logstash-input-s3 0.1.0 → 0.1.1

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    NzkxNDE2MTI2NWM5YzVjNGNlNzU5ZjI3OTMxM2U2OWVkZjQ1ZDJmOQ==
-  data.tar.gz: !binary |-
-    YzlhZWI4NGMyZTY1N2E0Njk5M2Y3NjI1YTIwNzYyNWJhM2QzZDI2ZQ==
+SHA1:
+  metadata.gz: 18491f4d5a8850a30b8bd5b25c33cc2a0dd9c247
+  data.tar.gz: c3017df48dd6ea484f8afb81e77d5b1e085d9d11
 SHA512:
-  metadata.gz: !binary |-
-    ZDkzNTVhYmE2YTg4ZWYyZTNiMjQ5M2RhMjRiNmZiNzE0ZDFhZjIxMTIwNDM0
-    NmFhMzMyZmY2MTkwZWM3Y2ZlZDhiYzQ1NThhNzQ2ODgyYThjNzFiNDhkMmE3
-    Zjc5N2U2ODlkYmYwM2RiZmQ4Y2I0OGVmZTc0YTdhN2IzMGI3YmU=
-  data.tar.gz: !binary |-
-    NjI1NmFiOTY1ZWNiNGZiZTQ4YjE4ZjFiNGY3ZjU3MGU1NDgwYTQyODI0YTEx
-    MGNkMjA5MGNmNTdmNTJlNDAyNjlhODc4ZDkzYWFkNWM4MzU3ZTJmZjZlZDdk
-    Y2I5ODIxM2RiYmEwNTA4ZmU5ZGQyN2YxZjMzNjc4NzEyYWM3NmM=
+  metadata.gz: 8d112c0f09cbfe563eebce342812e8082b125b660560a250971b81a16d12584cad7303cc2b8b37fd2c6dfb2d64a0b44b44b843e133a22cde89971b1568bc38f8
+  data.tar.gz: ecec7bab79976f09f84f72b516ebe95dfbc6e07998f23ff581e17e275ab994259707e311aed5441bb38be5557bbed8ca377abfeb41f701fdcd8e79716954a51e

data/Gemfile

@@ -1,4 +1,3 @@
-source 'http://rubygems.org'
-gem 'rake'
-gem 'gem_publisher'
-gem 'archive-tar-minitar'
+source 'https://rubygems.org'
+gemspec
+gem "logstash", :github => "elasticsearch/logstash", :branch => "1.5"

data/Rakefile

@@ -4,3 +4,4 @@ task :default do
   system("rake -T")
 end
 
+require "logstash/devutils/rake"

data/lib/logstash/inputs/s3.rb

@@ -8,20 +8,20 @@ require "tmpdir"
 # Stream events from files from a S3 bucket.
 #
 # Each line from each file generates an event.
-# Files ending in '.gz' are handled as gzip'ed files.
+# Files ending in `.gz` are handled as gzip'ed files.
 class LogStash::Inputs::S3 < LogStash::Inputs::Base
   config_name "s3"
   milestone 1
 
-  # TODO(sissel): refactor to use 'line' codec (requires removing both gzip
+  # TODO(sissel): refactor to use `line` codec (requires removing both gzip
   # support and readline usage). Support gzip through a gzip codec! ;)
   default :codec, "plain"
 
   # The credentials of the AWS account used to access the bucket.
   # Credentials can be specified:
-  # - As an ["id","secret"] array
-  # - As a path to a file containing AWS_ACCESS_KEY_ID=... and AWS_SECRET_ACCESS_KEY=...
-  # - In the environment, if not set (using variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY)
+  # - As an `["id","secret"]` array
+  # - As a path to a file containing `AWS_ACCESS_KEY_ID=...` and `AWS_SECRET_ACCESS_KEY=...`
+  # - In the environment, if not set (using variables `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`)
   config :credentials, :validate => :array, :default => []
 
   # The name of the S3 bucket.
@@ -44,6 +44,7 @@ class LogStash::Inputs::S3 < LogStash::Inputs::Base
   # Where to write the since database (keeps track of the date
   # the last handled file was added to S3). The default will write
   # sincedb files to some path matching "$HOME/.sincedb*"
+  # Should be a path with filename not just a directory.
   config :sincedb_path, :validate => :string, :default => nil
 
   # Name of a S3 bucket to backup processed files to.

data/logstash-input-s3.gemspec

@@ -1,13 +1,13 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-input-s3'
-  s.version         = '0.1.0'
+  s.version         = '0.1.1'
   s.licenses        = ['Apache License (2.0)']
   s.summary         = "Stream events from files from a S3 bucket."
-  s.description     = "Stream events from files from a S3 bucket."
+  s.description     = "This gem is a logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/plugin install gemname. This gem is not a stand-alone program"
   s.authors         = ["Elasticsearch"]
-  s.email           = 'richard.pijnenburg@elasticsearch.com'
-  s.homepage        = "http://logstash.net/"
+  s.email           = 'info@elasticsearch.com'
+  s.homepage        = "http://www.elasticsearch.org/guide/en/logstash/current/index.html"
   s.require_paths = ["lib"]
 
   # Files
@@ -17,13 +17,14 @@ Gem::Specification.new do |s|
   s.test_files = s.files.grep(%r{^(test|spec|features)/})
 
   # Special flag to let us know this is actually a logstash plugin
-  s.metadata = { "logstash_plugin" => "true", "group" => "input" }
+  s.metadata = { "logstash_plugin" => "true", "logstash_group" => "input" }
 
   # Gem dependencies
   s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
-
+  s.add_runtime_dependency 'logstash-mixin-aws'
   s.add_runtime_dependency 'logstash-codec-plain'
   s.add_runtime_dependency 'aws-sdk'
 
+  s.add_development_dependency 'logstash-devutils'
 end
 

data/spec/inputs/s3_spec.rb

@@ -1,4 +1,4 @@
-require 'spec_helper'
+require "logstash/devutils/rspec/spec_helper"
 require 'logstash/inputs/s3'
 
 describe LogStash::Inputs::S3 do

metadata

@@ -1,65 +1,93 @@
 --- !ruby/object:Gem::Specification
 name: logstash-input-s3
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Elasticsearch
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-11-05 00:00:00.000000000 Z
+date: 2014-11-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logstash
-  requirement: !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.4.0
     - - <
       - !ruby/object:Gem::Version
         version: 2.0.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.4.0
     - - <
       - !ruby/object:Gem::Version
         version: 2.0.0
+  prerelease: false
+  type: :runtime
 - !ruby/object:Gem::Dependency
-  name: logstash-codec-plain
+  name: logstash-mixin-aws
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: logstash-codec-plain
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :runtime
 - !ruby/object:Gem::Dependency
   name: aws-sdk
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: logstash-devutils
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: Stream events from files from a S3 bucket.
-email: richard.pijnenburg@elasticsearch.com
+  prerelease: false
+  type: :development
+description: This gem is a logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/plugin install gemname. This gem is not a stand-alone program
+email: info@elasticsearch.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -70,33 +98,31 @@ files:
 - Rakefile
 - lib/logstash/inputs/s3.rb
 - logstash-input-s3.gemspec
-- rakelib/publish.rake
-- rakelib/vendor.rake
 - spec/inputs/s3_spec.rb
-homepage: http://logstash.net/
+homepage: http://www.elasticsearch.org/guide/en/logstash/current/index.html
 licenses:
 - Apache License (2.0)
 metadata:
   logstash_plugin: 'true'
-  group: input
-post_install_message: 
+  logstash_group: input
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.1
-signing_key: 
+rubyforge_project:
+rubygems_version: 2.2.2
+signing_key:
 specification_version: 4
 summary: Stream events from files from a S3 bucket.
 test_files:

data/rakelib/publish.rake

@@ -1,9 +0,0 @@
-require "gem_publisher"
-
-desc "Publish gem to RubyGems.org"
-task :publish_gem do |t|
-  gem_file = Dir.glob(File.expand_path('../*.gemspec',File.dirname(__FILE__))).first
-  gem = GemPublisher.publish_if_updated(gem_file, :rubygems)
-  puts "Published #{gem}" if gem
-end
-

data/rakelib/vendor.rake

@@ -1,169 +0,0 @@
-require "net/http"
-require "uri"
-require "digest/sha1"
-
-def vendor(*args)
-  return File.join("vendor", *args)
-end
-
-directory "vendor/" => ["vendor"] do |task, args|
-  mkdir task.name
-end
-
-def fetch(url, sha1, output)
-
-  puts "Downloading #{url}"
-  actual_sha1 = download(url, output)
-
-  if actual_sha1 != sha1
-    fail "SHA1 does not match (expected '#{sha1}' but got '#{actual_sha1}')"
-  end
-end # def fetch
-
-def file_fetch(url, sha1)
-  filename = File.basename( URI(url).path )
-  output = "vendor/#{filename}"
-  task output => [ "vendor/" ] do
-    begin
-      actual_sha1 = file_sha1(output)
-      if actual_sha1 != sha1
-        fetch(url, sha1, output)
-      end
-    rescue Errno::ENOENT
-      fetch(url, sha1, output)
-    end
-  end.invoke
-
-  return output
-end
-
-def file_sha1(path)
-  digest = Digest::SHA1.new
-  fd = File.new(path, "r")
-  while true
-    begin
-      digest << fd.sysread(16384)
-    rescue EOFError
-      break
-    end
-  end
-  return digest.hexdigest
-ensure
-  fd.close if fd
-end
-
-def download(url, output)
-  uri = URI(url)
-  digest = Digest::SHA1.new
-  tmp = "#{output}.tmp"
-  Net::HTTP.start(uri.host, uri.port, :use_ssl => (uri.scheme == "https")) do |http|
-    request = Net::HTTP::Get.new(uri.path)
-    http.request(request) do |response|
-      fail "HTTP fetch failed for #{url}. #{response}" if [200, 301].include?(response.code)
-      size = (response["content-length"].to_i || -1).to_f
-      count = 0
-      File.open(tmp, "w") do |fd|
-        response.read_body do |chunk|
-          fd.write(chunk)
-          digest << chunk
-          if size > 0 && $stdout.tty?
-            count += chunk.bytesize
-            $stdout.write(sprintf("\r%0.2f%%", count/size * 100))
-          end
-        end
-      end
-      $stdout.write("\r      \r") if $stdout.tty?
-    end
-  end
-
-  File.rename(tmp, output)
-
-  return digest.hexdigest
-rescue SocketError => e
-  puts "Failure while downloading #{url}: #{e}"
-  raise
-ensure
-  File.unlink(tmp) if File.exist?(tmp)
-end # def download
-
-def untar(tarball, &block)
-  require "archive/tar/minitar"
-  tgz = Zlib::GzipReader.new(File.open(tarball))
-  # Pull out typesdb
-  tar = Archive::Tar::Minitar::Input.open(tgz)
-  tar.each do |entry|
-    path = block.call(entry)
-    next if path.nil?
-    parent = File.dirname(path)
-    
-    mkdir_p parent unless File.directory?(parent)
-
-    # Skip this file if the output file is the same size
-    if entry.directory?
-      mkdir path unless File.directory?(path)
-    else
-      entry_mode = entry.instance_eval { @mode } & 0777
-      if File.exists?(path)
-        stat = File.stat(path)
-        # TODO(sissel): Submit a patch to archive-tar-minitar upstream to
-        # expose headers in the entry.
-        entry_size = entry.instance_eval { @size }
-        # If file sizes are same, skip writing.
-        next if stat.size == entry_size && (stat.mode & 0777) == entry_mode
-      end
-      puts "Extracting #{entry.full_name} from #{tarball} #{entry_mode.to_s(8)}"
-      File.open(path, "w") do |fd|
-        # eof? check lets us skip empty files. Necessary because the API provided by
-        # Archive::Tar::Minitar::Reader::EntryStream only mostly acts like an
-        # IO object. Something about empty files in this EntryStream causes
-        # IO.copy_stream to throw "can't convert nil into String" on JRuby
-        # TODO(sissel): File a bug about this.
-        while !entry.eof?
-          chunk = entry.read(16384)
-          fd.write(chunk)
-        end
-          #IO.copy_stream(entry, fd)
-      end
-      File.chmod(entry_mode, path)
-    end
-  end
-  tar.close
-  File.unlink(tarball) if File.file?(tarball)
-end # def untar
-
-def ungz(file)
-
-  outpath = file.gsub('.gz', '')
-  tgz = Zlib::GzipReader.new(File.open(file))
-  begin
-    File.open(outpath, "w") do |out|
-      IO::copy_stream(tgz, out)
-    end
-    File.unlink(file)
-  rescue
-    File.unlink(outpath) if File.file?(outpath)
-   raise
-  end
-  tgz.close
-end
-
-desc "Process any vendor files required for this plugin"
-task "vendor" do |task, args|
-
-  @files.each do |file| 
-    download = file_fetch(file['url'], file['sha1'])
-    if download =~ /.tar.gz/
-      prefix = download.gsub('.tar.gz', '').gsub('vendor/', '')
-      untar(download) do |entry|
-        if !file['files'].nil?
-          next unless file['files'].include?(entry.full_name.gsub(prefix, ''))
-          out = entry.full_name.split("/").last
-        end
-        File.join('vendor', out)
-      end
-    elsif download =~ /.gz/
-      ungz(download)
-    end
-  end
-
-end