hexapdf 0.6.0 → 0.7.0

data/lib/hexapdf/content/parser.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -41,7 +41,14 @@ module HexaPDF
     # More efficient tokenizer for content streams. This tokenizer class works directly on a
     # string and not on an IO.
     #
-    # Note: Indirect object references are *not* supported by this tokenizer!
+    # Changes:
+    #
+    # * Since a content stream is normally parsed front to back, a StopIteration error can be raised
+    #   instead of returning +NO_MORE_TOKENS+ once the end of the string is reached to avoid costly
+    #   checks in each iteration. If this behaviour is wanted, pass "raise_on_eos: true" in the
+    #   constructor.
+    #
+    # * Indirect object references are *not* supported by this tokenizer!
     #
     # See: PDF1.7 s7.2
     class Tokenizer < HexaPDF::Tokenizer #:nodoc:
@@ -50,9 +57,10 @@ module HexaPDF
       attr_reader :string
 
       # Creates a new tokenizer.
-      def initialize(string)
+      def initialize(string, raise_on_eos: false)
         @ss = StringScanner.new(string)
         @string = string
+        @raise_on_eos = raise_on_eos
       end
 
       # See: HexaPDF::Tokenizer#pos
@@ -104,10 +112,12 @@ module HexaPDF
         elsif byte == 123 || byte == 125 # { }
           Token.new(@ss.get_byte)
         elsif byte == 37 # %
-          return NO_MORE_TOKENS unless @ss.skip_until(/(?=[\r\n])/)
+          unless @ss.skip_until(/(?=[\r\n])/)
+            (@raise_on_eos ? (raise StopIteration) : (return NO_MORE_TOKENS))
+          end
           next_token
         elsif byte == -1
-          NO_MORE_TOKENS
+          @raise_on_eos ? raise(StopIteration) : NO_MORE_TOKENS
         else
           parse_keyword
         end
@@ -117,11 +127,11 @@ module HexaPDF
 
       # See: HexaPDF::Tokenizer#parse_number
       def parse_number
-        if (val = @ss.scan(/[+-]?\d++(?!\.)/))
-          val.to_i
-        elsif (val = @ss.scan(/[+-]?(?:\d+\.\d*|\.\d+)/))
-          val << '0'.freeze if val.getbyte(-1) == 46 # dot '.'
+        if (val = @ss.scan(/[+-]?(?:\d+\.\d*|\.\d+)/))
+          val << '0' if val.getbyte(-1) == 46 # dot '.'
           Float(val)
+        elsif (val = @ss.scan(/[+-]?\d++/))
+          val.to_i
         else
           parse_keyword
         end
@@ -133,7 +143,6 @@ module HexaPDF
 
     end
 
-
     # This class knows how to correctly parse a content stream.
     #
     # == Overview
@@ -156,11 +165,12 @@ module HexaPDF
 
       # Parses the contents and calls the processor object for each parsed operator.
       def parse(contents, processor)
-        tokenizer = Tokenizer.new(contents)
+        tokenizer = Tokenizer.new(contents, raise_on_eos: true)
         params = []
-        while (obj = tokenizer.next_object(allow_keyword: true)) != Tokenizer::NO_MORE_TOKENS
+        loop do
+          obj = tokenizer.next_object(allow_keyword: true)
           if obj.kind_of?(Tokenizer::Token)
-            if obj == 'BI'.freeze
+            if obj == 'BI'
               params = parse_inline_image(tokenizer)
             end
             processor.process(obj.to_sym, params)
@@ -179,15 +189,15 @@ module HexaPDF
       def parse_inline_image(tokenizer)
         # BI has already been read, so read the image dictionary
         dict = {}
-        while (key = tokenizer.next_object(allow_keyword: true))
-          if key == 'ID'.freeze
+        while (key = tokenizer.next_object(allow_keyword: true) rescue Tokenizer::NO_MORE_TOKENS)
+          if key == 'ID'
             break
           elsif key == Tokenizer::NO_MORE_TOKENS
             raise HexaPDF::Error, "EOS while trying to read dictionary key for inline image"
           elsif !key.kind_of?(Symbol)
             raise HexaPDF::Error, "Inline image dictionary keys must be PDF name objects"
           end
-          value = tokenizer.next_object
+          value = tokenizer.next_object rescue Tokenizer::NO_MORE_TOKENS
           if value == Tokenizer::NO_MORE_TOKENS
             raise HexaPDF::Error, "EOS while trying to read dictionary value for inline image"
           end
@@ -213,7 +223,7 @@ module HexaPDF
           # Check if we found EI inside of the image data
           count = 0
           while count < MAX_TOKEN_CHECK
-            token = tokenizer.next_object(allow_keyword: true) rescue break
+            token = tokenizer.next_object(allow_keyword: true) rescue Tokenizer::NO_MORE_TOKENS
             if token == Tokenizer::NO_MORE_TOKENS
               count += MAX_TOKEN_CHECK
             elsif token.kind_of?(Tokenizer::Token) &&

data/lib/hexapdf/content/processor.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -145,7 +145,6 @@ module HexaPDF
 
       end
 
-
       # Represents a box composed of GlyphBox objects.
       #
       # The bounding box methods #lower_left, #lower_right, #upper_left, #upper_right are computed
@@ -387,10 +386,10 @@ module HexaPDF
       # text strings together with positioning information (+TJ+ operator).
       def decode_text(data)
         if data.kind_of?(Array)
-          data = data.each_with_object(''.b) {|obj, result| result << obj if obj.kind_of?(String)}
+          data = data.each_with_object(''.b) {|obj, result| result << obj if obj.kind_of?(String) }
         end
         font = graphics_state.font
-        font.decode(data).map {|code_point| font.to_utf8(code_point)}.join('')
+        font.decode(data).map {|code_point| font.to_utf8(code_point) }.join('')
       end
 
       # Decodes the given text object and returns it as a CompositeBox object.

data/lib/hexapdf/content/transformation_matrix.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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/data_dir.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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/dictionary.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -130,7 +130,6 @@ module HexaPDF
       defined?(@type) && @type
     end
 
-
     # Returns the value for the given dictionary entry.
     #
     # This method should be used instead of direct access to the value because it provides
@@ -150,14 +149,14 @@ module HexaPDF
       field = self.class.field(name)
       data = if key?(name)
                value[name]
-             elsif field && field.default?
+             elsif field&.default?
                value[name] = field.default
              end
       value[name] = data = document.deref(data) if data.kind_of?(HexaPDF::Reference)
       if data.class == HexaPDF::Object || (data.kind_of?(HexaPDF::Object) && data.value.nil?)
         data = data.value
       end
-      self[name] = data = field.convert(data, document) if field && field.convert?(data)
+      self[name] = data = field.convert(data, document) if field&.convert?(data)
       data
     end
 
@@ -199,7 +198,7 @@ module HexaPDF
     # Note that the yielded value is already preprocessed like in #[].
     def each
       return to_enum(__method__) unless block_given?
-      value.each_key {|name| yield(name, self[name])}
+      value.each_key {|name| yield(name, self[name]) }
       self
     end
 
@@ -244,7 +243,7 @@ module HexaPDF
 
     # Iterates over all currently set fields and those that are required.
     def each_set_key_or_required_field #:yields: name, field
-      value.each_key {|name| yield(name, self.class.field(name))}
+      value.each_key {|name| yield(name, self.class.field(name)) }
       self.class.each_field do |name, field|
         yield(name, field) if field.required? && !value.key?(name)
       end
@@ -287,11 +286,11 @@ module HexaPDF
           obj = value[name] # we need the unwrapped object!
           if field.indirect && (!obj.kind_of?(HexaPDF::Object) || !obj.indirect?)
             yield("Field #{name} needs to be an indirect object", true)
-            value[name] = obj = document.add(obj)
+            value[name] = document.add(obj)
           elsif !field.indirect && obj.kind_of?(HexaPDF::Object) && obj.indirect?
             yield("Field #{name} needs to be a direct object", true)
             document.delete(obj)
-            value[name] = obj = obj.value
+            value[name] = obj.value
           end
         end
       end

data/lib/hexapdf/dictionary_fields.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -94,10 +94,9 @@ module HexaPDF
       # two converters could potentially be used for the same type, the one that appears earlier
       # is used.
       def self.converter_for(type)
-        @converters.find {|converter| converter.usable_for?(type)}
+        @converters.find {|converter| converter.usable_for?(type) }
       end
 
-
       # Returns +true+ if the value for this field needs to be an indirect object, +false+ if it
       # needs to be a direct object or +nil+ if it can be either.
       attr_reader :indirect
@@ -123,7 +122,7 @@ module HexaPDF
         @type.concat(Array(@converter.additional_types))
         @type.map! do |type|
           if type.kind_of?(Symbol)
-            HexaPDF::GlobalConfiguration.constantize('object.type_map'.freeze, type)
+            HexaPDF::GlobalConfiguration.constantize('object.type_map', type)
           else
             type
           end
@@ -158,8 +157,8 @@ module HexaPDF
 
       # Returns +true+ if the given object is valid for this field.
       def valid_object?(obj)
-        type.any? {|t| obj.kind_of?(t)} ||
-          (obj.kind_of?(HexaPDF::Object) && type.any? {|t| obj.value.kind_of?(t)})
+        type.any? {|t| obj.kind_of?(t) } ||
+          (obj.kind_of?(HexaPDF::Object) && type.any? {|t| obj.value.kind_of?(t) })
       end
 
       # If a converter was defined, it is used. Otherwise +false+ is returned.
@@ -307,7 +306,7 @@ module HexaPDF
 
       # Returns +true+ if the given data should be converted to a Time object.
       def self.convert?(data, _type)
-        data.kind_of?(String) && data =~ DATE_RE
+        data.kind_of?(String) && data.match?(DATE_RE)
       end
 
       # Converts the string into a Time object.
@@ -320,7 +319,6 @@ module HexaPDF
 
     end
 
-
     # Converter module for file specification fields. A file specification in string format is
     # converted to the corresponding file specification dictionary.
     module FileSpecificationConverter
@@ -349,7 +347,6 @@ module HexaPDF
 
     end
 
-
     # Converter module for fields of type Rectangle.
     module RectangleConverter
 

data/lib/hexapdf/document.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -129,11 +129,11 @@ module HexaPDF
       @version = '1.2'
 
       @revisions = Revisions.from_io(self, io)
-      if encrypted? && @config['document.auto_decrypt']
-        @security_handler = Encryption::SecurityHandler.set_up_decryption(self, decryption_opts)
-      else
-        @security_handler = nil
-      end
+      @security_handler = if encrypted? && @config['document.auto_decrypt']
+                            Encryption::SecurityHandler.set_up_decryption(self, decryption_opts)
+                          else
+                            nil
+                          end
 
       @listeners = {}
       @cache = Hash.new {|h, k| h[k] = {} }
@@ -178,7 +178,7 @@ module HexaPDF
     # because this method takes *all* revisions into account. Also see the discussion on #each for
     # more information.
     def object?(ref)
-      @revisions.any? {|rev| rev.object?(ref)}
+      @revisions.any? {|rev| rev.object?(ref) }
     end
 
     # :call-seq:
@@ -241,7 +241,7 @@ module HexaPDF
       when :current
         @revisions.current.delete(ref, mark_as_free: mark_as_free)
       when :all
-        @revisions.each {|rev| rev.delete(ref, mark_as_free: mark_as_free)}
+        @revisions.each {|rev| rev.delete(ref, mark_as_free: mark_as_free) }
       else
         raise ArgumentError, "Unsupported option revision: #{revision}"
       end
@@ -318,14 +318,14 @@ module HexaPDF
         type = (klass <= HexaPDF::Dictionary ? klass.type : nil)
       else
         type ||= deref(data.value[:Type]) if data.value.kind_of?(Hash)
-        klass = GlobalConfiguration.constantize('object.type_map'.freeze, type) { nil } if type
+        klass = GlobalConfiguration.constantize('object.type_map', type) { nil } if type
       end
 
       if data.value.kind_of?(Hash)
         subtype ||= deref(data.value[:Subtype]) || deref(data.value[:S])
       end
       if subtype
-        klass = GlobalConfiguration.constantize('object.subtype_map'.freeze, type, subtype) { klass }
+        klass = GlobalConfiguration.constantize('object.subtype_map', type, subtype) { klass }
       end
 
       klass ||= if data.stream
@@ -354,10 +354,10 @@ module HexaPDF
       case object
       when Hash
         seen[object] = true
-        object.each_with_object({}) {|(key, val), memo| memo[key] = unwrap(val, seen.dup)}
+        object.each_with_object({}) {|(key, val), memo| memo[key] = unwrap(val, seen.dup) }
       when Array
         seen[object] = true
-        object.map {|inner_o| unwrap(inner_o, seen.dup)}
+        object.map {|inner_o| unwrap(inner_o, seen.dup) }
       when HexaPDF::PDFData
         seen[object] = true
         unwrap(object.value, seen.dup)
@@ -415,7 +415,7 @@ module HexaPDF
 
     # Dispatches the message +name+ with the given arguments to all registered listeners.
     def dispatch_message(name, *args)
-      @listeners[name] && @listeners[name].each {|obj| obj.call(*args)}
+      @listeners[name]&.each {|obj| obj.call(*args) }
     end
 
     # Caches the value or the return value of the given block using the given Object::PDFData and
@@ -477,7 +477,7 @@ module HexaPDF
     #
     # See Task for more information.
     def task(name, **opts, &block)
-      task = config.constantize('task.map'.freeze, name) do
+      task = config.constantize('task.map', name) do
         raise HexaPDF::Error, "No task named '#{name}' is available"
       end
       task.call(self, **opts, &block)
@@ -501,14 +501,14 @@ module HexaPDF
     #
     # See: PDF1.7 s7.2.2
     def version
-      catalog_version = (catalog[:Version] || '1.0'.freeze).to_s
+      catalog_version = (catalog[:Version] || '1.0').to_s
       (@version < catalog_version ? catalog_version : @version)
     end
 
     # Sets the version of the PDF document. The argument must be a string in the format 'M.N'
     # where M is the major version and N the minor version (e.g. '1.4' or '2.0').
     def version=(value)
-      raise ArgumentError, "PDF version must follow format M.N" unless value.to_s =~ /\A\d\.\d\z/
+      raise ArgumentError, "PDF version must follow format M.N" unless value.to_s.match?(/\A\d\.\d\z/)
       @version = value.to_s
     end
 
@@ -615,7 +615,7 @@ module HexaPDF
       dispatch_message(:before_write)
 
       if file_or_io.kind_of?(String)
-        File.open(file_or_io, 'w+') {|file| Writer.write(self, file)}
+        File.open(file_or_io, 'w+') {|file| Writer.write(self, file) }
       else
         Writer.write(self, file_or_io)
       end

data/lib/hexapdf/document/files.rb

@@ -1,10 +1,10 @@
-# -*- encoding: utf-8 -*-
+# -*- encoding: utf-8; frozen_string_literal: true -*-
 #
 #--
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2017 Thomas Leitner
+# Copyright (C) 2014-2018 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
@@ -49,8 +49,8 @@ module HexaPDF
       end
 
       # :call-seq:
-      #   files.add(filename, name: File.basename(filename), description: nil, embed: true) -> file_spec
-      #   files.add(io, name:, description: nil)                      -> file_spec
+      #   files.add(filename, name: nil, description: nil, embed: true) -> file_spec
+      #   files.add(io, name:, description: nil)                        -> file_spec
       #
       # Adds the file or IO to the PDF document and returns the corresponding file specification
       # object.
@@ -58,8 +58,11 @@ module HexaPDF
       # Options:
       #
       # name::
-      #     The name that should be used for the file path. This name is also for registering the
-      #     file in the EmbeddedFiles name tree.
+      #     The name that should be used for the file path. This name is also used for registering
+      #     the file in the EmbeddedFiles name tree.
+      #
+      #     When a filename is given, the basename of the file is used by default for +name+ if it
+      #     is not specified.
       #
       # description::
       #     A description of the file.
@@ -104,14 +107,13 @@ module HexaPDF
         else
           seen = {}
           tree = @document.catalog[:Names] && @document.catalog[:Names][:EmbeddedFiles]
-          tree.each_entry do |_, spec|
+          tree&.each_entry do |_, spec|
             seen[spec] = true
             yield(spec)
-          end if tree
+          end
 
           @document.pages.each do |page|
-            next unless page[:Annots]
-            page[:Annots].each do |annot|
+            page[:Annots]&.each do |annot|
               annot = @document.deref(annot)
               next unless annot[:Subtype] == :FileAttachment
               spec = @document.deref(annot[:FS])