pdf-reader 1.1.1 → 1.2.0

data/lib/pdf/reader/object_hash.rb

@@ -44,7 +44,7 @@ class PDF::Reader
       @pdf_version = read_version
       @xref        = PDF::Reader::XRef.new(@io)
       @trailer     = @xref.trailer
-      @cache       = PDF::Reader::ObjectCache.new
+      @cache       = opts[:cache] || PDF::Reader::ObjectCache.new
       @sec_handler = build_security_handler(opts)
     end
 

data/lib/pdf/reader/page.rb

@@ -20,14 +20,20 @@ module PDF
       # the raw PDF object that defines this page
       attr_reader :page_object
 
+      # a Hash-like object for storing cached data. Generally this is scoped to
+      # the current document and is used to avoid repeating expensive
+      # operations
+      attr_reader :cache
+
       # creates a new page wrapper.
       #
       # * objects - an ObjectHash instance that wraps a PDF file
       # * pagenum - an int specifying the page number to expose. 1 indexed.
       #
-      def initialize(objects, pagenum)
+      def initialize(objects, pagenum, options = {})
         @objects, @pagenum = objects, pagenum
         @page_object = objects.deref(objects.page_references[pagenum - 1])
+        @cache       = options[:cache] || {}
 
         unless @page_object.is_a?(::Hash)
           raise ArgumentError, "invalid page: #{pagenum}"

data/lib/pdf/reader/page_state.rb

@@ -22,6 +22,7 @@ module PDF
       # starting a new page
       def initialize(page)
         @page          = page
+        @cache         = page.cache
         @objects       = page.objects
         @font_stack    = [build_fonts(page.fonts)]
         @xobject_stack = [page.xobjects]
@@ -176,7 +177,7 @@ module PDF
         concatenate_matrix(*matrix) if matrix
 
         if xobject.hash[:Subtype] == :Form
-          form = PDF::Reader::FormXObject.new(@page, xobject)
+          form = PDF::Reader::FormXObject.new(@page, xobject, :cache => @cache)
           @font_stack.unshift(form.font_objects)
           @xobject_stack.unshift(form.xobjects)
           yield form if block_given?

data/lib/pdf/reader/stream.rb

@@ -58,7 +58,7 @@ class PDF::Reader
         end
 
         Array(hash[:Filter]).each_with_index do |filter, index|
-          @udata = Filter.new(filter, options[index]).filter(@udata)
+          @udata = Filter.with(filter, options[index]).filter(@udata)
         end
       end
       @udata

data/lib/pdf/reader/xref.rb

@@ -53,9 +53,11 @@ class PDF::Reader
     #
     def initialize (io)
       @io = io
+      @junk_offset = calc_junk_offset(io) || 0
       @xref = {}
       @trailer = load_offsets
     end
+
     ################################################################################
     # return the number of objects in this file. Objects with multiple generations are
     # only counter once.
@@ -93,6 +95,7 @@ class PDF::Reader
     #
     def load_offsets(offset = nil)
       offset ||= new_buffer.find_first_xref_offset
+      offset += @junk_offset
 
       buf = new_buffer(offset)
       tok_one = buf.token
@@ -124,7 +127,7 @@ class PDF::Reader
             generation = buf.token.to_i
             state = buf.token
 
-            store(objid, generation, offset) if state == "n" && offset > 0
+            store(objid, generation, offset + @junk_offset) if state == "n" && offset > 0
             objid += 1
             params.clear
           end
@@ -143,7 +146,7 @@ class PDF::Reader
     end
 
     ################################################################################
-    # Read a XReaf stream from the underlying buffer instead of a traditional xref table.
+    # Read an XRef stream from the underlying buffer instead of a traditional xref table.
     #
     def load_xref_stream(stream)
       unless stream.is_a?(PDF::Reader::Stream) && stream.hash[:Type] == :XRef
@@ -169,7 +172,7 @@ class PDF::Reader
           f2    = unpack_bytes(entry[widths[0],widths[1]])
           f3    = unpack_bytes(entry[widths[0]+widths[1],widths[2]])
           if f1 == 1 && f2 > 0
-            store(objid, f3, f2)
+            store(objid, f3, f2 + @junk_offset)
           elsif f1 == 2 && f2 > 0
             store(objid, 0, PDF::Reader::Reference.new(f2, 0))
           end
@@ -203,7 +206,7 @@ class PDF::Reader
     # Wrap the io stream we're working with in a buffer that can tokenise it for us.
     #
     # We create multiple buffers so we can be tokenising multiple sections of the file
-    # at the same time without worring about clearing the buffers contents.
+    # at the same time without worrying about clearing the buffers contents.
     #
     def new_buffer(offset = 0)
       PDF::Reader::Buffer.new(@io, :seek => offset)
@@ -214,6 +217,22 @@ class PDF::Reader
     def store (id, gen, offset)
       (@xref[id] ||= {})[gen] ||= offset
     end
+    ################################################################################
+    # Returns the offset of the PDF document in the +stream+. In theory this
+    # should always be 0, but all sort of crazy junk is prefixed to PDF files
+    # in the real world.
+    #
+    # Checks up to 50 chars into the file, returns nil if no PDF data detected.
+    #
+    def calc_junk_offset(io)
+      io.rewind
+      offset = io.pos
+      until (c = io.readchar) == '%' || c == 37 || offset > 50
+        offset += 1
+      end
+      io.rewind
+      offset < 50 ? offset : nil
+    end
   end
   ################################################################################
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-09 00:00:00.000000000 Z
+date: 2012-08-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &35841860 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *35841860
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: roodi
-  requirement: &35841400 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +37,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *35841400
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &35840900 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +53,15 @@ dependencies:
         version: '2.3'
   type: :development
   prerelease: false
-  version_requirements: *35840900
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
 - !ruby/object:Gem::Dependency
   name: ZenTest
-  requirement: &35840400 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,10 +69,15 @@ dependencies:
         version: 4.4.2
   type: :development
   prerelease: false
-  version_requirements: *35840400
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 4.4.2
 - !ruby/object:Gem::Dependency
   name: Ascii85
-  requirement: &35839940 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -65,18 +85,44 @@ dependencies:
         version: 1.0.0
   type: :runtime
   prerelease: false
-  version_requirements: *35839940
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.0.0
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
-  requirement: &35839520 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: hashery
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
   type: :runtime
   prerelease: false
-  version_requirements: *35839520
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
 description: The PDF::Reader library implements a PDF parser conforming as much as
   possible to the PDF specification from Adobe
 email:
@@ -93,54 +139,61 @@ extra_rdoc_files:
 - CHANGELOG
 - MIT-LICENSE
 files:
+- examples/extract_fonts.rb
+- examples/hash.rb
+- examples/extract_bates.rb
 - examples/metadata.rb
 - examples/extract_images.rb
-- examples/extract_bates.rb
-- examples/callbacks.rb
 - examples/rspec.rb
-- examples/hash.rb
-- examples/text.rb
-- examples/extract_fonts.rb
 - examples/page_count.rb
+- examples/callbacks.rb
+- examples/text.rb
 - examples/version.rb
-- lib/pdf/reader.rb
 - lib/pdf/hash.rb
-- lib/pdf/reader/print_receiver.rb
+- lib/pdf/reader.rb
 - lib/pdf/reader/xref.rb
-- lib/pdf/reader/buffer.rb
+- lib/pdf/reader/page.rb
+- lib/pdf/reader/encoding.rb
 - lib/pdf/reader/font.rb
-- lib/pdf/reader/parser.rb
-- lib/pdf/reader/error.rb
-- lib/pdf/reader/filter.rb
-- lib/pdf/reader/object_hash.rb
-- lib/pdf/reader/stream.rb
-- lib/pdf/reader/page_state.rb
-- lib/pdf/reader/standard_security_handler.rb
-- lib/pdf/reader/cmap.rb
-- lib/pdf/reader/form_xobject.rb
-- lib/pdf/reader/object_cache.rb
+- lib/pdf/reader/print_receiver.rb
+- lib/pdf/reader/lzw.rb
+- lib/pdf/reader/buffer.rb
 - lib/pdf/reader/object_stream.rb
-- lib/pdf/reader/encoding.rb
-- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/cmap.rb
 - lib/pdf/reader/text_receiver.rb
-- lib/pdf/reader/glyph_hash.rb
-- lib/pdf/reader/glyphlist.txt
-- lib/pdf/reader/lzw.rb
 - lib/pdf/reader/register_receiver.rb
-- lib/pdf/reader/page.rb
-- lib/pdf/reader/abstract_strategy.rb
-- lib/pdf/reader/pages_strategy.rb
-- lib/pdf/reader/reference.rb
-- lib/pdf/reader/encodings/standard.txt
+- lib/pdf/reader/page_text_receiver.rb
 - lib/pdf/reader/encodings/mac_roman.txt
+- lib/pdf/reader/encodings/zapf_dingbats.txt
 - lib/pdf/reader/encodings/symbol.txt
 - lib/pdf/reader/encodings/win_ansi.txt
-- lib/pdf/reader/encodings/zapf_dingbats.txt
-- lib/pdf/reader/encodings/pdf_doc.txt
 - lib/pdf/reader/encodings/mac_expert.txt
+- lib/pdf/reader/encodings/standard.txt
+- lib/pdf/reader/encodings/pdf_doc.txt
+- lib/pdf/reader/filter.rb
+- lib/pdf/reader/filter/null.rb
+- lib/pdf/reader/filter/flate.rb
+- lib/pdf/reader/filter/lzw.rb
+- lib/pdf/reader/filter/ascii85.rb
+- lib/pdf/reader/filter/ascii_hex.rb
+- lib/pdf/reader/filter/run_length.rb
+- lib/pdf/reader/filter/depredict.rb
+- lib/pdf/reader/object_hash.rb
+- lib/pdf/reader/reference.rb
+- lib/pdf/reader/glyphlist.txt
+- lib/pdf/reader/token.rb
+- lib/pdf/reader/parser.rb
+- lib/pdf/reader/page_state.rb
+- lib/pdf/reader/error.rb
+- lib/pdf/reader/glyph_hash.rb
 - lib/pdf/reader/resource_methods.rb
+- lib/pdf/reader/standard_security_handler.rb
+- lib/pdf/reader/form_xobject.rb
+- lib/pdf/reader/stream.rb
+- lib/pdf/reader/pages_strategy.rb
+- lib/pdf/reader/abstract_strategy.rb
 - lib/pdf/reader/metadata_strategy.rb
-- lib/pdf/reader/token.rb
+- lib/pdf/reader/object_cache.rb
 - lib/pdf-reader.rb
 - Rakefile
 - README.rdoc
@@ -181,7 +234,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.11
+rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: A library for accessing the content of PDF files