Sha256: 2d0520953ab4b47e42a501bb6cfff1ea5d22d8a910e8e2db0c87737729aa3f4d
Contents?: true
Size: 907 Bytes
Versions: 14
Compression:
Stored size: 907 Bytes
Contents
require "xmlsimple"
module Solrizer::XML::Extractor
#
# This method extracts solr fields from simple xml
# If you want to do anything more nuanced with the xml, use TerminologyBasedSolrizer instead.
#
# @param [xml] text xml content to index
# @param [Hash] solr_doc
def xml_to_solr( text, solr_doc=Hash.new )
doc = XmlSimple.xml_in( text )
doc.each_pair do |name, value|
if value.kind_of?(Array)
if value.first.kind_of?(Hash)
# This deals with the way xml-simple handles nodes with attributes
solr_doc.merge!({:"#{name}_t" => "#{value.first["content"]}"})
elsif value.length > 1
solr_doc.merge!({:"#{name}_t" => value})
else
solr_doc.merge!({:"#{name}_t" => "#{value.first}"})
end
else
solr_doc.merge!({:"#{name}_t" => "#{value}"})
end
end
return solr_doc
end
end
Version data entries
14 entries across 14 versions & 1 rubygems