Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Added author and page count to import. Adjusted schema to not stem or remove stop words. 

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@503377 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Erik Hatcher 2007-02-04 09:39:55 +00:00
parent c06fe80ce9
commit 32d4ad8b3b
2 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
client/ruby/solrb/examples/delicious_library/conf/schema.xml
View File

@ -146,19 +146,19 @@
<!-- in this example, we will only use synonyms at query time <!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
--> -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> <!-- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> -->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/> <filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> <!-- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer> </analyzer>
<analyzer type="query"> <analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/> <tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> <!-- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> <!-- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> -->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/> <filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> <!-- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer> </analyzer>
</fieldtype> </fieldtype>

10
client/ruby/solrb/examples/delicious_library/dl_importer.rb
View File

@ -1,3 +1,4 @@
#!/usr/bin/env ruby
# The ASF licenses this file to You under the Apache License, Version 2.0 # The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with # (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at # the License. You may obtain a copy of the License at
@ -22,7 +23,7 @@ debug = ARGV[1] == "-debug"
solr = Solr::Connection.new(solr_url) solr = Solr::Connection.new(solr_url)
lines = IO.readlines(dl_filename) lines = IO.readlines(dl_filename)
headers = lines[0].split("\t") headers = lines[0].split("\t").collect{|h| h.chomp}
puts headers.join(','),"-----" if debug puts headers.join(','),"-----" if debug
# Exported column names # Exported column names
@ -41,11 +42,13 @@ mapping = {
:title_text => :title, :title_text => :title,
:notes_text => :notes, :notes_text => :notes,
:publisher_text => :publisher, :publisher_text => :publisher,
:description_text => :description :description_text => :description,
:author_text => :author,
:pages_text => :pages
} }
lines[1..-1].each do |line| lines[1..-1].each do |line|
data = headers.zip(line.split("\t")) data = headers.zip(line.split("\t").collect{|s| s.chomp})
def data.method_missing(key) def data.method_missing(key)
self.assoc(key.to_s)[1] self.assoc(key.to_s)[1]
end end
@ -60,6 +63,7 @@ lines[1..-1].each do |line|
doc[solr_name] = value if value doc[solr_name] = value if value
end end
puts data.title
puts doc.inspect if debug puts doc.inspect if debug
solr.add doc unless debug solr.add doc unless debug