pdf-reader 1.4.1 → 2.0.0.beta1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: fb8a5be7c95212f559bb4d26af5fbdb484d21e77
-  data.tar.gz: f8fe70bf868dfff03b47a0b81993d1e680593e84
+  metadata.gz: f4ea96ce79d9f4cc65a0a026ea7e50da7b33cd19
+  data.tar.gz: e2302c2d18cdc64cd81654f30658b5cf1e8ae3c3
 SHA512:
-  metadata.gz: b881cecddfa41e3ad15dcafd31d4109290c664d0cf06478f3af6769aa7ced108e3ba082db54c6759c117d7559cc118e0d3a971c17b59cb23bf4e50024089fa6b
-  data.tar.gz: 50d61b135d79840dce5e5ca712b5db5185deefeee5de13d2adc63c1a8e1eb4b383bb0e8bb491c03bea49d11c4edf130b0fdb3b2eafea63ee0b85ca0390e047a0
+  metadata.gz: 31da13f8b8e38dffbb19a33855beb1c85a14c2633137fd8e1957db14f3bac16a434c174e79bab6092c72954e6a6f87f0ab585562e79d39d5ede8f9398fd63f7b
+  data.tar.gz: e097e8aed8bbeb918676bacded748a538e109fdcf1e8740cfe1ce3d63105d891cbe2a90ad228bb87fb494cd796bd7e1c66138592ff21d62c97b87fa270eb0899

data/CHANGELOG

@@ -1,5 +1,10 @@
+v2.0.0.beta1 (15th February 2017)
+- BREAKING CHANGE: remove all methods that were deprecated in 1.0.0
+- Bug: Support extra encrypted PDF variants (thanks to Gyuchang Jun)
+- various bug fixes
+
 v1.4.1 (2nd January 2017)
-- improve compatability with ruby 2.4 (thanks Akira Matsuda)
+- improve compatibility with ruby 2.4 (thanks Akira Matsuda)
 - various bug fixes
 
 v1.4.0 (22nd February 2016)
@@ -91,10 +96,10 @@ v0.9.2 (24th April 2011)
 
 v0.9.1 (21st December 2010)
 - force gem to only install on ruby 1.8.7 or higher
-  - maintaining supprot for earlier versions takes more time than I have
+  - maintaining support for earlier versions takes more time than I have
     available at the moment
 - bug: fix parsing of obscure pdf name format
-- bug: fix behaviour when loaded in confunction with htmldoc gem
+- bug: fix behaviour when loaded in conjunction with htmldoc gem
 
 v0.9.0 (19th November 2010)
 - support for pdf 1.5+ files that use object and xref streams

data/{README.rdoc → README.md}

@@ -1,4 +1,4 @@
-= Release Notes
+# Release Notes
 
 The PDF::Reader library implements a PDF parser conforming as much as possible
 to the PDF specification from Adobe.
@@ -15,46 +15,55 @@ higher level functionality - it's not going to render a PDF for you. There are
 a few exceptions to support very common use cases like extracting text from a
 page.
 
-= Installation
+# Installation
 
 The recommended installation method is via Rubygems.
 
+```ruby
   gem install pdf-reader
+```
 
-= Usage
+# Usage
 
 Begin by creating a PDF::Reader instance that points to a PDF file. Document
 level information (metadata, page count, bookmarks, etc) is available via
 this object.
 
+```ruby
     reader = PDF::Reader.new("somefile.pdf")
 
     puts reader.pdf_version
     puts reader.info
     puts reader.metadata
     puts reader.page_count
+ ```
 
 PDF::Reader.new accepts an IO stream or a filename. Here's an example with
 an IO stream:
 
+```ruby
     require 'open-uri'
 
     io     = open('http://example.com/somefile.pdf')
     reader = PDF::Reader.new(io)
     puts reader.info
+ ```
 
 If you open a PDF with File#open or IO#open, I strongly recommend using "rb"
 mode to ensure the file isn't mangled by ruby being 'helpful'. This is
 particularly important on windows and MRI >= 1.9.2.
 
+```ruby
     File.open("somefile.pdf", "rb") do |io|
       reader = PDF::Reader.new(io)
       puts reader.info
     end
+ ```
 
 PDF is a page based file format, so most visible information is available via
 page-based iteration
 
+```ruby
     reader = PDF::Reader.new("somefile.pdf")
 
     reader.pages.each do |page|
@@ -62,10 +71,12 @@ page-based iteration
       puts page.text
       puts page.raw_content
     end
+```
 
 If you need to access the full program for rendering a page, use the walk() method
 of PDF::Reader::Page.
 
+```ruby
     class RedGreenBlue
       def set_rgb_color_for_nonstroking(r, g, b)
         puts "R: #{r}, G: #{g}, B: #{b}"
@@ -76,31 +87,32 @@ of PDF::Reader::Page.
     page     = reader.page(1)
     receiver = RedGreenBlue.new
     page.walk(receiver)
+```
 
 For low level access to the objects in a PDF file, use the ObjectHash class like
 so:
 
+```ruby
     reader  = PDF::Reader.new("somefile.pdf")
     puts reader.objects.inspect
+```
 
-= Text Encoding
+# Text Encoding
 
 Regardless of the internal encoding used in the PDF all text will be converted
 to UTF-8 before it is passed back from PDF::Reader.
 
-Strings that contain binary data (like font blobs) will be marked as such on
-M17N aware VMs.
+Strings that contain binary data (like font blobs) will be marked as such.
 
-= Former API
+# Former API
 
 Version 1.0.0 of PDF::Reader introduced a new page-based API that provides
 efficient and easy access to any page.
 
-The previous API is marked as deprecated but will continue to work for the
-time being. Eventually calls to the old API will begin triggering deprecation
-warnings before it is completely removed in version 2.0.0.
+The pre-1.0 API was deprecated during the 1.x release series, and has been
+removed from 2.0.0.
 
-= Exceptions
+# Exceptions
 
 There are two key exceptions that you will need to watch out for when processing a
 PDF file:
@@ -120,7 +132,7 @@ don't, 'rescue MalformedPDFError' will catch all the subclassed errors as well.
 Any other exceptions should be considered bugs in either PDF::Reader (please
 report it!).
 
-= PDF Integrity
+# PDF Integrity
 
 Windows developers may run into problems when running specs due to MalformedPDFError's
 This is usually because CRLF characters are automatically added to some of the PDF's in
@@ -128,18 +140,20 @@ the spec folder when you checkout a branch from Git.
 
 To remove any invalid CRLF characters added while checking out a branch from Git, run:
 
+```ruby
     rake fix_integrity
+```
 
-= Maintainers
+# Maintainers
 
-- James Healy <mailto:jimmy@deefa.com>
+* James Healy <mailto:jimmy@deefa.com>
 
-= Licensing
+# Licensing
 
 This library is distributed under the terms of the MIT License. See the included file for
 more detail.
 
-= Mailing List
+# Mailing List
 
 Any questions or feedback should be sent to the PDF::Reader google group. It's
 better that any answers be available for others instead of hiding in someone's
@@ -147,20 +161,23 @@ inbox.
 
 http://groups.google.com/group/pdf-reader
 
-= Examples
+# Examples
 
 The easiest way to explain how this works in practice is to show some examples.
 Check out the examples/ directory for a few files.
 
-= Known Limitations
+# Known Limitations
 
 Occasionally some text cannot be extracted properly due to the way it has been
 stored, or the use of invalid bytes. In these cases PDF::Reader will output a
 little UTF-8 friendly box to indicate an unrecognisable character.
 
-= Resources
+# Resources
 
-- PDF::Reader Code Repository: http://github.com/yob/pdf-reader
-- PDF Specification: http://www.adobe.com/devnet/pdf/pdf_reference.html
-- PDF Tutorial Slide Presentations: http://home.comcast.net/~jk05/presentations/PDFTutorials.html
-- Developing with PDF (book): http://shop.oreilly.com/product/0636920025269.do
+* PDF::Reader Code Repository: http://github.com/yob/pdf-reader
+
+* PDF Specification: http://www.adobe.com/devnet/pdf/pdf_reference.html
+
+* PDF Tutorial Slide Presentations: http://home.comcast.net/~jk05/presentations/PDFTutorials.html
+
+* Developing with PDF (book): http://shop.oreilly.com/product/0636920025269.do

data/Rakefile

@@ -14,7 +14,7 @@ desc "Run cane to check quality metrics"
 Cane::RakeTask.new(:quality) do |cane|
   cane.abc_max = 20
   cane.style_measure = 100
-  cane.max_violations = 93
+  cane.max_violations = 31
 
   cane.use Morecane::EncodingCheck, :encoding_glob => "{app,lib,spec}/**/*.rb"
 end
@@ -41,7 +41,7 @@ end
 desc "Create a YAML file of integrity info for PDFs in the spec suite"
 task :integrity_yaml do
   data = {}
-  Dir.glob("spec/data/**/*.*").each do |path|
+  Dir.glob("spec/data/**/*.*").sort.each do |path|
     path_without_spec = path.gsub("spec/","")
     data[path_without_spec] = {
       :bytes => File.size(path),

data/bin/pdf_object

@@ -25,7 +25,10 @@ gen = gen.to_i
 
 # make magic happen
 begin
-  obj = PDF::Reader.object_file(filename, id, gen)
+  obj = nil
+  PDF::Reader.open(filename) do |pdf|
+    obj = pdf.objects[PDF::Reader::Reference.new(id, gen)]
+  end
 
   case obj
   when Hash, Array

data/lib/pdf/reader.rb

@@ -110,16 +110,10 @@ module PDF
     #
     #   reader = PDF::Reader.new("somefile.pdf", :password => "apples")
     #
-    def initialize(input = nil, opts = {})
-      if input # support the deprecated Reader API
-        @cache   = PDF::Reader::ObjectCache.new
-        opts.merge!(:cache => @cache)
-        @objects = PDF::Reader::ObjectHash.new(input, opts)
-      else
-        msg  = "Calling PDF::Reader#new with no arguments is deprecated and will be removed "
-        msg += "in the 2.0 release"
-        $stderr.puts(msg)
-      end
+    def initialize(input, opts = {})
+      @cache   = PDF::Reader::ObjectCache.new
+      opts.merge!(:cache => @cache)
+      @objects = PDF::Reader::ObjectHash.new(input, opts)
     end
 
     def info
@@ -133,7 +127,7 @@ module PDF
         nil
       else
         xml = stream.unfiltered_data
-        xml.force_encoding("utf-8") if xml.respond_to?(:force_encoding)
+        xml.force_encoding("utf-8")
         xml
       end
     end
@@ -164,61 +158,6 @@ module PDF
       yield PDF::Reader.new(input, opts)
     end
 
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    #
-    # Parse the file with the given name, sending events to the given receiver.
-    #
-    def self.file(name, receivers, opts = {})
-      msg  = "PDF::Reader#file is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      File.open(name,"rb") do |f|
-        new.parse(f, receivers, opts)
-      end
-    end
-
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    # Parse the given string, sending events to the given receiver.
-    #
-    def self.string(str, receivers, opts = {})
-      msg  = "PDF::Reader#string is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      StringIO.open(str) do |s|
-        new.parse(s, receivers, opts)
-      end
-    end
-
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    # Parse the file with the given name, returning an unmarshalled ruby version of
-    # represents the requested pdf object
-    #
-    def self.object_file(name, id, gen = 0)
-      msg  = "PDF::Reader#object_file is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      File.open(name,"rb") { |f|
-        new.object(f, id.to_i, gen.to_i)
-      }
-    end
-
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    # Parse the given string, returning an unmarshalled ruby version of represents
-    # the requested pdf object
-    #
-    def self.object_string(str, id, gen = 0)
-      msg  = "PDF::Reader#object_string is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      StringIO.open(str) { |s|
-        new.object(s, id.to_i, gen.to_i)
-      }
-    end
-
     # returns an array of PDF::Reader::Page objects, one for each
     # page in the source PDF.
     #
@@ -259,40 +198,6 @@ module PDF
       PDF::Reader::Page.new(@objects, num, :cache => @cache)
     end
 
-
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    # Given an IO object that contains PDF data, parse it.
-    #
-    def parse(io, receivers, opts = {})
-      msg  = "PDF::Reader#parse is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      ohash    = ObjectHash.new(io)
-
-      options = {:pages => true, :raw_text => false, :metadata => true}
-      options.merge!(opts)
-
-      strategies.each do |s|
-        s.new(ohash, receivers, options).process
-      end
-
-      self
-    end
-
-    # DEPRECATED: this method was deprecated in version 1.0.0 and will
-    #             eventually be removed
-    #
-    # Given an IO object that contains PDF data, return the contents of a single object
-    #
-    def object(io, id, gen)
-      msg  = "PDF::Reader#object is deprecated and will be removed in the 2.0 release"
-      $stderr.puts(msg)
-      @objects = ObjectHash.new(io)
-
-      @objects.deref(Reference.new(id, gen))
-    end
-
     private
 
     # recursively convert strings from outside a content stream into UTF-8
@@ -321,7 +226,7 @@ module PDF
     # TODO find a PDF I can use to spec this behaviour
     #
     def pdfdoc_to_utf8(obj)
-      obj.force_encoding("utf-8") if obj.respond_to?(:force_encoding)
+      obj.force_encoding("utf-8")
       obj
     end
 
@@ -331,17 +236,10 @@ module PDF
     def utf16_to_utf8(obj)
       str = obj[2, obj.size]
       str = str.unpack("n*").pack("U*")
-      str.force_encoding("utf-8") if str.respond_to?(:force_encoding)
+      str.force_encoding("utf-8")
       str
     end
 
-    def strategies
-      @strategies ||= [
-        ::PDF::Reader::MetadataStrategy,
-        ::PDF::Reader::PagesStrategy
-      ]
-    end
-
     def root
       @root ||= @objects.deref(@objects.trailer[:Root])
     end
@@ -351,7 +249,6 @@ end
 ################################################################################
 
 require 'pdf/reader/resource_methods'
-require 'pdf/reader/abstract_strategy'
 require 'pdf/reader/buffer'
 require 'pdf/reader/cid_widths'
 require 'pdf/reader/cmap'
@@ -370,7 +267,6 @@ require 'pdf/reader/font_descriptor'
 require 'pdf/reader/form_xobject'
 require 'pdf/reader/glyph_hash'
 require 'pdf/reader/lzw'
-require 'pdf/reader/metadata_strategy'
 require 'pdf/reader/object_cache'
 require 'pdf/reader/object_hash'
 require 'pdf/reader/object_stream'
@@ -381,7 +277,6 @@ require 'pdf/reader/reference'
 require 'pdf/reader/register_receiver'
 require 'pdf/reader/standard_security_handler'
 require 'pdf/reader/stream'
-require 'pdf/reader/text_receiver'
 require 'pdf/reader/text_run'
 require 'pdf/reader/page_state'
 require 'pdf/reader/page_text_receiver'

data/lib/pdf/reader/buffer.rb

@@ -37,6 +37,7 @@ class PDF::Reader
   #
   class Buffer
     TOKEN_WHITESPACE=[0x00, 0x09, 0x0A, 0x0C, 0x0D, 0x20]
+    TOKEN_DELIMITER=[0x25, 0x3C, 0x3E, 0x28, 0x5B, 0x7B, 0x29, 0x5D, 0x7D, 0x2F]
 
     # some strings for comparissons. Declaring them here avoids creating new
     # strings that need GC over and over
@@ -366,7 +367,7 @@ class PDF::Reader
           # PDF name, start of new token
           @tokens << tok if tok.size > 0
           @tokens << byte.chr
-          @tokens << "" if byte == 0x2F && [nil, 0x20, 0x0A].include?(peek_byte)
+          @tokens << "" if byte == 0x2F && ([nil, 0x20, 0x0A] + TOKEN_DELIMITER).include?(peek_byte)
           tok = ""
           break
         else

data/lib/pdf/reader/cmap.rb

@@ -31,6 +31,17 @@ class PDF::Reader
   # extracting various useful information.
   #
   class CMap # :nodoc:
+    CMAP_KEYWORDS = {
+      "begincodespacerange" => 1,
+      "endcodespacerange" => 1,
+      "beginbfchar" => 1,
+      "endbfchar" => 1,
+      "beginbfrange" => 1,
+      "endbfrange" => 1,
+      "begin" => 1,
+      "begincmap" => 1,
+      "def" => 1
+    }
 
     attr_reader :map
 
@@ -40,24 +51,25 @@ class PDF::Reader
     end
 
     def process_data(data)
+      parser = build_parser(data)
       mode = nil
-      instructions = ""
+      instructions = []
 
-      data.each_line do |l|
-        if l.include?("beginbfchar")
+      while token = parser.parse_token(CMAP_KEYWORDS)
+        if token == "beginbfchar"
           mode = :char
-        elsif l.include?("endbfchar")
+        elsif token == "endbfchar"
           process_bfchar_instructions(instructions)
-          instructions = ""
+          instructions = []
           mode = nil
-        elsif l.include?("beginbfrange")
+        elsif token == "beginbfrange"
           mode = :range
-        elsif l.include?("endbfrange")
+        elsif token == "endbfrange"
           process_bfrange_instructions(instructions)
-          instructions = ""
+          instructions = []
           mode = nil
         elsif mode == :char || mode == :range
-          instructions << l
+          instructions << token
         end
       end
     end
@@ -105,22 +117,15 @@ class PDF::Reader
     end
 
     def process_bfchar_instructions(instructions)
-      parser  = build_parser(instructions)
-      find    = str_to_int(parser.parse_token)
-      replace = str_to_int(parser.parse_token)
-      while find && replace
-        @map[find[0]] = replace
-        find       = str_to_int(parser.parse_token)
-        replace    = str_to_int(parser.parse_token)
+      instructions.each_slice(2) do |one, two|
+        find    = str_to_int(one)
+        replace = str_to_int(two)
+        @map[find.first] = replace
       end
     end
 
     def process_bfrange_instructions(instructions)
-      parser  = build_parser(instructions)
-      start   = parser.parse_token
-      finish  = parser.parse_token
-      to      = parser.parse_token
-      while start && finish && to
+      instructions.each_slice(3) do |start, finish, to|
         if start.kind_of?(String) && finish.kind_of?(String) && to.kind_of?(String)
           bfrange_type_one(start, finish, to)
         elsif start.kind_of?(String) && finish.kind_of?(String) && to.kind_of?(Array)
@@ -128,9 +133,6 @@ class PDF::Reader
         else
           raise "invalid bfrange section"
         end
-        start   = parser.parse_token
-        finish  = parser.parse_token
-        to      = parser.parse_token
       end
     end