xapian-indexer 1.2.19.1 → 1.2.19.2

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.
Files changed (11) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +2 -2
  3. data/lib/xapian/indexer.rb +24 -3
  4. data/lib/xapian/indexer/extensions/uri.rb +41 -0
  5. data/lib/xapian/indexer/extractors/html.rb +17 -12
  6. data/lib/xapian/indexer/loaders/http.rb +18 -13
  7. data/lib/xapian/indexer/resource.rb +17 -12
  8. data/lib/xapian/indexer/spider.rb +17 -12
  9. data/lib/xapian/indexer/version.rb +18 -13
  10. data/xapian-indexer.gemspec +1 -1
  11. metadata +6 -5
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 72b813e2b0019183e68679aebf13532f607f4adb
4
- data.tar.gz: 3806c150659093f02f1c394b227715790bfbe218
3
+ metadata.gz: 8effe1bf39e7072ee007a20249dd43f0c1c7bbe7
4
+ data.tar.gz: dfd99dfe5b79e17534ec7a26acd89432021183b1
5
5
  SHA512:
6
- metadata.gz: 2583e40e2e9eeecf3247822595e8dbedc09d07fd1bc18ba64c95b72a5ff0413cc0bba51434a69b6ccb61e60669a4f05616d615e3e229f4105512e93315316e12
7
- data.tar.gz: f77f2f725d2fb549b6c0eea955ef709390090916c090e8259c0d94474bbaaa686d340a56d7987711e755591b5e40aa757e9e2e1b88fe0651b753d0304be4b664
6
+ metadata.gz: 847af60f50c2f0da6397b536d0a4cdeea60977cb0945f7719a34d261c4f2bb227744e60af29b70e8a472e553302366fd49fbf683ef4432a4975d416479fca80f
7
+ data.tar.gz: c63cfb012a7f94aed6bb136e3069fa161e0c1e395e664d221a5e1127c4fbeca88de9573f0f6a19798c1cd20903eb5c7a60c28557faa202f4c56e4acaaa6142a0
data/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Xapian::Indexer
2
2
 
3
- TODO: Write a gem description
3
+ This gem provides basic infrastructure for indexing HTML documents over HTTP into a Xapian database.
4
4
 
5
5
  ## Installation
6
6
 
@@ -86,7 +86,7 @@ The following example shows how to create a spider and index some resources:
86
86
 
87
87
  ## License
88
88
 
89
- Released under the MIT license.
89
+ This code is dual licensed under the MIT license and GPLv3 license.
90
90
 
91
91
  Copyright, 2015, by [Samuel G. D. Williams](http://www.codeotaku.com/samuel-williams).
92
92
 
data/lib/xapian/indexer.rb CHANGED
@@ -1,7 +1,28 @@
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
2
+ #
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
9
+ #
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
1
20
 
2
- require 'xapian/indexer/version'
3
- require 'xapian/indexer/resource'
4
- require 'xapian/indexer/spider'
21
+ require_relative 'indexer/extensions/uri'
22
+
23
+ require_relative 'indexer/version'
24
+ require_relative 'indexer/resource'
25
+ require_relative 'indexer/spider'
5
26
 
6
27
  module Xapian
7
28
  module Indexer
data/lib/xapian/indexer/extensions/uri.rb ADDED
@@ -0,0 +1,41 @@
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
2
+ #
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
9
+ #
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
20
+
21
+ require 'uri'
22
+
23
+ class URI::Generic
24
+ # This change allows you to merge relative URLs which otherwise isn't possible.
25
+ def merge0(oth)
26
+ oth = parser.send(:convert_to_uri, oth)
27
+
28
+ if self.absolute? && oth.absolute?
29
+ #raise BadURIError,
30
+ # "both URI are absolute"
31
+ # hmm... should return oth for usability?
32
+ return oth, oth
33
+ end
34
+
35
+ if self.absolute?
36
+ return self.dup, oth
37
+ else
38
+ return oth, oth
39
+ end
40
+ end
41
+ end
data/lib/xapian/indexer/extractors/html.rb CHANGED
@@ -1,17 +1,22 @@
1
- # Copyright (c) 2010 Samuel Williams. Released under the GNU GPLv3.
2
- #
3
- # This program is free software: you can redistribute it and/or modify
4
- # it under the terms of the GNU General Public License as published by
5
- # the Free Software Foundation, either version 3 of the License, or
6
- # (at your option) any later version.
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
7
2
  #
8
- # This program is distributed in the hope that it will be useful,
9
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
10
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
- # GNU General Public License for more details.
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
12
9
  #
13
- # You should have received a copy of the GNU General Public License
14
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
15
20
 
16
21
  require 'nokogiri'
17
22
 
data/lib/xapian/indexer/loaders/http.rb CHANGED
@@ -1,20 +1,25 @@
1
- # Copyright (c) 2010 Samuel Williams. Released under the GNU GPLv3.
2
- #
3
- # This program is free software: you can redistribute it and/or modify
4
- # it under the terms of the GNU General Public License as published by
5
- # the Free Software Foundation, either version 3 of the License, or
6
- # (at your option) any later version.
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
7
2
  #
8
- # This program is distributed in the hope that it will be useful,
9
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
10
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
- # GNU General Public License for more details.
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
12
9
  #
13
- # You should have received a copy of the GNU General Public License
14
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
15
20
 
16
21
  require 'net/http'
17
- require 'xapian/indexer/version'
22
+ require_relative '../version'
18
23
 
19
24
  module Xapian
20
25
  module Indexer
data/lib/xapian/indexer/resource.rb CHANGED
@@ -1,17 +1,22 @@
1
- # Copyright (c) 2010 Samuel Williams. Released under the GNU GPLv3.
2
- #
3
- # This program is free software: you can redistribute it and/or modify
4
- # it under the terms of the GNU General Public License as published by
5
- # the Free Software Foundation, either version 3 of the License, or
6
- # (at your option) any later version.
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
7
2
  #
8
- # This program is distributed in the hope that it will be useful,
9
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
10
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
- # GNU General Public License for more details.
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
12
9
  #
13
- # You should have received a copy of the GNU General Public License
14
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
15
20
 
16
21
  require 'digest/md5'
17
22
  require 'yaml'
data/lib/xapian/indexer/spider.rb CHANGED
@@ -1,17 +1,22 @@
1
- # Copyright (c) 2010 Samuel Williams. Released under the GNU GPLv3.
2
- #
3
- # This program is free software: you can redistribute it and/or modify
4
- # it under the terms of the GNU General Public License as published by
5
- # the Free Software Foundation, either version 3 of the License, or
6
- # (at your option) any later version.
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
7
2
  #
8
- # This program is distributed in the hope that it will be useful,
9
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
10
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
- # GNU General Public License for more details.
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
12
9
  #
13
- # You should have received a copy of the GNU General Public License
14
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
15
20
 
16
21
  require 'xapian'
17
22
  require 'set'
data/lib/xapian/indexer/version.rb CHANGED
@@ -1,20 +1,25 @@
1
- # Copyright (c) 2010 Samuel Williams. Released under the GNU GPLv3.
2
- #
3
- # This program is free software: you can redistribute it and/or modify
4
- # it under the terms of the GNU General Public License as published by
5
- # the Free Software Foundation, either version 3 of the License, or
6
- # (at your option) any later version.
1
+ # Copyright, 2015, by Samuel G. D. Williams. <http://www.codeotaku.com>
7
2
  #
8
- # This program is distributed in the hope that it will be useful,
9
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
10
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
- # GNU General Public License for more details.
3
+ # Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ # of this software and associated documentation files (the "Software"), to deal
5
+ # in the Software without restriction, including without limitation the rights
6
+ # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ # copies of the Software, and to permit persons to whom the Software is
8
+ # furnished to do so, subject to the following conditions:
12
9
  #
13
- # You should have received a copy of the GNU General Public License
14
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
10
+ # The above copyright notice and this permission notice shall be included in
11
+ # all copies or substantial portions of the Software.
12
+ #
13
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
19
+ # THE SOFTWARE.
15
20
 
16
21
  module Xapian
17
22
  module Indexer
18
- VERSION = "1.2.19.1"
23
+ VERSION = "1.2.19.2"
19
24
  end
20
25
  end
data/xapian-indexer.gemspec CHANGED
@@ -17,7 +17,7 @@ Gem::Specification.new do |spec|
17
17
  spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
18
18
  spec.require_paths = ["lib"]
19
19
 
20
- spec.add_dependency 'xapian-core'
20
+ spec.add_dependency 'xapian-core', '~> 1.2.19.1'
21
21
  spec.add_dependency 'nokogiri'
22
22
 
23
23
  spec.add_development_dependency "bundler", "~> 1.6"
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: xapian-indexer
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.2.19.1
4
+ version: 1.2.19.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Samuel Williams
@@ -14,16 +14,16 @@ dependencies:
14
14
  name: xapian-core
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
- - - ">="
17
+ - - "~>"
18
18
  - !ruby/object:Gem::Version
19
- version: '0'
19
+ version: 1.2.19.1
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
- - - ">="
24
+ - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: '0'
26
+ version: 1.2.19.1
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: nokogiri
29
29
  requirement: !ruby/object:Gem::Requirement
@@ -78,6 +78,7 @@ files:
78
78
  - README.md
79
79
  - Rakefile
80
80
  - lib/xapian/indexer.rb
81
+ - lib/xapian/indexer/extensions/uri.rb
81
82
  - lib/xapian/indexer/extractors/html.rb
82
83
  - lib/xapian/indexer/loaders/http.rb
83
84
  - lib/xapian/indexer/resource.rb