ruby_powerpoint 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.rdoc +49 -0
- data/Rakefile +7 -0
- data/lib/ruby_powerpoint.rb +8 -0
- data/lib/ruby_powerpoint/presentation.rb +29 -0
- data/lib/ruby_powerpoint/slide.rb +27 -0
- data/lib/ruby_powerpoint/version.rb +3 -0
- data/ruby_powerpoint.gemspec +29 -0
- data/spec/fixtures/.~lock.sample.pptx# +1 -0
- data/spec/fixtures/invalid.xls +0 -0
- data/spec/fixtures/sample.pptx +0 -0
- data/spec/test_spec.rb +24 -0
- metadata +144 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 TODO: Write your name
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
= RubyPowerpoint -- Parser for Powerpoint(pptx) files.
|
2
|
+
|
3
|
+
RubyPowerpoint is a simple Ruby gem that can extract text from Powerpont(pptx) files.
|
4
|
+
|
5
|
+
|
6
|
+
== Installation
|
7
|
+
|
8
|
+
RubyPowerpont can be used from the command line or as part of a Ruby web framework. To install the gem using terminal, run the following command:
|
9
|
+
|
10
|
+
gem install ruby_powerpoint
|
11
|
+
|
12
|
+
To use it in Rails, add this line to your Gemfile:
|
13
|
+
|
14
|
+
gem "ruby_powerpoint"
|
15
|
+
|
16
|
+
|
17
|
+
== Basic Usage
|
18
|
+
RubyPowerpoint can simply parse a PowerPoint file(pptx) by extractng text from each slide:
|
19
|
+
|
20
|
+
require 'powerpint'
|
21
|
+
deck = RubyPowerpoint::Presentation.new "specs/fixtures/sample.ppts"
|
22
|
+
slide = deck.slides[0]
|
23
|
+
|
24
|
+
puts slde.content # => ["Prsentation Header", "Presentation Notes...", "12"]
|
25
|
+
|
26
|
+
|
27
|
+
== Contributing
|
28
|
+
|
29
|
+
Contributions are welcomed. You can fork a repository, add your code changes to the forked branch, ensure all existing unit tests pass, create new unit tests cover your new changes and finally create a pull request.
|
30
|
+
|
31
|
+
After forking and then cloning the repository locally, install Bundler and then use it
|
32
|
+
to install the development gem dependecies:
|
33
|
+
|
34
|
+
gem install bundler
|
35
|
+
bundle install
|
36
|
+
|
37
|
+
Once this is complete, you should be able to run the test suite:
|
38
|
+
|
39
|
+
rake
|
40
|
+
|
41
|
+
|
42
|
+
== Bug Reporting
|
43
|
+
|
44
|
+
Please use the {Issues}[https://github.com/pythonicrubyist/ruby_powerpoint/issues] page to report bugs or suggest new enhancements.
|
45
|
+
|
46
|
+
|
47
|
+
== License
|
48
|
+
|
49
|
+
RubyPowerpoint has been published under {MIT License}[https://github.com/pythonicrubyist/ruby_powerpoint/blob/master/LICENSE.txt]
|
data/Rakefile
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'zip/zipfilesystem'
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module RubyPowerpoint
|
5
|
+
|
6
|
+
class RubyPowerpoint::Presentation
|
7
|
+
|
8
|
+
attr_reader :files
|
9
|
+
|
10
|
+
def initialize path
|
11
|
+
raise 'Not a valid file format.' unless (['.pptx'].include? File.extname(path).downcase)
|
12
|
+
@files = Zip::ZipFile.open path
|
13
|
+
end
|
14
|
+
|
15
|
+
def slides
|
16
|
+
slides = Array.new
|
17
|
+
@files.each_with_index do |doc, i|
|
18
|
+
if doc.name.include? 'ppt/slides/slide'
|
19
|
+
slides.push RubyPowerpoint::Slide.new(self, doc.name, i)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
slides
|
23
|
+
end
|
24
|
+
|
25
|
+
def close
|
26
|
+
@files.close
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'zip/zipfilesystem'
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module RubyPowerpoint
|
5
|
+
class RubyPowerpoint::Slide
|
6
|
+
|
7
|
+
attr_reader :presentation,
|
8
|
+
:path,
|
9
|
+
:ndex
|
10
|
+
|
11
|
+
def initialize presentation, path, index
|
12
|
+
@presentation = presentation
|
13
|
+
@path = path
|
14
|
+
@index = index
|
15
|
+
end
|
16
|
+
|
17
|
+
def content
|
18
|
+
content = Array.new
|
19
|
+
doc = @presentation.files.file.open @path
|
20
|
+
xml = Nokogiri::XML::Document.parse doc
|
21
|
+
xml.xpath('//a:t').each do |node|
|
22
|
+
content.push node.text
|
23
|
+
end
|
24
|
+
content
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'ruby_powerpoint/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ruby_powerpoint"
|
8
|
+
spec.version = RubyPowerpoint::VERSION
|
9
|
+
spec.authors = ["pythonicrubyist"]
|
10
|
+
spec.email = ["pythonicrubyist@gmail.com"]
|
11
|
+
spec.description = %q{A Ruby gem that can extract text from PowerPoint(pptx) files.}
|
12
|
+
spec.summary = %q{A Ruby gem for Parsng text from PowerPoint(pptx) files.}
|
13
|
+
spec.homepage = "https://github.com/pythonicrubyist/ruby_powerpoint"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.required_ruby_version = '>= 1.9.2'
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
spec.add_development_dependency 'rspec', '~> 2.13.0'
|
26
|
+
|
27
|
+
spec.add_dependency 'nokogiri', '~> 1.6.0'
|
28
|
+
spec.add_dependency 'rubyzip', '~> 0.9.9'
|
29
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
,ramtin,ramtin-VirtualBox,26.06.2013 14:02,file:///home/ramtin/.config/libreoffice/3;
|
File without changes
|
Binary file
|
data/spec/test_spec.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'ruby_powerpoint'
|
2
|
+
|
3
|
+
describe 'RubyPowerpoint trying to parsing an invalid file.' do
|
4
|
+
it 'not open an XLS file successfully.' do
|
5
|
+
lambda { RubyPowerpoint::Presentation.new 'specs/fixtures/invalid.xls' }.should raise_error 'Not a valid file format.'
|
6
|
+
end
|
7
|
+
end
|
8
|
+
|
9
|
+
describe 'RubyPowerpoint parsing a sample PPTX file' do
|
10
|
+
before(:all) do
|
11
|
+
@deck = RubyPowerpoint::Presentation.new 'spec/fixtures/sample.pptx'
|
12
|
+
end
|
13
|
+
|
14
|
+
after(:all) do
|
15
|
+
@deck.close
|
16
|
+
end
|
17
|
+
|
18
|
+
it 'open a PPTX file successfully.' do
|
19
|
+
@deck.should_not be_nil
|
20
|
+
@deck.slides.should_not eql []
|
21
|
+
@deck.slides.first.content.should eql ["Some header here", "Some content here."]
|
22
|
+
@deck.slides.last.content.should eql ["WTF?", "What the hell s gong on?", "1234", "asdf", "34", "6"]
|
23
|
+
end
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,144 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruby_powerpoint
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- pythonicrubyist
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-06-26 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.3'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.3'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rspec
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: 2.13.0
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 2.13.0
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: nokogiri
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ~>
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: 1.6.0
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ~>
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: 1.6.0
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: rubyzip
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ~>
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: 0.9.9
|
86
|
+
type: :runtime
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ~>
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: 0.9.9
|
94
|
+
description: A Ruby gem that can extract text from PowerPoint(pptx) files.
|
95
|
+
email:
|
96
|
+
- pythonicrubyist@gmail.com
|
97
|
+
executables: []
|
98
|
+
extensions: []
|
99
|
+
extra_rdoc_files: []
|
100
|
+
files:
|
101
|
+
- .gitignore
|
102
|
+
- Gemfile
|
103
|
+
- LICENSE.txt
|
104
|
+
- README.rdoc
|
105
|
+
- Rakefile
|
106
|
+
- lib/ruby_powerpoint.rb
|
107
|
+
- lib/ruby_powerpoint/presentation.rb
|
108
|
+
- lib/ruby_powerpoint/slide.rb
|
109
|
+
- lib/ruby_powerpoint/version.rb
|
110
|
+
- ruby_powerpoint.gemspec
|
111
|
+
- spec/fixtures/.~lock.sample.pptx#
|
112
|
+
- spec/fixtures/invalid.xls
|
113
|
+
- spec/fixtures/sample.pptx
|
114
|
+
- spec/test_spec.rb
|
115
|
+
homepage: https://github.com/pythonicrubyist/ruby_powerpoint
|
116
|
+
licenses:
|
117
|
+
- MIT
|
118
|
+
post_install_message:
|
119
|
+
rdoc_options: []
|
120
|
+
require_paths:
|
121
|
+
- lib
|
122
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
123
|
+
none: false
|
124
|
+
requirements:
|
125
|
+
- - ! '>='
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
version: 1.9.2
|
128
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ! '>='
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
134
|
+
requirements: []
|
135
|
+
rubyforge_project:
|
136
|
+
rubygems_version: 1.8.25
|
137
|
+
signing_key:
|
138
|
+
specification_version: 3
|
139
|
+
summary: A Ruby gem for Parsng text from PowerPoint(pptx) files.
|
140
|
+
test_files:
|
141
|
+
- spec/fixtures/.~lock.sample.pptx#
|
142
|
+
- spec/fixtures/invalid.xls
|
143
|
+
- spec/fixtures/sample.pptx
|
144
|
+
- spec/test_spec.rb
|