isodoc 0.8.4 → 0.8.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7021ada69c40cacdfa9a54827a70bf9a949ea194a75c5a9bc9818cc76d458b95
-  data.tar.gz: 2f046c37b8094b3288f257f22e7efea00513bdafc09b6f9b2fa1ec4848a9bbe8
+  metadata.gz: dede2446b862431d30638a1f7f05f1048d70b153a343bd5e0ebc021a35f34f83
+  data.tar.gz: bef3d35e5e3e09a384768c961e4360dab94ec5760a090876ee8754b924c8a3a7
 SHA512:
-  metadata.gz: 0ae6effbeb78bce850bfe83a84bb311509e9f2f04ad7627e64f69c020974c6c6977768302b14ee13c5515f2da497dae17021aa9596e4525f58878e9b65b5d7a1
-  data.tar.gz: ccb84fc0e38711603a797dfa2560d3066291122c6a9fc6b1f71407999936a06e24611f075df121115025af70800a0cbd4008f346c22807564c587433f5edcc7b
+  metadata.gz: ed5cc8a8cd5fe504f7c6696e905e650840017b358d0d99d90546bed01397cfe7217d19c6a1e852368dc846044fc0a3467229abdd3285ffeedf966d624c162b44
+  data.tar.gz: 1523ac224ab7527eefe744e352aff22c746fbbc52689b451590a38b62c41c317afb6b4594c2f4ea7e8f9b4ea914144dedd4394cd68a50dbf16f6d607cd889e12

data/.travis.yml

@@ -6,7 +6,10 @@ rvm:
   - 2.4
   - ruby-head
 
-before_install: gem install bundler -v 1.16.2
+before_install: 
+  - gem install bundler -v 1.16.2
+  - npm install -g puppeteer
+  - npm install
 
 matrix:
   allow_failures:

data/Gemfile.lock

@@ -1,11 +1,12 @@
 PATH
   remote: .
   specs:
-    isodoc (0.8.3)
+    isodoc (0.8.5)
       asciimath
       html2doc (~> 0.8.1)
       htmlentities (~> 4.3.4)
       liquid
+      metanorma (~> 0.2.6)
       nokogiri
       roman-numerals
       ruby-xslt
@@ -16,7 +17,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    asciimath (1.0.4)
+    asciimath (1.0.5)
     ast (2.4.0)
     byebug (9.1.0)
     coderay (1.1.2)
@@ -59,6 +60,7 @@ GEM
       rb-inotify (~> 0.9, >= 0.9.7)
       ruby_dep (~> 1.2)
     lumberjack (1.0.13)
+    metanorma (0.2.6)
     method_source (0.9.0)
     mime-types (3.1)
       mime-types-data (~> 3.2015)
@@ -107,7 +109,7 @@ GEM
     ruby-progressbar (1.9.0)
     ruby-xslt (0.9.10)
     ruby_dep (1.5.0)
-    sass (3.5.6)
+    sass (3.5.7)
       sass-listen (~> 4.0.0)
     sass-listen (4.0.0)
       rb-fsevent (~> 0.9, >= 0.9.4)

data/isodoc.gemspec

@@ -38,6 +38,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "liquid"
   spec.add_dependency "roman-numerals"
   spec.add_dependency "sass"
+  spec.add_dependency "metanorma", "~> 0.2.6"
 
   spec.add_development_dependency "bundler", "~> 1.15"
   spec.add_development_dependency "byebug", "~> 9.1"

data/lib/isodoc.rb

@@ -20,8 +20,7 @@ require "isodoc/metadata"
 require "isodoc/html_convert"
 require "isodoc/word_convert"
 require "isodoc/pdf_convert"
-require "isodoc/iso/html_convert"
-require "isodoc/iso/word_convert"
+require "isodoc/headlesshtml_convert"
 
 module IsoDoc
 

data/lib/isodoc/convert.rb

@@ -62,7 +62,7 @@ module IsoDoc
       stylesheet.gsub!(/(\s|\{)mso-[^:]+:[^;]+;/m, "\\1") if stripwordcss
       engine = Sass::Engine.new(fontheader + stylesheet, syntax: :scss)
       outname = File.basename(filename, ".*") + ".css"
-      File.open(outname, "w") { |f| f.write(engine.render) }
+      File.open(outname, "w:UTF-8") { |f| f.write(engine.render) }
       @files_to_delete << outname
       outname
     end
@@ -86,8 +86,8 @@ module IsoDoc
       docxml = Nokogiri::XML(file)
       filename, dir = init_file(filename, debug)
       docxml.root.default_namespace = ""
-      lang = docxml&.at(ns("//bibdata/language"))&.text || "en"
-      script = docxml&.at(ns("//bibdata/script"))&.text || "Latn"
+      lang = docxml&.at(ns("//bibdata/language"))&.text || @lang
+      script = docxml&.at(ns("//bibdata/script"))&.text || @script
       i18n_init(lang, script)
       metadata_init(lang, script, @labels)
       [docxml, filename, dir]

data/lib/isodoc/function/i18n.rb

@@ -9,14 +9,17 @@ module IsoDoc::Function
       y = if @i18nyaml
             YAML.load_file(@i18nyaml)
           elsif lang == "en"
-            YAML.load_file(File.join(File.dirname(__FILE__), "../../isodoc-yaml/i18n-en.yaml"))
+            YAML.load_file(File.join(File.dirname(__FILE__),
+                                     "../../isodoc-yaml/i18n-en.yaml"))
           elsif lang == "fr"
-            YAML.load_file(File.join(File.dirname(__FILE__), "../../isodoc-yaml/i18n-fr.yaml"))
+            YAML.load_file(File.join(File.dirname(__FILE__),
+                                     "../../isodoc-yaml/i18n-fr.yaml"))
           elsif lang == "zh" && script == "Hans"
             YAML.load_file(File.join(File.dirname(__FILE__),
                                      "../../isodoc-yaml/i18n-zh-Hans.yaml"))
           else
-            YAML.load_file(File.join(File.dirname(__FILE__), "../../isodoc-yaml/i18n-en.yaml"))
+            YAML.load_file(File.join(File.dirname(__FILE__),
+                                     "../../isodoc-yaml/i18n-en.yaml"))
           end
       @term_def_boilerplate = y["term_def_boilerplate"]
       @scope_lbl = y["scope"]

data/lib/isodoc/function/inline.rb

@@ -9,11 +9,9 @@ module IsoDoc::Function
     end
 
     def link_parse(node, out)
-      linktext = node.text
-      linktext = node["target"] if linktext.empty?
       out.a(**{ "href": node["target"] }) do |l|
         if node.text.empty?
-          l << linktext 
+          l << node["target"].sub(/^mailto:/, "")
         else
           node.children.each { |n| parse(n, l) }
         end
@@ -25,7 +23,8 @@ module IsoDoc::Function
     end
 
     def anchor_linkend(node, linkend)
-      if node["citeas"].nil? && node["bibitemid"] && get_anchors.has_key?(node["bibitemid"])
+      if node["citeas"].nil? && node["bibitemid"] &&
+          get_anchors.has_key?(node["bibitemid"])
         return get_anchors[node["bibitemid"]][:xref]
       elsif node["target"] && get_anchors.has_key?(node["target"])
         linkend = get_anchors[node["target"]][:xref]

data/lib/isodoc/function/references.rb

@@ -1,6 +1,8 @@
 module IsoDoc::Function
   module References
 
+    # This is highly specific to ISO, but it's not a bad precedent for
+    # references anyway; keeping here instead of in IsoDoc::Iso for now
     def docid_l10n(x)
       return x if x.nil?
       x.gsub(/All Parts/, @all_parts_lbl)

data/lib/isodoc/function/section.rb

@@ -1,10 +1,13 @@
 module IsoDoc::Function
   module Section
-
     def inline_header_title(out, node, c1)
       out.span **{ class: "zzMoveToFollowing" } do |s|
         s.b do |b|
-          b << "#{get_anchors[node['id']][:label]}. #{c1.content} "
+          if get_anchors[node['id']][:label]
+            b << "#{get_anchors[node['id']][:label]}. #{c1.content} "
+          else
+            b << "#{c1.content} "
+          end
         end
       end
     end
@@ -14,7 +17,8 @@ module IsoDoc::Function
         inline_header_title(out, node, c1)
       else
         div.send "h#{get_anchors[node['id']][:level]}" do |h|
-          h << "#{get_anchors[node['id']][:label]}. "
+          lbl = get_anchors[node['id']][:label]
+          h << "#{lbl}. " if lbl
           c1.children.each { |c2| parse(c2, h) }
         end
       end
@@ -173,18 +177,12 @@ module IsoDoc::Function
 
     def introduction(isoxml, out)
       f = isoxml.at(ns("//introduction")) || return
-      num = f.at(ns(".//clause")) ? "0." : nil
       title_attr = { class: "IntroTitle" }
       page_break(out)
       out.div **{ class: "Section3", id: f["id"] } do |div|
-        # div.h1 "Introduction", **attr_code(title_attr)
-        clause_name(num, @introduction_lbl, div, title_attr)
+        clause_name(nil, @introduction_lbl, div, title_attr)
         f.elements.each do |e|
-          if e.name == "patent-notice"
-            e.elements.each { |e1| parse(e1, div) }
-          else
-            parse(e, div) unless e.name == "title"
-          end
+          parse(e, div) unless e.name == "title"
         end
       end
     end

data/lib/isodoc/function/to_word_html.rb

@@ -137,7 +137,7 @@ module IsoDoc::Function
         when "stem" then stem_parse(node, out)
         when "clause" then clause_parse(node, out)
           # when "subclause" then clause_parse(node, out)
-        when "appendix" then clause_parse(node, out)
+        #when "appendix" then clause_parse(node, out)
         when "xref" then xref_parse(node, out)
         when "eref" then eref_parse(node, out)
         when "origin" then eref_parse(node, out)

data/lib/isodoc/function/xref_sect_gen.rb

@@ -1,6 +1,5 @@
 module IsoDoc::Function
   module XrefSectGen
-
     def back_anchor_names(docxml)
       docxml.xpath(ns("//annex")).each_with_index do |c, i|
         annex_names(c, (65 + i).chr.to_s)
@@ -11,7 +10,8 @@ module IsoDoc::Function
     end
 
     def initial_anchor_names(d)
-      introduction_names(d.at(ns("//introduction")))
+      preface_names(d.at(ns("//foreword")))
+      preface_names(d.at(ns("//introduction")))
       n = 0
       n = section_names(d.at(ns("//clause[title = 'Scope']")), n, 1)
       n = section_names(d.at(ns(
@@ -25,6 +25,25 @@ module IsoDoc::Function
       termexample_anchor_names(d)
     end
 
+    # in StanDoc, prefaces have no numbering; they are referenced only by title
+    def preface_names(clause)
+      return if clause.nil?
+      clause.xpath(ns("./clause")).each_with_index do |c, i|
+        preface_names1(c, c.at(ns("./title"))&.text, "#{clause.at(ns('./title'))&.text}, #{i+1}", 2)
+      end
+    end
+
+    def preface_names1(clause, title, parent_title, level)
+      label = title || parent_title
+      @anchors[clause["id"]] =
+        { label: nil, level: level, xref: label }
+      # subclauses are not prefixed with "Clause"
+      clause.xpath(ns("./clause | ./terms | ./term | ./definitions")).
+        each_with_index do |c, i|
+        preface_names1(c, c.at(ns("./title"))&.text, "#{label} #{i+1}", level + 1)
+      end
+    end
+
     def middle_section_asset_names(d)
       middle_sections = "//clause[title = 'Scope'] | "\
         "//foreword | //introduction | "\
@@ -42,13 +61,6 @@ module IsoDoc::Function
       end
     end
 
-    def introduction_names(clause)
-      return if clause.nil?
-      clause.xpath(ns("./clause")).each_with_index do |c, i|
-        section_names1(c, "0.#{i + 1}", 2)
-      end
-    end
-
     def section_names(clause, num, lvl)
       return num if clause.nil?
       num = num + 1
@@ -83,7 +95,7 @@ module IsoDoc::Function
       clause.xpath(ns("./clause")).each_with_index do |c, i|
         annex_names1(c, "#{num}.#{i + 1}", 2)
       end
-      appendix_names(clause, num)
+      #appendix_names(clause, num)
       hierarchical_asset_names(clause, num)
     end
 
@@ -93,13 +105,5 @@ module IsoDoc::Function
         annex_names1(c, "#{num}.#{i + 1}", level + 1)
       end
     end
-
-    def appendix_names(clause, num)
-      clause.xpath(ns("./appendix")).each_with_index do |c, i|
-        @anchors[c["id"]] = anchor_struct(i + 1, nil, @appendix_lbl)
-        @anchors[c["id"]][:level] = 2
-        @anchors[c["id"]][:container] = clause["id"]
-      end
-    end
   end
 end

data/lib/isodoc/headlesshtml_convert.rb

@@ -0,0 +1,39 @@
+require_relative "html_function/comments.rb"
+require_relative "html_function/footnotes.rb"
+require_relative "html_function/html.rb"
+
+module IsoDoc
+  class HeadlessHtmlConvert < ::IsoDoc::Convert
+
+    include HtmlFunction::Comments
+    include HtmlFunction::Footnotes
+    include HtmlFunction::Html
+
+    def initialize(options)
+      super
+      @tmpimagedir = "_headlessimages"
+    end
+
+    def convert(filename, file = nil, debug = false)
+      file = File.read(filename, encoding: "utf-8") if file.nil?
+      @openmathdelim, @closemathdelim = extract_delims(file)
+      docxml, outname_html, dir = convert_init(file, filename, debug)
+      result = convert1(docxml, outname_html, dir)
+      return result if debug
+      postprocess(result, filename + ".tmp", dir)
+      system "rm -fr #{dir}"
+      strip_head(filename + ".tmp.html", outname_html + ".headless.html")
+      system "rm -r #{filename + '.tmp.html'} #{@tmpimagedir}"
+    end
+
+    def strip_head(input, output)
+      file = File.read(input, encoding: "utf-8")
+      doc = Nokogiri::XML(file)
+      doc.xpath("//head").each { |x| x.remove }
+      doc.xpath("//html").each { |x| x.name = "div" }
+      body = doc.at("//body")
+      body.replace(body.children)
+      File.open(output, "w") { |f| f.write(doc.to_xml) }
+    end
+  end
+end

data/lib/isodoc/html_function/html.rb

@@ -41,7 +41,7 @@ module IsoDoc::HtmlFunction
     def toHTML(result, filename)
       result = script_cdata(from_xhtml(html_cleanup(to_xhtml(result))))
       result = populate_template(result, :html)
-      File.open("#{filename}.html", "w") do |f|
+      File.open("#{filename}.html", "w:UTF-8") do |f|
         f.write(result)
       end
     end

data/lib/isodoc/metadata.rb

@@ -121,43 +121,22 @@ module IsoDoc
       dn
     end
 
-    STAGE_ABBRS = {
-      "00": "PWI",
-      "10": "NWIP",
-      "20": "WD",
-      "30": "CD",
-      "40": "DIS",
-      "50": "FDIS",
-      "60": "IS",
-      "90": "(Review)",
-      "95": "(Withdrawal)",
-    }.freeze
-
-    def stage_abbrev(stage, iter, draft)
-      stage = STAGE_ABBRS[stage.to_sym] || "??"
-      stage += iter.text if iter
-      stage = "Pre" + stage if draft&.text =~ /^0\./
-      stage
-    end
-
     def docstatus(isoxml, _out)
-      docstatus = isoxml.at(ns("//status/stage"))
+      docstatus = isoxml.at(ns("//bibdata/status"))
       if docstatus
-        set(:stage, docstatus.text)
-        set(:stage_int, docstatus.text.to_i)
-        abbr = stage_abbrev(docstatus.text, isoxml.at(ns("//status/iteration")),
-                            isoxml.at(ns("//version/draft")))
-        set(:stageabbr, abbr)
+        set(:status, status_print(docstatus.text))
       end
     end
 
+    def status_print(status)
+      status.split(/-/).map{ |w| w.capitalize }.join(" ")
+    end
+
     def docid(isoxml, _out)
       dn = docnumber(isoxml)
-      docstatus = get[:stage]
-      if docstatus
-        abbr = get[:stageabbr]
-        docstatus = get[:stage]
-        (docstatus.to_i < 60) && dn = abbr + " " + dn
+      docstatus = get[:status]
+      if docstatus && docstatus != "Published"
+        dn = "#{dn} #{docstatus}"
       end
       set(:docnumber, dn)
     end
@@ -180,59 +159,13 @@ module IsoDoc
           draftinfo(get[:draft], get[:revdate]))
     end
 
-    # we don't leave this to i18n.rb, because we have both English and
-    # French titles in the same document
-    def part_label(lang)
-      case lang
-      when "en" then "Part"
-      when "fr" then "Partie"
-      end
-    end
-
-    def part_title(part, partnum, subpartnum, lang)
-      return "" unless part
-      suffix = @c.encode(part.text, :hexadecimal)
-      partnum = "#{partnum}&ndash;#{subpartnum}" if partnum && subpartnum
-      suffix = "#{part_label(lang)}&nbsp;#{partnum}: " + suffix if partnum
-      suffix
-    end
-
-    def compose_title(main, intro, part, partnum, subpartnum, lang)
-      main = main.nil? ? "" : @c.encode(main.text, :hexadecimal)
-      intro &&
-        main = "#{@c.encode(intro.text, :hexadecimal)}&nbsp;&mdash; #{main}"
-      if part
-        suffix = part_title(part, partnum, subpartnum, lang)
-        main = "#{main}&nbsp;&mdash; #{suffix}"
-      end
-      main
-    end
-
     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"))
-
-      set(:doctitlemain, @c.encode(main ? main.text : "", :hexadecimal))
-      main = compose_title(main, intro, part, partnumber, subpartnumber, "en")
+      main = isoxml&.at(ns("//title[@language='en']"))&.text
       set(:doctitle, main)
-      set(:doctitleintro, @c.encode(intro ? intro.text : "", :hexadecimal)) if intro
-      set(:doctitlepart, part_title(part, partnumber, subpartnumber, "en"))
     end
 
     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"))
-      set(:docsubtitlemain, @c.encode(main ? main.text : "", :hexadecimal))
-      main = compose_title(main, intro, part, partnumber, subpartnumber, "fr")
-      set(:docsubtitle, main)
-      set(:docsubtitleintro, @c.encode(intro ? intro.text : "", :hexadecimal)) if intro
-      set(:docsubtitlepart, part_title(part, partnumber, subpartnumber, "fr"))
+      nil
     end
 
     def relations(isoxml, _out)