Bug #44747 for PDF-API2: [PATCH] Reduce PDF::API2 memory consumption

I'm using PDF:API2 to generate PDFs on the fly on a web server. Recently, I ran into the 32MB memory limit of a shared hosting provider. So I had a look at the memory consumption of PDF::API2. After creating a PDF::API2 object and loading some fonts, memory usage was about 25MB. With the following fixes I managed to reduce that to about 15MB. Most of the savings can be obtained if you only "require" some of the PDF::API2 packages when needed. See the attached patch pdf-api2-require-packages.diff. I could also save about three additional MB by rewriting the code for glyph name initialization. See the attached patch pdf-api2-glyph-names.diff. Note that this patch breaks the function initNameTable in PDF/API2 Util.pm. It doesn't seem to be part of the public API, though, and it isn't used internally.

diff -urN -x fonts -x 'CJKFont*' -x CMap PDF-API2-0.73/lib/PDF/API2.pm ../htdocs/cgi-bin/lib/PDF/API2.pm --- PDF-API2-0.73/lib/PDF/API2.pm 2008-01-18 01:11:38.000000000 +0100 +++ ../htdocs/cgi-bin/lib/PDF/API2.pm 2009-02-11 15:27:54.000000000 +0100 @@ -53,46 +53,8 @@ use PDF::API2::Util; use PDF::API2::Page; - use PDF::API2::Outlines; - use PDF::API2::NamedDestination; - use PDF::API2::Version; - use PDF::API2::Resource::ExtGState; - use PDF::API2::Resource::Pattern; - use PDF::API2::Resource::Shading; - - use PDF::API2::Resource::Font::CoreFont; - use PDF::API2::Resource::Font::Postscript; - use PDF::API2::Resource::Font::BdFont; - use PDF::API2::Resource::Font::SynFont; - use PDF::API2::Resource::Font::neTrueType; - use PDF::API2::Resource::CIDFont::TrueType; - use PDF::API2::Resource::CIDFont::CJKFont; - use PDF::API2::Resource::UniFont; - - use PDF::API2::Resource::XObject::Image::JPEG; - use PDF::API2::Resource::XObject::Image::TIFF; - use PDF::API2::Resource::XObject::Image::PNM; - use PDF::API2::Resource::XObject::Image::PNG; - use PDF::API2::Resource::XObject::Image::GIF; - use PDF::API2::Resource::XObject::Image::GD; - - use PDF::API2::Resource::XObject::Form::Hybrid; - - use PDF::API2::Resource::XObject::Form::BarCode::int2of5; - use PDF::API2::Resource::XObject::Form::BarCode::codabar; - use PDF::API2::Resource::XObject::Form::BarCode::code128; - use PDF::API2::Resource::XObject::Form::BarCode::code3of9; - use PDF::API2::Resource::XObject::Form::BarCode::ean13; - - use PDF::API2::Resource::ColorSpace::Indexed::ACTFile; - use PDF::API2::Resource::ColorSpace::Indexed::Hue; - use PDF::API2::Resource::ColorSpace::Indexed::WebColor; - - use PDF::API2::Resource::ColorSpace::Separation; - use PDF::API2::Resource::ColorSpace::DeviceN; - use Compress::Zlib; use Math::Trig; @@ -1644,6 +1606,7 @@ sub corefont { my ($self,$name,@opts)=@_; + require PDF::API2::Resource::Font::CoreFont; my $obj=PDF::API2::Resource::Font::CoreFont->new_api($self,$name,@opts); $self->resource('Font',$obj->name,$obj); $self->{pdf}->out_obj($self->{pages}); @@ -1689,6 +1652,7 @@ $opts{$o}=_findFont($opts{$o}); } $psf=_findFont($psf); + require PDF::API2::Resource::Font::Postscript; my $obj=PDF::API2::Resource::Font::Postscript->new_api($self,$psf,%opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1730,6 +1694,7 @@ my ($self,$file,%opts)=@_; $file=_findFont($file); + require PDF::API2::Resource::CIDFont::TrueType; my $obj=PDF::API2::Resource::CIDFont::TrueType->new_api($self,$file,%opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1743,6 +1708,7 @@ my ($self,$file,%opts)=@_; $file=_findFont($file); + require PDF::API2::Resource::Font::neTrueType; my $obj=PDF::API2::Resource::Font::neTrueType->new_api($self,$file,%opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1776,6 +1742,7 @@ sub cjkfont { my ($self,$name,%opts)=@_; + require PDF::API2::Resource::CIDFont::CJKFont; my $obj=PDF::API2::Resource::CIDFont::CJKFont->new_api($self,$name,%opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1821,6 +1788,7 @@ sub synfont { my ($self,@opts)=@_; + require PDF::API2::Resource::Font::SynFont; my $obj=PDF::API2::Resource::Font::SynFont->new_api($self,@opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1845,6 +1813,7 @@ sub bdfont { my ($self,@opts)=@_; + require PDF::API2::Resource::Font::BdFont; my $obj=PDF::API2::Resource::Font::BdFont->new_api($self,@opts); $self->resource('Font',$obj->name,$obj,$self->{reopened}); @@ -1875,6 +1844,7 @@ sub unifont { my ($self,@opts)=@_; + require PDF::API2::Resource::UniFont; my $obj=PDF::API2::Resource::UniFont->new_api($self,@opts); return($obj); @@ -1895,6 +1865,7 @@ sub image_jpeg { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::XObject::Image::JPEG; my $obj=PDF::API2::Resource::XObject::Image::JPEG->new_api($self,$file); $self->resource('XObject',$obj->name,$obj); @@ -1912,6 +1883,7 @@ sub image_tiff { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::XObject::Image::TIFF; my $obj=PDF::API2::Resource::XObject::Image::TIFF->new_api($self,$file); $self->resource('XObject',$obj->name,$obj); @@ -1929,6 +1901,7 @@ sub image_pnm { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::XObject::Image::PNM; my $obj=PDF::API2::Resource::XObject::Image::PNM->new_api($self,$file); $self->resource('XObject',$obj->name,$obj); @@ -1946,6 +1919,7 @@ sub image_png { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::XObject::Image::PNG; my $obj=PDF::API2::Resource::XObject::Image::PNG->new_api($self,$file); $self->resource('XObject',$obj->name,$obj); @@ -1963,6 +1937,7 @@ sub image_gif { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::XObject::Image::GIF; my $obj=PDF::API2::Resource::XObject::Image::GIF->new_api($self,$file); $self->resource('XObject',$obj->name,$obj); @@ -1982,6 +1957,7 @@ sub image_gd { my ($self,$gd,%opts)=@_; + require PDF::API2::Resource::XObject::Image::GD; my $obj=PDF::API2::Resource::XObject::Image::GD->new_api($self,$gd,undef,%opts); $self->resource('XObject',$obj->name,$obj); @@ -2136,6 +2112,7 @@ sub colorspace_act { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::ColorSpace::Indexed::ACTFile; my $obj=PDF::API2::Resource::ColorSpace::Indexed::ACTFile->new_api($self,$file); $self->resource('ColorSpace',$obj->name,$obj); @@ -2159,6 +2136,7 @@ sub colorspace_web { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::ColorSpace::Indexed::WebColor; my $obj=PDF::API2::Resource::ColorSpace::Indexed::WebColor->new_api($self); $self->resource('ColorSpace',$obj->name,$obj); @@ -2182,6 +2160,7 @@ sub colorspace_hue { my ($self,$file,%opts)=@_; + require PDF::API2::Resource::ColorSpace::Indexed::Hue; my $obj=PDF::API2::Resource::ColorSpace::Indexed::Hue->new_api($self); $self->resource('ColorSpace',$obj->name,$obj); @@ -2210,6 +2189,7 @@ sub colorspace_separation { my ($self,$name,@clr)=@_; + require PDF::API2::Resource::ColorSpace::Separation; my $obj=PDF::API2::Resource::ColorSpace::Separation->new_api($self,$name,@clr); $self->resource('ColorSpace',$obj->name,$obj); @@ -2244,6 +2224,7 @@ my ($self,$clrs,$samples)=@_; $samples||=2; + require PDF::API2::Resource::ColorSpace::DeviceN; my $obj=PDF::API2::Resource::ColorSpace::DeviceN->new_api($self,$clrs,$samples); $self->resource('ColorSpace',$obj->name,$obj); @@ -2275,6 +2256,7 @@ sub xo_code128 { my ($self,@opts)=@_; + require PDF::API2::Resource::XObject::Form::BarCode::code128; my $obj=PDF::API2::Resource::XObject::Form::BarCode::code128->new_api($self,@opts); $self->resource('XObject',$obj->name,$obj); @@ -2286,6 +2268,7 @@ sub xo_codabar { my ($self,@opts)=@_; + require PDF::API2::Resource::XObject::Form::BarCode::codabar; my $obj=PDF::API2::Resource::XObject::Form::BarCode::codabar->new_api($self,@opts); $self->resource('XObject',$obj->name,$obj); @@ -2297,6 +2280,7 @@ sub xo_2of5int { my ($self,@opts)=@_; + require PDF::API2::Resource::XObject::Form::BarCode::int2of5; my $obj=PDF::API2::Resource::XObject::Form::BarCode::int2of5->new_api($self,@opts); $self->resource('XObject',$obj->name,$obj); @@ -2308,6 +2292,7 @@ sub xo_3of9 { my ($self,@opts)=@_; + require PDF::API2::Resource::XObject::Form::BarCode::code3of9; my $obj=PDF::API2::Resource::XObject::Form::BarCode::code3of9->new_api($self,@opts); $self->resource('XObject',$obj->name,$obj); @@ -2319,6 +2304,7 @@ sub xo_ean13 { my ($self,@opts)=@_; + require PDF::API2::Resource::XObject::Form::BarCode::ean13; my $obj=PDF::API2::Resource::XObject::Form::BarCode::ean13->new_api($self,@opts); $self->resource('XObject',$obj->name,$obj); @@ -2346,6 +2332,7 @@ sub xo_form { my ($self)=@_; + require PDF::API2::Resource::XObject::Form::Hybrid; my $obj=PDF::API2::Resource::XObject::Form::Hybrid->new_api($self); $self->resource('XObject',$obj->name,$obj); @@ -2367,6 +2354,7 @@ sub egstate { my ($self)=@_; + require PDF::API2::Resource::ExtGState; my $obj=PDF::API2::Resource::ExtGState->new_api($self,pdfkey()); $self->resource('ExtGState',$obj->name,$obj); @@ -2384,6 +2372,7 @@ sub pattern { my ($self,%opts)=@_; + require PDF::API2::Resource::Pattern; my $obj=PDF::API2::Resource::Pattern->new_api($self,undef,%opts); $self->resource('Pattern',$obj->name,$obj); @@ -2401,6 +2390,7 @@ sub shading { my ($self,%opts)=@_; + require PDF::API2::Resource::Shading; my $obj=PDF::API2::Resource::Shading->new_api($self,undef,%opts); $self->resource('Shading',$obj->name,$obj); @@ -2418,6 +2408,7 @@ sub outlines { my ($self)=@_; + require PDF::API2::Outlines; $self->{pdf}->{Root}->{Outlines}||=PDF::API2::Outlines->new($self); my $obj=$self->{pdf}->{Root}->{Outlines}; @@ -2449,6 +2440,7 @@ unless(defined $obj) { + require PDF::API2::NamedDestination; $obj=PDF::API2::NamedDestination->new_api($self); } $root->{Names}->{$cat}->{-vals}->{$name}=$obj;

diff -urN -x fonts -x 'CJKFont*' -x CMap PDF-API2-0.73/lib/PDF/API2/Util.pm ../htdocs/cgi-bin/lib/PDF/API2/Util.pm --- PDF-API2-0.73/lib/PDF/API2/Util.pm 2005-11-16 03:16:00.000000000 +0100 +++ ../htdocs/cgi-bin/lib/PDF/API2/Util.pm 2009-04-02 15:15:16.000000000 +0200 @@ -49,10 +49,8 @@ $key_var2 %u2n %n2u - %u2n_o - %n2u_o $pua - $uuu + %prio %PaperSizes ); use Math::Trig; @@ -118,10 +116,6 @@ $pua=0xE000; - %u2n_o=(); - %n2u_o=(); - - $uuu={g=>{},u=>{}}; foreach my $dir (@INC) { if(-f "$dir/PDF/API2/Resource/uniglyph.txt") { @@ -134,28 +128,18 @@ $line=~s|\s+\#.+$||go; my ($uni,$name,$prio)=split(/\s+;\s+/,$line); $uni=hex($uni); - $uuu->{u}->{$uni}||=[]; - $uuu->{g}->{$name}||=[]; - push @{$uuu->{u}->{$uni}},{uni=>$uni,name=>$name,prio=>$prio}; - push @{$uuu->{g}->{$name}},{uni=>$uni,name=>$name,prio=>$prio}; + $u2n{$uni}||=$name; + if(!defined($prio{$name}) || $prio < $prio{$name}) + { + $n2u{$name}=$uni; + $prio{$name}=$prio; + } } close($fh); + %prio=(); last; } } - foreach my $k (sort {$a<=>$b} keys %{$uuu->{u}}) - { - $u2n_o{$k}=$uuu->{u}->{$k}->[0]->{name}; - } - foreach my $k (keys %{$uuu->{g}}) - { - my($r)=sort {$a->{prio}<=>$b->{prio}} @{$uuu->{g}->{$k}}; - $n2u_o{$k}=$r->{uni}; - } - $uuu=undef; - - %u2n=%u2n_o; - %n2u=%n2u_o; %colors=(); foreach my $dir (@INC) { @@ -706,8 +690,7 @@ } sub initNameTable { - %u2n=(); %u2n=%u2n_o; - %n2u=(); %n2u=%n2u_o; + die("not implemented"); $pua=0xE000; 1; }