ncode-syosetu-polly 0.2.1 → 0.2.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 9e4ff3806326fef794399435bbf177031e40ad78
4
- data.tar.gz: e60e6e5cecbf57f22be4d0fc76b2a24f590e7a30
3
+ metadata.gz: 07b6ac5d9bc4b8df8b12b2511e2f7b0f75abaf1e
4
+ data.tar.gz: 2bcd10de8e21838143005136d35762b9bd1d039f
5
5
  SHA512:
6
- metadata.gz: bd35ec825273a73a36399d663d797a54bc2f1060960e9bb8ebe4297f02c5540f8ee8b1b81891ba84c34af2d7c05842c1baee4d7f489079833680d45cd4290c32
7
- data.tar.gz: 1a06cf7c207a7e92a0ad84e12047ac70b815403f12693d3bda215e6f2a191300a7016684b2f7ef1bf83b7369c07a5bdf8256a5056601ace8e4e4efae9820a448
6
+ metadata.gz: 508384495e2635f45a26ed40b8f27d7632b2ed9c040c4f3ba4dfced45a8a950defaf3fb79953a16c82723655c8c1dd014a3e64e38793f8a631c42fc2880b29d7
7
+ data.tar.gz: c337d14dca9d9adef7c54fc249f0c87d5a784a334efaa09c991f0ac172d0c30bc58a483b7945e0e3e48a4e86f78c12ccdb251be3df06ba8d8069c1bba64875d0
@@ -3,11 +3,12 @@ require "sanitize"
3
3
  require "nokogiri"
4
4
  require "expeditor"
5
5
  require "concurrent"
6
+ require "htmlentities"
6
7
 
7
8
  module NcodeSyosetu
8
9
  module Builder
9
10
  class Polly
10
- POLLY_TEXT_LENGTH_LIMIT = 1500
11
+ POLLY_TEXT_LENGTH_LIMIT = 1000
11
12
 
12
13
  attr_reader :sample_rate, :client, :logger, :service
13
14
 
@@ -15,11 +16,13 @@ module NcodeSyosetu
15
16
  options[:region] ||= "us-west-2"
16
17
  @logger = options.delete(:logger)
17
18
  @sample_rate = options.delete(:sample_rate) || "16000"
19
+ @max_threads = options.delete(:max_threads) || 10
18
20
  @client = Aws::Polly::Client.new(options)
21
+ @htmlentities = HTMLEntities.new
19
22
  @service = Expeditor::Service.new(
20
23
  executor: Concurrent::ThreadPoolExecutor.new(
21
24
  min_threads: 0,
22
- max_threads: 10,
25
+ max_threads: @max_threads,
23
26
  )
24
27
  )
25
28
  end
@@ -33,22 +36,28 @@ module NcodeSyosetu
33
36
  dirname = File.dirname(path)
34
37
  basename = File.basename(path, ".mp3")
35
38
  tmpdir = File.join(dirname, basename)
36
- FileUtils.mkdir(tmpdir)
39
+ FileUtils.mkdir_p(tmpdir)
37
40
 
38
41
  ssmls.each_with_index do |ssml, i|
39
-
40
- File.write(File.join(tmpdir, "#{basename}-#{i}.ssml"), ssml)
42
+ tmp_ssml_path = File.join(tmpdir, "#{basename}-#{i}.ssml")
43
+ File.write(tmp_ssml_path, ssml)
41
44
  tmp_path = File.join(tmpdir, "#{basename}-#{i}.mp3")
42
45
  command = Expeditor::Command.new(service: service) do
43
46
  logger.info("#{tmp_path}...") if logger
44
- client.synthesize_speech(
45
- response_target: tmp_path,
46
- output_format: "mp3",
47
- sample_rate: sample_rate,
48
- text: ssml,
49
- text_type: "ssml",
50
- voice_id: "Mizuki",
51
- )
47
+ begin
48
+ client.synthesize_speech(
49
+ response_target: tmp_path,
50
+ output_format: "mp3",
51
+ sample_rate: sample_rate,
52
+ text: ssml,
53
+ text_type: "ssml",
54
+ voice_id: "Mizuki",
55
+ )
56
+ rescue => e
57
+ logger.error("#{e.message}\n#{ssml}")
58
+ logger.error("#{e.message}: #{tmp_ssml_path}\n#{ssml}")
59
+ raise e
60
+ end
52
61
  end
53
62
  command.start
54
63
  commands << command
@@ -86,13 +95,16 @@ module NcodeSyosetu
86
95
  while elements.size > 0 do
87
96
  element = elements.shift
88
97
 
89
- unless element.is_a?(Nokogiri::XML::Text) || element.is_a?(String)
90
- buffer.print(element.to_s)
91
- next
98
+ case element
99
+ when Nokogiri::XML::Text
100
+ text = @htmlentities.encode(element.text)
101
+ when String
102
+ text = @htmlentities.encode(element)
103
+ else
104
+ buffer.print(element.to_s)
105
+ next
92
106
  end
93
107
 
94
- text = element.to_s
95
-
96
108
  if text.size > POLLY_TEXT_LENGTH_LIMIT
97
109
  elements = text.chars.each_slice(POLLY_TEXT_LENGTH_LIMIT).map(&:join) + elements
98
110
  next
@@ -103,7 +115,7 @@ module NcodeSyosetu
103
115
  buffer = StringIO.new
104
116
  text_count = 0
105
117
  end
106
- buffer.print(element.to_s)
118
+ buffer.print(text)
107
119
  text_count += text.size
108
120
  end
109
121
  results << buffer.string if buffer.size > 0
@@ -24,6 +24,7 @@ Gem::Specification.new do |spec|
24
24
  spec.add_dependency "sanitize", "~> 4.4"
25
25
  spec.add_dependency "nokogiri", ">= 1.6"
26
26
  spec.add_dependency "expeditor", "~> 0.5.0"
27
+ spec.add_dependency "htmlentities"
27
28
 
28
29
  spec.add_development_dependency "bundler", "~> 1.13"
29
30
  spec.add_development_dependency "rake", "~> 10.0"
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: ncode-syosetu-polly
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.2.1
4
+ version: 0.2.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - hogelog
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2017-01-08 00:00:00.000000000 Z
11
+ date: 2017-01-12 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: ncode-syosetu-core
@@ -16,28 +16,28 @@ dependencies:
16
16
  requirements:
17
17
  - - '='
18
18
  - !ruby/object:Gem::Version
19
- version: 0.2.1
19
+ version: 0.2.2
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - '='
25
25
  - !ruby/object:Gem::Version
26
- version: 0.2.1
26
+ version: 0.2.2
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: ncode-syosetu-ssml
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
31
  - - '='
32
32
  - !ruby/object:Gem::Version
33
- version: 0.2.1
33
+ version: 0.2.2
34
34
  type: :runtime
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
38
  - - '='
39
39
  - !ruby/object:Gem::Version
40
- version: 0.2.1
40
+ version: 0.2.2
41
41
  - !ruby/object:Gem::Dependency
42
42
  name: aws-sdk-polly
43
43
  requirement: !ruby/object:Gem::Requirement
@@ -94,6 +94,20 @@ dependencies:
94
94
  - - "~>"
95
95
  - !ruby/object:Gem::Version
96
96
  version: 0.5.0
97
+ - !ruby/object:Gem::Dependency
98
+ name: htmlentities
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :runtime
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
97
111
  - !ruby/object:Gem::Dependency
98
112
  name: bundler
99
113
  requirement: !ruby/object:Gem::Requirement