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
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
Instance Method Summary collapse
- #align_callouts_to_annotations(xmldoc) ⇒ Object
- #bibabstract_location(x) ⇒ Object
- #biblio_cleanup(xmldoc) ⇒ Object
- #bookmark_cleanup(xmldoc) ⇒ Object
-
#bpart_cleanup(xmldoc) ⇒ Object
allows us to deal with doc relation localities, temporarily stashed to “bpart”.
- #callout_cleanup(xmldoc) ⇒ Object
- #cleanup(xmldoc) ⇒ Object
-
#dl_table_cleanup(xmldoc) ⇒ Object
move Key dl after table footer.
- #docid_prefix(prefix, docid) ⇒ Object
- #docidentifier_cleanup(xmldoc) ⇒ Object
- #element_name_cleanup(xmldoc) ⇒ Object
- #empty_element_cleanup(xmldoc) ⇒ Object
- #empty_text_before_first_element(x) ⇒ Object
- #extract_localities(x) ⇒ Object
- #figure_cleanup(xmldoc) ⇒ Object
-
#figure_dl_cleanup(xmldoc) ⇒ Object
include key definition list inside figure.
-
#figure_footnote_cleanup(xmldoc) ⇒ Object
include footnotes inside figure.
- #footnote_cleanup(xmldoc) ⇒ Object
- #footnote_content(fn) ⇒ Object
- #format_ref(ref, type, isopub) ⇒ Object
-
#formula_cleanup(x) ⇒ Object
include where definition list inside stem block.
- #header_rows_cleanup(xmldoc) ⇒ Object
-
#iev_cleanup(xmldoc) ⇒ Object
call after xref_cleanup and origin_cleanup.
- #insert_thead(s) ⇒ Object
- #link_callouts_to_annotations(callouts, annotations) ⇒ Object
-
#linksIev2iec60050part(xmldoc) ⇒ Object
converts generic IEV citation to citation of IEC 60050-n assumes IEV citations are of form <eref type=“inline” bibitemid=“a” citeas=“IEC 60050”> <locality type=“clause”><referenceFrom>101-01-01</referenceFrom></locality></eref>.
- #make_abstract(x, s) ⇒ Object
- #make_bibliography(x, s) ⇒ Object
- #make_preface(x, s) ⇒ Object
- #mathml_cleanup(xmldoc) ⇒ Object
- #maxlevel(x) ⇒ Object
- #merge_annotations_into_sourcecode(xmldoc) ⇒ Object
- #normref_cleanup(xmldoc) ⇒ Object
-
#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).
-
#notes_table_cleanup(xmldoc) ⇒ Object
move notes into table.
- #obligations_cleanup(x) ⇒ Object
- #obligations_cleanup_info(x) ⇒ Object
- #obligations_cleanup_inherit(x) ⇒ Object
- #obligations_cleanup_norm(x) ⇒ Object
- #omit_docid_prefix(prefix) ⇒ Object
- #origin_cleanup(xmldoc) ⇒ Object
- #other_footnote_renumber(xmldoc) ⇒ Object
- #other_footnote_renumber1(fn, i, seen) ⇒ Object
- #para_cleanup(xmldoc) ⇒ Object
- #quotesource_cleanup(xmldoc) ⇒ Object
-
#ref_cleanup(xmldoc) ⇒ Object
move ref before p.
- #reference_names(xmldoc) ⇒ Object
-
#refsIev2iec60050part(xmldoc, parts, iev) ⇒ Object
replace generic IEV reference with references to all extracted IEV parts.
- #requirement_cleanup(x) ⇒ Object
- #requirement_cleanup1(r) ⇒ Object
-
#script_cleanup(xmldoc) ⇒ Object
it seems Nokogiri::XML is treating the content of <script> as cdata, because of its use in HTML.
- #sections_cleanup(x) ⇒ Object
- #sections_level_cleanup(x) ⇒ Object
- #sections_order_cleanup(x) ⇒ Object
- #smartquotes_cleanup(xmldoc) ⇒ Object
- #strip_initial_space(x) ⇒ Object
-
#subfigure_cleanup(xmldoc) ⇒ Object
examples containing only figures become subfigures of figures.
- #table_cleanup(xmldoc) ⇒ Object
- #table_footnote_renumber(xmldoc) ⇒ Object
- #table_footnote_renumber1(fn, i, seen) ⇒ Object
- #term_children_cleanup(xmldoc) ⇒ Object
- #termdef_boilerplate_cleanup(xmldoc) ⇒ Object
- #termdef_cleanup(xmldoc) ⇒ Object
- #termdef_stem_cleanup(xmldoc) ⇒ Object
- #termdef_subclause_cleanup(xmldoc) ⇒ Object
- #termdef_unnest_cleanup(xmldoc) ⇒ Object
- #termdefinition_cleanup(xmldoc) ⇒ Object
- #termdocsource_cleanup(xmldoc) ⇒ Object
- #termdomain_cleanup(xmldoc) ⇒ Object
- #textcleanup(result) ⇒ Object
- #tq(x) ⇒ Object
- #xref_cleanup(xmldoc) ⇒ Object
- #xref_to_eref(x) ⇒ Object
Instance Method Details
#align_callouts_to_annotations(xmldoc) ⇒ Object
107 108 109 110 111 112 113 114 115 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 107 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
136 137 138 139 140 141 142 143 144 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 136 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
206 207 208 209 210 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 206 def biblio_cleanup(xmldoc) xmldoc.xpath("//references[references]").each do |t| t.name = "clause" end end |
#bookmark_cleanup(xmldoc) ⇒ Object
232 233 234 235 236 237 238 239 240 241 242 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 232 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”
56 57 58 59 60 61 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 56 def bpart_cleanup(xmldoc) xmldoc.xpath("//relation/bpart").each do |x| extract_localities(x) x.replace(x.children) end end |
#callout_cleanup(xmldoc) ⇒ Object
125 126 127 128 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 125 def callout_cleanup(xmldoc) merge_annotations_into_sourcecode(xmldoc) align_callouts_to_annotations(xmldoc) end |
#cleanup(xmldoc) ⇒ Object
29 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 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 29 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) normref_cleanup(xmldoc) biblio_cleanup(xmldoc) reference_names(xmldoc) xref_cleanup(xmldoc) origin_cleanup(xmldoc) iev_cleanup(xmldoc) element_name_cleanup(xmldoc) # cleanup IEV 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) xmldoc end |
#dl_table_cleanup(xmldoc) ⇒ Object
move Key dl after table footer
23 24 25 26 27 28 29 30 31 32 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 23 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
93 94 95 96 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 93 def docid_prefix(prefix, docid) docid = "#{prefix} #{docid}" unless omit_docid_prefix(prefix) docid end |
#docidentifier_cleanup(xmldoc) ⇒ Object
71 72 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 71 def docidentifier_cleanup(xmldoc) end |
#element_name_cleanup(xmldoc) ⇒ Object
96 97 98 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 96 def element_name_cleanup(xmldoc) xmldoc.traverse { |n| n.name = n.name.gsub(/_/, "-") } end |
#empty_element_cleanup(xmldoc) ⇒ Object
90 91 92 93 94 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 90 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
212 213 214 215 216 217 218 219 220 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 212 def empty_text_before_first_element(x) x.children.each do |c| if c.text? return false if /\S/.match(c.text) end return true if c.element? end true end |
#extract_localities(x) ⇒ Object
23 24 25 26 27 28 29 30 31 32 33 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 23 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
107 108 109 110 111 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 107 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
87 88 89 90 91 92 93 94 95 96 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 87 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
103 104 105 106 107 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 103 def format_ref(ref, type, isopub) return docid_prefix(type, ref) if isopub return "[#{ref}]" if /^\d+$/.match(ref) && !/^\[.*\]$/.match(ref) ref end |
#formula_cleanup(x) ⇒ Object
include where definition list inside stem block
75 76 77 78 79 80 81 82 83 84 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 75 def formula_cleanup(x) q = "//formula/following-sibling::*[1][self::p]" x.xpath(q).each do |s| if s.text =~ /^\s*where[^a-z]*$/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
44 45 46 47 48 49 50 51 52 53 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 44 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 |
#iev_cleanup(xmldoc) ⇒ Object
call after xref_cleanup and origin_cleanup
157 158 159 160 161 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 157 def iev_cleanup(xmldoc) iev = xmldoc.at("//bibitem[docidentifier = 'IEC 60050:2011']") || return parts = linksIev2iec60050part(xmldoc) refsIev2iec60050part(xmldoc, parts, iev) end |
#insert_thead(s) ⇒ Object
34 35 36 37 38 39 40 41 42 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 34 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 |
#link_callouts_to_annotations(callouts, annotations) ⇒ Object
100 101 102 103 104 105 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 100 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 |
#linksIev2iec60050part(xmldoc) ⇒ Object
converts generic IEV citation to citation of IEC 60050-n assumes IEV citations are of form <eref type=“inline” bibitemid=“a” citeas=“IEC 60050”> <locality type=“clause”><referenceFrom>101-01-01</referenceFrom></locality></eref>
128 129 130 131 132 133 134 135 136 137 138 139 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 128 def linksIev2iec60050part(xmldoc) parts = Set.new() xmldoc.xpath("//eref[@citeas = 'IEC 60050:2011'] | "\ "//origin[@citeas = 'IEC 60050:2011']").each do |x| cl = x&.at("./locality[@type = 'clause']/referenceFrom")&.text || next m = /^(\d+)/.match cl || next parts << m[0] x["citeas"] = x["citeas"].sub(/60050/, "60050-#{m[0]}") x["bibitemid"] = "IEC60050-#{m[0]}" end parts end |
#make_abstract(x, s) ⇒ Object
124 125 126 127 128 129 130 131 132 133 134 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 124 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") } bibabstract.next = dupabstract end end |
#make_bibliography(x, s) ⇒ Object
146 147 148 149 150 151 152 153 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 146 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
113 114 115 116 117 118 119 120 121 122 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 113 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
244 245 246 247 248 249 250 251 252 253 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 244 def mathml_cleanup(xmldoc) xmldoc.xpath("//stem[@type = 'MathML']").each do |x| next if x.children.any? { |y| y.element? } math = x.text.gsub(/</, "<").gsub(/>/, ">").gsub(/"/, '"'). gsub(/&/, "&").gsub(/<[^:\/]+:/, "<").gsub(/<\/[^:]+:/, "</"). gsub(/ xmlns[^>]+/, ""). gsub(/<math>/, '<math xmlns="http://www.w3.org/1998/Math/MathML">') x.children = math end end |
#maxlevel(x) ⇒ Object
178 179 180 181 182 183 184 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 178 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
117 118 119 120 121 122 123 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 117 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 |
#normref_cleanup(xmldoc) ⇒ Object
85 86 87 88 89 90 91 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 85 def normref_cleanup(xmldoc) q = "//references[title = 'Normative References']" r = xmldoc.at(q) || 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)
162 163 164 165 166 167 168 169 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 162 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
62 63 64 65 66 67 68 69 70 71 72 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 62 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
202 203 204 205 206 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 202 def obligations_cleanup(x) obligations_cleanup_info(x) obligations_cleanup_norm(x) obligations_cleanup_inherit(x) end |
#obligations_cleanup_info(x) ⇒ Object
208 209 210 211 212 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 208 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
222 223 224 225 226 227 228 229 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 222 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
214 215 216 217 218 219 220 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 214 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
98 99 100 101 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 98 def omit_docid_prefix(prefix) return true if prefix.nil? || prefix.empty? ["ISO", "IEC", "IEV"].include? prefix end |
#origin_cleanup(xmldoc) ⇒ Object
69 70 71 72 73 74 75 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 69 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 |
#para_cleanup(xmldoc) ⇒ Object
12 13 14 15 16 17 18 19 20 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 12 def para_cleanup(xmldoc) xmldoc.xpath("//p[not(@id)]").each do |x| x["id"] = Utils::anchor_or_uuid end xmldoc.xpath("//note[not(@id)][not(ancestor::bibitem)]"\ "[not(ancestor::table)]").each do |x| x["id"] = Utils::anchor_or_uuid end end |
#quotesource_cleanup(xmldoc) ⇒ Object
63 64 65 66 67 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 63 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
78 79 80 81 82 83 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 78 def ref_cleanup(xmldoc) xmldoc.xpath("//p/ref").each do |r| parent = r.parent parent.previous = r.remove end end |
#reference_names(xmldoc) ⇒ Object
115 116 117 118 119 120 121 122 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 115 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 |
#refsIev2iec60050part(xmldoc, parts, iev) ⇒ Object
replace generic IEV reference with references to all extracted IEV parts
143 144 145 146 147 148 149 150 151 152 153 154 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 143 def refsIev2iec60050part(xmldoc, parts, iev) new_iev = "" parts.sort.each do |p| hit = @bibdb&.fetch("IEC 60050-#{p}", nil, keep_year: true) || next new_iev += hit.to_xml.sub(/ id="[^"]+"/, %{ id="IEC60050-#{p}"}) date = hit.dates[0].on.year xmldoc.xpath("//*[@citeas = 'IEC 60050-#{p}:2011']").each do |x| x["citeas"] = x["citeas"].sub(/:2011$/, ":#{date}") end end iev.replace(new_iev) end |
#requirement_cleanup(x) ⇒ Object
231 232 233 234 235 236 237 238 239 240 241 242 243 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 231 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 recommnedation 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
245 246 247 248 249 250 251 252 253 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 245 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
84 85 86 87 88 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 84 def script_cleanup(xmldoc) xmldoc.xpath("//script").each do |x| x.content = x.to_str end end |
#sections_cleanup(x) ⇒ Object
197 198 199 200 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 197 def sections_cleanup(x) sections_order_cleanup(x) sections_level_cleanup(x) end |
#sections_level_cleanup(x) ⇒ Object
186 187 188 189 190 191 192 193 194 195 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 186 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
171 172 173 174 175 176 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 171 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
61 62 63 64 65 66 67 68 69 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 61 def smartquotes_cleanup(xmldoc) return unless @smartquotes xmldoc.traverse do |n| next unless n.text? next unless n.ancestors("pre, tt, sourcecode, bibdata, on").empty? n.replace(Utils::smartformat(n.text)) end xmldoc end |
#strip_initial_space(x) ⇒ Object
222 223 224 225 226 227 228 229 230 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 222 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
99 100 101 102 103 104 105 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 99 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
55 56 57 58 59 |
# File 'lib/asciidoctor/standoc/cleanup_block.rb', line 55 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
186 187 188 189 190 191 192 193 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 186 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 |
#termdef_boilerplate_cleanup(xmldoc) ⇒ Object
168 169 170 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 168 def termdef_boilerplate_cleanup(xmldoc) xmldoc.xpath("//terms/p | //terms/ul").each(&:remove) end |
#termdef_cleanup(xmldoc) ⇒ Object
195 196 197 198 199 200 201 202 203 204 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 195 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
130 131 132 133 134 135 136 137 138 139 140 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 130 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
172 173 174 175 176 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 172 def termdef_subclause_cleanup(xmldoc) xmldoc.xpath("//terms[terms]").each do |t| t.name = "clause" end end |
#termdef_unnest_cleanup(xmldoc) ⇒ Object
159 160 161 162 163 164 165 166 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 159 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
149 150 151 152 153 154 155 156 157 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 149 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
178 179 180 181 182 183 184 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 178 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
142 143 144 145 146 147 |
# File 'lib/asciidoctor/standoc/cleanup.rb', line 142 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 |
# 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>}, '<amathstem>\1</amathstem>') 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
19 20 21 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 19 def tq(x) x.sub(/^"/, "").sub(/"$/, "") end |
#xref_cleanup(xmldoc) ⇒ Object
43 44 45 46 47 48 49 50 51 52 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 43 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
35 36 37 38 39 40 41 |
# File 'lib/asciidoctor/standoc/cleanup_ref.rb', line 35 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 |