logstash-filter-xml 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    NjBhYWFkYzM0NjM2ODNkNmQwYTg3YzRkNjc0ZmUzMDFhYjkzNTkzNg==
+  data.tar.gz: !binary |-
+    ZjM5NWZhMzczOTZkZTRmOTFiZmVjNDNhOWNiNDk2YjJjODc3Y2M3OQ==
+SHA512:
+  metadata.gz: !binary |-
+    ODNkOTFiNDVhODEyNWI5NzcwYmJiNWU3ZmNjYTJmNDRmMWZkMGY0ZjAwODg1
+    ZDhhOGUzYTg5NmYxOTQ0ZjBjZTAzYzFiMDQ2ZjVmYmMwYTcyY2U1YmEzODE1
+    Mzc4OTkxY2JiMGI1YmJiMDgzMzIyMDg2ZWU0ZjVjYTdmZTFkNWU=
+  data.tar.gz: !binary |-
+    MmJlM2M0MTRhNDEwODU1Y2I2OWE5ZGIxYWMxZGZkMTRkMDllNjhlNWJlYTE3
+    NzQ4NmU0YTI5ZDkxMzY4NGJkZDgxODc4NTZmMGQ2ODkxMDdmMWU1YTE4N2Fj
+    MGMxYmJhN2FmNGMyY2ZhOGZmOGQzMTFlMjUwYmVjMzFkMTEwM2M=

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/Rakefile

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

data/lib/logstash/filters/xml.rb

@@ -0,0 +1,139 @@
+# encoding: utf-8
+require "logstash/filters/base"
+require "logstash/namespace"
+
+# XML filter. Takes a field that contains XML and expands it into
+# an actual datastructure.
+class LogStash::Filters::Xml < LogStash::Filters::Base
+
+  config_name "xml"
+  milestone 1
+
+  # Config for xml to hash is:
+  #
+  #     source => source_field
+  #
+  # For example, if you have the whole xml document in your @message field:
+  #
+  #     filter {
+  #       xml {
+  #         source => "message"
+  #       }
+  #     }
+  #
+  # The above would parse the xml from the @message field
+  config :source, :validate => :string
+
+  # Define target for placing the data
+  #
+  # for example if you want the data to be put in the 'doc' field:
+  #
+  #     filter {
+  #       xml {
+  #         target => "doc"
+  #       }
+  #     }
+  #
+  # XML in the value of the source field will be expanded into a
+  # datastructure in the "target" field.
+  # Note: if the "target" field already exists, it will be overridden
+  # Required
+  config :target, :validate => :string
+
+  # xpath will additionally select string values (.to_s on whatever is selected)
+  # from parsed XML (using each source field defined using the method above)
+  # and place those values in the destination fields. Configuration:
+  #
+  # xpath => [ "xpath-syntax", "destination-field" ]
+  #
+  # Values returned by XPath parsring from xpath-synatx will be put in the
+  # destination field. Multiple values returned will be pushed onto the
+  # destination field as an array. As such, multiple matches across
+  # multiple source fields will produce duplicate entries in the field
+  #
+  # More on xpath: http://www.w3schools.com/xpath/
+  #
+  # The xpath functions are particularly powerful:
+  # http://www.w3schools.com/xpath/xpath_functions.asp
+  #
+  config :xpath, :validate => :hash, :default => {}
+
+  # By default the filter will store the whole parsed xml in the destination
+  # field as described above. Setting this to false will prevent that.
+  config :store_xml, :validate => :boolean, :default => true
+
+  public
+  def register
+    require "nokogiri"
+    require "xmlsimple"
+
+  end # def register
+
+  public
+  def filter(event)
+    return unless filter?(event)
+    matched = false
+
+    @logger.debug("Running xml filter", :event => event)
+
+    return unless event.include?(@source)
+
+    value = event[@source]
+
+    if value.is_a?(Array) && value.length > 1
+      @logger.warn("XML filter only works on fields of length 1",
+                   :source => @source, :value => value)
+      return
+    end
+
+    # Do nothing with an empty string.
+    return if value.strip.length == 0
+
+    if @xpath
+      begin
+        doc = Nokogiri::XML(value)
+      rescue => e
+        event.tag("_xmlparsefailure")
+        @logger.warn("Trouble parsing xml", :source => @source, :value => value,
+                     :exception => e, :backtrace => e.backtrace)
+        return
+      end
+
+      @xpath.each do |xpath_src, xpath_dest|
+        nodeset = doc.xpath(xpath_src)
+
+        # If asking xpath for a String, like "name(/*)", we get back a
+        # String instead of a NodeSet.  We normalize that here.
+        normalized_nodeset = nodeset.kind_of?(Nokogiri::XML::NodeSet) ? nodeset : [nodeset]
+
+        normalized_nodeset.each do |value|
+          # some XPath functions return empty arrays as string
+          if value.is_a?(Array)
+            return if value.length == 0
+          end
+
+          unless value.nil?
+            matched = true
+            event[xpath_dest] ||= []
+            event[xpath_dest] << value.to_s
+          end
+        end # XPath.each
+      end # @xpath.each
+    end # if @xpath
+
+    if @store_xml
+      begin
+        event[@target] = XmlSimple.xml_in(value)
+        matched = true
+      rescue => e
+        event.tag("_xmlparsefailure")
+        @logger.warn("Trouble parsing xml with XmlSimple", :source => @source,
+                     :value => value, :exception => e, :backtrace => e.backtrace)
+        return
+      end
+    end # if @store_xml
+
+    filter_matched(event) if matched
+    @logger.debug("Event after xml filter", :event => event)
+  end # def filter
+end # class LogStash::Filters::Xml

data/logstash-filter-xml.gemspec

@@ -0,0 +1,27 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-filter-xml'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Takes a field that contains XML and expands it into an actual datastructure."
+  s.description     = "Takes a field that contains XML and expands it into an actual datastructure."
+  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($\)
+
+  # 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" => "filter" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+  s.add_runtime_dependency 'nokogiri'
+
+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/filters/xml_spec.rb

@@ -0,0 +1,175 @@
+# encoding: utf-8
+require "spec_helper"
+require "logstash/filters/xml"
+
+describe LogStash::Filters::Xml do
+
+  describe "parse standard xml (Deprecated checks)" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "raw"
+        target => "data"
+      }
+    }
+    CONFIG
+
+    sample("raw" => '<foo key="value"/>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key" => "value"}
+    end
+
+    #From parse xml with array as a value
+    sample("raw" => '<foo><key>value1</key><key>value2</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key" => ["value1", "value2"]}
+    end
+
+    #From parse xml with hash as a value
+    sample("raw" => '<foo><key1><key2>value</key2></key1></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key1" => [{"key2" => ["value"]}]}
+    end
+
+    #From bad xml
+    sample("raw" => '<foo /') do
+      insist { subject["tags"] }.include?("_xmlparsefailure")
+    end
+  end
+
+  describe "parse standard xml but do not store (Deprecated checks)" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "raw"
+        target => "data"
+        store_xml => false
+      }
+    }
+    CONFIG
+
+    sample("raw" => '<foo key="value"/>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == nil
+    end
+  end
+
+  describe "parse xml and store values with xpath (Deprecated checks)" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "raw"
+        target => "data"
+        xpath => [ "/foo/key/text()", "xpath_field" ]
+      }
+    }
+    CONFIG
+
+    # Single value
+    sample("raw" => '<foo><key>value</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["xpath_field"]} == ["value"]
+    end
+
+    #Multiple values
+    sample("raw" => '<foo><key>value1</key><key>value2</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["xpath_field"]} == ["value1","value2"]
+    end
+  end
+
+  ## New tests
+
+  describe "parse standard xml" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "xmldata"
+        target => "data"
+      }
+    }
+    CONFIG
+
+    sample("xmldata" => '<foo key="value"/>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key" => "value"}
+    end
+
+    #From parse xml with array as a value
+    sample("xmldata" => '<foo><key>value1</key><key>value2</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key" => ["value1", "value2"]}
+    end
+
+    #From parse xml with hash as a value
+    sample("xmldata" => '<foo><key1><key2>value</key2></key1></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == {"key1" => [{"key2" => ["value"]}]}
+    end
+
+    #From bad xml
+    sample("xmldata" => '<foo /') do
+      insist { subject["tags"] }.include?("_xmlparsefailure")
+    end
+  end
+
+  describe "parse standard xml but do not store" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "xmldata"
+        target => "data"
+        store_xml => false
+      }
+    }
+    CONFIG
+
+    sample("xmldata" => '<foo key="value"/>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["data"]} == nil
+    end
+  end
+
+  describe "parse xml and store values with xpath" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "xmldata"
+        target => "data"
+        xpath => [ "/foo/key/text()", "xpath_field" ]
+      }
+    }
+    CONFIG
+
+    # Single value
+    sample("xmldata" => '<foo><key>value</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["xpath_field"]} == ["value"]
+    end
+
+    #Multiple values
+    sample("xmldata" => '<foo><key>value1</key><key>value2</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["xpath_field"]} == ["value1","value2"]
+    end
+  end
+
+  describe "parse correctly non ascii content with xpath" do
+    config <<-CONFIG
+    filter {
+      xml {
+        source => "xmldata"
+        target => "data"
+        xpath => [ "/foo/key/text()", "xpath_field" ]
+      }
+    }
+    CONFIG
+
+    # Single value
+    sample("xmldata" => '<foo><key>Français</key></foo>') do
+      insist { subject["tags"] }.nil?
+      insist { subject["xpath_field"]} == ["Français"]
+    end
+  end
+
+end

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification
+name: logstash-filter-xml
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-10-25 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: nokogiri
+  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: Takes a field that contains XML and expands it into an actual datastructure.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/filters/xml.rb
+- logstash-filter-xml.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/filters/xml_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  group: filter
+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: Takes a field that contains XML and expands it into an actual datastructure.
+test_files:
+- spec/filters/xml_spec.rb