@@ -5,6 +5,7 @@ v0.6.2 (xxx) - Added a few callbacks to improve the way we supply information on page resources - Ignore whitespace in hex strings, as required by the spec (section 3.2.3) - Use our "unknown character box" when a single character in an Identity-H string fails to decode +- Support ToUnicode CMaps that use the bfrange operator v0.6.1 (12th March 2008) - Tweaked behaviour when we encounter Identity-H encoded text that doesn't have a ToUnicode mapping. We CHANGELOG @@ -4,7 +4,6 @@ v0.7 - maybe a third option to Reader.parse? parse(io, receiver, {:pages => true, :fonts => false, :metadata => true, :bookmarks => false}) - detect when a font's encoding is a CMap (generally used for pre-Unicode, multibyte asian encodings), and display a user friendly error -- When parsing a CMap into a ruby object, recognise ranged mappings defined by begincodespacerange (see spec, section 5.9.2) - Provide a way to get raw access to a particular object. Good for testing purposes v0.8 TODO @@ -28,12 +28,33 @@ class PDF::Reader def initialize(data) @map = {} - inmap = false + in_char_mode = false + in_range_mode = false + data.each_line do |l| - inmap = true if l.include?("beginbfchar") - if inmap + if l.include?("beginbfchar") + in_char_mode = true + elsif l.include?("endbfchar") + in_char_mode = false + elsif l.include?("beginbfrange") + in_range_mode = true + elsif l.include?("endbfrange") + in_range_mode = false + end + if in_char_mode m, find, replace = *l.match(/<([0-9a-fA-F]+)> <([0-9a-fA-F]+)>/) @map["0x#{find}".hex] = "0x#{replace}".hex if find && replace + elsif in_range_mode + m, start_code, end_code, dst = *l.match(/<([0-9a-fA-F]+)> <([0-9a-fA-F]+)> <([0-9a-fA-F]+)>/) + if start_code && end_code && dst + start_code = "0x#{start_code}".hex + end_code = "0x#{end_code}".hex + dst = "0x#{dst}".hex + (start_code..end_code).each do |val| + @map[val] = dst + dst += 1 + end + end end end end lib/pdf/reader/cmap.rb @@ -57,4 +57,13 @@ EOF map.decode(0x9).should eql(0x73) end + specify "should correctly load a cmap that uses the beginbfrange operator" do + filename = File.dirname(__FILE__) + "/data/cmap_with_bfrange.txt" + map = PDF::Reader::CMap.new(File.read(filename)) + map.decode(0x16C9).should eql(0x4F38) # mapped with the bfchar operator + map.decode(0x0003).should eql(0x0020) # mapped with the bfrange operator + map.decode(0x0004).should eql(0x0020+1) # mapped with the bfrange operator + map.decode(0x0005).should eql(0x0020+2) # mapped with the bfrange operator + end + end specs/cmap_spec.rb d04ce054e8e8602b375bfce111d4878cff979e9a jhealy jhealy@3db89d08-1e44-db11-a2a8-0014220fd31b http://github.com/yob/pdf-reader/commit/06c8dbbf2b202dce5fc5bbffec69413bb14d99f9 06c8dbbf2b202dce5fc5bbffec69413bb14d99f9 2008-03-21T02:25:41-07:00 2008-03-21T02:25:41-07:00 pdf-reader: added support for ToUnicode CMaps that use the bfrange operator (see section 5.9.2 of the spec) git-svn-id: https://pmade.com/svn/oss/pdf-reader/trunk@1327 3db89d08-1e44-db11-a2a8-0014220fd31b 3936f1ff2b27c0e4bfc2aac883c7083a0478276a jhealy jhealy@3db89d08-1e44-db11-a2a8-0014220fd31b