doc2text 0.3.2 → 0.4.3
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 +5 -5
- data/bin/doc2text +43 -0
- data/lib/doc2text.rb +16 -5
- data/lib/doc2text/docx/docx.rb +31 -0
- data/lib/doc2text/docx/docx_xml_namespaces.rb +55 -0
- data/lib/doc2text/docx/markdown_docx_parser.rb +81 -0
- data/lib/doc2text/generic_xml_nodes.rb +78 -0
- data/lib/doc2text/odt/markdown_odt_parser.rb +81 -0
- data/lib/doc2text/odt/odt.rb +43 -0
- data/lib/doc2text/odt/odt_xml_namespaces.rb +240 -0
- data/lib/doc2text/pptx/markdown_pptx_parser.rb +55 -0
- data/lib/doc2text/pptx/pptx.rb +30 -0
- data/lib/doc2text/pptx/pptx_xml_namespaces.rb +55 -0
- data/lib/doc2text/resolution.rb +14 -0
- data/lib/doc2text/styles_parser.rb +28 -0
- data/lib/doc2text/xml_based_document_file.rb +48 -0
- metadata +26 -29
- data/lib/doc2text/content.rb +0 -25
- data/lib/doc2text/markdown_odt_parser.rb +0 -72
- data/lib/doc2text/odt.rb +0 -73
- data/lib/doc2text/odt_xml_namespaces.rb +0 -215
- data/lib/doc2text/odt_xml_node.rb +0 -99
@@ -1,99 +0,0 @@
|
|
1
|
-
module Doc2Text
|
2
|
-
module Odt
|
3
|
-
module XmlNodes
|
4
|
-
module Node
|
5
|
-
attr_reader :parent, :children, :attrs, :prefix, :name
|
6
|
-
attr_accessor :text
|
7
|
-
|
8
|
-
def self.create_node(prefix, name, parent = nil, attrs = [], markdown_odt_parser = nil)
|
9
|
-
begin
|
10
|
-
clazz = XmlNodes.const_get "#{titleize prefix}::#{titleize name}"
|
11
|
-
rescue NameError => e
|
12
|
-
# markdown_odt_parser.logger.warn "No such <#{prefix}:#{name}> found"
|
13
|
-
Generic.new(parent, attrs, prefix, name, markdown_odt_parser)
|
14
|
-
else
|
15
|
-
clazz.new(parent, attrs, prefix, name, markdown_odt_parser)
|
16
|
-
end
|
17
|
-
end
|
18
|
-
|
19
|
-
def self.titleize(tag)
|
20
|
-
tag.split('-').map(&:capitalize).join
|
21
|
-
end
|
22
|
-
|
23
|
-
def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
|
24
|
-
@parent, @attrs, @prefix, @name, @markdown_odt_parser = parent, attrs, prefix, name, markdown_odt_parser
|
25
|
-
@children = []
|
26
|
-
@has_text = false
|
27
|
-
end
|
28
|
-
|
29
|
-
def root?
|
30
|
-
!@parent
|
31
|
-
end
|
32
|
-
|
33
|
-
def has_text?
|
34
|
-
@has_text
|
35
|
-
end
|
36
|
-
|
37
|
-
def open
|
38
|
-
''
|
39
|
-
end
|
40
|
-
|
41
|
-
def close
|
42
|
-
''
|
43
|
-
end
|
44
|
-
|
45
|
-
def office_text?
|
46
|
-
false
|
47
|
-
end
|
48
|
-
|
49
|
-
def delete
|
50
|
-
return true unless @children
|
51
|
-
@children.each { |child| child.delete }
|
52
|
-
@children = []
|
53
|
-
end
|
54
|
-
|
55
|
-
def eql?(object)
|
56
|
-
return false unless object.is_a? Node
|
57
|
-
object.xml_name == xml_name
|
58
|
-
end
|
59
|
-
|
60
|
-
def generic?
|
61
|
-
instance_of? Node
|
62
|
-
end
|
63
|
-
|
64
|
-
def xml_name
|
65
|
-
"#{@prefix}:#{@name}"
|
66
|
-
end
|
67
|
-
|
68
|
-
def to_s
|
69
|
-
"#{xml_name} : #{attrs}"
|
70
|
-
end
|
71
|
-
|
72
|
-
def expand
|
73
|
-
expanded = "#{open}#{@children.map(&:expand).join}#{close}"
|
74
|
-
delete
|
75
|
-
expanded.clone
|
76
|
-
end
|
77
|
-
|
78
|
-
def not_enclosing?
|
79
|
-
!root? && parent.class.not_enclosing_tags && parent.class.not_enclosing_tags.find do |tag|
|
80
|
-
@prefix == parent.prefix && @name == tag
|
81
|
-
end
|
82
|
-
end
|
83
|
-
|
84
|
-
def self.included(base)
|
85
|
-
base.extend ClassMethods
|
86
|
-
end
|
87
|
-
|
88
|
-
module ClassMethods
|
89
|
-
attr_reader :not_enclosing_tags
|
90
|
-
|
91
|
-
def not_enclosing(tag)
|
92
|
-
@not_enclosing_tags ||= []
|
93
|
-
@not_enclosing_tags << tag
|
94
|
-
end
|
95
|
-
end
|
96
|
-
end
|
97
|
-
end
|
98
|
-
end
|
99
|
-
end
|