pdf-reader 1.3.2 → 1.3.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ea0ed09942ae54e900f0387fd9e46213a6db401b
+  data.tar.gz: baa54a8a557c8ad86bf3760c0e361f84c16728ef
+SHA512:
+  metadata.gz: f276cce73b972af13426088bc33217efd576d4e7d7f9dc866aee27950d8cad0f8e8831308314599608a6161cf1aacd4efa1b228c39a6dbff4f78fbc606802c49
+  data.tar.gz: a9a9d46c2f2eebe93dd15d92fc22d6fb69577fba113bf8f123f7f3efb06d1dcaebe2238c07cc6e0dadcd54f96ed47a4cc57eb043f59d769d397fb36b38a1cc88

data/CHANGELOG

@@ -1,3 +1,6 @@
+v1.3.3 (7th April 2013)
+- various bug fixes
+
 v1.3.2 (26th February 2013)
 - various bug fixes
 

data/Rakefile

@@ -2,6 +2,7 @@ require "rubygems"
 require "bundler"
 Bundler.setup
 
+require 'yaml'
 require 'rake'
 require 'rdoc/task'
 require 'rspec/core/rake_task'
@@ -19,7 +20,7 @@ if RUBY_VERSION >= "1.9" && RUBY_ENGINE == "ruby"
   Cane::RakeTask.new(:quality) do |cane|
     cane.abc_max = 20
     cane.style_measure = 100
-    cane.max_violations = 94
+    cane.max_violations = 93
 
     cane.use Morecane::EncodingCheck, :encoding_glob => "{app,lib,spec}/**/*.rb"
   end

data/lib/pdf/reader/buffer.rb

@@ -38,6 +38,14 @@ class PDF::Reader
   class Buffer
     TOKEN_WHITESPACE=[0x00, 0x09, 0x0A, 0x0C, 0x0D, 0x20]
 
+    # some strings for comparissons. Declaring them here avoids creating new
+    # strings that need GC over and over
+    LEFT_PAREN = "("
+    LESS_THAN = "<"
+    STREAM = "stream"
+    ID = "ID"
+    FWD_SLASH = "/"
+
     attr_reader :pos
 
     # Creates a new buffer.
@@ -121,7 +129,7 @@ class PDF::Reader
 
       # the PDF 1.7 spec (section #3.4) says that EOL markers can be either \r, \n, or both.
       lines = data.split(/[\n\r]+/).reverse
-      eof_index = lines.index { |l| l.strip == "%%EOF" }
+      eof_index = lines.index { |l| l.strip[/^%%EOF/] }
 
       raise MalformedPDFError, "PDF does not contain EOF marker" if eof_index.nil?
       raise MalformedPDFError, "PDF EOF marker does not follow offset" if eof_index >= lines.size-1
@@ -176,11 +184,11 @@ class PDF::Reader
     #
     def state
       case @tokens.last
-      when "(" then :literal_string
-      when "<" then :hex_string
-      when "stream" then :stream
-      when "ID"
-        if in_content_stream?  && @tokens[-2] != "/"
+      when LEFT_PAREN then :literal_string
+      when LESS_THAN then :hex_string
+      when STREAM then :stream
+      when ID
+        if in_content_stream?  && @tokens[-2] != FWD_SLASH
           :inline
         else
           :regular

data/lib/pdf/reader/cmap.rb

@@ -142,8 +142,6 @@ class PDF::Reader
       # add all values in the range to our mapping
       (start_code..end_code).each_with_index do |val, idx|
         @map[val] = dst.length == 1 ? [dst[0] + idx] : [dst[0], dst[1] + 1]
-        # ensure a single range does not exceed 255 chars
-        raise PDF::Reader::MalformedPDFError, "a CMap bfrange cann't exceed 255 chars" if idx > 255
       end
     end
 

data/lib/pdf/reader/encoding.rb

@@ -36,8 +36,7 @@ class PDF::Reader
     attr_reader :unpack
 
     def initialize(enc)
-      @mapping  = {} # maps from character codes to Unicode codepoints
-                     # also maps control and invalid chars to UNKNOWN_CHAR
+      @mapping  = default_mapping # maps from character codes to Unicode codepoints
       @string_cache  = {} # maps from character codes to UTF-8 strings.
 
       if enc.kind_of?(Hash)
@@ -54,7 +53,6 @@ class PDF::Reader
       @map_file = get_mapping_file(enc)
 
       load_mapping(@map_file) if @map_file
-      add_control_chars_to_mapping
     end
 
     # set the differences table for this encoding. should be an array in the following format:
@@ -130,6 +128,21 @@ class PDF::Reader
 
     private
 
+    # returns a hash that:
+    # - maps control chars and nil to the unicode "unknown character"
+    # - leaves all other bytes <= 255 unchaged
+    #
+    # Each specific encoding will change this default as required for their glyphs
+    def default_mapping
+      all_bytes = (0..255).to_a
+      tuples = all_bytes.map {|i|
+        CONTROL_CHARS.include?(i) ? [i, UNKNOWN_CHAR] : [i,i]
+      }
+      mapping = Hash[tuples]
+      mapping[nil] = UNKNOWN_CHAR
+      mapping
+    end
+
     def internal_int_to_utf8_string(glyph_code)
       ret = [
         @mapping[glyph_code.to_i] || glyph_code.to_i
@@ -194,8 +207,6 @@ class PDF::Reader
     end
 
     def load_mapping(file)
-      return if has_mapping?
-
       RUBY_VERSION >= "1.9" ? mode = "r:BINARY" : mode = "r"
       File.open(file, mode) do |f|
         f.each do |l|
@@ -205,13 +216,5 @@ class PDF::Reader
       end
     end
 
-    def add_control_chars_to_mapping
-      PDF::Reader::Encoding::CONTROL_CHARS.each do |byte|
-        unless @mapping[byte]
-          @mapping[byte] = PDF::Reader::Encoding::UNKNOWN_CHAR
-        end
-      end
-      @mapping[nil] = PDF::Reader::Encoding::UNKNOWN_CHAR
-    end
   end
 end

data/lib/pdf/reader/font.rb

@@ -53,16 +53,7 @@ class PDF::Reader
     end
 
     def basefont=(font)
-      # setup a default encoding for the selected font. It can always be overridden
-      # with encoding= if required
-      case font
-      when "Symbol" then
-        @encoding = PDF::Reader::Encoding.new("SymbolEncoding")
-      when "ZapfDingbats" then
-        @encoding = PDF::Reader::Encoding.new("ZapfDingbatsEncoding")
-      else
-        @encoding = nil
-      end
+      @encoding ||= default_encoding(font)
       @basefont = font
     end
 
@@ -91,6 +82,17 @@ class PDF::Reader
 
     private
 
+    def default_encoding(font_name)
+      case font_name.to_s
+      when "Symbol" then
+        PDF::Reader::Encoding.new(:SymbolEncoding)
+      when "ZapfDingbats" then
+        PDF::Reader::Encoding.new(:ZapfDingbatsEncoding)
+      else
+        PDF::Reader::Encoding.new(:StandardEncoding)
+      end
+    end
+
     def build_width_calculator
       if @subtype == :Type0
         PDF::Reader::WidthCalculator::TypeZero.new(self)
@@ -114,7 +116,11 @@ class PDF::Reader
     def extract_base_info(obj)
       @subtype  = @ohash.object(obj[:Subtype])
       @basefont = @ohash.object(obj[:BaseFont])
-      @encoding = PDF::Reader::Encoding.new(@ohash.object(obj[:Encoding]))
+      if @ohash.object(obj[:Encoding])
+        @encoding = PDF::Reader::Encoding.new(@ohash.object(obj[:Encoding]))
+      else
+        @encoding = default_encoding(@basefont)
+      end
       @widths   = @ohash.object(obj[:Widths]) || []
       @first_char = @ohash.object(obj[:FirstChar])
       @last_char = @ohash.object(obj[:LastChar])

data/lib/pdf/reader/glyph_hash.rb

@@ -66,10 +66,10 @@ class PDF::Reader
         "0x#{str[3,4]}".hex
       elsif str.match(/\Au[A-F\d]{4,6}\Z/)
         "0x#{str[1,6]}".hex
-      elsif str.match(/\A[A-Za-z]\d{1,4}\Z/)
-        str[1,4].to_i
-      elsif str.match(/\A[A-Za-z]{2}\d{2,4}\Z/)
-        str[2,4].to_i
+      elsif str.match(/\A[A-Za-z]\d{1,5}\Z/)
+        str[1,5].to_i
+      elsif str.match(/\A[A-Za-z]{2}\d{2,5}\Z/)
+        str[2,5].to_i
       else
         nil
       end

data/lib/pdf/reader/pages_strategy.rb

@@ -30,9 +30,9 @@ class PDF::Reader
   # Walks the pages of the PDF file and calls the appropriate callback methods when
   # something of interest is found.
   #
-  # The callback methods should exist on the receiver object passed into the constructor. Whenever
-  # some content is found that will trigger a callback, the receiver is checked to see if the callback
-  # is defined.
+  # The callback methods should exist on the receiver object passed into the constructor.
+  # Whenever some content is found that will trigger a callback, the receiver is checked
+  # to see if the callback is defined.
   #
   # If it is defined it will be called. If not, processing will continue.
   #
@@ -40,9 +40,9 @@ class PDF::Reader
   # The following callbacks are available and should be methods defined on your receiver class. Only
   # implement the ones you need - the rest will be ignored.
   #
-  # Some callbacks will include parameters which will be passed in as an array. For callbacks that supply no
-  # paramters, or where you don't need them, the *params argument can be left off. Some example callback
-  # method definitions are:
+  # Some callbacks will include parameters which will be passed in as an array. For callbacks
+  # that supply no paramters, or where you don't need them, the *params argument can be left off.
+  # Some example callback method definitions are:
   #
   #   def begin_document
   #   def end_page

data/lib/pdf/reader/register_receiver.rb

@@ -11,10 +11,12 @@ class PDF::Reader
   #
   # Usage:
   #
-  #  receiver = PDF::Reader::RegisterReceiver.new
-  #  PDF::Reader.file("somefile.pdf", receiver)
-  #  callback = receiver.first_occurance_of(:show_text)
-  #  callback[:args].first.should == "Hellow World"
+  #     PDF::Reader.open("somefile.pdf") do |reader|
+  #       receiver = PDF::Reader::RegisterReceiver.new
+  #       reader.page(1).walk(receiver)
+  #       callback = receiver.first_occurance_of(:show_text)
+  #       callback[:args].first.should == "Hellow World"
+  #     end
   #
   class RegisterReceiver
 
@@ -34,18 +36,12 @@ class PDF::Reader
 
     # count the number of times a callback fired
     def count(methodname)
-      counter = 0
-      callbacks.each { |cb| counter += 1 if cb[:name] == methodname}
-      return counter
+      callbacks.count { |cb| cb[:name] == methodname}
     end
 
     # return the details for every time the specified callback was fired
     def all(methodname)
-      ret = []
-      callbacks.each do |cb|
-        ret << cb if cb[:name] == methodname
-      end
-      return ret
+      callbacks.select { |cb| cb[:name] == methodname }
     end
 
     def all_args(methodname)
@@ -54,42 +50,32 @@ class PDF::Reader
 
     # return the details for the first time the specified callback was fired
     def first_occurance_of(methodname)
-      callbacks.each do |cb|
-        return cb if cb[:name] == methodname
-      end
-      return nil
+      callbacks.find { |cb| cb[:name] == methodname }
     end
 
     # return the details for the final time the specified callback was fired
     def final_occurance_of(methodname)
-      returnme = nil
-      callbacks.each do |cb|
-        returnme = cb if cb[:name] == methodname
-      end
-      return returnme
+      all(methodname).last
     end
 
     # return the first occurance of a particular series of callbacks
     def series(*methods)
       return nil if methods.empty?
 
-      indexes = (0..(callbacks.size-1-methods.size))
+      indexes = (0..(callbacks.size-1))
       method_indexes = (0..(methods.size-1))
       match = nil
 
       indexes.each do |idx|
         count = methods.size
         method_indexes.each do |midx|
-          count -= 1 if callbacks[idx+midx][:name] == methods[midx]
+          count -= 1 if callbacks[idx+midx] && callbacks[idx+midx][:name] == methods[midx]
+        end
+        if count == 0
+          return callbacks[idx, methods.size]
         end
-        match = idx and break if count == 0
-      end
-
-      if match
-        return callbacks[match, methods.size]
-      else
-        return nil
       end
+      nil
     end
   end
 end

data/lib/pdf/reader/width_calculator/built_in.rb

@@ -3,12 +3,52 @@
 require 'afm'
 require 'pdf/reader/synchronized_cache'
 
-module AFM
-  # this is a monkey patch for the AFM gem. hopefully my patch will be accepted
-  # upstream and I can drop this
-  class Font
-    def metrics_for_name(name)
-      @char_metrics[name.to_s]
+# monkey patch the afm gem to give us access to the metrics by glyph code. I've
+# got a pull request to upstream so hopefully this can be removed soon. See
+# https://github.com/halfbyte/afm/pull/3
+class AFM::Font
+  attr_reader :char_metrics_by_code
+
+  # Loading a Font Metrics file by absolute path (no automatic font path resolution)
+  def initialize(filename)
+    @metadata = {}
+    @char_metrics = {}
+    @char_metrics_by_code = {}
+    @kern_pairs = []
+    File.open(filename) do |file|
+      mode = :meta
+      file.each_line do |line|
+        case(line)
+        when /^StartFontMetrics/ ; mode = :meta
+        when /^StartCharMetrics/ ; mode = :char_metrics
+        when /^EndCharMetrics/ ; mode = :meta
+        when /^StartKernData/ ; mode = :kern_data
+        when /^StartKernPairs/ ; mode = :kern_pairs
+        when /^EndKernPairs/ ; mode = :kern_data
+        when /^EndKernData/ ; mode = :meta
+        else
+          case(mode)
+          when :meta
+            if match = line.match(/^([\w]+) (.*)$/)
+              @metadata[match[1]] = match[2]
+            end
+          when :char_metrics
+            metrics = {}
+            metrics[:charcode] = match[1].to_i if match = line.match(/C (-?\d+) *?;/)
+            metrics[:wx] = match[1].to_i if match = line.match(/WX (-?\d+) *?;/)
+            metrics[:name] = match[1] if match = line.match(/N ([.\w]+) *?;/)
+            if match = line.match(/B (-?\d+) (-?\d+) (-?\d+) (-?\d+) *?;/)
+              metrics[:boundingbox] = [match[1].to_i, match[2].to_i, match[3].to_i, match[4].to_i]
+            end
+            @char_metrics[metrics[:name]] = metrics if metrics[:name]
+            @char_metrics_by_code[metrics[:charcode]] = metrics if metrics[:charcode] && metrics[:charcode] > 0
+          when :kern_pairs
+            if match = line.match(/^KPX ([.\w]+) ([.\w]+) (-?\d+)$/)
+              @kern_pairs << [match[1], match[2], match[3].to_i]
+            end
+          end
+        end
+      end
     end
   end
 end
@@ -37,11 +77,11 @@ class PDF::Reader
       def glyph_width(code_point)
         return 0 if code_point.nil? || code_point < 0
 
-        m = @metrics.metrics_for(code_point)
+        m = @metrics.char_metrics_by_code[code_point]
         if m.nil?
           names = @font.encoding.int_to_name(code_point)
           m = names.map { |name|
-            @metrics.metrics_for_name(name)
+            @metrics.char_metrics[name.to_s]
           }.compact.first
         end
 
@@ -50,7 +90,7 @@ class PDF::Reader
         elsif @font.widths[code_point - 1]
           @font.widths[code_point - 1]
         else
-          raise ArgumentError, "Unknown glyph width for #{code_point}"
+          raise ArgumentError, "Unknown glyph width for #{code_point} #{@font.basefont}"
         end
       end
 

metadata

@@ -1,36 +1,32 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 1.3.2
-  prerelease: 
+  version: 1.3.3
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-02-26 00:00:00.000000000 Z
+date: 2013-04-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -38,7 +34,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -46,7 +41,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: ZenTest
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -54,7 +48,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -62,7 +55,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: cane
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -70,7 +62,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -78,55 +69,48 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: morecane
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: ir_b
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: Ascii85
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -134,7 +118,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -142,23 +125,20 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
   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
@@ -166,7 +146,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -174,23 +153,20 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: ttfunk
   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: afm
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -198,7 +174,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -312,12 +287,22 @@ files:
 - bin/pdf_callbacks
 homepage: http://github.com/yob/pdf-reader
 licenses: []
-post_install_message: ! "\n  ********************************************\n\n  v1.0.0
-  of PDF::Reader introduced a new page-based API. There are extensive\n  examples
-  showing how to use it in the README and examples directory.\n\n  For detailed documentation,
-  check the rdocs for the PDF::Reader,\n  PDF::Reader::Page and PDF::Reader::ObjectHash
-  classes.\n\n  The old API is marked as deprecated but will continue to work with
-  no\n  visible warnings for now.\n\n  ********************************************\n\n"
+metadata: {}
+post_install_message: |2+
+
+    ********************************************
+
+    v1.0.0 of PDF::Reader introduced a new page-based API. There are extensive
+    examples showing how to use it in the README and examples directory.
+
+    For detailed documentation, check the rdocs for the PDF::Reader,
+    PDF::Reader::Page and PDF::Reader::ObjectHash classes.
+
+    The old API is marked as deprecated but will continue to work with no
+    visible warnings for now.
+
+    ********************************************
+
 rdoc_options:
 - --title
 - PDF::Reader Documentation
@@ -327,21 +312,19 @@ rdoc_options:
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: 1.8.7
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.0.0
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A library for accessing the content of PDF files
 test_files: []