logstash-filter-xml 2.1.4 → 2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0bbe7a26079ee72f9c7ff4a22f793757f798d664
-  data.tar.gz: 463335a351bae555a468961e02f8bd2e06757552
+  metadata.gz: 3c54641de27d0a2d3d1521cf95ca13053cf79fdf
+  data.tar.gz: 45fa43b4e3e0e8d55de05be69ab68c8b2e63b8e0
 SHA512:
-  metadata.gz: 895e1fabb1950929973a761d0c3899e5cfe6854b2c0a1b71184b75260fe10167c52a0e8d4b1a1b176a39d3b3b695b58ea8dfaf42dc68cc1ffc45d4e49b0ffd82
-  data.tar.gz: ef8a46d212ede4351ffcbf62f562dff080557279530e7cfa432f827a3d8afb7dd4c0fe47f6b314c5392e08c40f3e70728b53a391398c37e5efd41752cd27f5ef
+  metadata.gz: e43cd5a04b877149db47c036303f1a74cfef0e6f3033c5994409f2d98edd957dcd9dcefff64e679bee7f134aa1e737c37c5b39adc21143223807e78f2580cec0
+  data.tar.gz: a54963d0704933285befe3b70ef4ec35fd921808cea3c631d5900cb0a6934fcc8c48e863f3d722eeccff1d82027289a4b837dd3054d0061698bbb25d1ed1af0c

data/CHANGELOG.md

@@ -1,9 +1,19 @@
-# 2.1.4
+## 2.2.0
+ - config: New configuration `suppress_empty`. By default the filter creates empty hash from empty xml elements (`suppress_empty => false`). 
+   This can now be configured, `supress_empty => true` will not create event fields from empty xml elements.
+ - config: New configuration `force_content`. By default the filter expands attributes differently from content in xml elements.
+   This option allows you to force text content and attributes to always parse to a hash value.
+ - config: Ensure that `target` is set when storing xml content in the event (`store_xml => true`)
+
+## 2.1.4
   - Added setting to disable forcing single values to be added in arrays. Ref: https://github.com/logstash-plugins/logstash-filter-xml/pull/28.
-# 2.1.3
+
+## 2.1.3
   - Depend on logstash-core-plugin-api instead of logstash-core, removing the need to mass update plugins on major releases of logstash
-# 2.1.2
+
+## 2.1.2
   - New dependency requirements for logstash-core for the 5.0 release
+
 ## 2.1.1
  - Refactored field references, code cleanups
 

data/lib/logstash/filters/xml.rb

@@ -51,10 +51,10 @@ class LogStash::Filters::Xml < LogStash::Filters::Base
   # 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/
+  # More on XPath: http://www.w3schools.com/xml/xml_xpath.asp
   #
   # The XPath functions are particularly powerful:
-  # http://www.w3schools.com/xpath/xpath_functions.asp
+  # http://www.w3schools.com/xsl/xsl_functions.asp
   #
   config :xpath, :validate => :hash, :default => {}
 
@@ -66,6 +66,11 @@ class LogStash::Filters::Xml < LogStash::Filters::Base
   # false will prevent storing single elements in arrays.
   config :force_array, :validate => :boolean, :default => true
 
+  # By default the filter will expand attributes differently from content inside
+  # of tags. This option allows you to force text content and attributes to always
+  # parse to a hash value.
+  config :force_content, :validate => :boolean, :default => false
+
   # By default only namespaces declarations on the root element are considered.
   # This allows to configure all namespace declarations to parse the XML document.
   #
@@ -87,11 +92,24 @@ class LogStash::Filters::Xml < LogStash::Filters::Base
   # Of course, if the document had nodes with the same names but different namespaces, they will now be ambiguous.
   config :remove_namespaces, :validate => :boolean, :default => false
 
+  # By default, empty element will result in an empty hash object
+  # If set to `true`, output nothing if the element is empty..
+  config :suppress_empty, :validate => :boolean, :default => false
+
   XMLPARSEFAILURE_TAG = "_xmlparsefailure"
 
   def register
     require "nokogiri"
     require "xmlsimple"
+
+    if @store_xml && (!@target || @target.empty?)
+      raise LogStash::ConfigurationError, I18n.t(
+        "logstash.agent.configuration.invalid_plugin_register",
+        :plugin => "filter",
+        :type => "xml",
+        :error => "When the 'store_xml' configuration option is true, 'target' must also be set"
+      )
+    end
   end
 
   def filter(event)
@@ -163,7 +181,9 @@ class LogStash::Filters::Xml < LogStash::Filters::Base
 
     if @store_xml
       begin
-        event[@target] = XmlSimple.xml_in(value, "ForceArray" => @force_array)
+        xml_options = {"ForceArray" => @force_array, "ForceContent" => @force_content}
+        xml_options["SuppressEmpty"] = true if @suppress_empty
+        event[@target] = XmlSimple.xml_in(value, xml_options)
         matched = true
       rescue => e
         event.tag(XMLPARSEFAILURE_TAG)

data/logstash-filter-xml.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-filter-xml'
-  s.version         = '2.1.4'
+  s.version         = '2.2.0'
   s.licenses        = ['Apache License (2.0)']
   s.summary         = "Takes a field that contains XML and expands it into an actual datastructure."
   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

@@ -209,6 +209,7 @@ describe LogStash::Filters::Xml do
         source => "xmldata"
         xpath => [ "/foo/h:div", "xpath_field" ]
         remove_namespaces => false
+        store_xml => false
       }
     }
     CONFIG
@@ -227,6 +228,7 @@ describe LogStash::Filters::Xml do
           xpath => [ "/foo/h:div", "xpath_field" ]
           namespaces => {"h" => "http://www.w3.org/TR/html4/"}
           remove_namespaces => false
+          store_xml => false
         }
       }
       CONFIG
@@ -245,6 +247,7 @@ describe LogStash::Filters::Xml do
           xpath => [ "/foo/h:div", "xpath_field" ]
           namespaces => {"h" => "http://www.w3.org/TR/html4/"}
           remove_namespaces => false
+          store_xml => false
         }
       }
       CONFIG
@@ -262,6 +265,7 @@ describe LogStash::Filters::Xml do
         source => "xmldata"
         xpath => [ "/foo/div", "xpath_field" ]
         remove_namespaces => true
+        store_xml => false
       }
     }
     CONFIG
@@ -306,4 +310,92 @@ describe LogStash::Filters::Xml do
     end
   end
 
+  context "Using suppress_empty option" do
+    describe "suppress_empty => false" do
+      config <<-CONFIG
+      filter {
+        xml {
+          source => "xmldata"
+          target => "data"
+          suppress_empty => false
+        }
+      }
+      CONFIG
+
+      sample("xmldata" => '<foo><key>value1</key><key></key></foo>') do
+        insist { subject["tags"] }.nil?
+        insist { subject["data"] } == {"key" => ["value1", {}]}
+      end
+    end
+
+    describe "suppress_empty => true" do
+      config <<-CONFIG
+      filter {
+        xml {
+          source => "xmldata"
+          target => "data"
+          suppress_empty => true
+        }
+      }
+      CONFIG
+
+      sample("xmldata" => '<foo><key>value1</key><key></key></foo>') do
+        insist { subject["tags"] }.nil?
+        insist { subject["data"] } == {"key" => ["value1"]}
+      end
+    end
+  end
+
+  context "Using force content option" do
+    describe "force_content => false" do
+      config <<-CONFIG
+      filter {
+        xml {
+          source => "xmldata"
+          target => "data"
+          force_array => false
+          force_content => false
+        }
+      }
+      CONFIG
+
+      sample("xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>') do
+        insist { subject["tags"] }.nil?
+        insist { subject["data"] } ==  { 'x' => 'text1', 'y' => { 'a' => '2', 'content' => 'text2' } }
+      end
+    end
+    describe "force_content => true" do
+      config <<-CONFIG
+      filter {
+        xml {
+          source => "xmldata"
+          target => "data"
+          force_array => false
+          force_content => true
+        }
+      }
+      CONFIG
+
+      sample("xmldata" => '<opt><x>text1</x><y a="2">text2</y></opt>') do
+        insist { subject["tags"] }.nil?
+        insist { subject["data"] } ==  { 'x' => { 'content' => 'text1' }, 'y' => { 'a' => '2', 'content' => 'text2' } }
+      end
+    end
+  end
+
+  describe "plugin registration" do
+    config <<-CONFIG
+    filter {
+      xml {
+        xmldata => "message"
+        store_xml => true
+      }
+    }
+    CONFIG
+
+    sample("xmldata" => "<foo>random message</foo>") do
+      insist { subject }.raises(LogStash::ConfigurationError)
+    end
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-filter-xml
 version: !ruby/object:Gem::Version
-  version: 2.1.4
+  version: 2.2.0
 platform: ruby
 authors:
 - Elastic
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2016-04-25 00:00:00.000000000 Z
+date: 2016-05-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logstash-core-plugin-api