officex2str 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 +22 -0
- data/README.md +22 -0
- data/Rakefile +2 -0
- data/fixtures/sample.docx +0 -0
- data/fixtures/sample.pptx +0 -0
- data/fixtures/sample.xlsx +0 -0
- data/lib/officex2str/version.rb +3 -0
- data/lib/officex2str.rb +38 -0
- data/officex2str.gemspec +22 -0
- data/spec/officex2str_spec.rb +84 -0
- data/spec/spec_helper.rb +17 -0
- metadata +122 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Teruo Adachi
|
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.md
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# Officex2str
|
2
|
+
|
3
|
+
Convert office 2010 files to string.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'officex2str'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install officex2str
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Officex2str.convert("file_path")
|
22
|
+
|
data/Rakefile
ADDED
Binary file
|
Binary file
|
Binary file
|
data/lib/officex2str.rb
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'zipruby'
|
3
|
+
#require "officex2str/version"
|
4
|
+
|
5
|
+
module Officex2str
|
6
|
+
def self.convert(file_path)
|
7
|
+
archives = Zip::Archive.open(file_path) { |archive| archive.map(&:name) }
|
8
|
+
pages = self.pickup_pages(File.extname(file_path), archives)
|
9
|
+
xmls = self.extract_xmls(file_path, pages)
|
10
|
+
self.xml_to_str(xmls)
|
11
|
+
end
|
12
|
+
|
13
|
+
private
|
14
|
+
def self.pickup_pages extname, archives
|
15
|
+
case extname
|
16
|
+
when ".docx"
|
17
|
+
archives.select{|a| /^word\/document/ =~ a}
|
18
|
+
when ".xlsx"
|
19
|
+
archives.select{|a| /^xl\/worksheets\/sheet/ =~ a or /^xl\/sharedStrings/ =~ a or /^xl\/comments/ =~ a }
|
20
|
+
when ".pptx"
|
21
|
+
archives.select{|a| /^ppt\/slides\/slide/ =~ a}
|
22
|
+
else
|
23
|
+
nil
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.extract_xmls file_path, pages
|
28
|
+
xml_text = []
|
29
|
+
Zip::Archive.open(file_path) { |archive| pages.each{ |page| archive.fopen(page) do |f| xml_text << f.read end; } }
|
30
|
+
xml_text
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.xml_to_str xml_text
|
34
|
+
text = ""
|
35
|
+
xml_text.each{|xml_t| text << Nokogiri.XML(xml_t.toutf8, nil, 'utf8').to_str } unless xml_text.empty?
|
36
|
+
text
|
37
|
+
end
|
38
|
+
end
|
data/officex2str.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/officex2str/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["interu"]
|
6
|
+
gem.email = ["interu@sonicgarden.jp"]
|
7
|
+
gem.description = %q{convert office 2010 files to str}
|
8
|
+
gem.summary = %q{convert office 2010 files(docx,xlsx,pptx) to str}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "officex2str"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = Officex2str::VERSION
|
17
|
+
|
18
|
+
gem.add_development_dependency "rake", ["= 0.9.2"]
|
19
|
+
gem.add_development_dependency "nokogiri", [">= 1.4.7"]
|
20
|
+
gem.add_development_dependency "zipruby", ["= 0.3.6"]
|
21
|
+
|
22
|
+
end
|
@@ -0,0 +1,84 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
describe Officex2str do
|
5
|
+
context "#pickup_pages" do
|
6
|
+
subject do
|
7
|
+
archives = Zip::Archive.open(@file_path) { |archive| archive.map(&:name) }
|
8
|
+
Officex2str.send(:pickup_pages, File.extname(@file_path), archives).sort
|
9
|
+
end
|
10
|
+
context "extname is docx" do
|
11
|
+
before do
|
12
|
+
@file_path = "fixtures/sample.docx"
|
13
|
+
end
|
14
|
+
it { subject.should == ["word/document.xml"] }
|
15
|
+
end
|
16
|
+
|
17
|
+
context "extname is xlsx" do
|
18
|
+
before do
|
19
|
+
@file_path = "fixtures/sample.xlsx"
|
20
|
+
end
|
21
|
+
it { subject.should == ["xl/comments1.xml", "xl/sharedStrings.xml", "xl/worksheets/sheet1.xml", "xl/worksheets/sheet2.xml"] }
|
22
|
+
end
|
23
|
+
|
24
|
+
context "extname is pptx" do
|
25
|
+
before do
|
26
|
+
@file_path = "fixtures/sample.pptx"
|
27
|
+
end
|
28
|
+
it { subject.should == ["ppt/slides/slide1.xml", "ppt/slides/slide2.xml"] }
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
context "#convert" do
|
33
|
+
subject do
|
34
|
+
archives = Zip::Archive.open(@file_path) { |archive| archive.map(&:name) }
|
35
|
+
#pages = Officex2str.pickup_pages(File.extname(@file_path), archives)
|
36
|
+
pages = Officex2str.send(:pickup_pages, File.extname(@file_path), archives)
|
37
|
+
xmls = Officex2str.send(:extract_xmls, @file_path, pages)
|
38
|
+
Officex2str.convert(@file_path)
|
39
|
+
end
|
40
|
+
context "extname is xlsx" do
|
41
|
+
before do
|
42
|
+
@file_path = "fixtures/sample.xlsx"
|
43
|
+
end
|
44
|
+
it do
|
45
|
+
subject.should include("複数シート対応")
|
46
|
+
subject.should include("ソニックガーデン")
|
47
|
+
subject.should include("SONICGARDEN")
|
48
|
+
subject.should include("株式会社")
|
49
|
+
subject.should include("コメント")
|
50
|
+
subject.should_not include("sonicgarden")
|
51
|
+
subject.should_not include("sheet")
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
context "extname is docx" do
|
56
|
+
before do
|
57
|
+
@file_path = "fixtures/sample.docx"
|
58
|
+
end
|
59
|
+
it do
|
60
|
+
subject.should include("複数ページ対応")
|
61
|
+
subject.should include("ソニックガーデン")
|
62
|
+
subject.should include("テキストボックス")
|
63
|
+
subject.should_not include("sonicgarden")
|
64
|
+
subject.should_not include("sheet")
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
context "extname is pptx" do
|
69
|
+
before do
|
70
|
+
@file_path = "fixtures/sample.pptx"
|
71
|
+
end
|
72
|
+
it do
|
73
|
+
subject.should include("Aタイトル")
|
74
|
+
subject.should include("Aサブタイトル")
|
75
|
+
subject.should include("タイトルB")
|
76
|
+
subject.should include("テキストB")
|
77
|
+
subject.should include("テキストボックスB")
|
78
|
+
subject.should_not include("sonicgarden")
|
79
|
+
subject.should_not include("sheet")
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
end
|
84
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
2
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
3
|
+
|
4
|
+
require "rubygems"
|
5
|
+
require 'officex2str'
|
6
|
+
require "rspec"
|
7
|
+
require 'nokogiri'
|
8
|
+
require 'zipruby'
|
9
|
+
require 'kconv'
|
10
|
+
|
11
|
+
# Requires supporting files with custom matchers and macros, etc,
|
12
|
+
# in ./support/ and its subdirectories.
|
13
|
+
#Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
|
14
|
+
|
15
|
+
RSpec.configure do |config|
|
16
|
+
|
17
|
+
end
|
metadata
ADDED
@@ -0,0 +1,122 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: officex2str
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
version: 0.0.1
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- interu
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2012-07-18 00:00:00 +09:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rake
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - "="
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
segments:
|
29
|
+
- 0
|
30
|
+
- 9
|
31
|
+
- 2
|
32
|
+
version: 0.9.2
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: nokogiri
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
segments:
|
44
|
+
- 1
|
45
|
+
- 4
|
46
|
+
- 7
|
47
|
+
version: 1.4.7
|
48
|
+
type: :development
|
49
|
+
version_requirements: *id002
|
50
|
+
- !ruby/object:Gem::Dependency
|
51
|
+
name: zipruby
|
52
|
+
prerelease: false
|
53
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
54
|
+
none: false
|
55
|
+
requirements:
|
56
|
+
- - "="
|
57
|
+
- !ruby/object:Gem::Version
|
58
|
+
segments:
|
59
|
+
- 0
|
60
|
+
- 3
|
61
|
+
- 6
|
62
|
+
version: 0.3.6
|
63
|
+
type: :development
|
64
|
+
version_requirements: *id003
|
65
|
+
description: convert office 2010 files to str
|
66
|
+
email:
|
67
|
+
- interu@sonicgarden.jp
|
68
|
+
executables: []
|
69
|
+
|
70
|
+
extensions: []
|
71
|
+
|
72
|
+
extra_rdoc_files: []
|
73
|
+
|
74
|
+
files:
|
75
|
+
- .gitignore
|
76
|
+
- Gemfile
|
77
|
+
- LICENSE
|
78
|
+
- README.md
|
79
|
+
- Rakefile
|
80
|
+
- fixtures/sample.docx
|
81
|
+
- fixtures/sample.pptx
|
82
|
+
- fixtures/sample.xlsx
|
83
|
+
- lib/officex2str.rb
|
84
|
+
- lib/officex2str/version.rb
|
85
|
+
- officex2str.gemspec
|
86
|
+
- spec/officex2str_spec.rb
|
87
|
+
- spec/spec_helper.rb
|
88
|
+
has_rdoc: true
|
89
|
+
homepage: ""
|
90
|
+
licenses: []
|
91
|
+
|
92
|
+
post_install_message:
|
93
|
+
rdoc_options: []
|
94
|
+
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
none: false
|
99
|
+
requirements:
|
100
|
+
- - ">="
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
segments:
|
103
|
+
- 0
|
104
|
+
version: "0"
|
105
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
106
|
+
none: false
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
segments:
|
111
|
+
- 0
|
112
|
+
version: "0"
|
113
|
+
requirements: []
|
114
|
+
|
115
|
+
rubyforge_project:
|
116
|
+
rubygems_version: 1.3.7
|
117
|
+
signing_key:
|
118
|
+
specification_version: 3
|
119
|
+
summary: convert office 2010 files(docx,xlsx,pptx) to str
|
120
|
+
test_files:
|
121
|
+
- spec/officex2str_spec.rb
|
122
|
+
- spec/spec_helper.rb
|