html2doc 1.1.1 → 1.1.2
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.
- checksums.yaml +4 -4
- data/bin/html2doc +1 -1
- data/bin/rspec +1 -1
- data/html2doc.gemspec +7 -8
- data/lib/html2doc.rb +0 -3
- data/lib/html2doc/base.rb +3 -2
- data/lib/html2doc/lists.rb +24 -27
- data/lib/html2doc/math.rb +35 -18
- data/lib/html2doc/mime.rb +16 -17
- data/lib/html2doc/notes.rb +12 -9
- data/lib/html2doc/version.rb +1 -1
- data/spec/html2doc_spec.rb +162 -116
- metadata +41 -41
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 64215843fa5fb0918c0c24d6023f466b3602d36fe155ff49687f2a9e447e6681
|
|
4
|
+
data.tar.gz: 2fd0022ce58dd6106f27825b593b7d6c632913414699067cc70ba09936d47810
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: fc525ead15dbbdbfede252026ae44451cd5b45fe8225c70cdefcccafd3e5a903a32d8e6dfdb396f67c58d11e8b2c48a36562bf8e4f439181f99a8f49b3799202
|
|
7
|
+
data.tar.gz: 243b6c5efa00090e1248ad420d9641882fcc956fb8734333267459db9dbaffbf0742488164f4c72975ce4bb9b4e62458eb0c0d5dc03bb3cd7990863d77ba40a3
|
data/bin/html2doc
CHANGED
data/bin/rspec
CHANGED
data/html2doc.gemspec
CHANGED
|
@@ -1,5 +1,4 @@
|
|
|
1
|
-
|
|
2
|
-
lib = File.expand_path("../lib", __FILE__)
|
|
1
|
+
lib = File.expand_path("lib", __dir__)
|
|
3
2
|
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
4
3
|
require "html2doc/version"
|
|
5
4
|
|
|
@@ -16,8 +15,8 @@ Gem::Specification.new do |spec|
|
|
|
16
15
|
This gem is in active development.
|
|
17
16
|
DESCRIPTION
|
|
18
17
|
|
|
19
|
-
spec.homepage
|
|
20
|
-
spec.licenses
|
|
18
|
+
spec.homepage = "https://github.com/metanorma/html2doc"
|
|
19
|
+
spec.licenses = ["CC-BY-SA-3.0", "BSD-2-Clause"]
|
|
21
20
|
|
|
22
21
|
spec.bindir = "bin"
|
|
23
22
|
spec.require_paths = ["lib"]
|
|
@@ -25,14 +24,14 @@ Gem::Specification.new do |spec|
|
|
|
25
24
|
spec.test_files = `git ls-files -- {spec}/*`.split("\n")
|
|
26
25
|
spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
|
|
27
26
|
|
|
27
|
+
spec.add_dependency "asciimath", "~> 2.0.2"
|
|
28
28
|
spec.add_dependency "htmlentities", "~> 4.3.4"
|
|
29
29
|
spec.add_dependency "image_size"
|
|
30
30
|
spec.add_dependency "mime-types"
|
|
31
|
-
spec.add_dependency "nokogiri", "~> 1.10
|
|
31
|
+
spec.add_dependency "nokogiri", "~> 1.10"
|
|
32
|
+
spec.add_dependency "plane1converter", "~> 0.0.1"
|
|
32
33
|
spec.add_dependency "thread_safe"
|
|
33
34
|
spec.add_dependency "uuidtools"
|
|
34
|
-
spec.add_dependency "asciimath", "~> 2.0.2"
|
|
35
|
-
spec.add_dependency "plane1converter", "~> 0.0.1"
|
|
36
35
|
|
|
37
36
|
spec.add_development_dependency "byebug", "~> 9.1"
|
|
38
37
|
spec.add_development_dependency "equivalent-xml", "~> 0.6"
|
|
@@ -40,8 +39,8 @@ Gem::Specification.new do |spec|
|
|
|
40
39
|
spec.add_development_dependency "guard-rspec", "~> 4.7"
|
|
41
40
|
spec.add_development_dependency "rake", "~> 12.0"
|
|
42
41
|
spec.add_development_dependency "rspec", "~> 3.6"
|
|
42
|
+
spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
|
|
43
43
|
spec.add_development_dependency "rubocop", "~> 1.5.2"
|
|
44
44
|
spec.add_development_dependency "simplecov", "~> 0.15"
|
|
45
45
|
spec.add_development_dependency "timecop", "~> 0.9"
|
|
46
|
-
spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
|
|
47
46
|
end
|
data/lib/html2doc.rb
CHANGED
data/lib/html2doc/base.rb
CHANGED
|
@@ -106,6 +106,7 @@ module Html2Doc
|
|
|
106
106
|
doc.gsub!(%r{></o:lock>}, "/>")
|
|
107
107
|
doc.gsub!(%r{></v:imagedata>}, "/>")
|
|
108
108
|
doc.gsub!(%r{></w:wrap>}, "/>")
|
|
109
|
+
doc.gsub!(%r{<(/)?m:(span|em)\b}, "<\\1\\2")
|
|
109
110
|
doc.gsub!(%r{&tab;|&tab;},
|
|
110
111
|
'<span style="mso-tab-count:1">  </span>')
|
|
111
112
|
doc.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
|
|
@@ -127,7 +128,7 @@ module Html2Doc
|
|
|
127
128
|
<meta http-equiv=Content-Type content="text/html; charset=utf-8"/>
|
|
128
129
|
XML
|
|
129
130
|
|
|
130
|
-
def self.define_head1(docxml,
|
|
131
|
+
def self.define_head1(docxml, _dir)
|
|
131
132
|
docxml.xpath("//*[local-name() = 'head']").each do |h|
|
|
132
133
|
h.children.first.add_previous_sibling <<~XML
|
|
133
134
|
#{PRINT_VIEW}
|
|
@@ -147,7 +148,7 @@ module Html2Doc
|
|
|
147
148
|
end
|
|
148
149
|
end
|
|
149
150
|
|
|
150
|
-
def self.stylesheet(
|
|
151
|
+
def self.stylesheet(_filename, _header_filename, fn)
|
|
151
152
|
(fn.nil? || fn.empty?) and
|
|
152
153
|
fn = File.join(File.dirname(__FILE__), "wordstyle.css")
|
|
153
154
|
stylesheet = File.read(fn, encoding: "UTF-8")
|
data/lib/html2doc/lists.rb
CHANGED
|
@@ -2,30 +2,29 @@ require "uuidtools"
|
|
|
2
2
|
require "asciimath"
|
|
3
3
|
require "htmlentities"
|
|
4
4
|
require "nokogiri"
|
|
5
|
-
require "uuidtools"
|
|
6
5
|
|
|
7
6
|
module Html2Doc
|
|
8
|
-
def self.style_list(
|
|
7
|
+
def self.style_list(elem, level, liststyle, listnumber)
|
|
9
8
|
return unless liststyle
|
|
10
9
|
|
|
11
|
-
if
|
|
12
|
-
|
|
10
|
+
if elem["style"]
|
|
11
|
+
elem["style"] += ";"
|
|
13
12
|
else
|
|
14
|
-
|
|
13
|
+
elem["style"] = ""
|
|
15
14
|
end
|
|
16
|
-
|
|
15
|
+
elem["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
|
|
17
16
|
end
|
|
18
17
|
|
|
19
|
-
def self.list_add1(
|
|
18
|
+
def self.list_add1(elem, liststyles, listtype, level)
|
|
20
19
|
if %i[ul ol].include? listtype
|
|
21
|
-
list_add(
|
|
20
|
+
list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
|
|
22
21
|
liststyles, :ul, level + 1)
|
|
23
|
-
list_add(
|
|
22
|
+
list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
|
|
24
23
|
liststyles, :ol, level + 1)
|
|
25
24
|
else
|
|
26
|
-
list_add(
|
|
25
|
+
list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
|
|
27
26
|
liststyles, listtype, level + 1)
|
|
28
|
-
list_add(
|
|
27
|
+
list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
|
|
29
28
|
liststyles, listtype, level + 1)
|
|
30
29
|
end
|
|
31
30
|
end
|
|
@@ -47,45 +46,43 @@ module Html2Doc
|
|
|
47
46
|
end
|
|
48
47
|
end
|
|
49
48
|
|
|
50
|
-
def self.list2para(
|
|
51
|
-
return if
|
|
49
|
+
def self.list2para(list)
|
|
50
|
+
return if list.xpath("./li").empty?
|
|
52
51
|
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
52
|
+
list.xpath("./li").first["class"] ||= "MsoListParagraphCxSpFirst"
|
|
53
|
+
list.xpath("./li").last["class"] ||= "MsoListParagraphCxSpLast"
|
|
54
|
+
list.xpath("./li/p").each { |p| p["class"] ||= "MsoListParagraphCxSpMiddle" }
|
|
55
|
+
list.xpath("./li").each do |l|
|
|
57
56
|
l.name = "p"
|
|
58
57
|
l["class"] ||= "MsoListParagraphCxSpMiddle"
|
|
59
58
|
l&.first_element_child&.name == "p" and
|
|
60
59
|
l.first_element_child.replace(l.first_element_child.children)
|
|
61
60
|
end
|
|
62
|
-
|
|
61
|
+
list.replace(list.children)
|
|
63
62
|
end
|
|
64
63
|
|
|
65
64
|
TOPLIST = "[not(ancestor::ul) and not(ancestor::ol)]".freeze
|
|
66
65
|
|
|
67
|
-
def self.lists1(docxml, liststyles,
|
|
68
|
-
case
|
|
66
|
+
def self.lists1(docxml, liststyles, style)
|
|
67
|
+
case style
|
|
69
68
|
when :ul then list_add(docxml.xpath("//ul[not(@class)]#{TOPLIST}"),
|
|
70
69
|
liststyles, :ul, 1)
|
|
71
70
|
when :ol then list_add(docxml.xpath("//ol[not(@class)]#{TOPLIST}"),
|
|
72
71
|
liststyles, :ol, 1)
|
|
73
72
|
else
|
|
74
|
-
list_add(docxml.xpath("//ol[@class = '#{
|
|
75
|
-
"//ul[@class = '#{
|
|
76
|
-
liststyles,
|
|
73
|
+
list_add(docxml.xpath("//ol[@class = '#{style}']#{TOPLIST} | "\
|
|
74
|
+
"//ul[@class = '#{style}']#{TOPLIST}"),
|
|
75
|
+
liststyles, style, 1)
|
|
77
76
|
end
|
|
78
77
|
end
|
|
79
78
|
|
|
80
79
|
def self.lists_unstyled(docxml, liststyles)
|
|
81
|
-
|
|
80
|
+
liststyles.has_key?(:ul) and
|
|
82
81
|
list_add(docxml.xpath("//ul#{TOPLIST}[not(@seen)]"),
|
|
83
82
|
liststyles, :ul, 1)
|
|
84
|
-
|
|
85
|
-
if liststyles.has_key?(:ol)
|
|
83
|
+
liststyles.has_key?(:ol) and
|
|
86
84
|
list_add(docxml.xpath("//ol#{TOPLIST}[not(@seen)]"),
|
|
87
85
|
liststyles, :ul, 1)
|
|
88
|
-
end
|
|
89
86
|
docxml.xpath("//ul[@seen] | //ol[@seen]").each do |l|
|
|
90
87
|
l.delete("seen")
|
|
91
88
|
end
|
data/lib/html2doc/math.rb
CHANGED
|
@@ -25,13 +25,18 @@ module Html2Doc
|
|
|
25
25
|
|
|
26
26
|
m = doc.split(/(#{Regexp.escape(delims[0])}|#{Regexp.escape(delims[1])})/)
|
|
27
27
|
m.each_slice(4).map.with_index do |(*a), i|
|
|
28
|
-
i
|
|
29
|
-
warn "MathML #{i} of #{(m.size / 4).floor}"
|
|
28
|
+
progress_conv(i, 500, (m.size / 4).floor, 1000, "AsciiMath")
|
|
30
29
|
a[2].nil? || a[2] = asciimath_to_mathml1(a[2])
|
|
31
30
|
a.size > 1 ? a[0] + a[2] : a[0]
|
|
32
31
|
end.join
|
|
33
32
|
end
|
|
34
33
|
|
|
34
|
+
def self.progress_conv(idx, step, total, threshold, msg)
|
|
35
|
+
return unless (idx % step).zero? && total > threshold && idx.positive?
|
|
36
|
+
|
|
37
|
+
warn "#{msg} #{idx} of #{total}"
|
|
38
|
+
end
|
|
39
|
+
|
|
35
40
|
def self.unwrap_accents(doc)
|
|
36
41
|
doc.xpath("//*[@accent = 'true']").each do |x|
|
|
37
42
|
x.elements.length > 1 or next
|
|
@@ -69,18 +74,20 @@ module Html2Doc
|
|
|
69
74
|
math
|
|
70
75
|
end
|
|
71
76
|
|
|
77
|
+
HTML_NS = 'xmlns="http://www.w3.org/1999/xhtml"'.freeze
|
|
78
|
+
|
|
72
79
|
def self.unitalic(math)
|
|
73
80
|
math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'p']]").each do |x|
|
|
74
|
-
x.wrap("<span style='font-style:normal;'></span>")
|
|
81
|
+
x.wrap("<span #{HTML_NS} style='font-style:normal;'></span>")
|
|
75
82
|
end
|
|
76
83
|
math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'bi']]").each do |x|
|
|
77
|
-
x.wrap("<span class='nostem' style='font-weight:bold;'><em></em></span>")
|
|
84
|
+
x.wrap("<span #{HTML_NS} class='nostem' style='font-weight:bold;'><em></em></span>")
|
|
78
85
|
end
|
|
79
86
|
math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'i']]").each do |x|
|
|
80
|
-
x.wrap("<span class='nostem'><em></em></span>")
|
|
87
|
+
x.wrap("<span #{HTML_NS} class='nostem'><em></em></span>")
|
|
81
88
|
end
|
|
82
89
|
math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'b']]").each do |x|
|
|
83
|
-
x.wrap("<span style='font-style:normal;font-weight:bold;'></span>")
|
|
90
|
+
x.wrap("<span #{HTML_NS} style='font-style:normal;font-weight:bold;'></span>")
|
|
84
91
|
end
|
|
85
92
|
math.xpath(".//xmlns:r[xmlns:rPr/xmlns:scr[@m:val = 'monospace']]").each do |x|
|
|
86
93
|
to_plane1(x, :monospace)
|
|
@@ -128,20 +135,30 @@ module Html2Doc
|
|
|
128
135
|
docnamespaces = docxml.collect_namespaces
|
|
129
136
|
m = docxml.xpath("//*[local-name() = 'math']")
|
|
130
137
|
m.each_with_index do |x, i|
|
|
131
|
-
i
|
|
132
|
-
|
|
133
|
-
element = ooxml_cleanup(x, docnamespaces)
|
|
134
|
-
doc = Nokogiri::XML::Document::new
|
|
135
|
-
doc.root = element
|
|
136
|
-
ooxml = unitalic(esc_space(@xsltemplate.transform(doc))).to_s
|
|
137
|
-
.gsub(/<\?[^>]+>\s*/, "")
|
|
138
|
-
.gsub(/ xmlns(:[^=]+)?="[^"]+"/, "")
|
|
139
|
-
.gsub(%r{<(/)?(?!span)(?!em)([a-z])}, "<\\1m:\\2")
|
|
140
|
-
ooxml = uncenter(x, ooxml)
|
|
141
|
-
x.swap(ooxml)
|
|
138
|
+
progress_conv(i, 100, m.size, 500, "Math OOXML")
|
|
139
|
+
mathml_to_ooml1(x, docnamespaces)
|
|
142
140
|
end
|
|
143
141
|
end
|
|
144
142
|
|
|
143
|
+
# We need span and em not to be namespaced. Word can't deal with explicit
|
|
144
|
+
# namespaces.
|
|
145
|
+
# We will end up stripping them out again under Nokogiri 1.11, which correctly
|
|
146
|
+
# insists on inheriting namespace from parent.
|
|
147
|
+
def self.ooml_clean(xml)
|
|
148
|
+
xml.to_s
|
|
149
|
+
.gsub(/<\?[^>]+>\s*/, "")
|
|
150
|
+
.gsub(/ xmlns(:[^=]+)?="[^"]+"/, "")
|
|
151
|
+
.gsub(%r{<(/)?(?!span)(?!em)([a-z])}, "<\\1m:\\2")
|
|
152
|
+
end
|
|
153
|
+
|
|
154
|
+
def self.mathml_to_ooml1(xml, docnamespaces)
|
|
155
|
+
doc = Nokogiri::XML::Document::new
|
|
156
|
+
doc.root = ooxml_cleanup(xml, docnamespaces)
|
|
157
|
+
ooxml = ooml_clean(unitalic(esc_space(@xsltemplate.transform(doc))))
|
|
158
|
+
ooxml = uncenter(xml, ooxml)
|
|
159
|
+
xml.swap(ooxml)
|
|
160
|
+
end
|
|
161
|
+
|
|
145
162
|
# escape space as 2; we are removing any spaces generated by
|
|
146
163
|
# XML indentation
|
|
147
164
|
def self.esc_space(xml)
|
|
@@ -157,7 +174,7 @@ module Html2Doc
|
|
|
157
174
|
# left/right if parent is so tagged
|
|
158
175
|
def self.uncenter(math, ooxml)
|
|
159
176
|
alignnode = math.at(".//ancestor::*[@style][local-name() = 'p' or "\
|
|
160
|
-
|
|
177
|
+
"local-name() = 'div' or local-name() = 'td']/@style")
|
|
161
178
|
return ooxml unless alignnode && (math.next == nil && math.previous == nil)
|
|
162
179
|
|
|
163
180
|
%w(left right).each do |dir|
|
data/lib/html2doc/mime.rb
CHANGED
|
@@ -43,7 +43,7 @@ module Html2Doc
|
|
|
43
43
|
def self.mime_type(item)
|
|
44
44
|
types = MIME::Types.type_for(item)
|
|
45
45
|
type = types ? types.first.to_s : 'text/plain; charset="utf-8"'
|
|
46
|
-
type = type
|
|
46
|
+
type = %(#{type} charset="utf-8") if /^text/.match(type) && types
|
|
47
47
|
type
|
|
48
48
|
end
|
|
49
49
|
|
|
@@ -77,14 +77,14 @@ module Html2Doc
|
|
|
77
77
|
end
|
|
78
78
|
|
|
79
79
|
# max width for Word document is 400, max height is 680
|
|
80
|
-
def self.image_resize(
|
|
81
|
-
|
|
82
|
-
s = [
|
|
83
|
-
s =
|
|
84
|
-
return [nil, nil] if
|
|
85
|
-
|
|
86
|
-
s[1] = s[0] *
|
|
87
|
-
s[0] = s[1] *
|
|
80
|
+
def self.image_resize(img, path, maxheight, maxwidth)
|
|
81
|
+
realsize = ImageSize.path(path).size
|
|
82
|
+
s = [img["width"].to_i, img["height"].to_i]
|
|
83
|
+
s = realsize if s[0].zero? && s[1].zero?
|
|
84
|
+
return [nil, nil] if realsize.nil? || realsize[0].nil? || realsize[1].nil?
|
|
85
|
+
|
|
86
|
+
s[1] = s[0] * realsize[1] / realsize[0] if s[1].zero? && !s[0].zero?
|
|
87
|
+
s[0] = s[1] * realsize[0] / realsize[1] if s[0].zero? && !s[1].zero?
|
|
88
88
|
s = [(s[0] * maxheight / s[1]).ceil, maxheight] if s[1] > maxheight
|
|
89
89
|
s = [maxwidth, (s[1] * maxwidth / s[0]).ceil] if s[0] > maxwidth
|
|
90
90
|
s
|
|
@@ -100,16 +100,18 @@ module Html2Doc
|
|
|
100
100
|
warn "#{src}: SVG not supported" if /\.svg$/i.match?(src)
|
|
101
101
|
end
|
|
102
102
|
|
|
103
|
+
def self.localname(src, localdir)
|
|
104
|
+
%r{^([A-Z]:)?/}.match?(src) ? src : File.join(localdir, src)
|
|
105
|
+
end
|
|
106
|
+
|
|
103
107
|
# only processes locally stored images
|
|
104
108
|
def self.image_cleanup(docxml, dir, localdir)
|
|
105
109
|
docxml.traverse do |i|
|
|
106
110
|
next unless i.element? && %w(img v:imagedata).include?(i.name)
|
|
107
|
-
|
|
108
|
-
next if /^http/.match i["src"]
|
|
111
|
+
next if /^http/.match? i["src"]
|
|
109
112
|
next if %r{^data:(image|application)/[^;]+;base64}.match? i["src"]
|
|
110
113
|
|
|
111
|
-
local_filename =
|
|
112
|
-
File.join(localdir, i["src"])
|
|
114
|
+
local_filename = localname(i["src"], localdir)
|
|
113
115
|
new_filename = "#{mkuuid}#{File.extname(i['src'])}"
|
|
114
116
|
FileUtils.cp local_filename, File.join(dir, new_filename)
|
|
115
117
|
i["width"], i["height"] = image_resize(i, local_filename, 680, 400)
|
|
@@ -130,12 +132,9 @@ module Html2Doc
|
|
|
130
132
|
if a.size == 2 && !(/ src="https?:/.match a[1]) &&
|
|
131
133
|
!(%r{ src="data:(image|application)/[^;]+;base64}.match a[1])
|
|
132
134
|
m = / src=['"](?<src>[^"']+)['"]/.match a[1]
|
|
133
|
-
#warnsvg(m[:src])
|
|
134
135
|
m2 = /\.(?<suffix>[a-zA-Z_0-9]+)$/.match m[:src]
|
|
135
136
|
new_filename = "#{mkuuid}.#{m2[:suffix]}"
|
|
136
|
-
|
|
137
|
-
File.join(localdir, m[:src])
|
|
138
|
-
FileUtils.cp old_filename, File.join(dir, new_filename)
|
|
137
|
+
FileUtils.cp localname(m[:src], localdir), File.join(dir, new_filename)
|
|
139
138
|
a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='cid:#{new_filename}'")
|
|
140
139
|
end
|
|
141
140
|
a.join
|
data/lib/html2doc/notes.rb
CHANGED
|
@@ -56,19 +56,22 @@ module Html2Doc
|
|
|
56
56
|
|
|
57
57
|
set_footnote_link_attrs(elem, idx)
|
|
58
58
|
if elem.at("./span[@class = 'MsoFootnoteReference']")
|
|
59
|
-
elem
|
|
60
|
-
|
|
61
|
-
c.replace(FN)
|
|
62
|
-
else
|
|
63
|
-
c.wrap("<span class='MsoFootnoteReference'></span>")
|
|
64
|
-
end
|
|
65
|
-
end
|
|
66
|
-
else
|
|
67
|
-
elem.children = FN
|
|
59
|
+
process_footnote_link1(elem)
|
|
60
|
+
else elem.children = FN
|
|
68
61
|
end
|
|
69
62
|
footnote << transform_footnote_text(note)
|
|
70
63
|
end
|
|
71
64
|
|
|
65
|
+
def self.process_footnote_link1(elem)
|
|
66
|
+
elem.children.each do |c|
|
|
67
|
+
if c.name == "span" && c["class"] == "MsoFootnoteReference"
|
|
68
|
+
c.replace(FN)
|
|
69
|
+
else
|
|
70
|
+
c.wrap("<span class='MsoFootnoteReference'></span>")
|
|
71
|
+
end
|
|
72
|
+
end
|
|
73
|
+
end
|
|
74
|
+
|
|
72
75
|
def self.transform_footnote_text(note)
|
|
73
76
|
note["id"] = ""
|
|
74
77
|
note.xpath(".//div").each { |div| div.replace(div.children) }
|
data/lib/html2doc/version.rb
CHANGED
data/spec/html2doc_spec.rb
CHANGED
|
@@ -64,11 +64,11 @@ WORD_HDR_END = <<~HDR.freeze
|
|
|
64
64
|
</head>
|
|
65
65
|
HDR
|
|
66
66
|
|
|
67
|
-
def word_body(
|
|
67
|
+
def word_body(xml, footnote)
|
|
68
68
|
<<~BODY
|
|
69
69
|
<body>
|
|
70
|
-
#{
|
|
71
|
-
#{
|
|
70
|
+
#{xml}
|
|
71
|
+
#{footnote}</body></html>
|
|
72
72
|
BODY
|
|
73
73
|
end
|
|
74
74
|
|
|
@@ -317,26 +317,36 @@ RSpec.describe Html2Doc do
|
|
|
317
317
|
end
|
|
318
318
|
|
|
319
319
|
it "processes a stylesheet in an HTML document with an empty head" do
|
|
320
|
-
Html2Doc.process(html_input_empty_head(""),
|
|
320
|
+
Html2Doc.process(html_input_empty_head(""),
|
|
321
|
+
filename: "test", stylesheet: "lib/html2doc/wordstyle.css")
|
|
322
|
+
word_hdr_end = WORD_HDR_END
|
|
323
|
+
.sub(%(<meta name="Originator" content="Me"/>\n), "")
|
|
324
|
+
.sub("</style>\n</head>", "</style></head>")
|
|
321
325
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
322
326
|
.to match_fuzzy(<<~OUTPUT)
|
|
323
327
|
#{WORD_HDR.sub('<title>blank</title>', '')}
|
|
324
328
|
#{DEFAULT_STYLESHEET}
|
|
325
|
-
#{
|
|
329
|
+
#{word_hdr_end}
|
|
326
330
|
#{word_body('', '<div style="mso-element:footnote-list"/>')} #{WORD_FTR1}
|
|
327
331
|
OUTPUT
|
|
328
332
|
end
|
|
329
333
|
|
|
330
334
|
it "processes a header" do
|
|
331
|
-
Html2Doc.process(html_input(""),
|
|
335
|
+
Html2Doc.process(html_input(""),
|
|
336
|
+
filename: "test", header_file: "spec/header.html")
|
|
332
337
|
html = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
333
|
-
hdr = Base64.decode64(
|
|
334
|
-
|
|
335
|
-
|
|
338
|
+
hdr = Base64.decode64(
|
|
339
|
+
html
|
|
340
|
+
.sub(%r{^.*Content-Location: file:///C:/Doc/test_files/header.html}, "")
|
|
341
|
+
.sub(%r{^.*Content-Type: text/html charset="utf-8"}m, "")
|
|
342
|
+
.sub(%r{------=_NextPart_--.*$}m, ""),
|
|
343
|
+
).force_encoding("UTF-8")
|
|
336
344
|
# expect(hdr.gsub(/\xa0/, " ")).to match_fuzzy(HEADERHTML)
|
|
337
345
|
expect(HTMLEntities.new.encode(hdr, :hexadecimal)
|
|
338
|
-
|
|
339
|
-
|
|
346
|
+
.gsub(/</, "<").gsub(/>/, ">")
|
|
347
|
+
.gsub(/'/, "'").gsub(/"/, '"')
|
|
348
|
+
.gsub(/
/, "
").gsub(/
/, "\n"))
|
|
349
|
+
.to match_fuzzy(HEADERHTML)
|
|
340
350
|
expect(html.sub(%r{Content-ID: <header.html>.*$}m, ""))
|
|
341
351
|
.to match_fuzzy(<<~OUTPUT)
|
|
342
352
|
#{WORD_HDR} #{DEFAULT_STYLESHEET.gsub(/url\("[^"]+"\)/, 'url(cid:header.html)')}
|
|
@@ -345,7 +355,8 @@ RSpec.describe Html2Doc do
|
|
|
345
355
|
end
|
|
346
356
|
|
|
347
357
|
it "processes a header with an image" do
|
|
348
|
-
Html2Doc.process(html_input(""),
|
|
358
|
+
Html2Doc.process(html_input(""),
|
|
359
|
+
filename: "test", header_file: "spec/header_img.html")
|
|
349
360
|
doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
350
361
|
expect(doc).to match(%r{Content-Type: image/png})
|
|
351
362
|
expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
|
|
@@ -354,9 +365,13 @@ RSpec.describe Html2Doc do
|
|
|
354
365
|
it "processes a header with an image with absolute path" do
|
|
355
366
|
doc = File.read("spec/header_img.html", encoding: "utf-8")
|
|
356
367
|
File.open("spec/header_img1.html", "w:UTF-8") do |f|
|
|
357
|
-
f.write
|
|
368
|
+
f.write(
|
|
369
|
+
doc.sub(%r{spec/19160-6.png},
|
|
370
|
+
File.expand_path(File.join(File.dirname(__FILE__), "19160-6.png"))),
|
|
371
|
+
)
|
|
358
372
|
end
|
|
359
|
-
Html2Doc.process(html_input(""),
|
|
373
|
+
Html2Doc.process(html_input(""),
|
|
374
|
+
filename: "test", header_file: "spec/header_img1.html")
|
|
360
375
|
doc = guid_clean(File.read("test.doc", encoding: "utf-8"))
|
|
361
376
|
expect(doc).to match(%r{Content-Type: image/png})
|
|
362
377
|
expect(doc).to match(%r{iVBORw0KGgoAAAANSUhEUgAAA5cAAAN7CAYAAADRE24cAAAgAElEQVR4XuydB5gUxdaGC65gTogB})
|
|
@@ -375,43 +390,46 @@ RSpec.describe Html2Doc do
|
|
|
375
390
|
end
|
|
376
391
|
|
|
377
392
|
it "processes AsciiMath" do
|
|
378
|
-
Html2Doc.process(html_input(%[<div>{{sum_(i=1)^n i^3=((n(n+1))/2)^2 text("integer"))}}</div>]),
|
|
393
|
+
Html2Doc.process(html_input(%[<div>{{sum_(i=1)^n i^3=((n(n+1))/2)^2 text("integer"))}}</div>]),
|
|
394
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
379
395
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
380
396
|
.to match_fuzzy(<<~OUTPUT)
|
|
381
397
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
382
398
|
#{word_body(%{
|
|
383
|
-
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
|
|
399
|
+
<div><m:oMath>
|
|
400
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>"integer"</m:t></m:r><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>)</m:t></m:r></span>
|
|
401
|
+
</m:oMath>
|
|
402
|
+
</div>}, '<div style="mso-element:footnote-list"/>')}
|
|
387
403
|
#{WORD_FTR1}
|
|
388
404
|
OUTPUT
|
|
389
405
|
end
|
|
390
406
|
|
|
391
407
|
it "processes mstyle" do
|
|
392
|
-
Html2Doc.process(html_input(%[<div>{{bb (-log_2 (p_u)) bb "BB" bbb "BBB" cc "CC" bcc "BCC" tt "TT" fr "FR" bfr "BFR" sf "SF" bsf "BSFα" sfi "SFI" sfbi "SFBIα" bii "BII" ii "II"}}</div>]),
|
|
408
|
+
Html2Doc.process(html_input(%[<div>{{bb (-log_2 (p_u)) bb "BB" bbb "BBB" cc "CC" bcc "BCC" tt "TT" fr "FR" bfr "BFR" sf "SF" bsf "BSFα" sfi "SFI" sfbi "SFBIα" bii "BII" ii "II"}}</div>]),
|
|
409
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
393
410
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
394
411
|
.to match_fuzzy(<<~OUTPUT)
|
|
395
412
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
396
413
|
#{word_body(%{
|
|
397
|
-
|
|
398
|
-
|
|
399
|
-
|
|
400
|
-
|
|
414
|
+
<div><m:oMath>
|
|
415
|
+
<span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>−</m:t></m:r></span><m:sSub><m:e><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>log</m:t></m:r></span></m:e><m:sub><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>2</m:t></m:r></span></m:sub></m:sSub><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:sSub><m:e><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>p</m:t></m:r></span></m:e><m:sub><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:sty m:val="b"></m:sty></m:rPr><m:t>u</m:t></m:r></span></m:sub></m:sSub></m:e></m:d><span style="font-style:normal;font-weight:bold;"><m:r><m:rPr><m:nor></m:nor><m:sty m:val="b"></m:sty></m:rPr><m:t>BB</m:t></m:r></span><m:r><m:rPr><m:nor></m:nor><m:scr m:val="double-struck"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>𝔹𝔹𝔹</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="script"></m:scr></m:rPr><m:t>𝒞𝒞</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="script"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>𝓑𝓒𝓒</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="monospace"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>𝚃𝚃</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="fraktur"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>𝔉ℜ</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="fraktur"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>𝕭𝕱𝕽</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="p"></m:sty></m:rPr><m:t>𝖲𝖥</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="b"></m:sty></m:rPr><m:t>𝗕𝗦𝗙𝝰</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr></m:rPr><m:t>𝖲𝖥𝖨</m:t></m:r><m:r><m:rPr><m:nor></m:nor><m:scr m:val="sans-serif"></m:scr><m:sty m:val="bi"></m:sty></m:rPr><m:t>𝙎𝙁𝘽𝙄𝞪</m:t></m:r><span class="nostem" style="font-weight:bold;"><em></em><m:r><m:rPr><m:nor></m:nor><m:sty m:val="bi"></m:sty></m:rPr><m:t>BII</m:t></m:r></span><span class="nostem"><em></em><m:r><m:rPr><m:nor></m:nor><m:sty m:val="i"></m:sty></m:rPr><m:t>II</m:t></m:r></span>
|
|
416
|
+
</m:oMath>
|
|
417
|
+
</div>}, '<div style="mso-element:footnote-list"/>')}
|
|
401
418
|
#{WORD_FTR1}
|
|
402
419
|
OUTPUT
|
|
403
420
|
end
|
|
404
421
|
|
|
405
422
|
it "processes spaces in AsciiMath" do
|
|
406
|
-
Html2Doc.process(html_input(%[<div>{{text " integer ")}}</div>]),
|
|
423
|
+
Html2Doc.process(html_input(%[<div>{{text " integer ")}}</div>]),
|
|
424
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
407
425
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
408
426
|
.to match_fuzzy(<<~OUTPUT)
|
|
409
427
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
410
428
|
#{word_body('
|
|
411
|
-
|
|
412
|
-
|
|
413
|
-
|
|
414
|
-
|
|
429
|
+
<div><m:oMath>
|
|
430
|
+
<m:r><m:t>text</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t> integer </m:t></m:r><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>)</m:t></m:r></span>
|
|
431
|
+
</m:oMath>
|
|
432
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
415
433
|
#{WORD_FTR1}
|
|
416
434
|
OUTPUT
|
|
417
435
|
end
|
|
@@ -419,14 +437,15 @@ RSpec.describe Html2Doc do
|
|
|
419
437
|
it "processes spaces in MathML mtext" do
|
|
420
438
|
Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
|
|
421
439
|
<mrow><mi>H</mi><mtext> original </mtext><mi>J</mi></mrow>
|
|
422
|
-
</math></div>"),
|
|
440
|
+
</math></div>"),
|
|
441
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
423
442
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
424
443
|
.to match_fuzzy(<<~OUTPUT)
|
|
425
444
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
426
445
|
#{word_body('<div><m:oMath>
|
|
427
|
-
|
|
428
|
-
|
|
429
|
-
|
|
446
|
+
<m:r><m:t>H</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t> original </m:t></m:r><m:r><m:t>J</m:t></m:r>
|
|
447
|
+
</m:oMath>
|
|
448
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
430
449
|
#{WORD_FTR1}
|
|
431
450
|
OUTPUT
|
|
432
451
|
end
|
|
@@ -439,58 +458,67 @@ RSpec.describe Html2Doc do
|
|
|
439
458
|
.to match_fuzzy(<<~OUTPUT)
|
|
440
459
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
441
460
|
#{word_body('<div><m:oMath>
|
|
442
|
-
|
|
443
|
-
|
|
444
|
-
|
|
461
|
+
<m:acc><m:accPr><m:chr m:val="^"></m:chr></m:accPr><m:e><m:r><m:t>p</m:t></m:r></m:e></m:acc>
|
|
462
|
+
</m:oMath>
|
|
463
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
445
464
|
#{WORD_FTR1}
|
|
446
465
|
OUTPUT
|
|
447
466
|
end
|
|
448
467
|
|
|
449
468
|
it "left-aligns AsciiMath" do
|
|
450
|
-
Html2Doc.process(html_input("<div style='text-align:left;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
469
|
+
Html2Doc.process(html_input("<div style='text-align:left;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
470
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
451
471
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
452
472
|
.to match_fuzzy(<<~OUTPUT)
|
|
453
473
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
454
474
|
#{word_body(%{
|
|
455
|
-
|
|
456
|
-
|
|
457
|
-
|
|
458
|
-
|
|
475
|
+
<div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"/></m:oMathParaPr><m:oMath>
|
|
476
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
|
|
477
|
+
</m:oMath>
|
|
478
|
+
</m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
|
|
459
479
|
#{WORD_FTR1}
|
|
460
480
|
OUTPUT
|
|
461
481
|
end
|
|
462
482
|
|
|
463
483
|
it "right-aligns AsciiMath" do
|
|
464
|
-
Html2Doc.process(html_input("<div style='text-align:right;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
484
|
+
Html2Doc.process(html_input("<div style='text-align:right;'>{{sum_(i=1)^n i^3=((n(n+1))/2)^2}}</div>"),
|
|
485
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
465
486
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
466
487
|
.to match_fuzzy(<<~OUTPUT)
|
|
467
488
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
468
489
|
#{word_body(%{
|
|
469
|
-
|
|
470
|
-
|
|
471
|
-
|
|
472
|
-
|
|
490
|
+
<div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"/></m:oMathParaPr><m:oMath>
|
|
491
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><span style="font-style:normal;"><m:r><m:rPr><m:sty m:val="p"></m:sty></m:rPr><m:t>=</m:t></m:r></span><m:sSup><m:e><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:d><m:dPr><m:sepChr m:val=","></m:sepChr></m:dPr><m:e><m:r><m:t>n+1</m:t></m:r></m:e></m:d></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f></m:e></m:d></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
|
|
492
|
+
</m:oMath>
|
|
493
|
+
</m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
|
|
473
494
|
#{WORD_FTR1}
|
|
474
495
|
OUTPUT
|
|
475
496
|
end
|
|
476
497
|
|
|
477
498
|
it "raises error in processing of broken AsciiMath" do
|
|
478
499
|
begin
|
|
479
|
-
expect
|
|
500
|
+
expect do
|
|
501
|
+
Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]),
|
|
502
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
503
|
+
end.to output('parsing: u_c = 6.6"unitsml(kHz)').to_stderr
|
|
480
504
|
rescue StandardError
|
|
481
505
|
end
|
|
482
|
-
expect
|
|
506
|
+
expect do
|
|
507
|
+
Html2Doc.process(html_input(%[<div style='text-align:right;'>{{u_c = 6.6"unitsml(kHz)}}</div>]),
|
|
508
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
509
|
+
end.to raise_error(StandardError)
|
|
483
510
|
end
|
|
484
511
|
|
|
485
512
|
it "wraps msup after munderover in MathML" do
|
|
486
513
|
Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
|
|
487
|
-
<munderover><mo>∑</mo><mrow><mi>i</mi><mo>=</mo><mn>0</mn></mrow><mrow><mi>n</mi></mrow></munderover><msup><mn>2</mn><mrow><mi>i</mi></mrow></msup></math></div>"),
|
|
514
|
+
<munderover><mo>∑</mo><mrow><mi>i</mi><mo>=</mo><mn>0</mn></mrow><mrow><mi>n</mi></mrow></munderover><msup><mn>2</mn><mrow><mi>i</mi></mrow></msup></math></div>"),
|
|
515
|
+
filename: "test", asciimathdelims: ["{{", "}}"])
|
|
488
516
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
489
517
|
.to match_fuzzy(<<~OUTPUT)
|
|
490
518
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
491
519
|
#{word_body('<div><m:oMath>
|
|
492
|
-
|
|
493
|
-
|
|
520
|
+
<m:nary><m:naryPr><m:chr m:val="∑"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=0</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>2</m:t></m:r></m:e><m:sup><m:r><m:t>i</m:t></m:r></m:sup></m:sSup></m:e></m:nary></m:oMath>
|
|
521
|
+
</div>', '<div style="mso-element:footnote-list"/>')}
|
|
494
522
|
#{WORD_FTR1}
|
|
495
523
|
OUTPUT
|
|
496
524
|
end
|
|
@@ -573,33 +601,43 @@ RSpec.describe Html2Doc do
|
|
|
573
601
|
|
|
574
602
|
it "resizes images with missing or auto sizes" do
|
|
575
603
|
image = { "src" => "spec/19160-8.jpg" }
|
|
576
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
604
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
605
|
+
.to eq [30, 100]
|
|
577
606
|
image["width"] = "20"
|
|
578
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
607
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
608
|
+
.to eq [20, 65]
|
|
579
609
|
image.delete("width")
|
|
580
610
|
image["height"] = "50"
|
|
581
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
611
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
612
|
+
.to eq [15, 50]
|
|
582
613
|
image.delete("height")
|
|
583
614
|
image["width"] = "500"
|
|
584
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
615
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
616
|
+
.to eq [30, 100]
|
|
585
617
|
image.delete("width")
|
|
586
618
|
image["height"] = "500"
|
|
587
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
619
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
620
|
+
.to eq [30, 100]
|
|
588
621
|
image["width"] = "20"
|
|
589
622
|
image["height"] = "auto"
|
|
590
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
623
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
624
|
+
.to eq [20, 65]
|
|
591
625
|
image["width"] = "auto"
|
|
592
626
|
image["height"] = "50"
|
|
593
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
627
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
628
|
+
.to eq [15, 50]
|
|
594
629
|
image["width"] = "500"
|
|
595
630
|
image["height"] = "auto"
|
|
596
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
631
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
632
|
+
.to eq [30, 100]
|
|
597
633
|
image["width"] = "auto"
|
|
598
634
|
image["height"] = "500"
|
|
599
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
635
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
636
|
+
.to eq [30, 100]
|
|
600
637
|
image["width"] = "auto"
|
|
601
638
|
image["height"] = "auto"
|
|
602
|
-
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
639
|
+
expect(Html2Doc.image_resize(image, "spec/19160-8.jpg", 100, 100))
|
|
640
|
+
.to eq [30, 100]
|
|
603
641
|
end
|
|
604
642
|
|
|
605
643
|
it "does not move images if they are external URLs" do
|
|
@@ -627,7 +665,8 @@ RSpec.describe Html2Doc do
|
|
|
627
665
|
|
|
628
666
|
# it "warns about SVG" do
|
|
629
667
|
# simple_body = '<img src="https://example.com/19160-6.svg">'
|
|
630
|
-
# expect{ Html2Doc.process(html_input(simple_body), filename: "test") }
|
|
668
|
+
# expect{ Html2Doc.process(html_input(simple_body), filename: "test") }
|
|
669
|
+
# .to output("https://example.com/19160-6.svg: SVG not supported\n").to_stderr
|
|
631
670
|
# end
|
|
632
671
|
|
|
633
672
|
it "processes epub:type footnotes" do
|
|
@@ -638,15 +677,15 @@ RSpec.describe Html2Doc do
|
|
|
638
677
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
639
678
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
640
679
|
.to match_fuzzy(<<~OUTPUT)
|
|
641
|
-
|
|
642
|
-
|
|
643
|
-
|
|
644
|
-
|
|
645
|
-
|
|
646
|
-
|
|
647
|
-
|
|
648
|
-
|
|
649
|
-
|
|
680
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
681
|
+
#{word_body('<div>This is a very simple
|
|
682
|
+
document<a epub:type="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a epub:type="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
683
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
684
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
685
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
686
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
687
|
+
</div>')}
|
|
688
|
+
#{WORD_FTR1}
|
|
650
689
|
OUTPUT
|
|
651
690
|
end
|
|
652
691
|
|
|
@@ -658,15 +697,15 @@ RSpec.describe Html2Doc do
|
|
|
658
697
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
659
698
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
660
699
|
.to match_fuzzy(<<~OUTPUT)
|
|
661
|
-
|
|
662
|
-
|
|
663
|
-
|
|
664
|
-
|
|
665
|
-
|
|
666
|
-
|
|
667
|
-
|
|
668
|
-
|
|
669
|
-
|
|
700
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
701
|
+
#{word_body('<div>This is a very simple
|
|
702
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
703
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
704
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
705
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
706
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
707
|
+
</div>')}
|
|
708
|
+
#{WORD_FTR1}
|
|
670
709
|
OUTPUT
|
|
671
710
|
end
|
|
672
711
|
|
|
@@ -678,15 +717,15 @@ RSpec.describe Html2Doc do
|
|
|
678
717
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
679
718
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
680
719
|
.to match_fuzzy(<<~OUTPUT)
|
|
681
|
-
|
|
682
|
-
|
|
683
|
-
|
|
684
|
-
|
|
685
|
-
|
|
686
|
-
|
|
687
|
-
|
|
688
|
-
|
|
689
|
-
|
|
720
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
721
|
+
#{word_body('<div>This is a very simple
|
|
722
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
723
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
724
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a>Footnote</p></div>
|
|
725
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
726
|
+
<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
727
|
+
</div>')}
|
|
728
|
+
#{WORD_FTR1}
|
|
690
729
|
OUTPUT
|
|
691
730
|
end
|
|
692
731
|
|
|
@@ -698,15 +737,15 @@ RSpec.describe Html2Doc do
|
|
|
698
737
|
Html2Doc.process(html_input(simple_body), filename: "test")
|
|
699
738
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
700
739
|
.to match_fuzzy(<<~OUTPUT)
|
|
701
|
-
|
|
702
|
-
|
|
703
|
-
|
|
704
|
-
|
|
705
|
-
|
|
706
|
-
|
|
707
|
-
|
|
708
|
-
|
|
709
|
-
|
|
740
|
+
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
741
|
+
#{word_body('<div>This is a very simple
|
|
742
|
+
document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
|
|
743
|
+
'<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
|
|
744
|
+
<p class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Footnote</p></div>
|
|
745
|
+
<div style="mso-element:footnote" id="ftn2">
|
|
746
|
+
<p class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
|
|
747
|
+
</div>')}
|
|
748
|
+
#{WORD_FTR1}
|
|
710
749
|
OUTPUT
|
|
711
750
|
end
|
|
712
751
|
|
|
@@ -715,13 +754,14 @@ RSpec.describe Html2Doc do
|
|
|
715
754
|
<div><ul id="0">
|
|
716
755
|
<li><div><p><ol id="1"><li><ul id="2"><li><p><ol id="3"><li><ol id="4"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li><div><ul id="5"><li>C</li></ul></div>
|
|
717
756
|
BODY
|
|
718
|
-
Html2Doc.process(html_input(simple_body),
|
|
757
|
+
Html2Doc.process(html_input(simple_body),
|
|
758
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
719
759
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
720
760
|
.to match_fuzzy(<<~OUTPUT)
|
|
721
761
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
722
762
|
#{word_body('<div>
|
|
723
|
-
|
|
724
|
-
|
|
763
|
+
<p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p><div><p style="mso-list:l1 level1 lfo2;" class="MsoListParagraphCxSpFirst">C</p></div>
|
|
764
|
+
</div>',
|
|
725
765
|
'<div style="mso-element:footnote-list"/>')}
|
|
726
766
|
#{WORD_FTR1}
|
|
727
767
|
OUTPUT
|
|
@@ -733,13 +773,14 @@ RSpec.describe Html2Doc do
|
|
|
733
773
|
<ol id="1"><li><div><p><ol id="2"><li><ul id="3"><li><p><ol id="4"><li><ol id="5"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol>
|
|
734
774
|
<ol id="6"><li><div><p><ol id="7"><li><ul id="8"><li><p><ol id="9"><li><ol id="10"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol></div>
|
|
735
775
|
BODY
|
|
736
|
-
Html2Doc.process(html_input(simple_body),
|
|
776
|
+
Html2Doc.process(html_input(simple_body),
|
|
777
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
737
778
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
738
779
|
.to match_fuzzy(<<~OUTPUT)
|
|
739
780
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
740
781
|
#{word_body('<div>
|
|
741
|
-
|
|
742
|
-
|
|
782
|
+
<p style="mso-list:l2 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p></p></p></p></div></p>
|
|
783
|
+
<p style="mso-list:l2 level1 lfo2;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo2;" class="MsoListParagraphCxSpFirst">A</p></p></p></p></div></p></div>',
|
|
743
784
|
'<div style="mso-element:footnote-list"/>')}
|
|
744
785
|
#{WORD_FTR1}
|
|
745
786
|
OUTPUT
|
|
@@ -754,16 +795,18 @@ RSpec.describe Html2Doc do
|
|
|
754
795
|
<div><ul class="other" id="10">
|
|
755
796
|
<li><div><p><ol id="11"><li><ul id="12"><li><p><ol id="13"><li><ol id="14"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
|
|
756
797
|
BODY
|
|
757
|
-
Html2Doc.process(html_input(simple_body),
|
|
798
|
+
Html2Doc.process(html_input(simple_body),
|
|
799
|
+
filename: "test",
|
|
800
|
+
liststyles: { ul: "l1", ol: "l2", steps: "l3" })
|
|
758
801
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
759
802
|
.to match_fuzzy(<<~OUTPUT)
|
|
760
803
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
761
804
|
#{word_body('<div>
|
|
762
|
-
|
|
763
|
-
|
|
764
|
-
|
|
765
|
-
|
|
766
|
-
|
|
805
|
+
<p style="mso-list:l3 level1 lfo2;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l3 level2 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l3 level4 lfo2;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l3 level5 lfo2;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>
|
|
806
|
+
<div>
|
|
807
|
+
<p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>
|
|
808
|
+
<div>
|
|
809
|
+
<p style="mso-list:l1 level1 lfo3;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo3;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo3;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo3;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>',
|
|
767
810
|
'<div style="mso-element:footnote-list"/>')}
|
|
768
811
|
#{WORD_FTR1}
|
|
769
812
|
OUTPUT
|
|
@@ -776,14 +819,15 @@ RSpec.describe Html2Doc do
|
|
|
776
819
|
<p id="b"/>
|
|
777
820
|
</div>
|
|
778
821
|
BODY
|
|
779
|
-
Html2Doc.process(html_input(simple_body),
|
|
822
|
+
Html2Doc.process(html_input(simple_body),
|
|
823
|
+
filename: "test", liststyles: { ul: "l1", ol: "l2" })
|
|
780
824
|
expect(guid_clean(File.read("test.doc", encoding: "utf-8")))
|
|
781
825
|
.to match_fuzzy(<<~OUTPUT)
|
|
782
826
|
#{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
|
|
783
827
|
#{word_body('<div>
|
|
784
|
-
|
|
785
|
-
|
|
786
|
-
|
|
828
|
+
<p class="MsoNormal"><a name="a" id="a"></a>Hello</p>
|
|
829
|
+
<p class="MsoNormal"><a name="b" id="b"></a></p>
|
|
830
|
+
</div>',
|
|
787
831
|
'<div style="mso-element:footnote-list"/>')}
|
|
788
832
|
#{WORD_FTR1}
|
|
789
833
|
OUTPUT
|
|
@@ -791,12 +835,14 @@ RSpec.describe Html2Doc do
|
|
|
791
835
|
|
|
792
836
|
it "test image base64 image encoding" do
|
|
793
837
|
simple_body = '<img src="19160-6.png">'
|
|
794
|
-
Html2Doc.process(html_input(simple_body),
|
|
838
|
+
Html2Doc.process(html_input(simple_body),
|
|
839
|
+
filename: "spec/test", debug: true)
|
|
795
840
|
testdoc = File.read("spec/test.doc", encoding: "utf-8")
|
|
796
841
|
base64_image = testdoc[/image\/png\n\n(.*?)\n\n----/m, 1].gsub!("\n", "")
|
|
797
842
|
base64_image_basename = testdoc[%r{Content-ID: <([0-9a-z\-]+)\.png}m, 1]
|
|
798
843
|
doc_bin_image = Base64.strict_decode64(base64_image)
|
|
799
|
-
file_bin_image = IO
|
|
844
|
+
file_bin_image = IO
|
|
845
|
+
.read("spec/test_files/#{base64_image_basename}.png", mode: "rb")
|
|
800
846
|
expect(doc_bin_image).to eq file_bin_image
|
|
801
847
|
FileUtils.rm_rf %w[spec/test_files spec/test.doc spec/test.htm]
|
|
802
848
|
end
|
metadata
CHANGED
|
@@ -1,15 +1,29 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html2doc
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.1.
|
|
4
|
+
version: 1.1.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2021-05-
|
|
11
|
+
date: 2021-05-24 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: asciimath
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: 2.0.2
|
|
20
|
+
type: :runtime
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: 2.0.2
|
|
13
27
|
- !ruby/object:Gem::Dependency
|
|
14
28
|
name: htmlentities
|
|
15
29
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -58,30 +72,30 @@ dependencies:
|
|
|
58
72
|
requirements:
|
|
59
73
|
- - "~>"
|
|
60
74
|
- !ruby/object:Gem::Version
|
|
61
|
-
version: 1.10
|
|
75
|
+
version: '1.10'
|
|
62
76
|
type: :runtime
|
|
63
77
|
prerelease: false
|
|
64
78
|
version_requirements: !ruby/object:Gem::Requirement
|
|
65
79
|
requirements:
|
|
66
80
|
- - "~>"
|
|
67
81
|
- !ruby/object:Gem::Version
|
|
68
|
-
version: 1.10
|
|
82
|
+
version: '1.10'
|
|
69
83
|
- !ruby/object:Gem::Dependency
|
|
70
|
-
name:
|
|
84
|
+
name: plane1converter
|
|
71
85
|
requirement: !ruby/object:Gem::Requirement
|
|
72
86
|
requirements:
|
|
73
|
-
- - "
|
|
87
|
+
- - "~>"
|
|
74
88
|
- !ruby/object:Gem::Version
|
|
75
|
-
version:
|
|
89
|
+
version: 0.0.1
|
|
76
90
|
type: :runtime
|
|
77
91
|
prerelease: false
|
|
78
92
|
version_requirements: !ruby/object:Gem::Requirement
|
|
79
93
|
requirements:
|
|
80
|
-
- - "
|
|
94
|
+
- - "~>"
|
|
81
95
|
- !ruby/object:Gem::Version
|
|
82
|
-
version:
|
|
96
|
+
version: 0.0.1
|
|
83
97
|
- !ruby/object:Gem::Dependency
|
|
84
|
-
name:
|
|
98
|
+
name: thread_safe
|
|
85
99
|
requirement: !ruby/object:Gem::Requirement
|
|
86
100
|
requirements:
|
|
87
101
|
- - ">="
|
|
@@ -95,33 +109,19 @@ dependencies:
|
|
|
95
109
|
- !ruby/object:Gem::Version
|
|
96
110
|
version: '0'
|
|
97
111
|
- !ruby/object:Gem::Dependency
|
|
98
|
-
name:
|
|
99
|
-
requirement: !ruby/object:Gem::Requirement
|
|
100
|
-
requirements:
|
|
101
|
-
- - "~>"
|
|
102
|
-
- !ruby/object:Gem::Version
|
|
103
|
-
version: 2.0.2
|
|
104
|
-
type: :runtime
|
|
105
|
-
prerelease: false
|
|
106
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
107
|
-
requirements:
|
|
108
|
-
- - "~>"
|
|
109
|
-
- !ruby/object:Gem::Version
|
|
110
|
-
version: 2.0.2
|
|
111
|
-
- !ruby/object:Gem::Dependency
|
|
112
|
-
name: plane1converter
|
|
112
|
+
name: uuidtools
|
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
|
114
114
|
requirements:
|
|
115
|
-
- - "
|
|
115
|
+
- - ">="
|
|
116
116
|
- !ruby/object:Gem::Version
|
|
117
|
-
version: 0
|
|
117
|
+
version: '0'
|
|
118
118
|
type: :runtime
|
|
119
119
|
prerelease: false
|
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
|
121
121
|
requirements:
|
|
122
|
-
- - "
|
|
122
|
+
- - ">="
|
|
123
123
|
- !ruby/object:Gem::Version
|
|
124
|
-
version: 0
|
|
124
|
+
version: '0'
|
|
125
125
|
- !ruby/object:Gem::Dependency
|
|
126
126
|
name: byebug
|
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -207,61 +207,61 @@ dependencies:
|
|
|
207
207
|
- !ruby/object:Gem::Version
|
|
208
208
|
version: '3.6'
|
|
209
209
|
- !ruby/object:Gem::Dependency
|
|
210
|
-
name:
|
|
210
|
+
name: rspec-match_fuzzy
|
|
211
211
|
requirement: !ruby/object:Gem::Requirement
|
|
212
212
|
requirements:
|
|
213
213
|
- - "~>"
|
|
214
214
|
- !ruby/object:Gem::Version
|
|
215
|
-
version: 1.
|
|
215
|
+
version: 0.1.3
|
|
216
216
|
type: :development
|
|
217
217
|
prerelease: false
|
|
218
218
|
version_requirements: !ruby/object:Gem::Requirement
|
|
219
219
|
requirements:
|
|
220
220
|
- - "~>"
|
|
221
221
|
- !ruby/object:Gem::Version
|
|
222
|
-
version: 1.
|
|
222
|
+
version: 0.1.3
|
|
223
223
|
- !ruby/object:Gem::Dependency
|
|
224
|
-
name:
|
|
224
|
+
name: rubocop
|
|
225
225
|
requirement: !ruby/object:Gem::Requirement
|
|
226
226
|
requirements:
|
|
227
227
|
- - "~>"
|
|
228
228
|
- !ruby/object:Gem::Version
|
|
229
|
-
version:
|
|
229
|
+
version: 1.5.2
|
|
230
230
|
type: :development
|
|
231
231
|
prerelease: false
|
|
232
232
|
version_requirements: !ruby/object:Gem::Requirement
|
|
233
233
|
requirements:
|
|
234
234
|
- - "~>"
|
|
235
235
|
- !ruby/object:Gem::Version
|
|
236
|
-
version:
|
|
236
|
+
version: 1.5.2
|
|
237
237
|
- !ruby/object:Gem::Dependency
|
|
238
|
-
name:
|
|
238
|
+
name: simplecov
|
|
239
239
|
requirement: !ruby/object:Gem::Requirement
|
|
240
240
|
requirements:
|
|
241
241
|
- - "~>"
|
|
242
242
|
- !ruby/object:Gem::Version
|
|
243
|
-
version: '0.
|
|
243
|
+
version: '0.15'
|
|
244
244
|
type: :development
|
|
245
245
|
prerelease: false
|
|
246
246
|
version_requirements: !ruby/object:Gem::Requirement
|
|
247
247
|
requirements:
|
|
248
248
|
- - "~>"
|
|
249
249
|
- !ruby/object:Gem::Version
|
|
250
|
-
version: '0.
|
|
250
|
+
version: '0.15'
|
|
251
251
|
- !ruby/object:Gem::Dependency
|
|
252
|
-
name:
|
|
252
|
+
name: timecop
|
|
253
253
|
requirement: !ruby/object:Gem::Requirement
|
|
254
254
|
requirements:
|
|
255
255
|
- - "~>"
|
|
256
256
|
- !ruby/object:Gem::Version
|
|
257
|
-
version: 0.
|
|
257
|
+
version: '0.9'
|
|
258
258
|
type: :development
|
|
259
259
|
prerelease: false
|
|
260
260
|
version_requirements: !ruby/object:Gem::Requirement
|
|
261
261
|
requirements:
|
|
262
262
|
- - "~>"
|
|
263
263
|
- !ruby/object:Gem::Version
|
|
264
|
-
version: 0.
|
|
264
|
+
version: '0.9'
|
|
265
265
|
description: |
|
|
266
266
|
Convert HTML document to Microsoft Word document.
|
|
267
267
|
|