Hi Jack,
I copied schema.xml from solr-5.5.0\example\example-DIH\solr\db\conf\
to \solr-5.5.0\server\solr\myDatabase\conf\
I've attached the file too.
@Shawn
The file does not have any field which defined as <field name="somefield"
type="booleans" indexed="true" stored="true"/>
On Fri, Apr 1, 2016 at 9:13 AM, Jack Krupansky <jack.krupan...@gmail.com>
wrote:
> Exactly which file did you copy? Please give the specific directory.
>
> -- Jack Krupansky
>
> On Thu, Mar 31, 2016 at 3:24 PM, Girish Tavag <send2mymail...@gmail.com>
> wrote:
>
> > Hi Binoy,
> >
> > I copied the entire file schema.xml from the working example provided by
> > solr itself. Solr provided dih example i'm able to run successfully .How
> > could this be a problem?
> >
> > On Fri, Apr 1, 2016 at 12:39 AM, Binoy Dalal <binoydala...@gmail.com>
> > wrote:
> >
> > > Somewhere in your schema you've defined a field with type as
> "booleans".
> > > You should check if you've made a typo somewhere by adding that extra s
> > > after boolean.
> > > Else if it is a separate field that you're looking to add, define a new
> > > fieldtype called booleans.
> > >
> > > All the info to help you with this can be found here:
> > >
> > >
> >
> https://cwiki.apache.org/confluence/display/solr/Documents,+Fields,+and+Schema+Design
> > >
> > > I higly recommend that you go through the documentation before
> starting.
> > >
> > > On Fri, 1 Apr 2016, 00:34 Girish Tavag, <send2mymail...@gmail.com>
> > wrote:
> > >
> > > > Hi,
> > > >
> > > > I am new to solr, I started using this only from today, when I
> wanted
> > to
> > > > create dih, i'm getting the below error.
> > > >
> > > > SolrException: fieldType 'booleans' not found in the schema
> > > >
> > > > What does this mean? and How to resolve this.
> > > >
> > > > Regards,
> > > > GNT
> > > >
> > > --
> > > Regards,
> > > Binoy Dalal
> > >
> >
>
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="example" version="1.5">
<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="name" type="text_general" indexed="true" stored="true"/>
<!-- Dynamic field definitions allow using convention over configuration
for fields via the specification of patterns to match field names.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end. -->
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
<dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
<!-- Type used to index the lat and lon components for the "location" FieldType -->
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
<!-- some trie-coded dynamic fields for faster range queries -->
<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="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="random_*" type="random" />
<!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
unknown fields indexed and/or stored by default -->
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
parsing a query string that isn't explicit about the field. Machine (non-user)
generated queries are best made explicit, or they can use the "df" request parameter
which takes precedence over this.
Note: Un-commenting defaultSearchField will be insufficient if your request handler
in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
<defaultSearchField>text</defaultSearchField> -->
<!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
when parsing a query string to determine if a clause of the query should be marked as
required or optional, assuming the clause isn't already marked by some operator.
The default is OR, which is generally assumed so it is not a good idea to change it
globally here. The "q.op" request parameter takes precedence over this.
<solrQueryParser defaultOperator="OR"/> -->
<!-- copyField commands copy one field to another at the time a document
is added to the index. It's used either to index the same field differently,
or to add multiple fields to the same field for easier/faster searching. -->
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in a
standard package such as org.apache.solr.analysis
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
It supports doc values but in that case the field needs to be
single-valued and either required or have a default value.
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
These fields support doc values, but they require the field to be
single-valued and either be required or have a default value.
-->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
endpoints is large. See the javadoc for NumericRangeQuery for internal
implementation details.
Smaller precisionStep values (specified in bits) will lead to more tokens
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text type for English text where stopwords and synonyms are managed using the REST API -->
<fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ManagedStopFilterFactory" managed="english" />
<filter class="solr.ManagedSynonymFilterFactory" managed="english" />
</analyzer>
</fieldType>
<!-- A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "stopwords.txt"
(empty by default), and down cases. At query time only, it
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<!-- 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.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English: it
tokenizes with StandardTokenizer, removes English stop words
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus
aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds
WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and
non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match
document "WiFi" or "wi-fi".
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.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"/>
</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="lang/stopwords_en.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"/>
</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="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.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"/>
<!-- 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>
<!-- Just like text_general except it reverses the characters of
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
-->
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!--
Example of using PathHierarchyTokenizerFactory at index time, so
queries for paths match documents at that path, or in descendent paths
-->
<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>
<!--
Example of using PathHierarchyTokenizerFactory at query time, so
queries for paths match documents at that path, or in ancestor paths
-->
<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>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. Alternately, if
subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
For more information about this and other Spatial fields new to Solr 4, see:
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
-->
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
<!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
special relevancy modes: score=overlapRatio|area|area2D (local-param to the query). DocValues is required for
relevancy. -->
<fieldType name="bbox" class="solr.BBoxField"
geo="true" units="degrees" numberType="_bbox_coord" />
<fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
providerClass: Lets you plug in other exchange provider backend:
solr.FileExchangeRateProvider is the default and takes one parameter:
currencyConfig: name of an xml file holding exchange rates
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
-->
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
<!-- some examples for different languages (generally ordered by ISO code) -->
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ? to ?, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Bulgarian -->
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter class="solr.BulgarianStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
</analyzer>
</fieldType>
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
</analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Czech -->
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter class="solr.CzechStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Danish -->
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
</analyzer>
</fieldType>
<!-- German -->
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter class="solr.GermanNormalizationFilterFactory"/>
<filter class="solr.GermanLightStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Spanish -->
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter class="solr.SpanishLightStemFilterFactory"/>
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
</analyzer>
</fieldType>
<!-- Basque -->
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
</analyzer>
</fieldType>
<!-- Persian -->
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<!-- for ZWNJ -->
<charFilter class="solr.PersianCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.PersianNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
</analyzer>
</fieldType>
<!-- Finnish -->
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
<!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter class="solr.FrenchLightStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
</analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<!-- removes n-, etc. position increments is intentionally false! -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter class="solr.IrishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
</analyzer>
</fieldType>
<!-- Galician -->
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter class="solr.GalicianStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Hungarian -->
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
<!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Armenian -->
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
</analyzer>
</fieldType>
<!-- Indonesian -->
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
<!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter class="solr.ItalianLightStemFilterFactory"/>
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
</analyzer>
</fieldType>
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
NOTE: If you want to optimize search for precision, use default operator AND in your query
parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
OR if you would like to optimize for recall (default).
-->
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
<analyzer>
<!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
is used to segment compounds into its parts and the compound itself is kept as synonym.
Valid values for attribute mode are:
normal: regular segmentation
search: segmentation useful for search with synonyms compounds (default)
extended: same as search mode, but unigrams unknown words (experimental)
For some applications it might be good to use search mode for indexing and normal mode for
queries to reduce recall and prevent parts of compounds from being matched and highlighted.
Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
model with your own entries for segmentation, part-of-speech tags and readings without a need
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
User dictionary attributes are:
userDictionary: user dictionary filename
userDictionaryEncoding: user dictionary encoding (default is UTF-8)
See lang/userdict_ja.txt for a sample user dictionary file.
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (???) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
<filter class="solr.CJKWidthFilterFactory"/>
<!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
<!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- Latvian -->
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter class="solr.LatvianStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Dutch -->
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
</analyzer>
</fieldType>
<!-- Norwegian -->
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
<!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</fieldType>
<!-- Portuguese -->
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter class="solr.PortugueseLightStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
<!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Romanian -->
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
</analyzer>
</fieldType>
<!-- Russian -->
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
<!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Swedish -->
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
<!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Thai -->
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.ThaiTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
</analyzer>
</fieldType>
<!-- Similarity is the scoring routine for each document vs. a query.
A custom Similarity or SimilarityFactory may be specified here, but
the default is fine for most applications.
For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
-->
<!--
<similarity class="com.example.solr.CustomSimilarityFactory">
<str name="paramkey">param value</str>
</similarity>
-->
</schema>
