<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-->
- <!-- 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="*_pi" type="pint" 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
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
- <!--
- Note:
- These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
- Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
-
- Plain numeric field types that store and index the text
- value verbatim (and hence don't correctly support range queries, since the
- lexicographic ordering isn't equal to the numeric ordering)
- -->
- <fieldType name="pint" class="solr.IntField"/>
- <fieldType name="plong" class="solr.LongField"/>
- <fieldType name="pfloat" class="solr.FloatField"/>
- <fieldType name="pdouble" class="solr.DoubleField"/>
- <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
-
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate pseudo-random orderings of your docs for sorting
</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" enablePositionIncrements="true" />
- <!-- 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" enablePositionIncrements="true" />
- <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.
- add enablePositionIncrements=true in both the index and query
- analyzers to leave a 'gap' for more accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <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"
- enablePositionIncrements="true"
- />
- <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.
- add enablePositionIncrements=true in both the index and query
- analyzers to leave a 'gap' for more accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <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"
- enablePositionIncrements="true"
- />
- <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" enablePositionIncrements="true" />
- <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" enablePositionIncrements="true" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
</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://java.sun.com/j2se/1.6.0/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>
</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"/>
-
- <!--
- A Geohash is a compact representation of a latitude longitude pair in a single field.
- See http://wiki.apache.org/solr/SpatialSearch
- -->
- <fieldtype name="geohash" class="solr.GeoHashField"/>
-
- <!-- 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 exhange 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" /> - nie dziala -->
-
-
-
- <!-- 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" enablePositionIncrements="true"/>
- <!-- normalizes ﻯ to ﻱ, 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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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>
-
- <!-- 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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- </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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="false"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <!-- 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" enablePositionIncrements="true"/>
- <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 (辞書形) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Removes tokens with certain part-of-speech tags -->
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
- <!-- 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" enablePositionIncrements="true" />
- <!-- 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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
<!-- Polish -->
<fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/>
+ <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
</analyzer>
</fieldType>
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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" enablePositionIncrements="true"/>
- <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.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ThaiWordFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
</analyzer>
</fieldType>
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
- <luceneMatchVersion>LUCENE_40</luceneMatchVersion>
+ <luceneMatchVersion>6.0.1</luceneMatchVersion>
- <!-- lib directives can be used to instruct Solr to load an Jars
+ <!-- <lib/> directives can be used to instruct Solr to load any Jars
identified and use them to resolve any "plugins" specified in
your solrconfig.xml or schema.xml (ie: Analyzers, Request
Handlers, etc...).
If a "./lib" directory exists in your instanceDir, all files
found in it are included as if you had used the following
syntax...
-
+
<lib dir="./lib" />
-->
- <!-- A 'dir' option by itself adds any files found in the directory
+ <!-- A 'dir' option by itself adds any files found in the directory
to the classpath, this is useful for including all jars in a
directory.
-->
<!-- When a 'regex' is specified in addition to a 'dir', only the
files in that directory which completely match the regex
(anchored on both ends) will be included.
- -->
- <lib dir="../../../dist/" regex="apache-solr-cell-\d.*\.jar" />
- <lib dir="../../../contrib/extraction/lib" regex=".*\.jar" />
-
- <lib dir="../../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
- <lib dir="../../../contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="../../../dist/" regex="apache-solr-langid-\d.*\.jar" />
- <lib dir="../../../contrib/langid/lib/" regex=".*\.jar" />
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
- <lib dir="../../../dist/" regex="apache-solr-velocity-\d.*\.jar" />
- <lib dir="../../../contrib/velocity/lib" regex=".*\.jar" />
-
- <!-- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, it will be ignored
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
-->
- <lib dir="/total/crap/dir/ignored" />
-
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific file. This will cause a serious error to be logged if
- it can't be loaded.
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
+ <!-- browse-resources must come before solr-velocity JAR in order to override localized resources -->
+ <lib path="${solr.install.dir:../../../..}/example/files/browse-resources"/>
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
-->
<!--
- <lib path="../a-jar-that-does-not-exist.jar" />
+ <lib path="../a-jar-that-does-not-exist.jar" />
-->
-
+
<!-- Data Directory
Used to specify an alternate directory to hold all index data
-->
<dataDir>${solr.data.dir:}</dataDir>
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
<!-- The DirectoryFactory to use for indexes.
-
+
solr.StandardDirectoryFactory is filesystem
based and tries to pick the best implementation for the current
JVM and platform. solr.NRTCachingDirectoryFactory, the default,
solr.RAMDirectoryFactory is memory based, not
persistent, and doesn't work with replication.
-->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Index Config - These settings control low-level behavior of indexing
Most example settings here show the default value, but are commented
out, to more easily see where customizations have been made.
-
+
Note: This replaces <indexDefaults> and <mainIndex> from older versions
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
<filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
-->
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
<!-- <writeLockTimeout>1000</writeLockTimeout> -->
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
<!-- <useCompoundFile>false</useCompoundFile> -->
<!-- <ramBufferSizeMB>32</ramBufferSizeMB> -->
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
- <!-- Expert: Merge Policy
+ <!-- Expert: Merge Policy
The Merge Policy in Lucene controls how merging of segments is done.
The default since Solr/Lucene 3.3 is TieredMergePolicy.
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
<int name="segmentsPerTier">10</int>
</mergePolicy>
-->
-
+
<!-- Merge Factor
The merge factor controls how many segments will get merged at a time.
For TieredMergePolicy, mergeFactor is a convenience parameter which
will be allowed before they are merged into one.
Default is 10 for both merge policies.
-->
- <!--
+ <!--
<mergeFactor>10</mergeFactor>
-->
can perform merges in the background using separate threads.
The SerialMergeScheduler (Lucene 2.2 default) does not.
-->
- <!--
+ <!--
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
-->
- <!-- LockFactory
+ <!-- LockFactory
This option specifies which Lucene LockFactory implementation
to use.
-
+
single = SingleInstanceLockFactory - suggested for a
read-only index or when there is no possibility of
another process trying to modify the index.
<!--
<unlockOnStartup>false</unlockOnStartup>
-->
-
+
<!-- Expert: Controls how often Lucene loads terms into memory
Default is 128 and is likely good for most everyone.
-->
<!-- If true, IndexReaders will be reopened (often more efficient)
instead of closed and then opened. Default: true
-->
- <!--
+ <!--
<reopenReaders>true</reopenReaders>
-->
The default Solr IndexDeletionPolicy implementation supports
deleting index commit points on number of commits, age of
commit point and optimized status.
-
+
The latest commit point should always be preserved regardless
of the criteria.
-->
- <!--
+ <!--
<deletionPolicy class="solr.SolrDeletionPolicy">
-->
<!-- The number of commit points to be kept -->
<str name="maxCommitAge">30MINUTES</str>
<str name="maxCommitAge">1DAY</str>
-->
- <!--
+ <!--
</deletionPolicy>
-->
<!-- Lucene Infostream
-
+
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
Setting The value to true will instruct the underlying Lucene
IndexWriter to write its debugging info the specified file
-->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
</indexConfig>
<!-- JMX
-
+
This example enables JMX if and only if an existing MBeanServer
is found, use this if you want to configure JMX through JVM
parameters. Remove this to disable exposing Solr configuration
-->
<jmx />
<!-- If you want to connect to a particular server, specify the
- agentId
+ agentId
-->
<!-- <jmx agentId="myAgent" /> -->
<!-- If you want to start a new MBeanServer, specify the serviceUrl -->
<!-- The default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory. -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ </updateLog>
+
<!-- AutoCommit
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
+ when adding documents.
http://wiki.apache.org/solr/UpdateXmlMessages
maxTime - Maximum amount of time in ms that is allowed to pass
since a document was added before automaticly
- triggering a new commit.
+ triggering a new commit.
openSearcher - if false, the commit causes recent index changes
to be flushed to stable storage, but does not cause a new
searcher to be opened to make those changes visible.
-->
- <autoCommit>
- <maxTime>15000</maxTime>
- <openSearcher>false</openSearcher>
+ <autoCommit>
+ <maxTime>15000</maxTime>
+ <openSearcher>false</openSearcher>
</autoCommit>
<!-- softAutoCommit is like autoCommit except it causes a
faster and more near-realtime friendly than a hard commit.
-->
<!--
- <autoSoftCommit>
- <maxTime>1000</maxTime>
+ <autoSoftCommit>
+ <maxTime>1000</maxTime>
</autoSoftCommit>
-->
<!-- Update Related Event Listeners
-
+
Various IndexWriter related events can trigger Listeners to
take actions.
-->
<!-- The RunExecutableListener executes an external command from a
hook such as postCommit or postOptimize.
-
+
exe - the name of the executable to run
dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
+ wait - the calling thread waits until the executable returns.
(default="true")
args - the arguments to pass to the program. (default is none)
env - environment variables to set. (default is none)
</listener>
-->
- <!-- Enables a transaction log, currently used for real-time get.
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory. -->
- <updateLog>
- <str name="dir">${solr.data.dir:}</str>
- </updateLog>
-
-
</updateHandler>
-
+
<!-- IndexReaderFactory
Use the following format to specify a custom IndexReaderFactory,
be specified.
-->
<!--
- <indexReaderFactory name="IndexReaderFactory"
+ <indexReaderFactory name="IndexReaderFactory"
class="solr.StandardIndexReaderFactory">
<int name="setTermIndexDivisor">12</int>
</indexReaderFactory >
is thrown if exceeded.
** WARNING **
-
+
This option actually modifies a global Lucene property that
will affect all SolrCores. If multiple solrconfig.xml files
disagree on this property, the value at any given moment will
be based on the last SolrCore to be initialized.
-
+
-->
<maxBooleanClauses>1024</maxBooleanClauses>
There are two implementations of cache available for Solr,
LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
+ FastLRUCache, based on a ConcurrentHashMap.
FastLRUCache has faster gets and slower puts in single
threaded operation and thus is generally faster than LRUCache
initialSize - the initial capacity (number of entries) of
the cache. (see java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
- and old cache.
+ and old cache.
-->
<filterCache class="solr.FastLRUCache"
size="512"
autowarmCount="0"/>
<!-- Query Result Cache
-
+
Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
+ (DocList) based on a query, a sort, and the range of documents requested.
-->
<queryResultCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
-
+
<!-- Document Cache
Caches Lucene Document objects (the stored fields for each
document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
+ this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
-
+
<!-- Field Value Cache
-
+
Cache used to hold field values that are quickly accessible
by document id. The fieldValueCache is created by default
even if not configured here.
name through SolrIndexSearcher.getCache(),cacheLookup(), and
cacheInsert(). The purpose is to enable easy caching of
user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
-->
<!--
<cache name="myUserCache"
are collected. For example, if a search for a particular query
requests matching documents 10 through 19, and queryWindowSize is 50,
then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
+ requests in that range can be satisfied via the cache.
-->
<queryResultWindowSize>20</queryResultWindowSize>
<!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
+ queryResultCache.
-->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from.
-
+
-->
<!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
+ local query request for each NamedList in sequence.
-->
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<useColdSearcher>false</useColdSearcher>
<!-- Max Warming Searchers
-
+
Maximum number of searchers that may be warming in the
background concurrently. An error is returned if this limit
is exceeded.
multipartUploadLimitInKB - specifies the max size of
Multipart File Uploads that Solr will allow in a Request.
-
+
*** WARNING ***
The settings below authorize Solr to fetch remote files, You
should make sure your system has some authentication before
using enableRemoteStreaming="true"
- -->
- <requestParsers enableRemoteStreaming="true"
+ -->
+ <requestParsers enableRemoteStreaming="true"
multipartUploadLimitInKB="2048000" />
<!-- HTTP Caching
<!-- If you include a <cacheControl> directive, it will be used to
generate a Cache-Control header (as well as an Expires header
if the value contains "max-age=")
-
+
By default, no Cache-Control header is generated.
-
+
You can use the <cacheControl> option even if you have set
never304="true"
-->
<!--
<httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
+ <cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
<!-- To enable Solr to respond with automatically generated HTTP
Caching headers, and to response to Cache Validation requests
correctly, set the value of never304="false"
-
+
This will cause Solr to generate Last-Modified and ETag
headers based on the properties of the Index.
<!--
<httpCaching lastModifiedFrom="openTime"
etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
+ <cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
</requestDispatcher>
- <!-- Request Handlers
+ <!-- Request Handlers
http://wiki.apache.org/solr/SolrRequestHandler
like so: http://host/app/[core/]select?qt=name If no qt is
given, then the requestHandler that declares default="true" will be
used or the one named "standard".
-
+
If a Request Handler is declared with startup="lazy", then it will
not be initialized until the first request that uses it.
<str>nameOfCustomComponent2</str>
</arr>
-->
- </requestHandler>
+ </requestHandler>
<!-- A request handler that returns indented JSON by default -->
<requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- <str name="df">text</str>
- </lst>
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ <str name="df">text</str>
+ </lst>
</requestHandler>
</lst>
</requestHandler>
-
- <!-- A Robust Example
-
+
+ <!-- A Robust Example
+
This example SearchHandler declaration shows off usage of the
SearchHandler with many defaults declared
<!-- Spell checking defaults -->
<str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">false</str>
+ <str name="spellcheck.extendedResults">false</str>
<str name="spellcheck.count">5</str>
<str name="spellcheck.alternativeTermCount">2</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">5</str>
- <str name="spellcheck.maxCollations">3</str>
+ <str name="spellcheck.maxCollations">3</str>
</lst>
<!-- append spellchecking to our list of components -->
</requestHandler>
- <!-- Update Request Handler.
-
+ <!-- Update Request Handler.
+
http://wiki.apache.org/solr/UpdateXmlMessages
The canonical Request Handler for Modifying the Index through
Note: Since solr1.1 requestHandlers requires a valid content
type header if posted in the body. For example, curl now
requires: -H 'Content-type:text/xml; charset=utf-8'
-
- To override the request content type and force a specific
- Content-type, use the request parameter:
+
+ To override the request content type and force a specific
+ Content-type, use the request parameter:
?update.contentType=text/csv
-
+
This handler will pick a response format to match the input
if the 'wt' parameter is not explicit
-->
<requestHandler name="/update" class="solr.UpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
+ <!-- See below for information on defining
+ updateRequestProcessorChains that can be used by name
on each Update Request
-->
<!--
</lst>
-->
</requestHandler>
-
+
<!-- Solr Cell Update Request Handler
- http://wiki.apache.org/solr/ExtractingRequestHandler
+ http://wiki.apache.org/solr/ExtractingRequestHandler
-->
- <requestHandler name="/update/extract"
+ <requestHandler name="/update/extract"
startup="lazy"
class="solr.extraction.ExtractingRequestHandler" >
<lst name="defaults">
field value analysis will be marked as "matched" for every
token that is produces by the query analysis
-->
- <requestHandler name="/analysis/field"
+ <requestHandler name="/analysis/field"
startup="lazy"
class="solr.FieldAnalysisRequestHandler" />
request parameter that holds the query text to be analyzed. It
also supports the "analysis.showmatch" parameter which when set to
true, all field tokens that match the query tokens will be marked
- as a "match".
+ as a "match".
-->
- <requestHandler name="/analysis/document"
- class="solr.DocumentAnalysisRequestHandler"
+ <requestHandler name="/analysis/document"
+ class="solr.DocumentAnalysisRequestHandler"
startup="lazy" />
- <!-- Admin Handlers
-
- Admin Handlers - This will register all the standard admin
- RequestHandlers.
- -->
- <requestHandler name="/admin/"
- class="solr.admin.AdminHandlers" />
- <!-- This single handler is equivalent to the following... -->
- <!--
- <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
- <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
- <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
- <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
- <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
- <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
- -->
- <!-- If you wish to hide files under ${solr.home}/conf, explicitly
- register the ShowFileRequestHandler using:
- -->
- <!--
- <requestHandler name="/admin/file"
- class="solr.admin.ShowFileRequestHandler" >
- <lst name="invariants">
- <str name="hidden">synonyms.txt</str>
- <str name="hidden">anotherfile.txt</str>
- </lst>
- </requestHandler>
- -->
-
- <!-- ping/healthcheck -->
- <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
- <lst name="invariants">
- <str name="q">solrpingquery</str>
- </lst>
- <lst name="defaults">
- <str name="echoParams">all</str>
- </lst>
- <!-- An optional feature of the PingRequestHandler is to configure the
- handler with a "healthcheckFile" which can be used to enable/disable
- the PingRequestHandler.
- relative paths are resolved against the data dir
- -->
- <!-- <str name="healthcheckFile">server-enabled.txt</str> -->
- </requestHandler>
-
<!-- Echo the request contents back to the client -->
<requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
<lst name="defaults">
- <str name="echoParams">explicit</str>
+ <str name="echoParams">explicit</str>
<str name="echoHandler">true</str>
</lst>
</requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "slaves" used for queries.
-
- http://wiki.apache.org/solr/SolrReplication
-
- In the example below, remove the <lst name="master"> section if
- this is just a slave and remove the <lst name="slave"> section
- if this is just a master.
- -->
- <!--
- <requestHandler name="/replication" class="solr.ReplicationHandler" >
- <lst name="master">
- <str name="replicateAfter">commit</str>
- <str name="replicateAfter">startup</str>
- <str name="confFiles">schema.xml,stopwords.txt</str>
- </lst>
- <lst name="slave">
- <str name="masterUrl">http://localhost:8983/solr</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- </requestHandler>
- -->
-
- <!-- Solr Replication for SolrCloud Recovery
-
- This is the config need for SolrCloud's recovery replication.
- -->
- <requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
-
<!-- Search Components
- Search components are registered to SolrCore and used by
+ Search components are registered to SolrCore and used by
instances of SearchHandler (which can access them by name)
-
+
By default, the following components are available:
-
+
<searchComponent name="query" class="solr.QueryComponent" />
<searchComponent name="facet" class="solr.FacetComponent" />
<searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
<searchComponent name="highlight" class="solr.HighlightComponent" />
<searchComponent name="stats" class="solr.StatsComponent" />
<searchComponent name="debug" class="solr.DebugComponent" />
-
+
Default configuration in a requestHandler would look like:
<arr name="components">
<str>debug</str>
</arr>
- If you register a searchComponent to one of the standard names,
+ If you register a searchComponent to one of the standard names,
that will be used instead of the default.
To insert components before or after the 'standard' components, use:
-
+
<arr name="first-components">
<str>myFirstComponentName</str>
</arr>
-
+
<arr name="last-components">
<str>myLastComponentName</str>
</arr>
NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
+ always be executed after the "last-components"
+
-->
-
+
<!-- Spell Check
The spell check component can return a list of alternative spelling
- suggestions.
+ suggestions.
http://wiki.apache.org/solr/SpellCheckComponent
-->
<float name="thresholdTokenFrequency">.01</float>
-->
</lst>
-
+
<!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
<lst name="spellchecker">
<str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
<str name="field">name</str>
<str name="combineWords">true</str>
<str name="breakWords">true</str>
</lst>
-->
- <!-- a spellchecker that use an alternate comparator
+ <!-- a spellchecker that use an alternate comparator
comparatorClass be one of:
1. score (default)
-->
</searchComponent>
- <!-- A request handler for demonstrating the spellcheck component.
+ <!-- A request handler for demonstrating the spellcheck component.
NOTE: This is purely as an example. The whole purpose of the
SpellCheckComponent is to hook it into the request handler that
IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
+
See http://wiki.apache.org/solr/SpellCheckComponent for details
on the request parameters.
-->
<str name="spellcheck.dictionary">default</str>
<str name="spellcheck.dictionary">wordbreak</str>
<str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.extendedResults">true</str>
<str name="spellcheck.count">10</str>
<str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
+ <str name="spellcheck.maxCollations">5</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
This is purely as an example.
- In reality you will likely want to add the component to your
- already specified request handlers.
+ In reality you will likely want to add the component to your
+ already specified request handlers.
-->
<requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
</arr>
</requestHandler>
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- You'll need to set the solr.cluster.enabled system property
- when running solr to run with clustering enabled:
-
- java -Dsolr.clustering.enabled=true -jar start.jar
-
- -->
- <searchComponent name="clustering"
- enable="${solr.clustering.enabled:false}"
- class="solr.clustering.ClusteringComponent" >
- <!-- Declare an engine -->
- <lst name="engine">
- <!-- The name, only one can be named "default" -->
- <str name="name">default</str>
-
- <!-- Class name of Carrot2 clustering algorithm.
-
- Currently available algorithms are:
-
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
- * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
-
- See http://project.carrot2.org/algorithms.html for the
- algorithm's characteristics.
- -->
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
+ <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
- <!-- Overriding values for Carrot2 default algorithm attributes.
-
- For a description of all available attributes, see:
- http://download.carrot2.org/stable/manual/#chapter.components.
- Use attribute key as name attribute of str elements
- below. These can be further overridden for individual
- requests by specifying attribute key as request parameter
- name and attribute value as parameter value.
- -->
- <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
-
- <!-- Location of Carrot2 lexical resources.
-
- A directory from which to load Carrot2-specific stop words
- and stop labels. Absolute or relative to Solr config directory.
- If a specific resource (e.g. stopwords.en) is present in the
- specified dir, it will completely override the corresponding
- default one that ships with Carrot2.
-
- For an overview of Carrot2 lexical resources, see:
- http://download.carrot2.org/head/manual/#chapter.lexical-resources
- -->
- <str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
-
- <!-- The language to assume for the documents.
-
- For a list of allowed values, see:
- http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
- -->
- <str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
- </lst>
- <lst name="engine">
- <str name="name">stc</str>
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
- </lst>
- </searchComponent>
-
- <!-- A request handler for demonstrating the clustering component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/clustering"
- startup="lazy"
- enable="${solr.clustering.enabled:false}"
- class="solr.SearchHandler">
- <lst name="defaults">
- <bool name="clustering">true</bool>
- <str name="clustering.engine">default</str>
- <bool name="clustering.results">true</bool>
- <!-- The title field -->
- <str name="carrot.title">name</str>
- <str name="carrot.url">id</str>
- <!-- The field to cluster on -->
- <str name="carrot.snippet">features</str>
- <!-- produce summaries -->
- <bool name="carrot.produceSummary">true</bool>
- <!-- the maximum number of labels per cluster -->
- <!--<int name="carrot.numDescriptions">5</int>-->
- <!-- produce sub clusters -->
- <bool name="carrot.outputSubClusters">false</bool>
-
- <str name="defType">edismax</str>
- <str name="qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- </str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- </lst>
- <arr name="last-components">
- <str>clustering</str>
- </arr>
- </requestHandler>
-
<!-- Terms Component
http://wiki.apache.org/solr/TermsComponent
<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<bool name="terms">true</bool>
- </lst>
+ <bool name="distrib">false</bool>
+ </lst>
<arr name="components">
<str>terms</str>
</arr>
<highlighting>
<!-- Configure the standard fragmenter -->
<!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
+ <fragmenter name="gap"
default="true"
class="solr.highlight.GapFragmenter">
<lst name="defaults">
</lst>
</fragmenter>
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
-->
- <fragmenter name="regex"
+ <fragmenter name="regex"
class="solr.highlight.RegexFragmenter">
<lst name="defaults">
<!-- slightly smaller fragsizes work better because of slop -->
</fragmenter>
<!-- Configure the standard formatter -->
- <formatter name="html"
+ <formatter name="html"
default="true"
class="solr.highlight.HtmlFormatter">
<lst name="defaults">
</formatter>
<!-- Configure the standard encoder -->
- <encoder name="html"
+ <encoder name="html"
class="solr.highlight.HtmlEncoder" />
<!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
+ <fragListBuilder name="simple"
class="solr.highlight.SimpleFragListBuilder"/>
-
+
<!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
+ <fragListBuilder name="single"
class="solr.highlight.SingleFragListBuilder"/>
-
+
<!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
+ <fragListBuilder name="weighted"
default="true"
class="solr.highlight.WeightedFragListBuilder"/>
-
+
<!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
+ <fragmentsBuilder name="default"
default="true"
class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
+ <!--
<lst name="defaults">
<str name="hl.multiValuedSeparatorChar">/</str>
</lst>
</fragmentsBuilder>
<!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
+ <fragmentsBuilder name="colored"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<lst name="defaults">
<str name="hl.tag.pre"><![CDATA[
<str name="hl.tag.post"><![CDATA[</b>]]></str>
</lst>
</fragmentsBuilder>
-
- <boundaryScanner name="default"
+
+ <boundaryScanner name="default"
default="true"
class="solr.highlight.SimpleBoundaryScanner">
<lst name="defaults">
<str name="hl.bs.chars">.,!? 	 </str>
</lst>
</boundaryScanner>
-
- <boundaryScanner name="breakIterator"
+
+ <boundaryScanner name="breakIterator"
class="solr.highlight.BreakIteratorBoundaryScanner">
<lst name="defaults">
<!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
http://wiki.apache.org/solr/UpdateRequestProcessor
- -->
+ -->
<!-- Deduplication
An example dedup update processor that creates the "id" field
on the fly based on the hash code of some other fields. This
example has overwriteDupes set to false since we are using the
id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
+ uniqueness based on that anyway.
+
-->
<!--
<updateRequestProcessorChain name="dedupe">
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
-
+
<!-- Language identification
This example update chain identifies the language of the incoming
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
-
+
<!-- Response Writers
http://wiki.apache.org/solr/QueryResponseWriter
overridden...
-->
<!--
- <queryResponseWriter name="xml"
+ <queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
<queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
<queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
-->
<queryResponseWriter name="json" class="solr.JSONResponseWriter">
-->
<str name="content-type">text/plain; charset=UTF-8</str>
</queryResponseWriter>
-
+
<!--
Custom response writers can be declared as needed...
-->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
-
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
+ <str name="template.base.dir">${velocity.template.base.dir:}</str>
+ </queryResponseWriter>
<!-- XSLT response writer transforms the XML output by any xslt file found
in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
+ every xsltCacheLifetimeSeconds.
-->
<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
<int name="xsltCacheLifetimeSeconds">5</int>
-->
<!-- example of registering a custom function parser -->
<!--
- <valueSourceParser name="myfunc"
+ <valueSourceParser name="myfunc"
class="com.mycompany.MyValueSourceParser" />
-->
-
-
+
+
<!-- Document Transformers
http://wiki.apache.org/solr/DocTransformers
-->
<transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
<int name="connection">jdbc://....</int>
</transformer>
-
+
To add a constant value to all docs, use:
<transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<int name="value">5</int>
</transformer>
-
+
If you want the user to still be able to change it with _value:something_ use this:
<transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<double name="defaultValue">5</double>
EditorialMarkerFactory will do exactly that:
<transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
-->
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
- </admin>
</config>
fnp / wolnelektury.git / commitdiff