isodoc 1.0.24 → 1.0.29

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (61) hide show
  1. checksums.yaml +4 -4
  2. data/.github/workflows/macos.yml +14 -4
  3. data/.github/workflows/ubuntu.yml +19 -5
  4. data/.github/workflows/windows.yml +14 -4
  5. data/isodoc.gemspec +1 -1
  6. data/lib/isodoc-yaml/i18n-en.yaml +3 -1
  7. data/lib/isodoc-yaml/i18n-fr.yaml +3 -1
  8. data/lib/isodoc-yaml/i18n-zh-Hans.yaml +3 -1
  9. data/lib/isodoc/convert.rb +1 -0
  10. data/lib/isodoc/function/blocks.rb +43 -49
  11. data/lib/isodoc/function/{blocks_example.rb → blocks_example_note.rb} +57 -2
  12. data/lib/isodoc/function/cleanup.rb +16 -2
  13. data/lib/isodoc/function/i18n.rb +1 -0
  14. data/lib/isodoc/function/inline.rb +79 -77
  15. data/lib/isodoc/function/inline_simple.rb +72 -0
  16. data/lib/isodoc/function/lists.rb +12 -6
  17. data/lib/isodoc/function/references.rb +51 -39
  18. data/lib/isodoc/function/reqt.rb +13 -4
  19. data/lib/isodoc/function/section.rb +19 -8
  20. data/lib/isodoc/function/table.rb +3 -4
  21. data/lib/isodoc/function/terms.rb +1 -1
  22. data/lib/isodoc/function/to_word_html.rb +23 -13
  23. data/lib/isodoc/function/utils.rb +13 -6
  24. data/lib/isodoc/function/xref_counter.rb +43 -9
  25. data/lib/isodoc/function/xref_gen.rb +2 -1
  26. data/lib/isodoc/function/xref_gen_seq.rb +11 -10
  27. data/lib/isodoc/function/xref_sect_gen.rb +24 -24
  28. data/lib/isodoc/headlesshtml_convert.rb +5 -0
  29. data/lib/isodoc/html_convert.rb +5 -0
  30. data/lib/isodoc/html_function/footnotes.rb +3 -3
  31. data/lib/isodoc/html_function/html.rb +16 -1
  32. data/lib/isodoc/html_function/postprocess.rb +6 -5
  33. data/lib/isodoc/metadata.rb +10 -3
  34. data/lib/isodoc/metadata_date.rb +19 -7
  35. data/lib/isodoc/pdf_convert.rb +5 -0
  36. data/lib/isodoc/version.rb +1 -1
  37. data/lib/isodoc/word_convert.rb +5 -0
  38. data/lib/isodoc/word_function/body.rb +13 -51
  39. data/lib/isodoc/word_function/footnotes.rb +3 -3
  40. data/lib/isodoc/word_function/inline.rb +75 -0
  41. data/lib/isodoc/word_function/postprocess.rb +13 -2
  42. data/lib/isodoc/word_function/table.rb +3 -3
  43. data/lib/isodoc/xslfo_convert.rb +5 -0
  44. data/spec/assets/i18n.yaml +4 -1
  45. data/spec/assets/odf.emf +0 -0
  46. data/spec/assets/odf.svg +4 -0
  47. data/spec/assets/odf1.svg +4 -0
  48. data/spec/isodoc/blocks_spec.rb +274 -51
  49. data/spec/isodoc/cleanup_spec.rb +317 -25
  50. data/spec/isodoc/footnotes_spec.rb +20 -5
  51. data/spec/isodoc/i18n_spec.rb +12 -12
  52. data/spec/isodoc/inline_spec.rb +299 -4
  53. data/spec/isodoc/lists_spec.rb +8 -8
  54. data/spec/isodoc/metadata_spec.rb +112 -3
  55. data/spec/isodoc/postproc_spec.rb +39 -21
  56. data/spec/isodoc/ref_spec.rb +121 -52
  57. data/spec/isodoc/section_spec.rb +236 -207
  58. data/spec/isodoc/table_spec.rb +28 -28
  59. data/spec/isodoc/terms_spec.rb +57 -13
  60. data/spec/isodoc/xref_spec.rb +218 -71
  61. metadata +10 -5
@@ -154,9 +154,9 @@ RSpec.describe IsoDoc do
154
154
  <br/>
155
155
  <div>
156
156
  <h1 class="ForewordTitle">Foreword</h1>
157
- <p>A.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
158
- <p>B.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
159
- <p>C.<a rel="footnote" href="#fn:1" epub:type="footnote"><sup>1</sup></a></p>
157
+ <p>A.<a class="FootnoteRef" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
158
+ <p>B.<a class="FootnoteRef" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
159
+ <p>C.<a class="FootnoteRef" href="#fn:1" epub:type="footnote"><sup>1</sup></a></p>
160
160
  </div>
161
161
  <p class="zzSTDTitle1"/>
162
162
  <aside id="fn:2" class="footnote">
@@ -173,9 +173,9 @@ RSpec.describe IsoDoc do
173
173
  <br/>
174
174
  <div>
175
175
  <h1 class="ForewordTitle">Foreword</h1>
176
- <p>A.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>1</sup></a></p>
177
- <p>B.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
178
- <p>C.<a rel="footnote" href="#fn:1" epub:type="footnote"><sup>3</sup></a></p>
176
+ <p>A.<a class="FootnoteRef" href="#fn:2" epub:type="footnote"><sup>1</sup></a></p>
177
+ <p>B.<a class="FootnoteRef" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
178
+ <p>C.<a class="FootnoteRef" href="#fn:1" epub:type="footnote"><sup>3</sup></a></p>
179
179
  </div>
180
180
  <p class="zzSTDTitle1"/>
181
181
  <aside id="fn:2" class="footnote">
@@ -715,7 +715,7 @@ INPUT
715
715
  OUTPUT
716
716
  end
717
717
 
718
- it "breaks up very long strings in tables" do
718
+ it "does not break up very long strings in tables by default" do
719
719
  expect(xmlpp(IsoDoc::HtmlConvert.new({}).cleanup(Nokogiri::XML(<<~"INPUT")).to_s)).to be_equivalent_to xmlpp(<<~"OUTPUT")
720
720
  <html xmlns:epub="http://www.idpf.org/2007/ops">
721
721
  <head>
@@ -739,6 +739,7 @@ INPUT
739
739
  <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
740
740
  <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">Rice sample</td>
741
741
  </tr>
742
+ </thead>
742
743
  <tbody>
743
744
  <tr>
744
745
  <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
@@ -775,26 +776,102 @@ INPUT
775
776
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
776
777
  <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>Rice sample</td>
777
778
  </tr>
779
+ </thead>
778
780
  <tbody>
779
781
  <tr>
780
782
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
781
- http://www.example.com/
782
- AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAA/
783
- BBBBBBBBBBBBBBBBBBBBBBBBBBBB
783
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB
784
784
  </td>
785
785
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
786
- http://www.example.com/
787
- AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
788
- AAAAAAAABBBBBBBBBBBBBBBBBBBBBB BBBBBB
786
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB </td>
787
+ <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>
788
+ www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
789
+ </td>
790
+ </tr>
791
+ </tbody>
792
+ </table>
793
+ </div>
794
+ </div>
795
+ </body>
796
+ </head>
797
+ </html>
798
+ OUTPUT
799
+ end
800
+
801
+ it "does not break up very long strings in tables on request in HTML" do
802
+ expect(xmlpp(IsoDoc::HtmlConvert.new({break_up_urls_in_tables: "true"}).cleanup(Nokogiri::XML(<<~"INPUT")).to_s)).to be_equivalent_to xmlpp(<<~"OUTPUT")
803
+ <html xmlns:epub="http://www.idpf.org/2007/ops">
804
+ <head>
805
+ <title>test</title>
806
+ <body lang="EN-US" link="blue" vlink="#954F72">
807
+ <div class="WordSection1">
808
+ <p>&#160;</p>
809
+ </div>
810
+ <br clear="all" class="section"/>
811
+ <div class="WordSection2">
812
+ <br clear="all" style="mso-special-character:line-break;page-break-before:always"/>
813
+ <div>
814
+ <h1 class="ForewordTitle">Foreword</h1>
815
+ <p class="TableTitle" align="center">
816
+ <b>Table 1&#160;&#8212; Repeatability and reproducibility of husked rice yield</b>
817
+ </p>
818
+ <table id="tableD-1" class="MsoISOTable" border="1" cellspacing="0" cellpadding="0">
819
+ <thead>
820
+ <tr>
821
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
822
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
823
+ <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">Rice sample</td>
824
+ </tr>
825
+ </thead>
826
+ <tbody>
827
+ <tr>
828
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
829
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
830
+ <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
831
+ </tr>
832
+ </tbody>
833
+ </table>
834
+ </div>
835
+ </div>
836
+ </body>
837
+ </html>
838
+ INPUT
839
+ <?xml version='1.0'?>
840
+ <html xmlns:epub='http://www.idpf.org/2007/ops'>
841
+ <head>
842
+ <title>test</title>
843
+ <body lang='EN-US' link='blue' vlink='#954F72'>
844
+ <div class='WordSection1'>
845
+ <p>&#xA0;</p>
846
+ </div>
847
+ <br clear='all' class='section'/>
848
+ <div class='WordSection2'>
849
+ <br clear='all' style='mso-special-character:line-break;page-break-before:always'/>
850
+ <div>
851
+ <h1 class='ForewordTitle'>Foreword</h1>
852
+ <p class='TableTitle' align='center'>
853
+ <b>Table 1&#xA0;&#x2014; Repeatability and reproducibility of husked rice yield</b>
854
+ </p>
855
+ <table id='tableD-1' class='MsoISOTable' border='1' cellspacing='0' cellpadding='0'>
856
+ <thead>
857
+ <tr>
858
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
859
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
860
+ <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>Rice sample</td>
861
+ </tr>
862
+ </thead>
863
+ <tbody>
864
+ <tr>
865
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
866
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB
789
867
  </td>
868
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
869
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
790
870
  <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>
791
- www.example.com/
792
- AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
793
- ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
871
+ www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
794
872
  </td>
795
873
  </tr>
796
874
  </tbody>
797
- </thead>
798
875
  </table>
799
876
  </div>
800
877
  </div>
@@ -804,7 +881,8 @@ ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
804
881
  OUTPUT
805
882
  end
806
883
 
807
- it "breaks up very long strings in tables (Word)" do
884
+
885
+ it "does not break up very long strings in tables by default (Word)" do
808
886
  expect(xmlpp(IsoDoc::WordConvert.new({}).cleanup(Nokogiri::XML(<<~"INPUT")).to_s)).to be_equivalent_to xmlpp(<<~"OUTPUT")
809
887
  <html xmlns:epub="http://www.idpf.org/2007/ops">
810
888
  <head>
@@ -828,16 +906,17 @@ ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
828
906
  <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
829
907
  <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">Rice sample</td>
830
908
  </tr>
909
+ </thead>
831
910
  <tbody>
832
911
  <tr>
833
912
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
834
- http://www.example.com/ &amp;AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAA/ BBBBBBBBBBBBBBBBBBBBBBBBBBBB
913
+ http://www.example.com/&amp;AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB
835
914
  </td>
836
915
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
837
- http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAABBBBBBBBBBBBBBBBBBBBBB BBBBBB
916
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
838
917
  </td>
839
918
  <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>
840
- www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
919
+ www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
841
920
  </td>
842
921
  </tr>
843
922
  </tbody>
@@ -870,20 +949,20 @@ ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
870
949
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
871
950
  <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>Rice sample</td>
872
951
  </tr>
952
+ </thead>
873
953
  <tbody>
874
954
  <tr>
875
955
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
876
- http://www.example.com/ &amp;AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAA/ BBBBBBBBBBBBBBBBBBBBBBBBBBBB
956
+ http://www.example.com/&amp;AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB
877
957
  </td>
878
958
  <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
879
- http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAABBBBBBBBBBBBBBBBBBBBBB BBBBBB
959
+ http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
880
960
  </td>
881
961
  <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>
882
- www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
962
+ www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB
883
963
  </td>
884
964
  </tr>
885
965
  </tbody>
886
- </thead>
887
966
  </table>
888
967
  </div>
889
968
  </div>
@@ -893,4 +972,217 @@ ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
893
972
  OUTPUT
894
973
  end
895
974
 
975
+ it "breaks up very long strings in tables on request (Word)" do
976
+ expect(xmlpp(IsoDoc::WordConvert.new({break_up_urls_in_tables: "true"}).cleanup(Nokogiri::XML(<<~"INPUT")).to_s)).to be_equivalent_to xmlpp(<<~"OUTPUT")
977
+ <html xmlns:epub="http://www.idpf.org/2007/ops">
978
+ <head>
979
+ <title>test</title>
980
+ <body lang="EN-US" link="blue" vlink="#954F72">
981
+ <div class="WordSection1">
982
+ <p>&#160;</p>
983
+ </div>
984
+ <br clear="all" class="section"/>
985
+ <div class="WordSection2">
986
+ <br clear="all" style="mso-special-character:line-break;page-break-before:always"/>
987
+ <div>
988
+ <h1 class="ForewordTitle">Foreword</h1>
989
+ <p class="TableTitle" align="center">
990
+ <b>Table 1&#160;&#8212; Repeatability and reproducibility of husked rice yield</b>
991
+ </p>
992
+ <table id="tableD-1" class="MsoISOTable" border="1" cellspacing="0" cellpadding="0">
993
+ <thead>
994
+ <tr>
995
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
996
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">Description</td>
997
+ <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">Rice sample</td>
998
+ </tr>
999
+ </thead>
1000
+ <tbody>
1001
+ <tr>
1002
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
1003
+ <td align="left" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;">http://www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
1004
+ <td align="center" style="border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;">www.example.com/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBB</td>
1005
+ </tr>
1006
+ </tbody>
1007
+ </table>
1008
+ </div>
1009
+ </div>
1010
+ </body>
1011
+ </html>
1012
+ INPUT
1013
+ <?xml version='1.0'?>
1014
+ <html xmlns:epub='http://www.idpf.org/2007/ops'>
1015
+ <head>
1016
+ <title>test</title>
1017
+ <body lang='EN-US' link='blue' vlink='#954F72'>
1018
+ <div class='WordSection1'>
1019
+ <p>&#xA0;</p>
1020
+ </div>
1021
+ <br clear='all' class='section'/>
1022
+ <div class='WordSection2'>
1023
+ <br clear='all' style='mso-special-character:line-break;page-break-before:always'/>
1024
+ <div>
1025
+ <h1 class='ForewordTitle'>Foreword</h1>
1026
+ <p class='TableTitle' align='center'>
1027
+ <b>Table 1&#xA0;&#x2014; Repeatability and reproducibility of husked rice yield</b>
1028
+ </p>
1029
+ <table id='tableD-1' class='MsoISOTable' border='1' cellspacing='0' cellpadding='0'>
1030
+ <thead>
1031
+ <tr>
1032
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
1033
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>Description</td>
1034
+ <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>Rice sample</td>
1035
+ </tr>
1036
+ </thead>
1037
+ <tbody>
1038
+ <tr>
1039
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
1040
+ http://www.example.com/ AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAA/ BBBBBBBBBBBBBBBBBBBBBBBBBBBB
1041
+ </td>
1042
+ <td align='left' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;'>
1043
+ http://www.example.com/ AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA AAAAAAAABBBBBBBBBBBBBBBBBBBBBB BBBBBB
1044
+ </td>
1045
+ <td align='center' style='border-top:solid windowtext 1.5pt;border-bottom:solid windowtext 1.0pt;'>
1046
+ www.example.com/ AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA ABBBBBBBBBBBBBBBBBBBBBBBBBBBB
1047
+ </td>
1048
+ </tr>
1049
+ </tbody>
1050
+ </table>
1051
+ </div>
1052
+ </div>
1053
+ </body>
1054
+ </head>
1055
+ </html>
1056
+ OUTPUT
1057
+ end
1058
+
1059
+ it "cleans up term sources" do
1060
+ c = IsoDoc::HtmlConvert.new({i18nyaml: "spec/assets/i18n.yaml"})
1061
+ c.i18n_init("en", "Latn")
1062
+ expect(xmlpp(c.textcleanup(<<~"INPUT").to_s)).to be_equivalent_to xmlpp(<<~"OUTPUT")
1063
+ #{HTML_HDR}
1064
+ <p class="zzSTDTitle1"/>
1065
+ <div id="_terms_and_definitions"><h1>1.&#160; Terms and Definitions</h1><p>For the purposes of this document,
1066
+ the following terms and definitions apply.</p>
1067
+ <p class="TermNum" id="paddy1">1.1.</p><p class="Terms" style="text-align:left;">paddy</p>
1068
+
1069
+ <p id="_eb29b35e-123e-4d1c-b50b-2714d41e747f">&lt;rice&gt; rice retaining its husk after threshing</p>
1070
+ <div id="_bd57bbf1-f948-4bae-b0ce-73c00431f892" class="example"><p class="example-title">EXAMPLE 1</p>
1071
+ <p id="_65c9a509-9a89-4b54-a890-274126aeb55c">Foreign seeds, husks, bran, sand, dust.</p>
1072
+ <ul>
1073
+ <li>A</li>
1074
+ </ul>
1075
+ </div>
1076
+ <div id="_bd57bbf1-f948-4bae-b0ce-73c00431f894" class="example"><p class="example-title">EXAMPLE 2</p>
1077
+ <ul>
1078
+ <li>A</li>
1079
+ </ul>
1080
+ </div>
1081
+
1082
+ <p>[TERMREF]
1083
+ <a href="#ISO7301">ISO 7301:2011, Clause 3.1</a>
1084
+ [MODIFICATION]The term "cargo rice" is shown as deprecated, and Note 1 to entry is not included here
1085
+ [/TERMREF]</p>
1086
+ <p>[TERMREF] Termbase IEV, term ID xyz [/TERMREF]</p>
1087
+ <p>[TERMREF] Termbase IEV, term ID xyz [MODIFICATION]with adjustments [/TERMREF]</p>
1088
+ <p class="TermNum" id="paddy">1.2.</p><p class="Terms" style="text-align:left;">paddy</p><p class="AltTerms" style="text-align:left;">paddy rice</p>
1089
+ <p class="AltTerms" style="text-align:left;">rough rice</p>
1090
+ <p class="DeprecatedTerms" style="text-align:left;">DEPRECATED: cargo rice</p>
1091
+ <p id="_eb29b35e-123e-4d1c-b50b-2714d41e747f">rice retaining its husk after threshing</p>
1092
+ <div id="_bd57bbf1-f948-4bae-b0ce-73c00431f893" class="example"><p class="example-title">EXAMPLE</p>
1093
+ <ul>
1094
+ <li>A</li>
1095
+ </ul>
1096
+ </div>
1097
+ <div class="Note"><p>Note 1 to entry: The starch of waxy rice consists almost entirely of amylopectin. The kernels have a tendency to stick together after cooking.</p></div>
1098
+ <div class="Note"><p>Note 2 to entry: <ul><li>A</li></ul><p id="_19830f33-e46c-42cc-94ca-a5ef101132d5">The starch of waxy rice consists almost entirely of amylopectin. The kernels have a tendency to stick together after cooking.</p></p></div>
1099
+ <p>[TERMREF]
1100
+ <a href="#ISO7301">ISO 7301:2011, Clause 3.1</a>
1101
+ [/TERMREF]</p></div>
1102
+ </div>
1103
+ </body>
1104
+ </html>
1105
+ INPUT
1106
+ <html xmlns:epub='http://www.idpf.org/2007/ops' lang='en'>
1107
+ <head/>
1108
+ <body lang='en'>
1109
+ <div class='title-section'>
1110
+ <p>&#160;</p>
1111
+ </div>
1112
+ <br/>
1113
+ <div class='prefatory-section'>
1114
+ <p>&#160;</p>
1115
+ </div>
1116
+ <br/>
1117
+ <div class='main-section'>
1118
+ <p class='zzSTDTitle1'/>
1119
+ <div id='_terms_and_definitions'>
1120
+ <h1>1.&#160; Terms and Definitions</h1>
1121
+ <p>For the purposes of this document, the following terms and definitions apply.</p>
1122
+ <p class='TermNum' id='paddy1'>1.1.</p>
1123
+ <p class='Terms' style='text-align:left;'>paddy</p>
1124
+ <p id='_eb29b35e-123e-4d1c-b50b-2714d41e747f'>&lt;rice&gt; rice retaining its husk after threshing</p>
1125
+ <div id='_bd57bbf1-f948-4bae-b0ce-73c00431f892' class='example'>
1126
+ <p class='example-title'>EXAMPLE 1</p>
1127
+ <p id='_65c9a509-9a89-4b54-a890-274126aeb55c'>Foreign seeds, husks, bran, sand, dust.</p>
1128
+ <ul>
1129
+ <li>A</li>
1130
+ </ul>
1131
+ </div>
1132
+ <div id='_bd57bbf1-f948-4bae-b0ce-73c00431f894' class='example'>
1133
+ <p class='example-title'>EXAMPLE 2</p>
1134
+ <ul>
1135
+ <li>A</li>
1136
+ </ul>
1137
+ </div>
1138
+ <p>
1139
+ [SOURCE:
1140
+ <a href='#ISO7301'>ISO 7301:2011, Clause 3.1</a>
1141
+ , modified &mdash; The term "cargo rice" is shown as deprecated, and
1142
+ Note 1 to entry is not included here; Termbase IEV, term ID xyz;
1143
+ Termbase IEV, term ID xyz, modified &mdash; with adjustments]
1144
+ </p>
1145
+ <p class='TermNum' id='paddy'>1.2.</p>
1146
+ <p class='Terms' style='text-align:left;'>paddy</p>
1147
+ <p class='AltTerms' style='text-align:left;'>paddy rice</p>
1148
+ <p class='AltTerms' style='text-align:left;'>rough rice</p>
1149
+ <p class='DeprecatedTerms' style='text-align:left;'>DEPRECATED: cargo rice</p>
1150
+ <p id='_eb29b35e-123e-4d1c-b50b-2714d41e747f'>rice retaining its husk after threshing</p>
1151
+ <div id='_bd57bbf1-f948-4bae-b0ce-73c00431f893' class='example'>
1152
+ <p class='example-title'>EXAMPLE</p>
1153
+ <ul>
1154
+ <li>A</li>
1155
+ </ul>
1156
+ </div>
1157
+ <div class='Note'>
1158
+ <p>
1159
+ Note 1 to entry: The starch of waxy rice consists almost entirely of
1160
+ amylopectin. The kernels have a tendency to stick together after
1161
+ cooking.
1162
+ </p>
1163
+ </div>
1164
+ <div class='Note'>
1165
+ <p>
1166
+ Note 2 to entry:
1167
+ <ul>
1168
+ <li>A</li>
1169
+ </ul>
1170
+ <p id='_19830f33-e46c-42cc-94ca-a5ef101132d5'>
1171
+ The starch of waxy rice consists almost entirely of amylopectin.
1172
+ The kernels have a tendency to stick together after cooking.
1173
+ </p>
1174
+ </p>
1175
+ </div>
1176
+ <p>
1177
+ [SOURCE:
1178
+ <a href='#ISO7301'>ISO 7301:2011, Clause 3.1</a>
1179
+ ]
1180
+ </p>
1181
+ </div>
1182
+ </div>
1183
+ </body>
1184
+ </html>
1185
+ OUTPUT
1186
+ end
1187
+
896
1188
  end
@@ -24,9 +24,24 @@ RSpec.describe IsoDoc do
24
24
  <br/>
25
25
  <div>
26
26
  <h1 class="ForewordTitle">Foreword</h1>
27
- <p>A.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
28
- <p>B.<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
29
- <p>C.<a rel="footnote" href="#fn:1" epub:type="footnote"><sup>1</sup></a></p>
27
+ <p>
28
+ A.
29
+ <a class='FootnoteRef' href='#fn:2'>
30
+ <sup>2</sup>
31
+ </a>
32
+ </p>
33
+ <p>
34
+ B.
35
+ <a class='FootnoteRef' href='#fn:2'>
36
+ <sup>2</sup>
37
+ </a>
38
+ </p>
39
+ <p>
40
+ C.
41
+ <a class='FootnoteRef' href='#fn:1'>
42
+ <sup>1</sup>
43
+ </a>
44
+ </p>
30
45
  </div>
31
46
  <p class="zzSTDTitle1"/>
32
47
  <aside id="fn:2" class="footnote">
@@ -80,7 +95,7 @@ RSpec.describe IsoDoc do
80
95
  <p>
81
96
  A.
82
97
  <span style='mso-bookmark:_Ref'>
83
- <a href='#ftn2' epub:type='footnote'>
98
+ <a href='#ftn2' epub:type='footnote' class='FootnoteRef'>
84
99
  <sup>2</sup>
85
100
  </a>
86
101
  </span>
@@ -96,7 +111,7 @@ RSpec.describe IsoDoc do
96
111
  <p>
97
112
  C.
98
113
  <span style='mso-bookmark:_Ref'>
99
- <a href='#ftn1' epub:type='footnote'>
114
+ <a href='#ftn1' epub:type='footnote' class='FootnoteRef'>
100
115
  <sup>1</sup>
101
116
  </a>
102
117
  </span>