logstash-filter-i18n 0.1.0
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 +15 -0
- data/.gitignore +4 -0
- data/Gemfile +3 -0
- data/Rakefile +6 -0
- data/lib/logstash/filters/i18n.rb +52 -0
- data/logstash-filter-i18n.gemspec +27 -0
- data/rakelib/publish.rake +9 -0
- data/rakelib/vendor.rake +169 -0
- data/spec/filters/i18n_spec.rb +25 -0
- metadata +88 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
ZTQ0YjIwZmQ5ZGU2ZTk0N2VmNGNkNmJlYWE4Zjg1Y2I2MjlmYThkOQ==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
MTU1NDE0MTI2MWZjNWI2M2I5NTlmY2Y2MjYxMzY4MDEyYjkwZDk0ZA==
|
7
|
+
SHA512:
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
ZDI1NzMzYWQyMmZjM2QwN2ViYTU2NzYwMzNjNGJkNTMzOWJiYTI3NDUwZTAz
|
10
|
+
ZDA3OWMzMGQwNzNhODRmNWRmZjkwZTc0ZGEzOThkNmYyMDE4OTQzMzI2MTY4
|
11
|
+
YzQxMWQ0MDFkNmJiYTQxNTFmNjRiNjViMDEwOWZhMTQ5ZGRjNGQ=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
MTVlMGE3ZjU1NTYyNzZlYmZhZTFhM2JkMmQ5MWM2OGI1MmU1MDRlZGVlZDMw
|
14
|
+
M2UzOTFhYzdlMDk1YzYwYjY2MDRmNzYzZDlkYWMzMzViMDhiNDQxMjI4NWQ4
|
15
|
+
NWU3MGM3OTI2NWZhOWE3Njc0ZWI1NTM1YmMwYTY0NGZmMGIwNDA=
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require "i18n"
|
3
|
+
require "logstash/filters/base"
|
4
|
+
require "logstash/namespace"
|
5
|
+
|
6
|
+
|
7
|
+
# The i18n filter allows you to remove special characters from
|
8
|
+
# from a field
|
9
|
+
class LogStash::Filters::I18n < LogStash::Filters::Base
|
10
|
+
config_name "i18n"
|
11
|
+
milestone 0
|
12
|
+
|
13
|
+
# Replaces non-ASCII characters with an ASCII approximation, or
|
14
|
+
# if none exists, a replacement character which defaults to “?”
|
15
|
+
#
|
16
|
+
# Example:
|
17
|
+
#
|
18
|
+
# filter {
|
19
|
+
# i18n {
|
20
|
+
# transliterate => ["field1", "field2"]
|
21
|
+
# }
|
22
|
+
# }
|
23
|
+
config :transliterate, :validate => :array
|
24
|
+
|
25
|
+
public
|
26
|
+
def register
|
27
|
+
end # def register
|
28
|
+
|
29
|
+
public
|
30
|
+
def filter(event)
|
31
|
+
return unless filter?(event)
|
32
|
+
|
33
|
+
transliterate(event) if @transliterate
|
34
|
+
|
35
|
+
filter_matched(event)
|
36
|
+
end # def filter
|
37
|
+
|
38
|
+
private
|
39
|
+
def transliterate(event)
|
40
|
+
@transliterate.each do |field|
|
41
|
+
if event[field].is_a?(Array)
|
42
|
+
event[field].map! { |v| I18n.transliterate(v).encode('UTF-8') }
|
43
|
+
elsif event[field].is_a?(String)
|
44
|
+
event[field] = I18n.transliterate(event[field].encode('UTF-8'))
|
45
|
+
else
|
46
|
+
@logger.debug("Can't transliterate something that isn't a string",
|
47
|
+
:field => field, :value => event[field])
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end # def transliterate
|
51
|
+
|
52
|
+
end # class LogStash::Filters::I18n
|
@@ -0,0 +1,27 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
|
3
|
+
s.name = 'logstash-filter-i18n'
|
4
|
+
s.version = '0.1.0'
|
5
|
+
s.licenses = ['Apache License (2.0)']
|
6
|
+
s.summary = "The i18n filter allows you to remove special characters from a field"
|
7
|
+
s.description = "The i18n filter allows you to remove special characters from a field"
|
8
|
+
s.authors = ["Elasticsearch"]
|
9
|
+
s.email = 'richard.pijnenburg@elasticsearch.com'
|
10
|
+
s.homepage = "http://logstash.net/"
|
11
|
+
s.require_paths = ["lib"]
|
12
|
+
|
13
|
+
# Files
|
14
|
+
s.files = `git ls-files`.split($\)
|
15
|
+
|
16
|
+
# Tests
|
17
|
+
s.test_files = s.files.grep(%r{^(test|spec|features)/})
|
18
|
+
|
19
|
+
# Special flag to let us know this is actually a logstash plugin
|
20
|
+
s.metadata = { "logstash_plugin" => "true", "group" => "filter" }
|
21
|
+
|
22
|
+
# Gem dependencies
|
23
|
+
s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
|
24
|
+
s.add_runtime_dependency 'i18n', ['>=0.6.6']
|
25
|
+
|
26
|
+
end
|
27
|
+
|
@@ -0,0 +1,9 @@
|
|
1
|
+
require "gem_publisher"
|
2
|
+
|
3
|
+
desc "Publish gem to RubyGems.org"
|
4
|
+
task :publish_gem do |t|
|
5
|
+
gem_file = Dir.glob(File.expand_path('../*.gemspec',File.dirname(__FILE__))).first
|
6
|
+
gem = GemPublisher.publish_if_updated(gem_file, :rubygems)
|
7
|
+
puts "Published #{gem}" if gem
|
8
|
+
end
|
9
|
+
|
data/rakelib/vendor.rake
ADDED
@@ -0,0 +1,169 @@
|
|
1
|
+
require "net/http"
|
2
|
+
require "uri"
|
3
|
+
require "digest/sha1"
|
4
|
+
|
5
|
+
def vendor(*args)
|
6
|
+
return File.join("vendor", *args)
|
7
|
+
end
|
8
|
+
|
9
|
+
directory "vendor/" => ["vendor"] do |task, args|
|
10
|
+
mkdir task.name
|
11
|
+
end
|
12
|
+
|
13
|
+
def fetch(url, sha1, output)
|
14
|
+
|
15
|
+
puts "Downloading #{url}"
|
16
|
+
actual_sha1 = download(url, output)
|
17
|
+
|
18
|
+
if actual_sha1 != sha1
|
19
|
+
fail "SHA1 does not match (expected '#{sha1}' but got '#{actual_sha1}')"
|
20
|
+
end
|
21
|
+
end # def fetch
|
22
|
+
|
23
|
+
def file_fetch(url, sha1)
|
24
|
+
filename = File.basename( URI(url).path )
|
25
|
+
output = "vendor/#{filename}"
|
26
|
+
task output => [ "vendor/" ] do
|
27
|
+
begin
|
28
|
+
actual_sha1 = file_sha1(output)
|
29
|
+
if actual_sha1 != sha1
|
30
|
+
fetch(url, sha1, output)
|
31
|
+
end
|
32
|
+
rescue Errno::ENOENT
|
33
|
+
fetch(url, sha1, output)
|
34
|
+
end
|
35
|
+
end.invoke
|
36
|
+
|
37
|
+
return output
|
38
|
+
end
|
39
|
+
|
40
|
+
def file_sha1(path)
|
41
|
+
digest = Digest::SHA1.new
|
42
|
+
fd = File.new(path, "r")
|
43
|
+
while true
|
44
|
+
begin
|
45
|
+
digest << fd.sysread(16384)
|
46
|
+
rescue EOFError
|
47
|
+
break
|
48
|
+
end
|
49
|
+
end
|
50
|
+
return digest.hexdigest
|
51
|
+
ensure
|
52
|
+
fd.close if fd
|
53
|
+
end
|
54
|
+
|
55
|
+
def download(url, output)
|
56
|
+
uri = URI(url)
|
57
|
+
digest = Digest::SHA1.new
|
58
|
+
tmp = "#{output}.tmp"
|
59
|
+
Net::HTTP.start(uri.host, uri.port, :use_ssl => (uri.scheme == "https")) do |http|
|
60
|
+
request = Net::HTTP::Get.new(uri.path)
|
61
|
+
http.request(request) do |response|
|
62
|
+
fail "HTTP fetch failed for #{url}. #{response}" if [200, 301].include?(response.code)
|
63
|
+
size = (response["content-length"].to_i || -1).to_f
|
64
|
+
count = 0
|
65
|
+
File.open(tmp, "w") do |fd|
|
66
|
+
response.read_body do |chunk|
|
67
|
+
fd.write(chunk)
|
68
|
+
digest << chunk
|
69
|
+
if size > 0 && $stdout.tty?
|
70
|
+
count += chunk.bytesize
|
71
|
+
$stdout.write(sprintf("\r%0.2f%%", count/size * 100))
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
$stdout.write("\r \r") if $stdout.tty?
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
File.rename(tmp, output)
|
80
|
+
|
81
|
+
return digest.hexdigest
|
82
|
+
rescue SocketError => e
|
83
|
+
puts "Failure while downloading #{url}: #{e}"
|
84
|
+
raise
|
85
|
+
ensure
|
86
|
+
File.unlink(tmp) if File.exist?(tmp)
|
87
|
+
end # def download
|
88
|
+
|
89
|
+
def untar(tarball, &block)
|
90
|
+
require "archive/tar/minitar"
|
91
|
+
tgz = Zlib::GzipReader.new(File.open(tarball))
|
92
|
+
# Pull out typesdb
|
93
|
+
tar = Archive::Tar::Minitar::Input.open(tgz)
|
94
|
+
tar.each do |entry|
|
95
|
+
path = block.call(entry)
|
96
|
+
next if path.nil?
|
97
|
+
parent = File.dirname(path)
|
98
|
+
|
99
|
+
mkdir_p parent unless File.directory?(parent)
|
100
|
+
|
101
|
+
# Skip this file if the output file is the same size
|
102
|
+
if entry.directory?
|
103
|
+
mkdir path unless File.directory?(path)
|
104
|
+
else
|
105
|
+
entry_mode = entry.instance_eval { @mode } & 0777
|
106
|
+
if File.exists?(path)
|
107
|
+
stat = File.stat(path)
|
108
|
+
# TODO(sissel): Submit a patch to archive-tar-minitar upstream to
|
109
|
+
# expose headers in the entry.
|
110
|
+
entry_size = entry.instance_eval { @size }
|
111
|
+
# If file sizes are same, skip writing.
|
112
|
+
next if stat.size == entry_size && (stat.mode & 0777) == entry_mode
|
113
|
+
end
|
114
|
+
puts "Extracting #{entry.full_name} from #{tarball} #{entry_mode.to_s(8)}"
|
115
|
+
File.open(path, "w") do |fd|
|
116
|
+
# eof? check lets us skip empty files. Necessary because the API provided by
|
117
|
+
# Archive::Tar::Minitar::Reader::EntryStream only mostly acts like an
|
118
|
+
# IO object. Something about empty files in this EntryStream causes
|
119
|
+
# IO.copy_stream to throw "can't convert nil into String" on JRuby
|
120
|
+
# TODO(sissel): File a bug about this.
|
121
|
+
while !entry.eof?
|
122
|
+
chunk = entry.read(16384)
|
123
|
+
fd.write(chunk)
|
124
|
+
end
|
125
|
+
#IO.copy_stream(entry, fd)
|
126
|
+
end
|
127
|
+
File.chmod(entry_mode, path)
|
128
|
+
end
|
129
|
+
end
|
130
|
+
tar.close
|
131
|
+
File.unlink(tarball) if File.file?(tarball)
|
132
|
+
end # def untar
|
133
|
+
|
134
|
+
def ungz(file)
|
135
|
+
|
136
|
+
outpath = file.gsub('.gz', '')
|
137
|
+
tgz = Zlib::GzipReader.new(File.open(file))
|
138
|
+
begin
|
139
|
+
File.open(outpath, "w") do |out|
|
140
|
+
IO::copy_stream(tgz, out)
|
141
|
+
end
|
142
|
+
File.unlink(file)
|
143
|
+
rescue
|
144
|
+
File.unlink(outpath) if File.file?(outpath)
|
145
|
+
raise
|
146
|
+
end
|
147
|
+
tgz.close
|
148
|
+
end
|
149
|
+
|
150
|
+
desc "Process any vendor files required for this plugin"
|
151
|
+
task "vendor" do |task, args|
|
152
|
+
|
153
|
+
@files.each do |file|
|
154
|
+
download = file_fetch(file['url'], file['sha1'])
|
155
|
+
if download =~ /.tar.gz/
|
156
|
+
prefix = download.gsub('.tar.gz', '').gsub('vendor/', '')
|
157
|
+
untar(download) do |entry|
|
158
|
+
if !file['files'].nil?
|
159
|
+
next unless file['files'].include?(entry.full_name.gsub(prefix, ''))
|
160
|
+
out = entry.full_name.split("/").last
|
161
|
+
end
|
162
|
+
File.join('vendor', out)
|
163
|
+
end
|
164
|
+
elsif download =~ /.gz/
|
165
|
+
ungz(download)
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require "spec_helper"
|
3
|
+
require "logstash/filters/i18n"
|
4
|
+
|
5
|
+
describe LogStash::Filters::I18n do
|
6
|
+
|
7
|
+
|
8
|
+
describe "transliterate" do
|
9
|
+
config <<-CONFIG
|
10
|
+
filter {
|
11
|
+
i18n {
|
12
|
+
transliterate => [ "transliterateme" ]
|
13
|
+
}
|
14
|
+
}
|
15
|
+
CONFIG
|
16
|
+
|
17
|
+
event = {
|
18
|
+
"transliterateme" => [ "Ærøskøbing" ]
|
19
|
+
}
|
20
|
+
|
21
|
+
sample event do
|
22
|
+
insist { subject["transliterateme"] } == [ "AEroskobing" ]
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: logstash-filter-i18n
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Elasticsearch
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-02 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: logstash
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ! '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.4.0
|
20
|
+
- - <
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 2.0.0
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 1.4.0
|
30
|
+
- - <
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 2.0.0
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: i18n
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - ! '>='
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: 0.6.6
|
40
|
+
type: :runtime
|
41
|
+
prerelease: false
|
42
|
+
version_requirements: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - ! '>='
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 0.6.6
|
47
|
+
description: The i18n filter allows you to remove special characters from a field
|
48
|
+
email: richard.pijnenburg@elasticsearch.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- Gemfile
|
55
|
+
- Rakefile
|
56
|
+
- lib/logstash/filters/i18n.rb
|
57
|
+
- logstash-filter-i18n.gemspec
|
58
|
+
- rakelib/publish.rake
|
59
|
+
- rakelib/vendor.rake
|
60
|
+
- spec/filters/i18n_spec.rb
|
61
|
+
homepage: http://logstash.net/
|
62
|
+
licenses:
|
63
|
+
- Apache License (2.0)
|
64
|
+
metadata:
|
65
|
+
logstash_plugin: 'true'
|
66
|
+
group: filter
|
67
|
+
post_install_message:
|
68
|
+
rdoc_options: []
|
69
|
+
require_paths:
|
70
|
+
- lib
|
71
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ! '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
77
|
+
requirements:
|
78
|
+
- - ! '>='
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
version: '0'
|
81
|
+
requirements: []
|
82
|
+
rubyforge_project:
|
83
|
+
rubygems_version: 2.4.1
|
84
|
+
signing_key:
|
85
|
+
specification_version: 4
|
86
|
+
summary: The i18n filter allows you to remove special characters from a field
|
87
|
+
test_files:
|
88
|
+
- spec/filters/i18n_spec.rb
|