isodoc 2.4.2 → 2.4.3

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 5f122ad0105340afb41607b8639eb00b7205328f9bddad0a5a3726e9644c912e
4
- data.tar.gz: 04b386a592680a3315ed3d55e7c6716bc177fd628a8d67f520e224b1a4d4de5f
3
+ metadata.gz: a0720c3026536785125b4c6c495e4f2573dfa7b2186094c0f36efa9c20a1fbd3
4
+ data.tar.gz: 9ea3325d067e417956b865edd0baf70dff9a5cb80008e6dfe5fbfbdaaaf16ff4
5
5
  SHA512:
6
- metadata.gz: 6fef982e2095471e35cc7235a3bc5712066845fd4302131e9760e8d10da548ec73b40f344816077b915b63d93d32cb5b459507ad2133ac52da257a6230e99353
7
- data.tar.gz: cbbaa050b52517cf272d7d0da4d875075e094b3dcda074a89c55945ceedb6c357914f9e9be0cd09e45ac9d6ace9f61f71b8f9d2ccb5c8d3ebb5ba4fd9251e632
6
+ metadata.gz: 2e97827c7adacaa26ef823222897672413056219fba5a3e0a6dee92079ac680cd50a9f1dde9cb7c40fddf23ef000fcb0478709a95916a4e6b222bf3d4e94ca54
7
+ data.tar.gz: 888734821add95629f8709aac1e5ac8b95b372b6a33d43e366e78e0c4ec6a3957dc9264a86015501458ca2752b881f44053e1f7a3997c5d0fb1b43ec816abc74
@@ -50,6 +50,8 @@ module IsoDoc
50
50
  # fontlicenseagreement: fontist font license agreement
51
51
  # modspecidentifierbase: base prefix for any Modspec identifiers
52
52
  # sourcehighlighter: whether to apply sourcecode highlighting
53
+ # semantic_xml_insert: whether to insert into presentation XML
54
+ # a copy of semantic XML
53
55
  def initialize(options) # rubocop:disable Lint/MissingSuper
54
56
  @options = options_preprocess(options)
55
57
  init_stylesheets(@options)
@@ -60,6 +62,7 @@ module IsoDoc
60
62
  init_locations(@options)
61
63
  init_i18n(@options)
62
64
  init_rendering(@options)
65
+ init_arrangement(@options)
63
66
  end
64
67
 
65
68
  def options_preprocess(options)
@@ -77,14 +80,18 @@ module IsoDoc
77
80
  @datauriimage = options[:datauriimage]
78
81
  @suppressheadingnumbers = options[:suppressheadingnumbers]
79
82
  @break_up_urls_in_tables = options[:breakupurlsintables]
80
- @sectionsplit = options[:sectionsplit] == "true"
81
83
  @suppressasciimathdup = options[:suppressasciimathdup]
82
- @bare = options[:bare]
83
84
  @aligncrosselements = options[:aligncrosselements]
84
85
  @modspecidentifierbase = options[:modspecidentifierbase]
85
86
  @sourcehighlighter = options[:sourcehighlighter]
86
87
  end
87
88
 
89
+ def init_arrangement(options)
90
+ @sectionsplit = options[:sectionsplit] == "true"
91
+ @bare = options[:bare]
92
+ @semantic_xml_insert = options[:semanticxmlinsert] != "false"
93
+ end
94
+
88
95
  def init_i18n(options)
89
96
  @i18nyaml = options[:i18nyaml]
90
97
  @lang = options[:language] || "en"
@@ -187,7 +194,7 @@ module IsoDoc
187
194
  @xrefs.parse docxml
188
195
  bibitem_lookup(docxml)
189
196
  noko do |xml|
190
- xml.html **{ lang: @lang.to_s } do |html|
197
+ xml.html lang: @lang.to_s do |html|
191
198
  html.parent.add_namespace("epub", "http://www.idpf.org/2007/ops")
192
199
  info docxml, nil
193
200
  populate_css
@@ -82,8 +82,11 @@ module IsoDoc
82
82
 
83
83
  def sourcecode_parse1(node, div)
84
84
  @sourcecode = "pre"
85
- node.at(ns(".//table")) || !node.ancestors("table").empty? and
85
+ node.at(ns(".//table[@class = 'rouge-line-table']")) ||
86
+ node.at("./ancestor::xmlns:table[@class = 'rouge-line-table']") and
86
87
  @sourcecode = "table"
88
+ # !node.ancestors("table").empty? and
89
+ # @sourcecode = "table"
87
90
  node.children.each { |n| parse(n, div) unless n.name == "name" }
88
91
  @sourcecode = false
89
92
  end
@@ -96,7 +99,7 @@ module IsoDoc
96
99
  @sourcecode = false
97
100
  @annotation = true
98
101
  out.div class: "annotation" do |div|
99
- #node.at("./preceding-sibling::*[local-name() = 'annotation']") or
102
+ # node.at("./preceding-sibling::*[local-name() = 'annotation']") or
100
103
  # div << "<br/>"
101
104
  callout = node.at(ns("//callout[@target='#{node['id']}']"))
102
105
  div << "<span class='c'>&lt;#{callout.text}&gt;</span> "
@@ -30,7 +30,7 @@ module IsoDoc
30
30
  end
31
31
 
32
32
  def keyword_parse(node, out)
33
- out.span **{ class: "keyword" } do |s|
33
+ out.span class: "keyword" do |s|
34
34
  node.children.each { |n| parse(n, s) }
35
35
  end
36
36
  end
@@ -4,55 +4,35 @@ module IsoDoc
4
4
  # This is highly specific to ISO, but it's not a bad precedent for
5
5
  # references anyway; keeping here instead of in IsoDoc::Iso for now
6
6
  def docid_l10n(text)
7
- return text if text.nil?
8
-
9
- text.gsub(/All Parts/i, @i18n.all_parts.downcase) if @i18n.all_parts
7
+ text.nil? and return text
8
+ @i18n.all_parts and text.gsub!(/All Parts/i, @i18n.all_parts.downcase)
9
+ text.size < 20 and text.gsub!(/ /, "&#xa0;")
10
10
  text
11
11
  end
12
12
 
13
- def nonstd_bibitem(list, bib, _ordinal, biblio) # %%%
13
+ def nonstd_bibitem(list, bib, _ordinal, biblio)
14
14
  list.p **attr_code(iso_bibitem_entry_attrs(bib, biblio)) do |ref|
15
- # ids = bibitem_ref_code(bib)
16
- # idents = render_identifier(ids)
17
- # if biblio then ref_entry_code(ref, ordinal, idents, ids)
18
- # else
19
- # ref << (idents[:ordinal] || idents[:metanorma] || idents[:sdo]).to_s
20
- # ref << ", #{idents[sdo]}" if idents[:ordinal] && idents[:sdo]
21
- # end
22
- # ref << "," if idents[:sdo]
23
15
  tag = bib.at(ns("./biblio-tag"))
24
16
  tag&.children&.each { |n| parse(n, ref) }
25
17
  reference_format(bib, ref)
26
18
  end
27
19
  end
28
20
 
29
- def std_bibitem_entry(list, bib, _ordinal, biblio) # %%%
21
+ def std_bibitem_entry(list, bib, _ordinal, biblio)
30
22
  list.p **attr_code(iso_bibitem_entry_attrs(bib, biblio)) do |ref|
31
- # idents = render_identifier(bibitem_ref_code(bib))
32
- # if biblio then ref_entry_code(ref, ordinal, idents, nil)
33
- # else
34
- # ref << (idents[:ordinal] || idents[:metanorma] || idents[:sdo]).to_s
35
- # ref << ", #{idents[:sdo]}" if (idents[:ordinal] ||
36
- # idents[:metanorma]) && idents[:sdo]
37
- # end
38
- # date_note_process(bib, ref)
39
- # ref << "," if idents[:sdo]
40
23
  tag = bib.at(ns("./biblio-tag"))
41
24
  tag&.children&.each { |n| parse(n, ref) }
42
25
  reference_format(bib, ref)
43
26
  end
44
27
  end
45
28
 
46
- # # if ids is just a number, only use that ([1] Non-Standard)
47
- # # else, use both ordinal, as prefix, and ids
48
- # def ref_entry_code(ref, ordinal, ids, _id) #%%%
49
- # prefix_bracketed_ref(ref, ids[:ordinal] || ids[:metanorma] ||
50
- # "[#{ordinal}]")
51
- # ids[:sdo] and ref << (ids[:sdo]).to_s
52
- # end
29
+ SKIP_DOCID = <<~XPATH.strip.freeze
30
+ @type = 'DOI' or @type = 'doi' or @type = 'ISSN' or @type = 'issn' or @type = 'ISBN' or @type = 'isbn' or starts-with(@type, 'ISSN.') or starts-with(@type, 'ISBN.') or starts-with(@type, 'issn.') or starts-with(@type, 'isbn.')
31
+ XPATH
53
32
 
54
- SKIP_DOCID = "@type = 'DOI' or @type = 'metanorma' or @type = 'ISSN' or " \
55
- "@type = 'metanorma-ordinal' or @type = 'ISBN'".freeze
33
+ SKIP_DOC1 = <<~XPATH.strip.freeze
34
+ #{SKIP_DOCID} or @type = 'metanorma-ordinal' or @type = 'metanorma'
35
+ XPATH
56
36
 
57
37
  def pref_ref_code(bib)
58
38
  bib["suppress_identifier"] == "true" and return nil
@@ -61,8 +41,8 @@ module IsoDoc
61
41
  ret.empty? and
62
42
  ret = bib.xpath(ns("./docidentifier[@primary = 'true']"))
63
43
  ret.empty? and
64
- ret = bib.at(ns("./docidentifier[not(#{SKIP_DOCID})]#{lang}")) ||
65
- bib.at(ns("./docidentifier[not(#{SKIP_DOCID})]"))
44
+ ret = bib.at(ns("./docidentifier[not(#{SKIP_DOC1})]#{lang}")) ||
45
+ bib.at(ns("./docidentifier[not(#{SKIP_DOC1})]"))
66
46
  ret
67
47
  end
68
48
 
@@ -70,8 +50,7 @@ module IsoDoc
70
50
  def bibitem_ref_code(bib)
71
51
  id = bib.at(ns("./docidentifier[@type = 'metanorma']"))
72
52
  id1 = pref_ref_code(bib)
73
- id2 = bib.at(ns("./docidentifier[@type = 'DOI' or @type = 'ISSN' or " \
74
- "@type = 'ISBN']"))
53
+ id2 = bib.at(ns("./docidentifier[#{SKIP_DOCID}]"))
75
54
  id3 = bib.at(ns("./docidentifier[@type = 'metanorma-ordinal']"))
76
55
  return [id, id1, id2, id3] if id || id1 || id2 || id3
77
56
  return [nil, nil, nil, nil] if bib["suppress_identifier"] == "true"
@@ -139,9 +118,9 @@ module IsoDoc
139
118
 
140
119
  def standard?(bib)
141
120
  ret = false
142
- drop = %w(metanorma DOI ISSN ISBN)
143
121
  bib.xpath(ns("./docidentifier")).each do |id|
144
- next if id["type"].nil? || drop.include?(id["type"])
122
+ next if id["type"].nil? ||
123
+ id.at(".//self::*[#{SKIP_DOCID} or @type = 'metanorma']")
145
124
 
146
125
  ret = true
147
126
  end
@@ -194,7 +173,7 @@ module IsoDoc
194
173
  return
195
174
  page_break(out)
196
175
  out.div do |div|
197
- div.h1 **{ class: "Section3" } do |h1|
176
+ div.h1 class: "Section3" do |h1|
198
177
  f.at(ns("./title"))&.children&.each { |c2| parse(c2, h1) }
199
178
  end
200
179
  biblio_list(f, div, true)
@@ -69,7 +69,7 @@ module IsoDoc
69
69
  end
70
70
 
71
71
  def from_xhtml(xml)
72
- numeric_escapes(xml.to_xml
72
+ numeric_escapes(to_xml(xml)
73
73
  .sub(%r{ xmlns="http://www.w3.org/1999/xhtml"}, ""))
74
74
  end
75
75
 
@@ -170,7 +170,7 @@ module IsoDoc
170
170
  end
171
171
 
172
172
  def code_css(isoxml, _out)
173
- c = isoxml.at(ns("//misc-container/source-highlighter-css")) or return
173
+ c = isoxml.at(ns("//metanorma-extension/source-highlighter-css")) or return
174
174
  set(:code_css, c.text)
175
175
  end
176
176
  end
@@ -17,8 +17,8 @@ module IsoDoc
17
17
  def toc_metadata(docxml)
18
18
  return unless @tocfigures || @toctables || @tocrecommendations
19
19
 
20
- ins = docxml.at(ns("//misc-container")) ||
21
- docxml.at(ns("//bibdata")).after("<misc-container/>").next_element
20
+ ins = docxml.at(ns("//metanorma-extension")) ||
21
+ docxml.at(ns("//bibdata")).after("<metanorma-extension/>").next_element
22
22
  @tocfigures and
23
23
  ins << "<toc type='figure'><title>#{@i18n.toc_figures}</title></toc>"
24
24
  @toctables and
@@ -41,7 +41,7 @@ module IsoDoc
41
41
  return unless @fontist_fonts
42
42
 
43
43
  ins = xmldoc.at(ns("//presentation-metadata")) ||
44
- xmldoc.at(ns("//misc-container")) || xmldoc.at(ns("//bibdata"))
44
+ xmldoc.at(ns("//metanorma-extension")) || xmldoc.at(ns("//bibdata"))
45
45
  CSV.parse_line(@fontist_fonts, col_sep: ";").map(&:strip).each do |f|
46
46
  ins.next = presmeta("fonts", f)
47
47
  end
@@ -32,7 +32,7 @@ module IsoDoc
32
32
  return localized unless twitter_cldr_reader_symbols[:decimal]
33
33
 
34
34
  integer, fraction = localized.split(twitter_cldr_reader_symbols[:decimal])
35
- return localized if fraction.nil? || fraction.length.zero?
35
+ return localized if fraction.nil? || fraction.empty?
36
36
 
37
37
  [integer, decorate_fraction_part(fraction, locale)]
38
38
  .join(twitter_cldr_reader_symbols[:decimal])
@@ -97,14 +97,25 @@ module IsoDoc
97
97
  end
98
98
 
99
99
  def mathml1(node, locale)
100
+ mathml_style_inherit(node)
100
101
  asciimath_dup(node)
101
102
  localize_maths(node, locale)
102
- return unless node.elements.size == 1 && node.elements.first.name == "mn"
103
+ mathml_number_to_number(node)
104
+ end
105
+
106
+ def mathml_style_inherit(node)
107
+ node.at("./ancestor::xmlns:strong") or return
108
+ node.children =
109
+ "<mstyle fontweight='bold'>#{node.children.to_xml}</mstyle>"
110
+ end
103
111
 
112
+ def mathml_number_to_number(node)
113
+ (node.elements.size == 1 && node.elements.first.name == "mn") or return
114
+ repl = node.at("./m:mn", MATHML).children
104
115
  if node.parent.name == "stem"
105
- node.parent.replace(node.at("./m:mn", MATHML).children)
116
+ node.parent.replace(repl)
106
117
  else
107
- node.replace(node.at("./m:mn", MATHML).children)
118
+ node.replace(repl)
108
119
  end
109
120
  end
110
121
  end
@@ -2,8 +2,8 @@ module IsoDoc
2
2
  class PresentationXMLConvert < ::IsoDoc::Convert
3
3
  def sourcehighlighter_css(docxml)
4
4
  @sourcehighlighter or return
5
- ins = docxml.at(ns("//misc-container")) ||
6
- docxml.at(ns("//bibdata")).after("<misc-container/>").next_element
5
+ ins = docxml.at(ns("//metanorma-extension")) ||
6
+ docxml.at(ns("//bibdata")).after("<metanorma-extension/>").next_element
7
7
  ins << "<source-highlighter-css>#{sourcehighlighter_css_file}" \
8
8
  "</source-highlighter-css>"
9
9
  end
@@ -15,10 +15,11 @@ module IsoDoc
15
15
 
16
16
  def sourcehighlighter
17
17
  @sourcehighlighter or return
18
+ Rouge::Formatter.enable_escape!
18
19
  f = Rouge::Formatters::HTML.new
19
20
  opts = { gutter_class: "rouge-gutter", code_class: "rouge-code" }
20
- { formatter: f,
21
- formatter_line: Rouge::Formatters::HTMLLineTable.new(f, opts) }
21
+ f1 = Rouge::Formatters::HTMLLineTable.new(f, opts)
22
+ { formatter: f, formatter_line: f1 }
22
23
  end
23
24
 
24
25
  def sourcecode(docxml)
@@ -50,6 +51,11 @@ module IsoDoc
50
51
  def source_remove_markup(elem)
51
52
  ret = {}
52
53
  name = elem.at(ns("./name")) and ret[:name] = name.remove.to_xml
54
+ source_remove_annotations(ret, elem)
55
+ ret
56
+ end
57
+
58
+ def source_remove_annotations(ret, elem)
53
59
  ret[:ann] = elem.xpath(ns("./annotation")).each(&:remove)
54
60
  ret[:call] = elem.xpath(ns("./callout")).each_with_object([]) do |c, m|
55
61
  m << { xml: c.remove.to_xml, line: c.line - elem.line }
@@ -99,9 +105,11 @@ module IsoDoc
99
105
  end
100
106
 
101
107
  def source_lex(elem)
102
- l = (Rouge::Lexer.find(elem["lang"] || "plaintext") ||
108
+ lexer = (Rouge::Lexer.find(elem["lang"] || "plaintext") ||
103
109
  Rouge::Lexer.find("plaintext"))
104
- l.lex(@c.decode(elem.children.to_xml))
110
+ l = Rouge::Lexers::Escape.new(start: "{^^{", end: "}^^}", lang: lexer)
111
+ source = to_xml(elem.children).gsub(/</, "{^^{<").gsub(/>/, ">}^^}")
112
+ l.lex(@c.decode(source))
105
113
  end
106
114
 
107
115
  def source_label(elem)
@@ -24,6 +24,7 @@ module IsoDoc
24
24
  end
25
25
 
26
26
  def conversions(docxml)
27
+ semantic_xml_insert(docxml)
27
28
  bibdata docxml
28
29
  @xrefs.parse docxml
29
30
  section docxml
@@ -84,6 +85,43 @@ module IsoDoc
84
85
  related docxml
85
86
  end
86
87
 
88
+ def semantic_xml_insert(xml)
89
+ @semantic_xml_insert or return
90
+ embed = to_xml(embedable_semantic_xml(xml))
91
+ ins = metanorma_extension_insert_pt(xml)
92
+ ins = ins.at(ns("./metanorma")) || ins.add_child("<metanorma/>").first
93
+ ins << "<source>#{embed}</source>"
94
+ end
95
+
96
+ def metanorma_extension_insert_pt(xml)
97
+ xml.at(ns("//metanorma-extension")) ||
98
+ xml.at(ns("//bibdata"))&.after("<metanorma-extension/>")
99
+ &.next_element ||
100
+ xml.root.elements.first.before("<metanorma-extension/>")
101
+ .previous_element
102
+ end
103
+
104
+ def embedable_semantic_xml(xml)
105
+ xml = embedable_semantic_xml_tags(xml)
106
+ embedable_semantic_xml_attributes(xml)
107
+ end
108
+
109
+ def embedable_semantic_xml_tags(xml)
110
+ Nokogiri::XML(to_xml(xml).gsub(%r{(</?)([[:alpha:]])},
111
+ "\\1semantic__\\2")).root
112
+ end
113
+
114
+ def embedable_semantic_xml_attributes(xml)
115
+ Metanorma::Utils::anchor_attributes.each do |(tag_name, attr_name)|
116
+ tag_name == "*" or tag_name = "semantic__#{tag_name}"
117
+ xml.xpath(ns("//#{tag_name}[@#{attr_name}]")).each do |elem|
118
+ elem.attributes[attr_name].value =
119
+ "semantic__#{elem.attributes[attr_name].value}"
120
+ end
121
+ end
122
+ xml
123
+ end
124
+
87
125
  def postprocess(result, filename, _dir)
88
126
  to_xml_file(result, filename)
89
127
  @files_to_delete.each { |f| FileUtils.rm_rf f }
@@ -1,3 +1,3 @@
1
1
  module IsoDoc
2
- VERSION = "2.4.2".freeze
2
+ VERSION = "2.4.3".freeze
3
3
  end
@@ -244,11 +244,11 @@ module IsoDoc
244
244
 
245
245
  def info(isoxml, out)
246
246
  @tocfigurestitle =
247
- isoxml&.at(ns("//misc-container/toc[@type = 'figure']/title"))&.text
247
+ isoxml&.at(ns("//metanorma-extension/toc[@type = 'figure']/title"))&.text
248
248
  @toctablestitle =
249
- isoxml&.at(ns("//misc-container/toc[@type = 'table']/title"))&.text
249
+ isoxml&.at(ns("//metanorma-extension/toc[@type = 'table']/title"))&.text
250
250
  @tocrecommendationstitle = isoxml
251
- &.at(ns("//misc-container/toc[@type = 'recommendation']/title"))&.text
251
+ &.at(ns("//metanorma-extension/toc[@type = 'recommendation']/title"))&.text
252
252
  super
253
253
  end
254
254
  end
@@ -4,7 +4,7 @@ module IsoDoc
4
4
  def comments(div)
5
5
  return if @comments.empty?
6
6
 
7
- div.div **{ style: "mso-element:comment-list" } do |div1|
7
+ div.div style: "mso-element:comment-list" do |div1|
8
8
  @comments.each { |fn| div1.parent << fn }
9
9
  end
10
10
  end
@@ -26,28 +26,27 @@ module IsoDoc
26
26
  # add in from and to links to move the comment into place
27
27
  def make_comment_link(out, fnote, node)
28
28
  out.span(**comment_link_attrs(fnote, node)) do |s1|
29
- s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2|
30
- s2.a **{ style: "mso-comment-reference:SMC_#{fnote};"\
29
+ s1.span lang: "EN-GB", style: "font-size:9.0pt" do |s2|
30
+ s2.a style: "mso-comment-reference:SMC_#{fnote};" \
31
31
  "mso-comment-date:#{node['date'].gsub(/[:-]+/,
32
- '')}" }
33
- s2.span **{ style: "mso-special-character:comment",
34
- target: fnote } # do |s|
32
+ '')}"
33
+ s2.span style: "mso-special-character:comment", target: fnote # do |s|
35
34
  end
36
35
  end
37
36
  end
38
37
 
39
38
  def make_comment_target(out)
40
- out.span **{ style: "MsoCommentReference" } do |s1|
41
- s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2|
42
- s2.span **{ style: "mso-special-character:comment" }
39
+ out.span style: "MsoCommentReference" do |s1|
40
+ s1.span lang: "EN-GB", style: "font-size:9.0pt" do |s2|
41
+ s2.span style: "mso-special-character:comment"
43
42
  end
44
43
  end
45
44
  end
46
45
 
47
46
  def make_comment_text(node, fnote)
48
47
  noko do |xml|
49
- xml.div **{ style: "mso-element:comment", id: fnote } do |div|
50
- div.span **{ style: %{mso-comment-author:"#{node['reviewer']}"} }
48
+ xml.div style: "mso-element:comment", id: fnote do |div|
49
+ div.span style: %{mso-comment-author:"#{node['reviewer']}"}
51
50
  make_comment_target(div)
52
51
  node.children.each { |n| parse(n, div) }
53
52
  end
@@ -61,7 +60,7 @@ module IsoDoc
61
60
  end
62
61
 
63
62
  COMMENT_IN_COMMENT_LIST1 =
64
- '//div[@style="mso-element:comment-list"]//'\
63
+ '//div[@style="mso-element:comment-list"]//' \
65
64
  'span[@style="MsoCommentReference"]'.freeze
66
65
 
67
66
  def embed_comment_in_comment_list(docxml)
@@ -80,18 +79,24 @@ module IsoDoc
80
79
  link.children = fromlink
81
80
  end
82
81
 
83
- def comment_attributes(docxml, x)
84
- fromlink = docxml.at("//*[@id='#{x['from']}']")
82
+ def comment_attributes(docxml, span)
83
+ fromlink = docxml.at("//*[@id='#{span['from']}']")
85
84
  return(nil) if fromlink.nil?
86
85
 
87
- tolink = docxml.at("//*[@id='#{x['to']}']") || fromlink
88
- target = docxml.at("//*[@id='#{x['target']}']")
86
+ tolink = docxml.at("//*[@id='#{span['to']}']") || fromlink
87
+ target = docxml.at("//*[@id='#{span['target']}']")
89
88
  { from: fromlink, to: tolink, target: target }
90
89
  end
91
90
 
92
91
  def wrap_comment_cont(from, target)
93
- s = from.replace("<span style='mso-comment-continuation:#{target}'>")
94
- s.first.children = from
92
+ if %w(ol ul li div p).include?(from.name)
93
+ from.children.each do |c|
94
+ wrap_comment_cont(c, target)
95
+ end
96
+ else
97
+ s = from.replace("<span style='mso-comment-continuation:#{target}'>")
98
+ s.first.children = from
99
+ end
95
100
  end
96
101
 
97
102
  def skip_comment_wrap(from)
@@ -45,7 +45,7 @@ module IsoDoc
45
45
 
46
46
  def make_generic_footnote_text(node, fnid)
47
47
  noko do |xml|
48
- xml.aside **{ id: "ftn#{fnid}" } do |div|
48
+ xml.aside id: "ftn#{fnid}" do |div|
49
49
  node.children.each { |n| parse(n, div) }
50
50
  end
51
51
  end.join("\n")
@@ -72,13 +72,13 @@ module IsoDoc
72
72
  end
73
73
 
74
74
  def seen_footnote_parse(_node, out, footnote)
75
- out.span **{ style: "mso-element:field-begin" }
75
+ out.span style: "mso-element:field-begin"
76
76
  out << " NOTEREF _Ref#{@fn_bookmarks[footnote]} \\f \\h"
77
- out.span **{ style: "mso-element:field-separator" }
78
- out.span **{ class: "MsoFootnoteReference" } do |s|
77
+ out.span style: "mso-element:field-separator"
78
+ out.span class: "MsoFootnoteReference" do |s|
79
79
  s << footnote
80
80
  end
81
- out.span **{ style: "mso-element:field-end" }
81
+ out.span style: "mso-element:field-end"
82
82
  end
83
83
 
84
84
  def footnote_parse(node, out)
@@ -89,9 +89,9 @@ module IsoDoc
89
89
  return seen_footnote_parse(node, out, fn) if @seen_footnote.include?(fn)
90
90
 
91
91
  @fn_bookmarks[fn] = bookmarkid
92
- out.span **{ style: "mso-bookmark:_Ref#{@fn_bookmarks[fn]}" } do |s|
93
- s.a **{ class: "FootnoteRef", "epub:type": "footnote",
94
- href: "#ftn#{fn}" } do |a|
92
+ out.span style: "mso-bookmark:_Ref#{@fn_bookmarks[fn]}" do |s|
93
+ s.a class: "FootnoteRef", "epub:type": "footnote",
94
+ href: "#ftn#{fn}" do |a|
95
95
  a.sup { |sup| sup << fn }
96
96
  end
97
97
  end
@@ -1,17 +1,11 @@
1
1
  require "fileutils"
2
2
  require_relative "./postprocess_cover"
3
3
  require_relative "./postprocess_toc"
4
+ require_relative "./postprocess_table"
4
5
 
5
6
  module IsoDoc
6
7
  module WordFunction
7
8
  module Postprocess
8
- def table_note_cleanup(docxml)
9
- super
10
- # preempt html2doc putting MsoNormal there
11
- docxml.xpath("//p[not(self::*[@class])][ancestor::*[@class = 'Note']]")
12
- .each { |p| p["class"] = "Note" }
13
- end
14
-
15
9
  def postprocess(result, filename, dir)
16
10
  filename = filename.sub(/\.doc$/, "")
17
11
  header = generate_header(filename, dir)
@@ -55,6 +49,7 @@ module IsoDoc
55
49
  word_nested_tables(docxml)
56
50
  word_colgroup(docxml)
57
51
  word_table_align(docxml)
52
+ word_table_pagebreak(docxml)
58
53
  word_table_separator(docxml)
59
54
  word_admonition_images(docxml)
60
55
  word_list_continuations(docxml)
@@ -108,54 +103,6 @@ module IsoDoc
108
103
  end
109
104
  end
110
105
 
111
- def word_colgroup(docxml)
112
- cells2d = {}
113
- docxml.xpath("//table[colgroup]").each do |t|
114
- w = colgroup_widths(t)
115
- t.xpath(".//tr").each_with_index { |_tr, r| cells2d[r] = {} }
116
- t.xpath(".//tr").each_with_index do |tr, r|
117
- tr.xpath("./td | ./th").each_with_index do |td, _i|
118
- x = 0
119
- rs = td.attr("rowspan")&.to_i || 1
120
- cs = td.attr("colspan")&.to_i || 1
121
- while cells2d[r][x]
122
- x += 1
123
- end
124
- (r..(r + rs - 1)).each do |y2|
125
- cells2d[y2].nil? and next
126
- (x..(x + cs - 1)).each { |x2| cells2d[y2][x2] = 1 }
127
- end
128
- width = (x..(x + cs - 1)).each_with_object({ width: 0 }) do |z, m|
129
- m[:width] += w[z]
130
- end
131
- td["width"] = "#{width[:width]}%"
132
- x += cs
133
- end
134
- end
135
- end
136
- end
137
-
138
- # assume percentages
139
- def colgroup_widths(table)
140
- table.xpath("./colgroup/col").each_with_object([]) do |c, m|
141
- m << c["width"].sub(/%$/, "").to_f
142
- end
143
- end
144
-
145
- def word_nested_tables(docxml)
146
- docxml.xpath("//table").each do |t|
147
- t.xpath(".//table").reverse.each do |tt|
148
- t.next = tt.remove
149
- end
150
- end
151
- end
152
-
153
- def style_update(node, css)
154
- node or return
155
- node["style"] =
156
- node["style"] ? node["style"].sub(/;?$/, ";#{css}") : css
157
- end
158
-
159
106
  def word_image_caption(docxml)
160
107
  docxml.xpath("//p[@class = 'FigureTitle' or @class = 'SourceTitle']")
161
108
  .each do |t|
@@ -188,21 +135,6 @@ module IsoDoc
188
135
  end
189
136
  end
190
137
 
191
- def word_table_align(docxml)
192
- docxml.xpath("//td[@align]/p | //th[@align]/p").each do |p|
193
- p["align"] and next
194
- style_update(p, "text-align: #{p.parent['align']}")
195
- end
196
- end
197
-
198
- def word_table_separator(docxml)
199
- docxml.xpath("//p[@class = 'TableTitle']").each do |t|
200
- t.children.empty? or next
201
- t["style"] = t["style"].sub(/;?$/, ";font-size:0pt;")
202
- t.children = "&#xa0;"
203
- end
204
- end
205
-
206
138
  def word_annex_cleanup(docxml); end
207
139
 
208
140
  def word_example_cleanup(docxml)
@@ -0,0 +1,85 @@
1
+ module IsoDoc
2
+ module WordFunction
3
+ module Postprocess
4
+ def table_note_cleanup(docxml)
5
+ super
6
+ # preempt html2doc putting MsoNormal there
7
+ docxml.xpath("//p[not(self::*[@class])][ancestor::*[@class = 'Note']]")
8
+ .each { |p| p["class"] = "Note" }
9
+ end
10
+
11
+ def word_colgroup(docxml)
12
+ cells2d = {}
13
+ docxml.xpath("//table[colgroup]").each do |t|
14
+ w = colgroup_widths(t)
15
+ t.xpath(".//tr").each_with_index { |_tr, r| cells2d[r] = {} }
16
+ t.xpath(".//tr").each_with_index do |tr, r|
17
+ tr.xpath("./td | ./th").each_with_index do |td, _i|
18
+ x = 0
19
+ rs = td.attr("rowspan")&.to_i || 1
20
+ cs = td.attr("colspan")&.to_i || 1
21
+ while cells2d[r][x]
22
+ x += 1
23
+ end
24
+ (r..(r + rs - 1)).each do |y2|
25
+ cells2d[y2].nil? and next
26
+ (x..(x + cs - 1)).each { |x2| cells2d[y2][x2] = 1 }
27
+ end
28
+ width = (x..(x + cs - 1)).each_with_object({ width: 0 }) do |z, m|
29
+ m[:width] += w[z]
30
+ end
31
+ td["width"] = "#{width[:width]}%"
32
+ x += cs
33
+ end
34
+ end
35
+ end
36
+ end
37
+
38
+ # assume percentages
39
+ def colgroup_widths(table)
40
+ table.xpath("./colgroup/col").each_with_object([]) do |c, m|
41
+ m << c["width"].sub(/%$/, "").to_f
42
+ end
43
+ end
44
+
45
+ def word_nested_tables(docxml)
46
+ docxml.xpath("//table").each do |t|
47
+ t.xpath(".//table").reverse.each do |tt|
48
+ t.next = tt.remove
49
+ end
50
+ end
51
+ end
52
+
53
+ def style_update(node, css)
54
+ node or return
55
+ node["style"] =
56
+ node["style"] ? node["style"].sub(/;?$/, ";#{css}") : css
57
+ end
58
+
59
+ def word_table_align(docxml)
60
+ docxml.xpath("//td[@align]/p | //th[@align]/p").each do |p|
61
+ p["align"] and next
62
+ style_update(p, "text-align: #{p.parent['align']}")
63
+ end
64
+ end
65
+
66
+ def word_table_separator(docxml)
67
+ docxml.xpath("//p[@class = 'TableTitle']").each do |t|
68
+ t.children.empty? or next
69
+ t["style"] = t["style"].sub(/;?$/, ";font-size:0pt;")
70
+ t.children = "&#xa0;"
71
+ end
72
+ end
73
+
74
+ def word_table_pagebreak(docxml)
75
+ docxml.xpath("//td[@style] | //th[@style]").each do |t|
76
+ s = /(page-break-after:[^;]+)/.match(t["style"])
77
+ (s && s[1]) or next
78
+ t.xpath(".//div | .//p | .//pre").each do |p|
79
+ style_update(p, s[1])
80
+ end
81
+ end
82
+ end
83
+ end
84
+ end
85
+ end
@@ -24,35 +24,53 @@ module IsoDoc
24
24
  def make_tr_attr(cell, row, totalrows, header, bordered)
25
25
  style = cell.name == "th" ? "font-weight:bold;" : ""
26
26
  rowmax = cell["rowspan"] ? row + cell["rowspan"].to_i - 1 : row
27
- style += make_tr_attr_style(row, rowmax, totalrows, header, bordered)
27
+ style += make_tr_attr_style(cell, row, rowmax, totalrows,
28
+ { header: header, bordered: bordered })
28
29
  { rowspan: cell["rowspan"], colspan: cell["colspan"],
29
30
  valign: cell["valign"], align: cell["align"], style: style,
30
31
  class: cell["class"] }
31
32
  end
32
33
 
33
- def make_tr_attr_style(row, rowmax, totalrows, header, bordered)
34
+ def make_tr_attr_style(cell, row, rowmax, totalrows, opt)
35
+ top = row.zero? ? "#{SW1} 1.5pt;" : "none;"
36
+ bottom = "#{SW1} #{rowmax >= totalrows ? '1.5' : '1.0'}pt;"
34
37
  ret = <<~STYLE.gsub(/\n/, "")
35
- border-top:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
36
- mso-border-top-alt:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
37
- border-bottom:#{SW1} #{rowmax >= totalrows ? '1.5' : '1.0'}pt;
38
- mso-border-bottom-alt:#{SW1} #{rowmax >= totalrows ? '1.5' : '1.0'}pt;
38
+ border-top:#{top}mso-border-top-alt:#{top}
39
+ border-bottom:#{bottom}mso-border-bottom-alt:#{bottom}
39
40
  STYLE
40
- bordered or ret = ""
41
- pb = header || (totalrows <= 10 && rowmax < totalrows) ? "avoid" : "auto"
41
+ opt[:bordered] or ret = ""
42
+ pb = keep_rows_together(cell, rowmax, totalrows, opt) ? "avoid" : "auto"
42
43
  "#{ret}page-break-after:#{pb};"
43
44
  end
44
45
 
46
+ def keep_rows_together(cell, rowmax, totalrows, opt)
47
+ opt[:header] and return true
48
+ table_line_count(cell.parent.parent) > 15 and return false
49
+ (totalrows <= 10 && rowmax < totalrows)
50
+ end
51
+
52
+ def table_line_count(tbody)
53
+ sum = 0
54
+ tbody.xpath(ns(".//tr")).each do |r|
55
+ i = 1
56
+ r.xpath(ns(".//td | .//th")).each do |c|
57
+ n = c.xpath(ns(".//li | .//p | .//br")).size
58
+ n > i and i = n
59
+ end
60
+ sum += i
61
+ end
62
+ sum
63
+ end
64
+
45
65
  def table_attrs(node)
46
66
  c = node["class"]
47
67
  bordered = "border-spacing:0;border-width:1px;"
48
68
  (%w(modspec).include?(c) || !c) or bordered = nil
49
69
  ret = {
50
- summary: node["summary"],
51
- width: node["width"],
70
+ summary: node["summary"], width: node["width"],
52
71
  style: "mso-table-anchor-horizontal:column;mso-table-overlap:never;" \
53
72
  "#{bordered}#{keep_style(node)}",
54
- class: (node.text.length > 4000 ? "MsoISOTableBig" : "MsoISOTable"),
55
- }
73
+ class: (node.text.length > 4000 ? "MsoISOTableBig" : "MsoISOTable") }
56
74
  bordered or ret.delete(:class)
57
75
  super.merge(attr_code(ret))
58
76
  end
@@ -61,7 +79,7 @@ module IsoDoc
61
79
  colgroup = node.at(ns("./colgroup")) or return
62
80
  table.colgroup do |cg|
63
81
  colgroup.xpath(ns("./col")).each do |c|
64
- cg.col **{ width: c["width"] }
82
+ cg.col width: c["width"]
65
83
  end
66
84
  end
67
85
  end
@@ -69,7 +87,7 @@ module IsoDoc
69
87
  def table_parse(node, out)
70
88
  @in_table = true
71
89
  table_title_parse(node, out)
72
- out.div **{ align: "center", class: "table_container" } do |div|
90
+ out.div align: "center", class: "table_container" do |div|
73
91
  div.table **table_attrs(node) do |t|
74
92
  colgroup(node, t)
75
93
  thead_parse(node, t)
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: isodoc
3
3
  version: !ruby/object:Gem::Version
4
- version: 2.4.2
4
+ version: 2.4.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ribose Inc.
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2022-12-30 00:00:00.000000000 Z
11
+ date: 2023-01-23 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: asciimath
@@ -480,6 +480,7 @@ files:
480
480
  - lib/isodoc/word_function/inline.rb
481
481
  - lib/isodoc/word_function/postprocess.rb
482
482
  - lib/isodoc/word_function/postprocess_cover.rb
483
+ - lib/isodoc/word_function/postprocess_table.rb
483
484
  - lib/isodoc/word_function/postprocess_toc.rb
484
485
  - lib/isodoc/word_function/table.rb
485
486
  - lib/isodoc/xref.rb