carrot2 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 73489263c06ae2b8e9f7509570c35c052635340d8401f04d659fe4080188b049
-  data.tar.gz: 891c4d26486b4c39c1cdff7756bb97faea0ff01ae5aceaa8082ed122d4300f6c
+  metadata.gz: f7c82346a7d8fedbd0b875e1a755d5a16a1a2a28c680e7f71c1b7bebe9603ef8
+  data.tar.gz: b6493deebcce2d05039ba1c6546e4725f4fbc52d0d35f15583d1d49e6e9d086a
 SHA512:
-  metadata.gz: 30e723899e33b4ce32463b52a65b24ac1f1a1fc7a39fec038dfd95c5fad7cdf0bb78555e24fdeff18657905ca194fcc59afded05dc292cfcb06ca7aa919eca59
-  data.tar.gz: 1dae126a035baf128cc7e4ec265259056e1817694b2a61317edc339f4b193a1f0b81c4f08bc80a8d98fda28dd69f4ef12be75f30d2450be55654f33ee8085927
+  metadata.gz: 8587ddd05ff3d8c2d491b25c7a10bea228b92a198d18bdd788c03f44c40a89bdffa39cd7ac65b2ec59828c043cbceb4c2a127f2df961c83733440952e9201c23
+  data.tar.gz: f91d543e01915d25586b874970996f50c54a25ac4fd39d5a0a0bfb1a3e1aec84c992b60edea4acfc6073ffef5edef969bbce0174d7f32845bdf6d420a3b66596

data/CHANGELOG.md

@@ -1,18 +1,23 @@
-## 0.2.1
+## 0.3.0 (2020-07-29)
+
+- Added support for Carrot2 4
+- Dropped support for Carrot2 < 4
+
+## 0.2.1 (2019-10-28)
 
 - Added `open_timeout` and `read_timeout` options
 
-## 0.2.0
+## 0.2.0 (2017-01-22)
 
 - Added `request` method
 - Removed dependency on `rest-client`
 - Better error messages
 
-## 0.1.0
+## 0.1.0 (2017-01-17)
 
 - Added support for env var
 - Added tests
 
-## 0.0.1
+## 0.0.1 (2012-06-20)
 
 - First version

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2012 Andrew Kane
+Copyright (c) 2012-2020 Andrew Kane
 
 MIT License
 
@@ -19,4 +19,4 @@ 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.
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -1,12 +1,12 @@
 # Carrot2
 
-Ruby client for [Carrot2](https://project.carrot2.org/) - the open-source document clustering server
+Ruby client for [Carrot2](https://github.com/carrot2/carrot2) - the open-source document clustering server
 
-## Installation
+[![Build Status](https://travis-ci.org/ankane/carrot2.svg?branch=master)](https://travis-ci.org/ankane/carrot2)
 
-First, [download and run](https://project.carrot2.org/download-dcs.html) the Carrot2 server. It’s the one on [this page](https://github.com/carrot2/carrot2/releases) that begins with `carrot2-dcs`.
+## Installation
 
-With Homebrew, use:
+First, [download and run](https://github.com/carrot2/carrot2#installation) the Carrot2 server. With Homebrew, use:
 
 ```sh
 brew install carrot2
@@ -19,6 +19,8 @@ Then add this line to your application’s Gemfile:
 gem 'carrot2'
 ```
 
+The latest version works with Carrot2 4. For Carrot2 3, use version 0.2.1 and [this readme](https://github.com/ankane/carrot2/blob/v0.2.1/README.md).
+
 ## How to Use
 
 To cluster documents, use:
@@ -39,35 +41,20 @@ This returns:
 
 ```ruby
 {
-  "processing-time-total"=>1,
-  "clusters"=> [
+  "clusters" => [
     {
-      "id"=>0,
-      "size"=>3,
-      "phrases"=>["Coupon"],
-      "score"=>0.06462323710740674,
-      "documents"=>[0, 1, 2],
-      "attributes"=>{"score"=>0.06462323710740674}
+      "labels" => ["Coupon"],
+      "documents" => [0, 1, 2],
+      "clusters" => [],
+      "score" => 0.06418006702675011
     },
     {
-      "id"=>1,
-      "size"=>2,
-      "phrases"=>["Exclusive"],
-      "score"=>0.05873148311034013,
-      "documents"=>[0, 1],
-      "attributes"=>{"score"=>0.05873148311034013}
-    },
-    {
-      "id"=>2,
-      "size"=>1,
-      "phrases"=>["Other Topics"],
-      "score"=>0.0,
-      "documents"=>[3],
-      "attributes"=>{"other-topics"=>true, "score"=>0.0}
+      "labels" => ["Exclusive"],
+      "documents" => [0, 1],
+      "clusters" => [],
+      "score" => 0.7040290701763807
     }
-  ],
-  "processing-time-algorithm"=>1,
-  "query"=>nil
+  ]
 }
 ```
 
@@ -76,17 +63,39 @@ Documents are numbered in the order provided, starting with 0.
 Specify a language with:
 
 ```ruby
-carrot2.cluster(documents, language: "FRENCH")
+carrot2.cluster(documents, language: "French")
+```
+
+Specify an [algorithm](https://carrot2.github.io/release/4.0.0/doc/algorithms/) with:
+
+```ruby
+carrot2.cluster(documents, algorithm: "Lingo")
 ```
 
-[All of these languages are supported](https://doc.carrot2.org/#section.faq.preliminaries.supported-languages)
+Get a list of supported languages and algorithms with:
 
-For other requests, use:
+```ruby
+carrot2.list
+```
+
+Specify parameters with:
 
 ```ruby
-carrot2.request(
-  "dcs.c2stream" => xml_str
-)
+parameters = {
+  preprocessing: {
+    phraseDfThreshold: 1,
+    wordDfThreshold: 1
+  }
+}
+carrot2.cluster(documents, parameters: parameters)
+```
+
+See supported parameters for [Lingo](https://carrot2.github.io/release/4.0.0/doc/lingo-attributes/), [STC](https://carrot2.github.io/release/4.0.0/doc/stc-attributes/), and [Bisecting K-Means](https://carrot2.github.io/release/4.0.0/doc/kmeans-attributes/).
+
+Specify a [template](https://carrot2.github.io/release/4.0.0/doc/dcs-templates/) with:
+
+```ruby
+carrot2.cluster(documents, template: "lingo")
 ```
 
 ## Configuration
@@ -97,25 +106,15 @@ To specify the Carrot2 server, set `ENV["CARROT2_URL"]` or use:
 Carrot2.new(url: "http://localhost:8080")
 ```
 
-Set timeouts [master]
+Set timeouts
 
 ```ruby
 Carrot2.new(open_timeout: 3, read_timeout: 5)
 ```
 
-## Heroku
+## Resources
 
-Carrot2 can be easily deployed to Heroku thanks to support for [WAR deployment](https://devcenter.heroku.com/articles/war-deployment).
-
-You can find the `.war` file in the `war` directory in the dcs download. Then run:
-
-```sh
-heroku plugins:install heroku-cli-deploy
-heroku create <app_name>
-heroku war:deploy carrot2-dcs.war --app <app_name>
-```
-
-And set `ENV["CARROT2_URL"]` in your application.
+- [Carrot2 REST API Basics](https://carrot2.github.io/release/4.0.0/doc/rest-api-basics/)
 
 ## History
 
@@ -129,3 +128,12 @@ Everyone is encouraged to help improve this project. Here are a few ways you can
 - Fix bugs and [submit pull requests](https://github.com/ankane/carrot2/pulls)
 - Write, clarify, or fix documentation
 - Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/ankane/carrot2.git
+cd carrot2
+bundle install
+bundle exec rake test
+```

data/lib/carrot2.rb

@@ -1,63 +1,81 @@
-require "carrot2/version"
-require "builder"
-require "net/http"
+# dependencies
 require "json"
+require "net/http"
+
+# modules
+require "carrot2/version"
 
 class Carrot2
   class Error < StandardError; end
 
-  def initialize(url: nil, open_timeout: 3, read_timeout: nil)
-    @url = url || ENV["CARROT2_URL"] || "http://localhost:8080"
+  HEADERS = {
+    "Content-Type" => "application/json",
+    "Accept" => "application/json"
+  }
 
-    # add dcs/rest
-    @url = "#{@url.sub(/\/\z/, "")}/dcs/rest"
-    @uri = URI.parse(@url)
+  def initialize(url: nil, open_timeout: 3, read_timeout: nil)
+    url ||= ENV["CARROT2_URL"] || "http://localhost:8080"
+    @uri = URI.parse(url)
+    @http = Net::HTTP.new(@uri.host, @uri.port)
+    @http.use_ssl = true if @uri.scheme == "https"
+    @http.open_timeout = open_timeout if open_timeout
+    @http.read_timeout = read_timeout if read_timeout
+  end
 
-    @open_timeout = open_timeout
-    @read_timeout = read_timeout
+  def list
+    get("service/list")
   end
 
-  def cluster(documents, language: "English")
-    xml = Builder::XmlMarkup.new
-    xml.instruct! :xml, version: "1.0", encoding: "UTF-8"
-    xml.searchresult do |s|
-      documents.each do |document|
-        s.document do |d|
-          d.title document
-        end
-      end
+  def cluster(documents, language: nil, algorithm: nil, parameters: nil, template: nil)
+    # no defaults if template
+    unless template
+      language ||= "English"
+      algorithm ||= "Lingo"
+      parameters ||= {}
     end
 
-    request(
-      "dcs.clusters.only" => true,
-      "dcs.c2stream" => xml.target!,
-      "MultilingualClustering.defaultLanguage" => language.upcase,
-      multipart: true
-    )
+    # data
+    data = {
+      documents: documents.map { |v| v.is_a?(String) ? {field: v} : v }
+    }
+    data[:language] = language if language
+    data[:algorithm] = algorithm if algorithm
+    data[:parameters] = parameters if parameters
+
+    # path
+    path = "service/cluster"
+    path = "#{path}?#{URI.encode_www_form(template: template)}" if template
+
+    post(path, data)
   end
 
-  def request(params)
-    req = Net::HTTP::Post.new(@uri)
-    req.set_form_data(params.merge("dcs.output.format" => "JSON"))
+  private
 
-    options = {
-      use_ssl: @uri.scheme == "https"
-    }
-    options[:open_timeout] = @open_timeout if @open_timeout
-    options[:read_timeout] = @read_timeout if @read_timeout
+  def get(path)
+    handle_response do
+      @http.get("#{@uri.request_uri.chomp("/")}/#{path}", HEADERS)
+    end
+  end
 
-    response = Net::HTTP.start(@uri.hostname, @uri.port, options) do |http|
-      http.request(req)
+  def post(path, data)
+    handle_response do
+      @http.post("#{@uri.request_uri.chomp("/")}/#{path}", data.to_json, HEADERS)
+    end
+  end
+
+  def handle_response
+    begin
+      response = yield
+    rescue Errno::ECONNREFUSED => e
+      raise Carrot2::Error, e.message
     end
 
-    if response.code == "200"
-      JSON.parse(response.body)
-    else
-      body = response.body.to_s
-      # try to get reason from title
-      m = body.match(/<title>(.+)<\/title>/)
-      message = m ? m[1] : body
+    unless response.kind_of?(Net::HTTPSuccess)
+      body = JSON.parse(response.body) rescue {}
+      message = body["message"] || "Bad response: #{response.code}"
       raise Carrot2::Error, message
     end
+
+    JSON.parse(response.body)
   end
 end

data/lib/carrot2/version.rb

@@ -1,3 +1,3 @@
 class Carrot2
-  VERSION = "0.2.1"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: carrot2
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-10-28 00:00:00.000000000 Z
+date: 2020-07-30 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: builder
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -96,7 +82,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Ruby client for Carrot2