google-cloud-language 0.20.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/google-cloud-language.rb +116 -0
- data/lib/google/cloud/language.rb +229 -0
- data/lib/google/cloud/language/annotation.rb +630 -0
- data/lib/google/cloud/language/credentials.rb +32 -0
- data/lib/google/cloud/language/document.rb +368 -0
- data/lib/google/cloud/language/project.rb +365 -0
- data/lib/google/cloud/language/service.rb +112 -0
- data/lib/google/cloud/language/v1beta1/language_service_api.rb +204 -0
- data/lib/google/cloud/language/v1beta1/language_service_client_config.json +43 -0
- data/lib/google/cloud/language/v1beta1/language_service_pb.rb +228 -0
- data/lib/google/cloud/language/v1beta1/language_service_services_pb.rb +54 -0
- data/lib/google/cloud/language/version.rb +22 -0
- metadata +241 -0
@@ -0,0 +1,32 @@
|
|
1
|
+
# Copyright 2016 Google Inc. All rights reserved.
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
|
16
|
+
require "google/cloud/credentials"
|
17
|
+
require "google/cloud/language/v1beta1/language_service_api"
|
18
|
+
|
19
|
+
module Google
|
20
|
+
module Cloud
|
21
|
+
module Language
|
22
|
+
##
|
23
|
+
# @private Represents the OAuth 2.0 signing logic for Language.
|
24
|
+
class Credentials < Google::Cloud::Credentials
|
25
|
+
SCOPE = Google::Cloud::Language::V1beta1::LanguageServiceApi::ALL_SCOPES
|
26
|
+
PATH_ENV_VARS = %w(LANGUAGE_KEYFILE GOOGLE_CLOUD_KEYFILE GCLOUD_KEYFILE)
|
27
|
+
JSON_ENV_VARS = %w(LANGUAGE_KEYFILE_JSON GOOGLE_CLOUD_KEYFILE_JSON
|
28
|
+
GCLOUD_KEYFILE_JSON)
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,368 @@
|
|
1
|
+
# Copyright 2016 Google Inc. All rights reserved.
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
|
16
|
+
require "google/cloud/language/annotation"
|
17
|
+
|
18
|
+
module Google
|
19
|
+
module Cloud
|
20
|
+
module Language
|
21
|
+
##
|
22
|
+
# # Document
|
23
|
+
#
|
24
|
+
# Represents a document for the Language service.
|
25
|
+
#
|
26
|
+
# Cloud Natural Language API supports UTF-8, UTF-16, and UTF-32 encodings.
|
27
|
+
# (Ruby uses UTF-8 natively, which is the default sent to the API, so
|
28
|
+
# unless you're working with text processed in different platform, you
|
29
|
+
# should not need to set the encoding type.)
|
30
|
+
#
|
31
|
+
# Be aware that only English, Spanish, and Japanese language content are
|
32
|
+
# supported, and sentiment analysis only supports English text.
|
33
|
+
#
|
34
|
+
# See {Project#document}.
|
35
|
+
#
|
36
|
+
# @example
|
37
|
+
# require "google/cloud"
|
38
|
+
#
|
39
|
+
# gcloud = Google::Cloud.new
|
40
|
+
# language = gcloud.language
|
41
|
+
#
|
42
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
43
|
+
# document = language.document content
|
44
|
+
# annotation = document.annotate
|
45
|
+
#
|
46
|
+
# annotation.entities.count #=> 2
|
47
|
+
# annotation.sentiment.polarity #=> 1.0
|
48
|
+
# annotation.sentiment.magnitude #=> 0.8999999761581421
|
49
|
+
# annotation.sentences.count #=> 1
|
50
|
+
# annotation.tokens.count #=> 10
|
51
|
+
#
|
52
|
+
class Document
|
53
|
+
##
|
54
|
+
# @private The gRPC Service object.
|
55
|
+
attr_accessor :service
|
56
|
+
|
57
|
+
##
|
58
|
+
# @private Creates a new document instance.
|
59
|
+
def initialize
|
60
|
+
@grpc = nil
|
61
|
+
@service = nil
|
62
|
+
end
|
63
|
+
|
64
|
+
##
|
65
|
+
# @private Whether the document has content.
|
66
|
+
#
|
67
|
+
def content?
|
68
|
+
@grpc.source == :content
|
69
|
+
end
|
70
|
+
|
71
|
+
##
|
72
|
+
# @private Whether the document source is a Google Cloud Storage URI.
|
73
|
+
#
|
74
|
+
def url?
|
75
|
+
@grpc.source == :gcs_content_uri
|
76
|
+
end
|
77
|
+
|
78
|
+
##
|
79
|
+
# @private The source of the document's content.
|
80
|
+
#
|
81
|
+
def source
|
82
|
+
return @grpc.content if content?
|
83
|
+
@grpc.gcs_content_uri
|
84
|
+
end
|
85
|
+
|
86
|
+
##
|
87
|
+
# The document's format.
|
88
|
+
#
|
89
|
+
# @return [Symbol] `:text` or `:html`
|
90
|
+
#
|
91
|
+
def format
|
92
|
+
return :text if text?
|
93
|
+
return :html if html?
|
94
|
+
end
|
95
|
+
|
96
|
+
##
|
97
|
+
# Sets the document's format.
|
98
|
+
#
|
99
|
+
# @param [Symbol, String] new_format Accepted values are `:text` or
|
100
|
+
# `:html`.
|
101
|
+
#
|
102
|
+
# @example
|
103
|
+
# document = language.document "<p>The Old Man and the Sea</p>"
|
104
|
+
# document.format = :html
|
105
|
+
#
|
106
|
+
def format= new_format
|
107
|
+
@grpc.type = :PLAIN_TEXT if new_format.to_s == "text"
|
108
|
+
@grpc.type = :HTML if new_format.to_s == "html"
|
109
|
+
@grpc.type
|
110
|
+
end
|
111
|
+
|
112
|
+
##
|
113
|
+
# Whether the document is the `TEXT` format.
|
114
|
+
#
|
115
|
+
# @return [Boolean]
|
116
|
+
#
|
117
|
+
def text?
|
118
|
+
@grpc.type == :PLAIN_TEXT
|
119
|
+
end
|
120
|
+
|
121
|
+
##
|
122
|
+
# Sets the document to the `TEXT` format.
|
123
|
+
#
|
124
|
+
def text!
|
125
|
+
@grpc.type = :PLAIN_TEXT
|
126
|
+
end
|
127
|
+
|
128
|
+
##
|
129
|
+
# Whether the document is the `HTML` format.
|
130
|
+
#
|
131
|
+
# @return [Boolean]
|
132
|
+
#
|
133
|
+
def html?
|
134
|
+
@grpc.type == :HTML
|
135
|
+
end
|
136
|
+
|
137
|
+
##
|
138
|
+
# Sets the document to the `HTML` format.
|
139
|
+
#
|
140
|
+
def html!
|
141
|
+
@grpc.type = :HTML
|
142
|
+
end
|
143
|
+
|
144
|
+
##
|
145
|
+
# The document's language. ISO and BCP-47 language codes are supported.
|
146
|
+
#
|
147
|
+
# @return [String]
|
148
|
+
#
|
149
|
+
def language
|
150
|
+
@grpc.language
|
151
|
+
end
|
152
|
+
|
153
|
+
##
|
154
|
+
# Sets the document's language.
|
155
|
+
#
|
156
|
+
# @param [String, Symbol] new_language ISO and BCP-47 language codes are
|
157
|
+
# accepted.
|
158
|
+
#
|
159
|
+
# @example
|
160
|
+
# document = language.document "<p>El viejo y el mar</p>"
|
161
|
+
# document.language = "es"
|
162
|
+
#
|
163
|
+
def language= new_language
|
164
|
+
@grpc.language = new_language.to_s
|
165
|
+
end
|
166
|
+
|
167
|
+
##
|
168
|
+
# Analyzes the document and returns sentiment, entity, and syntactic
|
169
|
+
# feature results, depending on the option flags. Calling `annotate`
|
170
|
+
# with no arguments will perform **all** analysis features. Each feature
|
171
|
+
# is priced separately. See [Pricing](https://cloud.google.com/natural-language/pricing)
|
172
|
+
# for details.
|
173
|
+
#
|
174
|
+
# @param [Boolean] sentiment Whether to perform sentiment analysis.
|
175
|
+
# Optional. The default is `false`. If every feature option is
|
176
|
+
# `false`, **all** features will be performed.
|
177
|
+
# @param [Boolean] entities Whether to perform the entity analysis.
|
178
|
+
# Optional. The default is `false`. If every feature option is
|
179
|
+
# `false`, **all** features will be performed.
|
180
|
+
# @param [Boolean] syntax Whether to perform syntactic analysis.
|
181
|
+
# Optional. The default is `false`. If every feature option is
|
182
|
+
# `false`, **all** features will be performed.
|
183
|
+
# @param [String] encoding The encoding type used by the API to
|
184
|
+
# calculate offsets. Optional.
|
185
|
+
#
|
186
|
+
# @return [Annotation>] The results of the content analysis.
|
187
|
+
#
|
188
|
+
# @example
|
189
|
+
# require "google/cloud"
|
190
|
+
#
|
191
|
+
# gcloud = Google::Cloud.new
|
192
|
+
# language = gcloud.language
|
193
|
+
#
|
194
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
195
|
+
# document = language.document content
|
196
|
+
# annotation = document.annotate
|
197
|
+
#
|
198
|
+
# annotation.sentiment.polarity #=> 1.0
|
199
|
+
# annotation.sentiment.magnitude #=> 0.8999999761581421
|
200
|
+
# annotation.entities.count #=> 2
|
201
|
+
# annotation.sentences.count #=> 1
|
202
|
+
# annotation.tokens.count #=> 10
|
203
|
+
#
|
204
|
+
# @example With feature flags:
|
205
|
+
# require "google/cloud"
|
206
|
+
#
|
207
|
+
# gcloud = Google::Cloud.new
|
208
|
+
# language = gcloud.language
|
209
|
+
#
|
210
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
211
|
+
# document = language.document content
|
212
|
+
# annotation = document.annotate entities: true, text: true
|
213
|
+
#
|
214
|
+
# annotation.sentiment #=> nil
|
215
|
+
# annotation.entities.count #=> 2
|
216
|
+
# annotation.sentences.count #=> 1
|
217
|
+
# annotation.tokens.count #=> 10
|
218
|
+
#
|
219
|
+
def annotate sentiment: false, entities: false, syntax: false,
|
220
|
+
encoding: nil
|
221
|
+
ensure_service!
|
222
|
+
grpc = service.annotate to_grpc, sentiment: sentiment,
|
223
|
+
entities: entities,
|
224
|
+
syntax: syntax,
|
225
|
+
encoding: encoding
|
226
|
+
Annotation.from_grpc grpc
|
227
|
+
end
|
228
|
+
alias_method :mark, :annotate
|
229
|
+
alias_method :detect, :annotate
|
230
|
+
|
231
|
+
##
|
232
|
+
# Syntactic analysis extracts linguistic information, breaking up the
|
233
|
+
# given text into a series of sentences and tokens (generally, word
|
234
|
+
# boundaries), providing further analysis on those tokens.
|
235
|
+
#
|
236
|
+
# @param [String] encoding The encoding type used by the API to
|
237
|
+
# calculate offsets. Optional.
|
238
|
+
#
|
239
|
+
# @return [Annotation>] The results for the content analysis.
|
240
|
+
#
|
241
|
+
# @example
|
242
|
+
# require "google/cloud"
|
243
|
+
#
|
244
|
+
# gcloud = Google::Cloud.new
|
245
|
+
# language = gcloud.language
|
246
|
+
#
|
247
|
+
# document = language.document "Hello world!"
|
248
|
+
#
|
249
|
+
# annotation = document.syntax
|
250
|
+
# annotation.thing #=> Some Result
|
251
|
+
#
|
252
|
+
def syntax encoding: nil
|
253
|
+
annotate syntax: true, encoding: encoding
|
254
|
+
end
|
255
|
+
|
256
|
+
##
|
257
|
+
# Entity analysis inspects the given text for known entities (proper
|
258
|
+
# nouns such as public figures, landmarks, etc.) and returns information
|
259
|
+
# about those entities.
|
260
|
+
#
|
261
|
+
# @param [String] encoding The encoding type used by the API to
|
262
|
+
# calculate offsets. Optional.
|
263
|
+
#
|
264
|
+
# @return [Annotation::Entities>] The results for the entities analysis.
|
265
|
+
#
|
266
|
+
# @example
|
267
|
+
# require "google/cloud"
|
268
|
+
#
|
269
|
+
# gcloud = Google::Cloud.new
|
270
|
+
# language = gcloud.language
|
271
|
+
#
|
272
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
273
|
+
# document = language.document content
|
274
|
+
# entities = document.entities # API call
|
275
|
+
#
|
276
|
+
# entities.count #=> 2
|
277
|
+
# entities.first.name #=> "Darth Vader"
|
278
|
+
# entities.first.type #=> :PERSON
|
279
|
+
# entities.first.name #=> "Star Wars"
|
280
|
+
# entities.first.type #=> :WORK_OF_ART
|
281
|
+
#
|
282
|
+
def entities encoding: nil
|
283
|
+
ensure_service!
|
284
|
+
grpc = service.entities to_grpc, encoding: encoding
|
285
|
+
Annotation::Entities.from_grpc grpc
|
286
|
+
end
|
287
|
+
|
288
|
+
##
|
289
|
+
# Sentiment analysis inspects the given text and identifies the
|
290
|
+
# prevailing emotional opinion within the text, especially to determine
|
291
|
+
# a writer's attitude as positive, negative, or neutral. Currently, only
|
292
|
+
# English is supported for sentiment analysis.
|
293
|
+
#
|
294
|
+
# @return [Annotation::Sentiment>] The results for the sentiment
|
295
|
+
# analysis.
|
296
|
+
#
|
297
|
+
# @example
|
298
|
+
# require "google/cloud"
|
299
|
+
#
|
300
|
+
# gcloud = Google::Cloud.new
|
301
|
+
# language = gcloud.language
|
302
|
+
#
|
303
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
304
|
+
# document = language.document content
|
305
|
+
# sentiment = document.sentiment # API call
|
306
|
+
#
|
307
|
+
# sentiment.polarity #=> 1.0
|
308
|
+
# sentiment.magnitude #=> 0.8999999761581421
|
309
|
+
#
|
310
|
+
def sentiment
|
311
|
+
ensure_service!
|
312
|
+
grpc = service.sentiment to_grpc
|
313
|
+
Annotation::Sentiment.from_grpc grpc
|
314
|
+
end
|
315
|
+
|
316
|
+
# @private
|
317
|
+
def inspect
|
318
|
+
"#<#{self.class.name} (" \
|
319
|
+
"#{(content? ? "\"#{source[0, 16]}...\"" : source)}, " \
|
320
|
+
"format: #{format.inspect}, language: #{language.inspect})>"
|
321
|
+
end
|
322
|
+
|
323
|
+
##
|
324
|
+
# @private New gRPC object.
|
325
|
+
def to_grpc
|
326
|
+
@grpc
|
327
|
+
end
|
328
|
+
|
329
|
+
##
|
330
|
+
# @private
|
331
|
+
def self.from_grpc grpc, service
|
332
|
+
new.tap do |i|
|
333
|
+
i.instance_variable_set :@grpc, grpc
|
334
|
+
i.instance_variable_set :@service, service
|
335
|
+
end
|
336
|
+
end
|
337
|
+
|
338
|
+
##
|
339
|
+
# @private
|
340
|
+
def self.from_source source, service, format: nil, language: nil
|
341
|
+
source = String source
|
342
|
+
grpc = Google::Cloud::Language::V1beta1::Document.new
|
343
|
+
if source.start_with? "gs://"
|
344
|
+
grpc.gcs_content_uri = source
|
345
|
+
format ||= :html if source.end_with? ".html"
|
346
|
+
else
|
347
|
+
grpc.content = source
|
348
|
+
end
|
349
|
+
if format.to_s == "html"
|
350
|
+
grpc.type = :HTML
|
351
|
+
else
|
352
|
+
grpc.type = :PLAIN_TEXT
|
353
|
+
end
|
354
|
+
grpc.language = language.to_s unless language.nil?
|
355
|
+
from_grpc grpc, service
|
356
|
+
end
|
357
|
+
|
358
|
+
protected
|
359
|
+
|
360
|
+
##
|
361
|
+
# Raise an error unless an active language project object is available.
|
362
|
+
def ensure_service!
|
363
|
+
fail "Must have active connection" unless service
|
364
|
+
end
|
365
|
+
end
|
366
|
+
end
|
367
|
+
end
|
368
|
+
end
|
@@ -0,0 +1,365 @@
|
|
1
|
+
# Copyright 2016 Google Inc. All rights reserved.
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
|
16
|
+
require "google/cloud/errors"
|
17
|
+
require "google/cloud/core/gce"
|
18
|
+
require "google/cloud/language/service"
|
19
|
+
require "google/cloud/language/document"
|
20
|
+
require "google/cloud/language/annotation"
|
21
|
+
|
22
|
+
module Google
|
23
|
+
module Cloud
|
24
|
+
module Language
|
25
|
+
##
|
26
|
+
# # Project
|
27
|
+
#
|
28
|
+
# Google Cloud Natural Language API reveals the structure and meaning of
|
29
|
+
# text by offering powerful machine learning models in an easy to use REST
|
30
|
+
# API. You can analyze text uploaded in your request or integrate with
|
31
|
+
# your document storage on Google Cloud Storage.
|
32
|
+
#
|
33
|
+
# See {Google::Cloud#language}
|
34
|
+
#
|
35
|
+
# @example
|
36
|
+
# require "google/cloud"
|
37
|
+
#
|
38
|
+
# gcloud = Google::Cloud.new
|
39
|
+
# language = gcloud.language
|
40
|
+
#
|
41
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
42
|
+
# annotation = language.annotate content
|
43
|
+
#
|
44
|
+
# annotation.sentiment.polarity #=> 1.0
|
45
|
+
# annotation.sentiment.magnitude #=> 0.8999999761581421
|
46
|
+
# annotation.entities.count #=> 2
|
47
|
+
# annotation.sentences.count #=> 1
|
48
|
+
# annotation.tokens.count #=> 10
|
49
|
+
#
|
50
|
+
class Project
|
51
|
+
##
|
52
|
+
# @private The gRPC Service object.
|
53
|
+
attr_accessor :service
|
54
|
+
|
55
|
+
##
|
56
|
+
# @private Creates a new Language Project instance.
|
57
|
+
def initialize service
|
58
|
+
@service = service
|
59
|
+
end
|
60
|
+
|
61
|
+
# The Language project connected to.
|
62
|
+
#
|
63
|
+
# @example
|
64
|
+
# require "google/cloud"
|
65
|
+
#
|
66
|
+
# gcloud = Google::Cloud.new "my-project-id",
|
67
|
+
# "/path/to/keyfile.json"
|
68
|
+
# language = gcloud.language
|
69
|
+
#
|
70
|
+
# language.project #=> "my-project-id"
|
71
|
+
#
|
72
|
+
def project
|
73
|
+
service.project
|
74
|
+
end
|
75
|
+
|
76
|
+
##
|
77
|
+
# @private Default project.
|
78
|
+
def self.default_project
|
79
|
+
ENV["LANGUAGE_PROJECT"] ||
|
80
|
+
ENV["GOOGLE_CLOUD_PROJECT"] ||
|
81
|
+
ENV["GCLOUD_PROJECT"] ||
|
82
|
+
Google::Cloud::Core::GCE.project_id
|
83
|
+
end
|
84
|
+
|
85
|
+
##
|
86
|
+
# Returns a new document from the given content. No API call is made.
|
87
|
+
#
|
88
|
+
# @param [String, Google::Cloud::Storage::File] content A string of text
|
89
|
+
# to be annotated, or a Cloud Storage URI of the form
|
90
|
+
# `"gs://bucketname/path/to/document.ext"`; or an instance of
|
91
|
+
# Google::Cloud::Storage::File of the text to be annotated.
|
92
|
+
# @param [String] format The format of the document (TEXT/HTML).
|
93
|
+
# Optional.
|
94
|
+
# @param [String] language The language of the document (if not
|
95
|
+
# specified, the language is automatically detected). Both ISO and
|
96
|
+
# BCP-47 language codes are accepted. Optional.
|
97
|
+
#
|
98
|
+
# @return [Document] An document for the Language service.
|
99
|
+
#
|
100
|
+
# @example
|
101
|
+
# require "google/cloud"
|
102
|
+
#
|
103
|
+
# gcloud = Google::Cloud.new
|
104
|
+
# language = gcloud.language
|
105
|
+
#
|
106
|
+
# document = language.document "It was the best of times, it was..."
|
107
|
+
#
|
108
|
+
# @example With a Google Cloud Storage URI:
|
109
|
+
# require "google/cloud"
|
110
|
+
#
|
111
|
+
# gcloud = Google::Cloud.new
|
112
|
+
# language = gcloud.language
|
113
|
+
#
|
114
|
+
# document = language.document "gs://bucket-name/path/to/document"
|
115
|
+
#
|
116
|
+
# @example With a Google Cloud Storage File object:
|
117
|
+
# require "google/cloud"
|
118
|
+
#
|
119
|
+
# gcloud = Google::Cloud.new
|
120
|
+
# storage = gcloud.storage
|
121
|
+
#
|
122
|
+
# bucket = storage.bucket "bucket-name"
|
123
|
+
# file = bucket.file "path/to/document"
|
124
|
+
#
|
125
|
+
# language = gcloud.language
|
126
|
+
#
|
127
|
+
# document = language.document file
|
128
|
+
#
|
129
|
+
# @example With `format` and `language` options:
|
130
|
+
# require "google/cloud"
|
131
|
+
#
|
132
|
+
# gcloud = Google::Cloud.new
|
133
|
+
# language = gcloud.language
|
134
|
+
#
|
135
|
+
# document = language.document "<p>El viejo y el mar</p>",
|
136
|
+
# format: :html, language: "es"
|
137
|
+
#
|
138
|
+
def document content, format: nil, language: nil
|
139
|
+
content = content.to_gs_url if content.respond_to? :to_gs_url
|
140
|
+
if content.is_a? Document
|
141
|
+
# Create new document with the provided format and language
|
142
|
+
Document.from_source content.source, @service,
|
143
|
+
format: (format || content.format),
|
144
|
+
language: (language || content.language)
|
145
|
+
else
|
146
|
+
Document.from_source content, @service, format: format,
|
147
|
+
language: language
|
148
|
+
end
|
149
|
+
end
|
150
|
+
alias_method :doc, :document
|
151
|
+
|
152
|
+
##
|
153
|
+
# Returns a new document from the given content with the `format` value
|
154
|
+
# `:text`. No API call is made.
|
155
|
+
#
|
156
|
+
# @param [String, Google::Cloud::Storage::File] content A string of text
|
157
|
+
# to be annotated, or a Cloud Storage URI of the form
|
158
|
+
# `"gs://bucketname/path/to/document.ext"`; or an instance of
|
159
|
+
# Google::Cloud::Storage::File of the text to be annotated.
|
160
|
+
# @param [String] language The language of the document (if not
|
161
|
+
# specified, the language is automatically detected). Both ISO and
|
162
|
+
# BCP-47 language codes are accepted. Optional.
|
163
|
+
#
|
164
|
+
# @return [Document] An document for the Language service.
|
165
|
+
#
|
166
|
+
def text content, language: nil
|
167
|
+
document content, format: :text, language: language
|
168
|
+
end
|
169
|
+
|
170
|
+
##
|
171
|
+
# Returns a new document from the given content with the `format` value
|
172
|
+
# `:html`. No API call is made.
|
173
|
+
#
|
174
|
+
# @param [String, Google::Cloud::Storage::File] content A string of text
|
175
|
+
# to be annotated, or a Cloud Storage URI of the form
|
176
|
+
# `"gs://bucketname/path/to/document.ext"`; or an instance of
|
177
|
+
# Google::Cloud::Storage::File of the text to be annotated.
|
178
|
+
# @param [String] language The language of the document (if not
|
179
|
+
# specified, the language is automatically detected). Both ISO and
|
180
|
+
# BCP-47 language codes are accepted. Optional.
|
181
|
+
#
|
182
|
+
# @return [Document] An document for the Language service.
|
183
|
+
#
|
184
|
+
def html content, language: nil
|
185
|
+
document content, format: :html, language: language
|
186
|
+
end
|
187
|
+
|
188
|
+
##
|
189
|
+
# Analyzes the content and returns sentiment, entity, and syntactic
|
190
|
+
# feature results, depending on the option flags. Calling `annotate`
|
191
|
+
# with no arguments will perform **all** analysis features. Each feature
|
192
|
+
# is priced separately. See [Pricing](https://cloud.google.com/natural-language/pricing)
|
193
|
+
# for details.
|
194
|
+
#
|
195
|
+
# @param [String, Document, Google::Cloud::Storage::File] content The
|
196
|
+
# content to annotate. This can be an {Document} instance, or any
|
197
|
+
# other type that converts to an {Document}. See {#document} for
|
198
|
+
# details.
|
199
|
+
# @param [Boolean] sentiment Whether to perform the sentiment analysis.
|
200
|
+
# Optional. The default is `false`. If every feature option is
|
201
|
+
# `false`, **all** features will be performed.
|
202
|
+
# @param [Boolean] entities Whether to perform the entity analysis.
|
203
|
+
# Optional. The default is `false`. If every feature option is
|
204
|
+
# `false`, **all** features will be performed.
|
205
|
+
# @param [Boolean] syntax Whether to perform the syntactic analysis.
|
206
|
+
# Optional. The default is `false`. If every feature option is
|
207
|
+
# `false`, **all** features will be performed.
|
208
|
+
# @param [String] format The format of the document (TEXT/HTML).
|
209
|
+
# Optional.
|
210
|
+
# @param [String] language The language of the document (if not
|
211
|
+
# specified, the language is automatically detected). Both ISO and
|
212
|
+
# BCP-47 language codes are accepted. Optional.
|
213
|
+
# @param [String] encoding The encoding type used by the API to
|
214
|
+
# calculate offsets. Optional.
|
215
|
+
#
|
216
|
+
# @return [Annotation>] The results for the content analysis.
|
217
|
+
#
|
218
|
+
# @example
|
219
|
+
# require "google/cloud"
|
220
|
+
#
|
221
|
+
# gcloud = Google::Cloud.new
|
222
|
+
# language = gcloud.language
|
223
|
+
#
|
224
|
+
# content = "Darth Vader is the best villain in Star Wars."
|
225
|
+
# annotation = language.annotate content
|
226
|
+
#
|
227
|
+
# annotation.sentiment.polarity #=> 1.0
|
228
|
+
# annotation.sentiment.magnitude #=> 0.8999999761581421
|
229
|
+
# annotation.entities.count #=> 2
|
230
|
+
# annotation.sentences.count #=> 1
|
231
|
+
# annotation.tokens.count #=> 10
|
232
|
+
#
|
233
|
+
def annotate content, sentiment: false, entities: false, syntax: false,
|
234
|
+
format: nil, language: nil, encoding: nil
|
235
|
+
ensure_service!
|
236
|
+
doc = document content, language: language, format: format
|
237
|
+
grpc = service.annotate doc.to_grpc, sentiment: sentiment,
|
238
|
+
entities: entities,
|
239
|
+
syntax: syntax,
|
240
|
+
encoding: encoding
|
241
|
+
Annotation.from_grpc grpc
|
242
|
+
end
|
243
|
+
alias_method :mark, :annotate
|
244
|
+
alias_method :detect, :annotate
|
245
|
+
|
246
|
+
##
|
247
|
+
# Syntactic analysis extracts linguistic information, breaking up the
|
248
|
+
# given text into a series of sentences and tokens (generally, word
|
249
|
+
# boundaries), providing further analysis on those tokens.
|
250
|
+
#
|
251
|
+
# @param [String, Document, Google::Cloud::Storage::File] content The
|
252
|
+
# content to annotate. This can be an {Document} instance, or any
|
253
|
+
# other type that converts to an {Document}. See {#document} for
|
254
|
+
# details.
|
255
|
+
# @param [String] format The format of the document (TEXT/HTML).
|
256
|
+
# Optional.
|
257
|
+
# @param [String] language The language of the document (if not
|
258
|
+
# specified, the language is automatically detected). Both ISO and
|
259
|
+
# BCP-47 language codes are accepted. Optional.
|
260
|
+
# @param [String] encoding The encoding type used by the API to
|
261
|
+
# calculate offsets. Optional.
|
262
|
+
#
|
263
|
+
# @return [Annotation>] The results for the content syntax analysis.
|
264
|
+
#
|
265
|
+
# @example
|
266
|
+
# require "google/cloud"
|
267
|
+
#
|
268
|
+
# gcloud = Google::Cloud.new
|
269
|
+
# language = gcloud.language
|
270
|
+
#
|
271
|
+
# document = language.document "Hello world!"
|
272
|
+
#
|
273
|
+
# annotation = language.syntax document
|
274
|
+
# annotation.thing #=> Some Result
|
275
|
+
#
|
276
|
+
def syntax content, format: nil, language: nil, encoding: nil
|
277
|
+
annotate content, syntax: true, format: format, language: language,
|
278
|
+
encoding: encoding
|
279
|
+
end
|
280
|
+
|
281
|
+
##
|
282
|
+
# Entity analysis inspects the given text for known entities (proper
|
283
|
+
# nouns such as public figures, landmarks, etc.) and returns information
|
284
|
+
# about those entities.
|
285
|
+
#
|
286
|
+
# @param [String, Document] content The content to annotate. This
|
287
|
+
# can be an {Document} instance, or any other type that converts to an
|
288
|
+
# {Document}. See {#document} for details.
|
289
|
+
# @param [String] format The format of the document (TEXT/HTML).
|
290
|
+
# Optional.
|
291
|
+
# @param [String] language The language of the document (if not
|
292
|
+
# specified, the language is automatically detected). Both ISO and
|
293
|
+
# BCP-47 language codes are accepted. Optional.
|
294
|
+
# @param [String] encoding The encoding type used by the API to
|
295
|
+
# calculate offsets. Optional.
|
296
|
+
#
|
297
|
+
# @return [Annotation::Entities>] The results for the entities analysis.
|
298
|
+
#
|
299
|
+
# @example
|
300
|
+
# require "google/cloud"
|
301
|
+
#
|
302
|
+
# gcloud = Google::Cloud.new
|
303
|
+
# language = gcloud.language
|
304
|
+
#
|
305
|
+
# document = language.document "Hello Chris and Mike!"
|
306
|
+
#
|
307
|
+
# entities = language.entities document
|
308
|
+
# entities.count #=> 2
|
309
|
+
#
|
310
|
+
def entities content, format: :text, language: nil, encoding: nil
|
311
|
+
ensure_service!
|
312
|
+
doc = document content, language: language, format: format
|
313
|
+
grpc = service.entities doc.to_grpc, encoding: encoding
|
314
|
+
Annotation::Entities.from_grpc grpc
|
315
|
+
end
|
316
|
+
|
317
|
+
##
|
318
|
+
# Sentiment analysis inspects the given text and identifies the
|
319
|
+
# prevailing emotional opinion within the text, especially to determine
|
320
|
+
# a writer's attitude as positive, negative, or neutral. Currently, only
|
321
|
+
# English is supported for sentiment analysis.
|
322
|
+
#
|
323
|
+
# @param [String, Document] content The content to annotate. This
|
324
|
+
# can be an {Document} instance, or any other type that converts to an
|
325
|
+
# {Document}. See {#document} for details.
|
326
|
+
# @param [String] format The format of the document (TEXT/HTML).
|
327
|
+
# Optional.
|
328
|
+
# @param [String] language The language of the document (if not
|
329
|
+
# specified, the language is automatically detected). Both ISO and
|
330
|
+
# BCP-47 language codes are accepted. Optional.
|
331
|
+
#
|
332
|
+
# @return [Annotation::Sentiment>] The results for the sentiment
|
333
|
+
# analysis.
|
334
|
+
#
|
335
|
+
# @example
|
336
|
+
# require "google/cloud"
|
337
|
+
#
|
338
|
+
# gcloud = Google::Cloud.new
|
339
|
+
# language = gcloud.language
|
340
|
+
#
|
341
|
+
# document = language.document "Hello Chris and Mike!"
|
342
|
+
#
|
343
|
+
# sentiment = language.sentiment document
|
344
|
+
# sentiment.polarity #=> 1.0
|
345
|
+
# sentiment.magnitude #=> 0.8999999761581421
|
346
|
+
#
|
347
|
+
def sentiment content, format: :text, language: nil
|
348
|
+
ensure_service!
|
349
|
+
doc = document content, language: language, format: format
|
350
|
+
grpc = service.sentiment doc.to_grpc
|
351
|
+
Annotation::Sentiment.from_grpc grpc
|
352
|
+
end
|
353
|
+
|
354
|
+
protected
|
355
|
+
|
356
|
+
##
|
357
|
+
# @private Raise an error unless an active connection to the service is
|
358
|
+
# available.
|
359
|
+
def ensure_service!
|
360
|
+
fail "Must have active connection to service" unless service
|
361
|
+
end
|
362
|
+
end
|
363
|
+
end
|
364
|
+
end
|
365
|
+
end
|