PdfAnnotation* PdfPage::GetAnnotation( int index )
{
PdfAnnotation* pAnnot;
PdfReference ref;
PdfObject* pObj = this->GetAnnotationsArray( false );
if( !(pObj && pObj->IsArray()) )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidDataType );
}
if( index < 0 && static_cast<unsigned int>(index) >= pObj->GetArray().size() )
{
PODOFO_RAISE_ERROR( ePdfError_ValueOutOfRange );
}
ref = pObj->GetArray()[index].GetReference();
pAnnot = m_mapAnnotations[ref];
if( !pAnnot )
{
pObj = m_pObject->GetOwner()->GetObject( ref );
if( !pObj )
{
PdfError::DebugMessage( "Error looking up object %i %i R\n", ref.ObjectNumber(), ref.GenerationNumber() );
PODOFO_RAISE_ERROR( ePdfError_NoObject );
}
pAnnot = new PdfAnnotation( pObj, this );
m_mapAnnotations[ref] = pAnnot;
}
return pAnnot;
}
void PdfeFontType3::initGlyphs( const PdfObject* pFont )
{
// CharProcs and Resources objects.
PdfObject* pCharProcs = pFont->GetIndirectKey( "CharProcs" );
PdfObject* pResources = pFont->GetIndirectKey( "Resources" );
// No CharProcs: exception raised.
if( !pCharProcs || !pCharProcs->IsDictionary() ) {
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidDataType, "Entries missing in the Type 3 font dictionary." );
}
// Resize space vectors.
m_mapCIDToGID.resize( m_lastCID-m_firstCID+1, 0 );
m_glyphs.resize( m_lastCID-m_firstCID+1, PdfeGlyphType3() );
// Look at each character.
PdfName cname;
PdfObject* pGlyph;
for( pdfe_cid c = m_firstCID ; c <= m_lastCID ; ++c ) {
// Get character name and search it in CharProcs.
cname = this->fromCIDToName( c );
pGlyph = pCharProcs->GetIndirectKey( cname );
// If found, set GID to c-m_firstCID+1 and create glyph.
if( pGlyph ) {
m_mapCIDToGID[c-m_firstCID] = c-m_firstCID+1;
m_glyphs[c-m_firstCID] = PdfeGlyphType3( cname, pGlyph, pResources );
}
}
}
PdfObject* PdfContents::GetContentsForAppending() const
{
// if ( mContObj->GetDataType() == ePdfDataType_Stream ||
// mContObj->GetDataType() == ePdfDataType_Dictionary ) {
// Use PdfObject::HasStream() instead of the datatype ePdfDataType_Stream
// as large parts of the code rely on all PdfObjects having the datatype
// ePdfDataType_Dictionary wether they have a stream or not
if( mContObj->GetDataType() == ePdfDataType_Dictionary ) {
return mContObj; // just return the stream itself
} else if ( mContObj->GetDataType() == ePdfDataType_Array ) {
/*
Create a new stream, add it to the array, return it
*/
PdfObject* newStm = mContObj->GetOwner()->CreateObject();
newStm->GetStream();
PdfReference pdfr( newStm->Reference().ObjectNumber(), newStm->Reference().GenerationNumber() );
PdfArray& cArr = mContObj->GetArray();
cArr.push_back( pdfr );
return newStm;
} else {
PODOFO_RAISE_ERROR( ePdfError_InvalidDataType );
}
}
PdfContentsTokenizer::PdfContentsTokenizer( PdfCanvas* pCanvas )
: PdfTokenizer()
{
PdfObject* pContents = pCanvas->GetContents();
if( pContents && pContents->IsArray() )
{
PdfArray& a = pContents->GetArray();
for ( PdfArray::iterator it = a.begin(); it != a.end() ; ++it )
{
if ( !(*it).IsReference() )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidDataType, "/Contents array contained non-references" );
}
m_lstContents.push_back( pContents->GetOwner()->GetObject( (*it).GetReference() ) );
}
}
else if ( pContents && pContents->HasStream() )
{
m_lstContents.push_back( pContents );
}
else
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidDataType, "Page /Contents not stream or array of streams" );
}
if( m_lstContents.size() )
{
SetCurrentContentsStream( m_lstContents.front() );
m_lstContents.pop_front();
}
}
PdfObject* PdfVecObjects::CreateObject( const PdfVariant & rVariant )
{
PdfReference ref = this->GetNextFreeObject();
PdfObject* pObj = new PdfObject( ref, rVariant );
pObj->SetOwner( this );
this->push_back( pObj );
return pObj;
}
int PdfPage::GetRotation() const
{
int rot = 0;
PdfObject* pObj = GetInheritedKeyFromObject( "Rotate", m_pObject );
if ( pObj && pObj->IsNumber() )
rot = static_cast<int>(pObj->GetNumber());
return rot;
}
PdfObject* PdfVecObjects::CreateObject( const char* pszType )
{
PdfReference ref = this->GetNextFreeObject();
PdfObject* pObj = new PdfObject( ref, pszType );
pObj->SetOwner( this );
this->push_back( pObj );
return pObj;
}
PdfAnnotation* PdfPage::CreateAnnotation( EPdfAnnotation eType, const PdfRect & rRect )
{
PdfAnnotation* pAnnot = new PdfAnnotation( this, eType, rRect, m_pObject->GetOwner() );
PdfObject* pObj = this->GetAnnotationsArray( true );
PdfReference ref = pAnnot->GetObject()->Reference();
pObj->GetArray().push_back( ref );
m_mapAnnotations[ref] = pAnnot;
return pAnnot;
}
TVecFilters PdfFilterFactory::CreateFilterList( const PdfObject* pObject )
{
TVecFilters filters;
const PdfObject* pObj = NULL;
if( pObject->IsDictionary() && pObject->GetDictionary().HasKey( "Filter" ) )
pObj = pObject->GetDictionary().GetKey( "Filter" );
else if( pObject->IsArray() )
pObj = pObject;
else if( pObject->IsName() )
pObj = pObject;
if (!pObj)
// Object had no /Filter key . Return a null filter list.
return filters;
if( pObj->IsName() )
filters.push_back( PdfFilterFactory::FilterNameToType( pObj->GetName() ) );
else if( pObj->IsArray() )
{
TCIVariantList it = pObj->GetArray().begin();
while( it != pObj->GetArray().end() )
{
if ( (*it).IsName() )
{
filters.push_back( PdfFilterFactory::FilterNameToType( (*it).GetName() ) );
}
else if ( (*it).IsReference() )
{
PdfObject* pFilter = pObject->GetOwner()->GetObject( (*it).GetReference() );
if( pFilter == NULL )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidDataType, "Filter array contained unexpected reference" );
}
filters.push_back( PdfFilterFactory::FilterNameToType( pFilter->GetName() ) );
}
else
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidDataType, "Filter array contained unexpected non-name type" );
}
++it;
}
}
return filters;
}
PdfObject* PdfPagesTree::GetPageNodeFromArray( int nPageNum, const PdfArray & rKidsArray, PdfObjectList & rLstParents )
{
if( static_cast<size_t>(nPageNum) >= rKidsArray.GetSize() )
{
PdfError::LogMessage( eLogSeverity_Critical, "Requesting page index %i from array of size %i\n",
nPageNum, rKidsArray.size() );
return NULL;
}
// TODO: Fill cache immediately with all pages
// in this kids array
PdfVariant rVar = rKidsArray[nPageNum];
while( true )
{
if( rVar.IsArray() )
{
// Fixes some broken PDFs who have trees with 1 element kids arrays
return GetPageNodeFromArray( 0, rVar.GetArray(), rLstParents );
}
else if( !rVar.IsReference() )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_NotImplemented, "Cannot handle inline pages." );
}
PdfObject* pgObject = GetRoot()->GetOwner()->GetObject( rVar.GetReference() );
if(pgObject==NULL) {
PODOFO_RAISE_ERROR_INFO( ePdfError_PageNotFound, "Invalid reference." );
}
//printf("Reading %s\n", pgObject->Reference().ToString().c_str());
// make sure the object is a /Page and not a /Pages with a single kid
if( this->IsTypePage(pgObject) )
{
return pgObject;
}
// it's a /Pages with a single kid, so dereference and try again...
if (this->IsTypePages(pgObject) )
{
if( !pgObject->GetDictionary().HasKey( "Kids" ) )
return NULL;
rLstParents.push_back( pgObject );
rVar = *(pgObject->GetDictionary().GetKey( "Kids" ));
} else {
// Reference to unexpected object
PODOFO_RAISE_ERROR_INFO( ePdfError_PageNotFound, "Reference to unexpected object." );
}
}
return NULL;
}
PdfObject* PdfPage::GetFromResources( const PdfName & rType, const PdfName & rKey )
{
if( m_pResources->GetDictionary().HasKey( rType ) )
{
PdfObject* pType = m_pResources->GetDictionary().GetKey( rType );
if( pType->IsDictionary() && pType->GetDictionary().HasKey( rKey ) )
{
const PdfReference & ref = pType->GetDictionary().GetKey( rKey )->GetReference();
return m_pObject->GetOwner()->GetObject( ref );
}
}
return NULL;
}
const PdfRect PdfPage::GetPageBox( const char* inBox ) const
{
PdfRect pageBox;
PdfObject* pObj;
// Take advantage of inherited values - walking up the tree if necessary
pObj = GetInheritedKeyFromObject( inBox, m_pObject );
// assign the value of the box from the array
if ( pObj && pObj->IsArray() )
pageBox.FromArray( pObj->GetArray() );
return pageBox;
}
PDFColorSpace PDFAnalyzer::getCSType(PdfObject* cs)
{
try {
// colorspace is either a name or an array
if (cs && cs->IsName())
{
PdfName csName = cs->GetName();
if (csName == "DeviceGray")
return CS_DeviceGray;
else if (csName == "DeviceRGB")
return CS_DeviceRGB;
else if (csName == "DeviceCMYK")
return CS_DeviceCMYK;
}
else if (cs && cs->IsArray())
{
PdfArray csArr = cs->GetArray();
PdfObject csTypePdfName = csArr[0];
if (csTypePdfName.IsName())
{
PdfName csTypeName = csTypePdfName.GetName();
if (csTypeName == "ICCBased")
return CS_ICCBased;
else if (csTypeName == "CalGray")
return CS_CalGray;
else if (csTypeName == "CalRGB")
return CS_CalRGB;
else if (csTypeName == "Lab")
return CS_Lab;
else if (csTypeName == "Indexed")
{
PdfObject base = cs->GetArray()[1];
PdfObject* pBase = &base;
if (base.IsReference())
{
pBase = cs->GetOwner()->GetObject(base.GetReference());
}
pBase->SetOwner(cs->GetOwner());
return getCSType(pBase);
}
else if (csTypeName == "Separation")
return CS_Separation;
else if (csTypeName == "DeviceN")
return CS_DeviceN;
else if (csTypeName == "Pattern")
return CS_Pattern;
}
}
}
catch (PdfError & e)
{
qDebug() << "Error in identifying the color type";
e.PrintErrorMsg();
return CS_Unknown;
}
return CS_Unknown;
}
void PdfFileSpec::Init( const char* pszFilename, const unsigned char* data, ptrdiff_t size, bool bStripPath )
{
PdfObject* pEmbeddedStream;
PdfString filename( MaybeStripPath( pszFilename, true) );
this->GetObject()->GetDictionary().AddKey( "F", this->CreateFileSpecification( MaybeStripPath( pszFilename, bStripPath) ) );
this->GetObject()->GetDictionary().AddKey( "UF", filename.ToUnicode () );
PdfDictionary ef;
pEmbeddedStream = this->CreateObject( "EmbeddedFile" );
this->EmbeddFileFromMem( pEmbeddedStream, data, size );
ef.AddKey( "F", pEmbeddedStream->Reference() );
this->GetObject()->GetDictionary().AddKey( "EF", ef );
}
void PdfPage::DeleteAnnotation( const PdfReference & ref )
{
PdfAnnotation* pAnnot;
PdfArray::iterator it;
PdfObject* pObj = this->GetAnnotationsArray( false );
bool bFound = false;
// delete the annotation from the array
if( !(pObj && pObj->IsArray()) )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidDataType );
}
it = pObj->GetArray().begin();
while( it != pObj->GetArray().end() )
{
if( (*it).GetReference() == ref )
{
pObj->GetArray().erase( it );
bFound = true;
break;
}
++it;
}
// if no such annotation was found
// throw an error instead of deleting
// another object with this reference
if( !bFound )
{
PODOFO_RAISE_ERROR( ePdfError_NoObject );
}
// delete any cached PdfAnnotations
pAnnot = m_mapAnnotations[ref];
if( pAnnot )
{
delete pAnnot;
m_mapAnnotations.erase( ref );
}
// delete the PdfObject in the file
delete m_pObject->GetOwner()->RemoveObject( ref );
}
void PagesTreeTest::CreateTestTreeCustom( PoDoFo::PdfMemDocument & rDoc )
{
const int COUNT = PODOFO_TEST_NUM_PAGES / 10;
PdfObject* pRoot = rDoc.GetPagesTree()->GetObject();
PdfArray rootKids;
for(int z=0; z<COUNT; z++)
{
PdfObject* pNode = rDoc.GetObjects().CreateObject("Pages");
PdfArray nodeKids;
for(int i=0; i<COUNT; i++)
{
PdfPage* pPage = new PdfPage( PdfPage::CreateStandardPageSize( ePdfPageSize_A4 ),
&(rDoc.GetObjects()) );
pPage->GetObject()->GetDictionary().AddKey( PODOFO_TEST_PAGE_KEY,
static_cast<long long>(z * COUNT + i) );
//printf("Creating page %i z=%i i=%i\n", z * COUNT + i, z, i );
nodeKids.push_back( pPage->GetObject()->Reference() );
}
pNode->GetDictionary().AddKey( PdfName("Kids"), nodeKids );
pNode->GetDictionary().AddKey( PdfName("Count"), static_cast<long long>(COUNT) );
rootKids.push_back( pNode->Reference() );
}
pRoot->GetDictionary().AddKey( PdfName("Kids"), rootKids );
pRoot->GetDictionary().AddKey( PdfName("Count"), static_cast<long long>(PODOFO_TEST_NUM_PAGES) );
}
unsigned int PdfPage::GetPageNumber() const
{
unsigned int nPageNumber = 0;
PdfObject* pParent = m_pObject->GetIndirectKey( "Parent" );
PdfReference ref = m_pObject->Reference();
while( pParent )
{
const PdfArray& kids = pParent->GetIndirectKey( "Kids" )->GetArray();
PdfArray::const_iterator it = kids.begin();
while( it != kids.end() && (*it).GetReference() != ref )
{
PdfObject* pNode = m_pObject->GetOwner()->GetObject( (*it).GetReference() );
if( pNode->GetDictionary().GetKey( PdfName::KeyType )->GetName() == PdfName( "Pages" ) )
nPageNumber += static_cast<int>(pNode->GetDictionary().GetKey( "Count" )->GetNumber());
else
// if we do not have a page tree node,
// we most likely have a page object:
// so the page count is 1
++nPageNumber;
++it;
}
ref = pParent->Reference();
pParent = pParent->GetIndirectKey( "Parent" );
}
return ++nPageNumber;
}
void EncryptTest::testEnableAlgorithms()
{
int nDefault = PdfEncrypt::GetEnabledEncryptionAlgorithms();
// By default every algorithms should be enabled
CPPUNIT_ASSERT( PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_RC4V1 ) );
CPPUNIT_ASSERT( PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_RC4V2 ) );
CPPUNIT_ASSERT( PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_AESV2 ) );
CPPUNIT_ASSERT_EQUAL( PdfEncrypt::ePdfEncryptAlgorithm_RC4V1 |
PdfEncrypt::ePdfEncryptAlgorithm_RC4V2 |
PdfEncrypt::ePdfEncryptAlgorithm_AESV2,
PdfEncrypt::GetEnabledEncryptionAlgorithms() );
// Disable AES
PdfEncrypt::SetEnabledEncryptionAlgorithms( PdfEncrypt::ePdfEncryptAlgorithm_RC4V1 |
PdfEncrypt::ePdfEncryptAlgorithm_RC4V2 );
CPPUNIT_ASSERT( PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_RC4V1 ) );
CPPUNIT_ASSERT( PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_RC4V2 ) );
CPPUNIT_ASSERT( !PdfEncrypt::IsEncryptionEnabled( PdfEncrypt::ePdfEncryptAlgorithm_AESV2 ) );
CPPUNIT_ASSERT_EQUAL( PdfEncrypt::ePdfEncryptAlgorithm_RC4V1 |
PdfEncrypt::ePdfEncryptAlgorithm_RC4V2,
PdfEncrypt::GetEnabledEncryptionAlgorithms() );
PdfObject object;
object.GetDictionary().AddKey(PdfName("Filter"), PdfName("Standard"));
object.GetDictionary().AddKey(PdfName("V"), static_cast<pdf_int64>(4L));
object.GetDictionary().AddKey(PdfName("R"), static_cast<pdf_int64>(4L));
object.GetDictionary().AddKey(PdfName("P"), static_cast<pdf_int64>(1L));
object.GetDictionary().AddKey(PdfName("O"), PdfString(""));
object.GetDictionary().AddKey(PdfName("U"), PdfString(""));
try {
(void)PdfEncrypt::CreatePdfEncrypt( &object );
CPPUNIT_ASSERT( false );
} catch( PdfError & rError ) {
CPPUNIT_ASSERT_EQUAL( rError.GetError(), ePdfError_UnsupportedFilter );
}
// Restore default
PdfEncrypt::SetEnabledEncryptionAlgorithms( nDefault );
}
void PdfPage::DeleteAnnotation( int index )
{
PdfReference ref;
PdfObject* pObj = this->GetAnnotationsArray( false );
if( !(pObj && pObj->IsArray()) )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidDataType );
}
if( index < 0 && static_cast<unsigned int>(index) >= pObj->GetArray().size() )
{
PODOFO_RAISE_ERROR( ePdfError_ValueOutOfRange );
}
ref = pObj->GetArray()[index].GetReference();
this->DeleteAnnotation( ref );
}
void PdfFileSpec::Init( const char* pszFilename, bool bEmbedd, bool bStripPath )
{
PdfObject* pEmbeddedStream;
PdfString filename( MaybeStripPath( pszFilename, true) );
this->GetObject()->GetDictionary().AddKey( "F", this->CreateFileSpecification( MaybeStripPath( pszFilename, bStripPath ) ) );
this->GetObject()->GetDictionary().AddKey( "UF", filename.ToUnicode () );
if( bEmbedd )
{
PdfDictionary ef;
pEmbeddedStream = this->CreateObject( "EmbeddedFile" );
this->EmbeddFile( pEmbeddedStream, pszFilename );
ef.AddKey( "F", pEmbeddedStream->Reference() );
this->GetObject()->GetDictionary().AddKey( "EF", ef );
}
}
PdfObject* PdfPage::GetAnnotationsArray( bool bCreate ) const
{
PdfObject* pObj;
// check for it in the object itself
if ( m_pObject->GetDictionary().HasKey( "Annots" ) )
{
pObj = m_pObject->GetIndirectKey( "Annots" );
if( pObj && pObj->IsArray() )
return pObj;
}
else if( bCreate )
{
PdfArray array;
const_cast<PdfPage*>(this)->m_pObject->GetDictionary().AddKey( "Annots", array );
return m_pObject->GetDictionary().GetKey( "Annots" );
}
return NULL;
}
PdfObject* PdfVecObjects::RemoveObject( const PdfReference & ref, bool bMarkAsFree )
{
if( !m_bSorted )
this->Sort();
PdfObject* pObj;
PdfObject refObj( ref, NULL );
std::pair<TIVecObjects,TIVecObjects> it =
std::equal_range( m_vector.begin(), m_vector.end(), &refObj, ObjectComparatorPredicate() );
if( it.first != it.second )
{
pObj = *(it.first);
if( bMarkAsFree )
this->AddFreeObject( pObj->Reference() );
m_vector.erase( it.first );
return pObj;
}
return NULL;
}
PdfObject* PdfPage::GetInheritedKeyFromObject( const char* inKey, PdfObject* inObject ) const
{
PdfObject* pObj = NULL;
// check for it in the object itself
if ( inObject->GetDictionary().HasKey( inKey ) )
{
pObj = inObject->GetDictionary().GetKey( inKey );
if ( !pObj->IsNull() )
return pObj;
}
// if we get here, we need to go check the parent - if there is one!
if( inObject->GetDictionary().HasKey( "Parent" ) )
{
pObj = inObject->GetIndirectKey( "Parent" );
if( pObj )
pObj = GetInheritedKeyFromObject( inKey, pObj );
}
return pObj;
}
void PdfImmediateWriter::Finish()
{
// write all objects which are still in RAM
this->FinishLastObject();
// setup encrypt dictionary
if( m_pEncrypt )
{
// Add our own Encryption dictionary
m_pEncryptObj = m_vecObjects->CreateObject();
m_pEncrypt->CreateEncryptionDictionary( m_pEncryptObj->GetDictionary() );
}
this->WritePdfObjects( m_pDevice, *m_pParent, m_pXRef );
// write the XRef
pdf_long lXRefOffset = m_pDevice->Tell();
m_pXRef->Write( m_pDevice );
// XRef streams contain the trailer in the XRef
if( !m_bXRefStream )
{
PdfObject trailer;
// if we have a dummy offset we write also a prev entry to the trailer
FillTrailerObject( &trailer, m_pXRef->GetSize(), false, false );
m_pDevice->Print("trailer\n");
trailer.WriteObject( m_pDevice, this->GetWriteMode(), NULL );
}
m_pDevice->Print( "startxref\n%li\n%%%%EOF\n", lXRefOffset );
m_pDevice->Flush();
// we are done now
m_pParent->Detach( this );
m_pParent = NULL;
}
void PdfFontTrueType::EmbedFontFile( PdfObject* pDescriptor )
{
PdfObject* pContents;
pdf_long lSize = 0;
m_bWasEmbedded = true;
pContents = this->GetObject()->GetOwner()->CreateObject();
if( !pContents )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidHandle );
}
pDescriptor->GetDictionary().AddKey( "FontFile2", pContents->Reference() );
// if the data was loaded from memory - use it from there
// otherwise, load from disk
if ( m_pMetrics->GetFontDataLen() && m_pMetrics->GetFontData() )
{
// FIXME const_cast<char*> is dangerous if string literals may ever be passed
char* pBuffer = const_cast<char*>( m_pMetrics->GetFontData() );
lSize = m_pMetrics->GetFontDataLen();
// Set Length1 before creating the stream
// as PdfStreamedDocument does not allow
// adding keys to an object after a stream was written
pContents->GetDictionary().AddKey( "Length1", PdfVariant( static_cast<pdf_int64>(lSize) ) );
pContents->GetStream()->Set( pBuffer, lSize );
}
else
{
PdfFileInputStream stream( m_pMetrics->GetFilename() );
lSize = stream.GetFileLength();
// Set Length1 before creating the stream
// as PdfStreamedDocument does not allow
// adding keys to an object after a stream was written
pContents->GetDictionary().AddKey( "Length1", PdfVariant( static_cast<pdf_int64>(lSize) ) );
pContents->GetStream()->Set( &stream );
}
}
void PdfAcroForm::Init( EPdfAcroFormDefaulAppearance eDefaultAppearance )
{
// Add default appearance: black text, 12pt times
// -> only if we do not have a DA key yet
// Peter Petrov 27 April 2008
//this->GetObject()->GetDictionary().AddKey( PdfName("NeedAppearances"), PdfVariant(true) );
if( !this->GetObject()->GetDictionary().HasKey("DA") &&
eDefaultAppearance == ePdfAcroFormDefaultAppearance_BlackText12pt )
{
//PdfFont* pFont = pParent->GetDocument()->CreateFont( "Helvetica", false );
// TODO: It is no good idea to always embedd arial
// but handling of non embedded helvetica is currently broken
PdfFont* pFont = m_pDocument->CreateFont( "Arial" ); // embedd is default true
PdfObject* pResource;
PdfObject* pFontDict;
// Create DR key
if( !this->GetObject()->GetDictionary().HasKey( PdfName("DR") ) )
this->GetObject()->GetDictionary().AddKey( PdfName("DR"), PdfDictionary() );
pResource = this->GetObject()->GetDictionary().GetKey( PdfName("DR") );
if( !pResource->GetDictionary().HasKey( PdfName("Font") ) )
pResource->GetDictionary().AddKey( PdfName("Font"), PdfDictionary() );
pFontDict = pResource->GetDictionary().GetKey( PdfName("Font") );
pFontDict->GetDictionary().AddKey( pFont->GetIdentifier(), pFont->GetObject()->Reference() );
// Create DA key
std::ostringstream oss;
PdfLocaleImbue(oss);
oss << "0 0 0 rg /" << pFont->GetIdentifier().GetName() << " 12 Tf";
this->GetObject()->GetDictionary().AddKey( PdfName("DA"), PdfString( oss.str() ) );
}
}
void PdfDestination::Init( PdfObject* pObject, PdfDocument* pDocument )
{
bool bValueExpected = false;
PdfObject* pValue = NULL;
if ( pObject->GetDataType() == ePdfDataType_Array )
{
m_array = pObject->GetArray();
m_pObject = pObject;
}
else if( pObject->GetDataType() == ePdfDataType_String )
{
PdfNamesTree* pNames = pDocument->GetNamesTree( ePdfDontCreateObject );
if( !pNames )
{
PODOFO_RAISE_ERROR( ePdfError_NoObject );
}
pValue = pNames->GetValue( "Dests", pObject->GetString() );
bValueExpected = true;
}
else if( pObject->GetDataType() == ePdfDataType_Name )
{
PdfMemDocument* pMemDoc = dynamic_cast<PdfMemDocument*>(pDocument);
if ( !pMemDoc )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidHandle,
"For reading from a document, only use PdfMemDocument." );
}
PdfObject* pCatalog = pMemDoc->GetCatalog();
if ( !pCatalog )
{
PODOFO_RAISE_ERROR( ePdfError_NoObject );
}
PdfObject* pDests = pCatalog->GetIndirectKey( PdfName( "Dests" ) );
if( !pDests )
{
// The error code has been chosen for its distinguishability.
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidKey,
"No PDF-1.1-compatible destination dictionary found." );
}
pValue = pDests->GetIndirectKey( pObject->GetName() );
bValueExpected = true;
}
else
{
PdfError::LogMessage( eLogSeverity_Error, "Unsupported object given to"
" PdfDestination::Init of type %s", pObject->GetDataTypeString() );
m_array = PdfArray(); // needed to prevent crash on method calls
// needed for GetObject() use w/o checking its return value for NULL
m_pObject = pDocument->GetObjects()->CreateObject( m_array );
}
if ( bValueExpected )
{
if( !pValue )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidName );
}
if( pValue->IsArray() )
m_array = pValue->GetArray();
else if( pValue->IsDictionary() )
m_array = pValue->GetDictionary().GetKey( "D" )->GetArray();
m_pObject = pValue;
}
}
void PDFProcessor::start ()
{
int nNum = 0;
try
{
PdfObject* pObj = NULL;
// open document
qDebug() << "Opening file: " << filename.toStdString().c_str();
PdfMemDocument document( filename.toStdString().c_str() );
// m_pszOutputDirectory = const_cast<char*>(pszOutput);
TCIVecObjects it = document.GetObjects().begin();
while( it != document.GetObjects().end() )
{
if( (*it)->IsDictionary() )
{
PdfObject* pObjType = (*it)->GetDictionary().GetKey( PdfName::KeyType );
PdfObject* pObjSubType = (*it)->GetDictionary().GetKey( PdfName::KeySubtype );
if( ( pObjType && pObjType->IsName() && ( pObjType->GetName().GetName() == "XObject" ) ) ||
( pObjSubType && pObjSubType->IsName() && ( pObjSubType->GetName().GetName() == "Image" ) ) )
{
pObj = (*it)->GetDictionary().GetKey( PdfName::KeyFilter );
if( pObj && pObj->IsArray() && pObj->GetArray().GetSize() == 1 &&
pObj->GetArray()[0].IsName() && (pObj->GetArray()[0].GetName().GetName() == "DCTDecode") )
pObj = &pObj->GetArray()[0];
std::string filterName = pObj->GetName().GetName();
bool processed = 0;
if( pObj && pObj->IsName() && ( filterName == "DCTDecode" ) )
{
// The only filter is JPEG -> create a JPEG file
qDebug() << "JPG found.\n";
processed = true;
nNum++;
}
if( pObj && pObj->IsName() && ( filterName == "JPXDecode" ) )
{
// The only filter is JPEG -> create a JPEG file
qDebug() << "JPG found.\n";
processed = true;
nNum++;
}
if( pObj && pObj->IsName() && ( filterName == "FlateDecode" ) )
{
// The only filter is JPEG -> create a JPEG file
qDebug() << "JPG found.\n";
processed = true;
nNum++;
}
// else we found something strange, we do not care about it for now.
if (processed == false)
{
qDebug() << "Unknown image type found:" << QString::fromStdString(filterName) << "\n";
nNum++;
}
document.FreeObjectMemory( *it );
}
}
++it;
}
}
catch( PdfError & e )
{
qDebug() << "Error: An error ocurred during processing the pdf file:" << e.GetError();
e.PrintErrorMsg();
return;// e.GetError();
}
// TODO: statistics of no of images etc
// nNum = extractor.GetNumImagesExtracted();
qDebug() << "Extracted " << nNum << " images successfully from the PDF file.\n";
}
int PdfPage::GetNumAnnots() const
{
PdfObject* pObj = this->GetAnnotationsArray();
return pObj ? static_cast<int>(pObj->GetArray().size()) : 0;
}
PdfFontMetricsObject::PdfFontMetricsObject( PdfObject* pFont, PdfObject* pDescriptor, const PdfEncoding* const pEncoding )
: PdfFontMetrics( ePdfFontType_Unknown, "", NULL ),
m_pEncoding( pEncoding ), m_dDefWidth(0.0)
{
if( !pDescriptor )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidHandle );
}
const PdfName & rSubType = pFont->GetDictionary().GetKey( PdfName::KeySubtype )->GetName();
// OC 15.08.2010 BugFix: /FirstChar /LastChar /Widths are in the Font dictionary and not in the FontDescriptor
if ( rSubType == PdfName("Type1") || rSubType == PdfName("TrueType") ) {
m_sName = pDescriptor->GetIndirectKey( "FontName" )->GetName();
m_bbox = pDescriptor->GetIndirectKey( "FontBBox" )->GetArray();
m_nFirst = static_cast<int>(pFont->GetDictionary().GetKeyAsLong( "FirstChar", 0L ));
m_nLast = static_cast<int>(pFont->GetDictionary().GetKeyAsLong( "LastChar", 0L ));
// OC 15.08.2010 BugFix: GetIndirectKey() instead of GetDictionary().GetKey() and "Widths" instead of "Width"
PdfObject* widths = pFont->GetIndirectKey( "Widths" );
if( widths != NULL )
{
m_width = widths->GetArray();
m_missingWidth = NULL;
}
else
{
widths = pDescriptor->GetDictionary().GetKey( "MissingWidth" );
if( widths == NULL )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_NoObject, "Font object defines neither Widths, nor MissingWidth values!" );
m_missingWidth = widths;
}
}
} else if ( rSubType == PdfName("CIDFontType0") || rSubType == PdfName("CIDFontType2") ) {
PdfObject *pObj = pDescriptor->GetIndirectKey( "FontName" );
if (pObj) {
m_sName = pObj->GetName();
}
pObj = pDescriptor->GetIndirectKey( "FontBBox" );
if (pObj) {
m_bbox = pObj->GetArray();
}
m_nFirst = 0;
m_nLast = 0;
m_dDefWidth = static_cast<double>(pFont->GetDictionary().GetKeyAsLong( "DW", 1000L ));
PdfVariant default_width(m_dDefWidth);
PdfObject * pw = pFont->GetIndirectKey( "W" );
for (int i = m_nFirst; i <= m_nLast; ++i) {
m_width.push_back(default_width);
}
if (pw) {
PdfArray w = pw->GetArray();
int pos = 0;
while (pos < static_cast<int>(w.GetSize())) {
int start = static_cast<int>(w[pos++].GetNumber());
PODOFO_ASSERT (start >= 0);
if (w[pos].IsArray()) {
PdfArray widths = w[pos++].GetArray();
int length = start + static_cast<int>(widths.GetSize());
PODOFO_ASSERT (length >= start);
if (length > static_cast<int>(m_width.GetSize())) {
m_width.resize(length, default_width);
}
for (int i = 0; i < static_cast<int>(widths.GetSize()); ++i) {
m_width[start + i] = widths[i];
}
} else {
int end = static_cast<int>(w[pos++].GetNumber());
int length = start + end;
PODOFO_ASSERT (length >= start);
if (length > static_cast<int>(m_width.GetSize())) {
m_width.resize(length, default_width);
}
pdf_int64 width = w[pos++].GetNumber();
for (int i = start; i <= end; ++i)
m_width[i] = PdfVariant(width);
}
}
}
m_nLast = m_width.GetSize() - 1;
} else {
PODOFO_RAISE_ERROR_INFO( ePdfError_UnsupportedFontFormat, rSubType.GetEscapedName().c_str() );
}
m_nWeight = static_cast<unsigned int>(pDescriptor->GetDictionary().GetKeyAsLong( "FontWeight", 400L ));
m_nItalicAngle = static_cast<int>(pDescriptor->GetDictionary().GetKeyAsLong( "ItalicAngle", 0L ));
m_dPdfAscent = pDescriptor->GetDictionary().GetKeyAsReal( "Ascent", 0.0 );
m_dAscent = m_dPdfAscent / 1000.0;
m_dPdfDescent = pDescriptor->GetDictionary().GetKeyAsReal( "Descent", 0.0 );
m_dDescent = m_dPdfDescent / 1000.0;
m_dLineSpacing = m_dAscent + m_dDescent;
// Try to fine some sensible values
m_dUnderlineThickness = 1.0;
m_dUnderlinePosition = 0.0;
m_dStrikeOutThickness = m_dUnderlinePosition;
m_dStrikeOutPosition = m_dAscent / 2.0;
m_bSymbol = false; // TODO
}