Module: IsoDoc::WordFunction::Postprocess
- Included in:
- IsoDoc::WordConvert
- Defined in:
- lib/isodoc/word_function/postprocess.rb,
lib/isodoc/word_function/postprocess_toc.rb,
lib/isodoc/word_function/postprocess_cover.rb,
lib/isodoc/word_function/postprocess_table.rb
Constant Summary collapse
- TABLE_FN_ADJ =
<<~XPATH.freeze //a[@class='TableFootnoteRef'][following-sibling::*[1][self::a[@class='TableFootnoteRef']]] XPATH
- FN_ADJ =
<<~XPATH.freeze //span[@class='MsoFootnoteReference'][following-sibling::*[1][self::span[@class='MsoFootnoteReference']]] XPATH
- WORD_TOC_SUFFIX1 =
<<~TOC.freeze <p class="MsoToc1"><span lang="EN-GB"><span style='mso-element:field-end'></span></span><span lang="EN-GB"><o:p> </o:p></span></p> TOC
- WORD_NOKOHEAD =
add namespaces for Word fragments
<<~HERE.freeze <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml"> <head> <title></title> <meta charset="UTF-8" /> </head> <body> </body> </html> HERE
Instance Method Summary collapse
- #assemble_toc(docxml, level) ⇒ Object
- #authority_cleanup(docxml) ⇒ Object
- #authority_cleanup1(docxml, klass) ⇒ Object
-
#colgroup_widths(table) ⇒ Object
assume percentages.
- #coverpage_note_cleanup(docxml) ⇒ Object
- #figure_toc_class ⇒ Object
- #figure_toc_xpath ⇒ Object
- #generate_header(filename, _dir) ⇒ Object
- #header_params(filename) ⇒ Object
- #insert_toc(intro, docxml, level) ⇒ Object
- #list_add(xpath, lvl) ⇒ Object
- #make_figure_word_toc(docxml) ⇒ Object
- #make_recommendation_word_toc(docxml) ⇒ Object
- #make_table_word_toc(docxml) ⇒ Object
- #make_WordToC(docxml, level) ⇒ Object
- #postprocess(result, filename, dir) ⇒ Object
- #postprocess_cleanup(result) ⇒ Object
- #recommmendation_sort_key(header) ⇒ Object
- #recommmendation_sort_key1(type) ⇒ Object
- #remove_toc_div(docxml) ⇒ Object
- #reqt_toc_class ⇒ Object
- #reqt_toc_xpath ⇒ Object
- #sourcecode_style ⇒ Object
- #split_at_section_break(docxml, sect, brk, idx) ⇒ Object
- #style_update(node, css) ⇒ Object
- #table_note_cleanup(docxml) ⇒ Object
-
#table_toc_class ⇒ Object
inheriting gems need to add native Word name of style, if different including both CSS style name and human readable style name.
- #table_toc_xpath ⇒ Object
- #to_sourcecode_para(pre) ⇒ Object
- #to_word_xhtml_fragment(xml) ⇒ Object
- #toc_word_class_list(classes) ⇒ Object
- #toWord(result, filename, dir, header) ⇒ Object
- #word_admonition_images(docxml) ⇒ Object
- #word_annex_cleanup(docxml) ⇒ Object
- #word_cleanup(docxml) ⇒ Object
- #word_colgroup(docxml) ⇒ Object
- #word_cover(docxml) ⇒ Object
- #word_example_cleanup(docxml) ⇒ Object
-
#word_floating_titles(docxml) ⇒ Object
move p.h1 (floating title) after any page, section breaks.
- #word_fn_cleanup(docxml) ⇒ Object
- #word_image_caption(docxml) ⇒ Object
- #word_intro(docxml, level) ⇒ Object
- #word_list_continuations(docxml) ⇒ Object
- #word_nested_tables(docxml) ⇒ Object
- #word_nonbreaking_spans(docxml) ⇒ Object
- #word_preface(docxml) ⇒ Object
- #word_pseudocode_cleanup(docxml) ⇒ Object
- #word_remove_empty_sections(docxml) ⇒ Object
- #word_remove_empty_toc(docxml) ⇒ Object
-
#word_remove_pb_before_annex(docxml) ⇒ Object
applies for <div class=“WordSectionN_M”><p><pagebreak/></p>…
- #word_section_breaks(docxml) ⇒ Object
- #word_section_breaks1(docxml, sect) ⇒ Object
- #word_sourcecode_annotations(html) ⇒ Object
- #word_sourcecode_table(docxml) ⇒ Object
- #word_tab_clean(docxml) ⇒ Object
- #word_table_align(docxml) ⇒ Object
- #word_table_pagebreak(docxml) ⇒ Object
- #word_table_separator(docxml) ⇒ Object
- #word_toc_entry(toclevel, heading) ⇒ Object
- #word_toc_figure_preface1 ⇒ Object
- #word_toc_preface(level) ⇒ Object
- #word_toc_reqt_preface1 ⇒ Object
- #word_toc_table_preface1 ⇒ Object
- #wordstylesheet_update ⇒ Object
Instance Method Details
#assemble_toc(docxml, level) ⇒ Object
24 25 26 27 28 29 30 31 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 24 def assemble_toc(docxml, level) toc = "" toc += make_WordToC(docxml, level) toc += make_table_word_toc(docxml) toc += make_figure_word_toc(docxml) toc += make_recommendation_word_toc(docxml) toc end |
#authority_cleanup(docxml) ⇒ Object
81 82 83 84 85 86 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 81 def (docxml) %w(copyright license legal feedback).each do |t| (docxml, t) end coverpage_note_cleanup(docxml) end |
#authority_cleanup1(docxml, klass) ⇒ Object
69 70 71 72 73 74 75 76 77 78 79 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 69 def (docxml, klass) dest = docxml.at("//div[@id = 'boilerplate-#{klass}-destination']") auth = docxml.at("//div[@id = 'boilerplate-#{klass}' " \ "or @class = 'boilerplate-#{klass}']") auth&.xpath(".//h1[not(text())] | .//h2[not(text())]")&.each(&:remove) auth&.xpath(".//h1 | .//h2")&.each do |h| h.name = "p" h["class"] = "TitlePageSubhead" end dest and auth and dest.replace(auth.remove) end |
#colgroup_widths(table) ⇒ Object
assume percentages
39 40 41 42 43 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 39 def colgroup_widths(table) table.xpath("./colgroup/col").each_with_object([]) do |c, m| m << c["width"].sub(/%$/, "").to_f end end |
#coverpage_note_cleanup(docxml) ⇒ Object
88 89 90 91 92 93 94 95 96 97 98 99 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 88 def coverpage_note_cleanup(docxml) if dest = docxml.at("//div[@id = 'coverpage-note-destination']") auth = docxml.xpath("//*[@coverpage]") if auth.empty? then dest.remove else auth.each do |x| dest << x.remove end end end docxml.xpath("//*[@coverpage]").each { |x| x.delete("coverpage") } end |
#figure_toc_class ⇒ Object
85 86 87 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 85 def figure_toc_class %w(FigureTitle figuretitle) end |
#figure_toc_xpath ⇒ Object
135 136 137 138 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 135 def figure_toc_xpath attr = figure_toc_class.map { |x| "@class = '#{x}'" } "//p[#{attr.join(' or ')}]" end |
#generate_header(filename, _dir) ⇒ Object
101 102 103 104 105 106 107 108 109 110 111 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 101 def generate_header(filename, _dir) @header or return nil template = IsoDoc::Common.liquid(File.read(@header, encoding: "UTF-8")) params = header_params(filename) Tempfile.open(%w(header html), mode: File::BINARY | File::SHARE_DELETE, encoding: "utf-8") do |f| f.write(template.render(params)) f end end |
#header_params(filename) ⇒ Object
113 114 115 116 117 118 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 113 def header_params(filename) = @meta.get.merge(@labels ? { labels: @labels } : {}) .merge(@meta.labels ? { labels: @meta.labels } : {}) [:filename] = filename .transform_keys(&:to_s) end |
#insert_toc(intro, docxml, level) ⇒ Object
4 5 6 7 8 9 10 11 12 13 14 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 4 def insert_toc(intro, docxml, level) toc = assemble_toc(docxml, level) if intro&.include?("WORDTOC") remove_toc_div(docxml) intro.sub("WORDTOC", toc) else source = docxml.at("//div[@class = 'TOC']") and source.children = toc intro end end |
#list_add(xpath, lvl) ⇒ Object
136 137 138 139 140 141 142 143 144 145 146 147 148 |
# File 'lib/isodoc/word_function/postprocess.rb', line 136 def list_add(xpath, lvl) xpath.each do |list| (list.xpath(".//li") - list.xpath(".//ol//li | .//ul//li")).each do |l| l.xpath("./p | ./div | ./table").each_with_index do |p, i| i.zero? or p.wrap(%{<div class="ListContLevel#{lvl}"/>}) end list_add(l.xpath(".//ul") - l.xpath(".//ul//ul | .//ol//ul"), lvl + 1) list_add(l.xpath(".//ol") - l.xpath(".//ul//ol | .//ol//ol"), lvl + 1) end end end |
#make_figure_word_toc(docxml) ⇒ Object
140 141 142 143 144 145 146 147 148 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 140 def make_figure_word_toc(docxml) (docxml.at(figure_toc_xpath) && @tocfigurestitle) or return "" toc = %{<p class="TOCTitle">#{@tocfigurestitle}</p>} docxml.xpath(figure_toc_xpath).each do |h| toc += word_toc_entry(1, header_strip(h)) end toc.sub(/(<p class="MsoToc1">)/, %{\\1#{word_toc_figure_preface1}}) + WORD_TOC_SUFFIX1 end |
#make_recommendation_word_toc(docxml) ⇒ Object
155 156 157 158 159 160 161 162 163 164 165 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 155 def make_recommendation_word_toc(docxml) (docxml.at(reqt_toc_xpath) && @tocrecommendationstitle) or return "" toc = %{<p class="TOCTitle">#{@tocrecommendationstitle}</p>} docxml.xpath(reqt_toc_xpath).sort_by do |h| recommmendation_sort_key(h.text) end.each do |h| toc += word_toc_entry(1, header_strip(h)) end toc.sub(/(<p class="MsoToc1">)/, %{\\1#{word_toc_reqt_preface1}}) + WORD_TOC_SUFFIX1 end |
#make_table_word_toc(docxml) ⇒ Object
125 126 127 128 129 130 131 132 133 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 125 def make_table_word_toc(docxml) (docxml.at(table_toc_xpath) && @toctablestitle) or return "" toc = %{<p class="TOCTitle">#{@toctablestitle}</p>} docxml.xpath(table_toc_xpath).each do |h| toc += word_toc_entry(1, header_strip(h)) end toc.sub(/(<p class="MsoToc1">)/, %{\\1#{word_toc_table_preface1}}) + WORD_TOC_SUFFIX1 end |
#make_WordToC(docxml, level) ⇒ Object
63 64 65 66 67 68 69 70 71 72 73 74 75 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 63 def make_WordToC(docxml, level) toc = "" if source = docxml.at("//div[@class = 'TOC']") toc = to_xml(source.children) end # docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]"). xpath = (1..level).each.map { |i| "//h#{i}" }.join (" | ") docxml.xpath(xpath).each do |h| toc += word_toc_entry(h.name[1].to_i, header_strip(h)) end toc.sub(/(<p class="MsoToc1">)/, %{\\1#{word_toc_preface(level)}}) + WORD_TOC_SUFFIX1 end |
#postprocess(result, filename, dir) ⇒ Object
9 10 11 12 13 14 15 16 |
# File 'lib/isodoc/word_function/postprocess.rb', line 9 def postprocess(result, filename, dir) result = postprocess_cleanup(result) filename = filename.sub(/\.doc$/, "") header = generate_header(filename, dir) @wordstylesheet = wordstylesheet_update toWord(result, filename, dir, header) @files_to_delete.each { |f| FileUtils.rm_f f } end |
#postprocess_cleanup(result) ⇒ Object
18 19 20 21 22 |
# File 'lib/isodoc/word_function/postprocess.rb', line 18 def postprocess_cleanup(result) result = cleanup(to_xhtml(textcleanup(result))) from_xhtml(word_cleanup(result)) .gsub("-DOUBLE_HYPHEN_ESCAPE-", "--") end |
#recommmendation_sort_key(header) ⇒ Object
167 168 169 170 171 172 173 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 167 def recommmendation_sort_key(header) m = /^([^0-9]+) (\d+)/.match(header) || /^([^:]+)/.match(header) m ||= [header, nil] ret = "#{recommmendation_sort_key1(m[1]&.strip)}::" m[2] and ret += ("%04d" % m[2].to_i).to_s ret end |
#recommmendation_sort_key1(type) ⇒ Object
175 176 177 178 179 180 181 182 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 175 def recommmendation_sort_key1(type) case type&.downcase when "requirement" then "04" when "recommendation" then "05" when "permission" then "06" else type end end |
#remove_toc_div(docxml) ⇒ Object
16 17 18 19 20 21 22 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 16 def remove_toc_div(docxml) s = docxml.at("//div[@class = 'TOC']") or return prev = s.previous_element prev&.elements&.first&.name == "br" and prev&.remove # page break s.remove end |
#reqt_toc_class ⇒ Object
89 90 91 92 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 89 def reqt_toc_class %w(RecommendationTitle RecommendationTestTitle recommendationtitle recommendationtesttitle) end |
#reqt_toc_xpath ⇒ Object
150 151 152 153 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 150 def reqt_toc_xpath attr = reqt_toc_class.map { |x| "@class = '#{x}'" } "//p[#{attr.join(' or ')}]" end |
#sourcecode_style ⇒ Object
36 37 38 |
# File 'lib/isodoc/word_function/postprocess.rb', line 36 def sourcecode_style "Sourcecode" end |
#split_at_section_break(docxml, sect, brk, idx) ⇒ Object
140 141 142 143 144 145 146 147 148 149 150 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 140 def split_at_section_break(docxml, sect, brk, idx) move = brk.parent.xpath("following::node()") & brk.document.xpath("//div[@class = '#{sect}']//*") ins = docxml.at("//div[@class = '#{sect}']") .after("<div class='#{sect}_#{idx}'/>").next_element move.each do |m| next if m.at("./ancestor::div[@class = '#{sect}_#{idx}']") ins << m.remove end end |
#style_update(node, css) ⇒ Object
53 54 55 56 57 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 53 def style_update(node, css) node or return node["style"] = node["style"] ? node["style"].sub(/;?$/, ";#{css}") : css end |
#table_note_cleanup(docxml) ⇒ Object
4 5 6 7 8 9 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 4 def table_note_cleanup(docxml) super # preempt html2doc putting MsoNormal there docxml.xpath("//p[not(self::*[@class])][ancestor::*[@class = 'Note']]") .each { |p| p["class"] = "Note" } end |
#table_toc_class ⇒ Object
inheriting gems need to add native Word name of style, if different including both CSS style name and human readable style name. Any human readable style name needs to come first for the Word template to work in regenerating the ToC
81 82 83 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 81 def table_toc_class %w(TableTitle tabletitle) end |
#table_toc_xpath ⇒ Object
120 121 122 123 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 120 def table_toc_xpath attr = table_toc_class.map { |x| "@class = '#{x}'" } "//p[#{attr.join(' or ')}]" end |
#to_sourcecode_para(pre) ⇒ Object
99 100 101 102 103 104 105 106 107 108 |
# File 'lib/isodoc/word_function/postprocess.rb', line 99 def to_sourcecode_para(pre) @sourcecode = "pre" pre.traverse do |x| x.text? or next ret = [] text_parse(x, ret) x.replace(ret.join) end @sourcecode = false end |
#to_word_xhtml_fragment(xml) ⇒ Object
48 49 50 51 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 48 def to_word_xhtml_fragment(xml) doc = ::Nokogiri::XML.parse(WORD_NOKOHEAD) ::Nokogiri::XML::DocumentFragment.new(doc, xml, doc.root) end |
#toc_word_class_list(classes) ⇒ Object
94 95 96 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 94 def toc_word_class_list(classes) classes.map { |x| "#{x},1" }.join(",") end |
#toWord(result, filename, dir, header) ⇒ Object
24 25 26 27 28 29 30 31 32 33 34 |
# File 'lib/isodoc/word_function/postprocess.rb', line 24 def toWord(result, filename, dir, header) Html2Doc.new( filename: filename, imagedir: @localdir, stylesheet: @wordstylesheet&.path, header_file: header&.path, dir: dir, asciimathdelims: [@openmathdelim, @closemathdelim], liststyles: { ul: @ulstyle, ol: @olstyle } ).process(result) header&.unlink @wordstylesheet.unlink if @wordstylesheet.is_a?(Tempfile) end |
#word_admonition_images(docxml) ⇒ Object
40 41 42 43 44 45 |
# File 'lib/isodoc/word_function/postprocess.rb', line 40 def word_admonition_images(docxml) docxml.xpath("//div[@class = 'Admonition']//img").each do |i| i["width"], i["height"] = Vectory.image_resize(i, image_localfile(i), @maxheight, 300) end end |
#word_annex_cleanup(docxml) ⇒ Object
150 |
# File 'lib/isodoc/word_function/postprocess.rb', line 150 def word_annex_cleanup(docxml); end |
#word_cleanup(docxml) ⇒ Object
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
# File 'lib/isodoc/word_function/postprocess.rb', line 47 def word_cleanup(docxml) word_annex_cleanup(docxml) word_preface(docxml) word_sourcecode_annotations(docxml) word_sourcecode_table(docxml) word_nonbreaking_spans(docxml) word_nested_tables(docxml) word_colgroup(docxml) word_table_align(docxml) word_table_pagebreak(docxml) word_table_separator(docxml) word_admonition_images(docxml) word_list_continuations(docxml) word_example_cleanup(docxml) word_pseudocode_cleanup(docxml) word_image_caption(docxml) word_floating_titles(docxml) word_section_breaks(docxml) word_tab_clean(docxml) word_fn_cleanup(docxml) (docxml) word_remove_empty_toc(docxml) word_remove_empty_sections(docxml) docxml end |
#word_colgroup(docxml) ⇒ Object
11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 11 def word_colgroup(docxml) cells2d = {} docxml.xpath("//table[colgroup]").each do |t| w = colgroup_widths(t) t.xpath(".//tr").each_with_index { |_tr, r| cells2d[r] = {} } t.xpath(".//tr").each_with_index do |tr, r| tr.xpath("./td | ./th").each_with_index do |td, _i| x = 0 rs = td.attr("rowspan")&.to_i || 1 cs = td.attr("colspan")&.to_i || 1 while cells2d[r][x] x += 1 end (r..(r + rs - 1)).each do |y2| cells2d[y2].nil? and next (x..(x + cs - 1)).each { |x2| cells2d[y2][x2] = 1 } end width = (x..(x + cs - 1)).each_with_object({ width: 0 }) do |z, m| m[:width] += w[z] end td["width"] = "#{width[:width]}%" x += cs end end end end |
#word_cover(docxml) ⇒ Object
20 21 22 23 24 25 26 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 20 def word_cover(docxml) ins = docxml.at('//div[@class="WordSection1"]') or return cover = File.read(@wordcoverpage, encoding: "UTF-8") cover = populate_template(cover, :word) coverxml = to_word_xhtml_fragment(cover) ins.add_first_child coverxml.to_xml(encoding: "US-ASCII") end |
#word_example_cleanup(docxml) ⇒ Object
152 153 154 155 156 |
# File 'lib/isodoc/word_function/postprocess.rb', line 152 def word_example_cleanup(docxml) docxml.xpath("//div[@class = 'example']//p[not(@class)]").each do |p| p["class"] = "example" end end |
#word_floating_titles(docxml) ⇒ Object
move p.h1 (floating title) after any page, section breaks
177 178 179 180 181 182 183 184 185 186 187 188 189 |
# File 'lib/isodoc/word_function/postprocess.rb', line 177 def word_floating_titles(docxml) docxml.xpath("//p[@class = 'section-break' or @class = 'page-break']") .each do |b| out = b.xpath("./preceding-sibling::*").reverse .each_with_object([]) do |p, m| (p.name == "p" && p["class"] == "h1") or break m m << p end b.delete("class") out.empty? and next out[-1].previous = b.remove end end |
#word_fn_cleanup(docxml) ⇒ Object
210 211 212 213 214 215 216 217 |
# File 'lib/isodoc/word_function/postprocess.rb', line 210 def word_fn_cleanup(docxml) docxml.xpath(TABLE_FN_ADJ).each do |a| a.next = '<span class="TableFootnoteRef">, </span>' end docxml.xpath(FN_ADJ).each do |a| a.next = '<span class="MsoFootnoteReference">, </span>' end end |
#word_image_caption(docxml) ⇒ Object
118 119 120 121 122 123 124 125 126 127 |
# File 'lib/isodoc/word_function/postprocess.rb', line 118 def word_image_caption(docxml) docxml.xpath("//p[@class = 'FigureTitle' or @class = 'SourceTitle']") .each do |t| if t.previous_element&.name == "img" img = t.previous_element t.previous_element.swap("<p class='figure'>#{img.to_xml}</p>") end style_update(t.previous_element, "page-break-after:avoid;") end end |
#word_intro(docxml, level) ⇒ Object
28 29 30 31 32 33 34 35 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 28 def word_intro(docxml, level) ins = docxml.at('//div[@class="WordSection2"]') or return intro = insert_toc(File.read(@wordintropage, encoding: "UTF-8"), docxml, level) intro = populate_template(intro, :word) introxml = to_word_xhtml_fragment(intro) ins.add_first_child introxml.to_xml(encoding: "US-ASCII") end |
#word_list_continuations(docxml) ⇒ Object
129 130 131 132 133 134 |
# File 'lib/isodoc/word_function/postprocess.rb', line 129 def word_list_continuations(docxml) list_add(docxml.xpath("//ul[not(ancestor::ul) and not(ancestor::ol)]"), 1) list_add(docxml.xpath("//ol[not(ancestor::ul) and not(ancestor::ol)]"), 1) end |
#word_nested_tables(docxml) ⇒ Object
45 46 47 48 49 50 51 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 45 def word_nested_tables(docxml) docxml.xpath("//table").each do |t| t.xpath(".//table").reverse_each do |tt| t.next = tt.remove end end end |
#word_nonbreaking_spans(docxml) ⇒ Object
191 192 193 194 195 196 197 198 199 200 |
# File 'lib/isodoc/word_function/postprocess.rb', line 191 def word_nonbreaking_spans(docxml) docxml.xpath("//span[@style = 'white-space: nowrap;']").each do |s| s.delete("style") s.traverse do |n| n.text? or next n.replace(n.text.gsub(" ", "\u00a0").gsub("-", "\u2011") .gsub(/\.(?=.)/, ".\u2060")) end end end |
#word_preface(docxml) ⇒ Object
4 5 6 7 8 9 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 4 def word_preface(docxml) @wordcoverpage && !@wordcoverpage.empty? and word_cover(docxml) @wordintropage && !@wordintropage.empty? and word_intro(docxml, @wordToClevels) end |
#word_pseudocode_cleanup(docxml) ⇒ Object
158 159 160 161 162 |
# File 'lib/isodoc/word_function/postprocess.rb', line 158 def word_pseudocode_cleanup(docxml) docxml.xpath("//div[@class = 'pseudocode']//p[not(@class)]").each do |p| p["class"] = "pseudocode" end end |
#word_remove_empty_sections(docxml) ⇒ Object
11 12 13 14 15 16 17 18 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 11 def word_remove_empty_sections(docxml) %w(WordSection1 WordSection2).each do |x| ins = docxml.at("//div[@class='#{x}']") or next @c.decode(ins.text).gsub(/\p{Z}|\p{C}/, "").strip.empty? or next ins.next_element.remove ins.remove end end |
#word_remove_empty_toc(docxml) ⇒ Object
73 74 75 76 |
# File 'lib/isodoc/word_function/postprocess.rb', line 73 def word_remove_empty_toc(docxml) docxml.at("//div[@class = 'TOC']//p[@class = 'MsoToc1']") and return remove_toc_div(docxml) end |
#word_remove_pb_before_annex(docxml) ⇒ Object
applies for <div class=“WordSectionN_M”><p><pagebreak/></p>…
165 166 167 168 169 170 171 172 173 174 |
# File 'lib/isodoc/word_function/postprocess.rb', line 165 def word_remove_pb_before_annex(docxml) docxml.xpath("//div[p/br]").each do |d| /^WordSection\d+_\d+$/.match(d["class"]) or next (d.elements[0].name == "p" && !d.elements[0].elements.empty?) or next (d.elements[0].elements[0].name == "br" && d.elements[0].elements[0]["style"] == "mso-special-character:line-break;page-break-before:always") or next d.elements[0].remove end end |
#word_section_breaks(docxml) ⇒ Object
120 121 122 123 124 125 126 127 128 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 120 def word_section_breaks(docxml) @landscapestyle = "" word_section_breaks1(docxml, "WordSection2") word_section_breaks1(docxml, "WordSection3") word_remove_pb_before_annex(docxml) docxml.xpath("//br[@orientation]").each do |br| br.delete("orientation") end end |
#word_section_breaks1(docxml, sect) ⇒ Object
130 131 132 133 134 135 136 137 138 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 130 def word_section_breaks1(docxml, sect) docxml.xpath("//div[@class = '#{sect}']//br[@orientation]").reverse .each_with_index do |br, i| @landscapestyle += "\ndiv.#{sect}_#{i} {page:#{sect}" \ "#{br['orientation'] == 'landscape' ? 'L' : 'P'};}\n" split_at_section_break(docxml, sect, br, i) end end |
#word_sourcecode_annotations(html) ⇒ Object
78 79 80 81 82 83 84 85 86 87 |
# File 'lib/isodoc/word_function/postprocess.rb', line 78 def word_sourcecode_annotations(html) ann = ".//div[@class = 'annotation']" html.xpath("//p[@class = '#{sourcecode_style}'][#{ann}]") .each do |p| ins = p.after("<p class='#{sourcecode_style}'/>").next_element p.xpath(ann).each do |d| ins << d.remove.children end end end |
#word_sourcecode_table(docxml) ⇒ Object
89 90 91 92 93 94 95 96 97 |
# File 'lib/isodoc/word_function/postprocess.rb', line 89 def word_sourcecode_table(docxml) s = "p[@class='#{sourcecode_style}']" docxml.xpath("//#{s}/div[@class='table_container']").each do |d| pre = d.at(".//#{s}") to_sourcecode_para(pre) d["id"] = d.parent["id"] d.parent.replace(d) end end |
#word_tab_clean(docxml) ⇒ Object
110 111 112 113 114 115 116 |
# File 'lib/isodoc/word_function/postprocess.rb', line 110 def word_tab_clean(docxml) docxml.xpath("//p[@class='Biblio']//span[@style='mso-tab-count:1']") .each do |s| s.next&.text? or next s.next.replace(@c.encode(s.next.text.sub(/^\s+/, ""), :hexadecimal)) end end |
#word_table_align(docxml) ⇒ Object
59 60 61 62 63 64 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 59 def word_table_align(docxml) docxml.xpath("//td[@align]/p | //th[@align]/p").each do |p| p["align"] and next style_update(p, "text-align: #{p.parent['align']}") end end |
#word_table_pagebreak(docxml) ⇒ Object
74 75 76 77 78 79 80 81 82 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 74 def word_table_pagebreak(docxml) docxml.xpath("//td[@style] | //th[@style]").each do |t| s = /(page-break-after:[^;]+)/.match(t["style"]) (s && s[1]) or next t.xpath(".//div | .//p | .//pre").each do |p| style_update(p, s[1]) end end end |
#word_table_separator(docxml) ⇒ Object
66 67 68 69 70 71 72 |
# File 'lib/isodoc/word_function/postprocess_table.rb', line 66 def word_table_separator(docxml) docxml.xpath("//p[@class = 'TableTitle']").each do |t| t.children.empty? or next t["style"] = t["style"].sub(/;?$/, ";font-size:0pt;") t.children = " " end end |
#word_toc_entry(toclevel, heading) ⇒ Object
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 33 def word_toc_entry(toclevel, heading) bookmark = bookmarkid # Random.rand(1000000000) <<~TOC <p class="MsoToc#{toclevel}"><span class="MsoHyperlink"><span lang="EN-GB" style='mso-no-proof:yes'> <a href="#_Toc#{bookmark}">#{heading}<span lang="EN-GB" class="MsoTocTextSpan"> <span style='mso-tab-count:1 dotted'>. </span></span><span lang="EN-GB" class="MsoTocTextSpan"> <span style='mso-element:field-begin'></span></span> <span lang="EN-GB" class="MsoTocTextSpan"> PAGEREF _Toc#{bookmark} \\h </span> <span lang="EN-GB" class="MsoTocTextSpan"><span style='mso-element:field-separator'></span></span><span lang="EN-GB" class="MsoTocTextSpan">1</span> <span lang="EN-GB" class="MsoTocTextSpan"></span><span lang="EN-GB" class="MsoTocTextSpan"><span style='mso-element:field-end'></span></span></a></span></span></p> TOC end |
#word_toc_figure_preface1 ⇒ Object
113 114 115 116 117 118 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 113 def word_toc_figure_preface1 <<~TOC <span lang="EN-GB"><span style='mso-element:field-begin'></span><span style='mso-spacerun:yes'> </span>TOC \\h \\z \\t "#{toc_word_class_list figure_toc_class}" <span style='mso-element:field-separator'></span></span> TOC end |
#word_toc_preface(level) ⇒ Object
49 50 51 52 53 54 55 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 49 def word_toc_preface(level) <<~TOC <span lang="EN-GB"><span style='mso-element:field-begin'></span><span style='mso-spacerun:yes'> </span>TOC \\o "1-#{level}" \\h \\z \\u <span style='mso-element:field-separator'></span></span> TOC end |
#word_toc_reqt_preface1 ⇒ Object
98 99 100 101 102 103 104 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 98 def word_toc_reqt_preface1 <<~TOC <span lang="EN-GB"><span style='mso-element:field-begin'></span><span style='mso-spacerun:yes'> </span>TOC \\h \\z \\t "#{toc_word_class_list reqt_toc_class}" <span style='mso-element:field-separator'></span></span> TOC end |
#word_toc_table_preface1 ⇒ Object
106 107 108 109 110 111 |
# File 'lib/isodoc/word_function/postprocess_toc.rb', line 106 def word_toc_table_preface1 <<~TOC <span lang="EN-GB"><span style='mso-element:field-begin'></span><span style='mso-spacerun:yes'> </span>TOC \\h \\z \\t "#{toc_word_class_list table_toc_class}" <span style='mso-element:field-separator'></span></span> TOC end |
#wordstylesheet_update ⇒ Object
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 53 def wordstylesheet_update @wordstylesheet.nil? and return f = File.open(@wordstylesheet.path, "a") @landscapestyle.empty? or f.write(@landscapestyle) s = @meta.get[:code_css] and f.write(s.gsub(/sourcecode/, "p.#{sourcecode_style}")) if @wordstylesheet_override && @wordstylesheet f.write(@wordstylesheet_override.read) @wordstylesheet_override.close elsif @wordstylesheet_override && !@wordstylesheet @wordstylesheet = @wordstylesheet_override end f.close @wordstylesheet end |