Class: IsoDoc::Convert
- Inherits:
-
Object
- Object
- IsoDoc::Convert
- Defined in:
- lib/isodoc/html.rb,
lib/isodoc/i18n.rb,
lib/isodoc/lists.rb,
lib/isodoc/table.rb,
lib/isodoc/terms.rb,
lib/isodoc/utils.rb,
lib/isodoc/blocks.rb,
lib/isodoc/cleanup.rb,
lib/isodoc/convert.rb,
lib/isodoc/comments.rb,
lib/isodoc/metadata.rb,
lib/isodoc/xref_gen.rb,
lib/isodoc/footnotes.rb,
lib/isodoc/references.rb,
lib/isodoc/xref_sect_gen.rb
Direct Known Subclasses
Constant Summary collapse
- MATHJAX_ADDR =
"https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js".freeze
- MATHJAX =
<<~"MATHJAX".freeze <script type="text/x-mathjax-config"> MathJax.Hub.Config({ asciimath2jax: { delimiters: [['OPEN', 'CLOSE']] } }); </script> <script src="#{MATHJAX_ADDR}?config=AM_HTMLorMML"></script> MATHJAX
- OL_STYLE =
{ arabic: "1", roman: "i", alphabet: "a", roman_upper: "I", alphabet_upper: "A", }.freeze
- SW =
"solid windowtext".freeze
- STAGE_ABBRS =
{ "00": "PWI", "10": "NWIP", "20": "WD", "30": "CD", "40": "DIS", "50": "FDIS", "60": "IS", "90": "(Review)", "95": "(Withdrawal)", }.freeze
- NOKOHEAD =
"95": "(Withdrawal)", }.freeze def stage_abbreviation(stage) STAGE_ABBRS[stage.to_sym] || "??" end NOKOHEAD = <<~HERE.freeze <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <title></title> <meta charset="UTF-8" /> </head> <body> </body> </html> HERE
- CLAUSE_ANCESTOR =
".//ancestor::*[local-name() = 'subsection' or "\ "local-name() = 'foreword' or "\ "local-name() = 'introduction' or local-name() = 'terms' or "\ "local-name() = 'clause' or local-name() = 'references' or "\ "local-name() = 'annex']/@id".freeze
- NOTE_CONTAINER_ANCESTOR =
".//ancestor::*[local-name() = 'subsection' or "\ "local-name() = 'foreword' or "\ "local-name() = 'introduction' or local-name() = 'terms' or "\ "local-name() = 'clause' or local-name() = 'references' or "\ "local-name() = 'annex' or local-name() = 'formula' or "\ "local-name() = 'table' or local-name() = 'example' or "\ "local-name() = 'figure']/@id".freeze
- EXAMPLE_TBL_ATTR =
{ width: "110pt", valign: "top", style: "width:82.8pt;padding:.75pt .75pt .75pt .75pt" }.freeze
- FIGURE_WITH_FOOTNOTES =
"//div[@class = 'figure'][descendant::aside]"\ "[not(descendant::div[@class = 'figure'])]".freeze
- COMMENT_IN_COMMENT_LIST =
'//div[@style="mso-element:comment-list"]//'\ 'span[@style="MsoCommentReference"]'.freeze
- COMMENT_TARGET_XREFS =
"//span[@style='mso-special-character:comment']/@target".freeze
- SECTIONS_XPATH =
"//foreword | //introduction | //sections/terms | //annex | "\ "//sections/clause | //references[not(ancestor::clause)] | "\ "//clause[descendant::references][not(ancestor::clause)]".freeze
- CHILD_NOTES_XPATH =
"./*[not(self::xmlns:subsection)]//xmlns:note | ./xmlns:note".freeze
- CHILD_EXAMPLES_XPATH =
"./*[not(self::xmlns:subsection)]//xmlns:example | "\ "./xmlns:example".freeze
- ISO_PUBLISHER_XPATH =
"./contributor[xmlns:role/@type = 'publisher']/"\ "organization[abbreviation = 'ISO' or xmlns:abbreviation = 'IEC' or "\ "xmlns:name = 'International Organization for Standardization' or "\ "xmlns:name = 'International Electrotechnical Commission']".freeze
Instance Method Summary collapse
- #admitted_term_parse(node, out) ⇒ Object
- #admonition_cleanup(docxml) ⇒ Object
- #admonition_parse(node, out) ⇒ Object
- #agency(xml) ⇒ Object
-
#anchor_names(docxml) ⇒ Object
extract names for all anchors, xref and label.
- #anchor_struct(lbl, container, elem) ⇒ Object
- #annex_names(clause, num) ⇒ Object
- #annex_names1(clause, num, level) ⇒ Object
- #annotation_parse(node, out) ⇒ Object
- #attr_code(attributes) ⇒ Object
- #author(xml, _out) ⇒ Object
- #back_anchor_names(docxml) ⇒ Object
- #bibdate(isoxml, _out) ⇒ Object
- #biblio_list(f, div, bibliography) ⇒ Object
- #bibliography(isoxml, out) ⇒ Object
- #bibliography_parse(node, out) ⇒ Object
- #clause_names(docxml, sect_num) ⇒ Object
- #cleanup(docxml) ⇒ Object
- #comment_attributes(docxml, x) ⇒ Object
- #comment_cleanup(docxml) ⇒ Object
- #comment_link_attrs(fn, node) ⇒ Object
- #comments(div) ⇒ Object
- #compose_title(main, intro, part, partnum, subpartnum, lang) ⇒ Object
- #convert(filename, debug = false) ⇒ Object
- #convert1(docxml, filename, dir) ⇒ Object
- #convert_file(file, filename, debug) ⇒ Object
- #convert_init(file, filename, debug) ⇒ Object
- #date_note_process(b, ref) ⇒ Object
- #date_range(date) ⇒ Object
- #definition_parse(node, out) ⇒ Object
- #deprecated_term_parse(node, out) ⇒ Object
- #dl_parse(node, out) ⇒ Object
- #docid_l10n(x) ⇒ Object
- #docnumber(isoxml) ⇒ Object
- #draftinfo(draft, revdate) ⇒ Object
- #dt_parse(dt, term) ⇒ Object
- #embed_comment_in_comment_list(docxml) ⇒ Object
- #eref_localities1(type, from, to, lang = "en") ⇒ Object
- #eref_localities1_zh(type, from, to) ⇒ Object
- #example_anchor_names(sections) ⇒ Object
-
#example_div_parse(node, out) ⇒ Object
used if we are boxing examples.
- #example_label(node) ⇒ Object
- #example_parse(node, out) ⇒ Object
-
#extract_delims(text) ⇒ Object
avoid ‘; avoid {{ (Liquid Templates); avoid [[ (Javascript).
- #extract_symbols_list(dl) ⇒ Object
- #figure_aside_process(f, aside, key) ⇒ Object
-
#figure_cleanup(docxml) ⇒ Object
move footnotes into key, and get rid of footnote reference since it is in diagram.
- #figure_get_or_make_dl(t) ⇒ Object
- #figure_key(out) ⇒ Object
- #figure_name_parse(node, div, name) ⇒ Object
- #figure_parse(node, out) ⇒ Object
- #footnote_backlinks(docxml) ⇒ Object
- #footnote_cleanup(docxml) ⇒ Object
- #footnote_parse(node, out) ⇒ Object
- #footnotes(div) ⇒ Object
- #format_ref(ref, isopub, date) ⇒ Object
- #formula_parse(node, out) ⇒ Object
- #formula_where(dl, out) ⇒ Object
- #from_xhtml(xml) ⇒ Object
- #get_anchors ⇒ Object
- #get_clause_id(node) ⇒ Object
- #get_comments_from_text(docxml, link_order) ⇒ Object
- #get_metadata ⇒ Object
- #get_note_container_id(node) ⇒ Object
- #get_table_ancestor_id(node) ⇒ Object
- #header_strip(h) ⇒ Object
- #hierarchical_asset_names(clause, num) ⇒ Object
- #hierarchical_figure_names(clause, num) ⇒ Object
- #html_cleanup(x) ⇒ Object
- #html_cover(docxml) ⇒ Object
- #html_footnote_filter(docxml) ⇒ Object
- #html_intro(docxml) ⇒ Object
- #html_preface(docxml) ⇒ Object
- #html_toc(docxml) ⇒ Object
- #html_toc1(h, ret, prevname) ⇒ Object
- #htmlstyle(docxml) ⇒ Object
- #htmlstylesheet ⇒ Object
- #i18n_init(lang, script) ⇒ Object
- #id(isoxml, _out) ⇒ Object
- #image_parse(url, out, caption) ⇒ Object
- #image_title_parse(out, caption) ⇒ Object
- #in_comment ⇒ Object
- #init_metadata ⇒ Object
- #initial_anchor_names(d) ⇒ Object
-
#initialize(options) ⇒ Convert
constructor
htmlstylesheet: Generic stylesheet for HTML wordstylesheet: Generic stylesheet for Word standardsheet: Stylesheet specific to Standard header: Header file for Word htmlcoverpage: Cover page for HTML wordcoverpage: Cover page for Word htmlintropage: Introductory page for HTML wordintropage: Introductory page for Word i18nyaml: YAML file for internationalisation of text ulstyle: list style in Word CSS for unordered lists olstyle: list style in Word CSS for ordered lists.
- #inline_header_cleanup(docxml) ⇒ Object
- #insert_comment_cont(from, to, target) ⇒ Object
- #insert_tab(out, n) ⇒ Object
- #introduction_names(clause) ⇒ Object
- #iso?(org) ⇒ Boolean
- #iso_bibitem_entry(list, b, ordinal, biblio) ⇒ Object
- #iso_bibitem_entry_attrs(b, biblio) ⇒ Object
- #iso_bibitem_ref_code(b) ⇒ Object
-
#l10n(x, lang = @lang, script = @script) ⇒ Object
function localising spaces and punctuation.
- #li_parse(node, out) ⇒ Object
- #list_anchor_names(sections) ⇒ Object
- #list_item_anchor_names(list, list_anchor, depth, prev_label, refer_list) ⇒ Object
- #listlabel(depth, i) ⇒ Object
-
#make_comment_link(out, fn, node) ⇒ Object
add in from and to links to move the comment into place.
- #make_comment_target(out) ⇒ Object
- #make_comment_text(node, fn) ⇒ Object
- #make_generic_footnote_text(node, fnid) ⇒ Object
- #make_table_attr(node) ⇒ Object
- #make_table_footnote_link(out, fnid, fnref) ⇒ Object
- #make_table_footnote_target(out, fnid, fnref) ⇒ Object
- #make_table_footnote_text(node, fnid, fnref) ⇒ Object
-
#make_tr_attr(td, row, totalrows) ⇒ Object
def make_tr_attr(td, row, totalrows, cols, totalcols, header) border-left:#? “#{SW 1.5pt;” : “none;”} border-right:#SW #== totalcols && !header ? “1.5” : “1.0”pt;.
- #mathjax(open, close) ⇒ Object
- #merge_fnref_into_fn_text(a) ⇒ Object
- #middle_anchor_names(docxml) ⇒ Object
- #middle_section_asset_names(d) ⇒ Object
- #modification_parse(node, out) ⇒ Object
- #move_comment_link_to_from(docxml) ⇒ Object
- #move_comment_link_to_from1(x, fromlink) ⇒ Object
-
#move_images(docxml) ⇒ Object
presupposes that the image source is local.
- #new_fullcolspan_row(t, tfoot) ⇒ Object
-
#noko(&block) ⇒ Object
block for processing XML document fragments as XHTML, to allow for HTMLentities.
-
#noniso_bibitem(list, b, ordinal, bibliography) ⇒ Object
TODO generate formatted ref if not present.
- #norm_ref(isoxml, out) ⇒ Object
- #norm_ref_preface(f, div) ⇒ Object
- #note_anchor_names(sections) ⇒ Object
- #note_label(node) ⇒ Object
- #note_p_parse(node, div) ⇒ Object
- #note_parse(node, out) ⇒ Object
- #note_parse1(node, div) ⇒ Object
- #ns(xpath) ⇒ Object
-
#ol_depth(node) ⇒ Object
We don’t really want users to specify type of ordered list; we will use a fixed hierarchy as practiced by ISO (though not fully spelled out): a) 1) i) A) I).
- #ol_parse(node, out) ⇒ Object
- #ol_style(type) ⇒ Object
- #para_attrs(node) ⇒ Object
- #para_parse(node, out) ⇒ Object
- #para_then_remainder(first, node, p, div) ⇒ Object
-
#part_label(lang) ⇒ Object
we don’t leave this to i18n.rb, because we have both English and French titles in the same document.
- #populate_template(docxml, _format) ⇒ Object
- #postprocess(result, filename, dir) ⇒ Object
- #quote_attribution(node, out) ⇒ Object
- #quote_parse(node, out) ⇒ Object
- #ref_entry_code(r, ordinal, t) ⇒ Object
- #reference_format(b, r) ⇒ Object
- #reference_names(ref) ⇒ Object
- #relations(isoxml, _out) ⇒ Object
- #remove_bottom_border(td) ⇒ Object
- #reorder_comments_by_comment_link(docxml) ⇒ Object
- #review_note_parse(node, out) ⇒ Object
- #sc(xml) ⇒ Object
- #secretariat(xml) ⇒ Object
- #section_names(clause, num, lvl) ⇒ Object
- #section_names1(clause, num, level) ⇒ Object
- #sentence_join(array) ⇒ Object
- #sequential_asset_names(clause) ⇒ Object
- #sequential_figure_names(clause) ⇒ Object
- #set_metadata(key, value) ⇒ Object
- #skip_comment_wrap(from) ⇒ Object
- #sourcecode_name_parse(_node, div, name) ⇒ Object
- #sourcecode_parse(node, out) ⇒ Object
- #split_bibitems(f) ⇒ Object
- #stage_abbreviation(stage) ⇒ Object
- #subtitle(isoxml, _out) ⇒ Object
-
#symbol_key(x) ⇒ Object
We assume AsciiMath is being used in the terms & definitions.
- #symbols_cleanup(docxml) ⇒ Object
- #table_cleanup(docxml) ⇒ Object
- #table_footnote_cleanup(docxml) ⇒ Object
- #table_footnote_parse(node, out) ⇒ Object
- #table_get_or_make_tfoot(t) ⇒ Object
- #table_note_cleanup(docxml) ⇒ Object
- #table_parse(node, out) ⇒ Object
- #table_title_parse(node, out) ⇒ Object
- #tbody_parse(node, t) ⇒ Object
- #tc(xml) ⇒ Object
- #term_parse(node, out) ⇒ Object
- #termdef_parse(node, out) ⇒ Object
- #termexample_anchor_names(docxml) ⇒ Object
- #termnote_anchor_names(docxml) ⇒ Object
- #termnote_label(n) ⇒ Object
- #termnote_parse(node, out) ⇒ Object
- #termref_parse(node, out) ⇒ Object
- #tfoot_parse(node, t) ⇒ Object
- #thead_parse(node, t) ⇒ Object
- #title(isoxml, _out) ⇒ Object
- #to_xhtml(xml) ⇒ Object
- #to_xhtml_fragment(xml) ⇒ Object
- #toHTML(result, filename) ⇒ Object
- #tr_parse(node, out, ord, totalrows, _header) ⇒ Object
- #ul_parse(node, out) ⇒ Object
- #update_footnote_filter(fn, x, i, seen) ⇒ Object
- #version(isoxml, _out) ⇒ Object
- #wg(xml) ⇒ Object
- #wrap_comment_cont(from, target) ⇒ Object
Constructor Details
#initialize(options) ⇒ Convert
htmlstylesheet: Generic stylesheet for HTML wordstylesheet: Generic stylesheet for Word standardsheet: Stylesheet specific to Standard header: Header file for Word htmlcoverpage: Cover page for HTML wordcoverpage: Cover page for Word htmlintropage: Introductory page for HTML wordintropage: Introductory page for Word i18nyaml: YAML file for internationalisation of text ulstyle: list style in Word CSS for unordered lists olstyle: list style in Word CSS for ordered lists
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 63 64 |
# File 'lib/isodoc/convert.rb', line 33 def initialize() @htmlstylesheet = [:htmlstylesheet] @wordstylesheet = [:wordstylesheet] @standardstylesheet = [:standardstylesheet] @header = [:header] @htmlcoverpage = [:htmlcoverpage] @wordcoverpage = [:wordcoverpage] @htmlintropage = [:htmlintropage] @wordintropage = [:wordintropage] @i18nyaml = [:i18nyaml] @ulstyle = [:ulstyle] @olstyle = [:olstyle] @termdomain = "" @termexample = false @note = false @sourcecode = false @anchors = {} @meta = {} @footnotes = [] @comments = [] @in_footnote = false @in_comment = false @in_table = false @in_figure = false @seen_footnote = Set.new @c = HTMLEntities.new @openmathdelim = "`" @closemathdelim = "`" @lang = "en" @script = "Latn" end |
Instance Method Details
#admitted_term_parse(node, out) ⇒ Object
20 21 22 23 24 |
# File 'lib/isodoc/terms.rb', line 20 def admitted_term_parse(node, out) out.p **{ class: "AltTerms" } do |p| node.children.each { |c| parse(c, p) } end end |
#admonition_cleanup(docxml) ⇒ Object
18 19 20 21 22 23 24 25 |
# File 'lib/isodoc/cleanup.rb', line 18 def admonition_cleanup(docxml) docxml.xpath("//div[@class = 'Admonition'][title]").each do |d| title = d.at("./title") n = title.next_element n&.children&.first&.add_previous_sibling(title.remove.text + "—") end docxml end |
#admonition_parse(node, out) ⇒ Object
131 132 133 134 135 136 137 138 139 |
# File 'lib/isodoc/blocks.rb', line 131 def admonition_parse(node, out) name = node["type"] out.div **{ class: "Admonition" } do |t| t.title { |b| b << name.upcase } if name node.children.each do |n| parse(n, t) end end end |
#agency(xml) ⇒ Object
89 90 91 92 93 94 95 96 97 98 99 |
# File 'lib/isodoc/metadata.rb', line 89 def agency(xml) agency = "" xml.xpath(ns("//bibdata/contributor[xmlns:role/@type = 'publisher']/"\ "organization")).each do |org| name = org&.at(ns("./name"))&.text abbrev = org&.at(ns("./abbreviation"))&.text agency1 = abbrev || name agency = iso?(org) ? "ISO/#{agency}" : "#{agency}#{agency1}/" end (:agency, agency.sub(%r{/$}, "")) end |
#anchor_names(docxml) ⇒ Object
extract names for all anchors, xref and label
122 123 124 125 126 127 128 129 130 131 132 |
# File 'lib/isodoc/xref_gen.rb', line 122 def anchor_names(docxml) initial_anchor_names(docxml) middle_anchor_names(docxml) back_anchor_names(docxml) # preempt clause notes with all other types of note note_anchor_names(docxml.xpath(ns("//table | //example | //formula | "\ "//figure"))) note_anchor_names(docxml.xpath(ns(SECTIONS_XPATH))) example_anchor_names(docxml.xpath(ns(SECTIONS_XPATH))) list_anchor_names(docxml.xpath(ns(SECTIONS_XPATH))) end |
#anchor_struct(lbl, container, elem) ⇒ Object
147 148 149 150 151 152 153 154 |
# File 'lib/isodoc/xref_gen.rb', line 147 def anchor_struct(lbl, container, elem) ret = { label: lbl.to_s } ret[:xref] = elem == "Formula" ? l10n("#{elem} (#{lbl})") : l10n("#{elem} #{lbl}") ret[:xref].gsub!(/ $/, "") ret[:container] = get_clause_id(container) unless container.nil? ret end |
#annex_names(clause, num) ⇒ Object
63 64 65 66 67 68 69 70 71 72 73 |
# File 'lib/isodoc/xref_sect_gen.rb', line 63 def annex_names(clause, num) obl = l10n("(#{@inform_annex_lbl})") obl = l10n("(#{@norm_annex_lbl})") if clause["obligation"] == "normative" label = l10n("<b>#{@annex_lbl} #{num}</b><br/>#{obl}") @anchors[clause["id"]] = { label: label, xref: "#{@annex_lbl} #{num}", level: 1 } clause.xpath(ns("./subsection")).each_with_index do |c, i| annex_names1(c, "#{num}.#{i + 1}", 2) end hierarchical_asset_names(clause, num) end |
#annex_names1(clause, num, level) ⇒ Object
75 76 77 78 79 80 |
# File 'lib/isodoc/xref_sect_gen.rb', line 75 def annex_names1(clause, num, level) @anchors[clause["id"]] = { label: num, xref: num, level: level } clause.xpath(ns(".//subsection")).each_with_index do |c, i| annex_names1(c, "#{num}.#{i + 1}", level + 1) end end |
#annotation_parse(node, out) ⇒ Object
121 122 123 124 125 126 127 128 129 |
# File 'lib/isodoc/blocks.rb', line 121 def annotation_parse(node, out) @sourcecode = false @annotation = true out.span **{ class: "zzMoveToFollowing" } do |s| s << "<#{node.at(ns("//callout[@target='#{node['id']}']")).text}> " end node.children.each { |n| parse(n, out) } @annotation = false end |
#attr_code(attributes) ⇒ Object
49 50 51 52 53 54 |
# File 'lib/isodoc/utils.rb', line 49 def attr_code(attributes) attributes = attributes.reject { |_, val| val.nil? }.map attributes.map do |k, v| [k, (v.is_a? String) ? HTMLEntities.new.decode(v) : v] end.to_h end |
#author(xml, _out) ⇒ Object
24 25 26 27 28 29 30 |
# File 'lib/isodoc/metadata.rb', line 24 def (xml, _out) tc(xml) sc(xml) wg(xml) secretariat(xml) agency(xml) end |
#back_anchor_names(docxml) ⇒ Object
3 4 5 6 7 8 9 10 |
# File 'lib/isodoc/xref_sect_gen.rb', line 3 def back_anchor_names(docxml) docxml.xpath(ns("//annex")).each_with_index do |c, i| annex_names(c, (65 + i).chr.to_s) end docxml.xpath(ns("//bibitem")).each do |ref| reference_names(ref) end end |
#bibdate(isoxml, _out) ⇒ Object
76 77 78 79 80 |
# File 'lib/isodoc/metadata.rb', line 76 def bibdate(isoxml, _out) isoxml.xpath(ns("//bibdata/date")).each do |d| ("#{d['type']}date".to_sym, date_range(d)) end end |
#biblio_list(f, div, bibliography) ⇒ Object
88 89 90 91 92 93 94 95 96 |
# File 'lib/isodoc/references.rb', line 88 def biblio_list(f, div, bibliography) bibitems = split_bibitems(f) bibitems[:iso].each_with_index do |b, i| iso_bibitem_entry(div, b, (i + 1), bibliography) end bibitems[:noniso].each_with_index do |b, i| noniso_bibitem(div, b, (i + 1 + bibitems[:iso].size), bibliography) end end |
#bibliography(isoxml, out) ⇒ Object
119 120 121 122 123 124 125 126 127 128 129 130 |
# File 'lib/isodoc/references.rb', line 119 def bibliography(isoxml, out) q = "//clause[title = 'Bibliography'][descendant::references] | //references[title = 'Bibliography']" f = isoxml.at(ns(q)) || return page_break(out) out.div do |div| div.h1 @bibliography_lbl, **{ class: "Section3" } f.elements.reject do |e| ["reference", "title", "bibitem"].include? e.name end.each { |e| parse(e, div) } biblio_list(f, div, true) end end |
#bibliography_parse(node, out) ⇒ Object
132 133 134 135 136 137 138 139 140 141 |
# File 'lib/isodoc/references.rb', line 132 def bibliography_parse(node, out) title = node&.at(ns("./title"))&.text || "" out.div do |div| div.h2 title, **{ class: "Section3" } node.elements.reject do |e| ["reference", "title", "bibitem"].include? e.name end.each { |e| parse(e, div) } biblio_list(node, div, true) end end |
#clause_names(docxml, sect_num) ⇒ Object
29 30 31 32 33 34 |
# File 'lib/isodoc/xref_sect_gen.rb', line 29 def clause_names(docxml, sect_num) q = "//clause[parent::sections][not(xmlns:title = 'Scope')][not(descendant::terms)]" docxml.xpath(ns(q)).each_with_index do |c, i| section_names(c, (i + sect_num).to_s, 1) end end |
#cleanup(docxml) ⇒ Object
8 9 10 11 12 13 14 15 16 |
# File 'lib/isodoc/cleanup.rb', line 8 def cleanup(docxml) comment_cleanup(docxml) footnote_cleanup(docxml) inline_header_cleanup(docxml) figure_cleanup(docxml) table_cleanup(docxml) symbols_cleanup(docxml) admonition_cleanup(docxml) end |
#comment_attributes(docxml, x) ⇒ Object
85 86 87 88 89 90 91 |
# File 'lib/isodoc/comments.rb', line 85 def comment_attributes(docxml, x) fromlink = docxml.at("//*[@id='#{x['from']}']") return(nil) if fromlink.nil? tolink = docxml.at("//*[@id='#{x['to']}']") || fromlink target = docxml.at("//*[@id='#{x['target']}']") { from: fromlink, to: tolink, target: target } end |
#comment_cleanup(docxml) ⇒ Object
60 61 62 63 64 |
# File 'lib/isodoc/comments.rb', line 60 def comment_cleanup(docxml) move_comment_link_to_from(docxml) reorder_comments_by_comment_link(docxml) (docxml) end |
#comment_link_attrs(fn, node) ⇒ Object
24 25 26 27 28 |
# File 'lib/isodoc/comments.rb', line 24 def comment_link_attrs(fn, node) { style: "MsoCommentReference", target: fn, class: "commentLink", from: node["from"], to: node["to"] } end |
#comments(div) ⇒ Object
9 10 11 12 13 14 |
# File 'lib/isodoc/comments.rb', line 9 def comments(div) return if @comments.empty? div.div **{ style: "mso-element:comment-list" } do |div1| @comments.each { |fn| div1.parent << fn } end end |
#compose_title(main, intro, part, partnum, subpartnum, lang) ⇒ Object
150 151 152 153 154 155 156 157 158 159 160 161 |
# File 'lib/isodoc/metadata.rb', line 150 def compose_title(main, intro, part, partnum, subpartnum, lang) main = main.nil? ? "" : @c.encode(main.text, :hexadecimal) intro && main = "#{@c.encode(intro.text, :hexadecimal)} — #{main}" if part suffix = @c.encode(part.text, :hexadecimal) partnum = "#{partnum}–#{subpartnum}" if partnum && subpartnum suffix = "#{part_label(lang)} #{partnum}: " + suffix if partnum main = "#{main} — #{suffix}" end main end |
#convert(filename, debug = false) ⇒ Object
85 86 87 |
# File 'lib/isodoc/convert.rb', line 85 def convert(filename, debug = false) convert_file(File.read(filename), filename, debug) end |
#convert1(docxml, filename, dir) ⇒ Object
66 67 68 69 70 71 72 73 74 |
# File 'lib/isodoc/convert.rb', line 66 def convert1(docxml, filename, dir) noko do |xml| xml.html do |html| html.parent.add_namespace("epub", "http://www.idpf.org/2007/ops") html_header(html, docxml, filename, dir) make_body(html, docxml) end end.join("\n") end |
#convert_file(file, filename, debug) ⇒ Object
89 90 91 92 93 94 95 |
# File 'lib/isodoc/convert.rb', line 89 def convert_file(file, filename, debug) @openmathdelim, @closemathdelim = extract_delims(file) docxml, filename, dir = convert_init(file, filename, debug) result = convert1(docxml, filename, dir) return result if debug postprocess(result, filename, dir) end |
#convert_init(file, filename, debug) ⇒ Object
76 77 78 79 80 81 82 83 |
# File 'lib/isodoc/convert.rb', line 76 def convert_init(file, filename, debug) docxml = Nokogiri::XML(file) filename, dir = init_file(filename, debug) docxml.root.default_namespace = "" i18n_init(docxml&.at(ns("//bibdata/language"))&.text || "en", docxml&.at(ns("//bibdata/script"))&.text || "Latn") [docxml, filename, dir] end |
#date_note_process(b, ref) ⇒ Object
15 16 17 18 19 20 21 |
# File 'lib/isodoc/references.rb', line 15 def date_note_process(b, ref) date_note = b.at(ns("./note[text()][contains(.,'ISO DATE:')]")) return if date_note.nil? date_note.content = date_note.content.gsub(/ISO DATE: /, "") date_note.children.first.replace("<p>#{date_note.content}</p>") footnote_parse(date_note, ref) end |
#date_range(date) ⇒ Object
68 69 70 71 72 73 74 |
# File 'lib/isodoc/metadata.rb', line 68 def date_range(date) from = date.at(ns("./from")) to = date.at(ns("./to")) ret = from.text ret += "–#{to.text}" if to ret end |
#definition_parse(node, out) ⇒ Object
3 4 5 |
# File 'lib/isodoc/terms.rb', line 3 def definition_parse(node, out) node.children.each { |n| parse(n, out) } end |
#deprecated_term_parse(node, out) ⇒ Object
13 14 15 16 17 18 |
# File 'lib/isodoc/terms.rb', line 13 def deprecated_term_parse(node, out) out.p **{ class: "DeprecatedTerms" } do |p| p << l10n("#{@deprecated_lbl}: ") node.children.each { |c| parse(c, p) } end end |
#dl_parse(node, out) ⇒ Object
61 62 63 64 65 66 67 68 69 70 71 72 |
# File 'lib/isodoc/lists.rb', line 61 def dl_parse(node, out) out.dl do |v| node.elements.each_slice(2) do |dt, dd| v.dt do |term| dt_parse(dt, term) end v.dd do |listitem| dd.children.each { |n| parse(n, listitem) } end end end end |
#docid_l10n(x) ⇒ Object
3 4 5 |
# File 'lib/isodoc/references.rb', line 3 def docid_l10n(x) x.gsub(/All Parts/, @all_parts_lbl) end |
#docnumber(isoxml) ⇒ Object
101 102 103 104 105 106 107 108 109 |
# File 'lib/isodoc/metadata.rb', line 101 def docnumber(isoxml) docnumber = isoxml.at(ns("//project-number")) partnumber = isoxml.at(ns("//project-number/@part")) subpartnumber = isoxml.at(ns("//project-number/@subpart")) dn = docnumber&.text || "" dn += "-#{partnumber.text}" if partnumber dn += "-#{subpartnumber.text}" if subpartnumber dn end |
#draftinfo(draft, revdate) ⇒ Object
123 124 125 126 127 128 129 130 131 |
# File 'lib/isodoc/metadata.rb', line 123 def draftinfo(draft, revdate) draftinfo = "" if draft draftinfo = " (#{@draft_lbl} #{draft}" draftinfo += ", #{revdate}" if revdate draftinfo += ")" end l10n(draftinfo) end |
#dt_parse(dt, term) ⇒ Object
51 52 53 54 55 56 57 58 59 |
# File 'lib/isodoc/lists.rb', line 51 def dt_parse(dt, term) if dt.elements.empty? term.p **attr_code(class: note? ? "Note" : nil) do |p| p << dt.text end else dt.children.each { |n| parse(n, term) } end end |
#embed_comment_in_comment_list(docxml) ⇒ Object
70 71 72 73 74 75 76 |
# File 'lib/isodoc/comments.rb', line 70 def (docxml) docxml.xpath(COMMENT_IN_COMMENT_LIST).each do |x| n = x.next_element n&.children&.first&.add_previous_sibling(x.remove) end docxml end |
#eref_localities1(type, from, to, lang = "en") ⇒ Object
68 69 70 71 72 73 74 75 76 |
# File 'lib/isodoc/i18n.rb', line 68 def eref_localities1(type, from, to, lang = "en") subsection = from&.text&.match?(/\./) return l10n(eref_localities1_zh(type, from, to)) if lang == "zh" ret = "," ret += " #{@locality[type]}" unless subsection && type == "clause" ret += " #{from.text}" if from ret += "–#{to.text}" if to l10n(ret) end |
#eref_localities1_zh(type, from, to) ⇒ Object
61 62 63 64 65 66 |
# File 'lib/isodoc/i18n.rb', line 61 def eref_localities1_zh(type, from, to) ret = ", 第#{from.text}" if from ret += "–#{to}" if to ret += @locality[type] ret end |
#example_anchor_names(sections) ⇒ Object
62 63 64 65 66 67 68 69 70 71 72 |
# File 'lib/isodoc/xref_gen.rb', line 62 def example_anchor_names(sections) sections.each do |s| notes = s.xpath(CHILD_EXAMPLES_XPATH) notes.each_with_index do |n, i| next if @anchors[n["id"]] idx = notes.size == 1 ? "" : " #{i + 1}" @anchors[n["id"]] = anchor_struct(idx, s, @example_xref_lbl) end example_anchor_names(s.xpath(ns("./subsection"))) end end |
#example_div_parse(node, out) ⇒ Object
used if we are boxing examples
79 80 81 82 83 84 85 86 |
# File 'lib/isodoc/blocks.rb', line 79 def example_div_parse(node, out) out.div **attr_code(id: node["id"], class: "example") do |div| out.p { |p| p << example_label(node) } node.children.each do |n| parse(n, div) end end end |
#example_label(node) ⇒ Object
68 69 70 71 72 |
# File 'lib/isodoc/blocks.rb', line 68 def example_label(node) n = get_anchors[node["id"]] return @example_lbl if n.nil? || n[:label].empty? l10n("#{@example_lbl} #{n[:label]}") end |
#example_parse(node, out) ⇒ Object
88 89 90 91 92 93 94 95 96 97 98 99 |
# File 'lib/isodoc/blocks.rb', line 88 def example_parse(node, out) out.table **attr_code(id: node["id"], class: "example") do |t| t.tr do |tr| tr.td **EXAMPLE_TBL_ATTR do |td| td << example_label(node) end tr.td **{ valign: "top" } do |td| node.children.each { |n| parse(n, td) } end end end end |
#extract_delims(text) ⇒ Object
avoid ‘; avoid {{ (Liquid Templates); avoid [[ (Javascript)
111 112 113 114 115 116 117 118 119 |
# File 'lib/isodoc/utils.rb', line 111 def extract_delims(text) @openmathdelim = "(#(" @closemathdelim = ")#)" while text.include?(@openmathdelim) || text.include?(@closemathdelim) @openmathdelim += "(" @closemathdelim += ")" end [@openmathdelim, @closemathdelim] end |
#extract_symbols_list(dl) ⇒ Object
157 158 159 160 161 162 163 164 165 166 167 |
# File 'lib/isodoc/cleanup.rb', line 157 def extract_symbols_list(dl) dl_out = [] dl.xpath("./dt | ./dd").each do |dtd| if dtd.name == "dt" dl_out << { dt: dtd.remove, key: symbol_key(dtd) } else dl_out.last[:dd] = dtd.remove end end dl_out end |
#figure_aside_process(f, aside, key) ⇒ Object
40 41 42 43 44 45 46 47 48 49 50 51 |
# File 'lib/isodoc/cleanup.rb', line 40 def figure_aside_process(f, aside, key) # get rid of footnote link, it is in diagram f&.at("./a[@class='TableFootnoteRef']")&.remove fnref = f.at(".//a[@class='TableFootnoteRef']") dt = key.add_child("<dt></dt>").first dd = key.add_child("<dd></dd>").first fnref.parent = dt aside.xpath(".//p").each do |a| a.delete("class") a.parent = dd end end |
#figure_cleanup(docxml) ⇒ Object
move footnotes into key, and get rid of footnote reference since it is in diagram
55 56 57 58 59 60 61 62 63 |
# File 'lib/isodoc/cleanup.rb', line 55 def figure_cleanup(docxml) docxml.xpath(FIGURE_WITH_FOOTNOTES).each do |f| key = figure_get_or_make_dl(f) f.xpath(".//aside").each do |aside| figure_aside_process(f, aside, key) end end docxml end |
#figure_get_or_make_dl(t) ⇒ Object
27 28 29 30 31 32 33 34 |
# File 'lib/isodoc/cleanup.rb', line 27 def figure_get_or_make_dl(t) dl = t.at(".//dl") if dl.nil? t.add_child("<p><b>#{@key_lbl}</b></p><dl></dl>") dl = t.at(".//dl") end dl end |
#figure_key(out) ⇒ Object
49 50 51 52 53 |
# File 'lib/isodoc/blocks.rb', line 49 def figure_key(out) out.p do |p| p.b { |b| b << @key_lbl } end end |
#figure_name_parse(node, div, name) ⇒ Object
40 41 42 43 44 45 46 47 |
# File 'lib/isodoc/blocks.rb', line 40 def figure_name_parse(node, div, name) div.p **{ class: "FigureTitle", align: "center" } do |p| p.b do |b| b << l10n("#{@figure_lbl} #{get_anchors[node['id']][:label]}") b << " — #{name.text}" if name end end end |
#figure_parse(node, out) ⇒ Object
55 56 57 58 59 60 61 62 63 64 65 66 |
# File 'lib/isodoc/blocks.rb', line 55 def figure_parse(node, out) @in_figure = true name = node.at(ns("./name")) out.div **attr_code(id: node["id"], class: "figure") do |div| node.children.each do |n| figure_key(out) if n.name == "dl" parse(n, div) unless n.name == "name" end figure_name_parse(node, div, name) if name end @in_figure = false end |
#footnote_backlinks(docxml) ⇒ Object
100 101 102 103 104 105 106 107 108 109 110 111 |
# File 'lib/isodoc/html.rb', line 100 def footnote_backlinks(docxml) seen = {} docxml.xpath('//a[@epub:type = "footnote"]').each_with_index do |x, i| next if seen[x["href"]] seen[x["href"]] = true fn = docxml.at(%<//*[@id = '#{x['href'].sub(/^#/, '')}']>) || next x["id"] || x["id"] = "_footnote#{i + 1}" fn.elements.first.children.first.previous = "<a href='##{x['id']}'>#{x.at('./sup').text}) </a>" end docxml end |
#footnote_cleanup(docxml) ⇒ Object
78 79 80 81 82 83 |
# File 'lib/isodoc/cleanup.rb', line 78 def footnote_cleanup(docxml) docxml.xpath('//a[@epub:type = "footnote"]/sup').each_with_index do |x, i| x.content = (i + 1).to_s end docxml end |
#footnote_parse(node, out) ⇒ Object
61 62 63 64 65 66 67 68 69 70 71 72 |
# File 'lib/isodoc/footnotes.rb', line 61 def footnote_parse(node, out) return table_footnote_parse(node, out) if @in_table || @in_figure fn = node["reference"] out.a **{ "epub:type": "footnote", href: "#ftn#{fn}" } do |a| a.sup { |sup| sup << fn } end return if @seen_footnote.include?(fn) @in_footnote = true @footnotes << make_generic_footnote_text(node, fn) @in_footnote = false @seen_footnote << fn end |
#footnotes(div) ⇒ Object
5 6 7 8 |
# File 'lib/isodoc/footnotes.rb', line 5 def footnotes(div) return if @footnotes.empty? @footnotes.each { |fn| div.parent << fn } end |
#format_ref(ref, isopub, date) ⇒ Object
143 144 145 146 147 148 149 150 151 152 |
# File 'lib/isodoc/references.rb', line 143 def format_ref(ref, isopub, date) if isopub return ref unless date from = date.at(ns("./from")) return ref if from&.text == "--" return ref + ": #{date_range(date)}" end return "[#{ref}]" if /^\d+$/.match?(ref) && !/^\[.*\]$/.match?(ref) ref end |
#formula_parse(node, out) ⇒ Object
147 148 149 150 151 152 153 154 |
# File 'lib/isodoc/blocks.rb', line 147 def formula_parse(node, out) out.div **attr_code(id: node["id"], class: "formula") do |div| parse(node.at(ns("./stem")), out) insert_tab(div, 1) div << "(#{get_anchors[node['id']][:label]})" end formula_where(node.at(ns("./dl")), out) end |
#formula_where(dl, out) ⇒ Object
141 142 143 144 145 |
# File 'lib/isodoc/blocks.rb', line 141 def formula_where(dl, out) return unless dl out.p { |p| p << @where_lbl } parse(dl, out) end |
#from_xhtml(xml) ⇒ Object
71 72 73 |
# File 'lib/isodoc/utils.rb', line 71 def from_xhtml(xml) xml.to_xml.sub(%r{ xmlns="http://www.w3.org/1999/xhtml"}, "") end |
#get_anchors ⇒ Object
7 8 9 |
# File 'lib/isodoc/xref_gen.rb', line 7 def get_anchors @anchors end |
#get_clause_id(node) ⇒ Object
82 83 84 85 |
# File 'lib/isodoc/utils.rb', line 82 def get_clause_id(node) clause = node.xpath(CLAUSE_ANCESTOR) clause&.last&.text || nil end |
#get_comments_from_text(docxml, link_order) ⇒ Object
122 123 124 125 126 127 128 129 130 |
# File 'lib/isodoc/comments.rb', line 122 def get_comments_from_text(docxml, link_order) comments = [] docxml.xpath("//div[@style='mso-element:comment']").each do |c| next unless c["id"] && !link_order[c["id"]].nil? comments << { text: c.remove.to_s, id: c["id"] } end comments.sort! { |a, b| link_order[a[:id]] <=> link_order[b[:id]] } # comments end |
#get_metadata ⇒ Object
16 17 18 |
# File 'lib/isodoc/metadata.rb', line 16 def @meta end |
#get_note_container_id(node) ⇒ Object
96 97 98 99 |
# File 'lib/isodoc/utils.rb', line 96 def get_note_container_id(node) container = node.xpath(NOTE_CONTAINER_ANCESTOR) container&.last&.text || nil end |
#get_table_ancestor_id(node) ⇒ Object
43 44 45 46 47 |
# File 'lib/isodoc/footnotes.rb', line 43 def get_table_ancestor_id(node) table = node.ancestors("table") || node.ancestors("figure") return UUIDTools::UUID.random_create.to_s if table.empty? table.last["id"] end |
#header_strip(h) ⇒ Object
121 122 123 124 125 126 127 128 129 130 131 132 |
# File 'lib/isodoc/utils.rb', line 121 def header_strip(h) h = h.to_s.gsub(%r{<br/>}, " ").sub(/<\/?h[12][^>]*>/, "") h1 = to_xhtml_fragment(h.dup) h1.traverse do |x| x.remove if x.name == "span" && x["class"] == "MsoCommentReference" x.remove if x.name == "a" && x["epub:type"] == "footnote" if x.name == "a" x.replace(x.children) end end from_xhtml(h1) end |
#hierarchical_asset_names(clause, num) ⇒ Object
179 180 181 182 183 184 185 186 187 |
# File 'lib/isodoc/xref_gen.rb', line 179 def hierarchical_asset_names(clause, num) clause.xpath(ns(".//table")).each_with_index do |t, i| @anchors[t["id"]] = anchor_struct("#{num}.#{i + 1}", nil, @table_lbl) end hierarchical_figure_names(clause, num) clause.xpath(ns(".//formula")).each_with_index do |t, i| @anchors[t["id"]] = anchor_struct("#{num}.#{i + 1}", t, @formula_lbl) end end |
#hierarchical_figure_names(clause, num) ⇒ Object
166 167 168 169 170 171 172 173 174 175 176 177 |
# File 'lib/isodoc/xref_gen.rb', line 166 def hierarchical_figure_names(clause, num) i = j = 0 clause.xpath(ns(".//figure")).each do |t| if t.parent.name == "figure" then j += 1 else j = 0 i += 1 end label = "#{num}.#{i}" + (j.zero? ? "" : "-#{j}") @anchors[t["id"]] = anchor_struct(label, nil, @figure_lbl) end end |
#html_cleanup(x) ⇒ Object
16 17 18 19 20 |
# File 'lib/isodoc/html.rb', line 16 def html_cleanup(x) footnote_backlinks( html_toc(move_images(html_footnote_filter(html_preface(htmlstyle(x))))) ) end |
#html_cover(docxml) ⇒ Object
47 48 49 50 51 |
# File 'lib/isodoc/html.rb', line 47 def html_cover(docxml) cover = Nokogiri::HTML(File.read(@htmlcoverpage, encoding: "UTF-8")) d = docxml.at('//div[@class="WordSection1"]') d.children.first.add_previous_sibling cover.to_xml(encoding: "US-ASCII") end |
#html_footnote_filter(docxml) ⇒ Object
90 91 92 93 94 95 96 97 98 |
# File 'lib/isodoc/html.rb', line 90 def html_footnote_filter(docxml) seen = {} i = 1 docxml.xpath('//a[@epub:type = "footnote"]').each do |x| fn = docxml.at(%<//*[@id = '#{x['href'].sub(/^#/, '')}']>) || next i, seen = update_footnote_filter(fn, x, i, seen) end docxml end |
#html_intro(docxml) ⇒ Object
53 54 55 56 57 |
# File 'lib/isodoc/html.rb', line 53 def html_intro(docxml) cover = Nokogiri::HTML(File.read(@htmlintropage, encoding: "UTF-8")) d = docxml.at('//div[@class="WordSection2"]') d.children.first.add_previous_sibling cover.to_xml(encoding: "US-ASCII") end |
#html_preface(docxml) ⇒ Object
39 40 41 42 43 44 45 |
# File 'lib/isodoc/html.rb', line 39 def html_preface(docxml) html_cover(docxml) if @htmlcoverpage html_intro(docxml) if @htmlintropage docxml.at("//*[local-name() = 'body']") << mathjax(@openmathdelim, @closemathdelim) docxml end |
#html_toc(docxml) ⇒ Object
138 139 140 141 142 143 144 145 146 147 148 149 |
# File 'lib/isodoc/html.rb', line 138 def html_toc(docxml) return docxml unless @htmlintropage ret = "" prevname = "" docxml.xpath("//h1 | //h2").each do |h| ret = html_toc1(h, ret, prevname) unless h["class"] == "toc-contents" prevname = h.name end ret += "<ul>" if prevname == "h2" docxml.at("//*[@id='toc-list']").replace("<ul>#{ret}</ret>") docxml end |
#html_toc1(h, ret, prevname) ⇒ Object
127 128 129 130 131 132 133 134 135 136 |
# File 'lib/isodoc/html.rb', line 127 def html_toc1(h, ret, prevname) h["id"] = UUIDTools::UUID.random_create.to_s unless h["id"] li = "<li><a href='##{h["id"]}'>#{header_strip(h)}</a></li>" if h.name == "h1" ret += "</ul>" if prevname == "h2" else ret += "<ul>" if prevname == "h1" end ret + li end |
#htmlstyle(docxml) ⇒ Object
66 67 68 69 70 71 72 73 74 75 |
# File 'lib/isodoc/html.rb', line 66 def htmlstyle(docxml) title = docxml.at("//*[local-name() = 'head']/*[local-name() = 'title']") head = docxml.at("//*[local-name() = 'head']") css = htmlstylesheet if title.nil? then head.children.first.add_previous_sibling css else title.add_next_sibling css end docxml end |
#htmlstylesheet ⇒ Object
59 60 61 62 63 64 |
# File 'lib/isodoc/html.rb', line 59 def htmlstylesheet stylesheet = File.read(@htmlstylesheet, encoding: "UTF-8") xml = Nokogiri::XML("<style/>") xml.children.first << Nokogiri::XML::Comment.new(xml, "\n#{stylesheet}\n") xml.root.to_s end |
#i18n_init(lang, script) ⇒ Object
5 6 7 8 9 10 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 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/isodoc/i18n.rb', line 5 def i18n_init(lang, script) @lang = lang @script = script y = if @i18nyaml YAML.load_file(@i18nyaml) elsif lang == "en" YAML.load_file(File.join(File.dirname(__FILE__), "i18n-en.yaml")) elsif lang == "fr" YAML.load_file(File.join(File.dirname(__FILE__), "i18n-fr.yaml")) elsif lang == "zh" && script == "Hans" YAML.load_file(File.join(File.dirname(__FILE__), "i18n-zh-Hans.yaml")) else YAML.load_file(File.join(File.dirname(__FILE__), "i18n-en.yaml")) end @term_def_boilerplate = y["term_def_boilerplate"] @scope_lbl = y["scope"] @symbols_lbl = y["symbols"] @introduction_lbl = y["introduction"] @foreword_lbl = y["foreword"] @termsdef_lbl = y["termsdef"] @termsdefsymbols_lbl = y["termsdefsymbols"] @normref_lbl = y["normref"] @bibliography_lbl = y["bibliography"] @clause_lbl = y["clause"] @annex_lbl = y["annex"] @no_terms_boilerplate = y["no_terms_boilerplate"] @internal_terms_boilerplate = y["internal_terms_boilerplate"] @norm_with_refs_pref = y["norm_with_refs_pref"] @norm_empty_pref = y["norm_empty_pref"] @external_terms_boilerplate = y["external_terms_boilerplate"] @internal_external_terms_boilerplate = y["internal_external_terms_boilerplate"] @note_lbl = y["note"] @note_xref_lbl = y["note_xref"] @termnote_lbl = y["termnote"] @figure_lbl = y["figure"] @list_lbl = y["list"] @formula_lbl = y["formula"] @table_lbl = y["table"] @key_lbl = y["key"] @example_lbl = y["example"] @example_xref_lbl = y["example_xref"] @where_lbl = y["where"] @wholeoftext_lbl = y["wholeoftext"] @draft_lbl = y["draft"] @inform_annex_lbl = y["inform_annex"] @norm_annex_lbl = y["norm_annex"] @modified_lbl = y["modified"] @deprecated_lbl = y["deprecated"] @source_lbl = y["source"] @and_lbl = y["and"] @all_parts_lbl = y["all_parts"] @locality = y["locality"] end |
#id(isoxml, _out) ⇒ Object
111 112 113 114 115 116 117 118 119 120 121 |
# File 'lib/isodoc/metadata.rb', line 111 def id(isoxml, _out) dn = docnumber(isoxml) documentstatus = isoxml.at(ns("//status/stage")) if documentstatus (:stage, documentstatus.text) abbr = stage_abbreviation(documentstatus.text) (:stageabbr, abbr) (documentstatus.text.to_i < 60) && dn = abbr + " " + dn end (:docnumber, dn) end |
#image_parse(url, out, caption) ⇒ Object
207 208 209 210 |
# File 'lib/isodoc/blocks.rb', line 207 def image_parse(url, out, ) out.img **attr_code(src: url) image_title_parse(out, ) end |
#image_title_parse(out, caption) ⇒ Object
199 200 201 202 203 204 205 |
# File 'lib/isodoc/blocks.rb', line 199 def image_title_parse(out, ) unless .nil? out.p **{ class: "FigureTitle", align: "center" } do |p| p.b { |b| b << .to_s } end end end |
#in_comment ⇒ Object
5 6 7 |
# File 'lib/isodoc/comments.rb', line 5 def in_comment @in_comment end |
#init_metadata ⇒ Object
5 6 7 8 9 10 11 12 13 14 |
# File 'lib/isodoc/metadata.rb', line 5 def @meta = { tc: "XXXX", sc: "XXXX", wg: "XXXX", editorialgroup: [], secretariat: "XXXX", obsoletes: nil, obsoletes_part: nil } %w{published accessed created activated obsoleted}.each do |w| @meta["#{w}date".to_sym] = "XXX" end end |
#initial_anchor_names(d) ⇒ Object
12 13 14 15 16 17 18 19 |
# File 'lib/isodoc/xref_sect_gen.rb', line 12 def initial_anchor_names(d) introduction_names(d.at(ns("//introduction"))) section_names(d.at(ns("//clause[title = 'Scope']")), "1", 1) section_names(d.at(ns( "//references[title = 'Normative References']")), "2", 1) section_names(d.at(ns("//sections/terms | //sections/clause[descendant::terms]")), "3", 1) middle_section_asset_names(d) end |
#inline_header_cleanup(docxml) ⇒ Object
65 66 67 68 69 70 71 72 73 74 75 76 |
# File 'lib/isodoc/cleanup.rb', line 65 def inline_header_cleanup(docxml) docxml.xpath('//span[@class="zzMoveToFollowing"]').each do |x| x.delete("class") n = x.next_element if n.nil? x.name = "p" else n.children.first.previous = x.remove end end docxml end |
#insert_comment_cont(from, to, target) ⇒ Object
102 103 104 105 106 107 108 109 110 111 112 |
# File 'lib/isodoc/comments.rb', line 102 def insert_comment_cont(from, to, target) # includes_to = from.at(".//*[@id='#{to}']") while !from.nil? && from["id"] != to following = from.xpath("./following::*") (from = following.shift) && incl_to = from.at(".//*[@id='#{to}']") while !incl_to.nil? && !from.nil? && skip_comment_wrap(from) (from = following.shift) && incl_to = from.at(".//*[@id='#{to}']") end wrap_comment_cont(from, target) if !from.nil? end end |
#insert_tab(out, n) ⇒ Object
10 11 12 |
# File 'lib/isodoc/utils.rb', line 10 def insert_tab(out, n) [1..n].each { out << " " } end |
#introduction_names(clause) ⇒ Object
36 37 38 39 40 41 |
# File 'lib/isodoc/xref_sect_gen.rb', line 36 def introduction_names(clause) return if clause.nil? clause.xpath(ns("./subsection")).each_with_index do |c, i| section_names1(c, "0.#{i + 1}", 2) end end |
#iso?(org) ⇒ Boolean
82 83 84 85 86 87 |
# File 'lib/isodoc/metadata.rb', line 82 def iso?(org) name = org&.at(ns("./name"))&.text abbrev = org&.at(ns("./abbreviation"))&.text (abbrev == "ISO" || name == "International Organization for Standardization" ) end |
#iso_bibitem_entry(list, b, ordinal, biblio) ⇒ Object
27 28 29 30 31 32 33 34 35 36 37 38 |
# File 'lib/isodoc/references.rb', line 27 def iso_bibitem_entry(list, b, ordinal, biblio) list.p **attr_code(iso_bibitem_entry_attrs(b, biblio)) do |ref| if biblio ref << "[#{ordinal}]" insert_tab(ref, 1) end ref << iso_bibitem_ref_code(b) date_note_process(b, ref) ref << ", " ref.i { |i| i << " #{b.at(ns('./title')).text}" } end end |
#iso_bibitem_entry_attrs(b, biblio) ⇒ Object
23 24 25 |
# File 'lib/isodoc/references.rb', line 23 def iso_bibitem_entry_attrs(b, biblio) { id: b["id"], class: biblio ? "Biblio" : nil } end |
#iso_bibitem_ref_code(b) ⇒ Object
7 8 9 10 11 12 13 |
# File 'lib/isodoc/references.rb', line 7 def iso_bibitem_ref_code(b) isocode = b.at(ns("./docidentifier")).text isodate = b.at(ns("./date[@type = 'published']")) reference = docid_l10n(isocode) reference += ": #{date_range(isodate)}" if isodate reference end |
#l10n(x, lang = @lang, script = @script) ⇒ Object
function localising spaces and punctuation. Not clear if period needs to be localised for zh
80 81 82 83 84 85 86 87 88 89 |
# File 'lib/isodoc/i18n.rb', line 80 def l10n(x, lang = @lang, script = @script) if lang == "zh" && script == "Hans" x.gsub(/ /, "").gsub(/:/, ":").gsub(/,/, "、"). gsub(/\(/, "(").gsub(/\)/, ")"). gsub(/\[/, "【").gsub(/\]/, "】"). gsub(/<b>/, "").gsub("</b>", "") else x end end |
#li_parse(node, out) ⇒ Object
45 46 47 48 49 |
# File 'lib/isodoc/lists.rb', line 45 def li_parse(node, out) out.li do |li| node.children.each { |n| parse(n, li) } end end |
#list_anchor_names(sections) ⇒ Object
74 75 76 77 78 79 80 81 82 83 84 85 |
# File 'lib/isodoc/xref_gen.rb', line 74 def list_anchor_names(sections) sections.each do |s| notes = s.xpath(ns(".//ol")) - s.xpath(ns(".//subsection//ol")) - s.xpath(ns(".//ol//ol")) notes.each_with_index do |n, i| idx = notes.size == 1 ? "" : " #{i + 1}" @anchors[n["id"]] = anchor_struct(idx, s, @list_lbl) list_item_anchor_names(n, @anchors[n["id"]], 1, "", notes.size != 1) end list_anchor_names(s.xpath(ns("./subsection"))) end end |
#list_item_anchor_names(list, list_anchor, depth, prev_label, refer_list) ⇒ Object
96 97 98 99 100 101 102 103 104 105 106 107 |
# File 'lib/isodoc/xref_gen.rb', line 96 def list_item_anchor_names(list, list_anchor, depth, prev_label, refer_list) list.xpath(ns("./li")).each_with_index do |li, i| label = listlabel(depth, i + 1) label = "#{prev_label}.#{label}" unless prev_label.empty? label = "#{list_anchor[:xref]} #{label}" if refer_list li["id"] && @anchors[li["id"]] = { xref: "#{label})", container: list_anchor[:container] } li.xpath(ns("./ol")).each do |ol| list_item_anchor_names(ol, list_anchor, depth + 1, label, false) end end end |
#listlabel(depth, i) ⇒ Object
87 88 89 90 91 92 93 94 |
# File 'lib/isodoc/xref_gen.rb', line 87 def listlabel(depth, i) return i.to_s if [2, 7].include? depth return (96 + i).chr.to_s if [1, 6].include? depth return (64 + i).chr.to_s if [4, 9].include? depth return RomanNumerals.to_roman(i).downcase if [3, 8].include? depth return RomanNumerals.to_roman(i).upcase if [5, 10].include? depth return i.to_s end |
#make_comment_link(out, fn, node) ⇒ Object
add in from and to links to move the comment into place
31 32 33 34 35 36 37 38 39 40 |
# File 'lib/isodoc/comments.rb', line 31 def make_comment_link(out, fn, node) out.span(**comment_link_attrs(fn, node)) do |s1| s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2| s2.a **{ style: "mso-comment-reference:SMC_#{fn};"\ "mso-comment-date:#{node['date']}" } s2.span **{ style: "mso-special-character:comment", target: fn } # do |s| end end end |
#make_comment_target(out) ⇒ Object
42 43 44 45 46 47 48 |
# File 'lib/isodoc/comments.rb', line 42 def make_comment_target(out) out.span **{ style: "MsoCommentReference" } do |s1| s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2| s2.span **{ style: "mso-special-character:comment" } end end end |
#make_comment_text(node, fn) ⇒ Object
50 51 52 53 54 55 56 57 58 |
# File 'lib/isodoc/comments.rb', line 50 def make_comment_text(node, fn) noko do |xml| xml.div **{ style: "mso-element:comment", id: fn } do |div| div.span **{ style: %{mso-comment-author:"#{node['reviewer']}"} } make_comment_target(div) node.children.each { |n| parse(n, div) } end end.join("\n") end |
#make_generic_footnote_text(node, fnid) ⇒ Object
35 36 37 38 39 40 41 |
# File 'lib/isodoc/footnotes.rb', line 35 def make_generic_footnote_text(node, fnid) noko do |xml| xml.aside **{ id: "ftn#{fnid}" } do |div| node.children.each { |n| parse(n, div) } end end.join("\n") end |
#make_table_attr(node) ⇒ Object
44 45 46 47 48 49 50 51 52 |
# File 'lib/isodoc/table.rb', line 44 def make_table_attr(node) { id: node["id"], class: "MsoISOTable", border: 1, cellspacing: 0, cellpadding: 0, } end |
#make_table_footnote_link(out, fnid, fnref) ⇒ Object
10 11 12 13 14 15 |
# File 'lib/isodoc/footnotes.rb', line 10 def make_table_footnote_link(out, fnid, fnref) attrs = { href: "##{fnid}", class: "TableFootnoteRef" } out.a **attrs do |a| a << fnref end end |
#make_table_footnote_target(out, fnid, fnref) ⇒ Object
17 18 19 20 21 22 23 |
# File 'lib/isodoc/footnotes.rb', line 17 def make_table_footnote_target(out, fnid, fnref) attrs = { id: fnid, class: "TableFootnoteRef" } out.a **attrs do |a| a << fnref insert_tab(a, 1) end end |
#make_table_footnote_text(node, fnid, fnref) ⇒ Object
25 26 27 28 29 30 31 32 33 |
# File 'lib/isodoc/footnotes.rb', line 25 def make_table_footnote_text(node, fnid, fnref) attrs = { id: "ftn#{fnid}" } noko do |xml| xml.div **attr_code(attrs) do |div| make_table_footnote_target(div, fnid, fnref) node.children.each { |n| parse(n, div) } end end.join("\n") end |
#make_tr_attr(td, row, totalrows) ⇒ Object
def make_tr_attr(td, row, totalrows, cols, totalcols, header) border-left:#? “#{SW 1.5pt;” : “none;”} border-right:#SW #== totalcols && !header ? “1.5” : “1.0”pt;
74 75 76 77 78 79 80 81 82 83 |
# File 'lib/isodoc/table.rb', line 74 def make_tr_attr(td, row, totalrows) style = td.name == "th" ? "font-weight:bold;" : "" rowmax = td["rowspan"] ? row + td["rowspan"].to_i - 1 : row style += <<~STYLE border-top:#{row.zero? ? "#{SW} 1.5pt;" : 'none;'} border-bottom:#{SW} #{rowmax == totalrows ? '1.5' : '1.0'}pt; STYLE { rowspan: td["rowspan"], colspan: td["colspan"], align: td["align"], style: style.gsub(/\n/, "") } end |
#mathjax(open, close) ⇒ Object
35 36 37 |
# File 'lib/isodoc/html.rb', line 35 def mathjax(open, close) MATHJAX.gsub("OPEN", open).gsub("CLOSE", close) end |
#merge_fnref_into_fn_text(a) ⇒ Object
85 86 87 88 89 |
# File 'lib/isodoc/cleanup.rb', line 85 def merge_fnref_into_fn_text(a) fn = a.at('.//a[@class="TableFootnoteRef"]') n = fn.next_element n&.children&.first&.add_previous_sibling(fn.remove) end |
#middle_anchor_names(docxml) ⇒ Object
109 110 111 112 113 114 115 116 117 118 119 |
# File 'lib/isodoc/xref_gen.rb', line 109 def middle_anchor_names(docxml) symbols_abbrevs = docxml.at(ns("//sections/symbols-abbrevs")) sect_num = 4 if symbols_abbrevs section_names(symbols_abbrevs, sect_num.to_s, 1) sect_num += 1 end clause_names(docxml, sect_num) termnote_anchor_names(docxml) termexample_anchor_names(docxml) end |
#middle_section_asset_names(d) ⇒ Object
21 22 23 24 25 26 27 |
# File 'lib/isodoc/xref_sect_gen.rb', line 21 def middle_section_asset_names(d) middle_sections = "//clause[title = 'Scope'] | "\ "//foreword | //introduction | "\ "//references[title = 'Normative References'] | //sections/terms | "\ "//sections/symbols-abbrevs | //clause[parent::sections]" sequential_asset_names(d.xpath(ns(middle_sections))) end |
#modification_parse(node, out) ⇒ Object
7 8 9 10 11 |
# File 'lib/isodoc/terms.rb', line 7 def modification_parse(node, out) out << "[MODIFICATION]" para = node.at(ns("./p")) para.children.each { |n| parse(n, out) } end |
#move_comment_link_to_from(docxml) ⇒ Object
114 115 116 117 118 119 120 |
# File 'lib/isodoc/comments.rb', line 114 def move_comment_link_to_from(docxml) docxml.xpath('//span[@style="MsoCommentReference"][@from]').each do |x| attrs = comment_attributes(docxml, x) || next move_comment_link_to_from1(x, attrs[:from]) insert_comment_cont(attrs[:from], x["to"], x["target"]) end end |
#move_comment_link_to_from1(x, fromlink) ⇒ Object
78 79 80 81 82 83 |
# File 'lib/isodoc/comments.rb', line 78 def move_comment_link_to_from1(x, fromlink) x.remove link = x.at(".//a") fromlink.replace(x) link.children = fromlink end |
#move_images(docxml) ⇒ Object
presupposes that the image source is local
114 115 116 117 118 119 120 121 122 123 124 125 |
# File 'lib/isodoc/html.rb', line 114 def move_images(docxml) system "rm -r _images; mkdir _images" docxml.xpath("//*[local-name() = 'img']").each do |i| matched = /\.(?<suffix>\S+)$/.match i["src"] uuid = UUIDTools::UUID.random_create.to_s new_full_filename = File.join("_images", "#{uuid}.#{matched[:suffix]}") system "cp #{i['src']} #{new_full_filename}" i["src"] = new_full_filename i["width"], i["height"] = Html2Doc.image_resize(i, 800, 1200) end docxml end |
#new_fullcolspan_row(t, tfoot) ⇒ Object
118 119 120 121 122 123 124 125 126 127 |
# File 'lib/isodoc/cleanup.rb', line 118 def new_fullcolspan_row(t, tfoot) # how many columns in the table? cols = 0 t.at(".//tr").xpath("./td | ./th").each do |td| cols += (td["colspan"] ? td["colspan"].to_i : 1) end style = %{border-top:0pt;border-bottom:#{SW} 1.5pt;} tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>") tfoot.xpath(".//td").last end |
#noko(&block) ⇒ Object
block for processing XML document fragments as XHTML, to allow for HTMLentities
40 41 42 43 44 45 46 47 |
# File 'lib/isodoc/utils.rb', line 40 def noko(&block) doc = ::Nokogiri::XML.parse(NOKOHEAD) fragment = doc.fragment("") ::Nokogiri::XML::Builder.with fragment, &block fragment.to_xml(encoding: "US-ASCII").lines.map do |l| l.gsub(/\s*\n/, "") end end |
#noniso_bibitem(list, b, ordinal, bibliography) ⇒ Object
TODO generate formatted ref if not present
57 58 59 60 61 62 63 64 65 66 67 |
# File 'lib/isodoc/references.rb', line 57 def noniso_bibitem(list, b, ordinal, bibliography) list.p **attr_code("id": b["id"], class: "Biblio") do |r| if bibliography id = docid_l10n(b.at(ns("./docidentifier")).text.gsub(/[\[\]]/, "")) ref_entry_code(r, ordinal, id) else r << "#{iso_bibitem_ref_code(b)}, " end reference_format(b, r) end end |
#norm_ref(isoxml, out) ⇒ Object
109 110 111 112 113 114 115 116 117 |
# File 'lib/isodoc/references.rb', line 109 def norm_ref(isoxml, out) q = "./*/references[title = 'Normative References']" f = isoxml.at(ns(q)) || return out.div do |div| clause_name("2.", @normref_lbl, div, nil) norm_ref_preface(f, div) biblio_list(f, div, false) end end |
#norm_ref_preface(f, div) ⇒ Object
98 99 100 101 102 103 104 105 106 107 |
# File 'lib/isodoc/references.rb', line 98 def norm_ref_preface(f, div) refs = f.elements.select do |e| ["reference", "bibitem"].include? e.name end pref = if refs.empty? then @norm_empty_pref else @norm_with_refs_pref end div.p pref end |
#note_anchor_names(sections) ⇒ Object
45 46 47 48 49 50 51 52 53 54 55 56 |
# File 'lib/isodoc/xref_gen.rb', line 45 def note_anchor_names(sections) sections.each do |s| notes = s.xpath(CHILD_NOTES_XPATH) notes.each_with_index do |n, i| next if @anchors[n["id"]] next if n["id"].nil? idx = notes.size == 1 ? "" : " #{i + 1}" @anchors[n["id"]] = anchor_struct(idx, s, @note_xref_lbl) end note_anchor_names(s.xpath(ns("./subsection"))) end end |
#note_label(node) ⇒ Object
5 6 7 8 9 |
# File 'lib/isodoc/blocks.rb', line 5 def note_label(node) n = get_anchors[node["id"]] return @note_lbl if n.nil? || n[:label].empty? l10n("#{@note_lbl} #{n[:label]}") end |
#note_p_parse(node, div) ⇒ Object
11 12 13 14 15 16 17 18 |
# File 'lib/isodoc/blocks.rb', line 11 def note_p_parse(node, div) div.p **{ class: "Note" } do |p| p << note_label(node) insert_tab(p, 1) node.first_element_child.children.each { |n| parse(n, p) } end node.element_children[1..-1].each { |n| parse(n, div) } end |
#note_parse(node, out) ⇒ Object
28 29 30 31 32 33 34 35 36 37 38 |
# File 'lib/isodoc/blocks.rb', line 28 def note_parse(node, out) @note = true out.div **{ id: node["id"], class: "Note" } do |div| if node.first_element_child.name == "p" note_p_parse(node, div) else note_parse1(node, div) end end @note = false end |
#note_parse1(node, div) ⇒ Object
20 21 22 23 24 25 26 |
# File 'lib/isodoc/blocks.rb', line 20 def note_parse1(node, div) div.p **{ class: "Note" } do |p| p << note_label(node) insert_tab(p, 1) end node.children.each { |n| parse(n, div) } end |
#ns(xpath) ⇒ Object
3 4 5 6 7 8 |
# File 'lib/isodoc/utils.rb', line 3 def ns(xpath) xpath.gsub(%r{/([a-zA-z])}, "/xmlns:\\1"). gsub(%r{::([a-zA-z])}, "::xmlns:\\1"). gsub(%r{\[([a-zA-z]+ ?=)}, "[xmlns:\\1"). gsub(%r{\[([a-zA-z]+\])}, "[xmlns:\\1") end |
#ol_depth(node) ⇒ Object
We don’t really want users to specify type of ordered list; we will use a fixed hierarchy as practiced by ISO (though not fully spelled out): a) 1) i) A) I)
27 28 29 30 31 32 33 34 35 |
# File 'lib/isodoc/lists.rb', line 27 def ol_depth(node) depth = node.ancestors("ul, ol").size + 1 type = :alphabet type = :arabic if [2, 7].include? depth type = :roman if [3, 8].include? depth type = :alphabet_upper if [4, 9].include? depth type = :roman_upper if [5, 10].include? depth ol_style(type) end |
#ol_parse(node, out) ⇒ Object
37 38 39 40 41 42 43 |
# File 'lib/isodoc/lists.rb', line 37 def ol_parse(node, out) # style = ol_style(node["type"]) style = ol_depth(node) out.ol **attr_code(type: style) do |ol| node.children.each { |n| parse(n, ol) } end end |
#ol_style(type) ⇒ Object
17 18 19 20 |
# File 'lib/isodoc/lists.rb', line 17 def ol_style(type) type = :alphabet unless type OL_STYLE[type.to_sym] end |
#para_attrs(node) ⇒ Object
156 157 158 159 160 161 162 163 164 165 166 167 |
# File 'lib/isodoc/blocks.rb', line 156 def para_attrs(node) classtype = nil classtype = "Note" if @note classtype = "MsoCommentText" if in_comment classtype = "Sourcecode" if @annotation attrs = { class: classtype, id: node["id"] } unless node["align"].nil? attrs[:align] = node["align"] unless node["align"] == "justify" attrs[:style] = "text-align:#{node['align']}" end attrs end |
#para_parse(node, out) ⇒ Object
169 170 171 172 173 174 175 176 177 |
# File 'lib/isodoc/blocks.rb', line 169 def para_parse(node, out) out.p **attr_code(para_attrs(node)) do |p| unless @termdomain.empty? p << "<#{@termdomain}> " @termdomain = "" end node.children.each { |n| parse(n, p) } end end |
#para_then_remainder(first, node, p, div) ⇒ Object
32 33 34 35 36 37 38 39 |
# File 'lib/isodoc/terms.rb', line 32 def para_then_remainder(first, node, p, div) if first.name == "p" first.children.each { |n| parse(n, p) } node.elements.drop(1).each { |n| parse(n, div) } else node.elements.each { |n| parse(n, div) } end end |
#part_label(lang) ⇒ Object
we don’t leave this to i18n.rb, because we have both English and French titles in the same document
143 144 145 146 147 148 |
# File 'lib/isodoc/metadata.rb', line 143 def part_label(lang) case lang when "en" then "Part" when "fr" then "Partie" end end |
#populate_template(docxml, _format) ⇒ Object
134 135 136 137 138 139 140 141 142 |
# File 'lib/isodoc/utils.rb', line 134 def populate_template(docxml, _format) = docxml = docxml. gsub(/\[TERMREF\]\s*/, l10n("[#{@source_lbl}: ")). gsub(/\s*\[\/TERMREF\]\s*/, l10n("]")). gsub(/\s*\[MODIFICATION\]/, l10n(", #{@modified_lbl} — ")) template = Liquid::Template.parse(docxml) template.render(.map { |k, v| [k.to_s, v] }.to_h) end |
#postprocess(result, filename, dir) ⇒ Object
3 4 5 6 |
# File 'lib/isodoc/html.rb', line 3 def postprocess(result, filename, dir) result = from_xhtml(cleanup(to_xhtml(result))) toHTML(result, filename) end |
#quote_attribution(node, out) ⇒ Object
179 180 181 182 183 184 185 186 |
# File 'lib/isodoc/blocks.rb', line 179 def quote_attribution(node, out) = node.at(ns("./author")) source = node.at(ns("./source")) out.p **{ class: "QuoteAttribution" } do |p| p << "— #{.text}, " if eref_parse(source, p) if source end end |
#quote_parse(node, out) ⇒ Object
188 189 190 191 192 193 194 195 196 197 |
# File 'lib/isodoc/blocks.rb', line 188 def quote_parse(node, out) attrs = para_attrs(node) attrs[:class] = "Quote" out.div **attr_code(attrs) do |p| node.children.each do |n| parse(n, p) unless ["author", "source"].include? n.name end quote_attribution(node, out) end end |
#ref_entry_code(r, ordinal, t) ⇒ Object
40 41 42 43 44 45 46 47 48 49 |
# File 'lib/isodoc/references.rb', line 40 def ref_entry_code(r, ordinal, t) if /^\d+$/.match?(t) r << "[#{t}]" insert_tab(r, 1) else r << "[#{ordinal}]" insert_tab(r, 1) r << "#{t}," end end |
#reference_format(b, r) ⇒ Object
51 52 53 54 |
# File 'lib/isodoc/references.rb', line 51 def reference_format(b, r) title = b.at(ns("./formattedref")) || b.at(ns("./title")) title&.children&.each { |n| parse(n, r) } end |
#reference_names(ref) ⇒ Object
154 155 156 157 158 159 160 161 162 |
# File 'lib/isodoc/references.rb', line 154 def reference_names(ref) isopub = ref.at(ns(ISO_PUBLISHER_XPATH)) docid = ref.at(ns("./docidentifier")) # return ref_names(ref) unless docid date = ref.at(ns("./date[@type = 'published']")) reference = format_ref(docid_l10n(docid.text), isopub, date) # reference += ": #{date_range(date)}" if date && isopub && from.text != "--" @anchors[ref["id"]] = { xref: reference } end |
#relations(isoxml, _out) ⇒ Object
183 184 185 186 187 188 189 |
# File 'lib/isodoc/metadata.rb', line 183 def relations(isoxml, _out) std = isoxml.at(ns("//bibdata/relation[@type = 'obsoletes']")) || return locality = std.at(ns(".//locality")) id = std.at(ns(".//docidentifier")) (:obsoletes, id.text) if id (:obsoletes_part, locality.text) if locality end |
#remove_bottom_border(td) ⇒ Object
102 103 104 105 |
# File 'lib/isodoc/cleanup.rb', line 102 def remove_bottom_border(td) td["style"] = td["style"].gsub(/border-bottom:[^;]+;/, "border-bottom:0pt;") end |
#reorder_comments_by_comment_link(docxml) ⇒ Object
135 136 137 138 139 140 141 142 143 |
# File 'lib/isodoc/comments.rb', line 135 def reorder_comments_by_comment_link(docxml) link_order = {} docxml.xpath(COMMENT_TARGET_XREFS).each_with_index do |target, i| link_order[target.value] = i end comments = get_comments_from_text(docxml, link_order) list = docxml.at("//*[@style='mso-element:comment-list']") || return list.children = comments.map { |c| c[:text] }.join("\n") end |
#review_note_parse(node, out) ⇒ Object
16 17 18 19 20 21 22 |
# File 'lib/isodoc/comments.rb', line 16 def review_note_parse(node, out) fn = @comments.length + 1 make_comment_link(out, fn, node) @in_comment = true @comments << make_comment_text(node, fn) @in_comment = false end |
#sc(xml) ⇒ Object
43 44 45 46 47 48 49 50 51 |
# File 'lib/isodoc/metadata.rb', line 43 def sc(xml) sc_num = xml.at(ns("//editorialgroup/subcommittee/@number")) sc_type = xml.at(ns("//editorialgroup/subcommittee/@type"))&.text || "SC" if sc_num scid = "#{sc_type} #{sc_num.text}" (:sc, scid) (:editorialgroup, [:editorialgroup] << scid) end end |
#secretariat(xml) ⇒ Object
63 64 65 66 |
# File 'lib/isodoc/metadata.rb', line 63 def secretariat(xml) sec = xml.at(ns("//editorialgroup/secretariat")) (:secretariat, sec.text) if sec end |
#section_names(clause, num, lvl) ⇒ Object
43 44 45 46 47 48 49 50 51 |
# File 'lib/isodoc/xref_sect_gen.rb', line 43 def section_names(clause, num, lvl) return if clause.nil? @anchors[clause["id"]] = { label: num, xref: l10n("#{@clause_lbl} #{num}"), level: lvl } clause.xpath(ns("./subsection | ./term | ./terms | ./symbols-abbrevs")). each_with_index do |c, i| section_names1(c, "#{num}.#{i + 1}", lvl + 1) end end |
#section_names1(clause, num, level) ⇒ Object
53 54 55 56 57 58 59 60 61 |
# File 'lib/isodoc/xref_sect_gen.rb', line 53 def section_names1(clause, num, level) @anchors[clause["id"]] = { label: num, level: level, xref: num } # subclauses are not prefixed with "Clause" clause.xpath(ns("./subsection | ./terms | ./term | ./symbols-abbrevs")). each_with_index do |c, i| section_names1(c, "#{num}.#{i + 1}", level + 1) end end |
#sentence_join(array) ⇒ Object
101 102 103 104 105 106 107 108 |
# File 'lib/isodoc/utils.rb', line 101 def sentence_join(array) return "" if array.nil? || array.empty? if array.length == 1 array[0] else l10n("#{array[0..-2].join(', ')} #{@and_lbl} #{array.last}") end end |
#sequential_asset_names(clause) ⇒ Object
156 157 158 159 160 161 162 163 164 |
# File 'lib/isodoc/xref_gen.rb', line 156 def sequential_asset_names(clause) clause.xpath(ns(".//table")).each_with_index do |t, i| @anchors[t["id"]] = anchor_struct(i + 1, nil, @table_lbl) end sequential_figure_names(clause) clause.xpath(ns(".//formula")).each_with_index do |t, i| @anchors[t["id"]] = anchor_struct(i + 1, t, @formula_lbl) end end |
#sequential_figure_names(clause) ⇒ Object
134 135 136 137 138 139 140 141 142 143 144 145 |
# File 'lib/isodoc/xref_gen.rb', line 134 def sequential_figure_names(clause) i = j = 0 clause.xpath(ns(".//figure")).each do |t| if t.parent.name == "figure" then j += 1 else j = 0 i += 1 end label = i.to_s + (j.zero? ? "" : "-#{j}") @anchors[t["id"]] = anchor_struct(label, nil, @figure_lbl) end end |
#set_metadata(key, value) ⇒ Object
20 21 22 |
# File 'lib/isodoc/metadata.rb', line 20 def (key, value) @meta[key] = value end |
#skip_comment_wrap(from) ⇒ Object
98 99 100 |
# File 'lib/isodoc/comments.rb', line 98 def skip_comment_wrap(from) from["style"] != "mso-special-character:comment" end |
#sourcecode_name_parse(_node, div, name) ⇒ Object
101 102 103 104 105 106 107 |
# File 'lib/isodoc/blocks.rb', line 101 def sourcecode_name_parse(_node, div, name) div.p **{ class: "FigureTitle", align: "center" } do |p| p.b do |b| b << name.text end end end |
#sourcecode_parse(node, out) ⇒ Object
109 110 111 112 113 114 115 116 117 118 119 |
# File 'lib/isodoc/blocks.rb', line 109 def sourcecode_parse(node, out) name = node.at(ns("./name")) out.p **attr_code(id: node["id"], class: "Sourcecode") do |div| @sourcecode = true node.children.each do |n| parse(n, div) unless n.name == "name" end @sourcecode = false sourcecode_name_parse(node, div, name) if name end end |
#split_bibitems(f) ⇒ Object
75 76 77 78 79 80 81 82 83 84 85 86 |
# File 'lib/isodoc/references.rb', line 75 def split_bibitems(f) iso_bibitem = [] non_iso_bibitem = [] f.xpath(ns("./bibitem")).each do |x| if x.at(ns(ISO_PUBLISHER_XPATH)).nil? non_iso_bibitem << x else iso_bibitem << x end end { iso: iso_bibitem, noniso: non_iso_bibitem } end |
#stage_abbreviation(stage) ⇒ Object
26 27 28 |
# File 'lib/isodoc/utils.rb', line 26 def stage_abbreviation(stage) STAGE_ABBRS[stage.to_sym] || "??" end |
#subtitle(isoxml, _out) ⇒ Object
173 174 175 176 177 178 179 180 181 |
# File 'lib/isodoc/metadata.rb', line 173 def subtitle(isoxml, _out) intro = isoxml.at(ns("//title-intro[@language='fr']")) main = isoxml.at(ns("//title-main[@language='fr']")) part = isoxml.at(ns("//title-part[@language='fr']")) partnumber = isoxml.at(ns("//project-number/@part")) subpartnumber = isoxml.at(ns("//project-number/@subpart")) main = compose_title(main, intro, part, partnumber, subpartnumber, "fr") (:docsubtitle, main) end |
#symbol_key(x) ⇒ Object
We assume AsciiMath is being used in the terms & definitions. Indices sort after letter but before any following letter (x, x_m, x_1, xa); we use colon to force that sort order. Numbers sort after letters; we use thorn to force that sort order.
152 153 154 155 |
# File 'lib/isodoc/cleanup.rb', line 152 def symbol_key(x) HTMLEntities.new.decode(x.text).gsub(/_/, ":").gsub(/`/, ""). gsub(/[0-9]+/, "þ\\1") end |
#symbols_cleanup(docxml) ⇒ Object
169 170 171 172 173 174 175 176 |
# File 'lib/isodoc/cleanup.rb', line 169 def symbols_cleanup(docxml) dl = docxml.at("//div[@class = 'Symbols']/dl") return docxml unless dl dl_out = extract_symbols_list(dl) dl_out.sort! { |a, b| a[:key] <=> b[:key] } dl.replace(dl_out.map { |d| d[:dt].to_s + d[:dd].to_s }.join("\n")) docxml end |
#table_cleanup(docxml) ⇒ Object
142 143 144 145 146 |
# File 'lib/isodoc/cleanup.rb', line 142 def table_cleanup(docxml) table_footnote_cleanup(docxml) table_note_cleanup(docxml) docxml end |
#table_footnote_cleanup(docxml) ⇒ Object
91 92 93 94 95 96 97 98 99 100 |
# File 'lib/isodoc/cleanup.rb', line 91 def table_footnote_cleanup(docxml) docxml.xpath("//table[descendant::aside]").each do |t| t.xpath(".//aside").each do |a| merge_fnref_into_fn_text(a) a.name = "div" a["class"] = "Note" t << a.remove end end end |
#table_footnote_parse(node, out) ⇒ Object
49 50 51 52 53 54 55 56 57 58 59 |
# File 'lib/isodoc/footnotes.rb', line 49 def table_footnote_parse(node, out) fn = node["reference"] tid = get_table_ancestor_id(node) make_table_footnote_link(out, tid + fn, fn) # do not output footnote text if we have already seen it for this table return if @seen_footnote.include?(tid + fn) @in_footnote = true out.aside { |a| a << make_table_footnote_text(node, tid + fn, fn) } @in_footnote = false @seen_footnote << (tid + fn) end |
#table_get_or_make_tfoot(t) ⇒ Object
107 108 109 110 111 112 113 114 115 116 |
# File 'lib/isodoc/cleanup.rb', line 107 def table_get_or_make_tfoot(t) tfoot = t.at(".//tfoot") if tfoot.nil? t.add_child("<tfoot></tfoot>") tfoot = t.at(".//tfoot") else tfoot.xpath(".//td | .//th").each { |td| remove_bottom_border(td) } end tfoot end |
#table_note_cleanup(docxml) ⇒ Object
129 130 131 132 133 134 135 136 137 138 139 140 |
# File 'lib/isodoc/cleanup.rb', line 129 def table_note_cleanup(docxml) docxml.xpath("//table[div[@class = 'Note']]").each do |t| tfoot = table_get_or_make_tfoot(t) insert_here = new_fullcolspan_row(t, tfoot) t.xpath("div[@class = 'Note']").each { |d| d.parent = insert_here } end # preempt html2doc putting MsoNormal there docxml.xpath("//p[not(self::*[@class])]"\ "[ancestor::*[@class = 'Note']]").each do |p| p["class"] = "Note" end end |
#table_parse(node, out) ⇒ Object
54 55 56 57 58 59 60 61 62 63 64 65 66 |
# File 'lib/isodoc/table.rb', line 54 def table_parse(node, out) @in_table = true table_title_parse(node, out) out.table **make_table_attr(node) do |t| thead_parse(node, t) tbody_parse(node, t) tfoot_parse(node, t) (dl = node.at(ns("./dl"))) && parse(dl, out) node.xpath(ns("./note")).each { |n| parse(n, out) } end @in_table = false # out.p { |p| p << " " } end |
#table_title_parse(node, out) ⇒ Object
3 4 5 6 7 8 9 10 11 |
# File 'lib/isodoc/table.rb', line 3 def table_title_parse(node, out) name = node.at(ns("./name")) out.p **{ class: "TableTitle", align: "center" } do |p| p.b do |b| b << l10n("#{@table_lbl} #{get_anchors[node['id']][:label]}") b << l10n(" — #{name.text}") if name end end end |
#tbody_parse(node, t) ⇒ Object
24 25 26 27 28 29 30 31 |
# File 'lib/isodoc/table.rb', line 24 def tbody_parse(node, t) tbody = node.at(ns("./tbody")) t.tbody do |h| tbody.element_children.each_with_index do |n, i| tr_parse(n, h, i, tbody.element_children.size, false) end end end |
#tc(xml) ⇒ Object
32 33 34 35 36 37 38 39 40 41 |
# File 'lib/isodoc/metadata.rb', line 32 def tc(xml) tc_num = xml.at(ns("//editorialgroup/technical-committee/@number")) tc_type = xml.at(ns("//editorialgroup/technical-committee/@type"))&. text || "TC" if tc_num tcid = "#{tc_type} #{tc_num.text}" (:tc, tcid) (:editorialgroup, [:editorialgroup] << tcid) end end |
#term_parse(node, out) ⇒ Object
26 27 28 29 30 |
# File 'lib/isodoc/terms.rb', line 26 def term_parse(node, out) out.p **{ class: "Terms" } do |p| node.children.each { |c| parse(c, p) } end end |
#termdef_parse(node, out) ⇒ Object
59 60 61 62 63 64 65 |
# File 'lib/isodoc/terms.rb', line 59 def termdef_parse(node, out) out.p **{ class: "TermNum", id: node["id"] } do |p| p << get_anchors[node["id"]][:label] end set_termdomain("") node.children.each { |n| parse(n, out) } end |
#termexample_anchor_names(docxml) ⇒ Object
26 27 28 29 30 31 32 33 34 35 |
# File 'lib/isodoc/xref_gen.rb', line 26 def termexample_anchor_names(docxml) docxml.xpath(ns("//term[termexample]")).each do |t| t.xpath(ns("./termexample")).each_with_index do |n, i| @anchors[n["id"]] = { label: (i + 1).to_s, xref: l10n("#{@anchors[t['id']][:xref]}, "\ "#{@note_xref_lbl} #{i + 1}") } end end end |
#termnote_anchor_names(docxml) ⇒ Object
15 16 17 18 19 20 21 22 23 24 |
# File 'lib/isodoc/xref_gen.rb', line 15 def termnote_anchor_names(docxml) docxml.xpath(ns("//term[termnote]")).each do |t| t.xpath(ns("./termnote")).each_with_index do |n, i| @anchors[n["id"]] = { label: termnote_label(i + 1), xref: l10n("#{@anchors[t['id']][:xref]}, "\ "#{@note_xref_lbl} #{i + 1}") } end end end |
#termnote_label(n) ⇒ Object
11 12 13 |
# File 'lib/isodoc/xref_gen.rb', line 11 def termnote_label(n) @termnote_lbl.gsub(/%/, n.to_s) end |
#termnote_parse(node, out) ⇒ Object
41 42 43 44 45 46 47 48 49 |
# File 'lib/isodoc/terms.rb', line 41 def termnote_parse(node, out) out.div **{ class: "Note" } do |div| first = node.first_element_child div.p **{ class: "Note" } do |p| p << "#{get_anchors[node['id']][:label]}: " para_then_remainder(first, node, p, div) end end end |
#termref_parse(node, out) ⇒ Object
51 52 53 54 55 56 57 |
# File 'lib/isodoc/terms.rb', line 51 def termref_parse(node, out) out.p do |p| p << "[TERMREF]" node.children.each { |n| parse(n, p) } p << "[/TERMREF]" end end |
#tfoot_parse(node, t) ⇒ Object
33 34 35 36 37 38 39 40 41 42 |
# File 'lib/isodoc/table.rb', line 33 def tfoot_parse(node, t) tfoot = node.at(ns("./tfoot")) if tfoot t.tfoot do |h| tfoot.element_children.each_with_index do |n, i| tr_parse(n, h, i, tfoot.element_children.size, false) end end end end |
#thead_parse(node, t) ⇒ Object
13 14 15 16 17 18 19 20 21 22 |
# File 'lib/isodoc/table.rb', line 13 def thead_parse(node, t) thead = node.at(ns("./thead")) if thead t.thead do |h| thead.element_children.each_with_index do |n, i| tr_parse(n, h, i, thead.element_children.size, true) end end end end |
#title(isoxml, _out) ⇒ Object
163 164 165 166 167 168 169 170 171 |
# File 'lib/isodoc/metadata.rb', line 163 def title(isoxml, _out) intro = isoxml.at(ns("//title-intro[@language='en']")) main = isoxml.at(ns("//title-main[@language='en']")) part = isoxml.at(ns("//title-part[@language='en']")) partnumber = isoxml.at(ns("//project-number/@part")) subpartnumber = isoxml.at(ns("//project-number/@subpart")) main = compose_title(main, intro, part, partnumber, subpartnumber, "en") (:doctitle, main) end |
#to_xhtml(xml) ⇒ Object
56 57 58 59 60 61 62 63 |
# File 'lib/isodoc/utils.rb', line 56 def to_xhtml(xml) xml.gsub!(/<\?xml[^>]*>/, "") unless /<!DOCTYPE /.match? xml xml = '<!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml end Nokogiri::XML.parse(xml) end |
#to_xhtml_fragment(xml) ⇒ Object
65 66 67 68 69 |
# File 'lib/isodoc/utils.rb', line 65 def to_xhtml_fragment(xml) doc = ::Nokogiri::XML.parse(NOKOHEAD) fragment = doc.fragment(xml) fragment end |
#toHTML(result, filename) ⇒ Object
8 9 10 11 12 13 14 |
# File 'lib/isodoc/html.rb', line 8 def toHTML(result, filename) result = from_xhtml(html_cleanup(to_xhtml(result))) result = populate_template(result, :html) File.open("#{filename}.html", "w") do |f| f.write(result) end end |
#tr_parse(node, out, ord, totalrows, _header) ⇒ Object
85 86 87 88 89 90 91 92 93 94 95 |
# File 'lib/isodoc/table.rb', line 85 def tr_parse(node, out, ord, totalrows, _header) out.tr do |r| node.elements.each do |td| attrs = make_tr_attr(td, ord, totalrows - 1) # i, node.elements.size - 1, header) r.send td.name, **attr_code(attrs) do |entry| td.children.each { |n| parse(n, entry) } end end end end |
#ul_parse(node, out) ⇒ Object
3 4 5 6 7 |
# File 'lib/isodoc/lists.rb', line 3 def ul_parse(node, out) out.ul do |ul| node.children.each { |n| parse(n, ul) } end end |
#update_footnote_filter(fn, x, i, seen) ⇒ Object
77 78 79 80 81 82 83 84 85 86 87 88 |
# File 'lib/isodoc/html.rb', line 77 def update_footnote_filter(fn, x, i, seen) if seen[fn.text] x.at("./sup").content = seen[fn.text][:num].to_s fn.remove unless x["href"] == seen[fn.text][:href] x["href"] = seen[fn.text][:href] else seen[fn.text] = { num: i, href: x["href"] } x.at("./sup").content = i.to_s i += 1 end [i, seen] end |
#version(isoxml, _out) ⇒ Object
133 134 135 136 137 138 139 |
# File 'lib/isodoc/metadata.rb', line 133 def version(isoxml, _out) (:docyear, isoxml&.at(ns("//copyright/from"))&.text) (:draft, isoxml&.at(ns("//version/draft"))&.text) (:revdate, isoxml&.at(ns("//version/revision-date"))&.text) (:draftinfo, draftinfo([:draft], [:revdate])) end |
#wg(xml) ⇒ Object
53 54 55 56 57 58 59 60 61 |
# File 'lib/isodoc/metadata.rb', line 53 def wg(xml) wg_num = xml.at(ns("//editorialgroup/workgroup/@number")) wg_type = xml.at(ns("//editorialgroup/workgroup/@type"))&.text || "WG" if wg_num wgid = "#{wg_type} #{wg_num.text}" (:wg, wgid) (:editorialgroup, [:editorialgroup] << wgid) end end |
#wrap_comment_cont(from, target) ⇒ Object
93 94 95 96 |
# File 'lib/isodoc/comments.rb', line 93 def wrap_comment_cont(from, target) s = from.replace("<span style='mso-comment-continuation:#{target}'>") s.first.children = from end |