logstash-input-sqlite 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YmQ0ZTFlMzE0ZWRmNTFkY2U2MjY3NGExNzcxMDBhMjZhZDE1NTllMg==
+  data.tar.gz: !binary |-
+    NmNmMWY4ZmQ3NDBjMzA1ZTI5ZDY2OTEyOTYzZDE1YWMwOWI0ODhhMg==
+SHA512:
+  metadata.gz: !binary |-
+    NmQyMGMyMDE2YzRiMzFhZmQ3Yzc3MGUwOGQyYjA1MThhM2VhNWM5MmM4NWRl
+    YjNiNTMzM2E0MmIzMWIyNGJhNTFlNmQwZDZhNzA1MzY5ODRmZWIyNTIzZGNk
+    Nzc2ZWFhZTg5YTUwZTRkYjJhODczZTEzOWI2NTdiZjNiMmNlOTY=
+  data.tar.gz: !binary |-
+    NDE3OTBjMzM3Y2U0OWJkZjM3MjFjZmRjYTUwOGE3ODY2NzU4Njc3Njg4MjVi
+    YWE0MzI5Y2E4MzBhYjhlYjViN2VjMjIyNmY0NmVhZmIzZGM2ZjFkZDNkNzgy
+    MzliYWVjMmE5YmE2M2I1MDliMWYxNGU2ZGQ0ZTRkNzNkY2FlNzA=

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+Gemfile.lock
+.bundle
+vendor

data/Gemfile

@@ -0,0 +1,4 @@
+source 'http://rubygems.org'
+gem 'rake'
+gem 'gem_publisher'
+gem 'archive-tar-minitar'

data/LICENSE

@@ -0,0 +1,13 @@
+Copyright (c) 2012-2014 Elasticsearch <http://www.elasticsearch.org>
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/Rakefile

@@ -0,0 +1,6 @@
+@files=[]
+
+task :default do
+  system("rake -T")
+end
+

data/lib/logstash/inputs/sqlite.rb

@@ -0,0 +1,186 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "socket"
+
+
+# Read rows from an sqlite database.
+#
+# This is most useful in cases where you are logging directly to a table.
+# Any tables being watched must have an 'id' column that is monotonically
+# increasing.
+#
+# All tables are read by default except:
+# * ones matching 'sqlite_%' - these are internal/adminstrative tables for sqlite
+# * 'since_table' - this is used by this plugin to track state.
+#
+# ## Example
+# 
+#     % sqlite /tmp/example.db
+#     sqlite> CREATE TABLE weblogs (
+#         id INTEGER PRIMARY KEY AUTOINCREMENT,
+#         ip STRING,
+#         request STRING,
+#         response INTEGER);
+#     sqlite> INSERT INTO weblogs (ip, request, response) 
+#         VALUES ("1.2.3.4", "/index.html", 200);
+#
+# Then with this logstash config:
+#
+#     input {
+#       sqlite {
+#         path => "/tmp/example.db"
+#         type => weblogs
+#       }
+#     }
+#     output {
+#       stdout {
+#         debug => true
+#       }
+#     }
+#
+# Sample output:
+#
+#     {
+#       "@source"      => "sqlite://sadness/tmp/x.db",
+#       "@tags"        => [],
+#       "@fields"      => {
+#         "ip"       => "1.2.3.4",
+#         "request"  => "/index.html",
+#         "response" => 200
+#       },
+#       "@timestamp"   => "2013-05-29T06:16:30.850Z",
+#       "@source_host" => "sadness",
+#       "@source_path" => "/tmp/x.db",
+#       "@message"     => "",
+#       "@type"        => "foo"
+#     }
+#
+class LogStash::Inputs::Sqlite < LogStash::Inputs::Base
+  config_name "sqlite"
+  milestone 1
+
+  # The path to the sqlite database file.
+  config :path, :validate => :string, :required => true
+
+  # Any tables to exclude by name.
+  # By default all tables are followed.
+  config :exclude_tables, :validate => :array, :default => []
+
+  # How many rows to fetch at a time from each SELECT call.
+  config :batch, :validate => :number, :default => 5
+
+  SINCE_TABLE = :since_table
+
+  public
+  def init_placeholder_table(db)
+    begin
+      db.create_table SINCE_TABLE do 
+        String :table
+        Int    :place
+      end
+    rescue
+      @logger.debug("since tables already exists")
+    end
+  end
+
+  public
+  def get_placeholder(db, table)
+    since = db[SINCE_TABLE]
+    x = since.where(:table => "#{table}")
+    if x[:place].nil?
+      init_placeholder(db, table) 
+      return 0
+    else
+      @logger.debug("placeholder already exists, it is #{x[:place]}")
+      return x[:place][:place]
+    end
+  end
+
+  public 
+  def init_placeholder(db, table)
+    @logger.debug("init placeholder for #{table}")
+    since = db[SINCE_TABLE]
+    since.insert(:table => table, :place => 0)
+  end
+
+  public
+  def update_placeholder(db, table, place)
+    @logger.debug("set placeholder to #{place}")
+    since = db[SINCE_TABLE]
+    since.where(:table => table).update(:place => place)
+  end
+
+  public 
+  def get_all_tables(db)
+    return db["SELECT * FROM sqlite_master WHERE type = 'table' AND tbl_name != '#{SINCE_TABLE}' AND tbl_name NOT LIKE 'sqlite_%'"].map { |t| t[:name] }.select { |n| !@exclude_tables.include?(n) }
+  end
+  
+  public
+  def get_n_rows_from_table(db, table, offset, limit)
+    dataset = db["SELECT * FROM #{table}"]
+    return db["SELECT * FROM #{table} WHERE (id > #{offset}) ORDER BY 'id' LIMIT #{limit}"].map { |row| row }
+  end
+  
+  public
+  def register
+    require "sequel"
+    require "jdbc/sqlite3" 
+    @host = Socket.gethostname
+    @logger.info("Registering sqlite input", :database => @path)
+    @db = Sequel.connect("jdbc:sqlite:#{@path}") 
+    @tables = get_all_tables(@db)
+    @table_data = {}
+    @tables.each do |table|
+      init_placeholder_table(@db)
+      last_place = get_placeholder(@db, table)
+      @table_data[table] = { :name => table, :place => last_place }
+    end
+  end # def register
+
+  public
+  def run(queue)
+    sleep_min = 0.01
+    sleep_max = 5
+    sleeptime = sleep_min
+
+    begin
+      @logger.debug("Tailing sqlite db", :path => @path)
+      loop do
+        count = 0
+        @table_data.each do |k, table|
+          table_name = table[:name]
+          offset = table[:place]
+          @logger.debug("offset is #{offset}", :k => k, :table => table_name)
+          rows = get_n_rows_from_table(@db, table_name, offset, @batch)
+          count += rows.count
+          rows.each do |row| 
+            event = LogStash::Event.new("host" => @host, "db" => @db)
+            decorate(event)
+            # store each column as a field in the event.
+            row.each do |column, element|
+              next if column == :id
+              event[column.to_s] = element
+            end
+            queue << event
+            @table_data[k][:place] = row[:id]
+          end
+          # Store the last-seen row in the database
+          update_placeholder(@db, table_name, @table_data[k][:place])
+        end
+
+        if count == 0
+          # nothing found in that iteration
+          # sleep a bit
+          @logger.debug("No new rows. Sleeping.", :time => sleeptime)
+          sleeptime = [sleeptime * 2, sleep_max].min
+          sleep(sleeptime)
+        else
+          sleeptime = sleep_min
+        end
+      end # loop
+    end # begin/rescue
+  end #run
+
+end # class Logtstash::Inputs::EventLog
+

data/logstash-input-sqlite.gemspec

@@ -0,0 +1,29 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-input-sqlite'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Read rows from an sqlite database."
+  s.description     = "Read rows from an sqlite database."
+  s.authors         = ["Elasticsearch"]
+  s.email           = 'richard.pijnenburg@elasticsearch.com'
+  s.homepage        = "http://logstash.net/"
+  s.require_paths = ["lib"]
+
+  # Files
+  s.files = `git ls-files`.split($\)+::Dir.glob('vendor/*')
+
+  # Tests
+  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" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+  s.add_runtime_dependency 'sequel'
+  s.add_runtime_dependency 'jdbc-sqlite3'
+
+end
+

data/rakelib/publish.rake

@@ -0,0 +1,9 @@
+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

@@ -0,0 +1,169 @@
+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

data/spec/inputs/sqlite_spec.rb

@@ -0,0 +1 @@
+require 'spec_helper'

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: logstash-input-sqlite
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash
+  requirement: !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
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: sequel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: jdbc-sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Read rows from an sqlite database.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- Rakefile
+- lib/logstash/inputs/sqlite.rb
+- logstash-input-sqlite.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/inputs/sqlite_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  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: 
+specification_version: 4
+summary: Read rows from an sqlite database.
+test_files:
+- spec/inputs/sqlite_spec.rb