public static PdfRectangle ToIntRectangle(this ArrayToken array, IPdfTokenScanner tokenScanner)
{
if (array == null)
{
throw new ArgumentNullException(nameof(array));
}
if (array.Data.Count != 4)
{
throw new PdfDocumentFormatException($"Cannot convert array to rectangle, expected 4 values instead got: {array}.");
}
return(new PdfRectangle(DirectObjectFinder.Get <NumericToken>(array[0], tokenScanner).Int,
DirectObjectFinder.Get <NumericToken>(array[1], tokenScanner).Int,
DirectObjectFinder.Get <NumericToken>(array[2], tokenScanner).Int,
DirectObjectFinder.Get <NumericToken>(array[3], tokenScanner).Int));
}
/// <summary>
/// The purpose of this method is to resolve indirect reference. That mean copy the reference's content to the new document's stream
/// and replace the indirect reference with the correct/new one
/// </summary>
/// <param name="tokenToCopy">Token to inspect for reference</param>
/// <param name="tokenScanner">scanner get the content from the original document</param>
/// <returns>A copy of the token with all his content copied to the new document's stream</returns>
private IToken CopyToken(IToken tokenToCopy, IPdfTokenScanner tokenScanner)
{
if (tokenToCopy is DictionaryToken dictionaryToken)
{
var newContent = new Dictionary <NameToken, IToken>();
foreach (var setPair in dictionaryToken.Data)
{
var name = setPair.Key;
var token = setPair.Value;
newContent.Add(NameToken.Create(name), CopyToken(token, tokenScanner));
}
return(new DictionaryToken(newContent));
}
else if (tokenToCopy is ArrayToken arrayToken)
{
var newArray = new List <IToken>(arrayToken.Length);
foreach (var token in arrayToken.Data)
{
newArray.Add(CopyToken(token, tokenScanner));
}
return(new ArrayToken(newArray));
}
else if (tokenToCopy is IndirectReferenceToken referenceToken)
{
var tokenObject = DirectObjectFinder.Get <IToken>(referenceToken.Data, tokenScanner);
Debug.Assert(!(tokenObject is IndirectReferenceToken));
var newToken = CopyToken(tokenObject, tokenScanner);
var objToken = context.WriteObject(memory, newToken);
return(new IndirectReferenceToken(objToken.Number));
}
else if (tokenToCopy is StreamToken streamToken)
{
var properties = CopyToken(streamToken.StreamDictionary, tokenScanner) as DictionaryToken;
Debug.Assert(properties != null);
return(new StreamToken(properties, new List <byte>(streamToken.Data)));
}
else // Non Complex Token - BooleanToken, NumericToken, NameToken, Etc...
{
return(tokenToCopy);
}
}
/// <summary>
/// Get any embedded files contained in this PDF document.
/// Since PDF 1.3 any external file referenced by the document may have its contents embedded within the referring PDF file,
/// allowing its contents to be stored or transmitted along with the PDF file.
/// </summary>
/// <param name="embeddedFiles">The set of embedded files in this document.</param>
/// <returns><see langword="true"/> if this document contains more than zero embedded files, otherwise <see langword="false"/>.</returns>
public bool TryGetEmbeddedFiles(out IReadOnlyList <EmbeddedFile> embeddedFiles)
{
GuardDisposed();
embeddedFiles = null;
if (!catalog.CatalogDictionary.TryGet(NameToken.Names, pdfScanner, out DictionaryToken namesDictionary) ||
!namesDictionary.TryGet(NameToken.EmbeddedFiles, pdfScanner, out DictionaryToken embeddedFileNamesDictionary))
{
return(false);
}
var embeddedFileNames = NameTreeParser.FlattenNameTreeToDictionary(embeddedFileNamesDictionary, pdfScanner, x => x);
if (embeddedFileNames.Count == 0)
{
return(false);
}
var result = new List <EmbeddedFile>();
foreach (var keyValuePair in embeddedFileNames)
{
if (!DirectObjectFinder.TryGet(keyValuePair.Value, pdfScanner, out DictionaryToken fileDescriptorDictionaryToken) ||
!fileDescriptorDictionaryToken.TryGet(NameToken.Ef, pdfScanner, out DictionaryToken efDictionary) ||
!efDictionary.TryGet(NameToken.F, pdfScanner, out StreamToken fileStreamToken))
{
continue;
}
var fileSpecification = string.Empty;
if (fileDescriptorDictionaryToken.TryGet(NameToken.F, pdfScanner, out IDataToken <string> fileSpecificationToken))
{
fileSpecification = fileSpecificationToken.Data;
}
var fileBytes = fileStreamToken.Decode(filterProvider);
result.Add(new EmbeddedFile(keyValuePair.Key, fileSpecification, fileBytes, fileStreamToken));
}
embeddedFiles = result;
return(embeddedFiles.Count > 0);
}
private CharacterIdentifierToGlyphIndexMap GetCharacterIdentifierToGlyphIndexMap(DictionaryToken dictionary)
{
if (!dictionary.TryGet(NameToken.CidToGidMap, out var entry))
{
return(new CharacterIdentifierToGlyphIndexMap());
}
if (entry is NameToken)
{
return(new CharacterIdentifierToGlyphIndexMap());
}
var stream = DirectObjectFinder.Get <StreamToken>(entry, pdfScanner);
var bytes = stream.Decode(filterProvider);
return(new CharacterIdentifierToGlyphIndexMap(bytes));
}
public void GetFollowsSingleIndirectReferenceFromArray()
{
var reference = new IndirectReference(10, 0);
var reference2 = new IndirectReference(69, 0);
const string expected = "Goopy";
scanner.Objects[reference] = new ObjectToken(10, reference, new ArrayToken(new[]
{
new IndirectReferenceToken(reference2)
}));
scanner.Objects[reference2] = new ObjectToken(69, reference2, new StringToken(expected));
var result = DirectObjectFinder.Get <StringToken>(reference, scanner);
Assert.Equal(expected, result.Data);
}
public Encoding Read(DictionaryToken fontDictionary, bool isLenientParsing, FontDescriptor descriptor = null)
{
if (!fontDictionary.TryGet(NameToken.Encoding, out var baseEncodingObject))
{
return(null);
}
if (baseEncodingObject is NameToken name)
{
return(GetNamedEncoding(descriptor, name));
}
DictionaryToken encodingDictionary = DirectObjectFinder.Get <DictionaryToken>(baseEncodingObject, pdfScanner);
var encoding = ReadEncodingDictionary(encodingDictionary);
return(encoding);
}
/// <summary>
/// Convert the file trailer dictionary into a <see cref="DocumentInformation"/> instance.
/// </summary>
public static DocumentInformation Create(IPdfTokenScanner pdfTokenScanner, TrailerDictionary trailer)
{
if (!trailer.Info.HasValue)
{
return(DocumentInformation.Default);
}
var token = DirectObjectFinder.Get <IToken>(trailer.Info.Value, pdfTokenScanner);
if (token is DictionaryToken infoParsed)
{
var title = GetEntryOrDefault(infoParsed, NameToken.Title);
var author = GetEntryOrDefault(infoParsed, NameToken.Author);
var subject = GetEntryOrDefault(infoParsed, NameToken.Subject);
var keywords = GetEntryOrDefault(infoParsed, NameToken.Keywords);
var creator = GetEntryOrDefault(infoParsed, NameToken.Creator);
var producer = GetEntryOrDefault(infoParsed, NameToken.Producer);
var creationDate = GetEntryOrDefault(infoParsed, NameToken.CreationDate);
var modifiedDate = GetEntryOrDefault(infoParsed, NameToken.ModDate);
return(new DocumentInformation(infoParsed, title, author, subject,
keywords, creator, producer, creationDate, modifiedDate));
}
else if (token is StreamToken streamToken)
{
var streamDictionary = streamToken.StreamDictionary;
if (!streamDictionary.TryGet(NameToken.Type, out NameToken typeNameToken) || typeNameToken != "Metadata")
{
throw new PdfDocumentFormatException($"Unknown document metadata type was found");
}
if (!streamDictionary.TryGet(NameToken.Subtype, out NameToken subtypeToken) || subtypeToken != "XML")
{
throw new PdfDocumentFormatException($"Unknown document metadata subtype was found");
}
// We are not fully supporting XMP Stream so we left the user fully deserialize the stream
return(DocumentInformation.Default);
}
else
{
throw new PdfDocumentFormatException($"Unknown document information token was found {token.GetType().Name}");
}
}
public static Catalog Create(IndirectReference rootReference, DictionaryToken dictionary,
IPdfTokenScanner scanner,
bool isLenientParsing)
{
if (dictionary == null)
{
throw new ArgumentNullException(nameof(dictionary));
}
if (dictionary.TryGet(NameToken.Type, out var type) && !ReferenceEquals(type, NameToken.Catalog))
{
throw new PdfDocumentFormatException($"The type of the catalog dictionary was not Catalog: {dictionary}.");
}
if (!dictionary.TryGet(NameToken.Pages, out var value))
{
throw new PdfDocumentFormatException($"No pages entry was found in the catalog dictionary: {dictionary}.");
}
DictionaryToken pages;
var pagesReference = rootReference;
if (value is IndirectReferenceToken pagesRef)
{
pagesReference = pagesRef.Data;
pages = DirectObjectFinder.Get <DictionaryToken>(pagesRef, scanner);
}
else if (value is DictionaryToken pagesDict)
{
pages = pagesDict;
}
else
{
pages = DirectObjectFinder.Get <DictionaryToken>(value, scanner);
}
var pageNumber = 0;
var pageTree = ProcessPagesNode(pagesReference, pages, new IndirectReference(1, 0), true,
scanner, isLenientParsing, ref pageNumber);
return(new Catalog(dictionary, pages, pageTree));
}
private IReadOnlyDictionary <int, decimal> ReadWidths(DictionaryToken dict)
{
var widths = new Dictionary <int, decimal>();
if (!dict.TryGet(NameToken.W, out var widthsItem) || !(widthsItem is ArrayToken widthArray))
{
return(widths);
}
int size = widthArray.Data.Count;
int counter = 0;
while (counter < size)
{
var firstCode = (NumericToken)widthArray.Data[counter++];
var next = widthArray.Data[counter++];
if (DirectObjectFinder.TryGet(next, pdfScanner, out ArrayToken array))
{
int startRange = firstCode.Int;
int arraySize = array.Data.Count;
for (int i = 0; i < arraySize; i++)
{
var width = (NumericToken)array.Data[i];
widths[startRange + i] = width.Data;
}
}
else
{
var secondCode = (NumericToken)next;
var rangeWidth = (NumericToken)widthArray.Data[counter++];
int startRange = firstCode.Int;
int endRange = secondCode.Int;
var width = rangeWidth.Data;
for (var i = startRange; i <= endRange; i++)
{
widths[i] = width;
}
}
}
return(widths);
}
private IReadOnlyDictionary <int, double> ReadWidths(DictionaryToken dict)
{
var widths = new Dictionary <int, double>();
if (!dict.TryGet(NameToken.W, pdfScanner, out ArrayToken widthArray))
{
return(widths);
}
var size = widthArray.Data.Count;
var counter = 0;
while (counter < size)
{
var firstCode = DirectObjectFinder.Get <NumericToken>(widthArray.Data[counter++], pdfScanner);
var next = widthArray.Data[counter++];
if (DirectObjectFinder.TryGet(next, pdfScanner, out ArrayToken array))
{
var startRange = firstCode.Int;
var arraySize = array.Data.Count;
for (var i = 0; i < arraySize; i++)
{
var width = DirectObjectFinder.Get <NumericToken>(array.Data[i], pdfScanner);
widths[startRange + i] = width.Double;
}
}
else
{
var secondCode = DirectObjectFinder.Get <NumericToken>(next, pdfScanner);
var rangeWidth = DirectObjectFinder.Get <NumericToken>(widthArray.Data[counter++], pdfScanner);
var startRange = firstCode.Int;
var endRange = secondCode.Int;
var width = rangeWidth.Double;
for (var i = startRange; i <= endRange; i++)
{
widths[i] = width;
}
}
}
return(widths);
}
public DocumentInformation Create(IPdfTokenScanner pdfTokenScanner, TrailerDictionary trailer)
{
if (!trailer.Info.HasValue)
{
return(DocumentInformation.Default);
}
var infoParsed = DirectObjectFinder.Get <DictionaryToken>(trailer.Info.Value, pdfTokenScanner);
var title = GetEntryOrDefault(infoParsed, NameToken.Title);
var author = GetEntryOrDefault(infoParsed, NameToken.Author);
var subject = GetEntryOrDefault(infoParsed, NameToken.Subject);
var keywords = GetEntryOrDefault(infoParsed, NameToken.Keywords);
var creator = GetEntryOrDefault(infoParsed, NameToken.Creator);
var producer = GetEntryOrDefault(infoParsed, NameToken.Producer);
return(new DocumentInformation(infoParsed, title, author, subject,
keywords, creator, producer));
}
public DocumentInformation Create(IPdfTokenScanner pdfTokenScanner, DictionaryToken rootDictionary)
{
if (!rootDictionary.TryGet(NameToken.Info, out var infoBase))
{
return(DocumentInformation.Default);
}
var infoParsed = DirectObjectFinder.Get <DictionaryToken>(infoBase, pdfTokenScanner);
var title = GetEntryOrDefault(infoParsed, NameToken.Title);
var author = GetEntryOrDefault(infoParsed, NameToken.Author);
var subject = GetEntryOrDefault(infoParsed, NameToken.Subject);
var keywords = GetEntryOrDefault(infoParsed, NameToken.Keywords);
var creator = GetEntryOrDefault(infoParsed, NameToken.Creator);
var producer = GetEntryOrDefault(infoParsed, NameToken.Producer);
return(new DocumentInformation(title, author, subject,
keywords, creator, producer));
}
private static bool TryReadExplicitDestination(IToken value, Catalog catalog, IPdfTokenScanner pdfScanner,
ILog log, out ExplicitDestination destination)
{
destination = null;
if (DirectObjectFinder.TryGet(value, pdfScanner, out ArrayToken valueArray) &&
TryGetExplicitDestination(valueArray, catalog, log, out destination))
{
return(true);
}
if (DirectObjectFinder.TryGet(value, pdfScanner, out DictionaryToken valueDictionary) &&
valueDictionary.TryGet(NameToken.D, pdfScanner, out valueArray) &&
TryGetExplicitDestination(valueArray, catalog, log, out destination))
{
return(true);
}
return(false);
}
private CharacterIdentifierToGlyphIndexMap GetCharacterIdentifierToGlyphIndexMap(DictionaryToken dictionary)
{
if (!dictionary.TryGet(NameToken.CidToGidMap, out var entry))
{
return(new CharacterIdentifierToGlyphIndexMap());
}
if (DirectObjectFinder.TryGet(entry, pdfScanner, out NameToken _))
{
return(new CharacterIdentifierToGlyphIndexMap());
}
if (!DirectObjectFinder.TryGet(entry, pdfScanner, out StreamToken stream))
{
throw new PdfDocumentFormatException($"No stream or name token found for /CIDToGIDMap in dictionary: {dictionary}.");
}
var bytes = stream.Decode(filterProvider, pdfScanner);
return(new CharacterIdentifierToGlyphIndexMap(bytes));
}
public Catalog Create(IPdfTokenScanner scanner, DictionaryToken dictionary)
{
if (dictionary == null)
{
throw new ArgumentNullException(nameof(dictionary));
}
if (dictionary.TryGet(NameToken.Type, out var type) && !ReferenceEquals(type, NameToken.Catalog))
{
throw new PdfDocumentFormatException($"The type of the catalog dictionary was not Catalog: {dictionary}.");
}
if (!dictionary.TryGet(NameToken.Pages, out var value))
{
throw new PdfDocumentFormatException($"No pages entry was found in the catalog dictionary: {dictionary}.");
}
var pages = DirectObjectFinder.Get <DictionaryToken>(value, scanner);
return(new Catalog(dictionary, pages));
}
private static DictionaryToken ParseTrailer(CrossReferenceTable crossReferenceTable, bool isLenientParsing, IPdfTokenScanner pdfTokenScanner)
{
if (crossReferenceTable.Dictionary.ContainsKey(NameToken.Encrypt))
{
throw new NotSupportedException("Cannot currently parse a document using encryption: " + crossReferenceTable.Dictionary);
}
if (!crossReferenceTable.Dictionary.TryGet(NameToken.Root, out var rootToken))
{
throw new PdfDocumentFormatException($"Missing root object specification in trailer: {crossReferenceTable.Dictionary}.");
}
var rootDictionary = DirectObjectFinder.Get <DictionaryToken>(rootToken, pdfTokenScanner);
if (!rootDictionary.ContainsKey(NameToken.Type) && isLenientParsing)
{
rootDictionary = rootDictionary.With(NameToken.Type, NameToken.Catalog);
}
return(rootDictionary);
}
private AcroFieldBase GetTextField(DictionaryToken fieldDictionary, NameToken fieldType, uint fieldFlags,
AcroFieldCommonInformation information,
int?pageNumber,
PdfRectangle?bounds)
{
var textFlags = (AcroTextFieldFlags)fieldFlags;
var textValue = default(string);
if (fieldDictionary.TryGet(NameToken.V, out var textValueToken))
{
if (DirectObjectFinder.TryGet(textValueToken, tokenScanner, out StringToken valueStringToken))
{
textValue = valueStringToken.Data;
}
else if (DirectObjectFinder.TryGet(textValueToken, tokenScanner, out HexToken valueHexToken))
{
textValue = valueHexToken.Data;
}
else if (DirectObjectFinder.TryGet(textValueToken, tokenScanner, out StreamToken valueStreamToken))
{
textValue = OtherEncodings.BytesAsLatin1String(valueStreamToken.Decode(filterProvider).ToArray());
}
}
var maxLength = default(int?);
if (fieldDictionary.TryGetOptionalTokenDirect(NameToken.MaxLen, tokenScanner, out NumericToken maxLenToken))
{
maxLength = maxLenToken.Int;
}
var field = new AcroTextField(fieldDictionary, fieldType, textFlags, information,
textValue,
maxLength,
pageNumber,
bounds);
return(field);
}
private string GetNamedString(NameToken name, DictionaryToken dictionary)
{
string content = null;
if (dictionary.TryGet(name, out var contentToken))
{
if (contentToken is StringToken contentString)
{
content = contentString.Data;
}
else if (contentToken is HexToken contentHex)
{
content = contentHex.Data;
}
else if (DirectObjectFinder.TryGet(contentToken, tokenScanner, out StringToken indirectContentString))
{
content = indirectContentString.Data;
}
}
return(content);
}
private TrueTypeFontProgram ParseTrueTypeFont(FontDescriptor descriptor)
{
if (descriptor.FontFile == null)
{
try
{
return(systemFontFinder.GetTrueTypeFont(descriptor.FontName.Data));
}
catch (Exception ex)
{
log.Error($"Failed finding system font by name: {descriptor.FontName}.", ex);
}
// TODO: check if this font is present on the host OS. See: FileSystemFontProvider.java
return(null);
}
if (descriptor.FontFile.FileType != DescriptorFontFile.FontFileType.TrueType)
{
throw new InvalidFontFormatException(
$"Expected a TrueType font in the TrueType font descriptor, instead it was {descriptor.FontFile.FileType}.");
}
try
{
var fontFileStream = DirectObjectFinder.Get <StreamToken>(descriptor.FontFile.ObjectKey, pdfScanner);
var fontFile = fontFileStream.Decode(filterProvider);
var font = trueTypeFontParser.Parse(new TrueTypeDataBytes(new ByteArrayInputBytes(fontFile)));
return(font);
}
catch (Exception ex)
{
log.Error("Could not parse the TrueType font.", ex);
return(null);
}
}
private CharacterIdentifierSystemInfo GetSystemInfo(DictionaryToken dictionary)
{
if (!dictionary.TryGet(NameToken.CidSystemInfo, out var cidEntry))
{
throw new InvalidFontFormatException($"No CID System Info was found in the CID Font dictionary: {dictionary}");
}
if (cidEntry is DictionaryToken cidDictionary)
{
}
else
{
cidDictionary =
DirectObjectFinder.Get <DictionaryToken>(cidEntry, pdfScanner);
}
var registry = SafeKeyAccess(cidDictionary, NameToken.Registry);
var ordering = SafeKeyAccess(cidDictionary, NameToken.Ordering);
var supplement = cidDictionary.GetIntOrDefault(NameToken.Supplement);
return(new CharacterIdentifierSystemInfo(registry, ordering, supplement));
}
private bool TryGetFontDescriptor(DictionaryToken dictionary, out DictionaryToken descriptorDictionary)
{
descriptorDictionary = null;
if (!dictionary.TryGet(NameToken.FontDescriptor, out var baseValue))
{
return(false);
}
try
{
var descriptor = DirectObjectFinder.Get <DictionaryToken>(baseValue, pdfScanner);
descriptorDictionary = descriptor;
}
catch
{
return(false);
}
return(true);
}
private static EncryptionDictionary GetEncryptionDictionary(CrossReferenceTable crossReferenceTable, IPdfTokenScanner pdfTokenScanner)
{
if (crossReferenceTable.Trailer.EncryptionToken == null)
{
return(null);
}
if (!DirectObjectFinder.TryGet(crossReferenceTable.Trailer.EncryptionToken, pdfTokenScanner, out DictionaryToken encryptionDictionaryToken))
{
if (DirectObjectFinder.TryGet(crossReferenceTable.Trailer.EncryptionToken, pdfTokenScanner, out NullToken _))
{
return(null);
}
throw new PdfDocumentFormatException($"Unrecognized encryption token in trailer: {crossReferenceTable.Trailer.EncryptionToken}.");
}
var result = EncryptionDictionaryFactory.Read(encryptionDictionaryToken, pdfTokenScanner);
return(result);
}
private static NameToken GetFontName(DictionaryToken dictionary, IPdfTokenScanner scanner, bool isLenientParsing)
{
if (!dictionary.TryGet(NameToken.FontName, out var name) || !(name is NameToken nameToken))
{
if (name is IndirectReferenceToken nameReference)
{
var indirectName = DirectObjectFinder.Get <NameToken>(nameReference, scanner);
return(indirectName);
}
if (isLenientParsing)
{
nameToken = NameToken.Create(string.Empty);
}
else
{
throw new InvalidOperationException("Could not parse the font descriptor, could not retrieve the font name. " + dictionary);
}
}
return(nameToken);
}
/// <summary>
/// Extract bookmarks, if any.
/// </summary>
public Bookmarks GetBookmarks(Catalog catalog)
{
if (!catalog.CatalogDictionary.TryGet(NameToken.Outlines, pdfScanner, out DictionaryToken outlinesDictionary))
{
return(null);
}
if (!isLenientParsing && outlinesDictionary.TryGet(NameToken.Type, pdfScanner, out NameToken typeName) &&
typeName != NameToken.Outlines)
{
throw new PdfDocumentFormatException($"Outlines (bookmarks) dictionary did not have correct type specified: {typeName}.");
}
if (!outlinesDictionary.TryGet(NameToken.First, pdfScanner, out DictionaryToken next))
{
return(null);
}
var namedDestinations = ReadNamedDestinations(catalog, pdfScanner, isLenientParsing, log);
var roots = new List <BookmarkNode>();
var seen = new HashSet <IndirectReference>();
while (next != null)
{
ReadBookmarksRecursively(next, 0, false, seen, namedDestinations, catalog, roots);
if (!next.TryGet(NameToken.Next, out IndirectReferenceToken nextReference) ||
!seen.Add(nextReference.Data))
{
break;
}
next = DirectObjectFinder.Get <DictionaryToken>(nextReference, pdfScanner);
}
return(new Bookmarks(roots));
}
private static void ExtractNameTree(DictionaryToken nameTreeNodeDictionary, Catalog catalog, IPdfTokenScanner pdfScanner,
bool isLenientParsing,
ILog log,
Dictionary <string, ExplicitDestination> explicitDestinations)
{
if (nameTreeNodeDictionary.TryGet(NameToken.Names, pdfScanner, out ArrayToken nodeNames))
{
for (var i = 0; i < nodeNames.Length; i += 2)
{
if (!(nodeNames[i] is IDataToken <string> key))
{
continue;
}
var value = nodeNames[i + 1];
if (TryReadExplicitDestination(value, catalog, pdfScanner, log, out var destination))
{
explicitDestinations[key.Data] = destination;
}
}
}
if (nameTreeNodeDictionary.TryGet(NameToken.Kids, pdfScanner, out ArrayToken kids))
{
foreach (var kid in kids.Data)
{
if (DirectObjectFinder.TryGet(kid, pdfScanner, out DictionaryToken kidDictionary))
{
ExtractNameTree(kidDictionary, catalog, pdfScanner, isLenientParsing, log, explicitDestinations);
}
else if (!isLenientParsing)
{
throw new PdfDocumentFormatException($"Invalid kids entry in PDF name tree: {kid} in {kids}.");
}
}
}
}
private CharacterIdentifierToGlyphIndexMap GetCharacterIdentifierToGlyphIndexMap(DictionaryToken dictionary, bool isLenientParsing)
{
if (!dictionary.TryGet(NameToken.CidToGidMap, out var entry))
{
return(new CharacterIdentifierToGlyphIndexMap());
}
if (entry is NameToken name)
{
if (!name.Equals(NameToken.Identity) && !isLenientParsing)
{
throw new InvalidOperationException($"The CIDToGIDMap in a Type 0 font should have the value /Identity, instead got: {name}.");
}
return(new CharacterIdentifierToGlyphIndexMap());
}
var stream = DirectObjectFinder.Get <StreamToken>(entry, pdfScanner);
var bytes = stream.Decode(filterProvider);
return(new CharacterIdentifierToGlyphIndexMap(bytes));
}
public Encoding Read(DictionaryToken fontDictionary, bool isLenientParsing, FontDescriptor descriptor = null,
Encoding fontEncoding = null)
{
if (!fontDictionary.TryGet(NameToken.Encoding, out var baseEncodingObject))
{
return(null);
}
if (baseEncodingObject is NameToken name)
{
if (TryGetNamedEncoding(descriptor, name, out var namedEncoding))
{
return(namedEncoding);
}
if (fontDictionary.TryGet(NameToken.BaseFont, pdfScanner, out NameToken baseFontName))
{
if (string.Equals(baseFontName.Data, "ZapfDingbats", StringComparison.OrdinalIgnoreCase))
{
return(ZapfDingbatsEncoding.Instance);
}
if (string.Equals(baseFontName.Data, "Symbol", StringComparison.OrdinalIgnoreCase))
{
return(SymbolEncoding.Instance);
}
return(WinAnsiEncoding.Instance);
}
}
DictionaryToken encodingDictionary = DirectObjectFinder.Get <DictionaryToken>(baseEncodingObject, pdfScanner);
var encoding = ReadEncodingDictionary(encodingDictionary, fontEncoding);
return(encoding);
}
private MediaBox GetMediaBox(int number, DictionaryToken dictionary, PageTreeMembers pageTreeMembers, bool isLenientParsing)
{
MediaBox mediaBox;
if (dictionary.TryGet(NameToken.MediaBox, out var mediaboxObject) &&
DirectObjectFinder.TryGet(mediaboxObject, pdfScanner, out ArrayToken mediaboxArray))
{
if (mediaboxArray.Length != 4 && isLenientParsing)
{
log.Error($"The MediaBox was the wrong length in the dictionary: {dictionary}. Array was: {mediaboxArray}.");
mediaBox = MediaBox.A4;
return(mediaBox);
}
mediaBox = new MediaBox(mediaboxArray.ToIntRectangle());
}
else
{
mediaBox = pageTreeMembers.MediaBox;
if (mediaBox == null)
{
if (isLenientParsing)
{
mediaBox = MediaBox.A4;
}
else
{
throw new InvalidOperationException("No mediabox was present for page: " + number);
}
}
}
return(mediaBox);
}
private string SafeKeyAccess(DictionaryToken dictionary, NameToken keyName)
{
if (!dictionary.TryGet(keyName, out var token))
{
return(string.Empty);
}
if (token is StringToken str)
{
return(str.Data);
}
if (token is HexToken hex)
{
return(hex.Data);
}
if (token is IndirectReferenceToken obj)
{
return(DirectObjectFinder.Get <StringToken>(obj, pdfScanner).Data);
}
return(string.Empty);
}
private static (IndirectReference, DictionaryToken) ParseTrailer(CrossReferenceTable crossReferenceTable, bool isLenientParsing, IPdfTokenScanner pdfTokenScanner,
out EncryptionDictionary encryptionDictionary)
{
encryptionDictionary = null;
if (crossReferenceTable.Trailer.EncryptionToken != null)
{
if (!DirectObjectFinder.TryGet(crossReferenceTable.Trailer.EncryptionToken, pdfTokenScanner, out DictionaryToken encryptionDictionaryToken))
{
throw new PdfDocumentFormatException($"Unrecognized encryption token in trailer: {crossReferenceTable.Trailer.EncryptionToken}.");
}
encryptionDictionary = EncryptionDictionaryFactory.Read(encryptionDictionaryToken, pdfTokenScanner);
}
var rootDictionary = DirectObjectFinder.Get <DictionaryToken>(crossReferenceTable.Trailer.Root, pdfTokenScanner);
if (!rootDictionary.ContainsKey(NameToken.Type) && isLenientParsing)
{
rootDictionary = rootDictionary.With(NameToken.Type, NameToken.Catalog);
}
return(crossReferenceTable.Trailer.Root, rootDictionary);
}
