hexapdf 0.21.1 → 0.24.0

data/lib/hexapdf/layout/text_layouter.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -100,6 +100,10 @@ module HexaPDF
           :box
         end
 
+        def inspect #:nodoc:
+          "Box[#{@item.inspect}]"
+        end
+
       end
 
       # Used for layouting. Describes a glue item, i.e. an item describing white space that could
@@ -132,6 +136,10 @@ module HexaPDF
           :glue
         end
 
+        def inspect #:nodoc:
+          "Glue[#{@item.inspect}]"
+        end
+
       end
 
       # Used for layouting. Describes a penalty item, i.e. a point where a break is allowed.
@@ -173,6 +181,10 @@ module HexaPDF
           :penalty
         end
 
+        def inspect #:nodoc:
+          "Penalty[#{penalty} #{width} #{@item.inspect}]"
+        end
+
         # Singleton object describing a Penalty for a prohibited break.
         ProhibitedBreak = new(Penalty::INFINITY)
 
@@ -759,6 +771,9 @@ module HexaPDF
 
             # item didn't fit into first part, find next available part
             if line.items.empty? && line_fragments.empty?
+              # item didn't fit because no more height is available
+              next nil if actual_height + item.height > height
+
               old_height = actual_height
               while item.width > width_block.call(item.item) && actual_height <= height
                 width_spec_index += 1
@@ -815,7 +830,7 @@ module HexaPDF
           if too_wide_box && (too_wide_box.item.kind_of?(TextFragment) &&
                               too_wide_box.item.items.size > 1)
             rest[0..rest.index(too_wide_box)] = too_wide_box.item.items.map do |item|
-              Box.new(TextFragment.new([item], too_wide_box.item.style))
+              Box.new(TextFragment.new([item].freeze, too_wide_box.item.style))
             end
             too_wide_box = nil
           else
@@ -825,7 +840,12 @@ module HexaPDF
         end
 
         unless lines.empty?
-          lines.first.y_offset += initial_baseline_offset(lines, height, actual_height)
+          # Apply baseline offset only for non-variable width text
+          lines.first.y_offset += if width_block.arity == 1
+                                    lines.first.y_max
+                                  else
+                                    initial_baseline_offset(lines, height, actual_height)
+                                  end
         end
 
         Result.new(status, lines, rest)

data/lib/hexapdf/layout/text_shaper.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/layout/width_from_polygon.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -34,12 +34,16 @@
 # commercial licenses are available at <https://gettalong.at/hexapdf/>.
 #++
 
+require 'geom2d/utils'
+
 module HexaPDF
   module Layout
 
     # Utility class for generating width specifications for TextLayouter#fit from polygons.
     class WidthFromPolygon
 
+      include Geom2D::Utils
+
       # Creates a new object for the given polygon (or polygon set) and immediately prepares it so
       # that #call can be used.
       #
@@ -94,14 +98,15 @@ module HexaPDF
 
         @polygon_segments.each do |segments|
           temp_result = []
-          status = if segments.first[0].start_point.y > y2 || segments.first[0].start_point.y < y1
+          status = if float_compare(segments.first[0].start_point.y, y2) >= 0 ||
+                       float_compare(segments.first[0].start_point.y, y1) <= 0
                      :outside
                    else
                      :inside
                    end
 
           segments.each do |_segment, miny, maxy, minyx, maxyx, vertical, slope, intercept|
-            next unless miny < y2 && maxy > y1
+            next unless float_compare(miny, y2) < 0 && float_compare(maxy, y1) > 0
 
             if vertical
               min_x = max_x = minyx
@@ -111,9 +116,9 @@ module HexaPDF
               min_x, max_x = max_x, min_x if min_x > max_x
             end
 
-            if miny <= y1 && maxy >= y2 # segment crosses both lines
+            if float_compare(miny, y1) <= 0 && float_compare(maxy, y2) >= 0 # segment crosses both lines
               temp_result << [min_x, max_x, :crossed_both]
-            elsif miny <= y1 # segment crosses bottom line
+            elsif float_compare(miny, y1) <= 0 # segment crosses bottom line
               if status == :outside
                 temp_result << [min_x, max_x, :crossed_bottom]
                 status = :inside
@@ -127,7 +132,7 @@ module HexaPDF
                 temp_result << [min_x, max_x, :crossed_bottom]
                 status = :outside
               end
-            elsif maxy >= y2 # segment crosses top line
+            elsif float_compare(maxy, y2) >= 0 # segment crosses top line
               if status == :outside
                 temp_result << [min_x, max_x, :crossed_top]
                 status = :inside
@@ -199,7 +204,7 @@ module HexaPDF
       # Prepare the segments and other data for later use.
       def prepare(offset)
         @max_y = @polygon.bbox.max_y - offset
-        @polygon_segments = if @polygon.nr_of_contours > 1
+        @polygon_segments = if @polygon.respond_to?(:polygons)
                               @polygon.polygons.map {|polygon| process_polygon(polygon) }
                             else
                               [process_polygon(@polygon)]

data/lib/hexapdf/layout.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -50,9 +50,12 @@ module HexaPDF
     autoload(:TextLayouter, 'hexapdf/layout/text_layouter')
     autoload(:Box, 'hexapdf/layout/box')
     autoload(:Frame, 'hexapdf/layout/frame')
+    autoload(:BoxFitter, 'hexapdf/layout/box_fitter')
     autoload(:WidthFromPolygon, 'hexapdf/layout/width_from_polygon')
     autoload(:TextBox, 'hexapdf/layout/text_box')
     autoload(:ImageBox, 'hexapdf/layout/image_box')
+    autoload(:ColumnBox, 'hexapdf/layout/column_box')
+    autoload(:ListBox, 'hexapdf/layout/list_box')
 
   end
 

data/lib/hexapdf/name_tree_node.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/number_tree_node.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/object.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/parser.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -62,15 +62,9 @@ module HexaPDF
       @object_stream_data = {}
       @reconstructed_revision = nil
       @in_reconstruct_revision = false
-      @contains_xref_streams = false
       retrieve_pdf_header_offset_and_version
     end
 
-    # Returns +true+ if the PDF file contains cross-reference streams.
-    def contains_xref_streams?
-      @contains_xref_streams
-    end
-
     # Returns +true+ if the PDF file was damaged and could be reconstructed.
     def reconstructed?
       !@reconstructed_revision.nil?
@@ -241,7 +235,6 @@ module HexaPDF
           maybe_raise("Cross-reference stream doesn't contain entry for itself", pos: pos)
           xref_section.add_in_use_entry(obj.oid, obj.gen, pos)
         end
-        @contains_xref_streams = true
       end
       xref_section.delete(0)
       [xref_section, trailer]

data/lib/hexapdf/pdf_array.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/rectangle.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/reference.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/revision.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -82,6 +82,7 @@ module HexaPDF
       @loader = xref_section && (block || loader)
       @xref_section = xref_section || XRefSection.new
       @objects = HexaPDF::Utils::ObjectHash.new
+      @all_objects_loaded = false
     end
 
     # Returns the next free object number for adding an object to this revision.
@@ -209,7 +210,7 @@ module HexaPDF
     def each(only_loaded: false)
       return to_enum(__method__, only_loaded: only_loaded) unless block_given?
 
-      if defined?(@all_objects_loaded) || only_loaded
+      if @all_objects_loaded || only_loaded
         @objects.each {|_oid, _gen, data| yield(data) }
       else
         seen = {}
@@ -256,6 +257,12 @@ module HexaPDF
       self
     end
 
+    # Resets the revision by deleting all loaded and added objects from it.
+    def reset_objects
+      @objects = HexaPDF::Utils::ObjectHash.new
+      @all_objects_loaded = false
+    end
+
     private
 
     # Loads a single object from the associated cross-reference section.

data/lib/hexapdf/revisions.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -51,6 +51,10 @@ module HexaPDF
   # the newest revision the highest index. This is also the order in which the revisions get
   # written.
   #
+  # *Important*: It is possible to manipulate the individual revisions and their objects oneself but
+  # this should only be done if one is familiar with the inner workings of HexaPDF. Otherwise it is
+  # best to use the convenience methods of this class to create, access or delete indirect objects.
+  #
   # See: PDF1.7 s7.5.6, HexaPDF::Revision
   class Revisions
 
@@ -68,27 +72,26 @@ module HexaPDF
 
         revisions = []
         begin
-          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}
+          offset = parser.startxref_offset
+          seen_xref_offsets = {}
 
-          while (prev = revisions[0].trailer.value[:Prev]) &&
-              !seen_xref_offsets.key?(prev)
+          while offset && !seen_xref_offsets.key?(offset)
             # 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
+            xref_section, trailer = parser.load_revision(offset)
+            seen_xref_offsets[offset] = true
 
-            stm = revisions[0].trailer.value[:XRefStm]
+            stm = trailer[:XRefStm]
             if stm && !seen_xref_offsets.key?(stm)
               stm_xref_section, = parser.load_revision(stm)
-              xref_section.merge!(stm_xref_section)
+              stm_xref_section.merge!(xref_section)
+              xref_section = 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))
+            offset = trailer[:Prev]
           end
         rescue HexaPDF::MalformedPDFError
           reconstructed_revision = parser.reconstructed_revision
@@ -133,23 +136,154 @@ module HexaPDF
       end
     end
 
-    # Returns the revision at the specified index.
-    def revision(index)
-      @revisions[index]
+    # Returns the next object identifier that should be used when adding a new object.
+    def next_oid
+      @revisions.map(&:next_free_oid).max
+    end
+
+    # :call-seq:
+    #   revisions.object(ref)    -> obj or nil
+    #   revisions.object(oid)    -> obj or nil
+    #
+    # Returns the current version of the indirect object for the given exact reference or for the
+    # given object number.
+    #
+    # For references to unknown objects, +nil+ is returned but free objects are represented by a
+    # PDF Null object, not by +nil+!
+    #
+    # See: PDF1.7 s7.3.9
+    def object(ref)
+      i = @revisions.size - 1
+      while i >= 0
+        if (result = @revisions[i].object(ref))
+          return result
+        end
+        i -= 1
+      end
+      nil
+    end
+
+    # :call-seq:
+    #   revisions.object?(ref)    -> true or false
+    #   revisions.object?(oid)    -> true or false
+    #
+    # Returns +true+ if one of the revisions contains an indirect object for the given exact
+    # reference or for the given object number.
+    #
+    # Even though this method might return +true+ for some references, #object may return +nil+
+    # because this method takes *all* revisions into account.
+    def object?(ref)
+      @revisions.any? {|rev| rev.object?(ref) }
+    end
+
+    # :call-seq:
+    #   revisions.add_object(object)     -> object
+    #
+    # Adds the given HexaPDF::Object to the current revision and returns it.
+    #
+    # If +object+ is a direct object, an object number is automatically assigned.
+    def add_object(obj)
+      if obj.indirect? && (rev_obj = current.object(obj.oid))
+        if rev_obj.data == obj.data
+          return obj
+        else
+          raise HexaPDF::Error, "Can't add object because there is already " \
+            "an object with object number #{obj.oid}"
+        end
+      end
+
+      obj.oid = next_oid unless obj.indirect?
+      current.add(obj)
+    end
+
+    # :call-seq:
+    #   revisions.delete_object(ref)
+    #   revisions.delete_object(oid)
+    #
+    # Deletes the indirect object specified by an exact reference or by an object number.
+    def delete_object(ref)
+      @revisions.reverse_each do |rev|
+        if rev.object?(ref)
+          rev.delete(ref)
+          break
+        end
+      end
+    end
+
+    # :call-seq:
+    #   revisions.each_object(only_current: true, only_loaded: false) {|obj| block }      -> revisions
+    #   revisions.each_object(only_current: true, only_loaded: false) {|obj, rev| block } -> revisions
+    #   revisions.each_object(only_current: true, only_loaded: false)                     -> Enumerator
+    #
+    # Yields every object and optionally the revision it is in.
+    #
+    # If +only_loaded+ is +true+, only the already loaded objects of the PDF document are yielded.
+    # This does only matter when the document instance was created from an existing PDF document.
+    #
+    # By default, only the current version of each object is returned which implies that each object
+    # number is yielded exactly once. If the +only_current+ option is +false+, all stored objects
+    # from newest to oldest are returned, not only the current version of each object.
+    #
+    # The +only_current+ option can make a difference because the document can contain multiple
+    # revisions:
+    #
+    # * Multiple revisions may contain objects with the same object and generation numbers, e.g.
+    #   two (different) objects with oid/gen [3,0].
+    #
+    # * Additionally, there may also be objects with the same object number but different
+    #   generation numbers in different revisions, e.g. one object with oid/gen [3,0] and one with
+    #   oid/gen [3,1].
+    def each_object(only_current: true, only_loaded: false, &block)
+      unless block_given?
+        return to_enum(__method__, only_current: only_current, only_loaded: only_loaded)
+      end
+
+      yield_rev = (block.arity == 2)
+      oids = {}
+      @revisions.reverse_each do |rev|
+        rev.each(only_loaded: only_loaded) do |obj|
+          next if only_current && oids.include?(obj.oid)
+          yield_rev ? yield(obj, rev) : yield(obj)
+          oids[obj.oid] = true
+        end
+      end
+      self
     end
-    alias [] revision
 
     # Returns the current revision.
+    #
+    # *Note*: This method should only be used if one is familiar with the inner workings of HexaPDF
+    # *and the PDF specification.
     def current
       @revisions.last
     end
 
-    # Returns the number of HexaPDF::Revision objects managed by this object.
-    def size
-      @revisions.size
+    # Returns a list of all revisions.
+    #
+    # *Note*: This method should only be used if one is familiar with the inner workings of HexaPDF
+    # *and the PDF specification.
+    def all
+      @revisions
+    end
+
+    # :call-seq:
+    #   revisions.each {|rev| block }   -> revisions
+    #   revisions.each                  -> Enumerator
+    #
+    # Iterates over all revisions from oldest to current one.
+    #
+    # *Note*: This method should only be used if one is familiar with the inner workings of HexaPDF
+    # *and the PDF specification.
+    def each(&block)
+      return to_enum(__method__) unless block_given?
+      @revisions.each(&block)
+      self
     end
 
     # Adds a new empty revision to the document and returns it.
+    #
+    # *Note*: This method should only be used if one is familiar with the inner workings of HexaPDF
+    # *and the PDF specification.
     def add
       if @revisions.empty?
         trailer = {}
@@ -164,28 +298,6 @@ module HexaPDF
       rev
     end
 
-    # :call-seq:
-    #   revisions.delete(index)    -> rev or nil
-    #   revisions.delete(oid)      -> rev or nil
-    #
-    # Deletes a revision from the document, either by index or by specifying the revision object
-    # itself.
-    #
-    # Returns the deleted revision object, or +nil+ if the index was out of range or no matching
-    # revision was found.
-    #
-    # Regarding the index: The oldest revision has index 0 and the current revision the highest
-    # index!
-    def delete(index_or_rev)
-      if @revisions.length == 1
-        raise HexaPDF::Error, "A document must have a least one revision, can't delete last one"
-      elsif index_or_rev.kind_of?(Integer)
-        @revisions.delete_at(index_or_rev)
-      else
-        @revisions.delete(index_or_rev)
-      end
-    end
-
     # :call-seq:
     #   revisions.merge(range = 0..-1)    -> revisions
     #
@@ -206,17 +318,6 @@ module HexaPDF
       self
     end
 
-    # :call-seq:
-    #   revisions.each {|rev| block }   -> revisions
-    #   revisions.each                  -> Enumerator
-    #
-    # Iterates over all revisions from oldest to current one.
-    def each(&block)
-      return to_enum(__method__) unless block_given?
-      @revisions.each(&block)
-      self
-    end
-
   end
 
 end

data/lib/hexapdf/serializer.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/stream.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/task/dereference.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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