Module: Asciidoctor::Rfc::Common::Base

Included in:
V2::Converter, V3::Converter
Defined in:
lib/asciidoctor/rfc/common/base.rb

Constant Summary collapse

IETF_AREAS = 
["art", "Applications and Real-Time",
"gen", "General",
"int", "Internet",
"ops", "Operations and Management",
"rtg", "Routing",
"sec", "Security",
"tsv", "Transport"].freeze

Instance Method Summary collapse

Instance Method Details

#area(node, xml) ⇒ Object

Syntax:

= Title
Author
:area x, y



79
80
81
82
83
84
85
86
87
88
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 79

def area(node, xml)
  node.attr("area")&.split(/, ?/)&.each do |ar|
    if ar =~ / Area$/i
      warn %(asciidoctor: WARNING (#{current_location(node)}): stripping suffix "Area" from area #{ar})
      ar = ar.gsub(/ Area$/i, "")
    end
    warn %(asciidoctor: WARNING (#{current_location(node)}): unrecognised area #{ar}) unless IETF_AREAS.include?(ar)
    xml.area { |a| a << ar }
  end
end

#attr_code(attributes) ⇒ Object 



359
360
361
362
363
364
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 359

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

#cache_biblio(node) ⇒ Object 



420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 420

def cache_biblio(node)
  bibliocache_name = "#{Dir.home}/.asciidoc-rfc-biblio-cache.json"
  # If we are required to, clear the biblio cache
  if node.attr("flush-caches") == "true"
    system("rm -f #{bibliocache_name}")
  end
  # Is there already a biblio cache? If not, create it.
  biblio = {}
  if Pathname.new(bibliocache_name).file?
    File.open(bibliocache_name, "r") do |f|
      biblio = JSON.parse(f.read)
    end
  else
    File.open(bibliocache_name, "w") do |b|
      STDERR.puts "Reading references from https://xml2rfc.tools.ietf.org/public/rfc/bibxml/..."
      Kernel.open("https://xml2rfc.tools.ietf.org/public/rfc/bibxml/") do |f|
        # I'm just working off the ls output
        f.each_line do |line|
          line.scan(/a href="reference.RFC.(\d+).xml">/) do |w|
            biblio["RFC#{w[0]}"] = "https://xml2rfc.tools.ietf.org/public/rfc/bibxml/reference.RFC.#{w[0]}.xml"
          end
        end
        ["https://xml2rfc.tools.ietf.org/public/rfc/bibxml2/",
         "https://xml2rfc.tools.ietf.org/public/rfc/bibxml3/",
         "https://xml2rfc.tools.ietf.org/public/rfc/bibxml4/",
         "https://xml2rfc.tools.ietf.org/public/rfc/bibxml5/"].each do |url|
           STDERR.puts "Reading references from #{url}..."
           Kernel.open(url) do |f1|
             f1.each_line do |line|
               line.scan(/a href="reference.(\S+).xml">/) do |w|
                 biblio[w[0]] = "#{url}/reference.#{w[0]}.xml"
               end
             end
           end
         end
      end
      b << biblio.to_json
    end
  end
  biblio
end

#cache_workgroup(node) ⇒ Object 



376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 376

def cache_workgroup(node)
  wgcache_name = "#{Dir.home}/.asciidoc-rfc-workgroup-cache.json"
  # If we are required to, clear the wg cache
  if node.attr("flush-caches") == "true"
    FileUtils.rm wgcache_name, :force => true
  end
  # Is there already a wg cache? If not, create it.
  wg = []

  if Pathname.new(wgcache_name).file?
    begin
      File.open(wgcache_name, "r") do |f|
        wg = JSON.parse(f.read)
      end
    rescue Exception => e
      STDERR.puts "Cache #{wgcache_name} is invalid, drop it"
    end
  end

  if wg.empty?
    File.open(wgcache_name, "w") do |b|
      STDERR.puts "Reading workgroups from https://tools.ietf.org/wg/..."
      Kernel.open("https://tools.ietf.org/wg/") do |f|
        f.each_line do |line|
          line.scan(%r{<td width="50%" style='padding: 0 1ex'>([^<]+)</td>}) do |w|
            wg << w[0].gsub(/\s+$/, "").gsub(/ Working Group$/, "")
          end
        end
      end
      STDERR.puts "Reading workgroups from https://irtf.org/groups..."
      Kernel.open("https://irtf.org/groups", ssl_verify_mode: OpenSSL::SSL::VERIFY_NONE) do |f|
        f.each_line do |line|
          line.scan(%r{<a title="([^"]+) Research Group"[^>]+>([^<]+)<}) do |w|
            wg << w[0].gsub(/\s+$/, "")
            wg << w[1].gsub(/\s+$/, "") # abbrev
          end
        end
      end
      b << wg.to_json
    end
  end
  wg
end

#common_rfc_pis(node) ⇒ Object

def dash(camel_cased_word)

camel_cased_word.gsub(/([a-z])([A-Z])/, '\1-\2').downcase

end



195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 195

def common_rfc_pis(node)
  # Below are generally applicable Processing Instructions (PIs)
  # that most I-Ds might want to use, common to v2 and v3.
  # These are set only if explicitly specified, with the exception
  # of compact and subcompact
  rfc_pis = {
    artworkdelimiter: node.attr("artworkdelimiter"),
    artworklines: node.attr("artworklines"),
    authorship: node.attr("authorship"),
    autobreaks: node.attr("autobreaks"),
    background: node.attr("background"),
    colonspace: node.attr("colonspace"),
    comments: node.attr("comments"),
    docmapping: node.attr("docmapping"),
    editing: node.attr("editing"),
    emoticonic: node.attr("emoticonic"),
    footer: node.attr("footer"),
    header: node.attr("header"),
    inline: node.attr("inline"),
    iprnotified: node.attr("iprnotified"),
    linkmailto: node.attr("linkmailto"),
    linefile: node.attr("linefile"),
    notedraftinprogress: node.attr("notedraftinprogress"),
    private: node.attr("private"),
    refparent: node.attr("refparent"),
    rfcedstyle: node.attr("rfcedstyle"),
    slides: node.attr("slides"),
    "text-list-symbols": node.attr("text-list-symbols"),
    tocappendix: node.attr("tocappendix"),
    tocindent: node.attr("tocindent"),
    tocnarrow: node.attr("tocnarrow"),
    tocompact: node.attr("tocompact"),
    topblock: node.attr("topblock"),
    useobject: node.attr("useobject"),

    # give errors regarding ID-nits and DTD validation
    strict: node.attr("strict") || "yes",

    # Vertical whitespace control
    # (using these PIs as follows is recommended by the RFC Editor)

    # do not start each main section on a new page
    compact: node.attr("compact") || "yes",
    # keep one blank line between list items
    subcompact: node.attr("subcompact") || "no",

    # TOC control
    # generate a ToC
    toc: node.attr("toc-include") == "false" ? "no" : "yes",

    # the number of levels of subsections in ToC. default: 3
    tocdepth: node.attr("toc-depth") || "4",

    # use anchors rather than numbers for references
    symrefs: node.attr("sym-refs") || "yes",
    # sort references
    sortrefs: node.attr("sort-refs") || "yes",
  }

  attr_code(rfc_pis)
end

#content(node) ⇒ Object 



23
24
25
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 23

def content(node)
  node.content
end

#convert(node, transform = nil, opts = {}) ⇒ Object 



13
14
15
16
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 13

def convert(node, transform = nil, opts = {})
  transform ||= node.node_name
  opts.empty? ? (send transform, node) : (send transform, node, opts)
end

#current_location(node) ⇒ Object 



366
367
368
369
370
371
372
373
374
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 366

def current_location(node)
  return "Line #{node.lineno}" if node.respond_to?(:lineno) && !node.lineno.nil? && !node.lineno.empty?
  return "ID #{node.id}" if node.respond_to?(:id) && !node.id.nil?
  while !node.nil? && (!node.respond_to?(:level) || node.level > 0) && node.context != :section
    node = node.parent
    return "Section: #{node.title}" if !node.nil? && node.context == :section
  end
  "??"
end

#document_ns_attributes(_doc) ⇒ Object 



18
19
20
21
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 18

def document_ns_attributes(_doc)
  # ' xmlns="http://projectmallard.org/1.0/" xmlns:its="http://www.w3.org/2005/11/its"'
  nil
end

#extract_entities(node, xmldoc) ⇒ Object

extract references which can be expressed as externally defined entities



281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 281

def extract_entities(node, xmldoc)
  refs = xmldoc.xpath("//reference")
  ret = []
  biblio = cache_biblio(node)
  refs.each do |ref|
    next if ref.parent.name == "referencegroup"
    id = ref.at('.//seriesInfo[@name="Internet-Draft"]')
    anchor = ref["anchor"]
    url = if id.nil?
            biblio[anchor]
          else
            biblio["I-D.#{id['value']}"] # the specific version reference
          end
    if biblio.has_key? anchor
      ret << { entity: anchor,
               node: ref,
               url: url }
    end
  end
  ret
end

#flatten(node) ⇒ Object

if node contains blocks, flatten them into a single line



304
305
306
307
308
309
310
311
312
313
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 304

def flatten(node)
  result = []
  result << node.text if node.respond_to?(:text)
  if node.blocks?
    node.blocks.each { |b| result << flatten(b) }
  else
    result << node.content
  end
  result.reject(&:empty?)
end

#flatten_rawtext(node) ⇒ Object

if node contains blocks, flatten them into a single line; and extract only raw text



316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 316

def flatten_rawtext(node)
  result = []
  if node.respond_to?(:blocks) && node.blocks?
    node.blocks.each { |b| result << flatten_rawtext(b) }
  elsif node.respond_to?(:lines)
    node.lines.each do |x|
      result << if node.respond_to?(:context) && (node.context == :literal || node.context == :listing)
                  x.gsub(/</, "&lt;").gsub(/>/, "&gt;")
                else
                  # strip not only HTML tags <tag>, but also Asciidoc crossreferences <<xref>>
                  x.gsub(/<[^>]*>+/, "")
                end
    end
  elsif node.respond_to?(:text)
    result << node.text.gsub(/<[^>]*>+/, "")
  else
    result << node.content.gsub(/<[^>]*>+/, "")
  end
  result.reject(&:empty?)
end

#inline_indexterm(node) ⇒ Object 



134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 134

def inline_indexterm(node)
  # supports only primary and secondary terms
  # primary attribute (highlighted major entry) not supported
  if node.type == :visible
    iref_attributes = {
      item: node.text,
    }
    node.text + noko { |xml| xml.iref **attr_code(iref_attributes) }.join
  else
    terms = node.attr "terms"
    warn %(asciidoctor: WARNING (#{current_location(node)}): only primary and secondary index terms supported: #{terms.join(': ')}) if terms.size > 2
    iref_attributes = {
      item: terms[0],
      subitem: (terms.size > 1 ? terms[1] : nil),
    }
    noko { |xml| xml.iref **attr_code(iref_attributes) }.join
  end
end

#insert_biblio(node, xmldoc) ⇒ Object

insert bibliography based on anchors, references directory, and list of normatives in doc attribute



463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 463

def insert_biblio(node, xmldoc)
  # we want no references in this document, so we can ignore any anchors of references
  xmldoc.xpath("//referencegroup | //reference").each(&:remove)
  refs = Set.new
  xmldoc.xpath("//xref | //relref").each { |r| refs << r["target"] }
  anchors1 = Set.new
  # we have no references in this document, so any remaining anchors are internal cross-refs only
  xmldoc.xpath("//@anchor").each { |r| anchors1 << r.value }
  refs = refs - anchors1
  anchors = {}

  norm_refs_spec = Set.new(node.attr("normative").split(/,[ ]?/))
  anchors[:norm] = refs.intersection(norm_refs_spec)
  anchors[:info] = refs - anchors[:norm]
  seen_refs = { norm: Set.new, info: Set.new }
  refxml_in = { norm: {}, info: {} }
  refxml_out = { norm: [], info: [] }

  bibliodir = node.attr("biblio-dir")
  Dir.foreach bibliodir do |f|
    next if [".", ".."].include? f
    text = File.read("#{bibliodir}/#{f}", encoding: "utf-8")
    next unless text =~ /<reference/
    text =~ /<reference[^>]*anchor=['"]([^'"]*)/
    anchor = Regexp.last_match(1)
    next if anchor.nil? || anchor.empty?
    if anchors[:norm].include?(anchor)
      refxml_in[:norm][anchor] = text
      seen_refs[:norm] << anchor
    else
      refxml_in[:info][anchor] = text
      seen_refs[:info] << anchor
    end
  end

  biblio = cache_biblio(node)
  [:norm, :info].each do |reftype|
    anchors[reftype].each do |r|
      if refxml_in[reftype].has_key?(r)
        # priority to on-disk references over skeleton references: they may contain draft information
        refxml_out[reftype] << refxml_in[reftype][r]
      elsif biblio.has_key?(r)
        refxml_out[reftype] << %{<reference anchor="#{r}"/>}
      else
        warn "Reference #{r} has not been includes in references directory, and is not a recognised external RFC reference"
      end
    end
  end

  xml_location = xmldoc.at('//references[@title="Normative References" or name="Normative References"]')
  xml_location&.children = Nokogiri::XML.fragment(refxml_out[:norm].join)
  xml_location = xmldoc.at('//references[@title="Informative References" or name="Informative References"]')
  xml_location&.children = Nokogiri::XML.fragment(refxml_out[:info].join)
  xmldoc
end

#keyword(node, xml) ⇒ Object

Syntax:

= Title
Author
:keyword x, y



114
115
116
117
118
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 114

def keyword(node, xml)
  node.attr("keyword")&.split(/, ?/)&.each do |kw|
    xml.keyword { |k| k << kw }
  end
end

#noko(&block) ⇒ Object

block for processing XML document fragments as XHTML, to allow for HTMLentities



338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 338

def noko(&block)
  # fragment = ::Nokogiri::XML::DocumentFragment.parse("")
  # fragment.doc.create_internal_subset("xml", nil, "xhtml.dtd")
  head = <<HERE
  <!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
  doc = ::Nokogiri::XML.parse(head)
  fragment = doc.fragment("")
  ::Nokogiri::XML::Builder.with fragment, &block
  fragment.to_xml(encoding: "US-ASCII").lines.map { |l| l.gsub(/\s*\n/, "") }
end

#open(node) ⇒ Object 



171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 171

def open(node)
  # open block is a container of multiple blocks, treated as a single block.
  # We append each contained block to its parent
  result = []
  if node.role == "comment"
    return noko do |xml|
      xml.comment " " + [flatten_rawtext(node).map { |x| [x, ""] } ].flatten.join("\n") + " "
    end
  end

  if node.blocks?
    node.blocks.each do |b|
      result << send(b.context, b)
    end
  else
    result = paragraph(node)
  end
  result
end

#paragraph1(node) ⇒ Object 



120
121
122
123
124
125
126
127
128
129
130
131
132
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 120

def paragraph1(node)
  result = []
  result1 = node.content
  if result1 =~ /^(<t>|<dl>|<ol>|<ul>)/
    result = result1
  else
    t_attributes = {
      anchor: node.id,
    }
    result << noko { |xml| xml.t result1, **attr_code(t_attributes) }
  end
  result
end

#preamble(node) ⇒ Object

Note:

(boilerplate is ignored)

Syntax:

= Title
Author
:HEADER

ABSTRACT

NOTE: note



42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 42

def preamble(node)
  result = []

  # NOTE: *list is V3, verse is V2, paragraph is both
  abstractable_contexts = %i{paragraph dlist olist ulist verse open}

  abstract_blocks = node.blocks.take_while do |block|
    abstractable_contexts.include? block.context
  end

  remainder_blocks = node.blocks[abstract_blocks.length..-1]

  result << noko do |xml|
    if abstract_blocks.any?
      xml.abstract do |xml_abstract|
        xml_abstract << abstract_blocks.map(&:render).flatten.join("\n")
      end
    end
    xml << remainder_blocks.map(&:render).flatten.join("\n")
  end

  result << "</front><middle>"
  result
end

#reflist(node) ⇒ Object

ulist repurposed as reference list



154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 154

def reflist(node)
  # ++++
  # <xml>
  # ++++
  result = []
  if node.context == :pass
    node.lines.each do |item|
      # undo XML substitution
      ref = item.gsub(/\&lt;/, "<").gsub(/\&gt;/, ">")
      result << ref
    end
  else
    warn %(asciidoctor: WARNING (#{current_location(node)}): references are not raw XML: #{node.context})
  end
  result
end

#set_pis(node, doc) ⇒ Object 



257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 257

def set_pis(node, doc)
  # Below are generally applicable Processing Instructions (PIs)
  # that most I-Ds might want to use. (Here they are set differently than
  # their defaults in xml2rfc v1.32)

  if node.attr("rfc2629xslt") != "false"
    pi = Nokogiri::XML::ProcessingInstruction.new(doc, "xml-stylesheet",
                                                  'type="text/xsl" href="rfc2629.xslt"')
    doc.root.add_previous_sibling(pi)
  end

  doc.create_internal_subset("rfc", nil, Metanorma::Ietf::RFC2629DTD_URL)
  rfc_pis = common_rfc_pis(node)
  rfc_pis.each_pair do |k, v|
    pi = Nokogiri::XML::ProcessingInstruction.new(doc,
                                                  "rfc",
                                                  "#{k}=\"#{v}\"")
    doc.root.add_previous_sibling(pi)
  end

  doc
end

#skip(node, name = nil) ⇒ Object 



27
28
29
30
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 27

def skip(node, name = nil)
  warn %(asciidoctor: WARNING (#{current_location(node)}): converter missing for #{name || node.node_name} node in RFC backend)
  nil
end

#smart_quote_cleanup(xmldoc) ⇒ Object 



519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 519

def smart_quote_cleanup(xmldoc)
  # smart quotes: handle smart apostrophe
  xmldoc.traverse do |node|
    if node.text?
      node.content = node.content.tr("\u2019", "'")
      node.content = node.content.gsub(/\&#8217;/, "'")
      node.content = node.content.gsub(/\&#x2019;/, "'")
    elsif node.element?
      node.attributes.each do |k, v|
        node.set_attribute(k, v.content.tr("\u2019", "'"))
        node.set_attribute(k, v.content.gsub(/\&#8217;/, "'"))
        node.set_attribute(k, v.content.gsub(/\&#x2019;/, "'"))
      end
    end
  end
  xmldoc
end

#workgroup(node, xml) ⇒ Object

Syntax:

= Title
Author
:workgroup x, y



94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
 
# File 'lib/asciidoctor/rfc/common/base.rb', line 94

def workgroup(node, xml)
  workgroups = cache_workgroup(node)
  node.attr("workgroup")&.split(/, ?/)&.each do |wg|
    if wg =~ / (Working Group)$/i
      warn %(asciidoctor: WARNING (#{current_location(node)}): suffix "Working Group" will be stripped in published RFC from #{wg})
      wg_norm = wg.gsub(/ Working Group$/i, "")
    end
    if wg =~ / (Research Group)$/i
      warn %(asciidoctor: WARNING (#{current_location(node)}): suffix "Research Group" will be stripped from working group #{wg})
      wg_norm = wg.gsub(/ Research Group$/i, "")
    end
    warn %(asciidoctor: WARNING (#{current_location(node)}): unrecognised working group #{wg}) unless workgroups.include?(wg_norm)
    xml.workgroup { |w| w << wg }
  end
end