logstash-filter-xml 4.2.0 → 4.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 41486355fca6576c993aabd98476dd39888ba6467b8f91f3a4e76d3d45da06b0
-  data.tar.gz: 13ea42b6f0b45fcf03051b468965b342e6d02b72c5ee41a8bb5ae08423dfe714
+  metadata.gz: c200fc7ce008ce13a62be488be3e2b683afc4df6cb93a9d7bfcd54f5f9480d1e
+  data.tar.gz: d2d2bd14a0a79ca27d17ce59cad5464b62ba3bc7963feb0e2b6be987d3fc9b4c
 SHA512:
-  metadata.gz: 938a1e47c3739672583e4cad10c6083a092335bb3191a6479b4da757d14d9dca02542446f1bb2db3d87cbf77860f2cb7e9b1759a4fad5b82baaaf73cd6c83902
-  data.tar.gz: 67e01e1ce39cd128bad8f1450d542f8c5ecf79ad3268675fb01f415d26c196f0b3ff7b71ac880ba248474b6be8a82310fe24aa76d1f3dbcdcf404767be20c839
+  metadata.gz: 4f0c8ebb2e173d759d52574ffb61ed93d7fea20ae455d8fcee0e15171ebafad0fe094be9351061cdb55f203390cc533d5780e3803492b0ed11d719371a1aecc5
+  data.tar.gz: 42a633c4a27b41bdf785e19eeff71cce3a26d986e9237fe70960f899c384bbaf3f22d3d57a4949a974fe1e6f6d49b5e2e6280c92e1d91c9aa2f6a640ce157d10

data/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)
 

data/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

data/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.

data/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"

data/spec/filters/xml_spec.rb

@@ -15,55 +15,55 @@ describe LogStash::Filters::Xml do
     }
     CONFIG
 
-    sample("raw" => '<foo key="value"/>') do
+    sample({"raw" => '<foo key="value"/>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == {"key" => "value"}
     end
 
     #From parse xml with array as a value
-    sample("raw" => '<foo><key>value1</key><key>value2</key></foo>') do
+    sample({"raw" => '<foo><key>value1</key><key>value2</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == {"key" => ["value1", "value2"]}
     end
 
     #From parse xml with hash as a value
-    sample("raw" => '<foo><key1><key2>value</key2></key1></foo>') do
+    sample({"raw" => '<foo><key1><key2>value</key2></key1></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == {"key1" => [{"key2" => ["value"]}]}
     end
 
     # parse xml in single item array
-    sample("raw" => ["<foo bar=\"baz\"/>"]) do
+    sample({"raw" => ["<foo bar=\"baz\"/>"]}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == {"bar" => "baz"}
     end
 
     # fail in multi items array
-    sample("raw" => ["<foo bar=\"baz\"/>", "jojoba"]) do
+    sample({"raw" => ["<foo bar=\"baz\"/>", "jojoba"]}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
       insist { subject.get("data")} == nil
     end
 
     # fail in empty array
-    sample("raw" => []) do
+    sample({"raw" => []}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
       insist { subject.get("data")} == nil
     end
 
     # fail for non string field
-    sample("raw" => {"foo" => "bar"}) do
+    sample({"raw" => {"foo" => "bar"}}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
       insist { subject.get("data")} == nil
     end
 
     # fail for non string single item array
-    sample("raw" => [{"foo" => "bar"}]) do
+    sample({"raw" => [{"foo" => "bar"}]}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
       insist { subject.get("data")} == nil
     end
 
     #From bad xml
-    sample("raw" => '<foo /') do
+    sample({"raw" => '<foo /'}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
     end
   end
@@ -79,7 +79,7 @@ describe LogStash::Filters::Xml do
     }
     CONFIG
 
-    sample("raw" => '<foo key="value"/>') do
+    sample({"raw" => '<foo key="value"/>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == nil
     end
@@ -97,13 +97,13 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("raw" => '<foo><key>value</key></foo>') do
+    sample({"raw" => '<foo><key>value</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("xpath_field")} == ["value"]
     end
 
     #Multiple values
-    sample("raw" => '<foo><key>value1</key><key>value2</key></foo>') do
+    sample({"raw" => '<foo><key>value1</key><key>value2</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("xpath_field")} == ["value1","value2"]
     end
@@ -121,25 +121,25 @@ describe LogStash::Filters::Xml do
     }
     CONFIG
 
-    sample("xmldata" => '<foo key="value"/>') do
+    sample({"xmldata" => '<foo key="value"/>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data") } == {"key" => "value"}
     end
 
     #From parse xml with array as a value
-    sample("xmldata" => '<foo><key>value1</key><key>value2</key></foo>') do
+    sample({"xmldata" => '<foo><key>value1</key><key>value2</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data") } == {"key" => ["value1", "value2"]}
     end
 
     #From parse xml with hash as a value
-    sample("xmldata" => '<foo><key1><key2>value</key2></key1></foo>') do
+    sample({"xmldata" => '<foo><key1><key2>value</key2></key1></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data") } == {"key1" => [{"key2" => ["value"]}]}
     end
 
     #From bad xml
-    sample("xmldata" => '<foo /') do
+    sample({"xmldata" => '<foo /'}) do
       insist { subject.get("tags") }.include?("_xmlparsefailure")
     end
   end
@@ -155,7 +155,7 @@ describe LogStash::Filters::Xml do
     }
     CONFIG
 
-    sample("xmldata" => '<foo key="value"/>') do
+    sample({"xmldata" => '<foo key="value"/>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("data")} == nil
     end
@@ -173,13 +173,13 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo><key>value</key></foo>') do
+    sample({"xmldata" => '<foo><key>value</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("xpath_field") } == ["value"]
     end
 
     #Multiple values
-    sample("xmldata" => '<foo><key>value1</key><key>value2</key></foo>') do
+    sample({"xmldata" => '<foo><key>value1</key><key>value2</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("xpath_field") } == ["value1","value2"]
     end
@@ -197,7 +197,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo><key>Français</key></foo>') do
+    sample({"xmldata" => '<foo><key>Français</key></foo>'}) do
       insist { subject.get("tags") }.nil?
       insist { subject.get("xpath_field")} == ["Français"]
     end
@@ -216,7 +216,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>') do
+    sample({"xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>'}) do
       insist { subject.get("xpath_field") } == ["<h:div>Content</h:div>"]
     end
   end
@@ -235,7 +235,7 @@ describe LogStash::Filters::Xml do
       CONFIG
 
       # Single value
-      sample("xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>') do
+      sample({"xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>'}) do
         insist { subject.get("xpath_field") } == ["<h:div>Content</h:div>"]
       end
   end
@@ -254,7 +254,7 @@ describe LogStash::Filters::Xml do
       CONFIG
 
       # Single value
-      sample("xmldata" => '<foo><h:div xmlns:h="http://www.w3.org/TR/html4/">Content</h:div></foo>') do
+      sample({"xmldata" => '<foo><h:div xmlns:h="http://www.w3.org/TR/html4/">Content</h:div></foo>'}) do
         insist { subject.get("xpath_field") } == ["<h:div xmlns:h=\"http://www.w3.org/TR/html4/\">Content</h:div>"]
       end
   end
@@ -272,7 +272,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>') do
+    sample({"xmldata" => '<foo xmlns:h="http://www.w3.org/TR/html4/"><h:div>Content</h:div></foo>'}) do
       insist { subject.get("xpath_field") } == ["<div>Content</div>"]
     end
   end
@@ -289,7 +289,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo><bar>Content</bar></foo>') do
+    sample({"xmldata" => '<foo><bar>Content</bar></foo>'}) do
       insist { subject.get("parseddata") } == { "bar" => ["Content"] }
     end
   end
@@ -306,7 +306,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<foo><bar>Content</bar></foo>') do
+    sample({"xmldata" => '<foo><bar>Content</bar></foo>'}) do
       insist { subject.get("parseddata") } == { "bar" => "Content" }
     end
   end
@@ -326,7 +326,7 @@ describe LogStash::Filters::Xml do
     CONFIG
 
     # Single value
-    sample("xmldata" => '<element><field1>bbb</field1><field2>789</field2><field3>e3f<field3></element>') do
+    sample({"xmldata" => '<element><field1>bbb</field1><field2>789</field2><field3>e3f<field3></element>'}) do
       insist { subject.get("field1") } == "bbb"
     end
   end
@@ -343,7 +343,7 @@ describe LogStash::Filters::Xml do
       }
       CONFIG
 
-      sample("xmldata" => '<foo><key>value1</key><key></key></foo>') do
+      sample({"xmldata" => '<foo><key>value1</key><key></key></foo>'}) do
         insist { subject.get("tags") }.nil?
         insist { subject.get("data") } == {"key" => ["value1", {}]}
       end
@@ -360,7 +360,7 @@ describe LogStash::Filters::Xml do
       }
       CONFIG
 
-      sample("xmldata" => '<foo><key>value1</key><key></key></foo>') do
+      sample({"xmldata" => '<foo><key>value1</key><key></key></foo>'}) do
         insist { subject.get("tags") }.nil?
         insist { subject.get("data") } == {"key" => ["value1"]}
       end
@@ -380,7 +380,7 @@ describe LogStash::Filters::Xml do
       }
       CONFIG
 
-      sample("xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>') do
+      sample({"xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>'}) do
         insist { subject.get("tags") }.nil?
         insist { subject.get("data") } ==  { 'x' => 'text1', 'y' => { 'a' => '2', 'content' => 'text2' } }
       end
@@ -397,7 +397,7 @@ describe LogStash::Filters::Xml do
       }
       CONFIG
 
-      sample("xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>') do
+      sample({"xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>'}) do
         insist { subject.get("tags") }.nil?
         insist { subject.get("data") } ==  { 'x' => { 'content' => 'text1' }, 'y' => { 'a' => '2', 'content' => 'text2' } }
       end
@@ -413,7 +413,7 @@ describe LogStash::Filters::Xml do
       }
       CONFIG
 
-      sample("raw" => '<foobar></foobar>') do
+      sample({"raw" => '<foobar></foobar>'}) do
         insist { subject.get("tags") }.nil?
         insist { subject.get("xpath_field")}.nil?
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-filter-xml
 version: !ruby/object:Gem::Version
-  version: 4.2.0
+  version: 4.2.1
 platform: ruby
 authors:
 - Elastic
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-08-17 00:00:00.000000000 Z
+date: 2024-10-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -17,8 +17,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 8.4.0
   name: logstash-core
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -34,8 +34,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.99'
   name: logstash-core-plugin-api
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -51,8 +51,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 1.13.8
   name: nokogiri
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -65,8 +65,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
   name: xml-simple
-  prerelease: false
   type: :runtime
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -79,8 +79,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
   name: logstash-devutils
-  prerelease: false
   type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -93,8 +93,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
   name: insist
-  prerelease: false
   type: :development
+  prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -116,6 +116,7 @@ files:
 - README.md
 - docs/index.asciidoc
 - lib/logstash/filters/xml.rb
+- lib/logstash/filters/xml/patch_rexml.rb
 - logstash-filter-xml.gemspec
 - spec/filters/xml_spec.rb
 homepage: http://www.elastic.co/guide/en/logstash/current/index.html
@@ -139,7 +140,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.29
+rubygems_version: 3.3.26
 signing_key:
 specification_version: 4
 summary: Parses XML into fields