vasily 0.1.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +68 -1
- data/lib/vasily/client.rb +59 -0
- data/lib/vasily/document.rb +13 -0
- data/lib/vasily/error.rb +90 -0
- data/lib/vasily/version.rb +1 -1
- data/lib/vasily.rb +3 -4
- data/vasily.gemspec +2 -0
- metadata +18 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0e9f44d40f4eb754ebb6fcbda54434593f05ada4
|
4
|
+
data.tar.gz: 54b730601c28b30338ca70d2b29a5445155753e3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d1fc29b978dd18222e3d79b3c7b08cb0bfff042a3a590a9900795ceea5e39fe340688b04dcc385193684abcd5aee03b07fad4eb448df152020129557cb994067
|
7
|
+
data.tar.gz: c3b71abe353c043b784537c777de8b1e94cc57b51f581e91e21c35cffc0e40e2d9ee8257a59da766f4c8cf514fe14f2ecf55be14ed4ef417b4b4d0d27436afbb
|
data/README.md
CHANGED
@@ -21,7 +21,74 @@ Or install it yourself as:
|
|
21
21
|
|
22
22
|
## Usage
|
23
23
|
|
24
|
-
|
24
|
+
To use API, first you need to obtain (free) token from [textocat.com](http://textocat.com).
|
25
|
+
Then you can use it to initialize client:
|
26
|
+
```ruby
|
27
|
+
client = Vasily::Client.new('auth_token')
|
28
|
+
client.status # => 200
|
29
|
+
```
|
30
|
+
Let's analyze some documents!
|
31
|
+
```ruby
|
32
|
+
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")
|
33
|
+
doc2 = Vasily::Document.new("Не перепутает Генри Форда и компанию «Форд» в документах", "doc2")
|
34
|
+
doc3 = Vasily::Document.new("Штаб-квартира компании Форд Моторс располагается в городе Дирборн.", "doc3")
|
35
|
+
batch_id, status = client.queue([doc1, doc2, doc3]) # => ["abcdefgh-1111-2222-3333-abcdefabcdef", "IN_PROGRESS"]
|
36
|
+
status = client.request(batch_id) # => "FINISHED"
|
37
|
+
```
|
38
|
+
To retrieve entities:
|
39
|
+
```ruby
|
40
|
+
entities = client.retrieve([batch_id])
|
41
|
+
puts JSON.pretty_generate(entities)
|
42
|
+
[
|
43
|
+
{
|
44
|
+
"status": "SUCCESS",
|
45
|
+
"tag": "doc1",
|
46
|
+
"entities": [
|
47
|
+
{
|
48
|
+
"span": "Председатель совета директоров ОАО «МДМ Банк» Олег Вьюгин",
|
49
|
+
"category": "PERSON",
|
50
|
+
"beginOffset": 0,
|
51
|
+
"endOffset": 57
|
52
|
+
},
|
53
|
+
...
|
54
|
+
]
|
55
|
+
},
|
56
|
+
{
|
57
|
+
"status": "SUCCESS",
|
58
|
+
"tag": "doc2",
|
59
|
+
"entities": [
|
60
|
+
...
|
61
|
+
]
|
62
|
+
},
|
63
|
+
...
|
64
|
+
]
|
65
|
+
```
|
66
|
+
To perform search:
|
67
|
+
```ruby
|
68
|
+
search_result = client.search('ORGANIZATION:форд')
|
69
|
+
puts JSON.pretty_generate(search_result)
|
70
|
+
[
|
71
|
+
{
|
72
|
+
"status": "SUCCESS",
|
73
|
+
"tag": "doc2",
|
74
|
+
"entities": [
|
75
|
+
{
|
76
|
+
"span": "Генри Форда",
|
77
|
+
"category": "PERSON",
|
78
|
+
"beginOffset": 14,
|
79
|
+
"endOffset": 25
|
80
|
+
},
|
81
|
+
{
|
82
|
+
"span": "компанию «Форд»",
|
83
|
+
"category": "ORGANIZATION",
|
84
|
+
"beginOffset": 28,
|
85
|
+
"endOffset": 43
|
86
|
+
}
|
87
|
+
]
|
88
|
+
},
|
89
|
+
...
|
90
|
+
]
|
91
|
+
```
|
25
92
|
|
26
93
|
## Development
|
27
94
|
|
@@ -0,0 +1,59 @@
|
|
1
|
+
require 'httparty'
|
2
|
+
require 'vasily/document'
|
3
|
+
require 'vasily/error'
|
4
|
+
|
5
|
+
module Vasily
|
6
|
+
class Client
|
7
|
+
include HTTParty
|
8
|
+
base_uri 'api.textocat.com'
|
9
|
+
|
10
|
+
def initialize(auth_token)
|
11
|
+
@auth = { auth_token: auth_token }
|
12
|
+
end
|
13
|
+
|
14
|
+
def status
|
15
|
+
self.class.get('/status').code
|
16
|
+
end
|
17
|
+
|
18
|
+
def queue(docs)
|
19
|
+
body = docs.map(&:to_hash).to_json
|
20
|
+
options = { body: body, query: @auth, headers: {'Content-Type' => 'application/json'} }
|
21
|
+
response = self.class.post('/entity/queue', options)
|
22
|
+
if response.code == 202
|
23
|
+
return response['batchId'], response['status']
|
24
|
+
else
|
25
|
+
fail(Vasily::Error.from_message_and_code(response.body, response.code))
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def request(batch_id)
|
30
|
+
options = { query: @auth.merge({ batch_id: batch_id }) }
|
31
|
+
response = self.class.get('/entity/request', options)
|
32
|
+
if response.code == 200
|
33
|
+
return response['status']
|
34
|
+
else
|
35
|
+
fail(Vasily::Error.from_message_and_code(response.body, response.code))
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
def retrieve(batch_ids)
|
40
|
+
batch_ids_query = URI.encode_www_form("batch_id" => batch_ids)
|
41
|
+
response = self.class.get('/entity/retrieve?' + batch_ids_query, { query: @auth })
|
42
|
+
if response.code == 200
|
43
|
+
return response['documents']
|
44
|
+
else
|
45
|
+
fail(Vasily::Error.from_message_and_code(response.body, response.code))
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
def search(search_query)
|
50
|
+
options = { query: @auth.merge({ search_query: search_query }) }
|
51
|
+
response = self.class.get('/entity/search', options)
|
52
|
+
if response.code == 200
|
53
|
+
return response['documents']
|
54
|
+
else
|
55
|
+
fail(Vasily::Error.from_message_and_code(response.body, response.code))
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
data/lib/vasily/error.rb
ADDED
@@ -0,0 +1,90 @@
|
|
1
|
+
module Vasily
|
2
|
+
class Error < StandardError
|
3
|
+
attr_reader :code
|
4
|
+
|
5
|
+
# Raised when Textocat returns a 4xx HTTP status code
|
6
|
+
ClientError = Class.new(self)
|
7
|
+
|
8
|
+
# Raised when Textocat returns the HTTP status code 400
|
9
|
+
BadRequest = Class.new(ClientError)
|
10
|
+
|
11
|
+
# Raised when Textocat returns the HTTP status code 401
|
12
|
+
Unauthorized = Class.new(ClientError)
|
13
|
+
|
14
|
+
# Raised when Textocat returns the HTTP status code 402
|
15
|
+
LimitExceeded = Class.new(ClientError)
|
16
|
+
|
17
|
+
# Raised when Textocat returns the HTTP status code 403
|
18
|
+
Forbidden = Class.new(ClientError)
|
19
|
+
|
20
|
+
# Raised when Textocat returns the HTTP status code 404
|
21
|
+
NotFound = Class.new(ClientError)
|
22
|
+
|
23
|
+
# Raised when Textocat returns the HTTP status code 405
|
24
|
+
UnacceptableMethod = Class.new(ClientError)
|
25
|
+
|
26
|
+
# Raised when Textocat returns the HTTP status code 406
|
27
|
+
NotAcceptable = Class.new(ClientError)
|
28
|
+
|
29
|
+
# Raised when Textocat returns the HTTP status code 413
|
30
|
+
InputLimitExceeded = Class.new(ClientError)
|
31
|
+
|
32
|
+
# Raised when Textocat returns the HTTP status code 415
|
33
|
+
UnacceptableMIME = Class.new(ClientError)
|
34
|
+
|
35
|
+
# Raised when Textocat returns the HTTP status code 416
|
36
|
+
TooManyCollections = Class.new(ClientError)
|
37
|
+
|
38
|
+
# Raised when Textocat returns the HTTP status code 429
|
39
|
+
TooManyRequests = Class.new(ClientError)
|
40
|
+
|
41
|
+
# Raised when Textocat returns a 5xx HTTP status code
|
42
|
+
ServerError = Class.new(self)
|
43
|
+
|
44
|
+
# Raised when Textocat returns the HTTP status code 500
|
45
|
+
InternalServerError = Class.new(ServerError)
|
46
|
+
|
47
|
+
# Raised when Twitter returns the HTTP status code 502
|
48
|
+
BadGateway = Class.new(ServerError)
|
49
|
+
|
50
|
+
# Raised when Twitter returns the HTTP status code 503
|
51
|
+
ServiceUnavailable = Class.new(ServerError)
|
52
|
+
|
53
|
+
# Raised when Twitter returns the HTTP status code 504
|
54
|
+
GatewayTimeout = Class.new(ServerError)
|
55
|
+
|
56
|
+
ERRORS = {
|
57
|
+
400 => Vasily::Error::BadRequest,
|
58
|
+
401 => Vasily::Error::Unauthorized,
|
59
|
+
402 => Vasily::Error::LimitExceeded,
|
60
|
+
403 => Vasily::Error::Forbidden,
|
61
|
+
404 => Vasily::Error::NotFound,
|
62
|
+
405 => Vasily::Error::UnacceptableMethod,
|
63
|
+
406 => Vasily::Error::NotAcceptable,
|
64
|
+
413 => Vasily::Error::InputLimitExceeded,
|
65
|
+
415 => Vasily::Error::UnacceptableMIME,
|
66
|
+
416 => Vasily::Error::TooManyCollections,
|
67
|
+
429 => Vasily::Error::TooManyRequests,
|
68
|
+
500 => Vasily::Error::InternalServerError,
|
69
|
+
502 => Vasily::Error::BadGateway,
|
70
|
+
503 => Vasily::Error::ServiceUnavailable,
|
71
|
+
504 => Vasily::Error::GatewayTimeout,
|
72
|
+
}
|
73
|
+
|
74
|
+
class << self
|
75
|
+
def from_message_and_code(message = '', code)
|
76
|
+
klass = ERRORS[code]
|
77
|
+
if klass.nil?
|
78
|
+
nil
|
79
|
+
else
|
80
|
+
klass.new(message, code)
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def initialize(message = '', code = nil)
|
86
|
+
super(message)
|
87
|
+
@code = code
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
data/lib/vasily/version.rb
CHANGED
data/lib/vasily.rb
CHANGED
data/vasily.gemspec
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: vasily
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Fedor Nikolaev
|
@@ -38,6 +38,20 @@ dependencies:
|
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: httparty
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
41
55
|
description:
|
42
56
|
email:
|
43
57
|
- fsqcds@gmail.com
|
@@ -52,6 +66,9 @@ files:
|
|
52
66
|
- bin/console
|
53
67
|
- bin/setup
|
54
68
|
- lib/vasily.rb
|
69
|
+
- lib/vasily/client.rb
|
70
|
+
- lib/vasily/document.rb
|
71
|
+
- lib/vasily/error.rb
|
55
72
|
- lib/vasily/version.rb
|
56
73
|
- vasily.gemspec
|
57
74
|
homepage: https://github.com/fedorn/vasily
|