hexapdf 0.5.0 → 0.6.0

data/lib/hexapdf/number_tree_node.rb

@@ -47,7 +47,7 @@ module HexaPDF
     include Utils::SortedTreeNode
 
     define_field :Kids,   type: Array
-    define_field :Nums,  type: Array
+    define_field :Nums,   type: Array
     define_field :Limits, type: Array
 
     private

data/lib/hexapdf/parser.rb

@@ -228,7 +228,10 @@ module HexaPDF
 
         @tokenizer.skip_whitespace
         start.upto(start + number_of_entries - 1) do |oid|
-          pos, gen, type = @tokenizer.next_xref_entry
+          pos, gen, type = @tokenizer.next_xref_entry do |matched_size|
+            maybe_raise("Invalid cross-reference subsection entry", pos: @tokenizer.pos,
+                        force: matched_size == 20)
+          end
           if xref.entry?(oid)
             next
           elsif type == 'n'.freeze

data/lib/hexapdf/revisions.rb

@@ -67,15 +67,22 @@ module HexaPDF
         xref_section, trailer = parser.load_revision(parser.startxref_offset)
         revisions << Revision.new(document.wrap(trailer, type: :XXTrailer),
                                   xref_section: xref_section, loader: object_loader)
+        seen_xref_offsets = {parser.startxref_offset => true}
 
-
-        while (prev = revisions[0].trailer.value[:Prev])
+        while (prev = revisions[0].trailer.value[:Prev]) &&
+            !seen_xref_offsets.key?(prev)
           # PDF1.7 s7.5.5 states that :Prev needs to be indirect, Adobe's reference 3.4.4 says it
           # should be direct. Adobe's POV is followed here. Same with :XRefStm.
           xref_section, trailer = parser.load_revision(prev)
+          seen_xref_offsets[prev] = true
+
           stm = revisions[0].trailer.value[:XRefStm]
-          stm_xref_section, = parser.load_revision(stm) if stm
-          xref_section.merge!(stm_xref_section) if stm
+          if stm && !seen_xref_offsets.key?(stm)
+            stm_xref_section, = parser.load_revision(stm)
+            xref_section.merge!(stm_xref_section)
+            seen_xref_offsets[stm] = true
+          end
+
           revisions.unshift(Revision.new(document.wrap(trailer, type: :XXTrailer),
                                          xref_section: xref_section, loader: object_loader))
         end

data/lib/hexapdf/stream.rb

@@ -117,7 +117,7 @@ module HexaPDF
     define_field :Length,       type: Integer # not required, will be auto-filled when writing
     define_field :Filter,       type: [Symbol, Array]
     define_field :DecodeParms,  type: [Dictionary, Hash, Array]
-    define_field :F,            type: :FileSpec, version: '1.2'
+    define_field :F,            type: :Filespec, version: '1.2'
     define_field :FFilter,      type: [Symbol, Array], version: '1.2'
     define_field :FDecodeParms, type: [Dictionary, Hash, Array], version: '1.2'
     define_field :DL,           type: Integer
@@ -181,17 +181,16 @@ module HexaPDF
       source
     end
 
-    # Returns the encoder Fiber for the stream data.
+    # :call-seq:
+    #   stream.stream_encoder
     #
-    # The two arguments can be used to add additional filters for *only* this returned encoder
-    # Fiber. They should normally *not* be used and are here for use by the encryption facilities.
+    # Returns the encoder Fiber for the stream data.
     #
     # See the Filter module for more information on how to work with the fiber.
-    def stream_encoder(additional_filter = nil, additional_decode_parms = nil)
-      encoder_data = [additional_filter, document.unwrap(self[:Filter])].flatten.
-        zip([additional_decode_parms, document.unwrap(self[:DecodeParms])].flatten).
+    def stream_encoder(source = stream_source)
+      encoder_data = [document.unwrap(self[:Filter])].flatten.
+        zip([document.unwrap(self[:DecodeParms])].flatten).
         delete_if {|f, _| f.nil?}
-      source = stream_source
 
       if data.stream.kind_of?(StreamData)
         decoder_data = data.stream.filter.zip(data.stream.decode_parms)
@@ -249,7 +248,7 @@ module HexaPDF
     #
     # See: HexaPDF::Filter
     def filter_for_name(filter_name)
-      GlobalConfiguration.constantize('filter.map', filter_name) do
+      config.constantize('filter.map', filter_name) do
         raise HexaPDF::Error, "Unknown stream filter '#{filter_name}' encountered"
       end
     end

data/lib/hexapdf/tokenizer.rb

@@ -196,11 +196,13 @@ module HexaPDF
     # Reads the cross-reference subsection entry at the current position and advances the scan
     # pointer.
     #
+    # If a possible problem is detected, yields to caller.
+    #
     # See: PDF1.7 7.5.4
-    def next_xref_entry
+    def next_xref_entry #:yield: matched_size
       prepare_string_scanner(20)
-      unless @ss.skip(/(\d{10}) (\d{5}) ([nf])(?: \r| \n|\r\n)/)
-        raise HexaPDF::MalformedPDFError.new("Invalid cross-reference subsection entry", pos: pos)
+      unless @ss.skip(/(\d{10}) (\d{5}) ([nf])(?: \r| \n|\r\n|\r|\n)/) && @ss.matched_size == 20
+        yield(@ss.matched_size)
       end
       [@ss[1].to_i, @ss[2].to_i, @ss[3]]
     end

data/lib/hexapdf/type.rb

@@ -31,6 +31,9 @@
 # is created or manipulated using HexaPDF.
 #++
 
+require 'hexapdf/type/actions'
+require 'hexapdf/type/annotations'
+
 module HexaPDF
 
   # == Overview

data/lib/hexapdf/type/action.rb

@@ -0,0 +1,56 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/dictionary'
+
+module HexaPDF
+  module Type
+
+    # Represents a generic PDF action dictionary.
+    #
+    # Action dictionaries are used, for example, by annotations or outline items to specify the
+    # action that should be performed. Each action class should be defined under the Actions module.
+    #
+    # See: PDF1.7 s12.6
+    class Action < Dictionary
+
+      define_type :Action
+
+      define_field :Type, type: Symbol, default: self.type
+      define_field :S,    type: Symbol, required: true
+      define_field :Next, type: [Dictionary, Hash, Array], version: '1.2'
+
+    end
+
+  end
+end

data/lib/hexapdf/type/actions.rb

@@ -0,0 +1,52 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+module HexaPDF
+  module Type
+
+    autoload(:Action, 'hexapdf/type/action')
+
+    # Namespace module for all PDF action dictionary types.
+    #
+    # See: PDF1.7 s12.6.4, Action
+    module Actions
+
+      autoload(:GoTo, 'hexapdf/type/actions/go_to')
+      autoload(:GoToR, 'hexapdf/type/actions/go_to_r')
+      autoload(:Launch, 'hexapdf/type/actions/launch')
+      autoload(:URI, 'hexapdf/type/actions/uri')
+
+    end
+
+  end
+end

data/lib/hexapdf/type/actions/go_to.rb

@@ -0,0 +1,52 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/type/action'
+
+module HexaPDF
+  module Type
+    module Actions
+
+      # A Go-To action changes the view to a specific destination.
+      #
+      # See: PDF1.7 s12.6.4.2
+      class GoTo < Action
+
+        define_field :S, type: Symbol, required: true, default: :GoTo
+        define_field :D, type: [Symbol, PDFByteString, Array], required: true
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/type/actions/go_to_r.rb

@@ -0,0 +1,54 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/type/action'
+
+module HexaPDF
+  module Type
+    module Actions
+
+      # A remote Go-To action dictionary jumps to a destination in a different PDF file.
+      #
+      # See: PDF1.7 s12.6.4.3
+      class GoToR < Action
+
+        define_field :S,         type: Symbol, required: true, default: :GoToR
+        define_field :F,         type: :Filespec, required: true
+        define_field :D,         type: [Symbol, PDFByteString, Array], required: true
+        define_field :NewWindow, type: Boolean, version: '1.2'
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/type/actions/launch.rb

@@ -0,0 +1,73 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/type/action'
+
+module HexaPDF
+  module Type
+    module Actions
+
+      # A Launch action dictionary launches an application, opens a document or prints a document.
+      #
+      # See: PDF1.7 s12.6.4.5
+      class Launch < Action
+
+        # The type used for the /Win field of a Launch action dictionary.
+        class WinParameters < Dictionary
+
+          define_type :XXLaunchActionWinParameters
+
+          define_field :F, type: PDFByteString, required: true
+          define_field :D, type: PDFByteString
+          define_field :O, type: String
+          define_field :P, type: PDFByteString
+
+        end
+
+        define_field :S,         type: Symbol, required: true, default: :Launch
+        define_field :F,         type: :Filespec
+        define_field :Win,       type: :XXLaunchActionWinParameters
+        define_field :NewWindow, type: Boolean, version: '1.2'
+
+        private
+
+        def perform_validation #:nodoc:
+          super
+          yield("A Launch action needs a target") unless key?(:F) || key?(:Win)
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/type/actions/uri.rb

@@ -0,0 +1,65 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/type/action'
+
+module HexaPDF
+  module Type
+    module Actions
+
+      # Represents an URI action dictionary, mostly used for opening Internet pages.
+      #
+      # See: PDF1.7 s12.6.4.7
+      class URI < Action
+
+        define_field :S,     type: Symbol, required: true, default: :URI
+        define_field :URI,   type: String, required: true
+        define_field :IsMap, type: Boolean
+
+        private
+
+        def perform_validation #:nodoc:
+          super
+          unless self[:URI].ascii_only?
+            yield("URIs have to contain ASCII characters only", true)
+            uri = self[:URI].dup.force_encoding(Encoding::BINARY)
+            uri.encode!(Encoding::US_ASCII, fallback: ->(c) { "%#{c.ord.to_s(16).upcase}"})
+            self[:URI] = uri
+          end
+        end
+
+      end
+
+    end
+  end
+end