vasily 0.1.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ddac35717667230c45a6913c60c62c317afe8553
-  data.tar.gz: cf715294ef7d11c6de86f8a3cf511316f18c2a13
+  metadata.gz: 0e9f44d40f4eb754ebb6fcbda54434593f05ada4
+  data.tar.gz: 54b730601c28b30338ca70d2b29a5445155753e3
 SHA512:
-  metadata.gz: e79fde09b4b5698292959578e17a46c9659dc40ea52d45e3ea705a4f98ef04ac66dc06a19bfdc2715ea8168bcc8d88bea729e3259a0d7a9f688939eeab9f67f4
-  data.tar.gz: 16da7ff21e953f9d9500af7abb4549e71bed67abbda9daa5cdf8c01937c2493b6b5a716b70b95e7a1530b1390072da2e9ba9d0e8abdcadc58f900505566a44b2
+  metadata.gz: d1fc29b978dd18222e3d79b3c7b08cb0bfff042a3a590a9900795ceea5e39fe340688b04dcc385193684abcd5aee03b07fad4eb448df152020129557cb994067
+  data.tar.gz: c3b71abe353c043b784537c777de8b1e94cc57b51f581e91e21c35cffc0e40e2d9ee8257a59da766f4c8cf514fe14f2ecf55be14ed4ef417b4b4d0d27436afbb

data/README.md

@@ -21,7 +21,74 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+To use API, first you need to obtain (free) token from [textocat.com](http://textocat.com).
+Then you can use it to initialize client:
+```ruby
+client = Vasily::Client.new('auth_token')
+client.status # => 200
+```
+Let's analyze some documents!
+```ruby
+doc1 = Vasily::Document.new("Председатель совета директоров ОАО «МДМ Банк» Олег Вьюгин — о том, чему приведет обмен санкциями между Россией и Западом в следующем году. Беседовала Светлана Сухова.", "doc1")
+doc2 = Vasily::Document.new("Не перепутает Генри Форда и компанию «Форд» в документах", "doc2")
+doc3 = Vasily::Document.new("Штаб-квартира компании Форд Моторс располагается в городе Дирборн.", "doc3")
+batch_id, status = client.queue([doc1, doc2, doc3]) # => ["abcdefgh-1111-2222-3333-abcdefabcdef", "IN_PROGRESS"]
+status = client.request(batch_id) # => "FINISHED"
+```
+To retrieve entities:
+```ruby
+entities = client.retrieve([batch_id])
+puts JSON.pretty_generate(entities)
+[
+  {
+    "status": "SUCCESS",
+    "tag": "doc1",
+    "entities": [
+      {
+        "span": "Председатель совета директоров ОАО «МДМ Банк» Олег Вьюгин",
+        "category": "PERSON",
+        "beginOffset": 0,
+        "endOffset": 57
+      },
+      ...
+    ]
+  },
+  {
+    "status": "SUCCESS",
+    "tag": "doc2",
+    "entities": [
+      ...
+    ]
+  },
+  ...
+]
+```
+To perform search:
+```ruby
+search_result = client.search('ORGANIZATION:форд')
+puts JSON.pretty_generate(search_result)
+[
+  {
+    "status": "SUCCESS",
+    "tag": "doc2",
+    "entities": [
+      {
+        "span": "Генри Форда",
+        "category": "PERSON",
+        "beginOffset": 14,
+        "endOffset": 25
+      },
+      {
+        "span": "компанию «Форд»",
+        "category": "ORGANIZATION",
+        "beginOffset": 28,
+        "endOffset": 43
+      }
+    ]
+  },
+  ...
+]
+```
 
 ## Development
 

data/lib/vasily/client.rb

@@ -0,0 +1,59 @@
+require 'httparty'
+require 'vasily/document'
+require 'vasily/error'
+
+module Vasily
+  class Client
+    include HTTParty
+    base_uri 'api.textocat.com'
+
+    def initialize(auth_token)
+      @auth = { auth_token: auth_token }
+    end
+
+    def status
+      self.class.get('/status').code
+    end
+
+    def queue(docs)
+      body = docs.map(&:to_hash).to_json
+      options = { body: body, query: @auth, headers: {'Content-Type' => 'application/json'} }
+      response = self.class.post('/entity/queue', options)
+      if response.code == 202
+        return response['batchId'], response['status']
+      else
+        fail(Vasily::Error.from_message_and_code(response.body, response.code))
+      end
+    end
+
+    def request(batch_id)
+      options = { query: @auth.merge({ batch_id: batch_id }) }
+      response = self.class.get('/entity/request', options)
+      if response.code == 200
+        return response['status']
+      else
+        fail(Vasily::Error.from_message_and_code(response.body, response.code))
+      end
+    end
+
+    def retrieve(batch_ids)
+      batch_ids_query = URI.encode_www_form("batch_id" => batch_ids)
+      response = self.class.get('/entity/retrieve?' + batch_ids_query, { query: @auth })
+      if response.code == 200
+        return response['documents']
+      else
+        fail(Vasily::Error.from_message_and_code(response.body, response.code))
+      end
+    end
+
+    def search(search_query)
+      options = { query: @auth.merge({ search_query: search_query }) }
+      response = self.class.get('/entity/search', options)
+      if response.code == 200
+        return response['documents']
+      else
+        fail(Vasily::Error.from_message_and_code(response.body, response.code))
+      end
+    end
+  end
+end

data/lib/vasily/document.rb

@@ -0,0 +1,13 @@
+module Vasily
+  class Document
+    attr_reader :text, :tag
+    def initialize(text, tag)
+      @text = text
+      @tag = tag
+    end
+
+    def to_hash
+      {'text' => @text, 'tag' => @tag}
+    end
+  end
+end

data/lib/vasily/error.rb

@@ -0,0 +1,90 @@
+module Vasily
+  class Error < StandardError
+    attr_reader :code
+
+    # Raised when Textocat returns a 4xx HTTP status code
+    ClientError = Class.new(self)
+
+    # Raised when Textocat returns the HTTP status code 400
+    BadRequest = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 401
+    Unauthorized = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 402
+    LimitExceeded = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 403
+    Forbidden = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 404
+    NotFound = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 405
+    UnacceptableMethod = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 406
+    NotAcceptable = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 413
+    InputLimitExceeded = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 415
+    UnacceptableMIME = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 416
+    TooManyCollections = Class.new(ClientError)
+
+    # Raised when Textocat returns the HTTP status code 429
+    TooManyRequests = Class.new(ClientError)
+
+    # Raised when Textocat returns a 5xx HTTP status code
+    ServerError = Class.new(self)
+
+    # Raised when Textocat returns the HTTP status code 500
+    InternalServerError = Class.new(ServerError)
+
+    # Raised when Twitter returns the HTTP status code 502
+    BadGateway = Class.new(ServerError)
+
+    # Raised when Twitter returns the HTTP status code 503
+    ServiceUnavailable = Class.new(ServerError)
+
+    # Raised when Twitter returns the HTTP status code 504
+    GatewayTimeout = Class.new(ServerError)
+
+    ERRORS = {
+              400 => Vasily::Error::BadRequest,
+              401 => Vasily::Error::Unauthorized,
+              402 => Vasily::Error::LimitExceeded,
+              403 => Vasily::Error::Forbidden,
+              404 => Vasily::Error::NotFound,
+              405 => Vasily::Error::UnacceptableMethod,
+              406 => Vasily::Error::NotAcceptable,
+              413 => Vasily::Error::InputLimitExceeded,
+              415 => Vasily::Error::UnacceptableMIME,
+              416 => Vasily::Error::TooManyCollections,
+              429 => Vasily::Error::TooManyRequests,
+              500 => Vasily::Error::InternalServerError,
+              502 => Vasily::Error::BadGateway,
+              503 => Vasily::Error::ServiceUnavailable,
+              504 => Vasily::Error::GatewayTimeout,
+             }
+
+    class << self
+      def from_message_and_code(message = '', code)
+        klass = ERRORS[code]
+        if klass.nil?
+          nil
+        else
+          klass.new(message, code)
+        end
+      end
+    end
+
+    def initialize(message = '', code = nil)
+      super(message)
+      @code = code
+    end
+  end
+end

data/lib/vasily/version.rb

@@ -1,3 +1,3 @@
 module Vasily
-  VERSION = "0.1.0"
+  VERSION = "0.3.0"
 end

data/lib/vasily.rb

@@ -1,5 +1,4 @@
 require "vasily/version"
-
-module Vasily
-  # Your code goes here...
-end
+require "vasily/client"
+require "vasily/document"
+require "vasily/error"

data/vasily.gemspec

@@ -19,4 +19,6 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.10"
   spec.add_development_dependency "rake", "~> 10.0"
+
+  spec.add_runtime_dependency "httparty"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: vasily
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Fedor Nikolaev
@@ -38,6 +38,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: httparty
+  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'
 description: 
 email:
 - fsqcds@gmail.com
@@ -52,6 +66,9 @@ files:
 - bin/console
 - bin/setup
 - lib/vasily.rb
+- lib/vasily/client.rb
+- lib/vasily/document.rb
+- lib/vasily/error.rb
 - lib/vasily/version.rb
 - vasily.gemspec
 homepage: https://github.com/fedorn/vasily