opener-chained-daemon 3.0.6 → 3.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/opener/chained_daemon.rb +3 -0
- data/lib/opener/chained_daemon/chained_daemon.rb +12 -0
- data/lib/opener/chained_daemon/cli.rb +8 -1
- data/lib/opener/chained_daemon/version.rb +1 -1
- data/lib/opener/stanza/tokenizer_pos.rb +22 -3
- data/opener-chained-daemon.gemspec +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1dafbc02ba750a4f1f2e360e5febf6521bdb3c5019c3c9bea961ec2a20b56ef3
|
4
|
+
data.tar.gz: '09915d7c540dd6932da9f5da8bee68fa259611ba628e53b6796c775b7ff73368'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8f89040096bb0f6f9c755c0db9564cbc8a63e772352b5f05c0e4a4341f659e7bd8abdfe3b8b1aa87b6cccf7db17355628105079d95fd0679e4f650f504fcc41e
|
7
|
+
data.tar.gz: 3fbb26c4542fae6143077292a288e10ec0aba51c9b2f463f55355d3a3cab518b4c2f1135de978d6f8aeec6e2b30d06f50bc60da9d2cc0cb4ee072a3040e6f81a
|
@@ -47,6 +47,7 @@ module Opener
|
|
47
47
|
output = xml.to_s
|
48
48
|
end
|
49
49
|
|
50
|
+
output = pretty_print output if params[:cache_keys][:environment] == 'staging'
|
50
51
|
output
|
51
52
|
|
52
53
|
rescue Core::UnsupportedLanguageError
|
@@ -54,6 +55,17 @@ module Opener
|
|
54
55
|
output
|
55
56
|
end
|
56
57
|
|
58
|
+
def pretty_print(output)
|
59
|
+
doc = REXML::Document.new output
|
60
|
+
doc.context[:attribute_quote] = :quote
|
61
|
+
out = ""
|
62
|
+
formatter = REXML::Formatters::Pretty.new
|
63
|
+
formatter.compact = true
|
64
|
+
formatter.write(doc, out)
|
65
|
+
|
66
|
+
out.strip
|
67
|
+
end
|
68
|
+
|
57
69
|
def translate xml, params
|
58
70
|
raw = xml.at :raw
|
59
71
|
case translate_service params
|
@@ -47,7 +47,14 @@ Example:
|
|
47
47
|
run do |opts, args|
|
48
48
|
daemon = ChainedDaemon.new args: args
|
49
49
|
input = STDIN.tty? ? nil : STDIN.read
|
50
|
-
|
50
|
+
|
51
|
+
params = if ENV['PARAMS']
|
52
|
+
JSON.parse ENV['PARAMS']
|
53
|
+
else
|
54
|
+
{}
|
55
|
+
end
|
56
|
+
# Set environment as staging from console for testing purposes
|
57
|
+
params[:cache_keys] = { environment: 'staging', merged: true }
|
51
58
|
|
52
59
|
puts daemon.run input, params || {}
|
53
60
|
end
|
@@ -8,6 +8,9 @@ module Opener
|
|
8
8
|
BASE_URL = ENV['STANZA_SERVER']
|
9
9
|
LANGUAGES_CACHE = Opener::ChainedDaemon::LanguagesCache.new
|
10
10
|
|
11
|
+
RTL_LANGUAGES = [ "ar", "ara", "arc", "ae", "ave", "egy", "he", "heb", "nqo", "pal", "phn", "sam",
|
12
|
+
"syc", "syr", "fa", "per", "fas", "ku", "kur", "ur", "urd" ]
|
13
|
+
|
11
14
|
POS = {
|
12
15
|
'DET' => 'D',
|
13
16
|
'ADJ' => 'G',
|
@@ -35,20 +38,36 @@ module Opener
|
|
35
38
|
|
36
39
|
kaf = KAF::Document.from_xml input
|
37
40
|
|
38
|
-
|
41
|
+
prod = params[:cache_keys][:environment] != 'staging'
|
42
|
+
if prod and !LANGUAGES_CACHE.get.include?(kaf.language)
|
39
43
|
raise Core::UnsupportedLanguageError.new kaf.language
|
40
44
|
end
|
41
45
|
|
42
|
-
|
46
|
+
input = kaf.raw
|
47
|
+
input = input.gsub(/\,[^\ ]/, ', ')
|
48
|
+
response = Faraday.post BASE_URL, {lang: kaf.language, input: input}.to_query
|
43
49
|
raise Core::UnsupportedLanguageError, kaf.language if response.status == 406
|
44
50
|
raise response.body if response.status >= 400
|
45
51
|
tokens = JSON.parse response.body
|
46
52
|
|
47
53
|
w_index = 0
|
54
|
+
|
55
|
+
tokens.map{ |t| t.reverse! } if RTL_LANGUAGES.include? kaf.language
|
48
56
|
tokens.each_with_index do |sentence, s_index|
|
57
|
+
miscs = {}
|
49
58
|
sentence.each_with_index do |word|
|
50
59
|
w_index += 1
|
51
|
-
misc
|
60
|
+
# save misc for later usase in a MWT case
|
61
|
+
if word['id'].is_a? Array
|
62
|
+
word['id'].each { |id| miscs[id] = word['misc'] }
|
63
|
+
next
|
64
|
+
end
|
65
|
+
misc = word['misc'] || miscs[word['id']]
|
66
|
+
|
67
|
+
Rollbar.scoped({ input: input, params: params, tokens: tokens, word: word }) do
|
68
|
+
raise 'Missing misc'
|
69
|
+
end if misc.nil?
|
70
|
+
|
52
71
|
offset = misc.match(/start_char=(\d+)|/)[1].to_i
|
53
72
|
length = misc.match(/end_char=(\d+)/)[1].to_i - offset
|
54
73
|
|
@@ -36,7 +36,7 @@ Gem::Specification.new do |spec|
|
|
36
36
|
spec.add_dependency 'opener-tokenizer', '>= 2.2.0'
|
37
37
|
spec.add_dependency 'opener-pos-tagger', '>= 3.2.0'
|
38
38
|
spec.add_dependency 'opener-polarity-tagger', '>= 3.2.7'
|
39
|
-
spec.add_dependency 'opener-property-tagger', '>= 3.3.
|
39
|
+
spec.add_dependency 'opener-property-tagger', '>= 3.3.5'
|
40
40
|
spec.add_dependency 'opener-opinion-detector-basic', '>= 3.2.3'
|
41
41
|
|
42
42
|
spec.add_development_dependency 'bundler', '~> 1.3'
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: opener-chained-daemon
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.
|
4
|
+
version: 3.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- development@olery.com
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-11-
|
11
|
+
date: 2020-11-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|
@@ -198,14 +198,14 @@ dependencies:
|
|
198
198
|
requirements:
|
199
199
|
- - ">="
|
200
200
|
- !ruby/object:Gem::Version
|
201
|
-
version: 3.3.
|
201
|
+
version: 3.3.5
|
202
202
|
type: :runtime
|
203
203
|
prerelease: false
|
204
204
|
version_requirements: !ruby/object:Gem::Requirement
|
205
205
|
requirements:
|
206
206
|
- - ">="
|
207
207
|
- !ruby/object:Gem::Version
|
208
|
-
version: 3.3.
|
208
|
+
version: 3.3.5
|
209
209
|
- !ruby/object:Gem::Dependency
|
210
210
|
name: opener-opinion-detector-basic
|
211
211
|
requirement: !ruby/object:Gem::Requirement
|