Module: IsoDoc::WordFunction::Postprocess

Included in:
IsoDoc::WordConvert
Defined in:
lib/isodoc/word_function/postprocess.rb,
lib/isodoc/word_function/postprocess_cover.rb

Constant Summary collapse

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
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>&nbsp;</o:p></span></p>
TOC

Instance Method Summary collapse

Instance Method Details

#authority_cleanup(docxml) ⇒ Object 



100
101
102
103
104
 
# File 'lib/isodoc/word_function/postprocess.rb', line 100

def authority_cleanup(docxml)
  %w(copyright license legal feedback).each do |t|
    authority_cleanup1(docxml, t)
  end
end

#authority_cleanup1(docxml, klass) ⇒ Object 



89
90
91
92
93
94
95
96
97
98
 
# File 'lib/isodoc/word_function/postprocess.rb', line 89

def authority_cleanup1(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 { |h| h.remove }
  auth&.xpath(".//h1 | .//h2")&.each do |h|
    h.name = "p"
    h["class"] = "TitlePageSubhead"
  end
  dest and auth and dest.replace(auth.remove)
end

#generate_header(filename, _dir) ⇒ Object 



183
184
185
186
187
188
189
190
191
192
193
 
# File 'lib/isodoc/word_function/postprocess.rb', line 183

def generate_header(filename, _dir)
  return nil unless @header
  template = IsoDoc::Common.liquid(File.read(@header, encoding: "UTF-8"))
  meta = @meta.get.merge(@labels || {}).merge(@meta.labels || {})
  meta[:filename] = filename
  params = meta.map { |k, v| [k.to_s, v] }.to_h
  Tempfile.open(%w(header html), :encoding => "utf-8") do |f|
    f.write(template.render(params))
    f
  end
end

#insert_toc(intro, docxml, level) ⇒ Object 



25
26
27
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 25

def insert_toc(intro, docxml, level)
  intro.sub(/WORDTOC/, make_WordToC(docxml, level))
end

#list_add(xpath, lvl) ⇒ Object 



127
128
129
130
131
132
133
134
135
136
137
138
 
# File 'lib/isodoc/word_function/postprocess.rb', line 127

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|
        next if i == 0
        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_WordToC(docxml, level) ⇒ Object 



68
69
70
71
72
73
74
75
76
77
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 68

def make_WordToC(docxml, level)
  toc = ""
  #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 



34
35
36
37
38
39
40
 
# File 'lib/isodoc/word_function/postprocess.rb', line 34

def postprocess(result, filename, dir)
  filename = filename.sub(/\.doc$/, "")
  header = generate_header(filename, dir)
  result = from_xhtml(cleanup(to_xhtml(textcleanup(result))))
  toWord(result, filename, dir, header)
  @files_to_delete.each { |f| FileUtils.rm_f f }
end

#split_at_section_break(docxml, sect, br, i) ⇒ Object 



212
213
214
215
216
217
218
219
220
221
 
# File 'lib/isodoc/word_function/postprocess.rb', line 212

def split_at_section_break(docxml, sect, br, i)
  move = br.parent.xpath("following::node()") &
    br.document.xpath("//div[@class = '#{sect}']//*")
  ins = docxml.at("//div[@class = '#{sect}']").
    after("<div class='#{sect}_#{i}'/>").next_element
  move.each do |m|
    next if m.at("./ancestor::div[@class = '#{sect}_#{i}']")
    ins << m.remove
  end
end

#style_update(node, css) ⇒ Object 



106
107
108
109
 
# File 'lib/isodoc/word_function/postprocess.rb', line 106

def style_update(node, css)
  return unless node
  node["style"] = node["style"] ?  node["style"].sub(/;?$/, ";#{css}") : css
end

#table_note_cleanup(docxml) ⇒ Object 



25
26
27
28
29
30
31
32
 
# File 'lib/isodoc/word_function/postprocess.rb', line 25

def table_note_cleanup(docxml)
  super
  # preempt html2doc putting MsoNormal there
  docxml.xpath("//p[not(self::*[@class])]"\
               "[ancestor::*[@class = 'Note']]").each do |p|
    p["class"] = "Note"
  end
end

#to_word_xhtml_fragment(xml) ⇒ Object 



19
20
21
22
23
 
# File 'lib/isodoc/word_function/postprocess.rb', line 19

def to_word_xhtml_fragment(xml)
  doc = ::Nokogiri::XML.parse(WORD_NOKOHEAD)
  fragment = ::Nokogiri::XML::DocumentFragment.new(doc, xml, doc.root)
  fragment
end

#toWord(result, filename, dir, header) ⇒ Object 



42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/isodoc/word_function/postprocess.rb', line 42

def toWord(result, filename, dir, header)
  result = from_xhtml(word_cleanup(to_xhtml(result)))
  unless @landscapestyle.empty?
    @wordstylesheet&.open
    @wordstylesheet&.write(@landscapestyle)
    @wordstylesheet&.close
  end
  Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet&.path,
                   header_file: header&.path, dir: dir,
                   asciimathdelims: [@openmathdelim, @closemathdelim],
                   liststyles: { ul: @ulstyle, ol: @olstyle })
  header&.unlink
  @wordstylesheet&.unlink
end

#word_admonition_images(docxml) ⇒ Object 



57
58
59
60
61
62
 
# File 'lib/isodoc/word_function/postprocess.rb', line 57

def word_admonition_images(docxml)
  docxml.xpath("//div[@class = 'Admonition']//img").each do |i|
    i["width"], i["height"] =
      Html2Doc.image_resize(i, image_localfile(i), @maxheight, 300)
  end
end

#word_annex_cleanup(docxml) ⇒ Object 



168
169
 
# File 'lib/isodoc/word_function/postprocess.rb', line 168

def word_annex_cleanup(docxml)
end

#word_cleanup(docxml) ⇒ Object 



64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
 
# File 'lib/isodoc/word_function/postprocess.rb', line 64

def word_cleanup(docxml)
  word_annex_cleanup(docxml)
  word_preface(docxml)
  word_nested_tables(docxml)
  word_table_align(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_section_breaks(docxml)
  authority_cleanup(docxml)
  word_footnote_format(docxml)
  docxml
end

#word_cover(docxml) ⇒ Object 



8
9
10
11
12
13
14
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 8

def word_cover(docxml)
  cover = File.read(@wordcoverpage, encoding: "UTF-8")
  cover = populate_template(cover, :word)
  coverxml = to_word_xhtml_fragment(cover)
  docxml.at('//div[@class="WordSection1"]').children.first.previous =
    coverxml.to_xml(encoding: "US-ASCII")
end

#word_example_cleanup(docxml) ⇒ Object 



171
172
173
174
175
 
# File 'lib/isodoc/word_function/postprocess.rb', line 171

def word_example_cleanup(docxml)
  docxml.xpath("//div[@class = 'example']//p[not(@class)]").each do |p|
    p["class"] = "example"
  end
end

#word_footnote_format(docxml) ⇒ Object 



234
235
236
237
238
239
240
241
242
243
244
245
 
# File 'lib/isodoc/word_function/postprocess.rb', line 234

def word_footnote_format(docxml)
  # the content is in a[@epub:type = 'footnote']//sup, but in Word, 
  # we need to inject content around the autonumbered footnote reference
  docxml.xpath("//a[@epub:type = 'footnote']").each do |x|
    footnote_reference_format(x)
  end
  docxml.xpath("//a[@class = 'TableFootnoteRef'] | "\
               "//span[@class = 'TableFootnoteRef']").each do |x|
    table_footnote_reference_format(x)
  end
  docxml
end

#word_image_caption(docxml) ⇒ Object 



111
112
113
114
115
116
117
118
119
120
 
# File 'lib/isodoc/word_function/postprocess.rb', line 111

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 



16
17
18
19
20
21
22
23
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 16

def word_intro(docxml, level)
  intro = insert_toc(File.read(@wordintropage, encoding: "UTF-8"),
                     docxml, level)
  intro = populate_template(intro, :word)
  introxml = to_word_xhtml_fragment(intro)
  docxml.at('//div[@class="WordSection2"]').children.first.previous =
    introxml.to_xml(encoding: "US-ASCII")
end

#word_list_continuations(docxml) ⇒ Object 



122
123
124
125
 
# File 'lib/isodoc/word_function/postprocess.rb', line 122

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 



81
82
83
84
85
86
87
 
# File 'lib/isodoc/word_function/postprocess.rb', line 81

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_preface(docxml) ⇒ Object 



3
4
5
6
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 3

def word_preface(docxml)
  word_cover(docxml) if @wordcoverpage
  word_intro(docxml, @wordToClevels) if @wordintropage
end

#word_pseudocode_cleanup(docxml) ⇒ Object 



177
178
179
180
181
 
# File 'lib/isodoc/word_function/postprocess.rb', line 177

def word_pseudocode_cleanup(docxml)
  docxml.xpath("//div[@class = 'pseudocode']//p[not(@class)]").each do |p|
    p["class"] = "pseudocode"
  end
end

#word_remove_pb_before_annex(docxml) ⇒ Object

applies for <div class=“WordSectionN_M”><p><pagebreak/></p>…



224
225
226
227
228
229
230
231
232
 
# File 'lib/isodoc/word_function/postprocess.rb', line 224

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 



195
196
197
198
199
200
201
 
# File 'lib/isodoc/word_function/postprocess.rb', line 195

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 { |br| br.delete("orientation") }
end

#word_section_breaks1(docxml, sect) ⇒ Object 



203
204
205
206
207
208
209
210
 
# File 'lib/isodoc/word_function/postprocess.rb', line 203

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_table_align(docxml) ⇒ Object 



140
141
142
143
144
145
 
# File 'lib/isodoc/word_function/postprocess.rb', line 140

def word_table_align(docxml)
  docxml.xpath("//td[@align]/p | //th[@align]/p").each do |p|
    next if p["align"]
    style_update(p, "text-align: #{p.parent["align"]}")
  end
end

#word_table_separator(docxml) ⇒ Object

EMPTY_PARA = “<p style=‘margin-top:0cm;margin-right:0cm;”\

  "margin-bottom:0cm;margin-left:0.0pt;margin-bottom:.0001pt;"\
  "line-height:1.0pt;mso-line-height-rule:exactly'>"\
  "<span lang=EN-GB style='display:none;mso-hide:all'>&nbsp;</span></p>"

def table_after_table(docxml)
 docxml.xpath("//table[following-sibling::*[1]/self::table]").each do |t|
    t.add_next_sibling(EMPTY_PARA)
  end
end



160
161
162
163
164
165
166
 
# File 'lib/isodoc/word_function/postprocess.rb', line 160

def word_table_separator(docxml)
  docxml.xpath("//p[@class = 'TableTitle']").each do |t|
    next unless t.children.empty?
    t["style"] = t["style"].sub(/;?$/, ";font-size:0pt;")
    t.children = "&nbsp;"
  end
end

#word_toc_entry(toclevel, heading) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 29

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_preface(level) ⇒ Object 



52
53
54
55
56
57
58
59
60
 
# File 'lib/isodoc/word_function/postprocess_cover.rb', line 52

def word_toc_preface(level)
  <<~TOC.freeze
  <span lang="EN-GB"><span
    style='mso-element:field-begin'></span><span
    style='mso-spacerun:yes'>&#xA0;</span>TOC
    \\o &quot;1-#{level}&quot; \\h \\z \\u <span
    style='mso-element:field-separator'></span></span>
  TOC
end