pdf-reader 0.9.1 → 0.9.2

data/CHANGELOG

@@ -1,3 +1,11 @@
+v0.9.2 (24th April 2011)
+- add basic support for fonts with Identity-V encoding.
+- bug: improve robustness of text extraction
+  - thanks to Evan Arnold for reporting
+- bug: fix loading of nested resources on XObjects
+  - thanks to Samuel Williams for reporting
+- bug: improve parsing of files with XRef object streams
+
 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

data/lib/pdf/reader/encoding.rb

@@ -116,7 +116,7 @@ class PDF::Reader
     def original_codepoint_to_unicode(cp, tounicode = nil)
       if tounicode && (code = tounicode.decode(cp))
         code
-      elsif tounicode || ( tounicode.nil? && to_unicode_required? )
+      elsif to_unicode_required? && (tounicode.nil? || tounicode.decode(cp).nil?)
         PDF::Reader::Encoding::UNKNOWN_CHAR
       elsif mapping[cp]
         mapping[cp]
@@ -129,7 +129,7 @@ class PDF::Reader
 
     def get_unpack(enc)
       case enc
-      when :"Identity-H", :UTF16Encoding
+      when :"Identity-H", :"Identity-V", :UTF16Encoding
         "n*"
       else
         "C*"
@@ -140,6 +140,7 @@ class PDF::Reader
       return File.dirname(__FILE__) + "/encodings/standard.txt" if enc.nil?
       files = {
         :"Identity-H"      => nil,
+        :"Identity-V"      => nil,
         :MacRomanEncoding  => File.dirname(__FILE__) + "/encodings/mac_roman.txt",
         :MacExpertEncoding => File.dirname(__FILE__) + "/encodings/mac_expert.txt",
         :PDFDocEncoding    => File.dirname(__FILE__) + "/encodings/pdf_doc.txt",
@@ -158,7 +159,7 @@ class PDF::Reader
     end
 
     def unicode_required?(enc)
-      enc == :"Identity-H"
+      enc == :"Identity-H" or enc == :"Identity-V"
     end
 
     def mapping

data/lib/pdf/reader/pages_strategy.rb

@@ -310,11 +310,15 @@ class PDF::Reader
 
       if xobject && xobject.hash[:Subtype] == :Form
         callback(:begin_form_xobject)
-        resources = @ohash.object(xobject.hash[:Resources])
-        walk_resources(resources) if resources
-        fonts = font_hash_from_resources(resources)
+        xobj_resources = @ohash.object(xobject.hash[:Resources])
+        if xobj_resources
+          resources.push xobj_resources
+          walk_resources(xobj_resources)
+        end
+        fonts = font_hash_from_resources(xobj_resources)
         content_stream(xobject, fonts)
         callback(:end_form_xobject)
+        resources.pop if xobj_resources
       end
     end
 
@@ -439,8 +443,11 @@ class PDF::Reader
         obj
       when PDF::Reader::Reference then
         resolve_references(@ohash.object(obj))
-      when Hash                   then obj.each { |key,val| obj[key] = resolve_references(val) }
-      when Array                  then obj.collect { |item| resolve_references(item) }
+      when Hash                   then
+        arr = obj.map { |key,val| [key, resolve_references(val)] }.flatten(1)
+        Hash[*arr]
+      when Array                  then
+        obj.collect { |item| resolve_references(item) }
       else
         obj
       end

data/lib/pdf/reader/xref.rb

@@ -154,23 +154,26 @@ class PDF::Reader
       trailer[:Info] = stream.hash[:Info] if stream.hash[:Info]
       trailer[:Prev] = stream.hash[:Prev] if stream.hash[:Prev]
 
-      widths = stream.hash[:W]
+      widths       = stream.hash[:W]
       entry_length = widths.inject(0) { |s, w| s + w }
-      raw_data = stream.unfiltered_data
+      raw_data     = StringIO.new(stream.unfiltered_data)
       if stream.hash[:Index]
-        index = stream.hash[:Index][0]
+        index = stream.hash[:Index]
       else
-        index = 0
+        index = [0, stream.hash[:Size]]
       end
-      stream.hash[:Size].times do |i|
-        entry = raw_data[i*entry_length, entry_length] || ""
-        f1    = unpack_bytes(entry[0,widths[0]])
-        f2    = unpack_bytes(entry[widths[0],widths[1]])
-        f3    = unpack_bytes(entry[widths[0]+widths[1],widths[2]])
-        if f1 == 1
-          store(index + i, f3, f2)
-        elsif f1 == 2
-          store(index + i, 0, PDF::Reader::Reference.new(f2, 0))
+      index.each_slice(2) do |start_id, size|
+        obj_ids = (start_id..(start_id+(size-1)))
+        obj_ids.each do |objid|
+          entry = raw_data.read(entry_length) || ""
+          f1    = unpack_bytes(entry[0,widths[0]])
+          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)
+          elsif f1 == 2 && f2 > 0
+            store(objid, 0, PDF::Reader::Reference.new(f2, 0))
+          end
         end
       end
 

metadata

@@ -1,13 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: pdf-reader
 version: !ruby/object:Gem::Version 
-  hash: 57
   prerelease: false
   segments: 
   - 0
   - 9
-  - 1
-  version: 0.9.1
+  - 2
+  version: 0.9.2
 platform: ruby
 authors: 
 - James Healy
@@ -15,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-21 00:00:00 +11:00
+date: 2011-04-24 00:00:00 +10:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -26,7 +25,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
         segments: 
         - 0
         version: "0"
@@ -40,7 +38,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
         segments: 
         - 0
         version: "0"
@@ -54,7 +51,6 @@ dependencies:
     requirements: 
     - - ~>
       - !ruby/object:Gem::Version 
-        hash: 1
         segments: 
         - 2
         - 1
@@ -69,7 +65,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 25
         segments: 
         - 0
         - 9
@@ -158,7 +153,6 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 57
       segments: 
       - 1
       - 8
@@ -169,7 +163,6 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
       segments: 
       - 0
       version: "0"