patch rexml to improve performance of multi-threaded xml parsing

.travis.yml

@@ -5,5 +5,5 @@ import:
 env:
   jobs:
     # lock on version 8.x because use Ruby 2.6.0 available from 8.4.0
-    - ELASTIC_STACK_VERSION=8.x DOCKER_ENV=dockerjdk17.env
-    - SNAPSHOT=true ELASTIC_STACK_VERSION=8.x DOCKER_ENV=dockerjdk17.env
+    - ELASTIC_STACK_VERSION=8.x DOCKER_ENV=dockerjdk21.env
+    - SNAPSHOT=true ELASTIC_STACK_VERSION=8.x DOCKER_ENV=dockerjdk21.env

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 4.2.1
+  - patch rexml to improve performance of multi-threaded xml parsing [#84](https://github.com/logstash-plugins/logstash-filter-xml/pull/84)
+#84
+
 ## 4.2.0
   - Update Nokogiri dependency version [#78](https://github.com/logstash-plugins/logstash-filter-xml/pull/78)
 

lib/logstash/filters/xml.rb

@@ -1,6 +1,7 @@
 # encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
+require "logstash/filters/xml/patch_rexml"
 
 # XML filter. Takes a field that contains XML and expands it into
 # an actual datastructure.

lib/logstash/filters/xml/patch_rexml.rb

@@ -0,0 +1,27 @@
+require 'xmlsimple'
+require 'stringio'
+
+module REXML
+  class SourceFactory
+    # Generates a Source object
+    # @param arg Either a String, or an IO
+    # @return a Source, or nil if a bad argument was given
+    def SourceFactory::create_from(arg)
+      if arg.respond_to? :read and
+          arg.respond_to? :readline and
+          arg.respond_to? :nil? and
+          arg.respond_to? :eof?
+        IOSource.new(arg)
+      elsif arg.respond_to? :to_str
+        # remove this require to speed up multi-threaded parsing
+        #require 'stringio'
+        IOSource.new(StringIO.new(arg))
+      elsif arg.kind_of? Source
+        arg
+      else
+        raise "#{arg.class} is not a valid input stream.  It must walk \n"+
+          "like either a String, an IO, or a Source."
+      end
+    end
+  end
+end

logstash-filter-xml.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-filter-xml'
-  s.version         = '4.2.0'
+  s.version         = '4.2.1'
   s.licenses        = ['Apache License (2.0)']
   s.summary         = "Parses XML into fields"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"