Module: Asciidoctor::Standoc::Cleanup

Included in:
Converter
Defined in:
lib/asciidoctor/standoc/cleanup.rb,
lib/asciidoctor/standoc/cleanup_ref.rb,
lib/asciidoctor/standoc/cleanup_block.rb,
lib/asciidoctor/standoc/cleanup_footnotes.rb,
lib/asciidoctor/standoc/cleanup_boilerplate.rb

Constant Summary collapse

TEXT_ELEMS = 
%w{status language script version author name callout phone email 
street city state country postcode identifier referenceFrom
referenceTo docidentifier docnumber prefix initial addition surname
forename
title draft secretariat title-main title-intro title-part}.freeze
LOCALITY_REGEX_STR =

extending localities to cover ISO referencing

<<~REGEXP.freeze
  ^((?<locality>section|clause|part|paragraph|chapter|page|
                table|annex|figure|example|note|formula|list|
                locality:[^ \\t\\n\\r:,]+)(\\s+|=)
         (?<ref>[^"][^ \\t\\n,:-]*|"[^"]+")
           (-(?<to>[^"][^ \\t\\n,:-]*|"[^"]"))?|
    (?<locality2>whole|locality:[^ \\t\\n\\r:,]+))[,:]?\\s*
   (?<text>.*)$
REGEXP
LOCALITY_RE = 
Regexp.new(LOCALITY_REGEX_STR.gsub(/\s/, ""),
Regexp::IGNORECASE | Regexp::MULTILINE)
ISO_PUBLISHER_XPATH = 
"./contributor[role/@type = 'publisher']/"\
"organization[abbreviation = 'ISO' or abbreviation = 'IEC' or "\
"name = 'International Organization for Standardization' or "\
"name = 'International Electrotechnical Commission']".freeze
ELEMS_ALLOW_NOTES = 
%w[p formula ul ol dl figure].freeze
TERM_CLAUSE = 
"//sections/terms | "\
"//sections/clause[descendant::terms]".freeze
NORM_REF = 
"//bibliography/references[title = 'Normative References' or "\
"title = 'Normative references']".freeze

Instance Method Summary collapse

Instance Method Details

#add_to_hash(bib, key, val) ⇒ Object 



213
214
215
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 213

def add_to_hash(bib, key, val)
  Utils::set_nested_value(bib, key.split(/\./), val)
end

#align_callouts_to_annotations(xmldoc) ⇒ Object 



111
112
113
114
115
116
117
118
119
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 111

def align_callouts_to_annotations(xmldoc)
  xmldoc.xpath("//sourcecode").each do |x|
    callouts = x.elements.select { |e| e.name == "callout" }
    annotations = x.elements.select { |e| e.name == "annotation" }
    if callouts.size == annotations.size
      link_callouts_to_annotations(callouts, annotations)
    end
  end
end

#bibabstract_location(x) ⇒ Object 



147
148
149
150
151
152
153
154
155
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 147

def bibabstract_location(x)
  bibabstract = x.at("//bibdata/script") || x.at("//bibdata/language") ||
    x.at("//bibdata/contributor[not(following-sibling::contributor)]") ||
    x.at("//bibdata/date[not(following-sibling::date)]") ||
    x.at("//docnumber") ||
    x.at("//bibdata/docidentifier[not(following-sibling::docidentifier)]") ||
    x.at("//bibdata/uri[not(following-sibling::uri)]") ||
    x.at("//bibdata/title[not(following-sibling::title)]")
end

#biblio_cleanup(xmldoc) ⇒ Object 



126
127
128
129
130
131
132
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 126

def biblio_cleanup(xmldoc)
  biblio_reorder(xmldoc)
  biblio_renumber(xmldoc)
  xmldoc.xpath("//references[references]").each do |t|
    t.name = "clause"
  end
end

#biblio_renumber(xmldoc) ⇒ Object

default presuppose that all citations in biblio numbered consecutively, but that standards codes are preserved as is: only numeric references are renumbered



101
102
103
104
105
106
107
108
109
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 101

def biblio_renumber(xmldoc)
  r = xmldoc.at("//references[title = 'Bibliography'] | "\
                "//clause[title = 'Bibliography'][.//bibitem]") or return
  r.xpath(".//bibitem[not(ancestor::bibitem)]").each_with_index do |b, i|
    next unless docid = b.at("./docidentifier[@type = 'metanorma']")
    next unless  /^\[\d+\]$/.match(docid.text)
    docid.children = "[#{i + 1}]"
  end
end

#biblio_reorder(xmldoc) ⇒ Object 



78
79
80
81
82
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 78

def biblio_reorder(xmldoc)
  xmldoc.xpath("//references[title = 'Bibliography']").each do |r|
    biblio_reorder1(r)
  end
end

#biblio_reorder1(refs) ⇒ Object 



84
85
86
87
88
89
90
91
92
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 84

def biblio_reorder1(refs)
  bib = sort_biblio(refs.xpath("./bibitem"))
  refs.xpath("./bibitem").each { |b| b.remove }
  bib.reverse.each do |b|
  insert = refs.at("./title") and insert.next = b.to_xml or
    refs.children.first.add_previous_sibling b.to_xml
  end
  refs.xpath("./references").each { |r| biblio_reorder1(r) }
end

#boilerplate_cleanup(xmldoc) ⇒ Object 



52
53
54
55
56
57
58
59
60
61
62
63
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 52

def boilerplate_cleanup(xmldoc)
  isodoc = IsoDoc::Convert.new({})
  @lang = xmldoc&.at("//bibdata/language")&.text
  @script = xmldoc&.at("//bibdata/script")&.text
  isodoc.i18n_init(@lang, @script)
  f = xmldoc.at(self.class::TERM_CLAUSE) and
    term_defs_boilerplate(f.at("./title"),
                          xmldoc.xpath(".//termdocsource"),
                          f.at(".//term"), f.at(".//p"), isodoc)
  f = xmldoc.at(self.class::NORM_REF) and
  norm_ref_preface(f)
end

#bookmark_cleanup(xmldoc) ⇒ Object 



226
227
228
229
230
231
232
233
234
235
236
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 226

def bookmark_cleanup(xmldoc)
  xmldoc.xpath("//li[descendant::bookmark]").each do |x|
    if x&.elements&.first&.name == "p" &&
        x&.elements&.first&.elements&.first&.name == "bookmark"
      if empty_text_before_first_element(x.elements[0])
        x["id"] = x.elements[0].elements[0].remove["id"]
        strip_initial_space(x.elements[0])
      end
    end
  end
end

#bpart_cleanup(xmldoc) ⇒ Object

allows us to deal with doc relation localities, temporarily stashed to “bpart”



57
58
59
60
61
62
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 57

def bpart_cleanup(xmldoc)
  xmldoc.xpath("//relation/bpart").each do |x|
    extract_localities(x)
    x.replace(x.children)
  end
end

#callout_cleanup(xmldoc) ⇒ Object 



129
130
131
132
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 129

def callout_cleanup(xmldoc)
  merge_annotations_into_sourcecode(xmldoc)
  align_callouts_to_annotations(xmldoc)
end

#cleanup(xmldoc) ⇒ Object 



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 30

def cleanup(xmldoc)
  element_name_cleanup(xmldoc)
  termdef_cleanup(xmldoc)
  sections_cleanup(xmldoc)
  obligations_cleanup(xmldoc)
  table_cleanup(xmldoc)
  formula_cleanup(xmldoc)
  figure_cleanup(xmldoc)
  ref_cleanup(xmldoc)
  note_cleanup(xmldoc)
  ref_dl_cleanup(xmldoc)
  normref_cleanup(xmldoc)
  biblio_cleanup(xmldoc)
  reference_names(xmldoc)
  xref_cleanup(xmldoc)
  origin_cleanup(xmldoc)
  RelatonIev::iev_cleanup(xmldoc, @bibdb)
  element_name_cleanup(xmldoc)
  bpart_cleanup(xmldoc)
  quotesource_cleanup(xmldoc)
  para_cleanup(xmldoc)
  callout_cleanup(xmldoc)
  footnote_cleanup(xmldoc)
  empty_element_cleanup(xmldoc)
  mathml_cleanup(xmldoc)
  script_cleanup(xmldoc)
  docidentifier_cleanup(xmldoc)
  bookmark_cleanup(xmldoc)
  smartquotes_cleanup(xmldoc)
  requirement_cleanup(xmldoc)
  boilerplate_cleanup(xmldoc)
  xmldoc
end

#dd_bib_extract(dtd) ⇒ Object 



200
201
202
203
204
205
206
207
208
209
210
211
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 200

def dd_bib_extract(dtd)
  return nil if dtd.children.empty?
  dtd.at("./dl") and return dl_bib_extract(dtd)
  elems = dtd.remove.elements
  return p_unwrap(dtd) unless elems.size == 1 &&
    %w(ol ul).include?(elems[0].name)
  ret = []
  elems[0].xpath("./li").each do |li|
    ret << p_unwrap(li)
  end
  ret
end

#dl_bib_extract(c, nested = false) ⇒ Object

definition list, with at most one level of unordered lists



218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 218

def dl_bib_extract(c, nested = false)
  dl = c.at("./dl") or return
  bib = {}
  key = ""
  dl.xpath("./dt | ./dd").each do |dtd|
    dtd.name == "dt" and key = dtd.text.sub(/:+$/, "") or
      add_to_hash(bib, key, dd_bib_extract(dtd))
  end
  c.xpath("./clause").each do |c1|
    key = c1&.at("./title")&.text&.downcase&.strip
    next unless %w(contributor relation series).include? key
    add_to_hash(bib, key, dl_bib_extract(c1, true))
  end
  if !nested and c.at("./title")
    title = c.at("./title").remove.children.to_xml
    bib["title"] = bib["title"] ? Array(bib["title"]) : []
    bib["title"] << title if !title.empty?
  end
  bib
end

#dl_table_cleanup(xmldoc) ⇒ Object

move Key dl after table footer



24
25
26
27
28
29
30
31
32
33
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 24

def dl_table_cleanup(xmldoc)
  q = "//table/following-sibling::*[1][self::p]"
  xmldoc.xpath(q).each do |s|
    if s.text =~ /^\s*key[^a-z]*$/i && !s.next_element.nil? &&
        s.next_element.name == "dl"
      s.previous_element << s.next_element.remove
      s.remove
    end
  end
end

#docid_prefix(prefix, docid) ⇒ Object 



134
135
136
137
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 134

def docid_prefix(prefix, docid)
  docid = "#{prefix} #{docid}" unless omit_docid_prefix(prefix)
  docid
end

#docidentifier_cleanup(xmldoc) ⇒ Object 



77
78
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 77

def docidentifier_cleanup(xmldoc)
end

#element_name_cleanup(xmldoc) ⇒ Object 



100
101
102
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 100

def element_name_cleanup(xmldoc)
  xmldoc.traverse { |n| n.name = n.name.gsub(/_/, "-") }
end

#empty_element_cleanup(xmldoc) ⇒ Object 



94
95
96
97
98
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 94

def empty_element_cleanup(xmldoc)
  xmldoc.xpath("//" + TEXT_ELEMS.join(" | //")).each do |x|
    x.remove if x.children.empty?
  end
end

#empty_text_before_first_element(x) ⇒ Object 



208
209
210
211
212
213
214
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 208

def empty_text_before_first_element(x)
  x.children.each do |c|
    return false if c.text? and /\S/.match(c.text)
    return true if c.element?
  end
  true
end

#external_terms_boilerplate(sources) ⇒ Object 



4
5
6
7
8
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 4

def external_terms_boilerplate(sources)
  IsoDoc::Function::I18n::l10n(
    @external_terms_boilerplate.gsub(/%/, sources || "???"),
    @lang, @script)
end

#extract_from_p(tag, bib, key) ⇒ Object 



176
177
178
179
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 176

def extract_from_p(tag, bib, key)
  return unless bib[tag]
  "<#{key}>#{bib[tag].at('p').children}</#{key}>"
end

#extract_localities(x) ⇒ Object 



24
25
26
27
28
29
30
31
32
33
34
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 24

def extract_localities(x)
  text = x.children.first.remove.text
  while (m = LOCALITY_RE.match text)
    ref = m[:ref] ? "<referenceFrom>#{tq m[:ref]}</referenceFrom>" : ""
    refto = m[:to] ? "<referenceTo>#{tq m[:to]}</referenceTo>" : ""
    loc = m[:locality]&.downcase || m[:locality2]&.downcase
    x.add_child("<locality type='#{loc}'>#{ref}#{refto}</locality>")
    text = m[:text]
  end
  x.add_child(text)
end

#figure_cleanup(xmldoc) ⇒ Object 



116
117
118
119
120
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 116

def figure_cleanup(xmldoc)
  figure_footnote_cleanup(xmldoc)
  figure_dl_cleanup(xmldoc)
  subfigure_cleanup(xmldoc)
end

#figure_dl_cleanup(xmldoc) ⇒ Object

include key definition list inside figure



88
89
90
91
92
93
94
95
96
97
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 88

def figure_dl_cleanup(xmldoc)
  q = "//figure/following-sibling::*[self::p]"
  xmldoc.xpath(q).each do |s|
    if s.text =~ /^\s*key[^a-z]*$/i && !s.next_element.nil? &&
        s.next_element.name == "dl"
      s.previous_element << s.next_element.remove
      s.remove
    end
  end
end

#figure_footnote_cleanup(xmldoc) ⇒ Object

include footnotes inside figure



18
19
20
21
22
23
24
25
26
27
28
29
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 18

def figure_footnote_cleanup(xmldoc)
  nomatches = false
  until nomatches
    q = "//figure/following-sibling::*[1][self::p and *[1][self::fn]]"
    nomatches = true
    xmldoc.xpath(q).each do |s|
      s.previous_element << s.first_element_child.remove
      s.remove
      nomatches = false
    end
  end
end

#footnote_cleanup(xmldoc) ⇒ Object 



76
77
78
79
80
81
82
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 76

def footnote_cleanup(xmldoc)
  table_footnote_renumber(xmldoc)
  other_footnote_renumber(xmldoc)
  xmldoc.xpath("//fn").each do |fn|
    fn.delete("table")
  end
end

#footnote_content(fn) ⇒ Object 



12
13
14
15
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 12

def footnote_content(fn)
  c = fn.children.respond_to?(:to_xml) ? fn.children.to_xml : fn.children
  c.gsub(/ id="[^"]+"/, "")
end

#format_ref(ref, type, isopub) ⇒ Object 



144
145
146
147
148
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 144

def format_ref(ref, type, isopub)
  return docid_prefix(type, ref) if isopub
  return "[#{ref}]" if /^\d+$/.match(ref) && !/^\[.*\]$/.match(ref)
  ref
end

#formula_cleanup(x) ⇒ Object

include where definition list inside stem block



76
77
78
79
80
81
82
83
84
85
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 76

def formula_cleanup(x)
  q = "//formula/following-sibling::*[1][self::p]"
  x.xpath(q).each do |s|
    if s.text =~ /^\s*where[^a-z]*$/i && !s.next_element.nil? &&
        s.next_element.name == "dl"
      s.previous_element << s.next_element.remove
      s.remove
    end
  end
end

#header_rows_cleanup(xmldoc) ⇒ Object 



45
46
47
48
49
50
51
52
53
54
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 45

def header_rows_cleanup(xmldoc)
  xmldoc.xpath("//table[@headerrows]").each do |s|
    thead = insert_thead(s)
    (thead.xpath("./tr").size...s["headerrows"].to_i).each do
      row = s.at("./tbody/tr")
      row.parent = thead
    end
    s.delete("headerrows")
  end
end

#inject_id(xmldoc, path) ⇒ Object 



17
18
19
20
21
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 17

def inject_id(xmldoc, path)
  xmldoc.xpath(path).each do |x|
    x["id"] ||= Utils::anchor_or_uuid
  end
end

#insert_thead(s) ⇒ Object 



35
36
37
38
39
40
41
42
43
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 35

def insert_thead(s)
  thead = s.at("./thead")
  return thead unless thead.nil?
  if tname = s.at("./name")
    thead = tname.add_next_sibling("<thead/>").first
    return thead
  end
  s.children.first.add_previous_sibling("<thead/>").first
end

#internal_external_terms_boilerplate(sources) ⇒ Object 



10
11
12
13
14
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 10

def internal_external_terms_boilerplate(sources)
  IsoDoc::Function::I18n::l10n(
    @internal_external_terms_boilerplate.gsub(/%/, sources || "??"),
    @lang, @script)
end

#link_callouts_to_annotations(callouts, annotations) ⇒ Object 



104
105
106
107
108
109
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 104

def link_callouts_to_annotations(callouts, annotations)
  callouts.each_with_index do |c, i|
    c["target"] = "_" + UUIDTools::UUID.random_create
    annotations[i]["id"] = c["target"]
  end
end

#link_unwrap(p) ⇒ Object 



192
193
194
195
196
197
198
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 192

def link_unwrap(p)
  elems = p.elements
  if elems.size == 1 && elems[0].name == "link"
    p.at("./link").replace(elems[0]["target"].strip)
  end
  p
end

#make_abstract(x, s) ⇒ Object 



133
134
135
136
137
138
139
140
141
142
143
144
145
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 133

def make_abstract(x, s)
  if x.at("//abstract[not(ancestor::bibitem)]")
    preface = s.at("//preface") || s.add_previous_sibling("<preface/>").first
    abstract = x.at("//abstract[not(ancestor::bibitem)]").remove
    preface.prepend_child abstract.remove
    bibabstract = bibabstract_location(x)
    dupabstract = abstract.dup
    dupabstract.traverse { |n| n.remove_attribute("id") }
    dupabstract.remove_attribute("language")
    dupabstract.remove_attribute("script")
    bibabstract.next = dupabstract
  end
end

#make_bibliography(x, s) ⇒ Object 



157
158
159
160
161
162
163
164
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 157

def make_bibliography(x, s)
  if x.at("//sections/references")
    biblio = s.add_next_sibling("<bibliography/>").first
    x.xpath("//sections/references").each do |r|
      biblio.add_child r.remove
    end
  end
end

#make_preface(x, s) ⇒ Object 



122
123
124
125
126
127
128
129
130
131
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 122

def make_preface(x, s)
  if x.at("//foreword | //introduction")
    preface = s.add_previous_sibling("<preface/>").first
    foreword = x.at("//foreword")
    preface.add_child foreword.remove if foreword
    introduction = x.at("//introduction")
    preface.add_child introduction.remove if introduction
  end
  make_abstract(x, s)
end

#mathml_cleanup(xmldoc) ⇒ Object 



238
239
240
241
242
243
244
245
246
247
248
249
250
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 238

def mathml_cleanup(xmldoc)
  xmldoc.xpath("//stem[@type = 'MathML']").each do |x|
    next if x.children.any? { |y| y.element? }
    math = x.text.gsub(/&lt;/, "<").gsub(/&gt;/, ">").gsub(/&quot;/, '"').
      gsub(/&apos;/, "'").gsub(/&amp;/, "&").
      gsub(/<[^: \r\n\t\/]+:/, "<").
      gsub(/<\/[^ \r\n\t:]+:/, "</").
      gsub(/ xmlns[^>"']+/, "").
      gsub(/<math /, '<math xmlns="http://www.w3.org/1998/Math/MathML" ').
      gsub(/<math>/, '<math xmlns="http://www.w3.org/1998/Math/MathML">')
    x.children = math
  end
end

#maxlevel(x) ⇒ Object 



189
190
191
192
193
194
195
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 189

def maxlevel(x)
  max = 5
  x.xpath("//clause[@level]").each do |c|
    max = c["level"].to_i if max < c["level"].to_i
  end
  max
end

#merge_annotations_into_sourcecode(xmldoc) ⇒ Object 



121
122
123
124
125
126
127
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 121

def merge_annotations_into_sourcecode(xmldoc)
  xmldoc.xpath("//sourcecode").each do |x|
    while x&.next_element&.name == "annotation"
      x.next_element.parent = x
    end
  end
end

#norm_ref_preface(f) ⇒ Object 



38
39
40
41
42
43
44
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 38

def norm_ref_preface(f)
  refs = f.elements.select do |e|
    ["reference", "bibitem"].include? e.name
  end
  f.at("./title").next =
    "<p>#{(refs.empty? ? @norm_empty_pref : @norm_with_refs_pref)}</p>"
end

#normref_cleanup(xmldoc) ⇒ Object 



119
120
121
122
123
124
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 119

def normref_cleanup(xmldoc)
  r = xmldoc.at(NORM_REF) || return
  r.elements.each do |n|
    n.remove unless ["title", "bibitem"].include? n.name
  end
end

#note_cleanup(xmldoc) ⇒ Object

if a note is at the end of a section, it is left alone if a note is followed by a non-note block, it is moved inside its preceding block if it is not delimited (so there was no way of making that block include the note)



173
174
175
176
177
178
179
180
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 173

def note_cleanup(xmldoc)
  q = "//note[following-sibling::*[not(local-name() = 'note')]]"
  xmldoc.xpath(q).each do |n|
    next unless n.ancestors("table").empty?
    prev = n.previous_element || next
    n.parent = prev if ELEMS_ALLOW_NOTES.include? prev.name
  end
end

#notes_table_cleanup(xmldoc) ⇒ Object

move notes into table



63
64
65
66
67
68
69
70
71
72
73
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 63

def notes_table_cleanup(xmldoc)
  nomatches = false
  until nomatches
    q = "//table/following-sibling::*[1][self::note]"
    nomatches = true
    xmldoc.xpath(q).each do |n|
      n.previous_element << n.remove
      nomatches = false
    end
  end
end

#obligations_cleanup(x) ⇒ Object 



213
214
215
216
217
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 213

def obligations_cleanup(x)
  obligations_cleanup_info(x)
  obligations_cleanup_norm(x)
  obligations_cleanup_inherit(x)
end

#obligations_cleanup_info(x) ⇒ Object 



219
220
221
222
223
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 219

def obligations_cleanup_info(x)
  (s = x.at("//foreword")) && s["obligation"] = "informative"
  (s = x.at("//introduction")) && s["obligation"] = "informative"
  x.xpath("//references").each { |r| r["obligation"] = "informative" }
end

#obligations_cleanup_inherit(x) ⇒ Object 



233
234
235
236
237
238
239
240
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 233

def obligations_cleanup_inherit(x)
  x.xpath("//annex | //clause").each do |r|
    r["obligation"] = "normative" unless r["obligation"]
  end
  x.xpath(Utils::SUBCLAUSE_XPATH).each do |r|
    r["obligation"] = r.at("./ancestor::*/@obligation").text
  end
end

#obligations_cleanup_norm(x) ⇒ Object 



225
226
227
228
229
230
231
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 225

def obligations_cleanup_norm(x)
  (s = x.at("//clause[title = 'Scope']")) && s["obligation"] = "normative"
  (s = x.at("//clause[title = 'Symbols and Abbreviated Terms']")) &&
    s["obligation"] = "normative"
  x.xpath("//terms").each { |r| r["obligation"] = "normative" }
  x.xpath("//symbols-abbrevs").each { |r| r["obligation"] = "normative" }
end

#omit_docid_prefix(prefix) ⇒ Object 



139
140
141
142
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 139

def omit_docid_prefix(prefix)
  return true if prefix.nil? || prefix.empty?
  %(ISO IEC IEV ITU).include? prefix
end

#origin_cleanup(xmldoc) ⇒ Object 



70
71
72
73
74
75
76
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 70

def origin_cleanup(xmldoc)
  xmldoc.xpath("//origin").each do |x|
    x["citeas"] = @anchors&.dig(x["bibitemid"], :xref) ||
      warn("#{x['bibitemid']} is not a real reference!")
    extract_localities(x) unless x.children.empty?
  end
end

#other_footnote_renumber(xmldoc) ⇒ Object 



68
69
70
71
72
73
74
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 68

def other_footnote_renumber(xmldoc)
  seen = {}
  i = 0
  xmldoc.xpath("//fn").each do |fn|
    i, seen = other_footnote_renumber1(fn, i, seen)
  end
end

#other_footnote_renumber1(fn, i, seen) ⇒ Object 



54
55
56
57
58
59
60
61
62
63
64
65
66
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 54

def other_footnote_renumber1(fn, i, seen)
  unless fn["table"]
    content = footnote_content(fn)
    if seen[content] then outnum = seen[content]
    else
      i += 1
      outnum = i
      seen[content] = outnum
    end
    fn["reference"] = outnum.to_s
  end
  [i, seen]
end

#p_unwrap(p) ⇒ Object

if the content is a single paragraph, replace it with its children single links replaced with uri



183
184
185
186
187
188
189
190
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 183

def p_unwrap(p)
  elems = p.elements
  if elems.size == 1 && elems[0].name == "p"
    link_unwrap(elems[0]).children.to_xml.strip
  else
    p.to_xml.strip
  end
end

#para_cleanup(xmldoc) ⇒ Object 



12
13
14
15
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 12

def para_cleanup(xmldoc)
  inject_id(xmldoc, "//p | //ol | //ul")
  inject_id(xmldoc, "//note[not(ancestor::bibitem)][not(ancestor::table)]")
end

#quotesource_cleanup(xmldoc) ⇒ Object 



64
65
66
67
68
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 64

def quotesource_cleanup(xmldoc)
  xmldoc.xpath("//quote/source | //terms/source").each do |x|
    xref_to_eref(x)
  end
end

#ref_cleanup(xmldoc) ⇒ Object

move ref before p



112
113
114
115
116
117
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 112

def ref_cleanup(xmldoc)
  xmldoc.xpath("//p/ref").each do |r|
    parent = r.parent
    parent.previous = r.remove
  end
end

#ref_dl_cleanup(xmldoc) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 165

def ref_dl_cleanup(xmldoc)
  xmldoc.xpath("//clause[@bibitem = 'true']").each do |c|
    bib = dl_bib_extract(c) or next
    bibitemxml = RelatonBib::BibliographicItem.new(
      RelatonBib::HashConverter::hash_to_bib(bib)).to_xml or next
    bibitem = Nokogiri::XML(bibitemxml)
    bibitem["id"] = c["id"] if c["id"]
    c.replace(bibitem.root)
  end
end

#reference_names(xmldoc) ⇒ Object 



156
157
158
159
160
161
162
163
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 156

def reference_names(xmldoc)
  xmldoc.xpath("//bibitem[not(ancestor::bibitem)]").each do |ref|
    isopub = ref.at(ISO_PUBLISHER_XPATH)
    docid = ref.at("./docidentifier[not(@type = 'DOI')]")
    reference = format_ref(docid.text, docid["type"], isopub)
    @anchors[ref["id"]] = { xref: reference }
  end
end

#requirement_cleanup(x) ⇒ Object 



242
243
244
245
246
247
248
249
250
251
252
253
254
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 242

def requirement_cleanup(x)
  x.xpath("//requirement | //recommendation | //permission").each do |r|
    r.children.each do |e|
      unless e.element? && (Utils::reqt_subpart(e.name) || 
          %w(requirement recommendation permission).include?(e.name))
        t = Nokogiri::XML::Element.new("description", x)
        e.before(t)
        t.children = e.remove
      end
    end
    requirement_cleanup1(r)
  end
end

#requirement_cleanup1(r) ⇒ Object 



256
257
258
259
260
261
262
263
264
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 256

def requirement_cleanup1(r)
  while d = r.at("./description[following-sibling::*[1][self::description]]")
    n = d.next.remove
    d << n.children
  end
  r.xpath("./description[not(./*) and normalize-space(.)='']").each do |d|
    d.replace("\n")
  end
end

#script_cleanup(xmldoc) ⇒ Object

it seems Nokogiri::XML is treating the content of <script> as cdata, because of its use in HTML. Bad nokogiri. Undoing that, since we use script as a normal tag



90
91
92
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 90

def script_cleanup(xmldoc)
  xmldoc.xpath("//script").each { |x| x.content = x.to_str }
end

#sections_cleanup(x) ⇒ Object 



208
209
210
211
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 208

def sections_cleanup(x)
  sections_order_cleanup(x)
  sections_level_cleanup(x)
end

#sections_level_cleanup(x) ⇒ Object 



197
198
199
200
201
202
203
204
205
206
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 197

def sections_level_cleanup(x)
  m = maxlevel(x)
  return if m < 6
  m.downto(6).each do |l|
    x.xpath("//clause[@level = '#{l}']").each do |c|
      c.delete("level")
      c.previous_element << c.remove
    end
  end
end

#sections_order_cleanup(x) ⇒ Object 



182
183
184
185
186
187
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 182

def sections_order_cleanup(x)
  s = x.at("//sections")
  make_preface(x, s)
  make_bibliography(x, s)
  x.xpath("//sections/annex").reverse_each { |r| s.next = r.remove }
end

#smartquotes_cleanup(xmldoc) ⇒ Object 



64
65
66
67
68
69
70
71
72
73
74
75
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 64

def smartquotes_cleanup(xmldoc)
  xmldoc.traverse do |n|
    next unless n.text?
    if @smartquotes
      next unless n.ancestors("pre, tt, sourcecode, bibdata, on").empty?
      n.replace(Utils::smartformat(n.text))
    else
      n.replace(n.text.gsub(/(?<=\p{Alnum})\u2019(?=\p{Alpha})/, "'"))
    end
  end
  xmldoc
end

#sort_biblio(bib) ⇒ Object 



94
95
96
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 94

def sort_biblio(bib)
  bib
end

#strip_initial_space(x) ⇒ Object 



216
217
218
219
220
221
222
223
224
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 216

def strip_initial_space(x)
  if x.children[0].text?
    if !/\S/.match(x.children[0].text)
      x.children[0].remove
    else
      x.children[0].content = x.children[0].text.gsub(/^ /, "")
    end
  end
end

#subfigure_cleanup(xmldoc) ⇒ Object

examples containing only figures become subfigures of figures



100
101
102
103
104
105
106
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 100

def subfigure_cleanup(xmldoc)
  nodes = xmldoc.xpath("//example/figure")
  while !nodes.empty?
    nodes[0].parent.name = "figure"
    nodes = xmldoc.xpath("//example/figure")
  end
end

#table_cleanup(xmldoc) ⇒ Object 



56
57
58
59
60
 
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 56

def table_cleanup(xmldoc)
  dl_table_cleanup(xmldoc)
  notes_table_cleanup(xmldoc)
  header_rows_cleanup(xmldoc)
end

#table_footnote_renumber(xmldoc) ⇒ Object 



44
45
46
47
48
49
50
51
52
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 44

def table_footnote_renumber(xmldoc)
  xmldoc.xpath("//table | //figure").each do |t|
    seen = {}
    i = 0
    t.xpath(".//fn").each do |fn|
      i, seen = table_footnote_renumber1(fn, i, seen)
    end
  end
end

#table_footnote_renumber1(fn, i, seen) ⇒ Object 



31
32
33
34
35
36
37
38
39
40
41
42
 
# File 'lib/asciidoctor/standoc/cleanup_footnotes.rb', line 31

def table_footnote_renumber1(fn, i, seen)
  content = footnote_content(fn)
  if seen[content] then outnum = seen[content]
  else
    i += 1
    outnum = i
    seen[content] = outnum
  end
  fn["reference"] = (outnum - 1 + "a".ord).chr
  fn["table"] = true
  [i, seen]
end

#term_children_cleanup(xmldoc) ⇒ Object 



188
189
190
191
192
193
194
195
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 188

def term_children_cleanup(xmldoc)
  xmldoc.xpath("//term").each do |t|
    ex = t.xpath("./termexample")
    t.xpath("./termnote").each { |n| t << n.remove }
    t.xpath("./termexample").each { |n| t << n.remove }
    t.xpath("./termsource").each { |n| t << n.remove }
  end
end

#term_defs_boilerplate(div, source, term, preface, isodoc) ⇒ Object 



16
17
18
19
20
21
22
23
24
25
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 16

def term_defs_boilerplate(div, source, term, preface, isodoc)
  div.next = @term_def_boilerplate
  source.each { |s| @anchors[s["bibitemid"]] or
                warn "term source #{s['bibitemid']} not referenced" }
  if source.empty? && term.nil?
    div.next = @no_terms_boilerplate
  else
    div.next = term_defs_boilerplate_cont(source, term, isodoc)
  end
end

#term_defs_boilerplate_cont(src, term, isodoc) ⇒ Object 



27
28
29
30
31
32
33
34
35
36
 
# File 'lib/asciidoctor/standoc/cleanup_boilerplate.rb', line 27

def term_defs_boilerplate_cont(src, term, isodoc)
  sources = isodoc.sentence_join(src.map do |s|
    %{<eref bibitemid="#{s['bibitemid']}"/>}
  end)
  if src.empty? then @internal_terms_boilerplate
  elsif term.nil? then external_terms_boilerplate(sources)
  else
    internal_external_terms_boilerplate(sources)
  end
end

#termdef_boilerplate_cleanup(xmldoc) ⇒ Object 



172
173
174
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 172

def termdef_boilerplate_cleanup(xmldoc)
  xmldoc.xpath("//terms/p | //terms/ul").each(&:remove)
end

#termdef_cleanup(xmldoc) ⇒ Object 



197
198
199
200
201
202
203
204
205
206
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 197

def termdef_cleanup(xmldoc)
  termdef_unnest_cleanup(xmldoc)
  termdef_stem_cleanup(xmldoc)
  termdomain_cleanup(xmldoc)
  termdefinition_cleanup(xmldoc)
  termdef_boilerplate_cleanup(xmldoc)
  termdef_subclause_cleanup(xmldoc)
  term_children_cleanup(xmldoc)
  termdocsource_cleanup(xmldoc)
end

#termdef_stem_cleanup(xmldoc) ⇒ Object 



134
135
136
137
138
139
140
141
142
143
144
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 134

def termdef_stem_cleanup(xmldoc)
  xmldoc.xpath("//term/p/stem").each do |a|
    if a.parent.elements.size == 1
      # para containing just a stem expression
      t = Nokogiri::XML::Element.new("admitted", xmldoc)
      parent = a.parent
      t.children = a.remove
      parent.replace(t)
    end
  end
end

#termdef_subclause_cleanup(xmldoc) ⇒ Object 



176
177
178
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 176

def termdef_subclause_cleanup(xmldoc)
  xmldoc.xpath("//terms[terms]").each { |t| t.name = "clause" }
end

#termdef_unnest_cleanup(xmldoc) ⇒ Object 



163
164
165
166
167
168
169
170
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 163

def termdef_unnest_cleanup(xmldoc)
  # release termdef tags from surrounding paras
  nodes = xmldoc.xpath("//p/admitted | //p/deprecates")
  while !nodes.empty?
    nodes[0].parent.replace(nodes[0].parent.children)
    nodes = xmldoc.xpath("//p/admitted | //p/deprecates")
  end
end

#termdefinition_cleanup(xmldoc) ⇒ Object 



153
154
155
156
157
158
159
160
161
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 153

def termdefinition_cleanup(xmldoc)
  xmldoc.xpath("//term").each do |d|
    first_child = d.at("./p | ./figure | ./formula") || return
    t = Nokogiri::XML::Element.new("definition", xmldoc)
    first_child.replace(t)
    t << first_child.remove
    d.xpath("./p | ./figure | ./formula").each { |n| t << n.remove }
  end
end

#termdocsource_cleanup(xmldoc) ⇒ Object 



180
181
182
183
184
185
186
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 180

def termdocsource_cleanup(xmldoc)
  f = xmldoc.at("//preface | //sections")
  xmldoc.xpath("//terms/termdocsource | "\
               "//clause/termdocsource").each do |s|
    f.previous = s.remove
  end
end

#termdomain_cleanup(xmldoc) ⇒ Object 



146
147
148
149
150
151
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 146

def termdomain_cleanup(xmldoc)
  xmldoc.xpath("//p/domain").each do |a|
    prev = a.parent.previous
    prev.next = a.remove
  end
end

#textcleanup(result) ⇒ Object 



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
 
# File 'lib/asciidoctor/standoc/cleanup.rb', line 14

def textcleanup(result)
  text = result.flatten.map { |l| l.sub(/\s*$/, "") }  * "\n"
  if !@keepasciimath
    text = text.gsub(%r{<stem type="AsciiMath">(.+?)</stem>}m) do |m|
      "<amathstem>#{HTMLEntities.new.decode($1)}</amathstem>"
    end
    text = Html2Doc.
      asciimath_to_mathml(text, ["<amathstem>", "</amathstem>"]).
      gsub(%r{<math xmlns='http://www.w3.org/1998/Math/MathML'>},
           "<stem type='MathML'>"\
           "<math xmlns='http://www.w3.org/1998/Math/MathML'>").
           gsub(%r{</math>}, %{</math></stem>})
  end
  text.gsub(/\s+<fn /, "<fn ")
end

#tq(x) ⇒ Object 



20
21
22
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 20

def tq(x)
  x.sub(/^"/, "").sub(/"$/, "")
end

#xref_cleanup(xmldoc) ⇒ Object 



44
45
46
47
48
49
50
51
52
53
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 44

def xref_cleanup(xmldoc)
  xmldoc.xpath("//xref").each do |x|
    if refid? x["target"]
      x.name = "eref"
      xref_to_eref(x)
    else
      x.delete("type")
    end
  end
end

#xref_to_eref(x) ⇒ Object 



36
37
38
39
40
41
42
 
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 36

def xref_to_eref(x)
  x["bibitemid"] = x["target"]
  x["citeas"] = @anchors&.dig(x["target"], :xref) ||
    warn("#{x['target']} is not a real reference!")
  x.delete("target")
  extract_localities(x) unless x.children.empty?
end