
documentCatalog.setMetadata(pDMetadatum);
this.doc.save(this.tempFileName);
documentInformation = this.doc.getDocumentInformation();
}
public PDFDocumentInformation()
{
this.documentInformation = new PDDocumentInformation();
}
public static Document ParseDocument(string filePath, GEN_FILE doc)
{
string author = null;
string keywords = null;
string summary = null;
string text = null;
try
{
PDFTextStripper stripper = new PDFTextStripper();
PDDocument document = PDDocument.load(filePath);
text = stripper.getText(document);
PDDocumentInformation info = document.getDocumentInformation();
author = info.getAuthor();
keywords = info.getKeywords();
summary = info.getSubject();
document.close();
}
catch (Exception ex)
{
Debug.WriteLine("Exception in reading file: " + filePath + " ex: " + ex.Message);
}
Document lucDoc = new Document();
string filename = Path.GetFileNameWithoutExtension(doc.File_Name);
string short_name = doc.Short_Name;
string title = doc.Title;
string header = doc.Summary;
string doc_id = doc.Gen_File_Id.ToString();
Debug.WriteLine("DocID: " + doc_id);
StringBuilder keyTextBuilder = new StringBuilder();
foreach (FILE_KEYWORDS keywordobj in doc.FILE_KEYWORDS.ToList())
{
keyTextBuilder.Append(keywordobj.Keyword + " ");
}
string keyword = keyTextBuilder.ToString();
lucDoc.Add(new Field(FieldNames.FILE_NAME, filename, Field.Store.YES, Field.Index.ANALYZED));
if (author != null && author.Trim() != "")
{
lucDoc.Add(new Field(FieldNames.AUTHOR, author, Field.Store.YES, Field.Index.ANALYZED));
}
if (keywords != null && keywords.Trim() != "")
{
lucDoc.Add(new Field(FieldNames.KEYWORDS, keywords, Field.Store.YES, Field.Index.ANALYZED));
}
if (summary != null && summary.Trim() != "")
{
lucDoc.Add(new Field(FieldNames.SUMMARY, summary, Field.Store.YES, Field.Index.ANALYZED));
}
lucDoc.Add(new Field(FieldNames.SHORT_NAME, short_name, Field.Store.YES, Field.Index.ANALYZED));
lucDoc.Add(new Field(FieldNames.TITLE, title, Field.Store.YES, Field.Index.ANALYZED));
if (!String.IsNullOrWhiteSpace(header))
{
lucDoc.Add(new Field(FieldNames.HEADER, header, Field.Store.YES, Field.Index.ANALYZED));
}
if (text != null && text.Trim() != "")
{
lucDoc.Add(new Field(FieldNames.TEXT, text, Field.Store.YES, Field.Index.ANALYZED));
}
lucDoc.Add(new Field(FieldNames.DOC_ID, doc_id, Field.Store.YES, Field.Index.NO));
lucDoc.Add(new Field(FieldNames.RESOURCE_TYPE, ResourceTypeEnum.Resource_Doc.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
return(lucDoc);
}
private PDDocumentCatalog makeDocPDFA3compliant(String producer,
String creator, bool attachZugferdHeaders)
{
String fullProducer = producer + " (via mustangproject.org "
+ versionStr + ")";
PDDocumentCatalog cat = doc.getDocumentCatalog();
PDMetadata metadata = new PDMetadata(doc);
cat.setMetadata(metadata);
// we're using the jempbox org.apache.jempbox.xmp.XMPMetadata version,
// not the xmpbox one
XMPMetadata xmp = new XMPMetadata();
XMPSchemaPDFAId pdfaid = new XMPSchemaPDFAId(xmp);
pdfaid.setAbout(""); //$NON-NLS-1$
xmp.addSchema(pdfaid);
XMPSchemaDublinCore dc = xmp.addDublinCoreSchema();
dc.addCreator(creator);
dc.setAbout(""); //$NON-NLS-1$
XMPSchemaBasic xsb = xmp.addBasicSchema();
xsb.setAbout(""); //$NON-NLS-1$
xsb.setCreatorTool(creator);
xsb.setCreateDate(GregorianCalendar.getInstance());
// PDDocumentInformation pdi=doc.getDocumentInformation();
PDDocumentInformation pdi = new PDDocumentInformation();
pdi.setProducer(fullProducer);
pdi.setAuthor(creator);
doc.setDocumentInformation(pdi);
XMPSchemaPDF pdf = xmp.addPDFSchema();
pdf.setProducer(fullProducer);
pdf.setAbout(""); //$NON-NLS-1$
/*
* // Mandatory: PDF/A3-a is tagged PDF which has to be expressed using
* a // MarkInfo dictionary (PDF A/3 Standard sec. 6.7.2.2) PDMarkInfo
* markinfo = new PDMarkInfo(); markinfo.setMarked(true);
* doc.getDocumentCatalog().setMarkInfo(markinfo);
*/
/*
*
* To be on the safe side, we use level B without Markinfo because we
* can not guarantee that the user correctly tagged the templates for
* the PDF.
*/
pdfaid.setConformance(conformanceLevel);//$NON-NLS-1$ //$NON-NLS-1$
pdfaid.setPart(new java.lang.Integer(3));
if (attachZugferdHeaders)
{
addZugferdXMP(xmp); /*
* this is the only line where we do something
* Zugferd-specific, i.e. add PDF metadata
* specifically for Zugferd, not generically for
* a embedded file
*/
}
metadata.importXMPMetadata(xmp);
return(cat);
}
