Class: PDFBeads::PDFBuilder
- Inherits:
-
Object
- Object
- PDFBeads::PDFBuilder
- Defined in:
- lib/pdfbeads/pdfbuilder.rb
Overview
The key class where the actual generation of a PDF file is performed.
Defined Under Namespace
Classes: Dict, Doc, FontDataProvider, PDFLabels, PDFTOC, XObj
Constant Summary collapse
- @@cmodes =
Hash[ 'BilevelType' => '/DeviceGray', 'GrayscaleType' => '/DeviceGray', 'PaletteType' => '/Indexed', 'PaletteMatteType' => '/Indexed', 'TrueColorType' => '/DeviceRGB', 'TrueColorMatteType' => '/DeviceRGB', 'ColorSeparationType' => '/DeviceCMYK', 'ColorSeparationMatteType' => '/DeviceCMYK', 'PaletteBilevelMatteType' => '/DeviceGray' ]
Instance Method Summary collapse
-
#initialize(pdfargs) ⇒ PDFBuilder
constructor
A new instance of PDFBuilder.
-
#output(outpath) ⇒ Object
Output the created PDF file to the disk.
- #process(pagefiles, st_format) ⇒ Object
Constructor Details
#initialize(pdfargs) ⇒ PDFBuilder
Returns a new instance of PDFBuilder.
57 58 59 60 61 62 63 64 65 |
# File 'lib/pdfbeads/pdfbuilder.rb', line 57 def initialize( pdfargs ) @pdfargs = pdfargs @now = Time.now() @doc = Doc.new() @fdata = FontDataProvider.new() @dictpath = '' @dictobj = nil end |
Instance Method Details
#output(outpath) ⇒ Object
Output the created PDF file to the disk.
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
# File 'lib/pdfbeads/pdfbuilder.rb', line 361 def output( outpath ) begin if outpath.eql? 'STDOUT' out = $stdout else out = File.open( outpath,'w' ) end out.binmode if /(win|w)32$/.match( RUBY_PLATFORM ) out.write( @doc.to_s ) out.close unless outpath.eql? 'STDOUT' rescue $stderr.puts( "Error: could not write to #{outpath}" ) end end |
#process(pagefiles, st_format) ⇒ Object
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 |
# File 'lib/pdfbeads/pdfbuilder.rb', line 67 def process( pagefiles,st_format ) labels = toc = nil labels = PDFLabels.new( @pdfargs[:labels] ) unless @pdfargs[:labels].nil? toc = PDFTOC.new( @pdfargs[:toc] ) unless @pdfargs[:toc].nil? = parseMeta( @pdfargs[:meta] ) reader = getPDFReader( @pdfargs[:textpdf] ) cat = XObj.new(Hash[ 'Type' => '/Catalog', 'PageLayout' => "/#{@pdfargs[:pagelayout]}" ]) @doc.addObject(cat) offsign = 'Z' if @now.gmt_offset > 0 offsign = "+" else offsign = "-" end creationDate = sprintf( "D:%04d%02d%02d%02d%02d%02d%s", @now.year, @now.month, @now.day, @now.hour, @now.min, @now.sec, offsign ) unless offsign.eql? 'Z' gmt_mins = @now.gmt_offset/60 creationDate << sprintf( "%02d'%02d", gmt_mins/60, gmt_mins%60 ) end info = XObj.new(Hash[ 'Creator' => "(PDFBeads)", 'Producer' => "(PDFBeads)", 'CreationDate' => "(#{creationDate})" ]) @doc.addObject(info) .each_key do |key| info.addToDict(key, "(\xFE\xFF#{[key].to_text})") end if ( toc != nil and toc.length > 0 ) or @pdfargs[:rtl] vpref = XObj.new(Hash.new()) vpref.addToDict('Direction', "/R2L") if @pdfargs[:rtl] @doc.addObject(vpref) cat.addToDict('ViewerPreferences', ref(vpref.getID)) end pages = XObj.new(Hash[ 'Type' => '/Pages' ]) @doc.addObject(pages) cat.addToDict('Pages', ref(pages.getID)) creator = XObj.new(Hash[ 'Subtype' => '/Artwork', 'Creator' => "(PDFBeads)", 'Feature' => '(Layers)' ]) @doc.addObject(creator) ocFore = XObj.new(Hash[ 'Type' => '/OCG', 'Name' => '(Foreground)', 'Usage' => "<</CreatorInfo #{ref(creator.getID)}>>", 'Intent' => '[/View/Design]' ]) @doc.addObject(ocFore) ocBack = XObj.new({ 'Type' => '/OCG', 'Name' => '(Background)', 'Usage' => "<</CreatorInfo #{ref(creator.getID)}>>", 'Intent' => '[/View/Design]' }) @doc.addObject(ocBack) cat.addToDict('OCProperties', sprintf("<< /OCGs[%s %s] /D<< /Intent /View /BaseState (ON) /Order[%s %s] >>>>", ref(ocFore.getID), ref(ocBack.getID), ref(ocFore.getID), ref(ocBack.getID))) page_objs = Array.new() pages_by_num = Hash.new() symd = nil font = nil pidx = 0 if labels != nil and labels.length > 0 nTree = "<</Nums[\n" labels.each do |rng| nTree << "#{rng[:first]} << " if rng.has_key? :prefix begin # If possible, use iso8859-1 (aka PDFDocEncoding) for page labels: # it is at least guaranteed to be safe if rng[:prefix].respond_to? :encode ltitl = rng[:prefix].encode( "iso8859-1", "utf-8" ) else ltitl = Iconv.iconv( "iso8859-1", "utf-8", rng[:prefix] ).first end nTree << "/P (#{ltitl.to_text}) " # Iconv::InvalidCharacter, Iconv::IllegalSequence, Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError rescue ltitl = Iconv.iconv( "utf-16be", "utf-8", rng[:prefix] ).first # If there is no number (just prefix) then put a zero character after the prefix: # this makes acroread happy, but prevents displaying the number in evince unless rng.has_key? :style nTree << "/P (\xFE\xFF#{ltitl.to_text}\x00\x00) " # Otherwise put a formally correct Unicode string, which, however, may stumble acroread else nTree << "/P (\xFE\xFF#{ltitl.to_text}) " end end end nTree << "/S /#{rng[:style]} " if rng.has_key? :style nTree << "/St #{rng[:start]}" if rng.has_key? :start nTree << ">>\n" end nTree << "]\n>>" cat.addToDict('PageLabels', nTree) cur_range_id = 0 end needs_font = false fonts = encodings = nil unless reader.nil? fdict = importPDFFonts( reader,@pdfargs[:textpdf] ) else pagefiles.each do |p| unless p.hocr_path.nil? needs_font = true break end end if needs_font fonts = Array.new() encodings = [ [' '] ] fdict = XObj.new( Hash[] ) @doc.addObject( fdict ) descr = XObj.new( Hash[ 'Type' => '/FontDescriptor', 'BaseFont' => '/Times-Roman', ] ) @fdata.header.each_key do |key| descr.addToDict( key,@fdata.header[key] ) end @doc.addObject( descr ) end end pagefiles.each do |p| procSet = ['/PDF', '/ImageB'] c_str = '' doc_objs = Array.new() lastimg = 0 width = p.width; height = p.height xres = p.x_res; yres = p.y_res pwidth = width.to_f / xres * 72 pheight = height.to_f / yres * 72 p.stencils.each do |s| if st_format.eql? 'JBIG2' xobj,width,height,xres,yres = loadJBIG2Page( s[:jbig2path],s[:jbig2dict],ref(ocFore.getID) ) else xobj,width,height,xres,yres = loadCCITTPage( s[:path],ref(ocFore.getID) ) end break if xobj.nil? color = s[:rgb].join(' ') << ' rg' doc_objs << xobj c_str << "#{color} /Im#{lastimg} Do " lastimg += 1 end fg_image = bg_image = nil fg_image = loadImage( p.fg_layer,ocFore.getID,procSet ) unless p.fg_layer.nil? bg_image = loadImage( p.bg_layer,ocBack.getID,procSet ) unless p.bg_layer.nil? contents = XObj.new(Hash[ 'Filter' => '/FlateDecode' ]) resobj = XObj.new(Hash.new()) resources = XObj.new(Hash[ 'XObject' => ref(resobj.getID) ]) unless fg_image.nil? xobj = doc_objs[0] fg_image.addToDict('SMask', ref(xobj.getID)) xobj.removeFromDict('ImageMask') xobj.addToDict('Decode', '[1 0]') resobj.addToDict('Im0', ref(fg_image.getID)) doc_objs << fg_image c_str = '/Im0 Do ' else doc_objs.each_index do |i| resobj.addToDict( "Im#{i}", ref(doc_objs[i].getID) ) end end unless bg_image.nil? c_str = "/Im#{resobj.dictLength} Do " << c_str resobj.addToDict( "Im#{resobj.dictLength}", ref(bg_image.getID) ) doc_objs << bg_image end c_str = sprintf( "q %.2f 0 0 %.2f 0 0 cm %sQ",pwidth,pheight,c_str ) doc_objs.concat( [contents, resobj, resources] ) hocr = nil if not reader.nil? procSet << '/Text' c_str << getPDFText( reader,pidx,@pdfargs[:debug] ) elsif not p.hocr_path.nil? hocr = open( p.hocr_path ) { |f| Nokogiri::HTML( f ) } procSet << '/Text' c_str << getHOCRText( hocr,pheight,72.0/xres,72.0/yres,encodings ) end unless @pdfargs[:debug] contents.reinit( Hash[ 'Filter' => '/FlateDecode' ], Zlib::Deflate.deflate( c_str,9 ) ) else contents.reinit( Hash[], c_str ) end resources.addToDict( 'ProcSet', "[ #{procSet.join(' ')} ]" ) resources.addToDict( 'Font', ref( fdict.getID ) ) unless hocr.nil? and reader.nil? page = XObj.new(Hash[ 'Type' => '/Page', 'Parent' => "#{pages.getID} 0 R", 'MediaBox' => sprintf( "[ 0 0 %.02f %.02f ]",pwidth,pheight ), 'Contents' => ref( contents.getID ), 'Resources' => ref( resources.getID ) ]) # By default acroread uses /DeviceCMYK as a transparency blending space, # so adding an SMask image to a page would result to colors being shifted, # uless we take a special care of this. For more details see # http://comments.gmane.org/gmane.comp.tex.pdftex/3747 unless fg_image.nil? cspace = '/DeviceRGB' cspace = fg_image.getFromDict( 'ColorSpace' ) if fg_image.hasInDict( 'ColorSpace' ) page.addToDict( 'Group', "<< /S /Transparency /CS #{cspace} >>" ) end doc_objs << page doc_objs.each{ |x| @doc.addObject(x) } page_objs << page pages.addToDict( 'Count', page_objs.length ) pages.addToDict( 'Kids', '[' << page_objs.map{|x| ref(x.getID).to_s}.join(' ') << ']' ) pkey = (pidx + 1).to_s pkey = labels.getPageLabel( cur_range_id,pidx ) if labels != nil and labels.length > 0 pages_by_num[pkey] = page.getID pidx += 1 if labels != nil and labels.length > 0 if cur_range_id < labels.length - 1 and labels[cur_range_id + 1][:first] == pidx cur_range_id += 1 end end $stderr.puts("Processed #{p.name}\n") $stderr.puts(" Added background image from #{p.bg_layer}\n") unless bg_image.nil? $stderr.puts(" Added foreground image from #{p.fg_layer}\n") unless fg_image.nil? end if needs_font fidx = 1 encodings.each do |enc| font = addFont( descr,enc,"Fnt#{fidx}" ) fdict.addToDict( "Fnt#{fidx}",ref(font.getID) ) fonts << font fidx += 1 end end if toc != nil and toc.length > 0 getOutlineObjs( toc,pages_by_num,page_objs[0].getID ) cat.addToDict('Outlines', ref(toc[0][:pdfobj].getID)) cat.addToDict('PageMode', "/UseOutlines") vpref.addToDict('NonFullScreenPageMode', "/UseOutlines") end if @pdfargs[:delfiles] pagefiles.each do |p| $stderr.puts( "Cleaning up temporary files for #{p.name}" ) safe_delete( p.fg_layer ) if p.fg_created safe_delete( p.bg_layer ) if p.bg_created p.stencils.each do |s| safe_delete( s[:path] ) if s[:created] end end end end |