logstash-filter-ezproxy 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d55b67f72348d7a1e6b0afa2fa3df83ba7c09967
+  data.tar.gz: ca1a3ec43e516224aec41ac687f095e052fa53ed
+SHA512:
+  metadata.gz: 00f3455d7f27aa70148ac3d952b486b4dae1119bed7258bac2431ef7e0959b77ae4410fe231b07d550679f590514d48d6ce22e195b59d4c968bbe58dc01c1cbf
+  data.tar.gz: b510124c44d2df0adddbebe35b8dd418689435652fc972475c0917c254adc14ac785a547b956546fc406e0b4d4343324c4d58929c31c023a1b13ff00c9d3f9b2

data/CHANGELOG.md

@@ -0,0 +1,2 @@
+## 0.1.0
+  - Plugin created with the logstash plugin generator

data/CONTRIBUTORS

@@ -0,0 +1,10 @@
+The following is a list of people who have contributed ideas, code, bug
+reports, or in general have helped logstash along its way.
+
+Contributors:
+* Dom Belcher - dominic.belcher@gmail.com
+
+Note: If you've sent us patches, bug reports, or otherwise contributed to
+Logstash, and you aren't on the list above and want to be, please let us know
+and we'll make sure you're here. Contributions from folks like you are what make
+open source awesome.

data/DEVELOPER.md

@@ -0,0 +1,2 @@
+# logstash-filter-ezproxy
+Example filter plugin. This should help bootstrap your effort to write your own filter plugin!

data/Gemfile

@@ -0,0 +1,5 @@
+source 'https://rubygems.org'
+gemspec
+# gem "logstash", :github => "elastic/logstash", :branch => "6.1"
+
+gem 'rspec', '~> 3.0'

data/LICENSE

@@ -0,0 +1,7 @@
+Copyright 2018 Lancaster University
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,86 @@
+# Logstash Plugin
+
+This is a plugin for [Logstash](https://github.com/elastic/logstash).
+
+It is fully free and fully open source. The license is Apache 2.0, meaning you are pretty much free to use it however you want in whatever way.
+
+## Documentation
+
+Logstash provides infrastructure to automatically generate documentation for this plugin. We use the asciidoc format to write documentation so any comments in the source code will be first converted into asciidoc and then into html. All plugin documentation are placed under one [central location](http://www.elastic.co/guide/en/logstash/current/).
+
+- For formatting code or config example, you can use the asciidoc `[source,ruby]` directive
+- For more asciidoc formatting tips, see the excellent reference here https://github.com/elastic/docs#asciidoc-guide
+
+## Need Help?
+
+Need help? Try #logstash on freenode IRC or the https://discuss.elastic.co/c/logstash discussion forum.
+
+## Developing
+
+### 1. Plugin Developement and Testing
+
+#### Code
+- To get started, you'll need JRuby with the Bundler gem installed.
+
+- Create a new plugin or clone and existing from the GitHub [logstash-plugins](https://github.com/logstash-plugins) organization. We also provide [example plugins](https://github.com/logstash-plugins?query=example).
+
+- Install dependencies
+```sh
+bundle install
+```
+
+#### Test
+
+- Update your dependencies
+
+```sh
+bundle install
+```
+
+- Run tests
+
+```sh
+bundle exec rspec
+```
+
+### 2. Running your unpublished Plugin in Logstash
+
+#### 2.1 Run in a local Logstash clone
+
+- Edit Logstash `Gemfile` and add the local plugin path, for example:
+```ruby
+gem "logstash-filter-awesome", :path => "/your/local/logstash-filter-awesome"
+```
+- Install plugin
+```sh
+bin/logstash-plugin install --no-verify
+```
+- Run Logstash with your plugin
+```sh
+bin/logstash -e 'filter {awesome {}}'
+```
+At this point any modifications to the plugin code will be applied to this local Logstash setup. After modifying the plugin, simply rerun Logstash.
+
+#### 2.2 Run in an installed Logstash
+
+You can use the same **2.1** method to run your plugin in an installed Logstash by editing its `Gemfile` and pointing the `:path` to your local plugin development directory or you can build the gem and install it using:
+
+- Build your plugin gem
+```sh
+gem build logstash-filter-awesome.gemspec
+```
+- Install the plugin from the Logstash home
+```sh
+bin/logstash-plugin install /your/local/plugin/logstash-filter-awesome.gem
+```
+- Start Logstash and proceed to test the plugin
+
+## Contributing
+
+All contributions are welcome: ideas, patches, documentation, bug reports, complaints, and even something you drew up on a napkin.
+
+Programming is not a required skill. Whatever you've seen about open source and maintainers or community members  saying "send patches or die" - you will not see that here.
+
+It is more important to the community that you are able to contribute.
+
+For more information about contributing, see the [CONTRIBUTING](https://github.com/elastic/logstash/blob/master/CONTRIBUTING.md) file.

data/lib/logstash/filters/dawsonera.rb

@@ -0,0 +1,41 @@
+
+require 'uri'
+require 'cgi'
+
+module DawsonEra
+  def DawsonEra.parse (input)
+
+    uri = URI(URI.unescape(input))
+
+    path = uri.path
+    params = {}
+    if (uri.query)
+        params = CGI::parse(uri.query)
+    end
+
+    data = {
+        "provider" => "dawsonera"
+    }
+
+    if (match = /^(\/abstract\/([0-9]+))$/.match(path))
+      data['rtype']             = 'ABS'
+      data['mime']              = 'MISC'
+      data['online_identifier'] = match[2]
+      data['unit_id']           = match[1]
+
+    elsif (match = /^(\/readonline\/([0-9]+))$/.match(path))
+      data['rtype']             = 'BOOK'
+      data['mime']              = 'MISC'
+      data['online_identifier'] = match[2]
+      data['unit_id']            = match[1]
+
+    elsif ((match = /^(\/download\/drm\/[0-9]+\/([0-9]+))$/.match(path)))
+      data['rtype']             = 'BOOK'
+      data['mime']              = 'PDF'
+      data['online_identifier'] = match[2]
+      data['unit_id']            = match[1]
+    end
+
+    return data;
+  end
+end

data/lib/logstash/filters/ebscohost.rb

@@ -0,0 +1,116 @@
+
+require 'uri'
+require 'cgi'
+
+module Ebscohost
+
+  @openUrlFields = {
+    'issn' => 'print_identifier',
+    'isbn' => 'print_identifier',
+    'volume' => 'vol',
+    'issue' => 'num',
+    'spage' => 'first_page',
+    'title' => 'publication_title',
+    'id' => 'unit_id'
+  }
+
+  def Ebscohost.parse (input)
+
+    uri = URI(URI.unescape(input))
+
+    path = uri.path
+    params = {}
+    if (uri.query)
+        params = CGI::parse(uri.query)
+    end
+
+    data = {
+        "provider" => "ebscohost"
+    }
+    
+
+    if ((match = /^\/(ehost|eds)\/([a-z]+)(?:\/[a-z]+)?$/i.match(path)))
+      category = match[2].downcase
+
+      if (match[1].downcase == 'eds')
+        data['platform_name'] = 'EBSCO Discovery Service'
+      end
+    
+
+      case (category)
+      when 'results', 'resultsadvanced'
+        data['rtype'] = 'TOC'
+        data['mime']  = 'MISC'
+
+      when 'ebookviewer'
+        data['rtype'] = 'BOOK'
+        data['mime']  = 'PDF'
+
+      when 'pdfviewer'
+        data['rtype'] = 'ARTICLE'
+        data['mime']  = 'PDF'
+
+      when 'search'
+        data['rtype'] = 'SEARCH'
+        data['mime']  = 'MISC'
+
+      when 'detail'
+        data['rtype'] = 'REF'
+        data['mime']  = 'HTML'
+
+        if (uri.fragment)
+          hashedUrl = uri.fragment
+          query = CGI::parse(hashedUrl)
+                  
+          if (query.key?('AN'))
+            data['unit_id'] = query['AN'][0]
+          end
+        end
+      end
+
+    
+
+    elsif ((match = /^\/pdf[a-z0-9_]*\/pdf\/\S+\/([a-z0-9]+)\.pdf$/i.match(path)))
+      data['rtype']  = 'ARTICLE'
+      data['mime']   = 'PDF'
+      data['unit_id'] = match[1]
+
+    elsif (path.downcase === '/contentserver.asp')
+      data['rtype'] = 'ARTICLE'
+      data['mime']  = 'PDF'
+
+      if (params.key?('K'))
+        data['unit_id'] = params['K'][0]
+      end
+
+    elsif (path.downcase == '/openurl')
+      data['rtype'] = 'OPENURL'
+      data['mime']  = 'HTML'
+
+      params.each do |key, value|
+        
+        if (@openUrlFields.key?(key))
+          data[@openUrlFields[key]] = value[0]
+        end
+      end
+      
+    
+
+      if (params.key?('pages'))
+        pagesMatch = /^(\d+)-(\d+)$/.match(params['pages'][0]);
+        if (pagesMatch)
+          data['first_page'] = pagesMatch[1]
+          data['last_page']  = pagesMatch[2]
+        end
+      end
+      
+    
+
+      if (data['unit_id'] && data['unit_id'].downcase.start_with?('doi:'))
+        data['doi'] = data['unit_id'] = data['unit_id'][4..-1]
+      end
+    end
+    
+    return data
+  end
+end

data/lib/logstash/filters/emerald.rb

@@ -0,0 +1,96 @@
+
+require 'uri'
+require 'cgi'
+
+module Emerald
+  def Emerald.parse (input)
+
+    uri = URI(URI.unescape(input))
+
+    path = uri.path
+    params = {}
+    if (uri.query)
+        params = CGI::parse(uri.query)
+    end
+
+    data = {
+        "provider" => "emerald"
+    }
+
+    if ((match = /^\/series\/([a-z]+)$/.match(path)))
+      data['rtype']    = 'BOOKSERIE'
+      data['mime']     = 'MISC'
+      data['title_id'] = match[1]
+      data['unit_id']   = 'series/' +match[1]
+    elsif ((match = /^\/doi\/([a-z]+)\/([0-9]{2}\.[0-9]{4,5})\/(([A-Z]{1})([0-9]+)([-])([0-9]+)[(]([0-9]{4})[)]([0-9]+))$/.match(path)))
+      
+      if (match[1] === 'abs')
+        data['rtype']    = 'ABS'
+        data['mime']     = 'MISC'
+      elsif (match[1] === 'book')
+        data['rtype']    = 'BOOKSERIE'
+        data['mime']     = 'MISC'
+      elsif (match[1] === 'full')
+        data['mime']     = 'HTML'
+        data['rtype']    = 'ARTICLE'
+      elsif (match[1] === 'pdfplus')
+        data['mime']     = 'PDFPLUS'
+        data['rtype']    = 'ARTICLE'
+      else
+        data['rtype']    = 'ARTICLE'
+        data['mime']     = 'MISC'
+      end
+
+      data['publication_date']= match[8]
+      data['title_id'] = match[5] +match[6] +match[7]
+      data['unit_id'] =data['doi']  = match[2] + '/' + match[3]
+    elsif ((match = /^\/loi\/([a-z]+)$/.match(path)))
+      
+      data['mime']     = 'MISC'
+      data['title_id'] = match[1]
+      data['unit_id']   = 'loi/' +match[1]
+    elsif ((match = /^\/toc\/([a-z]+)\/([0-9]+)\/([0-9]+)/.match(path)))
+      data['rtype']    = 'TOC'
+      data['mime']     = 'MISC'
+      data['title_id'] = match[1]
+      data['unit_id']   = match[1] + '/' + match[2] + '/'+ match[3]
+    elsif ((match = /^\/doi\/([a-z]+)\/([0-9]{2}\.[0-9]{4,5})\/(([A-Z]+)([-])([0-9]+)([-])([0-9]+)([-])([0-9]+))$/.match(path)))
+    
+      if (match[1] === 'abs')
+        data['rtype']    = 'ABS'
+        data['mime']     = 'MISC'
+      elsif (match[1] === 'full')
+        data['mime']     = 'HTML'
+        data['rtype']    = 'ARTICLE'
+      elsif (match[1] === 'pdfplus')
+        data['mime']     = 'PDFPLUS'
+        data['rtype']    = 'ARTICLE'
+      else
+        data['rtype']    = 'ARTICLE'
+      end
+    
+      data['title_id'] = match[4] 
+      data['unit_id'] =data['doi']  = match[2] + '/' + match[3]
+    elsif ((match = /^\/doi\/([a-z]+)\/([0-9]{2}\.[0-9]{4,5})\/([0-9]+)$/.match(path)))
+    
+      if (match[1] === 'abs')
+        data['rtype']    = 'ABS'
+        data['mime']     = 'MISC'
+      elsif (match[1] === 'full')
+        data['mime']     = 'HTML'
+        data['rtype']    = 'ARTICLE'
+      elsif (match[1] === 'pdfplus')
+        data['mime']     = 'PDFPLUS'
+        data['rtype']    = 'ARTICLE'
+      else
+        data['rtype']    = 'ARTICLE'
+      end
+    
+      data['title_id'] = match[3] 
+      data['unit_id'] =data['doi']  = match[2] + '/' + match[3]
+    end
+  
+
+    return data;
+  end
+end

data/lib/logstash/filters/ezproxy.rb

@@ -0,0 +1,93 @@
+# encoding: utf-8
+require "logstash/filters/base"
+require "logstash/namespace"
+require_relative "./jstor"
+require_relative "./lexisnexis"
+require_relative "./sage"
+require_relative "./wiley"
+require_relative "./sciencedirect"
+require_relative "./dawsonera"
+require_relative "./tandf"
+require_relative "./emerald"
+require_relative "./ebscohost"
+require 'uri'
+require 'cgi'
+
+# This  filter will replace the contents of the default 
+# message field with whatever you specify in the configuration.
+#
+# It is only intended to be used as an .
+class LogStash::Filters::Ezproxy < LogStash::Filters::Base
+
+  # Setting the config_name here is required. This is how you
+  # configure this filter from your Logstash config.
+  #
+  # filter {
+  #    {
+  #     message => "My message..."
+  #   }
+  # }
+  #
+  config_name "ezproxy"
+  
+  # The url to be parsed by the filter
+  config :url, :validate => :string, :required => true
+
+  # hosts = {
+  #   "www.jstor.org" => Jstor::parse
+  # }
+  
+
+  public
+  def register
+    # Add instance variables 
+  end # def register
+
+  public
+  def filter(event)
+    url = event.get(@url)
+    data = {}
+    uri = URI(URI::extract(url)[0])
+
+    # if (uri.host == "ezproxy.lancs.ac.uk")
+    #   if (uri.query)
+    #     puts uri
+    #     params = CGI::parse(uri.query)
+    #     if params.key?('url')
+    #       uri = URI(params['url'][0])
+    #     elsif params.key?('qurl')
+    #       uri = URI(params['qurl'][0])
+    #     end
+    #     event.tag("requested_host_ezproxy")
+    #     event.set("requested_host", uri.host)
+    #   end
+    # end
+
+    case
+    when uri.host.include?("www.jstor.org")
+      data = Jstor::parse(uri.to_s)
+    when uri.host.include?("www.lexisnexis.com")
+      data = LexisNexis::parse(uri.to_s)
+    when uri.host.include?("journals.sagepub.com")
+      data = Sage::parse(uri.to_s)
+    when uri.host.include?("onlinelibrary.wiley.com")
+      data = Wiley::parse(uri.to_s)
+    when uri.host.include?("www.sciencedirect.com")
+      data = ScienceDirect::parse(uri.to_s)
+    when uri.host.include?("www.dawsonera.com")
+      data = DawsonEra::parse(uri.to_s)
+    when uri.host.include?("www.tandfonline.com")
+      data = TandF::parse(uri.to_s)
+    when uri.host.include?("www.emeraldinsight.com")
+      data = Emerald::parse(uri.to_s)
+    when uri.host.include?("ebscohost.com")
+      data = Ebscohost::parse(uri.to_s)
+    end
+    event.set("request_metadata", data)
+    event.tag("ezproxy_parse_success")
+
+
+    # filter_matched should go in the last line of our successful code
+    filter_matched(event)
+  end # def filter
+end # class LogStash::Filters::Ezproxy