Hi Ahmet,
I am using solr 5.5.0. I am running single instance with single core. No shards
I have added <similarity class="solr.BM25SimilarityFactory"/> to my schema as
suggested by Rick Sullivan. Now the scores are same between explain and score
field.
But instead of previous results "Lync - Microsoft Office 365" and "Microsoft
Office 365" I am getting
{
"title":"Office 365",
"score":7.471676
},
{
"title":"Office 365",
"score":7.471676
},
If I try NGram title:(Microsoft Ofice 365)
The scores are same for top 10 results even though they are differing by min of
3 characters. I have attached my schema.xml so it can help
<doc>
<str name="title">Lync - Microsoft Office 365</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 1.0</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 14.0</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 14.3</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 14.4</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 14.5(Mac)</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 15.0</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 16.0</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 4.0</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Office 365 E4</str>
<float name="score">52.056263</float></doc>
<doc>
<str name="title">Microsoft Mail Protection Reports for Office 365
15.0</str>
<float name="score">50.215454</float></doc>
Thanks
Rajesh
Corporate Executive Board India Private Limited. Registration No:
U741040HR2004PTC035324. Registered office: 6th Floor, Tower B, DLF Building
No.10 DLF Cyber City, Gurgaon, Haryana-122002, India.
This e-mail and/or its attachments are intended only for the use of the
addressee(s) and may contain confidential and legally privileged information
belonging to CEB and/or its subsidiaries, including CEB subsidiaries that offer
SHL Talent Measurement products and services. If you have received this e-mail
in error, please notify the sender and immediately, destroy all copies of this
email and its attachments. The publication, copying, in whole or in part, or
use or dissemination in any other way of this e-mail and attachments by anyone
other than the intended person(s) is prohibited.
-----Original Message-----
From: Ahmet Arslan [mailto:iori...@yahoo.com]
Sent: Sunday, March 20, 2016 2:10 AM
To: solr-user@lucene.apache.org; G, Rajesh <r...@cebglobal.com>;
r...@ricksullivan.net
Subject: Re: Explain score is different from score
Hi Rick and Rajesh,
I wasn't able re-produce this neither with lucene nor solr.
What version of solr is this?
Are you using a sharded request?
@BeforeClass
public static void beforeClass() throws Exception { initCore("solrconfig.xml",
"schema.xml");
assertU(adoc("id", "1722669", "title", "Lync - Microsoft Office 365"));
assertU(adoc("id", "2043876", "title", "Microsoft Office 365"));
assertU(commit());
}
/**
* Checks whether fl=score equals to Explain's score */ @Test public void
testExplain() throws Exception { SolrQueryRequest req =
req(CommonParams.DEBUG_QUERY, "true", "indent", "true", "q", "title:(Microsoft
Ofice 365)", CommonParams.FL, "id,title,score"); String response =
h.query(req); System.out.println(response); }
@Test
public void testExplain() throws Exception {
Analyzer analyzer = new WhitespaceAnalyzer();
Directory directory = new RAMDirectory();
IndexWriterConfig config = new IndexWriterConfig(analyzer);
config.setSimilarity(new ClassicSimilarity()); IndexWriter iwriter = new
IndexWriter(directory, config);
Document doc = new Document();
doc.add(new Field("id", "1722669", TextField.TYPE_STORED)); doc.add(new
Field("title", "Lync - Microsoft Office 365", TextField.TYPE_STORED));
iwriter.addDocument(doc);
doc = new Document();
doc.add(new Field("id", "2043876", TextField.TYPE_STORED)); doc.add(new
Field("title", "Microsoft Office 365", TextField.TYPE_STORED));
iwriter.addDocument(doc);
iwriter.close();
// Now search the index:
DirectoryReader reader = DirectoryReader.open(directory); IndexSearcher
searcher = new IndexSearcher(reader); searcher.setSimilarity(new
ClassicSimilarity());
QueryParser parser = new QueryParser("title", analyzer); Query query =
parser.parse("Microsoft Ofice 365"); ScoreDoc[] hits = searcher.search(query,
10).scoreDocs;
Assert.assertEquals(2, hits.length);
// Iterate through the results:
for (int i = 0; i < hits.length; i++) {
Document hitDoc = searcher.doc(hits[i].doc); Explanation explanation =
searcher.explain(query, hits[i].doc);
Assert.assertEquals("score from explain should equal to ScoreDoc.score!",
hits[i].score, explanation.getValue(), 0.0);
}
reader.close();
directory.close();
}
On Saturday, March 19, 2016 7:54 AM, "G, Rajesh" <r...@cebglobal.com> wrote:
I don’t use boost at index time and query time.
Corporate Executive Board India Private Limited. Registration No:
U741040HR2004PTC035324. Registered office: 6th Floor, Tower B, DLF Building
No.10 DLF Cyber City, Gurgaon, Haryana-122002, India.
This e-mail and/or its attachments are intended only for the use of the
addressee(s) and may contain confidential and legally privileged information
belonging to CEB and/or its subsidiaries, including CEB subsidiaries that offer
SHL Talent Measurement products and services. If you have received this e-mail
in error, please notify the sender and immediately, destroy all copies of this
email and its attachments. The publication, copying, in whole or in part, or
use or dissemination in any other way of this e-mail and attachments by anyone
other than the intended person(s) is prohibited.
-----Original Message-----
From: Rick Sullivan [mailto:r...@ricksullivan.net]
Sent: Friday, March 18, 2016 10:18 PM
To: solr-user@lucene.apache.org
Subject: RE: Explain score is different from score
I'm not. I only have query boosts.
----------------------------------------
> Date: Fri, 18 Mar 2016 16:42:36 +0000
> From: iori...@yahoo.com.INVALID
> To: solr-user@lucene.apache.org
> Subject: Re: Explain score is different from score
>
> Hi Rick,
>
> This could be a bug I think. Do you guys use index time boosts?
>
> Ahmet
>
>
>
> On Friday, March 18, 2016 6:15 PM, Rick Sullivan <r...@ricksullivan.net>
> wrote:
> Yes it seems to be something similar, but the normalization isn't applied to
> all retrieved documents, which messes with the document rankings.
>
> Some documents have the exact values from the 'explain' response, while
> others are normalized.
>
> -Rick
>
>
> ----------------------------------------
>> Date: Fri, 18 Mar 2016 16:06:19 +0000
>> From: iori...@yahoo.com.INVALID
>> To: solr-user@lucene.apache.org
>> Subject: Re: Explain score is different from score
>>
>> Hi Rajesh,
>>
>> I suspect it is due to the queryNorm(q). But it is weird that relative order
>> is different in your example.
>>
>>
>> "queryNorm(q) is a normalizing factor used to make scores between
>> queries comparable. This factor does not affect document ranking
>> (since all ranked documents are multiplied by the same factor), but
>> rather just attempts to make scores from different queries (or even
>> different indexes) comparable." [1]
>>
>> [1]
>> https://lucene.apache.org/core/5_5_0/core/org/apache/lucene/search/si
>> milarities/TFIDFSimilarity.html
>>
>> Ahmet
>>
>>
>> On Friday, March 18, 2016 4:24 PM, Rick Sullivan <r...@ricksullivan.net>
>> wrote:
>> Hi Rajesh,
>>
>> I've been seeing the same problem you have. My debug scores seem to be what
>> I expect, but the actual scores applied by Solr are sometimes divided by an
>> integer.
>>
>> I raised the same question in this email distribution about a week ago, but
>> haven't yet found a solution. There's also a StackOverflow question I
>> created here:
>> http://stackoverflow.com/questions/35921106/how-and-why-do-solr-expla
>> in-values-differ-from-the-solr-score
>>
>> Can you verify whether all of your affected scores are (1/N)*score? I
>> think N seems to be the number of OR elements in the query. For
>> example, your case below has
>>
>> debug_score/score
>> = 1.2517526/0.41725087
>> = 3
>>
>> Thanks,
>> -Rick
>>
>>
>> ----------------------------------------
>>> From: r...@cebglobal.com
>>> To: solr-user@lucene.apache.org
>>> Subject: RE: Explain score is different from score
>>> Date: Fri, 18 Mar 2016 13:29:14 +0000
>>>
>>> Can someone help?
>>>
>>>
>>>
>>>
>>> Corporate Executive Board India Private Limited. Registration No:
>>> U741040HR2004PTC035324. Registered office: 6th Floor, Tower B, DLF Building
>>> No.10 DLF Cyber City, Gurgaon, Haryana-122002, India..
>>>
>>>
>>>
>>> This e-mail and/or its attachments are intended only for the use of the
>>> addressee(s) and may contain confidential and legally privileged
>>> information belonging to CEB and/or its subsidiaries, including CEB
>>> subsidiaries that offer SHL Talent Measurement products and services. If
>>> you have received this e-mail in error, please notify the sender and
>>> immediately, destroy all copies of this email and its attachments. The
>>> publication, copying, in whole or in part, or use or dissemination in any
>>> other way of this e-mail and attachments by anyone other than the intended
>>> person(s) is prohibited.
>>>
>>>
>>> From: G, Rajesh
>>> Sent: Friday, March 18, 2016 12:56 PM
>>> To: solr-user@lucene.apache.org
>>> Subject: Explain score is different from score
>>>
>>> Mismatch in score displayed in debug and score field. Please refer attached
>>> xml.
>>>
>>> When I search for title_ws:(Microsoft Ofice 365). If the results are
>>> displayed by explain score order then we would have the expected result
>>> “Microsoft Office 365” then “Lync - Microsoft Office 365”
>>>
>>> <result name="response" numFound="13617" start="0"
>>> maxScore="1.0952835"> <doc> <str name="title">Lync - Microsoft
>>> Office 365</str> <str name="title_ws">Lync - Microsoft Office
>>> 365</str> <int name="id">1722669</int> <float
>>> name="score">1.0952835</float></doc> Score from explain 1.0952835
>>> <doc> <str name="title">Microsoft Office 365</str> <str
>>> name="title_ws">Microsoft Office 365</str> <int
>>> name="id">2043876</int> <float name="score">0.41725087</float></doc>
>>> Score from explain 1.2517526 </result>
>>>
>>> Thanks
>>> Rajesh
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
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 obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="example" version="1.5">
<similarity class="solr.BM25SimilarityFactory">
<float name="k1">1.2</float>
<float name="b">0.75</float>
</similarity>
<uniqueKey>id</uniqueKey>
<defaultSearchField>title</defaultSearchField>
<solrQueryParser defaultOperator="OR"/>
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
</analyzer>
</fieldType>
<fieldType name="binary" class="solr.BinaryField"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
<fieldType name="currency" class="solr.CurrencyField" currencyConfig="currency.xml" defaultCurrency="USD" precisionStep="8"/>
<fieldType name="date" class="solr.TrieDateField" positionIncrementGap="0" precisionStep="0"/>
<fieldType name="dates" class="solr.TrieDateField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="double" class="solr.TrieDoubleField" positionIncrementGap="0" precisionStep="0"/>
<fieldType name="doubles" class="solr.TrieDoubleField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
<fieldType name="float" class="solr.TrieFloatField" positionIncrementGap="0" precisionStep="0"/>
<fieldType name="floats" class="solr.TrieFloatField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
<fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/>
<fieldType name="int" class="solr.TrieIntField" positionIncrementGap="0" precisionStep="0"/>
<fieldType name="ints" class="solr.TrieIntField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
<fieldType name="long" class="solr.TrieLongField" positionIncrementGap="0" precisionStep="0"/>
<fieldType name="longs" class="solr.TrieLongField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true"/>
<fieldType name="tdate" class="solr.TrieDateField" positionIncrementGap="0" precisionStep="6"/>
<fieldType name="tdates" class="solr.TrieDateField" positionIncrementGap="0" multiValued="true" precisionStep="6"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" positionIncrementGap="0" precisionStep="8"/>
<fieldType name="tdoubles" class="solr.TrieDoubleField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ar.txt" ignoreCase="true"/>
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_bg.txt" ignoreCase="true"/>
<filter class="solr.BulgarianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ca.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ca.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
</analyzer>
</fieldType>
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.CJKWidthFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_cz.txt" ignoreCase="true"/>
<filter class="solr.CzechStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
</analyzer>
</fieldType>
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
<filter class="solr.GermanNormalizationFilterFactory"/>
<filter class="solr.GermanLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_el.txt" ignoreCase="false"/>
<filter class="solr.GreekStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
<filter class="solr.SpanishLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_eu.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
</analyzer>
</fieldType>
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<charFilter class="solr.PersianCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.PersianNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_fa.txt" ignoreCase="true"/>
</analyzer>
</fieldType>
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
</analyzer>
</fieldType>
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_fr.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
<filter class="solr.FrenchLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ga.txt" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
<filter class="solr.IrishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ga.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
</analyzer>
</fieldType>
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_gl.txt" ignoreCase="true"/>
<filter class="solr.GalicianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_hi.txt" ignoreCase="true"/>
<filter class="solr.HindiStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
</analyzer>
</fieldType>
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_hy.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
</analyzer>
</fieldType>
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_id.txt" ignoreCase="true"/>
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
</analyzer>
</fieldType>
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
<filter class="solr.ItalianLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/>
<filter class="solr.CJKWidthFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ja.txt" ignoreCase="true"/>
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_lv.txt" ignoreCase="true"/>
<filter class="solr.LatvianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
</analyzer>
</fieldType>
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
</analyzer>
</fieldType>
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
<filter class="solr.PortugueseLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ro.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
</analyzer>
</fieldType>
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
</analyzer>
</fieldType>
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
</analyzer>
</fieldType>
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.ThaiTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_th.txt" ignoreCase="true"/>
</analyzer>
</fieldType>
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_tr.txt" ignoreCase="false"/>
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
</analyzer>
</fieldType>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="tfloat" class="solr.TrieFloatField" positionIncrementGap="0" precisionStep="8"/>
<fieldType name="tfloats" class="solr.TrieFloatField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
<fieldType name="tint" class="solr.TrieIntField" positionIncrementGap="0" precisionStep="8"/>
<fieldType name="tints" class="solr.TrieIntField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
<fieldType name="tlong" class="solr.TrieLongField" positionIncrementGap="0" precisionStep="8"/>
<fieldType name="tlongs" class="solr.TrieLongField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
<fieldType name="txt_token_ng" class="solr.TextField" positionIncrementGap="0" omitNorms="false">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="800"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="800"/>
</analyzer>
</fieldType>
<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="_root_" type="string" indexed="true" stored="false"/>
<field name="_text_" type="string" indexed="true" stored="false"/>
<field name="id" type="int" indexed="true" stored="true" required="true" multiValued="false" />
<field name="title" type="txt_token_ng" indexed="true" stored="true" multiValued="false"/>
<field name="manufacturername" type="txt_token_ng" indexed="true" stored="true" multiValued="false"/>
<field name="productname" type="txt_token_ng" indexed="true" stored="true" multiValued="false"/>
<field name="version" type="txt_token_ng" indexed="true" stored="true" multiValued="false"/>
<!--
<field name="a" type="txt_token_ng" indexed="false" stored="false" multiValued="false" />
<field name="b" type="txt_token_ng" indexed="false" stored="false" multiValued="false" />
<copyField source="a" dest="b"/>
-->
<fieldType name="txt_token_ws" class="solr.TextField" positionIncrementGap="0" omitNorms="false">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<field name="title_ws" type="txt_token_ws" indexed="true" stored="true" multiValued="false"/>
<field name="manufacturername_ws" type="txt_token_ws" indexed="true" stored="true" multiValued="false"/>
<field name="productname_ws" type="txt_token_ws" indexed="true" stored="true" multiValued="false"/>
<field name="version_ws" type="txt_token_ws" indexed="true" stored="true" multiValued="false"/>
<copyField source="title" dest="title_ws"/>
<copyField source="manufacturername" dest="manufacturername_ws"/>
<copyField source="productname" dest="productname_ws"/>
<copyField source="version" dest="version_ws"/>
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
<dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
<dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
<dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
<dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
<dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
<dynamicField name="random_*" type="random"/>
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
<dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
<dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
<dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
<dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
<dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
<dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
<dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
<dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
<dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
<dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
<dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
<dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
<dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
<dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
<dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
<dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
<dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
<dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
<dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
<dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
<dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
<dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
<dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
<dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
<dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
<dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
<dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
<dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
<dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
<dynamicField name="*_point" type="point" indexed="true" stored="true"/>
<dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
<dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
<dynamicField name="attr_*" type="text_general" multiValued="true" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_dts" type="date" multiValued="true" indexed="true" stored="true"/>
<dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
<dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
<dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
<dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
<dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
<dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
<dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
<dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
<dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
<dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
<dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
</schema>
