docx 0.1.0
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.
- data/LICENSE.md +21 -0
- data/README.md +32 -0
- data/lib/docx.rb +5 -0
- data/lib/docx/containers.rb +2 -0
- data/lib/docx/containers/paragraph.rb +23 -0
- data/lib/docx/containers/text_run.rb +35 -0
- data/lib/docx/document.rb +27 -0
- data/lib/docx/parser.rb +49 -0
- data/lib/docx/version.rb +3 -0
- metadata +75 -0
data/LICENSE.md
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License
|
2
|
+
|
3
|
+
Copyright (c) Marcus Ortiz, http://marcusortiz.com
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# docx
|
2
|
+
|
3
|
+
a ruby library/gem for interacting with `.docx` files
|
4
|
+
|
5
|
+
## usage
|
6
|
+
|
7
|
+
### basic
|
8
|
+
|
9
|
+
``` ruby
|
10
|
+
require 'docx'
|
11
|
+
|
12
|
+
d = Docx::Document.open('example.docx')
|
13
|
+
d.each_paragraph do |p|
|
14
|
+
puts d
|
15
|
+
end
|
16
|
+
```
|
17
|
+
|
18
|
+
### advanced
|
19
|
+
|
20
|
+
``` ruby
|
21
|
+
require 'docx'
|
22
|
+
|
23
|
+
d = Docx::Document.open('example.docx')
|
24
|
+
d.each_paragraph do |p|
|
25
|
+
p.each_text_run do |run|
|
26
|
+
run.italicized?
|
27
|
+
run.bolded?
|
28
|
+
run.underlined?
|
29
|
+
run.formatting
|
30
|
+
run.text
|
31
|
+
end
|
32
|
+
end
|
data/lib/docx.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'docx/containers/text_run'
|
2
|
+
|
3
|
+
module Docx
|
4
|
+
module Containers
|
5
|
+
class Paragraph
|
6
|
+
attr_accessor :text_runs
|
7
|
+
|
8
|
+
def initialize(txt_runs)
|
9
|
+
@text_runs = txt_runs
|
10
|
+
end
|
11
|
+
|
12
|
+
def to_s
|
13
|
+
@text_runs.map(&:text).join('')
|
14
|
+
end
|
15
|
+
|
16
|
+
def each_text_run
|
17
|
+
@text_runs.each { |tr| yield(tr) }
|
18
|
+
end
|
19
|
+
|
20
|
+
alias_method :text, :to_s
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
module Docx
|
2
|
+
module Containers
|
3
|
+
class TextRun
|
4
|
+
DEFAULT_FORMATTING = {
|
5
|
+
italic: false,
|
6
|
+
bold: false,
|
7
|
+
underline: false
|
8
|
+
}
|
9
|
+
|
10
|
+
attr_reader :text
|
11
|
+
attr_reader :formatting
|
12
|
+
|
13
|
+
def initialize(attrs)
|
14
|
+
@text = attrs[:text] || ''
|
15
|
+
@formatting = attrs[:formatting] || DEFAULT_FORMATTING
|
16
|
+
end
|
17
|
+
|
18
|
+
def to_s
|
19
|
+
@text
|
20
|
+
end
|
21
|
+
|
22
|
+
def italicized?
|
23
|
+
@formatting[:italic]
|
24
|
+
end
|
25
|
+
|
26
|
+
def bolded?
|
27
|
+
@formatting[:bold]
|
28
|
+
end
|
29
|
+
|
30
|
+
def underlined?
|
31
|
+
@formatting[:underline]
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'docx/parser'
|
2
|
+
|
3
|
+
module Docx
|
4
|
+
class Document
|
5
|
+
attr_reader :paragraphs
|
6
|
+
|
7
|
+
def initialize(path)
|
8
|
+
Parser.new(File.expand_path(path)) do |p|
|
9
|
+
@paragraphs = p.paragraphs
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.open(path)
|
14
|
+
self.new(path)
|
15
|
+
end
|
16
|
+
|
17
|
+
def each_paragraph
|
18
|
+
@paragraphs.each { |p| yield(p) }
|
19
|
+
end
|
20
|
+
|
21
|
+
def to_s
|
22
|
+
@paragraphs.map(&:to_s).join("\n")
|
23
|
+
end
|
24
|
+
|
25
|
+
alias_method :text, :to_s
|
26
|
+
end
|
27
|
+
end
|
data/lib/docx/parser.rb
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'docx/containers'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'zip/zip'
|
4
|
+
|
5
|
+
module Docx
|
6
|
+
class Parser
|
7
|
+
def initialize(path)
|
8
|
+
@zip = Zip::ZipFile.open(path)
|
9
|
+
@xml = Nokogiri::XML(@zip.find_entry('word/document.xml').get_input_stream)
|
10
|
+
|
11
|
+
if block_given?
|
12
|
+
yield self
|
13
|
+
@zip.close
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
def paragraphs
|
18
|
+
@xml.xpath('//w:document//w:body//w:p').map { |p_node| parse_paragraph_from p_node }
|
19
|
+
end
|
20
|
+
|
21
|
+
private
|
22
|
+
|
23
|
+
def parse_paragraph_from(p_node)
|
24
|
+
Containers::Paragraph.new(parse_runs_from(p_node))
|
25
|
+
end
|
26
|
+
|
27
|
+
def parse_runs_from(p_node)
|
28
|
+
p_node.xpath('w:r').map do |r_node|
|
29
|
+
rpr_node = r_node.xpath('w:rPr')
|
30
|
+
Containers::TextRun.new({
|
31
|
+
text: parse_text_from(r_node),
|
32
|
+
formatting: parse_formatting_from(rpr_node)
|
33
|
+
})
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def parse_text_from(r_node)
|
38
|
+
r_node.xpath('w:t').map(&:text).join('')
|
39
|
+
end
|
40
|
+
|
41
|
+
def parse_formatting_from(rpr_node)
|
42
|
+
{
|
43
|
+
italic: !rpr_node.xpath('w:i').empty?,
|
44
|
+
bold: !rpr_node.xpath('w:b').empty?,
|
45
|
+
underline: !rpr_node.xpath('w:u').empty?
|
46
|
+
}
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
data/lib/docx/version.rb
ADDED
metadata
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: docx
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Marcus Ortiz
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-04-12 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: &70332799492380 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.5'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70332799492380
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: rubyzip
|
27
|
+
requirement: &70332799491720 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ~>
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0.9'
|
33
|
+
type: :runtime
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *70332799491720
|
36
|
+
description: a ruby library/gem for interacting with .docx files
|
37
|
+
email: mportiz08@gmail.com
|
38
|
+
executables: []
|
39
|
+
extensions: []
|
40
|
+
extra_rdoc_files: []
|
41
|
+
files:
|
42
|
+
- README.md
|
43
|
+
- LICENSE.md
|
44
|
+
- lib/docx/containers/paragraph.rb
|
45
|
+
- lib/docx/containers/text_run.rb
|
46
|
+
- lib/docx/containers.rb
|
47
|
+
- lib/docx/document.rb
|
48
|
+
- lib/docx/parser.rb
|
49
|
+
- lib/docx/version.rb
|
50
|
+
- lib/docx.rb
|
51
|
+
homepage: https://github.com/mportiz08/docx
|
52
|
+
licenses: []
|
53
|
+
post_install_message:
|
54
|
+
rdoc_options: []
|
55
|
+
require_paths:
|
56
|
+
- lib
|
57
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ! '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
63
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
64
|
+
none: false
|
65
|
+
requirements:
|
66
|
+
- - ! '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
requirements: []
|
70
|
+
rubyforge_project:
|
71
|
+
rubygems_version: 1.8.11
|
72
|
+
signing_key:
|
73
|
+
specification_version: 3
|
74
|
+
summary: a ruby library/gem for interacting with .docx files
|
75
|
+
test_files: []
|