isodoc 1.6.3 → 1.6.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/rake.yml +2 -12
- data/.hound.yml +3 -1
- data/.rubocop.yml +3 -5
- data/isodoc.gemspec +1 -1
- data/lib/isodoc.rb +0 -2
- data/lib/isodoc/convert.rb +4 -0
- data/lib/isodoc/function/cleanup.rb +52 -43
- data/lib/isodoc/function/inline.rb +7 -7
- data/lib/isodoc/function/section.rb +29 -16
- data/lib/isodoc/function/to_word_html.rb +6 -3
- data/lib/isodoc/function/utils.rb +181 -163
- data/lib/isodoc/headlesshtml_convert.rb +8 -7
- data/lib/isodoc/html_function/comments.rb +2 -0
- data/lib/isodoc/html_function/footnotes.rb +14 -7
- data/lib/isodoc/html_function/html.rb +30 -26
- data/lib/isodoc/html_function/postprocess.rb +16 -13
- data/lib/isodoc/pdf_convert.rb +11 -13
- data/lib/isodoc/presentation_function/bibdata.rb +43 -22
- data/lib/isodoc/presentation_function/inline.rb +20 -15
- data/lib/isodoc/version.rb +1 -1
- data/lib/isodoc/word_function/postprocess.rb +50 -36
- data/lib/isodoc/xref/xref_gen_seq.rb +60 -35
- data/lib/isodoc/xref/xref_sect_gen.rb +4 -4
- data/spec/assets/scripts_override.html +3 -0
- data/spec/isodoc/blocks_spec.rb +196 -245
- data/spec/isodoc/inline_spec.rb +442 -289
- data/spec/isodoc/postproc_spec.rb +111 -50
- data/spec/isodoc/presentation_xml_spec.rb +354 -277
- data/spec/isodoc/terms_spec.rb +83 -83
- metadata +5 -4
|
@@ -21,9 +21,10 @@ module IsoDoc::Function
|
|
|
21
21
|
filename = filepath.sub_ext("").sub(/\.presentation$/, "").to_s
|
|
22
22
|
dir = init_dir(filename, debug)
|
|
23
23
|
@filename = filename
|
|
24
|
-
@localdir = filepath.parent
|
|
24
|
+
@localdir = "#{filepath.parent}/"
|
|
25
25
|
@sourcedir = @localdir
|
|
26
|
-
@sourcefilename and
|
|
26
|
+
@sourcefilename and
|
|
27
|
+
@sourcedir = "#{Pathname.new(@sourcefilename).parent}/"
|
|
27
28
|
[filename, dir]
|
|
28
29
|
end
|
|
29
30
|
|
|
@@ -47,7 +48,7 @@ module IsoDoc::Function
|
|
|
47
48
|
|
|
48
49
|
# isodoc.css overrides any CSS injected by Html2Doc, which
|
|
49
50
|
# is inserted before this CSS.
|
|
50
|
-
def define_head(head,
|
|
51
|
+
def define_head(head, _filename, _dir)
|
|
51
52
|
if @standardstylesheet
|
|
52
53
|
head.style do |style|
|
|
53
54
|
@standardstylesheet.open
|
|
@@ -128,6 +129,8 @@ module IsoDoc::Function
|
|
|
128
129
|
end
|
|
129
130
|
|
|
130
131
|
def boilerplate(node, out)
|
|
132
|
+
return if @bare
|
|
133
|
+
|
|
131
134
|
boilerplate = node.at(ns("//boilerplate")) or return
|
|
132
135
|
out.div **{ class: "authority" } do |s|
|
|
133
136
|
boilerplate.children.each do |n|
|
|
@@ -1,193 +1,211 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
-
module IsoDoc
|
|
4
|
-
module
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
3
|
+
module IsoDoc
|
|
4
|
+
module Function
|
|
5
|
+
module Utils
|
|
6
|
+
def date_range(date)
|
|
7
|
+
self.class.date_range(date)
|
|
8
|
+
end
|
|
8
9
|
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
10
|
+
def ns(xpath)
|
|
11
|
+
self.class.ns(xpath)
|
|
12
|
+
end
|
|
12
13
|
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
14
|
+
def insert_tab(out, count)
|
|
15
|
+
tab = %w(Hans Hant).include?(@script) ? "　" : " "
|
|
16
|
+
[1..count].each { out << tab }
|
|
17
|
+
end
|
|
17
18
|
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
19
|
+
# add namespaces for Word fragments
|
|
20
|
+
NOKOHEAD = <<~HERE
|
|
21
|
+
<!DOCTYPE html SYSTEM
|
|
22
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
23
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
24
|
+
<head> <title></title> <meta charset="UTF-8" /> </head>
|
|
25
|
+
<body> </body> </html>
|
|
26
|
+
HERE
|
|
27
|
+
|
|
28
|
+
# block for processing XML document fragments as XHTML,
|
|
29
|
+
# to allow for HTMLentities
|
|
30
|
+
def noko(&block)
|
|
31
|
+
doc = ::Nokogiri::XML.parse(NOKOHEAD)
|
|
32
|
+
fragment = doc.fragment("")
|
|
33
|
+
::Nokogiri::XML::Builder.with fragment, &block
|
|
34
|
+
fragment.to_xml(encoding: "US-ASCII").lines.map do |l|
|
|
35
|
+
l.gsub(/\s*\n/, "")
|
|
36
|
+
end
|
|
35
37
|
end
|
|
36
|
-
end
|
|
37
38
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
39
|
+
def attr_code(attributes)
|
|
40
|
+
attributes = attributes.reject { |_, val| val.nil? }.map
|
|
41
|
+
attributes.map do |k, v|
|
|
42
|
+
[k, v.is_a?(String) ? HTMLEntities.new.decode(v) : v]
|
|
43
|
+
end.to_h
|
|
44
|
+
end
|
|
44
45
|
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
abort "Malformed Output XML for #{@format}: #{e} "\
|
|
60
|
-
"(see #{@filename}.#{@format}.err)"
|
|
46
|
+
DOCTYPE_HDR = "<!DOCTYPE html SYSTEM "\
|
|
47
|
+
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">'
|
|
48
|
+
|
|
49
|
+
def to_xhtml(xml)
|
|
50
|
+
xml = to_xhtml_prep(xml)
|
|
51
|
+
begin
|
|
52
|
+
Nokogiri::XML.parse(xml, &:strict)
|
|
53
|
+
rescue Nokogiri::XML::SyntaxError => e
|
|
54
|
+
File.open("#{@filename}.#{@format}.err", "w:UTF-8") do |f|
|
|
55
|
+
f.write xml
|
|
56
|
+
end
|
|
57
|
+
abort "Malformed Output XML for #{@format}: #{e} "\
|
|
58
|
+
"(see #{@filename}.#{@format}.err)"
|
|
59
|
+
end
|
|
61
60
|
end
|
|
62
|
-
end
|
|
63
61
|
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
62
|
+
def to_xhtml_prep(xml)
|
|
63
|
+
xml.gsub!(/<\?xml[^>]*>/, "")
|
|
64
|
+
/<!DOCTYPE /.match(xml) || (xml = DOCTYPE_HDR + xml)
|
|
65
|
+
xml.split(/(&[^ \r\n\t#;]+;)/).map do |t|
|
|
66
|
+
if /^(&[^ \t\r\n#;]+;)/.match?(t)
|
|
67
|
+
HTMLEntities.new.encode(HTMLEntities.new.decode(t), :hexadecimal)
|
|
68
|
+
else t
|
|
69
|
+
end
|
|
70
|
+
end.join("")
|
|
71
|
+
end
|
|
69
72
|
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
+
def to_xhtml_fragment(xml)
|
|
74
|
+
doc = ::Nokogiri::XML.parse(NOKOHEAD)
|
|
75
|
+
doc.fragment(xml)
|
|
76
|
+
end
|
|
73
77
|
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
"local-name() = 'acknowledgements' or local-name() = 'term' or "\
|
|
78
|
-
"local-name() = 'appendix' or local-name() = 'foreword' or "\
|
|
79
|
-
"local-name() = 'introduction' or local-name() = 'terms' or "\
|
|
80
|
-
"local-name() = 'clause' or local-name() = 'references']/@id"
|
|
81
|
-
|
|
82
|
-
def get_clause_id(node)
|
|
83
|
-
clause = node.xpath(CLAUSE_ANCESTOR)
|
|
84
|
-
clause&.last&.text || nil
|
|
85
|
-
end
|
|
78
|
+
def from_xhtml(xml)
|
|
79
|
+
xml.to_xml.sub(%r{ xmlns="http://www.w3.org/1999/xhtml"}, "")
|
|
80
|
+
end
|
|
86
81
|
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
end
|
|
82
|
+
CLAUSE_ANCESTOR =
|
|
83
|
+
".//ancestor::*[local-name() = 'annex' or "\
|
|
84
|
+
"local-name() = 'definitions' or "\
|
|
85
|
+
"local-name() = 'acknowledgements' or local-name() = 'term' or "\
|
|
86
|
+
"local-name() = 'appendix' or local-name() = 'foreword' or "\
|
|
87
|
+
"local-name() = 'introduction' or local-name() = 'terms' or "\
|
|
88
|
+
"local-name() = 'clause' or local-name() = 'references']/@id"
|
|
89
|
+
|
|
90
|
+
def get_clause_id(node)
|
|
91
|
+
clause = node.xpath(CLAUSE_ANCESTOR)
|
|
92
|
+
clause&.last&.text || nil
|
|
93
|
+
end
|
|
100
94
|
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
95
|
+
NOTE_CONTAINER_ANCESTOR =
|
|
96
|
+
".//ancestor::*[local-name() = 'annex' or "\
|
|
97
|
+
"local-name() = 'foreword' or local-name() = 'appendix' or "\
|
|
98
|
+
"local-name() = 'introduction' or local-name() = 'terms' or "\
|
|
99
|
+
"local-name() = 'acknowledgements' or local-name() = 'term' or "\
|
|
100
|
+
"local-name() = 'clause' or local-name() = 'references' or "\
|
|
101
|
+
"local-name() = 'figure' or local-name() = 'formula' or "\
|
|
102
|
+
"local-name() = 'table' or local-name() = 'example']/@id"
|
|
103
|
+
|
|
104
|
+
def get_note_container_id(node)
|
|
105
|
+
container = node.xpath(NOTE_CONTAINER_ANCESTOR)
|
|
106
|
+
container&.last&.text || nil
|
|
108
107
|
end
|
|
109
|
-
end
|
|
110
108
|
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
109
|
+
def sentence_join(array)
|
|
110
|
+
return "" if array.nil? || array.empty?
|
|
111
|
+
|
|
112
|
+
if array.length == 1 then array[0]
|
|
113
|
+
else
|
|
114
|
+
@i18n.l10n("#{array[0..-2].join(', ')} "\
|
|
115
|
+
"#{@i18n.and} #{array.last}",
|
|
116
|
+
@lang, @script)
|
|
117
|
+
end
|
|
118
118
|
end
|
|
119
|
-
[@openmathdelim, @closemathdelim]
|
|
120
|
-
end
|
|
121
119
|
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
x.replace(x.children) if x.name == "a"
|
|
133
|
-
end
|
|
134
|
-
from_xhtml(h1)
|
|
135
|
-
end
|
|
120
|
+
# avoid `; avoid {{ (Liquid Templates); avoid [[ (Javascript)
|
|
121
|
+
def extract_delims(text)
|
|
122
|
+
@openmathdelim = "(#("
|
|
123
|
+
@closemathdelim = ")#)"
|
|
124
|
+
while text.include?(@openmathdelim) || text.include?(@closemathdelim)
|
|
125
|
+
@openmathdelim += "("
|
|
126
|
+
@closemathdelim += ")"
|
|
127
|
+
end
|
|
128
|
+
[@openmathdelim, @closemathdelim]
|
|
129
|
+
end
|
|
136
130
|
|
|
137
|
-
|
|
138
|
-
|
|
139
|
-
|
|
131
|
+
def header_strip(hdr)
|
|
132
|
+
h1 = to_xhtml_fragment(hdr.to_s.gsub(%r{<br\s*/>}, " ")
|
|
133
|
+
.gsub(/<\/?h[123456][^>]*>/, "").gsub(/<\/?b[^>]*>/, "").dup)
|
|
134
|
+
h1.traverse do |x|
|
|
135
|
+
if x.name == "span" && /mso-tab-count/.match(x["style"])
|
|
136
|
+
x.replace(" ")
|
|
137
|
+
elsif header_strip_elem?(x) then x.remove
|
|
138
|
+
elsif x.name == "a" then x.replace(x.children)
|
|
139
|
+
end
|
|
140
|
+
end
|
|
141
|
+
from_xhtml(h1)
|
|
142
|
+
end
|
|
140
143
|
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
end
|
|
147
|
-
Liquid::Template.parse(doc)
|
|
148
|
-
end
|
|
144
|
+
def header_strip_elem?(elem)
|
|
145
|
+
elem.name == "img" ||
|
|
146
|
+
elem.name == "span" && elem["class"] == "MsoCommentReference" ||
|
|
147
|
+
elem.name == "a" && elem["class"] == "FootnoteRef" ||
|
|
148
|
+
elem.name == "span" && /mso-bookmark/.match(elem["style"])
|
|
149
|
+
end
|
|
149
150
|
|
|
150
|
-
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
|
|
151
|
+
=begin
|
|
152
|
+
def liquid(doc)
|
|
153
|
+
self.class.liquid(doc)
|
|
154
|
+
end
|
|
155
|
+
=end
|
|
156
|
+
|
|
157
|
+
def liquid(doc)
|
|
158
|
+
# unescape HTML escapes in doc
|
|
159
|
+
doc = doc.split(%r<(\{%|%\})>).each_slice(4).map do |a|
|
|
160
|
+
a[2] = a[2].gsub(/</, "<").gsub(/>/, ">") if a.size > 2
|
|
161
|
+
a.join("")
|
|
162
|
+
end.join("")
|
|
163
|
+
Liquid::Template.parse(doc)
|
|
164
|
+
end
|
|
154
165
|
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
.get
|
|
158
|
-
.merge(@labels ? {labels: @labels} : {})
|
|
159
|
-
.merge(@meta.labels ? {labels: @meta.labels} : {})
|
|
160
|
-
.merge(fonts_options || {})
|
|
161
|
-
template = liquid(docxml)
|
|
162
|
-
template.render(meta.map { |k, v| [k.to_s, empty2nil(v)] }.to_h)
|
|
163
|
-
.gsub("<", "<").gsub(">", ">").gsub("&", "&")
|
|
164
|
-
end
|
|
166
|
+
def empty2nil(str)
|
|
167
|
+
return nil if !str.nil? && str.is_a?(String) && str.empty?
|
|
165
168
|
|
|
166
|
-
|
|
167
|
-
%r{^data:(image|application)/(?<imgtype>[^;]+);base64,(?<imgdata>.+)$} =~ uri
|
|
168
|
-
imgtype.sub!(/\+[a-z0-9]+$/, "") # svg+xml
|
|
169
|
-
imgtype = "png" unless /^[a-z0-9]+$/.match imgtype
|
|
170
|
-
Tempfile.open(["image", ".#{imgtype}"]) do |f|
|
|
171
|
-
f.binmode
|
|
172
|
-
f.write(Base64.strict_decode64(imgdata))
|
|
173
|
-
@tempfile_cache << f # persist to the end
|
|
174
|
-
f.path
|
|
169
|
+
str
|
|
175
170
|
end
|
|
176
|
-
end
|
|
177
171
|
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
|
|
181
|
-
|
|
182
|
-
|
|
183
|
-
|
|
184
|
-
|
|
172
|
+
def populate_template(docxml, _format = nil)
|
|
173
|
+
meta = @meta
|
|
174
|
+
.get
|
|
175
|
+
.merge(@labels ? { labels: @labels } : {})
|
|
176
|
+
.merge(@meta.labels ? { labels: @meta.labels } : {})
|
|
177
|
+
.merge(fonts_options || {})
|
|
178
|
+
template = liquid(docxml)
|
|
179
|
+
template.render(meta.map { |k, v| [k.to_s, empty2nil(v)] }.to_h)
|
|
180
|
+
.gsub("<", "<").gsub(">", ">").gsub("&", "&")
|
|
185
181
|
end
|
|
186
|
-
end
|
|
187
182
|
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
183
|
+
def save_dataimage(uri, _relative_dir = true)
|
|
184
|
+
%r{^data:(image|application)/(?<imgtype>[^;]+);base64,(?<imgdata>.+)$} =~ uri
|
|
185
|
+
imgtype.sub!(/\+[a-z0-9]+$/, "") # svg+xml
|
|
186
|
+
imgtype = "png" unless /^[a-z0-9]+$/.match? imgtype
|
|
187
|
+
Tempfile.open(["image", ".#{imgtype}"]) do |f|
|
|
188
|
+
f.binmode
|
|
189
|
+
f.write(Base64.strict_decode64(imgdata))
|
|
190
|
+
@tempfile_cache << f # persist to the end
|
|
191
|
+
f.path
|
|
192
|
+
end
|
|
193
|
+
end
|
|
194
|
+
|
|
195
|
+
def image_localfile(img)
|
|
196
|
+
if /^data:/.match? img["src"]
|
|
197
|
+
save_dataimage(img["src"], false)
|
|
198
|
+
elsif %r{^([A-Z]:)?/}.match? img["src"]
|
|
199
|
+
img["src"]
|
|
200
|
+
else
|
|
201
|
+
File.join(@localdir, img["src"])
|
|
202
|
+
end
|
|
203
|
+
end
|
|
204
|
+
|
|
205
|
+
def labelled_ancestor(node)
|
|
206
|
+
!node.ancestors("example, requirement, recommendation, permission, "\
|
|
207
|
+
"note, table, figure, sourcecode").empty?
|
|
208
|
+
end
|
|
191
209
|
end
|
|
192
210
|
end
|
|
193
211
|
end
|
|
@@ -1,11 +1,10 @@
|
|
|
1
|
-
require_relative "html_function/comments
|
|
2
|
-
require_relative "html_function/footnotes
|
|
3
|
-
require_relative "html_function/html
|
|
1
|
+
require_relative "html_function/comments"
|
|
2
|
+
require_relative "html_function/footnotes"
|
|
3
|
+
require_relative "html_function/html"
|
|
4
4
|
require "fileutils"
|
|
5
5
|
|
|
6
6
|
module IsoDoc
|
|
7
7
|
class HeadlessHtmlConvert < ::IsoDoc::Convert
|
|
8
|
-
|
|
9
8
|
include HtmlFunction::Comments
|
|
10
9
|
include HtmlFunction::Footnotes
|
|
11
10
|
include HtmlFunction::Html
|
|
@@ -26,16 +25,18 @@ module IsoDoc
|
|
|
26
25
|
docxml, filename, dir = convert_init(file, input_filename, debug)
|
|
27
26
|
result = convert1(docxml, filename, dir)
|
|
28
27
|
return result if debug
|
|
29
|
-
|
|
28
|
+
|
|
29
|
+
postprocess(result, "#{filename}.tmp.html", dir)
|
|
30
30
|
FileUtils.rm_rf dir
|
|
31
|
-
strip_head(filename
|
|
31
|
+
strip_head("#{filename}.tmp.html",
|
|
32
|
+
output_filename || "#{filename}.#{@suffix}")
|
|
32
33
|
FileUtils.rm_rf ["#{filename}.tmp.html", tmpimagedir]
|
|
33
34
|
end
|
|
34
35
|
|
|
35
36
|
def strip_head(input, output)
|
|
36
37
|
file = File.read(input, encoding: "utf-8")
|
|
37
38
|
doc = Nokogiri::XML(file)
|
|
38
|
-
doc.xpath("//head").each
|
|
39
|
+
doc.xpath("//head").each(&:remove)
|
|
39
40
|
doc.xpath("//html").each { |x| x.name = "div" }
|
|
40
41
|
body = doc.at("//body")
|
|
41
42
|
body.replace(body.children)
|
|
@@ -84,6 +84,7 @@ module IsoDoc::HtmlFunction
|
|
|
84
84
|
def comment_attributes(docxml, x)
|
|
85
85
|
fromlink = docxml.at("//*[@id='#{x['from']}']")
|
|
86
86
|
return(nil) if fromlink.nil?
|
|
87
|
+
|
|
87
88
|
tolink = docxml.at("//*[@id='#{x['to']}']") || fromlink
|
|
88
89
|
target = docxml.at("//*[@id='#{x['target']}']")
|
|
89
90
|
{ from: fromlink, to: tolink, target: target }
|
|
@@ -122,6 +123,7 @@ module IsoDoc::HtmlFunction
|
|
|
122
123
|
comments = []
|
|
123
124
|
docxml.xpath("//div[@style='mso-element:comment']").each do |c|
|
|
124
125
|
next unless c["id"] && !link_order[c["id"]].nil?
|
|
126
|
+
|
|
125
127
|
comments << { text: c.remove.to_s, id: c["id"] }
|
|
126
128
|
end
|
|
127
129
|
comments.sort! { |a, b| link_order[a[:id]] <=> link_order[b[:id]] }
|