html2doc 1.5.3 → 1.5.5
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/lib/html2doc/base.rb +17 -94
- data/lib/html2doc/mime.rb +91 -15
- data/lib/html2doc/version.rb +1 -1
- data/lib/html2doc/xml.rb +83 -0
- data/lib/html2doc.rb +1 -0
- metadata +3 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 46856bf56ad5dd95f8f5781dc11049bb4600060c28c49715a262837ece8028bf
|
|
4
|
+
data.tar.gz: 866ba19867f233b45aeee436df719679623d671902b30476b61952f7a6357e1f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b949f47c356437ce418f65ce7fd1c497648d0d0e960fe1e05d7318d280ddf6de23ddad8e5ab94a18f447b3eaba948b2a4db69ca2d00f0dcfebd692933a64c1da
|
|
7
|
+
data.tar.gz: 953999bd39aa1c1b6a0e1a34c939dcbdba01242c898f5a587eab546b4c9a4578e8051c9c68b49900390fcb3ab5d2de4ad6f0f1bce1af5a8ee6e7bd4daf300966
|
data/lib/html2doc/base.rb
CHANGED
|
@@ -30,8 +30,7 @@ class Html2Doc
|
|
|
30
30
|
end
|
|
31
31
|
|
|
32
32
|
def process_header(headerfile)
|
|
33
|
-
|
|
34
|
-
|
|
33
|
+
headerfile.nil? and return
|
|
35
34
|
doc = File.read(headerfile, encoding: "utf-8")
|
|
36
35
|
doc = header_image_cleanup(doc, @dir1, @filename,
|
|
37
36
|
File.dirname(@filename))
|
|
@@ -66,6 +65,7 @@ class Html2Doc
|
|
|
66
65
|
end
|
|
67
66
|
|
|
68
67
|
def cleanup(docxml)
|
|
68
|
+
locate_landscape(docxml)
|
|
69
69
|
namespace(docxml.root)
|
|
70
70
|
image_cleanup(docxml, @dir1, @imagedir)
|
|
71
71
|
mathml_to_ooml(docxml)
|
|
@@ -76,76 +76,11 @@ class Html2Doc
|
|
|
76
76
|
docxml
|
|
77
77
|
end
|
|
78
78
|
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
<body> </body> </html>
|
|
85
|
-
HERE
|
|
86
|
-
|
|
87
|
-
def to_xhtml(xml)
|
|
88
|
-
xml.gsub!(/<\?xml[^>]*>/, "")
|
|
89
|
-
unless /<!DOCTYPE /.match? xml
|
|
90
|
-
xml = '<!DOCTYPE html SYSTEM
|
|
91
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml
|
|
92
|
-
end
|
|
93
|
-
xml = xml.gsub(/<!--\s*\[([^\]]+)\]>/, "<!-- MSWORD-COMMENT \\1 -->")
|
|
94
|
-
.gsub(/<!\s*\[endif\]\s*-->/, "<!-- MSWORD-COMMENT-END -->")
|
|
95
|
-
Nokogiri::XML.parse(xml)
|
|
96
|
-
end
|
|
97
|
-
|
|
98
|
-
DOCTYPE = <<~"DOCTYPE".freeze
|
|
99
|
-
<!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
100
|
-
DOCTYPE
|
|
101
|
-
|
|
102
|
-
def from_xhtml(xml)
|
|
103
|
-
xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "")
|
|
104
|
-
.sub(DOCTYPE, "").gsub(%{ />}, "/>")
|
|
105
|
-
.gsub(/<!-- MSWORD-COMMENT (.+?) -->/, "<!--[\\1]>")
|
|
106
|
-
.gsub(/<!-- MSWORD-COMMENT-END -->/, "<![endif]-->")
|
|
107
|
-
.gsub("\n-->\n", "\n-->\n")
|
|
108
|
-
end
|
|
109
|
-
|
|
110
|
-
def msword_fix(doc)
|
|
111
|
-
# brain damage in MSWord parser
|
|
112
|
-
doc.gsub!(%r{<w:DoNotOptimizeForBrowser></w:DoNotOptimizeForBrowser>},
|
|
113
|
-
"<w:DoNotOptimizeForBrowser/>")
|
|
114
|
-
doc.gsub!(%r{<span style="mso-special-character:footnote"/>},
|
|
115
|
-
'<span style="mso-special-character:footnote"></span>')
|
|
116
|
-
doc.gsub!(%r{<div style="mso-element:footnote-list"></div>},
|
|
117
|
-
'<div style="mso-element:footnote-list"/>')
|
|
118
|
-
doc.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
|
|
119
|
-
doc.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
|
|
120
|
-
doc.gsub!(%r{<meta http-equiv="Content-Type"},
|
|
121
|
-
"<meta http-equiv=Content-Type")
|
|
122
|
-
doc.gsub!(%r{></m:jc>}, "/>")
|
|
123
|
-
doc.gsub!(%r{></v:stroke>}, "/>")
|
|
124
|
-
doc.gsub!(%r{></v:f>}, "/>")
|
|
125
|
-
doc.gsub!(%r{></v:path>}, "/>")
|
|
126
|
-
doc.gsub!(%r{></o:lock>}, "/>")
|
|
127
|
-
doc.gsub!(%r{></v:imagedata>}, "/>")
|
|
128
|
-
doc.gsub!(%r{></w:wrap>}, "/>")
|
|
129
|
-
doc.gsub!(%r{<(/)?m:(span|em)\b}, "<\\1\\2")
|
|
130
|
-
doc.gsub!(%r{&tab;|&tab;},
|
|
131
|
-
'<span style="mso-tab-count:1">  </span>')
|
|
132
|
-
doc.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
|
|
133
|
-
a.size > 2 and a[2] = a[2].gsub(/>\s+</, "><")
|
|
134
|
-
a
|
|
135
|
-
end.join
|
|
136
|
-
end
|
|
137
|
-
|
|
138
|
-
PRINT_VIEW = <<~XML.freeze
|
|
139
|
-
|
|
140
|
-
<xml>
|
|
141
|
-
<w:WordDocument>
|
|
142
|
-
<w:View>Print</w:View>
|
|
143
|
-
<w:Zoom>100</w:Zoom>
|
|
144
|
-
<w:DoNotOptimizeForBrowser/>
|
|
145
|
-
</w:WordDocument>
|
|
146
|
-
</xml>
|
|
147
|
-
<meta http-equiv='Content-Type' content="text/html; charset=utf-8"/>
|
|
148
|
-
XML
|
|
79
|
+
def locate_landscape(_docxml)
|
|
80
|
+
css = read_stylesheet(@stylesheet)
|
|
81
|
+
@landscape = css.scan(/div\.\S+\s+\{\s*page:\s*[^;]+L;\s*\}/m)
|
|
82
|
+
.map { |e| e.sub(/^div\.(\S+).*$/m, "\\1") }
|
|
83
|
+
end
|
|
149
84
|
|
|
150
85
|
def define_head1(docxml, _dir)
|
|
151
86
|
docxml.xpath("//*[local-name() = 'head']").each do |h|
|
|
@@ -168,18 +103,21 @@ class Html2Doc
|
|
|
168
103
|
end
|
|
169
104
|
|
|
170
105
|
def stylesheet(_filename, _header_filename, cssname)
|
|
171
|
-
|
|
172
|
-
cssname = File.join(File.dirname(__FILE__), "wordstyle.css")
|
|
173
|
-
stylesheet = File.read(cssname, encoding: "UTF-8")
|
|
106
|
+
stylesheet = read_stylesheet(cssname)
|
|
174
107
|
xml = Nokogiri::XML("<style/>")
|
|
175
108
|
# s = Nokogiri::XML::CDATA.new(xml, "\n#{stylesheet}\n")
|
|
176
109
|
# xml.children.first << Nokogiri::XML::Comment.new(xml, s)
|
|
177
110
|
xml.children.first << Nokogiri::XML::CDATA
|
|
178
111
|
.new(xml, "\n<!--\n#{stylesheet}\n-->\n")
|
|
179
|
-
|
|
180
112
|
xml.root.to_s
|
|
181
113
|
end
|
|
182
114
|
|
|
115
|
+
def read_stylesheet(cssname)
|
|
116
|
+
(cssname.nil? || cssname.empty?) and
|
|
117
|
+
cssname = File.join(File.dirname(__FILE__), "wordstyle.css")
|
|
118
|
+
File.read(cssname, encoding: "UTF-8")
|
|
119
|
+
end
|
|
120
|
+
|
|
183
121
|
def define_head(docxml)
|
|
184
122
|
title = docxml.at("//*[local-name() = 'head']/*[local-name() = 'title']")
|
|
185
123
|
head = docxml.at("//*[local-name() = 'head']")
|
|
@@ -195,30 +133,15 @@ class Html2Doc
|
|
|
195
133
|
head.add_child css
|
|
196
134
|
elsif title.nil?
|
|
197
135
|
head.children.first.add_previous_sibling css
|
|
198
|
-
else
|
|
199
|
-
title.add_next_sibling css
|
|
136
|
+
else title.add_next_sibling css
|
|
200
137
|
end
|
|
201
138
|
end
|
|
202
139
|
|
|
203
|
-
def namespace(root)
|
|
204
|
-
{
|
|
205
|
-
o: "urn:schemas-microsoft-com:office:office",
|
|
206
|
-
w: "urn:schemas-microsoft-com:office:word",
|
|
207
|
-
v: "urn:schemas-microsoft-com:vml",
|
|
208
|
-
m: "http://schemas.microsoft.com/office/2004/12/omml",
|
|
209
|
-
}.each { |k, v| root.add_namespace_definition(k.to_s, v) }
|
|
210
|
-
end
|
|
211
|
-
|
|
212
|
-
def rootnamespace(root)
|
|
213
|
-
root.add_namespace(nil, "http://www.w3.org/TR/REC-html40")
|
|
214
|
-
end
|
|
215
|
-
|
|
216
140
|
def bookmarks(docxml)
|
|
217
141
|
docxml.xpath("//*[@id][not(@name)][not(@style = 'mso-element:footnote')]")
|
|
218
142
|
.each do |x|
|
|
219
|
-
|
|
220
|
-
%w(shapetype v:shapetype shape v:shape).include?(x.name)
|
|
221
|
-
|
|
143
|
+
(x["id"].empty? ||
|
|
144
|
+
%w(shapetype v:shapetype shape v:shape).include?(x.name)) and next
|
|
222
145
|
if x.children.empty? then x.add_child("<a name='#{x['id']}'></a>")
|
|
223
146
|
else x.children.first.previous = "<a name='#{x['id']}'></a>"
|
|
224
147
|
end
|
data/lib/html2doc/mime.rb
CHANGED
|
@@ -76,11 +76,9 @@ class Html2Doc
|
|
|
76
76
|
end
|
|
77
77
|
end
|
|
78
78
|
|
|
79
|
-
# max width for Word document is 400, max height is 680
|
|
80
79
|
def image_resize(img, path, maxheight, maxwidth)
|
|
81
80
|
s, realsize = get_image_size(img, path)
|
|
82
|
-
|
|
83
|
-
|
|
81
|
+
s[0] == nil && s[1] == nil and return s
|
|
84
82
|
if img.name == "svg" && !img["viewBox"]
|
|
85
83
|
img["viewBox"] = "0 0 #{s[0]} #{s[1]}"
|
|
86
84
|
end
|
|
@@ -115,21 +113,100 @@ class Html2Doc
|
|
|
115
113
|
|
|
116
114
|
# only processes locally stored images
|
|
117
115
|
def image_cleanup(docxml, dir, localdir)
|
|
116
|
+
maxheight, maxwidth = page_dimensions(docxml)
|
|
118
117
|
docxml.traverse do |i|
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
|
|
127
|
-
i["width"], i["height"] = image_resize(i, local_filename, 680, 400)
|
|
128
|
-
i["src"] = File.join(File.basename(dir), new_filename)
|
|
118
|
+
skip_image_cleanup?(i) and next
|
|
119
|
+
local_filename = rename_image(i, dir, localdir)
|
|
120
|
+
i["width"], i["height"] =
|
|
121
|
+
if landscape?(i)
|
|
122
|
+
image_resize(i, local_filename, maxwidth, maxheight)
|
|
123
|
+
else
|
|
124
|
+
image_resize(i, local_filename, maxheight, maxwidth)
|
|
125
|
+
end
|
|
129
126
|
end
|
|
130
127
|
docxml
|
|
131
128
|
end
|
|
132
129
|
|
|
130
|
+
def landscape?(img)
|
|
131
|
+
img.ancestors.each do |a|
|
|
132
|
+
a.name == "div" or next
|
|
133
|
+
@landscape.include?(a["class"]) and return true
|
|
134
|
+
end
|
|
135
|
+
false
|
|
136
|
+
end
|
|
137
|
+
|
|
138
|
+
def rename_image(img, dir, localdir)
|
|
139
|
+
local_filename = localname(img["src"], localdir)
|
|
140
|
+
new_filename = "#{mkuuid}#{File.extname(img['src'])}"
|
|
141
|
+
FileUtils.cp local_filename, File.join(dir, new_filename)
|
|
142
|
+
img["src"] = File.join(File.basename(dir), new_filename)
|
|
143
|
+
local_filename
|
|
144
|
+
end
|
|
145
|
+
|
|
146
|
+
def skip_image_cleanup?(img)
|
|
147
|
+
src = img["src"]
|
|
148
|
+
(img.element? && %w(img v:imagedata).include?(img.name)) or return true
|
|
149
|
+
(src.nil? || src.empty? || /^http/.match?(src) ||
|
|
150
|
+
%r{^data:(image|application)/[^;]+;base64}.match?(src)) and return true
|
|
151
|
+
false
|
|
152
|
+
end
|
|
153
|
+
|
|
154
|
+
# we are going to use the 2nd instance of @page in the Word CSS,
|
|
155
|
+
# skipping the cover page. Currently doesn't deal with Landscape.
|
|
156
|
+
# Scan both @stylesheet and docxml.to_xml (where @standardstylesheet has ended up)
|
|
157
|
+
# Allow 0.9 * height to fit caption
|
|
158
|
+
def page_dimensions(docxml)
|
|
159
|
+
stylesheet = read_stylesheet(@stylesheet)
|
|
160
|
+
page_size = find_page_size_in_doc(stylesheet, docxml.to_xml) or
|
|
161
|
+
return [680, 400]
|
|
162
|
+
m_size = /size:\s*(\S+)\s+(\S+)\s*;/.match(page_size) or return [680, 400]
|
|
163
|
+
m_marg = /margin:\s*(\S+)\s+(\S+)\s*(\S+)\s*(\S+)\s*;/.match(page_size) or
|
|
164
|
+
return [680, 400]
|
|
165
|
+
[0.9 * (units_to_px(m_size[2]) - units_to_px(m_marg[1]) - units_to_px(m_marg[3])),
|
|
166
|
+
units_to_px(m_size[1]) - units_to_px(m_marg[2]) - units_to_px(m_marg[4])]
|
|
167
|
+
rescue StandardError
|
|
168
|
+
[680, 400]
|
|
169
|
+
end
|
|
170
|
+
|
|
171
|
+
def find_page_size_in_doc(stylesheet, doc)
|
|
172
|
+
find_page_size(stylesheet, "WordSection2", false) ||
|
|
173
|
+
find_page_size(stylesheet, "WordSection3", false) ||
|
|
174
|
+
find_page_size(doc, "WordSection2", true) ||
|
|
175
|
+
find_page_size(doc, "WordSection3", true) ||
|
|
176
|
+
find_page_size(stylesheet, "", false) || find_page_size(doc, "", true)
|
|
177
|
+
end
|
|
178
|
+
|
|
179
|
+
# if in_xml, CSS is embedded in XML <style> tag
|
|
180
|
+
def find_page_size(stylesheet, klass, in_xml)
|
|
181
|
+
xml_found = false
|
|
182
|
+
found = false
|
|
183
|
+
ret = ""
|
|
184
|
+
stylesheet&.lines&.each do |l|
|
|
185
|
+
in_xml && l.include?("<style") and xml_found = true and found = false
|
|
186
|
+
in_xml && l.include?("</style>") and xml_found = false
|
|
187
|
+
/^\s*@page\s+#{klass}/.match?(l) and found = true
|
|
188
|
+
found && /^\s*\{?size:/.match?(l) and ret += l
|
|
189
|
+
found && /^\s*\{?margin:/.match?(l) and ret += l
|
|
190
|
+
if found && /}/.match?(l)
|
|
191
|
+
!ret.blank? && (!in_xml || xml_found) and return ret
|
|
192
|
+
ret = ""
|
|
193
|
+
found = false
|
|
194
|
+
end
|
|
195
|
+
end
|
|
196
|
+
nil
|
|
197
|
+
end
|
|
198
|
+
|
|
199
|
+
def units_to_px(measure)
|
|
200
|
+
m = /^(\S+)(pt|cm)/.match(measure)
|
|
201
|
+
ret = case m[2]
|
|
202
|
+
when "px" then (m[1].to_f * 0.75)
|
|
203
|
+
when "pt" then m[1].to_f
|
|
204
|
+
when "cm" then (m[1].to_f * 28.346456693)
|
|
205
|
+
when "in" then (m[1].to_f * 72)
|
|
206
|
+
end
|
|
207
|
+
ret.to_i
|
|
208
|
+
end
|
|
209
|
+
|
|
133
210
|
# do not parse the header through Nokogiri, since it will contain
|
|
134
211
|
# non-XML like <![if !supportFootnotes]>
|
|
135
212
|
def header_image_cleanup(doc, dir, filename, localdir)
|
|
@@ -155,8 +232,7 @@ class Html2Doc
|
|
|
155
232
|
f.write %{<xml xmlns:o="urn:schemas-microsoft-com:office:office">
|
|
156
233
|
<o:MainFile HRef="../#{filename}.htm"/>}
|
|
157
234
|
Dir.entries(dir).sort.each do |item|
|
|
158
|
-
|
|
159
|
-
|
|
235
|
+
(item == "." || item == ".." || /^\./.match(item)) and next
|
|
160
236
|
f.write %{ <o:File HRef="#{item}"/>\n}
|
|
161
237
|
end
|
|
162
238
|
f.write("</xml>\n")
|
data/lib/html2doc/version.rb
CHANGED
data/lib/html2doc/xml.rb
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
class Html2Doc
|
|
2
|
+
NOKOHEAD = <<~HERE.freeze
|
|
3
|
+
<!DOCTYPE html SYSTEM
|
|
4
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
5
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
6
|
+
<head> <title></title> <meta charset="UTF-8" /> </head>
|
|
7
|
+
<body> </body> </html>
|
|
8
|
+
HERE
|
|
9
|
+
|
|
10
|
+
def to_xhtml(xml)
|
|
11
|
+
xml.gsub!(/<\?xml[^>]*>/, "")
|
|
12
|
+
unless /<!DOCTYPE /.match? xml
|
|
13
|
+
xml = '<!DOCTYPE html SYSTEM
|
|
14
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml
|
|
15
|
+
end
|
|
16
|
+
xml = xml.gsub(/<!--\s*\[([^\]]+)\]>/, "<!-- MSWORD-COMMENT \\1 -->")
|
|
17
|
+
.gsub(/<!\s*\[endif\]\s*-->/, "<!-- MSWORD-COMMENT-END -->")
|
|
18
|
+
Nokogiri::XML.parse(xml)
|
|
19
|
+
end
|
|
20
|
+
|
|
21
|
+
DOCTYPE = <<~DOCTYPE.freeze
|
|
22
|
+
<!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
23
|
+
DOCTYPE
|
|
24
|
+
|
|
25
|
+
def from_xhtml(xml)
|
|
26
|
+
xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "")
|
|
27
|
+
.sub(DOCTYPE, "").gsub(%{ />}, "/>")
|
|
28
|
+
.gsub(/<!-- MSWORD-COMMENT (.+?) -->/, "<!--[\\1]>")
|
|
29
|
+
.gsub(/<!-- MSWORD-COMMENT-END -->/, "<![endif]-->")
|
|
30
|
+
.gsub("\n-->\n", "\n-->\n")
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
def msword_fix(doc)
|
|
34
|
+
# brain damage in MSWord parser
|
|
35
|
+
doc.gsub!(%r{<w:DoNotOptimizeForBrowser></w:DoNotOptimizeForBrowser>},
|
|
36
|
+
"<w:DoNotOptimizeForBrowser/>")
|
|
37
|
+
doc.gsub!(%r{<span style="mso-special-character:footnote"/>},
|
|
38
|
+
'<span style="mso-special-character:footnote"></span>')
|
|
39
|
+
doc.gsub!(%r{<div style="mso-element:footnote-list"></div>},
|
|
40
|
+
'<div style="mso-element:footnote-list"/>')
|
|
41
|
+
doc.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
|
|
42
|
+
doc.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
|
|
43
|
+
doc.gsub!(%r{<meta http-equiv="Content-Type"},
|
|
44
|
+
"<meta http-equiv=Content-Type")
|
|
45
|
+
doc.gsub!(%r{></m:jc>}, "/>")
|
|
46
|
+
doc.gsub!(%r{></v:stroke>}, "/>")
|
|
47
|
+
doc.gsub!(%r{></v:f>}, "/>")
|
|
48
|
+
doc.gsub!(%r{></v:path>}, "/>")
|
|
49
|
+
doc.gsub!(%r{></o:lock>}, "/>")
|
|
50
|
+
doc.gsub!(%r{></v:imagedata>}, "/>")
|
|
51
|
+
doc.gsub!(%r{></w:wrap>}, "/>")
|
|
52
|
+
doc.gsub!(%r{<(/)?m:(span|em)\b}, "<\\1\\2")
|
|
53
|
+
doc.gsub!(%r{&tab;|&tab;},
|
|
54
|
+
'<span style="mso-tab-count:1">  </span>')
|
|
55
|
+
doc.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
|
|
56
|
+
a.size > 2 and a[2] = a[2].gsub(/>\s+</, "><")
|
|
57
|
+
a
|
|
58
|
+
end.join
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
PRINT_VIEW = <<~XML.freeze
|
|
62
|
+
|
|
63
|
+
<xml>
|
|
64
|
+
<w:WordDocument>
|
|
65
|
+
<w:View>Print</w:View>
|
|
66
|
+
<w:Zoom>100</w:Zoom>
|
|
67
|
+
<w:DoNotOptimizeForBrowser/>
|
|
68
|
+
</w:WordDocument>
|
|
69
|
+
</xml>
|
|
70
|
+
<meta http-equiv='Content-Type' content="text/html; charset=utf-8"/>
|
|
71
|
+
XML
|
|
72
|
+
|
|
73
|
+
def namespace(root)
|
|
74
|
+
{ o: "urn:schemas-microsoft-com:office:office",
|
|
75
|
+
w: "urn:schemas-microsoft-com:office:word",
|
|
76
|
+
v: "urn:schemas-microsoft-com:vml",
|
|
77
|
+
m: "http://schemas.microsoft.com/office/2004/12/omml" }.each { |k, v| root.add_namespace_definition(k.to_s, v) }
|
|
78
|
+
end
|
|
79
|
+
|
|
80
|
+
def rootnamespace(root)
|
|
81
|
+
root.add_namespace(nil, "http://www.w3.org/TR/REC-html40")
|
|
82
|
+
end
|
|
83
|
+
end
|
data/lib/html2doc.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html2doc
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.5.
|
|
4
|
+
version: 1.5.5
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-
|
|
11
|
+
date: 2023-06-29 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: htmlentities
|
|
@@ -293,6 +293,7 @@ files:
|
|
|
293
293
|
- lib/html2doc/notes.rb
|
|
294
294
|
- lib/html2doc/version.rb
|
|
295
295
|
- lib/html2doc/wordstyle.css
|
|
296
|
+
- lib/html2doc/xml.rb
|
|
296
297
|
homepage: https://github.com/metanorma/html2doc
|
|
297
298
|
licenses:
|
|
298
299
|
- CC-BY-SA-3.0
|