A couple of possibilities:
1. Make sure to reload the core.
2. Check that the Solr schema version is new enough to recognize
autoGeneratePhraseQueries.
3. What query parser are you using?
-- Jack Krupansky
-----Original Message-----
From: James Bathgate
Sent: Thursday, July 11, 2013 5:26 PM
To: solr-user@lucene.apache.org
Subject: Re: Partial Matching in both query and field
I just noticed I pasted the wrong fieldType with the extra tokenizer not
commented out.
<fieldType name="ngram" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="false">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="1" splitOnCaseChange="0"
splitOnNumerics="0" preserveOriginal="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<filter class="solr.NGramFilterFactory" minGramSize="4"
maxGramSize="16"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.NGramTokenizerFactory" minGramSize="4"
maxGramSize="16" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.PatternReplaceFilterFactory"
pattern="[^A-Za-z0-9]+" replacement="" replace="all"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
[image: SearchSpring | Findability Unleashed]
James Bathgate | Sr. Developer
Toll Free (888) 643-9043 x610 - Fax (719) 358-2027
4291 Austin Bluffs Pkwy #206 | Colorado Springs, CO 80918
www.searchspring.net <http://www.searchspring.net>
On Thu, Jul 11, 2013 at 2:15 PM, James Bathgate
<ja...@b7interactive.com>wrote:
Jack,
This still isn't working. I just upgraded to 3.6.2 to verify that wasn't
the issue.
Here's query information:
<lst name="params">
<str name="debugQuery">on</str>
<str name="indent">on</str>
<str name="start">0</str>
<str name="q">0_extrafield1_n:20454</str>
<str name="rows">10</str>
<str name="version">2.2</str>
</lst>
</lst>
<result name="response" numFound="0" start="0"/>
<lst name="debug">
<str name="rawquerystring">0_extrafield1_n:20454</str>
<str name="querystring">0_extrafield1_n:20454</str>
<str name="parsedquery">PhraseQuery(0_extrafield1_n:"2o45 o454
2o454")</str>
<str name="parsedquery_toString">0_extrafield1_n:"2o45 o454 2o454"</str>
<lst name="explain"/>
<str name="QParser">LuceneQParser</str>
Here's the applicable lines from schema.xml:
<fieldType name="ngram" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="false">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="1" splitOnCaseChange="0"
splitOnNumerics="0" preserveOriginal="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<filter class="solr.NGramFilterFactory" minGramSize="4"
maxGramSize="16"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.NGramTokenizerFactory" minGramSize="4"
maxGramSize="16" />
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.PatternReplaceFilterFactory"
pattern="[^A-Za-z0-9]+" replacement="" replace="all"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<!--<filter class="solr.NGramFilterFactory" minGramSize="4"
maxGramSize="4" />-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<dynamicField name="*_n" type="ngram" indexed="true" stored="true" />
It looks like it's generating phrases to me even though I have it set to
false.
James
[image: SearchSpring | Findability Unleashed]
James Bathgate | Sr. Developer
Toll Free (888) 643-9043 x610 - Fax (719) 358-2027
4291 Austin Bluffs Pkwy #206 | Colorado Springs, CO 80918
www.searchspring.net <http://www.searchspring.net>
On Tue, Jul 2, 2013 at 2:47 PM, Jack Krupansky
<j...@basetechnology.com>wrote:
Ahhh... you put autoGeneratePhraseQueries="**false" on the field - but
it needs to be on the field type.
You can see from the parsed query that it generated the phrase.
-- Jack Krupansky
-----Original Message----- From: James Bathgate
Sent: Tuesday, July 02, 2013 5:35 PM
To: solr-user@lucene.apache.org
Subject: Re: Partial Matching in both query and field
Jack,
I've already tried that, here's my query:
<str name="debugQuery">on</str>
<str name="indent">on</str>
<str name="start">0</str>
<str name="q">0_extrafield1_n:**20454</str>
<str name="q.op">OR</str>
<str name="rows">10</str>
<str name="version">2.2</str>
Here's the parsed query:
<str name="parsedquery_toString">0_**extrafield1_n:"2o45 o454
2o454"</str>
Here's the applicable lines from schema.xml:
<fieldType name="ngram" class="solr.TextField"
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.**WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="**true"/>
<filter class="solr.**SynonymFilterFactory"
synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
<filter class="solr.**WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="1" splitOnCaseChange="0"
splitOnNumerics="0" preserveOriginal="0"/>
<filter class="solr.**LowerCaseFilterFactory"/>
<filter class="solr.**PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.**PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<filter class="solr.**NGramFilterFactory" minGramSize="4"
maxGramSize="16"/>
<filter class="solr.**RemoveDuplicatesTokenFilterFac**tory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.**NGramTokenizerFactory" minGramSize="4"
maxGramSize="16" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="**true"/>
<filter class="solr.**PatternReplaceFilterFactory"
pattern="[^A-Za-z0-9]+" replacement="" replace="all"/>
<filter class="solr.**LowerCaseFilterFactory"/>
<filter class="solr.**PatternReplaceFilterFactory" pattern="0"
replacement="o" replace="all"/>
<filter class="solr.**PatternReplaceFilterFactory" pattern="1|l"
replacement="i" replace="all"/>
<filter class="solr.**RemoveDuplicatesTokenFilterFac**tory"/>
</analyzer>
</fieldType>
<dynamicField name="*_n" type="ngram" indexed="true" stored="true"
autoGeneratePhraseQueries="**false" />
James
[image: SearchSpring | Findability Unleashed]
James Bathgate | Sr. Developer
Toll Free (888) 643-9043 x610 - Fax (719) 358-2027
4291 Austin Bluffs Pkwy #206 | Colorado Springs, CO 80918
www.searchspring.net <http://www.searchspring.net>
On Tue, Jul 2, 2013 at 2:22 PM, Jack Krupansky <j...@basetechnology.com>*
*wrote:
You will need to set q.op to "OR", and... use a field type that has the
autoGeneratePhraseQueries attribute set to "false".
-- Jack Krupansky
-----Original Message----- From: James Bathgate
Sent: Tuesday, July 02, 2013 5:10 PM
To: solr-user@lucene.apache.org
Subject: Partial Matching in both query and field
Given a string of "123456" and a search query "923459", what should the
schema look like to consider this a match because at least 4 consecutive
in
characters the query match 4 consecutive characters in the data? I'm
trying
an NGramFilterFactory on the index and NGramTokenizerFactory on the
query
in the schema, but that's not working.
I believe the problem is 'field:923459' is parsed as 'field:"9234 2345
3459"' instead of 'field:9234 field:2345 field:3459'.
[image: SearchSpring | Findability Unleashed]
James Bathgate | Sr. Developer
Toll Free (888) 643-9043 x610 - Fax (719) 358-2027
4291 Austin Bluffs Pkwy #206 | Colorado Springs, CO 80918
www.searchspring.net <http://www.searchspring.net>
