@@ -97,8 +97,8 @@ module GEDCOM next if level.nil? or tag.nil? level = level.to_i - if tag == 'CONT' and @auto_concat - concat_data rest + if (tag == 'CONT' || tag == 'CONC') and @auto_concat + concat_data tag, rest next end @@ -124,14 +124,19 @@ module GEDCOM end end - def concat_data rest + def concat_data tag, rest if @dataStack[-1].nil? @dataStack[-1] = rest else if @ctxStack[-1] == 'BLOB' @dataStack[-1] << rest else - @dataStack[-1] << "\n" + rest + if tag == 'CONT' + @dataStack[-1] << "\n" + rest + elsif tag == 'CONC' + old = @dataStack[-1].chomp + @dataStack[-1] = old + rest + end end end end lib/gedcom.rb @@ -67,18 +67,27 @@ describe Parser do end it "should parse TGC551.ged (\\r)" do + # Should handle CONC and CONT differently + @parser.after(["HEAD", "NOTE"]) do |data| + expected_text = <<-EOS +This file demonstrates all tags that are allowed in GEDCOM 5.5. Here are some comments about the HEADER record and comments about where to look for information on the other 9 types of GEDCOM records. Most other records will have their own notes that describe what to look for in that record and what to hope the importing software will find. + +Many applications will fail to import these notes. The notes are therefore also provided with the files as a plain-text "Read-Me" file. +EOS + data.should =~ /^#{expected_text}/ + end @parser.parse "#{GEDCOMS}/TGC551.ged" - @tag_count[:all].should == 1653 + @tag_count[:all].should == 1396 end it "should parse TGC551LF.ged (\\r\\n)" do @parser.parse "#{GEDCOMS}/TGC551LF.ged" - @tag_count[:all].should == 1653 + @tag_count[:all].should == 1396 end it "should parse TGC55C.ged (\\r)" do @parser.parse "#{GEDCOMS}/TGC55C.ged" - @tag_count[:all].should == 1684 + @tag_count[:all].should == 1420 end it "should parse TGC55CLF.ged (\\r\\n) with auto-concat" do @@ -86,7 +95,7 @@ describe Parser do @parser.after %w(OBJE BLOB) do |data| data.size.should == 458 end - @tag_count[:all].should == 1684 + @tag_count[:all].should == 1420 end it "should parse TGC55CLF.ged (\\r\\n) without auto-concat" do tests/parser_spec.rb af8ee42eb462a674540d8e0c3081bd578942532b Tim Shadel github@timshadel.com http://github.com/timshadel/gedcom-ruby/commit/9bcdd5c8c4254c6dc44f3785aab85dae3e41e4ee 9bcdd5c8c4254c6dc44f3785aab85dae3e41e4ee 2009-01-18T17:44:31-08:00 2009-01-18T17:36:44-08:00 Handle CONC properly by not including newlines. From the GEDCOM 5.5 Spec (http://homepages.rootsweb.ancestry.com/~pmcbride/gedcom/55gcappa.htm) CONC {CONCATENATION}: = An indicator that additional data belongs to the superior value. The information from the CONC value is to be connected to the value of the superior preceding line without a space and without a carriage return and/or new line character. Values that are split for a CONC tag must always be split at a non-space. If the value is split on a space the space will be lost when concatenation takes place. This is because of the treatment that spaces get as a GEDCOM delimiter, many GEDCOM values are trimmed of trailing spaces and some systems look for the first non-space starting after the tag to determine the beginning of the value. CONT {CONTINUED}: = An indicator that additional data belongs to the superior value. The information from the CONT value is to be connected to the value of the superior preceding line with a carriage return and/or new line character. Leading spaces could be important to the formatting of the resultant text. When importing values from CONT lines the reader should assume only one delimiter character following the CONT tag. Assume that the rest of the leading spaces are to be a part of the value. Signed-off-by: Tim Shadel <github@timshadel.com> 0151063e6bdef94a5fb0e2135aff6470bc3d6e06 Tim Shadel github@timshadel.com