sitemaps 0.6.0
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/.document +5 -0
- data/.gitignore +5 -0
- data/LICENSE +20 -0
- data/README.rdoc +173 -0
- data/Rakefile +60 -0
- data/VERSION +1 -0
- data/bin/sitemaps +8 -0
- data/lib/configuration.rb +109 -0
- data/lib/generator.rb +136 -0
- data/lib/invalid_configuration_error.rb +6 -0
- data/lib/sitemaps.rb +12 -0
- data/sitemaps.gemspec +79 -0
- data/test/configuration_test.rb +108 -0
- data/test/data/empty_configuration_file.yml +0 -0
- data/test/data/generator_with_http_configuration_file.yml +11 -0
- data/test/data/generator_with_port_configuration_file.yml +11 -0
- data/test/data/invalid_configuration_file.yml +0 -0
- data/test/data/no_domain_configuration_file.yml +9 -0
- data/test/data/no_dump_dir_configuration_file.yml +9 -0
- data/test/data/no_generator_configuration_file.yml +9 -0
- data/test/data/no_port_configuration_file.yml +9 -0
- data/test/data/no_targets_configuration_file.yml +8 -0
- data/test/data/no_timeout_configuration_file.yml +8 -0
- data/test/data/valid_configuration_file.yml +48 -0
- data/test/data/valid_configuration_file2.yml +19 -0
- data/test/generator_test.rb +38 -0
- data/test/test_helper.rb +10 -0
- metadata +103 -0
data/.document
ADDED
data/LICENSE
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
Copyright (c) 2009 kazuyoshi tlacaelel
|
|
2
|
+
|
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
|
4
|
+
a copy of this software and associated documentation files (the
|
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
|
9
|
+
the following conditions:
|
|
10
|
+
|
|
11
|
+
The above copyright notice and this permission notice shall be
|
|
12
|
+
included in all copies or substantial portions of the Software.
|
|
13
|
+
|
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
1
|
+
= Sitemaps
|
|
2
|
+
|
|
3
|
+
Setup a config yaml file. I will download & compress your sitemaps!
|
|
4
|
+
|
|
5
|
+
Sitemaps provides an executable that will take a configuration yaml file.
|
|
6
|
+
When runned it will download and gzip-compress your sitemaps ready for production!
|
|
7
|
+
|
|
8
|
+
Basically the idea is that you do not want your production server to
|
|
9
|
+
compile the xml every single time, and on top of that you do not want
|
|
10
|
+
to (gzip) your sitemap on the fly nor tell your web-server to do that
|
|
11
|
+
for every single request.
|
|
12
|
+
|
|
13
|
+
So we precompile, the sitemaps and compress them in a "generator"
|
|
14
|
+
machine and store the static gziped-sitemaps on the webserver.
|
|
15
|
+
|
|
16
|
+
Sitemaps provides a simple way to do this, put the name of your
|
|
17
|
+
'generator-machine' and setup your production domain, subdirectories
|
|
18
|
+
and sitemap-index (sitemap of sitemaps) will be dinamically generated
|
|
19
|
+
for you. so all you have to do is execute and copy to your web-servers!
|
|
20
|
+
|
|
21
|
+
a sample robots file is also generated for you, you can simply cat
|
|
22
|
+
this and append it to your existing robots.txt file or simply use it
|
|
23
|
+
as a reference if you are generating it dinamically.
|
|
24
|
+
|
|
25
|
+
By Kazuyoshi Tlacaelel
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
Run..
|
|
29
|
+
|
|
30
|
+
$ sitemaps config.yml
|
|
31
|
+
|
|
32
|
+
Enjoy!
|
|
33
|
+
|
|
34
|
+
$ tree sitemaps
|
|
35
|
+
sitemaps
|
|
36
|
+
|-- downloads
|
|
37
|
+
| `-- communities.xml
|
|
38
|
+
|-- index.xml
|
|
39
|
+
|-- index.xml.gz
|
|
40
|
+
|-- robots.txt
|
|
41
|
+
`-- sitemaps
|
|
42
|
+
`-- communities.xml.gz
|
|
43
|
+
|
|
44
|
+
2 directories, 5 files
|
|
45
|
+
|
|
46
|
+
== Dependancies
|
|
47
|
+
|
|
48
|
+
# external libraries
|
|
49
|
+
require 'net/http'
|
|
50
|
+
require 'yaml'
|
|
51
|
+
require 'zlib'
|
|
52
|
+
require 'builder'
|
|
53
|
+
|
|
54
|
+
== Features
|
|
55
|
+
|
|
56
|
+
* automatic generation of sitemap indexes ( a sitemap of sitemaps )
|
|
57
|
+
|
|
58
|
+
$ cat sitemaps/index.xml
|
|
59
|
+
|
|
60
|
+
<?version1.0encodingUTF-8?>
|
|
61
|
+
<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
|
62
|
+
<sitemap>
|
|
63
|
+
<loc>http://example.com/sitemaps/communities.xml.gz</loc>
|
|
64
|
+
<lastmod>2009-09-15</lastmod>
|
|
65
|
+
</sitemap>
|
|
66
|
+
</sitemapindex>
|
|
67
|
+
|
|
68
|
+
* sample robots.txt generation
|
|
69
|
+
|
|
70
|
+
Sitemap: http://example.com/sitemaps/index.xml.gz
|
|
71
|
+
|
|
72
|
+
* download of sitemaps + compression
|
|
73
|
+
|
|
74
|
+
$ tree sitemaps
|
|
75
|
+
|
|
76
|
+
sitemaps
|
|
77
|
+
|-- downloads
|
|
78
|
+
| `-- communities.xml
|
|
79
|
+
|-- index.xml
|
|
80
|
+
|-- index.xml.gz
|
|
81
|
+
|-- robots.txt
|
|
82
|
+
`-- sitemaps
|
|
83
|
+
`-- communities.xml.gz
|
|
84
|
+
|
|
85
|
+
2 directories, 5 files
|
|
86
|
+
|
|
87
|
+
* The config file
|
|
88
|
+
|
|
89
|
+
configuration:
|
|
90
|
+
|
|
91
|
+
# Machine that generates your sitemaps
|
|
92
|
+
# do not prefix "http://" nor append the port
|
|
93
|
+
generator: localhost
|
|
94
|
+
|
|
95
|
+
# The http-port of your generator
|
|
96
|
+
generator_port: 3000
|
|
97
|
+
|
|
98
|
+
# The time to wait for each sitemap to be received
|
|
99
|
+
generator_timeout: 999
|
|
100
|
+
|
|
101
|
+
# Domain from where the sitemaps will be available.
|
|
102
|
+
# It is important that you do not append the last slash
|
|
103
|
+
# otherwise you may get an error message
|
|
104
|
+
#
|
|
105
|
+
# NG
|
|
106
|
+
# http://example.com/
|
|
107
|
+
#
|
|
108
|
+
# OK
|
|
109
|
+
# http://example.com
|
|
110
|
+
#
|
|
111
|
+
domain: http://example.com
|
|
112
|
+
|
|
113
|
+
# Path to sitemaps to be compiled on "generator".
|
|
114
|
+
# For example: if you have the following url
|
|
115
|
+
#
|
|
116
|
+
# http://localhost:3000/sitemap_for/users.xml
|
|
117
|
+
#
|
|
118
|
+
# The target must be specified as such
|
|
119
|
+
#
|
|
120
|
+
# Note: you can have multiple targets
|
|
121
|
+
#
|
|
122
|
+
targets:
|
|
123
|
+
- /sitemap_for/users.xml
|
|
124
|
+
|
|
125
|
+
# Directory where compressed maps will be placed.
|
|
126
|
+
#
|
|
127
|
+
# Its a good idea to use a sub-path in your domain.
|
|
128
|
+
#
|
|
129
|
+
# For example:
|
|
130
|
+
# (your dump_dir could be sitemaps for the following url)
|
|
131
|
+
#
|
|
132
|
+
# http://example.com/sitemaps
|
|
133
|
+
#
|
|
134
|
+
dump_dir: sitemaps
|
|
135
|
+
|
|
136
|
+
== Install
|
|
137
|
+
|
|
138
|
+
$ gem sources -a http://gems.github.com
|
|
139
|
+
$ gem install ktlacaelel-sitemaps
|
|
140
|
+
|
|
141
|
+
== Note on Patches/Pull Requests
|
|
142
|
+
|
|
143
|
+
* Fork the project.
|
|
144
|
+
* Make your feature addition or bug fix.
|
|
145
|
+
* Add tests for it. This is important so I don't break it in a
|
|
146
|
+
future version unintentionally.
|
|
147
|
+
* Commit, do not mess with rakefile, version, or history.
|
|
148
|
+
(if you want to have your own version, that is fine but
|
|
149
|
+
bump version in a commit by itself I can ignore when I pull)
|
|
150
|
+
* Send me a pull request. Bonus points for topic branches.
|
|
151
|
+
|
|
152
|
+
== Ruby versions
|
|
153
|
+
|
|
154
|
+
ruby 1.8.6 (2008-08-11 patchlevel 287) [universal-darwin9.0]
|
|
155
|
+
ruby 1.8.7 (2009-06-12 patchlevel 174) [x86_64-linux]
|
|
156
|
+
|
|
157
|
+
(havent tried any other let me know if you have any problems)
|
|
158
|
+
|
|
159
|
+
== Tested under
|
|
160
|
+
|
|
161
|
+
# Darwin tlacaelel.local 9.8.0 Darwin Kernel Version 9.8.0: Wed Jul 15 16:55:01 PDT 2009; root:xnu-1228.15.4~1/RELEASE_I386 i386
|
|
162
|
+
# Linux utopia.local 2.6.28-11-server #42-Ubuntu SMP Fri Apr 17 02:45:36 UTC 2009 x86_64 GNU/Linux
|
|
163
|
+
|
|
164
|
+
== Tests
|
|
165
|
+
only the download and compression part have no tests but the api is
|
|
166
|
+
pretty stable
|
|
167
|
+
|
|
168
|
+
== Copyright
|
|
169
|
+
|
|
170
|
+
MIT LICENSE
|
|
171
|
+
|
|
172
|
+
Copyright (c) 2009 kazuyoshi tlacaelel. See "LICENSE" file for details.
|
|
173
|
+
|
data/Rakefile
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
require 'rubygems'
|
|
2
|
+
require 'rake'
|
|
3
|
+
|
|
4
|
+
begin
|
|
5
|
+
require 'jeweler'
|
|
6
|
+
Jeweler::Tasks.new do |gem|
|
|
7
|
+
gem.name = "sitemaps"
|
|
8
|
+
gem.summary = %Q{Setup a config yaml file. I will download & compress your sitemaps!}
|
|
9
|
+
gem.description = %Q{
|
|
10
|
+
Sitemaps provides an executable that will take a configuration yaml file.
|
|
11
|
+
When runned it will download and gzip-compress your sitemaps ready for production!
|
|
12
|
+
}
|
|
13
|
+
gem.email = "kazu.dev@gmail.com"
|
|
14
|
+
gem.homepage = "http://github.com/ktlacaelel/sitemaps"
|
|
15
|
+
gem.authors = ["kazuyoshi tlacaelel"]
|
|
16
|
+
gem.add_development_dependency "thoughtbot-shoulda"
|
|
17
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
|
18
|
+
gem.add_dependency('builder', '>=2.1.2')
|
|
19
|
+
end
|
|
20
|
+
rescue LoadError
|
|
21
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
require 'rake/testtask'
|
|
25
|
+
Rake::TestTask.new(:test) do |test|
|
|
26
|
+
test.libs << 'lib' << 'test'
|
|
27
|
+
test.pattern = 'test/**/*_test.rb'
|
|
28
|
+
test.verbose = true
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
begin
|
|
32
|
+
require 'rcov/rcovtask'
|
|
33
|
+
Rcov::RcovTask.new do |test|
|
|
34
|
+
test.libs << 'test'
|
|
35
|
+
test.pattern = 'test/**/*_test.rb'
|
|
36
|
+
test.verbose = true
|
|
37
|
+
end
|
|
38
|
+
rescue LoadError
|
|
39
|
+
task :rcov do
|
|
40
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
|
41
|
+
end
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
task :test => :check_dependencies
|
|
45
|
+
|
|
46
|
+
task :default => :test
|
|
47
|
+
|
|
48
|
+
require 'rake/rdoctask'
|
|
49
|
+
Rake::RDocTask.new do |rdoc|
|
|
50
|
+
if File.exist?('VERSION')
|
|
51
|
+
version = File.read('VERSION')
|
|
52
|
+
else
|
|
53
|
+
version = ""
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
rdoc.rdoc_dir = 'rdoc'
|
|
57
|
+
rdoc.title = "sitemaps #{version}"
|
|
58
|
+
rdoc.rdoc_files.include('README*')
|
|
59
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
|
60
|
+
end
|
data/VERSION
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
0.6.0
|
data/bin/sitemaps
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
1
|
+
module Sitemaps
|
|
2
|
+
|
|
3
|
+
class Configuration
|
|
4
|
+
|
|
5
|
+
attr_reader :generator, :domain, :targets, :dump_dir, :generator_port, :generator_timeout
|
|
6
|
+
|
|
7
|
+
def initialize(yaml_file)
|
|
8
|
+
@yaml_file = yaml_file
|
|
9
|
+
validate!
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
protected
|
|
13
|
+
|
|
14
|
+
def validate!
|
|
15
|
+
validate_file!
|
|
16
|
+
validate_generator!
|
|
17
|
+
validate_generator_port!
|
|
18
|
+
validate_generator_timeout!
|
|
19
|
+
validate_domain!
|
|
20
|
+
validate_dump_dir!
|
|
21
|
+
validate_targets!
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
def validate_file!
|
|
25
|
+
unless @yaml_file.is_a? String
|
|
26
|
+
raise InvalidConfigurationError.new('Not a valid config filename')
|
|
27
|
+
end
|
|
28
|
+
unless File.exist? @yaml_file
|
|
29
|
+
raise InvalidConfigurationError.new('File not found: %s' % @yaml_file)
|
|
30
|
+
end
|
|
31
|
+
@configuration = YAML::load_file(@yaml_file)
|
|
32
|
+
unless @configuration.is_a? Hash
|
|
33
|
+
raise InvalidConfigurationError.new('Incorrect yaml-syntax')
|
|
34
|
+
end
|
|
35
|
+
@configuration = @configuration['configuration']
|
|
36
|
+
end
|
|
37
|
+
|
|
38
|
+
def validate_generator_timeout!
|
|
39
|
+
unless @configuration.keys.include? 'generator_timeout'
|
|
40
|
+
raise InvalidConfigurationError.new('Missing generator timeout in config')
|
|
41
|
+
end
|
|
42
|
+
unless @configuration['generator_timeout'].is_a? Fixnum
|
|
43
|
+
raise InvalidConfigurationError.new('Please specify a generator timeout')
|
|
44
|
+
end
|
|
45
|
+
@generator_timeout = @configuration['generator_timeout']
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def validate_generator_port!
|
|
49
|
+
unless @configuration.keys.include? 'generator_port'
|
|
50
|
+
raise InvalidConfigurationError.new('Missing generator port in config')
|
|
51
|
+
end
|
|
52
|
+
unless @configuration['generator_port'].is_a? Fixnum
|
|
53
|
+
raise InvalidConfigurationError.new('Please specify a generator port')
|
|
54
|
+
end
|
|
55
|
+
@generator_port = @configuration['generator_port']
|
|
56
|
+
end
|
|
57
|
+
|
|
58
|
+
def validate_generator!
|
|
59
|
+
unless @configuration.keys.include? 'generator'
|
|
60
|
+
raise InvalidConfigurationError.new('Missing generator in config')
|
|
61
|
+
end
|
|
62
|
+
if @configuration['generator'].nil? || @configuration['generator'] == ''
|
|
63
|
+
raise InvalidConfigurationError.new('Please specify a generator')
|
|
64
|
+
end
|
|
65
|
+
unless @configuration['generator'].is_a? String
|
|
66
|
+
raise InvalidConfigurationError.new('Generator is not a string')
|
|
67
|
+
end
|
|
68
|
+
if @configuration['generator'] =~ /^http/
|
|
69
|
+
raise InvalidConfigurationError.new('Do not prefix generator with http')
|
|
70
|
+
end
|
|
71
|
+
if @configuration['generator'] =~ /:\d+$/
|
|
72
|
+
raise InvalidConfigurationError.new('Do not sufix generator with port!')
|
|
73
|
+
end
|
|
74
|
+
@generator = @configuration['generator']
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
def validate_domain!
|
|
78
|
+
unless @configuration.keys.include? 'domain'
|
|
79
|
+
raise InvalidConfigurationError.new('Missing domain in config')
|
|
80
|
+
end
|
|
81
|
+
if @configuration['domain'].nil? || @configuration['domain'] == ''
|
|
82
|
+
raise InvalidConfigurationError.new('Please specify a domain')
|
|
83
|
+
end
|
|
84
|
+
@domain = @configuration['domain']
|
|
85
|
+
end
|
|
86
|
+
|
|
87
|
+
def validate_targets!
|
|
88
|
+
unless @configuration.keys.include? 'targets'
|
|
89
|
+
raise InvalidConfigurationError.new('Missing targets in config')
|
|
90
|
+
end
|
|
91
|
+
if !@configuration['targets'].is_a?(Array) || @configuration['targets'].size == 0
|
|
92
|
+
raise InvalidConfigurationError.new('Please specify some targets')
|
|
93
|
+
end
|
|
94
|
+
@targets = @configuration['targets']
|
|
95
|
+
end
|
|
96
|
+
|
|
97
|
+
def validate_dump_dir!
|
|
98
|
+
unless @configuration.keys.include? 'dump_dir'
|
|
99
|
+
raise InvalidConfigurationError.new('Missing dump_dir in config')
|
|
100
|
+
end
|
|
101
|
+
if @configuration['dump_dir'].nil? || @configuration['dump_dir'] == ''
|
|
102
|
+
raise InvalidConfigurationError.new('Please specify a dump_dir')
|
|
103
|
+
end
|
|
104
|
+
@dump_dir = @configuration['dump_dir']
|
|
105
|
+
end
|
|
106
|
+
|
|
107
|
+
end
|
|
108
|
+
|
|
109
|
+
end
|
data/lib/generator.rb
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
module Sitemaps
|
|
2
|
+
|
|
3
|
+
class Generator
|
|
4
|
+
|
|
5
|
+
attr_reader :configuration
|
|
6
|
+
|
|
7
|
+
def initialize(configuration_object)
|
|
8
|
+
self.configuration = configuration_object
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
def prepare
|
|
12
|
+
Dir.mkdir configuration.dump_dir
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
def configuration=(object)
|
|
16
|
+
unless object.is_a? Configuration
|
|
17
|
+
raise InvalidConfigurationError.new('Not a sitemap configuration object!')
|
|
18
|
+
end
|
|
19
|
+
@configuration = object
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
def execute!
|
|
23
|
+
download!
|
|
24
|
+
compress!
|
|
25
|
+
compile!
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
protected
|
|
29
|
+
|
|
30
|
+
def compile!
|
|
31
|
+
compile_index
|
|
32
|
+
compile_robots
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
def compile_index
|
|
36
|
+
output = File.new(sitemaps_index_filename, 'w+')
|
|
37
|
+
xml = Builder::XmlMarkup.new(:target => output, :indent => 2)
|
|
38
|
+
xml.instruct! :version => '1.0', :encoding => 'UTF-8'
|
|
39
|
+
xml.sitemapindex :xmlns => 'http://www.sitemaps.org/schemas/sitemap/0.9' do
|
|
40
|
+
downloaded_maps.each do |map|
|
|
41
|
+
xml.sitemap do
|
|
42
|
+
xml.loc get_gzip_url(map)
|
|
43
|
+
xml.lastmod Time.now.strftime('%Y-%m-%d')
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
end
|
|
47
|
+
output.close
|
|
48
|
+
compress_file(sitemaps_index_filename, sitemaps_gziped_index_filename)
|
|
49
|
+
end
|
|
50
|
+
|
|
51
|
+
def compile_robots
|
|
52
|
+
File.open(robots_filename, 'w+') do |rostob|
|
|
53
|
+
rostob.puts 'Sitemap: %s/%s' % [@configuration.domain, sitemaps_gziped_index_filename]
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def robots_filename
|
|
58
|
+
File.join(@configuration.dump_dir, 'robots.txt')
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
def sitemaps_index_filename
|
|
62
|
+
File.join(@configuration.dump_dir, 'index.xml')
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
def sitemaps_gziped_index_filename
|
|
66
|
+
File.join(@configuration.dump_dir, 'index.xml' + '.gz')
|
|
67
|
+
end
|
|
68
|
+
|
|
69
|
+
def download!
|
|
70
|
+
ensure_dump_dir
|
|
71
|
+
Net::HTTP.start(@configuration.generator, @configuration.generator_port) do |http|
|
|
72
|
+
http.read_timeout = @configuration.generator_timeout
|
|
73
|
+
@configuration.targets.each do |target|
|
|
74
|
+
store_downloaded_data target, http.get(target).body
|
|
75
|
+
end
|
|
76
|
+
end
|
|
77
|
+
end
|
|
78
|
+
|
|
79
|
+
def compress!
|
|
80
|
+
ensure_compress_dir
|
|
81
|
+
downloaded_maps.each { |map| compress_file(map, get_gzip_filename(map)) }
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
def compress_file(source, target)
|
|
85
|
+
Zlib::GzipWriter.open(target) { |gz| gz.write File.read(source) }
|
|
86
|
+
end
|
|
87
|
+
|
|
88
|
+
def downloaded_maps
|
|
89
|
+
Dir.glob(download_path + '/*')
|
|
90
|
+
end
|
|
91
|
+
|
|
92
|
+
def get_gzip_filename(long_path)
|
|
93
|
+
File.join(compress_path, File.basename(long_path) + '.gz')
|
|
94
|
+
end
|
|
95
|
+
|
|
96
|
+
def get_gzip_url(long_path)
|
|
97
|
+
[
|
|
98
|
+
@configuration.domain,
|
|
99
|
+
@configuration.dump_dir,
|
|
100
|
+
File.basename(long_path) + '.gz'
|
|
101
|
+
].join('/')
|
|
102
|
+
end
|
|
103
|
+
|
|
104
|
+
def ensure_dump_dir
|
|
105
|
+
[@configuration.dump_dir, download_path].each do |path|
|
|
106
|
+
Dir.mkdir path unless File.exist? path
|
|
107
|
+
end
|
|
108
|
+
end
|
|
109
|
+
|
|
110
|
+
def ensure_compress_dir
|
|
111
|
+
unless File.exist? compress_path
|
|
112
|
+
Dir.mkdir compress_path
|
|
113
|
+
end
|
|
114
|
+
end
|
|
115
|
+
|
|
116
|
+
def store_downloaded_data(target, data)
|
|
117
|
+
File.open(download_target_for(target), 'w+') do |file|
|
|
118
|
+
file.write data
|
|
119
|
+
end
|
|
120
|
+
end
|
|
121
|
+
|
|
122
|
+
def compress_path
|
|
123
|
+
@compress_path ||= File.join(@configuration.dump_dir, @configuration.dump_dir)
|
|
124
|
+
end
|
|
125
|
+
|
|
126
|
+
def download_target_for(target)
|
|
127
|
+
File.join(download_path, File.basename(target))
|
|
128
|
+
end
|
|
129
|
+
|
|
130
|
+
def download_path
|
|
131
|
+
File.join(@configuration.dump_dir, 'downloads')
|
|
132
|
+
end
|
|
133
|
+
|
|
134
|
+
end
|
|
135
|
+
|
|
136
|
+
end
|
data/lib/sitemaps.rb
ADDED
data/sitemaps.gemspec
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
# Generated by jeweler
|
|
2
|
+
# DO NOT EDIT THIS FILE
|
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
|
|
4
|
+
# -*- encoding: utf-8 -*-
|
|
5
|
+
|
|
6
|
+
Gem::Specification.new do |s|
|
|
7
|
+
s.name = %q{sitemaps}
|
|
8
|
+
s.version = "0.6.0"
|
|
9
|
+
|
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
|
11
|
+
s.authors = ["kazuyoshi tlacaelel"]
|
|
12
|
+
s.date = %q{2009-09-15}
|
|
13
|
+
s.default_executable = %q{sitemaps}
|
|
14
|
+
s.description = %q{
|
|
15
|
+
Sitemaps provides an executable that will take a configuration yaml file.
|
|
16
|
+
When runned it will download and gzip-compress your sitemaps ready for production!
|
|
17
|
+
}
|
|
18
|
+
s.email = %q{kazu.dev@gmail.com}
|
|
19
|
+
s.executables = ["sitemaps"]
|
|
20
|
+
s.extra_rdoc_files = [
|
|
21
|
+
"LICENSE",
|
|
22
|
+
"README.rdoc"
|
|
23
|
+
]
|
|
24
|
+
s.files = [
|
|
25
|
+
".document",
|
|
26
|
+
".gitignore",
|
|
27
|
+
"LICENSE",
|
|
28
|
+
"README.rdoc",
|
|
29
|
+
"Rakefile",
|
|
30
|
+
"VERSION",
|
|
31
|
+
"bin/sitemaps",
|
|
32
|
+
"lib/configuration.rb",
|
|
33
|
+
"lib/generator.rb",
|
|
34
|
+
"lib/invalid_configuration_error.rb",
|
|
35
|
+
"lib/sitemaps.rb",
|
|
36
|
+
"sitemaps.gemspec",
|
|
37
|
+
"test/configuration_test.rb",
|
|
38
|
+
"test/data/empty_configuration_file.yml",
|
|
39
|
+
"test/data/generator_with_http_configuration_file.yml",
|
|
40
|
+
"test/data/generator_with_port_configuration_file.yml",
|
|
41
|
+
"test/data/invalid_configuration_file.yml",
|
|
42
|
+
"test/data/no_domain_configuration_file.yml",
|
|
43
|
+
"test/data/no_dump_dir_configuration_file.yml",
|
|
44
|
+
"test/data/no_generator_configuration_file.yml",
|
|
45
|
+
"test/data/no_port_configuration_file.yml",
|
|
46
|
+
"test/data/no_targets_configuration_file.yml",
|
|
47
|
+
"test/data/no_timeout_configuration_file.yml",
|
|
48
|
+
"test/data/valid_configuration_file.yml",
|
|
49
|
+
"test/data/valid_configuration_file2.yml",
|
|
50
|
+
"test/generator_test.rb",
|
|
51
|
+
"test/test_helper.rb"
|
|
52
|
+
]
|
|
53
|
+
s.homepage = %q{http://github.com/ktlacaelel/sitemaps}
|
|
54
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
|
55
|
+
s.require_paths = ["lib"]
|
|
56
|
+
s.rubygems_version = %q{1.3.3}
|
|
57
|
+
s.summary = %q{Setup a config yaml file. I will download & compress your sitemaps!}
|
|
58
|
+
s.test_files = [
|
|
59
|
+
"test/configuration_test.rb",
|
|
60
|
+
"test/generator_test.rb",
|
|
61
|
+
"test/test_helper.rb"
|
|
62
|
+
]
|
|
63
|
+
|
|
64
|
+
if s.respond_to? :specification_version then
|
|
65
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
|
66
|
+
s.specification_version = 3
|
|
67
|
+
|
|
68
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
|
69
|
+
s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
|
70
|
+
s.add_runtime_dependency(%q<builder>, [">= 2.1.2"])
|
|
71
|
+
else
|
|
72
|
+
s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
|
73
|
+
s.add_dependency(%q<builder>, [">= 2.1.2"])
|
|
74
|
+
end
|
|
75
|
+
else
|
|
76
|
+
s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
|
|
77
|
+
s.add_dependency(%q<builder>, [">= 2.1.2"])
|
|
78
|
+
end
|
|
79
|
+
end
|
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
require 'test_helper'
|
|
2
|
+
|
|
3
|
+
class ConfigurationTest < Test::Unit::TestCase
|
|
4
|
+
|
|
5
|
+
def setup
|
|
6
|
+
@empty = 'test/data/empty_configuration_file.yml'
|
|
7
|
+
@invalid = 'test/data/invalid_configuration_file.yml'
|
|
8
|
+
@no_domain = 'test/data/no_domain_configuration_file.yml'
|
|
9
|
+
@no_dump_dir = 'test/data/no_dump_dir_configuration_file.yml'
|
|
10
|
+
@no_generator = 'test/data/no_generator_configuration_file.yml'
|
|
11
|
+
@no_port = 'test/data/no_port_configuration_file.yml'
|
|
12
|
+
@no_targets = 'test/data/no_targets_configuration_file.yml'
|
|
13
|
+
@no_timeout = 'test/data/no_timeout_configuration_file.yml'
|
|
14
|
+
@gen_n_port = 'test/data/generator_with_port_configuration_file.yml'
|
|
15
|
+
@gen_n_http = 'test/data/generator_with_http_configuration_file.yml'
|
|
16
|
+
@valid = 'test/data/valid_configuration_file.yml'
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
# ============================================================================
|
|
20
|
+
# YAML LOADING
|
|
21
|
+
# ============================================================================
|
|
22
|
+
|
|
23
|
+
should 'check if configuration file exists' do
|
|
24
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new('a') }
|
|
25
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(nil) }
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
should 'load a configuration file' do
|
|
29
|
+
Sitemaps::Configuration.new(@valid)
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
# ============================================================================
|
|
33
|
+
# MISSING PARAMETERS
|
|
34
|
+
# ============================================================================
|
|
35
|
+
|
|
36
|
+
should 'raise an error when generator is not given' do
|
|
37
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_generator) }
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
should 'raise an error when generator port is not given' do
|
|
41
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_port) }
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
should 'raise an error when generator timeout is not given' do
|
|
45
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_timeout) }
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
should 'raise an error when domain is not given' do
|
|
49
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_domain) }
|
|
50
|
+
end
|
|
51
|
+
|
|
52
|
+
should 'raise an error when targets is not given' do
|
|
53
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_targets) }
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
should 'raise an error when dump_dir is not given' do
|
|
57
|
+
assert_raise(Sitemaps::InvalidConfigurationError) { Sitemaps::Configuration.new(@no_dump_dir) }
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
# ============================================================================
|
|
61
|
+
# INVALID FORMAT
|
|
62
|
+
# ============================================================================
|
|
63
|
+
|
|
64
|
+
should 'raise an error when generator given has port' do
|
|
65
|
+
assert_raise(Sitemaps::InvalidConfigurationError) do
|
|
66
|
+
Sitemaps::Configuration.new(@gen_n_port)
|
|
67
|
+
end
|
|
68
|
+
end
|
|
69
|
+
|
|
70
|
+
should 'raise an error when generator given includes "http://" prefixed' do
|
|
71
|
+
assert_raise(Sitemaps::InvalidConfigurationError) do
|
|
72
|
+
Sitemaps::Configuration.new(@gen_n_http)
|
|
73
|
+
end
|
|
74
|
+
end
|
|
75
|
+
|
|
76
|
+
# ============================================================================
|
|
77
|
+
# CONFIGURATION ACCESS
|
|
78
|
+
# ============================================================================
|
|
79
|
+
|
|
80
|
+
def config
|
|
81
|
+
Sitemaps::Configuration.new(@valid)
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
should 'retrive generator' do
|
|
85
|
+
assert_equal 'localhost', config.generator
|
|
86
|
+
end
|
|
87
|
+
|
|
88
|
+
should 'retrive generator port' do
|
|
89
|
+
assert_equal 3000, config.generator_port
|
|
90
|
+
end
|
|
91
|
+
|
|
92
|
+
should 'retrive ttl' do
|
|
93
|
+
assert_equal 999, config.generator_timeout
|
|
94
|
+
end
|
|
95
|
+
|
|
96
|
+
should 'retrive domain' do
|
|
97
|
+
assert_equal 'http://example.com', config.domain
|
|
98
|
+
end
|
|
99
|
+
|
|
100
|
+
should 'retrive targets' do
|
|
101
|
+
assert_equal ['/sitemap_for/users.xml'], config.targets
|
|
102
|
+
end
|
|
103
|
+
|
|
104
|
+
should 'retrive dump_dir' do
|
|
105
|
+
assert_equal 'sitemaps', config.dump_dir
|
|
106
|
+
end
|
|
107
|
+
|
|
108
|
+
end
|
|
File without changes
|
|
File without changes
|
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
|
|
2
|
+
configuration:
|
|
3
|
+
|
|
4
|
+
# Machine that generates your sitemaps
|
|
5
|
+
# do not prefix "http://" nor append the port
|
|
6
|
+
generator: localhost
|
|
7
|
+
|
|
8
|
+
# The http-port of your generator
|
|
9
|
+
generator_port: 3000
|
|
10
|
+
|
|
11
|
+
# The time to wait for each sitemap to be received
|
|
12
|
+
generator_timeout: 999
|
|
13
|
+
|
|
14
|
+
# Domain from where the sitemaps will be available.
|
|
15
|
+
# It is important that you do not append the last slash
|
|
16
|
+
# otherwise you may get an error message
|
|
17
|
+
#
|
|
18
|
+
# NG
|
|
19
|
+
# http://example.com/
|
|
20
|
+
#
|
|
21
|
+
# OK
|
|
22
|
+
# http://example.com
|
|
23
|
+
#
|
|
24
|
+
domain: http://example.com
|
|
25
|
+
|
|
26
|
+
# Path to sitemaps to be compiled on "generator".
|
|
27
|
+
# For example: if you have the following url
|
|
28
|
+
#
|
|
29
|
+
# http://localhost:3000/sitemap_for/users.xml
|
|
30
|
+
#
|
|
31
|
+
# The target must be specified as such
|
|
32
|
+
#
|
|
33
|
+
# Note: you can have multiple targets
|
|
34
|
+
#
|
|
35
|
+
targets:
|
|
36
|
+
- /sitemap_for/users.xml
|
|
37
|
+
|
|
38
|
+
# Directory where compressed maps will be placed.
|
|
39
|
+
#
|
|
40
|
+
# Its a good idea to use a sub-path in your domain.
|
|
41
|
+
#
|
|
42
|
+
# For example:
|
|
43
|
+
# (your dump_dir could be sitemaps for the following url)
|
|
44
|
+
#
|
|
45
|
+
# http://example.com/sitemaps
|
|
46
|
+
#
|
|
47
|
+
dump_dir: sitemaps
|
|
48
|
+
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
|
|
2
|
+
configuration:
|
|
3
|
+
|
|
4
|
+
# machine that generates sitemaps in xml format
|
|
5
|
+
generator: xxxxxxxxx
|
|
6
|
+
|
|
7
|
+
generator_timeout: 999
|
|
8
|
+
generator_port: 3000
|
|
9
|
+
|
|
10
|
+
# domain from where the sitemaps will be available
|
|
11
|
+
domain: http://example.com
|
|
12
|
+
|
|
13
|
+
# path to sitemaps to be compiled
|
|
14
|
+
targets:
|
|
15
|
+
- /sitemap_for/users.xml
|
|
16
|
+
|
|
17
|
+
# directory where compressed maps will be placed
|
|
18
|
+
dump_dir: sitemaps
|
|
19
|
+
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
require 'test_helper'
|
|
2
|
+
|
|
3
|
+
class GeneratorTest < Test::Unit::TestCase
|
|
4
|
+
|
|
5
|
+
def setup
|
|
6
|
+
@valid = 'test/data/valid_configuration_file.yml'
|
|
7
|
+
@valid2 = 'test/data/valid_configuration_file2.yml'
|
|
8
|
+
@config = Sitemaps::Configuration.new(@valid)
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
should 'check for a sitemap configuration on instantiantion' do
|
|
12
|
+
assert_raise (Sitemaps::InvalidConfigurationError) do
|
|
13
|
+
Sitemaps::Generator.new(nil)
|
|
14
|
+
end
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
should 'prepare dump_dir' do
|
|
18
|
+
`rm -rf sitemaps`
|
|
19
|
+
Sitemaps::Generator.new(@config).prepare
|
|
20
|
+
assert File.exist? 'sitemaps'
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
should 'get config' do
|
|
24
|
+
config = Sitemaps::Generator.new(@config).configuration
|
|
25
|
+
assert_equal config.generator, 'localhost'
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
should 'change config' do
|
|
29
|
+
generator = Sitemaps::Generator.new(@config)
|
|
30
|
+
new_config = Sitemaps::Configuration.new(@valid2)
|
|
31
|
+
generator.configuration = new_config
|
|
32
|
+
assert_equal new_config, generator.configuration
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
should 'should download sitemaps'
|
|
36
|
+
should 'should gzip sitemaps'
|
|
37
|
+
|
|
38
|
+
end
|
data/test/test_helper.rb
ADDED
metadata
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: sitemaps
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.6.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- kazuyoshi tlacaelel
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
|
|
12
|
+
date: 2009-09-15 00:00:00 +09:00
|
|
13
|
+
default_executable: sitemaps
|
|
14
|
+
dependencies:
|
|
15
|
+
- !ruby/object:Gem::Dependency
|
|
16
|
+
name: thoughtbot-shoulda
|
|
17
|
+
type: :development
|
|
18
|
+
version_requirement:
|
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
20
|
+
requirements:
|
|
21
|
+
- - ">="
|
|
22
|
+
- !ruby/object:Gem::Version
|
|
23
|
+
version: "0"
|
|
24
|
+
version:
|
|
25
|
+
- !ruby/object:Gem::Dependency
|
|
26
|
+
name: builder
|
|
27
|
+
type: :runtime
|
|
28
|
+
version_requirement:
|
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - ">="
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: 2.1.2
|
|
34
|
+
version:
|
|
35
|
+
description: "\n Sitemaps provides an executable that will take a configuration yaml file.\n When runned it will download and gzip-compress your sitemaps ready for production!\n "
|
|
36
|
+
email: kazu.dev@gmail.com
|
|
37
|
+
executables:
|
|
38
|
+
- sitemaps
|
|
39
|
+
extensions: []
|
|
40
|
+
|
|
41
|
+
extra_rdoc_files:
|
|
42
|
+
- LICENSE
|
|
43
|
+
- README.rdoc
|
|
44
|
+
files:
|
|
45
|
+
- .document
|
|
46
|
+
- .gitignore
|
|
47
|
+
- LICENSE
|
|
48
|
+
- README.rdoc
|
|
49
|
+
- Rakefile
|
|
50
|
+
- VERSION
|
|
51
|
+
- bin/sitemaps
|
|
52
|
+
- lib/configuration.rb
|
|
53
|
+
- lib/generator.rb
|
|
54
|
+
- lib/invalid_configuration_error.rb
|
|
55
|
+
- lib/sitemaps.rb
|
|
56
|
+
- sitemaps.gemspec
|
|
57
|
+
- test/configuration_test.rb
|
|
58
|
+
- test/data/empty_configuration_file.yml
|
|
59
|
+
- test/data/generator_with_http_configuration_file.yml
|
|
60
|
+
- test/data/generator_with_port_configuration_file.yml
|
|
61
|
+
- test/data/invalid_configuration_file.yml
|
|
62
|
+
- test/data/no_domain_configuration_file.yml
|
|
63
|
+
- test/data/no_dump_dir_configuration_file.yml
|
|
64
|
+
- test/data/no_generator_configuration_file.yml
|
|
65
|
+
- test/data/no_port_configuration_file.yml
|
|
66
|
+
- test/data/no_targets_configuration_file.yml
|
|
67
|
+
- test/data/no_timeout_configuration_file.yml
|
|
68
|
+
- test/data/valid_configuration_file.yml
|
|
69
|
+
- test/data/valid_configuration_file2.yml
|
|
70
|
+
- test/generator_test.rb
|
|
71
|
+
- test/test_helper.rb
|
|
72
|
+
has_rdoc: true
|
|
73
|
+
homepage: http://github.com/ktlacaelel/sitemaps
|
|
74
|
+
licenses: []
|
|
75
|
+
|
|
76
|
+
post_install_message:
|
|
77
|
+
rdoc_options:
|
|
78
|
+
- --charset=UTF-8
|
|
79
|
+
require_paths:
|
|
80
|
+
- lib
|
|
81
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
82
|
+
requirements:
|
|
83
|
+
- - ">="
|
|
84
|
+
- !ruby/object:Gem::Version
|
|
85
|
+
version: "0"
|
|
86
|
+
version:
|
|
87
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
88
|
+
requirements:
|
|
89
|
+
- - ">="
|
|
90
|
+
- !ruby/object:Gem::Version
|
|
91
|
+
version: "0"
|
|
92
|
+
version:
|
|
93
|
+
requirements: []
|
|
94
|
+
|
|
95
|
+
rubyforge_project:
|
|
96
|
+
rubygems_version: 1.3.5
|
|
97
|
+
signing_key:
|
|
98
|
+
specification_version: 3
|
|
99
|
+
summary: Setup a config yaml file. I will download & compress your sitemaps!
|
|
100
|
+
test_files:
|
|
101
|
+
- test/configuration_test.rb
|
|
102
|
+
- test/generator_test.rb
|
|
103
|
+
- test/test_helper.rb
|