When I issue a query (e.g., "ABC*") it seems to ignore the asterisk and just searches the document store for everything containing "ABC" rather than starting with "ABC".
I've looked through numerous examples and documentation, but can't seem to determine why Solr searches don't behave the way I think they should.
What am I missing here?
Here is my schema.xml:
<schema name="db" version="1.1">
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.TrimFilterFactory" />
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
id
name
Right now, I'm only searching on the name field. When I changed the type attribute to "text_ws", it behaves closer to the way I expect.
Hopefully this helps some folks out there!
Related
I'm trying to make my site ignore some Arabic characters ex("ه"،"ة") during the search. when user search for word end with "ة" like "مدينة" it brings only word end with that character "ة", it's supposed to bring also the words ends with "ه" like "مدينه".
these characters are the same in the Arabic language so the search result shouldn't be different, but my site produce different results
what I try on my schema_extra_types.xml
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_ar.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ar.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="Arabic" protected="protwords_ar.txt"/>
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="25" />
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_ar.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ar.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_ar.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="Arabic" protected="protwords_ar.txt"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
but the accents_ar.txt empty when I download the config folder from drupal admin interface,and where I can find an example of accents_ar.txt to use on my site? or there is another filter class to handle these kind of issues?
I'm trying search-api and search-api-solr modules and Solr to search with match partial words that are in the middle of a word, and aren't necessarily at the beginning of a word.
I use
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="25" />
but still it doesn't work properly?
Any advice?
my English text field in schema_extra_types.xml
Note: there are other text fields in schema_extra_types.xml but I currently try with the English field.
<!--
English Text Field
7.0.0 --> <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt"
splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="25" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt"
splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer> </fieldType>
I have these values for the title field in my database:
"I Am A String"
"I am A string"
I want to make the title field available as facets in my search results.
Current result:
<lst name="title">
<int name="I Am A String">4</int>
<int name="I am A string">3</int>
</lst>
Desired result:
<lst name="title">
<int name="I Am A String">7</int>
</lst>
I actually don't care which of the 2 available string options is chosen for the final result, as long as the same strings (case insenstive) are counted for the same facet.
I tried the following field definitions for the title field. I also added the resulting facet logic.
string = sees casing as different strings
string_exact = sees casing as different strings
text_ws = breaks up into words with casing intact
text = breaks into separate words
textTight = breaks into separate words
textTrue = breaks up in words with casing intact
string_exacttest = breaks up in words with casing intact
Here's my schema.xml
<field name="title" type="string" indexed="true" stored="true"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true" />
<fieldType name="string_exact" class="solr.TextField"
sortMissingLast="true" omitNorms="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of words on case-change, alpha numeric boundaries, and non-alphanumeric chars, so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled. Duplicate tokens at the same position (which may result from Stemmed Synonyms or WordDelim parts) are removed.-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_dutch.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_dutch.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_dutch.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="Dutch" protected="protwords.txt"/>
<!--
this filter can remove any duplicate tokens that appear at the same position - sometimes possible with WordDelimiterFilter in conjuncton with
stemming.
-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="textTrue" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_dutch.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="Dutch" protected="protwords.txt"/>
</analyzer>
</fieldType>
How can I make sure that the same strings (ignoring case) are grouped together when calculating the facets?
The string_exact definition is almost what you need, but you need to have a LowercaseFilter applied as well, so that each sentence is lowercased. The KeywordTokenizer keeps the whole value as a single token (so you won't see it broken into separate terms based on whitespace), and while a string field doesn't allow any additional processing, a TextField with a KeywordTokenizer behaves the same way - but you can add filters to how the token is processed afterwards.
<fieldType name="string_facet" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
I've got an issue where my index and query are exactly the same, however no results are returned. It seems to fail on any words that are longer than the ENGTF max length. Here's my schema.
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1" stemEnglishPossessive="0" preserveOriginal="1" types="wdfftypes.txt" protected="protwords.txt"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.ASCIIFoldingFilterFactory" words="mapping-FoldToASCII.txt"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="10" side="front"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.ASCIIFoldingFilterFactory" words="mapping-FoldToASCII.txt"/>
</analyzer>
</fieldType>
Here is a screenshot of the analyzer when "Satisfaction" is put into the index, and "Satisfaction" is put into the query.
Any ideas? Thanks
Once obvious option is to increase the nGram length limit. You seem to be aware of this option and probably agree that is is not ideal.
Another option is to create a second field to use the nGram search, and another to use a search without nGram. For exmaple, somewhere in your schema.xml you might see:
<field name="myCoolNGramField" type="text_en_splitting" indexed="true" stored="false"/>
<!-- make a new type, text_en_non_ngram, and use it for this new field below. -->
<field name="myCoolField" type="text_en_non_ngram" indexed="true" stored="false"/>
<copyField source="myCoolNGramField" dest="myCoolField" />
I use SnowballPorterFilterFactory for index and query analyzers.
When i search for "profession" word. Solr successfully finds only articles that contains "profession", but i want "professional" "professionalism" ...
This is the current configuration on schema.xml
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.SnowballPorterFilterFactory" language="French"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.SnowballPorterFilterFactory" language="French"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</analyzer>
</fieldType>
What is happening is porter is over-stemming your query. When you search for profession your keyword gets stemmed down to profess, whereas profession professional and professionalism are all stored in the index as profession.
The only real way you are going to get around this is by adding another fieldType where you do not stem your query.
Something like:
<fieldType name="text_unstemmed_query" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.SnowballPorterFilterFactory" language="French"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</analyzer>
</fieldType>
With a copyfield like:
<copyField source="your_text_field" dest="text_unstem_query_field"/>