public DacReport isPdfAccessible(String sourceFile)
{
DacReport dr = new DacReport();
PdfReader reader = new PdfReader(sourceFile);
if (reader.IsTagged())
{
dr.IsTagged = true;
var trailerKeys = reader.Trailer.Keys;
var catalogKeys = reader.Catalog.Keys;
//continue checking for accessibility, possibly follow the Matterhorn Protocol
/*
* 01-003 Content marked as Artifact is present inside tagged content.
* 01-004 Tagged content is present inside content marked as Artifact.
* 01-005 Content is neither marked as Artifact nor tagged as real content.
* 01-007 Suspect entry has a value of true.
* 02-001 One or more non-standard tag’s mapping does not terminate with a standard type.
* 02-003 A circular mapping exists.
* 02-004 One or more standard types are remapped.
* 06-001 Document does not contain XMP metadata stream
* 06-002 The metadata stream in the Catalog dictionary does not include the PDF/UA identifier.
* 06-003 Metadata stream does not contain dc:title
* 07-001 ViewerPreferences dictionary of the Catalog dictionary does not contain DisplayDocTitle key.
* 07-002 ViewerPreferences dictionary of the Catalog dictionary contains DisplayDocTitle key with a value of false.
* 09-004 A table-related structure element is used in a way that does not conform to the syntax defined in ISO 32000-1, Table 337.
* 09-005 A list-related structure element is used in a way that does not conform to Table 336 in ISO 32000-1.
* 09-006 A TOC-related structure element is used in a way that does not conform to Table 333 in ISO 32000-1.
* 09-007 A Ruby-related structure element is used in a way that does not conform to Table 338 in ISO 32000-1.
* 09-008 A Warichu-related structure element is used in a way that does not conform to Table 338 in ISO 32000-1.
* 10-001 Character code cannot be mapped to Unicode.
* 11-001 Natural language for text in page content cannot be determined.
* 11-002 Natural language for text in “Alt”, “ActualText” and “E” attributes cannot be determined.
* 11-003 Natural language in the Outline entries cannot be determined.
* 11-004 Natural language in the “Contents” entry for annotations cannot be determined.
* 11-005 Natural language in the TU key for form fields cannot be determined.
* 11-006 Natural language for document metadata cannot be determined.
* 13-004 Figure tag alternative or replacement text missing.
* 14-002 Does use numbered headings, but the first heading tag is not H1.
* 14-003 Numbered heading levels in descending sequence are skipped (Example: H3 follows directly after H1).
*/
}
else
{
dr.IsTagged = false;
}
return(dr);
}
public DacReport isPdfAccessible(String sourceFile)
{
DacReport dr = new DacReport();
PdfReader reader = new PdfReader(sourceFile);
if (reader.IsTagged())
{
dr.IsTagged = true;
var trailerKeys = reader.Trailer.Keys;
var catalogKeys = reader.Catalog.Keys;
//continue checking for accessibility, possibly follow the Matterhorn Protocol
/*
* 01-003 Content marked as Artifact is present inside tagged content.
* 01-004 Tagged content is present inside content marked as Artifact.
* 01-005 Content is neither marked as Artifact nor tagged as real content.
* 01-007 Suspect entry has a value of true.
* 02-001 One or more non-standard tag’s mapping does not terminate with a standard type.
* 02-003 A circular mapping exists.
* 02-004 One or more standard types are remapped.
* 06-001 Document does not contain XMP metadata stream
* 06-002 The metadata stream in the Catalog dictionary does not include the PDF/UA identifier.
* 06-003 Metadata stream does not contain dc:title
* 07-001 ViewerPreferences dictionary of the Catalog dictionary does not contain DisplayDocTitle key.
* 07-002 ViewerPreferences dictionary of the Catalog dictionary contains DisplayDocTitle key with a value of false.
* 09-004 A table-related structure element is used in a way that does not conform to the syntax defined in ISO 32000-1, Table 337.
* 09-005 A list-related structure element is used in a way that does not conform to Table 336 in ISO 32000-1.
* 09-006 A TOC-related structure element is used in a way that does not conform to Table 333 in ISO 32000-1.
* 09-007 A Ruby-related structure element is used in a way that does not conform to Table 338 in ISO 32000-1.
* 09-008 A Warichu-related structure element is used in a way that does not conform to Table 338 in ISO 32000-1.
* 10-001 Character code cannot be mapped to Unicode.
* 11-001 Natural language for text in page content cannot be determined.
* 11-002 Natural language for text in “Alt”, “ActualText” and “E” attributes cannot be determined.
* 11-003 Natural language in the Outline entries cannot be determined.
* 11-004 Natural language in the “Contents” entry for annotations cannot be determined.
* 11-005 Natural language in the TU key for form fields cannot be determined.
* 11-006 Natural language for document metadata cannot be determined.
* 13-004 Figure tag alternative or replacement text missing.
* 14-002 Does use numbered headings, but the first heading tag is not H1.
* 14-003 Numbered heading levels in descending sequence are skipped (Example: H3 follows directly after H1).
*/
}
else
{
dr.IsTagged = false;
}
return dr;
}