void PdfPagesTree::InsertPagesIntoNode( PdfObject* pParent, const PdfObjectList & rlstParents,
int nIndex, const std::vector<PdfObject*>& vecPages )
{
if( !pParent || !vecPages.size() )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidHandle );
}
// 1. Add the reference of the new page to the kids array of pParent
// 2. Increase count of every node in lstParents (which also includes pParent)
// 3. Add Parent key to the page
// 1. Add reference
const PdfArray oldKids = pParent->GetDictionary().GetKey( PdfName("Kids") )->GetArray();
PdfArray newKids;
newKids.reserve( oldKids.GetSize() + vecPages.size() );
bool bIsPushedIn = false;
int i=0;
for (PdfArray::const_iterator it=oldKids.begin(); it!=oldKids.end(); ++it, ++i )
{
if ( !bIsPushedIn && (nIndex < i) ) // Pushing before
{
for (std::vector<PdfObject*>::const_iterator itPages=vecPages.begin(); itPages!=vecPages.end(); ++itPages)
{
newKids.push_back( (*itPages)->Reference() ); // Push all new kids at once
}
bIsPushedIn = true;
}
newKids.push_back( *it ); // Push in the old kids
}
// If new kids are still not pushed in then they may be appending to the end
if ( !bIsPushedIn && ( (nIndex + 1) == static_cast<int>(oldKids.size())) )
{
for (std::vector<PdfObject*>::const_iterator itPages=vecPages.begin(); itPages!=vecPages.end(); ++itPages)
{
newKids.push_back( (*itPages)->Reference() ); // Push all new kids at once
}
bIsPushedIn = true;
}
pParent->GetDictionary().AddKey( PdfName("Kids"), newKids );
// 2. increase count
for ( PdfObjectList::const_reverse_iterator itParents = rlstParents.rbegin(); itParents != rlstParents.rend(); ++itParents )
{
this->ChangePagesCount( *itParents, vecPages.size() );
}
// 3. add parent key to each of the pages
for (std::vector<PdfObject*>::const_iterator itPages=vecPages.begin(); itPages!=vecPages.end(); ++itPages)
{
(*itPages)->GetDictionary().AddKey( PdfName("Parent"), pParent->Reference() );
}
}
void PdfPagesTree::InsertPageIntoNode( PdfObject* pParent, const PdfObjectList & rlstParents,
int nIndex, PdfObject* pPage )
{
if( !pParent || !pPage )
{
PODOFO_RAISE_ERROR( ePdfError_InvalidHandle );
}
// 1. Add the reference of the new page to the kids array of pParent
// 2. Increase count of every node in lstParents (which also includes pParent)
// 3. Add Parent key to the page
// 1. Add reference
const PdfArray oldKids = pParent->GetDictionary().GetKey( PdfName("Kids") )->GetArray();
PdfArray::const_iterator it = oldKids.begin();
PdfArray newKids;
newKids.reserve( oldKids.GetSize() + 1 );
if( nIndex < 0 )
{
newKids.push_back( pPage->Reference() );
}
int i = 0;
while( it != oldKids.end() )
{
newKids.push_back( *it );
if( i == nIndex )
newKids.push_back( pPage->Reference() );
++i;
++it;
}
/*
PdfVariant var2( newKids );
std::string str2;
var2.ToString(str2);
printf("newKids= %s\n", str2.c_str() );
*/
pParent->GetDictionary().AddKey( PdfName("Kids"), newKids );
// 2. increase count
PdfObjectList::const_reverse_iterator itParents = rlstParents.rbegin();
while( itParents != rlstParents.rend() )
{
this->ChangePagesCount( *itParents, 1 );
++itParents;
}
// 3. add parent key to the page
pPage->GetDictionary().AddKey( PdfName("Parent"), pParent->Reference() );
}
void PdfSampledFunction::Init( const PdfArray & rDomain, const PdfArray & rRange, const PdfFunction::Sample & rlstSamples )
{
PdfArray Size;
for( unsigned i = 0; i < rDomain.GetSize() / 2; i++ )
Size.push_back( PdfObject( (long long) (rDomain.GetSize()) / 2L ) );
this->GetObject()->GetDictionary().AddKey( PdfName("Domain"), rDomain );
this->GetObject()->GetDictionary().AddKey( PdfName("Range"), rRange );
this->GetObject()->GetDictionary().AddKey( PdfName("Size"), Size );
this->GetObject()->GetDictionary().AddKey( PdfName("Order"), PdfObject( 1LL ) );
this->GetObject()->GetDictionary().AddKey( PdfName("BitsPerSample"), PdfObject( 8LL ) );
this->GetObject()->GetStream()->BeginAppend();
PdfFunction::Sample::const_iterator it = rlstSamples.begin();
while( it != rlstSamples.end() )
{
this->GetObject()->GetStream()->Append( & ( *it ), 1 );
++it;
}
this->GetObject()->GetStream()->EndAppend();
}
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
}
void PDFAnalyzer::inspectExtGStateObj(PdfObject* extGStateObj, QList<PDFColorSpace> & usedColorSpaces, bool & hasTransparency, QList<PDFFont> & usedFonts, PDFGraphicState & currGS)
{
PdfObject* bmObj = extGStateObj->GetIndirectKey("BM");
if (bmObj && bmObj->IsName())
{
currGS.blendModes.clear();
currGS.blendModes.append(bmObj->GetName().GetEscapedName().c_str());
if (!(bmObj->GetName() == "Normal" || bmObj->GetName() == "Compatible"))
hasTransparency = true;
}
else if (bmObj && bmObj->IsArray())
{
PdfArray arr = bmObj->GetArray();
currGS.blendModes.clear();
for(int i=0; i<arr.GetSize(); ++i)
currGS.blendModes.append(arr[i].GetName().GetEscapedName().c_str());
if (arr[0].IsName() && !(arr[0].GetName() == "Normal" || arr[0].GetName() == "Compatible"))
hasTransparency = true;
}
PdfObject* caObj = extGStateObj->GetIndirectKey("ca");
if (caObj && (caObj->IsReal() || caObj->IsNumber()))
{
currGS.fillAlphaConstant = caObj->GetReal();
if (caObj->GetReal() < 1)
hasTransparency = true;
}
PdfObject* cAObj = extGStateObj->GetIndirectKey("CA");
if (cAObj && (cAObj->IsReal() || cAObj->IsNumber()))
{
if (cAObj->GetReal() < 1)
hasTransparency = true;
}
PdfObject* sMaskObj = extGStateObj->GetIndirectKey("SMask");
if (sMaskObj && !(sMaskObj->IsName() && sMaskObj->GetName() == "None"))
hasTransparency = true;
PdfObject* fontObj = extGStateObj->GetIndirectKey("Font");
if (fontObj && fontObj->IsArray())
{
PdfArray arr = fontObj->GetArray();
if (arr[0].IsReference())
{
PdfReference ref = arr[0].GetReference();
PdfObject* fontObject = m_doc->GetObjects().GetObject(ref);
if (fontObject)
{
PDFFont font = getFontInfo(fontObject);
usedFonts.append(font);
currGS.font.first = font;
currGS.font.second = arr[1].GetReal();
}
}
}
PdfObject* lwObj = extGStateObj->GetIndirectKey("LW");
if (lwObj)
currGS.lineWidth = lwObj->GetReal();
PdfObject* lcObj = extGStateObj->GetIndirectKey("LC");
if (lcObj)
currGS.lineCap = lcObj->GetNumber();
PdfObject* ljObj = extGStateObj->GetIndirectKey("LJ");
if (ljObj)
currGS.lineJoin = ljObj->GetNumber();
PdfObject* mlObj = extGStateObj->GetIndirectKey("ML");
if (mlObj)
currGS.miterLimit = mlObj->GetReal();
PdfObject* dObj = extGStateObj->GetIndirectKey("D");
if (dObj)
{
PdfArray dashArr = dObj->GetArray()[0];
currGS.dashPattern.first.clear();
for (int i=0; i<dashArr.GetSize(); ++i)
currGS.dashPattern.first.append(dashArr[i].GetNumber());
currGS.dashPattern.second = dObj->GetArray()[1].GetNumber();
}
}
void TextExtractor::ExtractText( PdfMemDocument* pDocument, PdfPage* pPage )
{
const char* pszToken = NULL;
PdfVariant var;
EPdfContentsType eType;
PdfContentsTokenizer tokenizer( pPage );
double dCurPosX = 0.0;
double dCurPosY = 0.0;
double dCurFontSize = 0.0;
bool bTextBlock = false;
PdfFont* pCurFont = NULL;
std::stack<PdfVariant> stack;
while( tokenizer.ReadNext( eType, pszToken, var ) )
{
if( eType == ePdfContentsType_Keyword )
{
// support 'l' and 'm' tokens
if( strcmp( pszToken, "l" ) == 0 ||
strcmp( pszToken, "m" ) == 0 )
{
dCurPosX = stack.top().GetReal();
stack.pop();
dCurPosY = stack.top().GetReal();
stack.pop();
}
else if( strcmp( pszToken, "BT" ) == 0 )
{
bTextBlock = true;
// BT does not reset font
// dCurFontSize = 0.0;
// pCurFont = NULL;
}
else if( strcmp( pszToken, "ET" ) == 0 )
{
if( !bTextBlock )
fprintf( stderr, "WARNING: Found ET without BT!\n" );
}
if( bTextBlock )
{
if( strcmp( pszToken, "Tf" ) == 0 )
{
dCurFontSize = stack.top().GetReal();
stack.pop();
PdfName fontName = stack.top().GetName();
PdfObject* pFont = pPage->GetFromResources( PdfName("Font"), fontName );
if( !pFont )
{
PODOFO_RAISE_ERROR_INFO( ePdfError_InvalidHandle, "Cannot create font!" );
}
pCurFont = pDocument->GetFont( pFont );
if( !pCurFont )
{
fprintf( stderr, "WARNING: Unable to create font for object %i %i R\n",
pFont->Reference().ObjectNumber(),
pFont->Reference().GenerationNumber() );
}
}
else if( strcmp( pszToken, "Tj" ) == 0 ||
strcmp( pszToken, "'" ) == 0 )
{
AddTextElement( dCurPosX, dCurPosY, pCurFont, stack.top().GetString() );
stack.pop();
}
else if( strcmp( pszToken, "\"" ) == 0 )
{
AddTextElement( dCurPosX, dCurPosY, pCurFont, stack.top().GetString() );
stack.pop();
stack.pop(); // remove char spacing from stack
stack.pop(); // remove word spacing from stack
}
else if( strcmp( pszToken, "TJ" ) == 0 )
{
PdfArray array = stack.top().GetArray();
stack.pop();
for( int i=0; i<static_cast<int>(array.GetSize()); i++ )
{
if( array[i].IsString() )
AddTextElement( dCurPosX, dCurPosY, pCurFont, array[i].GetString() );
}
}
}
}
else if ( eType == ePdfContentsType_Variant )
{
stack.push( var );
}
else
{
// Impossible; type must be keyword or variant
PODOFO_RAISE_ERROR( ePdfError_InternalLogic );
}
}
}