RubyGems - isodoc - Versions diffs - 1.6.1 → 1.6.6 - Mend

isodoc 1.6.1 → 1.6.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (69) hide show

checksums.yaml +4 -4
data/.github/workflows/rake.yml +2 -12
data/.hound.yml +3 -1
data/.rubocop.yml +4 -8
data/Rakefile +2 -2
data/isodoc.gemspec +4 -3
data/lib/isodoc-yaml/i18n-ar.yaml +152 -0
data/lib/isodoc-yaml/i18n-de.yaml +149 -0
data/lib/isodoc-yaml/i18n-en.yaml +1 -0
data/lib/isodoc-yaml/i18n-es.yaml +151 -0
data/lib/isodoc-yaml/i18n-fr.yaml +1 -0
data/lib/isodoc-yaml/i18n-ru.yaml +154 -0
data/lib/isodoc-yaml/i18n-zh-Hans.yaml +1 -0
data/lib/isodoc.rb +0 -2
data/lib/isodoc/common.rb +2 -0
data/lib/isodoc/convert.rb +8 -2
data/lib/isodoc/function/blocks.rb +15 -4
data/lib/isodoc/function/cleanup.rb +52 -43
data/lib/isodoc/function/form.rb +51 -0
data/lib/isodoc/function/inline.rb +8 -7
data/lib/isodoc/function/references.rb +71 -77
data/lib/isodoc/function/section.rb +28 -16
data/lib/isodoc/function/table.rb +22 -22
data/lib/isodoc/function/terms.rb +6 -7
data/lib/isodoc/function/to_word_html.rb +19 -25
data/lib/isodoc/function/utils.rb +181 -163
data/lib/isodoc/gem_tasks.rb +8 -9
data/lib/isodoc/headlesshtml_convert.rb +8 -7
data/lib/isodoc/html_convert.rb +6 -0
data/lib/isodoc/html_function/comments.rb +14 -12
data/lib/isodoc/html_function/footnotes.rb +14 -7
data/lib/isodoc/html_function/form.rb +62 -0
data/lib/isodoc/html_function/html.rb +30 -26
data/lib/isodoc/html_function/postprocess.rb +191 -182
data/lib/isodoc/html_function/sectionsplit.rb +230 -0
data/lib/isodoc/i18n.rb +13 -11
data/lib/isodoc/metadata.rb +22 -20
data/lib/isodoc/metadata_contributor.rb +31 -28
data/lib/isodoc/pdf_convert.rb +11 -13
data/lib/isodoc/presentation_function/bibdata.rb +54 -30
data/lib/isodoc/presentation_function/inline.rb +70 -120
data/lib/isodoc/presentation_function/math.rb +84 -0
data/lib/isodoc/presentation_function/section.rb +55 -19
data/lib/isodoc/presentation_xml_convert.rb +3 -0
data/lib/isodoc/sassc_importer.rb +1 -1
data/lib/isodoc/version.rb +1 -1
data/lib/isodoc/word_function/body.rb +28 -24
data/lib/isodoc/word_function/postprocess.rb +50 -36
data/lib/isodoc/xref.rb +2 -0
data/lib/isodoc/xref/xref_counter.rb +1 -2
data/lib/isodoc/xref/xref_gen.rb +21 -14
data/lib/isodoc/xref/xref_gen_seq.rb +60 -35
data/lib/isodoc/xref/xref_sect_gen.rb +15 -15
data/spec/assets/scripts_override.html +3 -0
data/spec/isodoc/blocks_spec.rb +624 -997
data/spec/isodoc/cleanup_spec.rb +40 -42
data/spec/isodoc/form_spec.rb +156 -0
data/spec/isodoc/i18n_spec.rb +694 -821
data/spec/isodoc/inline_spec.rb +1105 -921
data/spec/isodoc/metadata_spec.rb +384 -379
data/spec/isodoc/postproc_spec.rb +461 -333
data/spec/isodoc/presentation_xml_spec.rb +355 -278
data/spec/isodoc/ref_spec.rb +5 -5
data/spec/isodoc/section_spec.rb +216 -199
data/spec/isodoc/sectionsplit_spec.rb +190 -0
data/spec/isodoc/table_spec.rb +41 -42
data/spec/isodoc/terms_spec.rb +84 -84
data/spec/isodoc/xref_spec.rb +974 -932
metadata +32 -7

data/lib/isodoc/html_function/sectionsplit.rb ADDED Viewed

@@ -0,0 +1,230 @@
+require "metanorma"
+require "yaml"
+module IsoDoc::HtmlFunction
+  module Html
+    # assume we pass in Presentation XML, but we want to recover Semantic XML
+    def sectionsplit_convert(input_filename, file, debug, output_filename = nil)
+      input_filename += ".xml" unless input_filename.match?(/\.xml$/)
+      File.exist?(input_filename) or
+        File.open(input_filename, "w:UTF-8") { |f| f.write(file) }
+      presxml = File.read(input_filename, encoding: "utf-8")
+      @openmathdelim, @closemathdelim = extract_delims(presxml)
+      xml, filename, dir = convert_init(presxml, input_filename, debug)
+      build_collection(xml, presxml, output_filename || filename, dir)
+    end
+    def build_collection(xml, presxml, filename, dir)
+      base = File.basename(filename)
+      collection_setup(base, dir)
+      files = sectionsplit(xml, base, dir)
+      collection_manifest(base, files, xml, presxml, dir).render(
+        format: %i(html), output_folder: "#{filename}_collection",
+        coverpage: File.join(dir, "cover.html")
+      )
+    end
+    def collection_manifest(filename, files, origxml, _presxml, dir)
+      File.open(File.join(dir, "#{filename}.html.yaml"), "w:UTF-8") do |f|
+        f.write(collectionyaml(files, origxml))
+      end
+      Metanorma::Collection.parse File.join(dir, "#{filename}.html.yaml")
+    end
+    def collection_setup(filename, dir)
+      FileUtils.mkdir_p "#{filename}_collection"
+      FileUtils.mkdir_p dir
+      File.open(File.join(dir, "cover.html"), "w:UTF-8") do |f|
+        f.write(coll_cover)
+      end
+    end
+    def coll_cover
+      <<~COVER
+        <html>
+          <head/>
+            <body>
+              <h1>{{ doctitle }}</h1>
+              <h2>{{ docnumber }}</h2>
+              <nav>{{ labels["navigation"] }}</nav>
+            </body>
+        </html>
+      COVER
+    end
+    def sectionsplit(xml, filename, dir)
+      xref_preprocess(xml)
+      out = emptydoc(xml)
+      [["//preface/*", "preface"], ["//sections/*", "sections"],
+       ["//annex", nil],
+       ["//bibliography/*[not(@hidden = 'true')]", "bibliography"],
+       ["//indexsect", nil]].each_with_object([]) do |n, ret|
+         xml.xpath(ns(n[0])).each do |s|
+           ret << sectionfile(out, dir, "#{filename}.#{ret.size}", s, n[1])
+         end
+       end
+    end
+    def emptydoc(xml)
+      out = xml.dup
+      out.xpath(
+        ns("//preface | //sections | //annex | //bibliography/clause | "\
+           "//bibliography/references[not(@hidden = 'true')] | //indexsect"),
+      ).each(&:remove)
+      out
+    end
+    def sectionfile(xml, dir, file, chunk, parentnode)
+      fname = create_sectionfile(xml.dup, dir, file, chunk, parentnode)
+      { order: chunk["displayorder"].to_i, url: fname,
+        title: titlerender(chunk) }
+    end
+    def create_sectionfile(out, dir, file, chunk, parentnode)
+      ins = out.at(ns("//misccontainer")) || out.at(ns("//bibdata"))
+      if parentnode
+        ins.next = "<#{parentnode}/>"
+        ins.next.add_child(chunk.dup)
+      else
+        ins.next = chunk.dup
+      end
+      outname = "#{file}.xml"
+      File.open(File.join(dir, outname), "w:UTF-8") { |f| f.write(out) }
+      outname
+    end
+    def xref_preprocess(xml)
+      svg_preprocess(xml)
+      key = (0...8).map { rand(65..90).chr }.join # random string
+      refs = eref_to_internal_eref(xml, key)
+      refs += xref_to_internal_eref(xml, key)
+      xml.root["type"] = key # to force recognition of internal refs
+      insert_indirect_biblio(xml, refs, key)
+    end
+    def svg_preprocess(xml)
+      xml.xpath("//m:svg", "m" => "http://www.w3.org/2000/svg").each do |s|
+        m = svgmap_wrap(s)
+        s.xpath(".//m:a", "m" => "http://www.w3.org/2000/svg").each do |a|
+          next unless /^#/.match? a["href"]
+          a["href"] = a["href"].sub(/^#/, "")
+          m << "<target href='#{a['href']}'>"\
+            "<xref target='#{a['href']}'/></target>"
+        end
+      end
+    end
+    def svgmap_wrap(svg)
+      ret = svg.at("./ancestor::xmlns:svgmap") and return ret
+      ret = svg.at("./ancestor::xmlns:figure")
+      ret.wrap("<svgmap/>")
+      svg.at("./ancestor::xmlns:svgmap")
+    end
+    def make_anchor(anchor)
+      "<localityStack><locality type='anchor'><referenceFrom>"\
+        "#{anchor}</referenceFrom></locality></localityStack>"
+    end
+    def xref_to_internal_eref(xml, key)
+      xml.xpath(ns("//xref")).each_with_object({}) do |x, m|
+        x["bibitemid"] = "#{key}_#{x['target']}"
+        x << make_anchor(x["target"])
+        m[x["bibitemid"]] = true
+        x.delete("target")
+        x["type"] = key
+        x.name = "eref"
+      end.keys
+    end
+    def eref_to_internal_eref(xml, key)
+      eref_to_internal_eref_select(xml).each_with_object([]) do |x, m|
+        url = xml.at(ns("//bibitem[@id = '#{x}']/url[@type = 'citation']"))
+        xml.xpath(("//*[@bibitemid = '#{x}']")).each do |e|
+          id = eref_to_internal_eref1(e, key, url)
+          id and m << id
+        end
+      end
+    end
+    def eref_to_internal_eref1(elem, key, url)
+      if url
+        elem.name = "link"
+        elem["target"] = url
+        nil
+      else
+        elem["bibitemid"] = "#{key}_#{elem['bibitemid']}"
+        elem << make_anchor(elem["bibitemid"])
+        elem["type"] = key
+        elem["bibitemid"]
+      end
+    end
+    def eref_to_internal_eref_select(xml)
+      refs = xml.xpath(("//*/@bibitemid")).map { |x| x.text } # rubocop:disable Style/SymbolProc
+      refs.uniq.reject do |x|
+        xml.at(ns("//bibitem[@id = '#{x}'][@type = 'internal']"))
+      end
+    end
+    # from standoc
+    def insert_indirect_biblio(xmldoc, refs, prefix)
+      ins = xmldoc.at("bibliography") or
+        xmldoc.root << "<bibliography/>" and ins = xmldoc.at("bibliography")
+      ins = ins.add_child("<references hidden='true' normative='false'/>").first
+      refs.each do |x|
+        ins << <<~BIBENTRY
+          <bibitem id="#{x}" type="internal">
+          <docidentifier type="repository">#{x.sub(/^#{prefix}_/, "#{prefix}/")}</docidentifier>
+          </bibitem>
+        BIBENTRY
+      end
+    end
+    def recursive_string_keys(hash)
+      case hash
+      when Hash then Hash[
+        hash.map { |k, v| [k.to_s, recursive_string_keys(v)] }
+      ]
+      when Enumerable then hash.map { |v| recursive_string_keys(v) }
+      else
+        hash
+      end
+    end
+    def titlerender(section)
+      title = section.at(ns("./title")) or return "[Untitled]"
+      t = title.dup
+      t.xpath(ns(".//tab | .//br")).each { |x| x.replace(" ") }
+      t.xpath(ns(".//strong")).each { |x| x.replace(x.children) }
+      t.children.to_xml
+    end
+    def collectionyaml(files, xml)
+      ret = {
+        directives: ["presentation-xml", "bare-after-first"],
+        bibdata: {
+          title: {
+            type: "title-main",
+            language: @lang,
+            content: xml.at(ns("//bibdata/title")).text,
+          },
+          type: "collection",
+          docid: {
+            type: xml.at(ns("//bibdata/docidentifier/@type")).text,
+            id: xml.at(ns("//bibdata/docidentifier")).text,
+          },
+        },
+        manifest: {
+          level: "collection",
+          title: "Collection",
+          docref: files.sort_by { |f| f[:order] }.each.map do |f|
+            { fileref: f[:url], identifier: f[:title] }
+          end,
+        },
+      }
+      recursive_string_keys(ret).to_yaml
+    end
+  end
+end

data/lib/isodoc/i18n.rb CHANGED Viewed

@@ -23,21 +23,23 @@ module IsoDoc
     end
     def load_yaml1(lang, script)
-      if lang == "en"
-        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"))
-      elsif lang == "zh" && script == "Hans"
-        YAML.load_file(File.join(File.dirname(__FILE__),
-                                 "../isodoc-yaml/i18n-zh-Hans.yaml"))
+      case lang
+      when "en", "fr", "ru", "de", "es", "ar"
+        load_yaml2(lang)
+      when "zh"
+        if script == "Hans" then load_yaml2("zh-Hans")
+        else load_yaml2("en")
+        end
       else
-        YAML.load_file(File.join(File.dirname(__FILE__),
-                                 "../isodoc-yaml/i18n-en.yaml"))
+        load_yaml2("en")
       end
     end
+    def load_yaml2(str)
+      YAML.load_file(File.join(File.dirname(__FILE__),
+                               "../isodoc-yaml/i18n-#{str}.yaml"))
+    end
     def get
       @labels
     end

data/lib/isodoc/metadata.rb CHANGED Viewed

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
-require_relative './metadata_date'
-require_relative './metadata_contributor'
+require_relative "./metadata_date"
+require_relative "./metadata_contributor"
 module IsoDoc
   class Metadata
@@ -17,7 +17,7 @@ module IsoDoc
     def initialize(lang, script, i18n, fonts_options = {})
       @metadata = { lang: lang, script: script }
-      DATETYPES.each { |w| @metadata["#{w.gsub(/-/, '_')}date".to_sym] = 'XXX' }
+      DATETYPES.each { |w| @metadata["#{w.gsub(/-/, '_')}date".to_sym] = "XXX" }
       @lang = lang
       @script = script
       @c = HTMLEntities.new
@@ -38,7 +38,7 @@ module IsoDoc
       @metadata[key] = value
     end
-    NOLANG = "[not(@language) or @language = '']".freeze
+    NOLANG = "[not(@language) or @language = '']"
     def currlang
       "[@language = '#{@lang}']"
@@ -54,6 +54,7 @@ module IsoDoc
     def docstatus(xml, _out)
       set(:unpublished, true)
       return unless s = xml.at(ns("//bibdata/status/stage#{NOLANG}"))
       s1 = xml.at(ns("//bibdata/status/stage#{currlang}")) || s
       set(:stage, status_print(s.text))
       s1 and set(:stage_display, status_print(s1.text))
@@ -61,26 +62,26 @@ module IsoDoc
         set(:substage, i)
       (i1 = xml&.at(ns("//bibdata/status/substage#{currlang}"))&.text || i) and
         set(:substage_display, i1)
-      (i2 = xml&.at(ns('//bibdata/status/iteration'))&.text) and
+      (i2 = xml&.at(ns("//bibdata/status/iteration"))&.text) and
         set(:iteration, i2)
       set(:unpublished, unpublished(s.text))
       unpublished(s.text) && set(:stageabbr, stage_abbr(s.text))
     end
     def stage_abbr(docstatus)
-      status_print(docstatus).split(/ /).map { |s| s[0].upcase }.join('')
+      status_print(docstatus).split(/ /).map { |s| s[0].upcase }.join("")
     end
     def unpublished(status)
-      !status.casecmp('published').zero?
+      !status.casecmp("published").zero?
     end
     def status_print(status)
-      status.split(/[- ]/).map(&:capitalize).join(' ')
+      status.split(/[- ]/).map(&:capitalize).join(" ")
     end
     def docid(isoxml, _out)
-      dn = isoxml.at(ns('//bibdata/docidentifier'))
+      dn = isoxml.at(ns("//bibdata/docidentifier"))
       set(:docnumber, dn&.text)
     end
@@ -92,23 +93,24 @@ module IsoDoc
     end
     def docnumeric(isoxml, _out)
-      dn = isoxml.at(ns('//bibdata/docnumber'))
+      dn = isoxml.at(ns("//bibdata/docnumber"))
       set(:docnumeric, dn&.text)
     end
     def draftinfo(draft, revdate)
       return "" unless draft
       draftinfo = " (#{@labels['draft_label']} #{draft}"
       draftinfo += ", #{revdate}" if revdate
-      draftinfo += ')'
+      draftinfo += ")"
       l10n(draftinfo, @lang, @script)
     end
     def version(isoxml, _out)
-      set(:edition, isoxml&.at(ns('//bibdata/edition'))&.text)
-      set(:docyear, isoxml&.at(ns('//bibdata/copyright/from'))&.text)
-      set(:draft, isoxml&.at(ns('//version/draft'))&.text)
-      revdate = isoxml&.at(ns('//version/revision-date'))&.text
+      set(:edition, isoxml&.at(ns("//bibdata/edition"))&.text)
+      set(:docyear, isoxml&.at(ns("//bibdata/copyright/from"))&.text)
+      set(:draft, isoxml&.at(ns("//bibdata/version/draft"))&.text)
+      revdate = isoxml&.at(ns("//bibdata/version/revision-date"))&.text
       set(:revdate, revdate)
       set(:revdate_monthyear, monthyr(revdate))
       set(:draftinfo,
@@ -131,20 +133,20 @@ module IsoDoc
     def relations_partof(isoxml)
       std = isoxml.at(ns("//bibdata/relation[@type = 'partOf']")) || return
-      id = std.at(ns('.//docidentifier'))
+      id = std.at(ns(".//docidentifier"))
       set(:partof, id.text) if id
     end
     def relations_obsoletes(isoxml)
       std = isoxml.at(ns("//bibdata/relation[@type = 'obsoletes']")) || return
-      locality = std.at(ns('.//locality'))
-      id = std.at(ns('.//docidentifier'))
+      locality = std.at(ns(".//locality"))
+      id = std.at(ns(".//docidentifier"))
       set(:obsoletes, id.text) if id
       set(:obsoletes_part, locality.text) if locality
     end
     def url(xml, _out)
-      (a = xml.at(ns('//bibdata/uri[not(@type)]'))) && set(:url, a.text)
+      (a = xml.at(ns("//bibdata/uri[not(@type)]"))) && set(:url, a.text)
       (a = xml.at(ns("//bibdata/uri[@type = 'html']"))) && set(:html, a.text)
       (a = xml.at(ns("//bibdata/uri[@type = 'xml']"))) && set(:xml, a.text)
       (a = xml.at(ns("//bibdata/uri[@type = 'pdf']"))) && set(:pdf, a.text)
@@ -153,7 +155,7 @@ module IsoDoc
     def keywords(isoxml, _out)
       ret = []
-      isoxml.xpath(ns('//bibdata/keyword')).each { |kw| ret << kw.text }
+      isoxml.xpath(ns("//bibdata/keyword")).each { |kw| ret << kw.text }
       set(:keywords, ret)
     end

data/lib/isodoc/metadata_contributor.rb CHANGED Viewed

@@ -2,26 +2,29 @@ module IsoDoc
   class Metadata
     def extract_person_names(authors)
       authors.reduce([]) do |ret, a|
-        if a.at(ns('./name/completename'))
-          ret << a.at(ns('./name/completename')).text
+        if a.at(ns("./name/completename"))
+          ret << a.at(ns("./name/completename")).text
         else
-          fn = []
-          forenames = a.xpath(ns('./name/forename'))
-          forenames.each { |f| fn << f.text }
-          surname = a&.at(ns('./name/surname'))&.text
-          ret << fn.join(' ') + ' ' + surname
+          forenames = a.xpath(ns("./name/forename"))
+          fn = forenames.each_with_object([]) { |f, m| m << f.text }
+          surname = a&.at(ns("./name/surname"))&.text
+          ret << "#{fn.join(' ')} #{surname}"
         end
       end
     end
     def extract_person_affiliations(authors)
       authors.reduce([]) do |m, a|
-        name = a&.at(ns('./affiliation/organization/name'))&.text
-        subdivs = a&.xpath(ns('./affiliation/organization/subdivision'))&.map(&:text)&.join(", ")
-        name and subdivs and !subdivs.empty? and name = l10n("#{name}, #{subdivs}", @lang, @script)
-        location = a&.at(ns('./affiliation/organization/address/formattedAddress'))&.text
-        m << (!name.nil? && !location.nil? ? l10n("#{name}, #{location}", @lang, @script) :
-          (name || location || ''))
+        name = a&.at(ns("./affiliation/organization/name"))&.text
+        subdivs = a&.xpath(ns("./affiliation/organization/subdivision"))&.map(&:text)&.join(", ")
+        name and subdivs and !subdivs.empty? and
+          name = l10n("#{name}, #{subdivs}", @lang, @script)
+        location = a&.at(ns("./affiliation/organization/address/formattedAddress"))&.text
+        m << (if !name.nil? && !location.nil?
+                l10n("#{name}, #{location}", @lang, @script)
+              else
+                (name || location || "")
+              end)
         m
       end
     end
@@ -50,19 +53,19 @@ module IsoDoc
     end
     def iso?(org)
-      name = org&.at(ns('./name'))&.text
-      abbrev = org&.at(ns('./abbreviation'))&.text
-      (abbrev == 'ISO' ||
-       name == 'International Organization for Standardization')
+      name = org&.at(ns("./name"))&.text
+      abbrev = org&.at(ns("./abbreviation"))&.text
+      (abbrev == "ISO" ||
+       name == "International Organization for Standardization")
     end
     def agency1(xml)
-      agency = ''
+      agency = ""
       publisher = []
       xml.xpath(ns("//bibdata/contributor[xmlns:role/@type = 'publisher']/"\
-                   'organization')).each do |org|
-        name = org&.at(ns('./name'))&.text
-        agency1 = org&.at(ns('./abbreviation'))&.text || name
+                   "organization")).each do |org|
+        name = org&.at(ns("./name"))&.text
+        agency1 = org&.at(ns("./abbreviation"))&.text || name
         publisher << name if name
         agency = iso?(org) ? "ISO/#{agency}" : "#{agency}#{agency1}/"
       end
@@ -71,21 +74,21 @@ module IsoDoc
     def agency(xml)
       agency, publisher = agency1(xml)
-      set(:agency, agency.sub(%r{/$}, ''))
-      set(:publisher, @i18n.multiple_and(publisher, @labels['and']))
+      set(:agency, agency.sub(%r{/$}, ""))
+      set(:publisher, @i18n.multiple_and(publisher, @labels["and"]))
       agency_addr(xml)
     end
     def agency_addr(xml)
       a = xml.at(ns("//bibdata/contributor[xmlns:role/@type = 'publisher'][1]/"\
                     "organization")) or return
-      n = a.at(ns("./subdivision")) and set(:subdivision, n.text)
+      { subdivision: "./subdivision", pub_phone: "./phone[not(@type = 'fax')]",
+        pub_fax: "./phone[@type = 'fax']", pub_email: "./email",
+        pub_uri: "./uri" }.each do |k, v|
+          n = a.at(ns(v)) and set(k, n.text)
+        end
       n = a.at(ns("./address/formattedAddress")) and
         set(:pub_address, n.children.to_xml)
-      n = a.at(ns("./phone[not(@type = 'fax')]")) and set(:pub_phone, n.text)
-      n = a.at(ns("./phone[@type = 'fax']")) and set(:pub_fax, n.text)
-      n = a.at(ns("./email")) and set(:pub_email, n.text)
-      n = a.at(ns("./uri")) and set(:pub_uri, n.text)
     end
   end
 end