+++ /dev/null
-0.7 WIP
- - add dynamic binary field *_bin
+++ /dev/null
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Syntax:
-# "source" => "target"
-# "source".length() > 0 (source cannot be empty.)
-# "target".length() >= 0 (target can be empty.)
-
-# example:
-# "À" => "A"
-# "\u00C0" => "A"
-# "\u00C0" => "\u0041"
-# "ß" => "ss"
-# "\t" => " "
-# "\n" => ""
-
-# À => A
-"\u00C0" => "A"
-
-# Á => A
-"\u00C1" => "A"
-
-# Â => A
-"\u00C2" => "A"
-
-# Ã => A
-"\u00C3" => "A"
-
-# Ä => A
-"\u00C4" => "A"
-
-# Å => A
-"\u00C5" => "A"
-
-# Æ => AE
-"\u00C6" => "AE"
-
-# Ç => C
-"\u00C7" => "C"
-
-# È => E
-"\u00C8" => "E"
-
-# É => E
-"\u00C9" => "E"
-
-# Ê => E
-"\u00CA" => "E"
-
-# Ë => E
-"\u00CB" => "E"
-
-# Ì => I
-"\u00CC" => "I"
-
-# Í => I
-"\u00CD" => "I"
-
-# Î => I
-"\u00CE" => "I"
-
-# Ï => I
-"\u00CF" => "I"
-
-# IJ => IJ
-"\u0132" => "IJ"
-
-# Ð => D
-"\u00D0" => "D"
-
-# Ñ => N
-"\u00D1" => "N"
-
-# Ò => O
-"\u00D2" => "O"
-
-# Ó => O
-"\u00D3" => "O"
-
-# Ô => O
-"\u00D4" => "O"
-
-# Õ => O
-"\u00D5" => "O"
-
-# Ö => O
-"\u00D6" => "O"
-
-# Ø => O
-"\u00D8" => "O"
-
-# Π=> OE
-"\u0152" => "OE"
-
-# Þ
-"\u00DE" => "TH"
-
-# Ù => U
-"\u00D9" => "U"
-
-# Ú => U
-"\u00DA" => "U"
-
-# Û => U
-"\u00DB" => "U"
-
-# Ü => U
-"\u00DC" => "U"
-
-# Ý => Y
-"\u00DD" => "Y"
-
-# Ÿ => Y
-"\u0178" => "Y"
-
-# à => a
-"\u00E0" => "a"
-
-# á => a
-"\u00E1" => "a"
-
-# â => a
-"\u00E2" => "a"
-
-# ã => a
-"\u00E3" => "a"
-
-# ä => a
-"\u00E4" => "a"
-
-# å => a
-"\u00E5" => "a"
-
-# æ => ae
-"\u00E6" => "ae"
-
-# ç => c
-"\u00E7" => "c"
-
-# è => e
-"\u00E8" => "e"
-
-# é => e
-"\u00E9" => "e"
-
-# ê => e
-"\u00EA" => "e"
-
-# ë => e
-"\u00EB" => "e"
-
-# ì => i
-"\u00EC" => "i"
-
-# í => i
-"\u00ED" => "i"
-
-# î => i
-"\u00EE" => "i"
-
-# ï => i
-"\u00EF" => "i"
-
-# ij => ij
-"\u0133" => "ij"
-
-# ð => d
-"\u00F0" => "d"
-
-# ñ => n
-"\u00F1" => "n"
-
-# ò => o
-"\u00F2" => "o"
-
-# ó => o
-"\u00F3" => "o"
-
-# ô => o
-"\u00F4" => "o"
-
-# õ => o
-"\u00F5" => "o"
-
-# ö => o
-"\u00F6" => "o"
-
-# ø => o
-"\u00F8" => "o"
-
-# œ => oe
-"\u0153" => "oe"
-
-# ß => ss
-"\u00DF" => "ss"
-
-# þ => th
-"\u00FE" => "th"
-
-# ù => u
-"\u00F9" => "u"
-
-# ú => u
-"\u00FA" => "u"
-
-# û => u
-"\u00FB" => "u"
-
-# ü => u
-"\u00FC" => "u"
-
-# ý => y
-"\u00FD" => "y"
-
-# ÿ => y
-"\u00FF" => "y"
-
-# ff => ff
-"\uFB00" => "ff"
-
-# fi => fi
-"\uFB01" => "fi"
-
-# fl => fl
-"\uFB02" => "fl"
-
-# ffi => ffi
-"\uFB03" => "ffi"
-
-# ffl => ffl
-"\uFB04" => "ffl"
-
-# ſt => ft
-"\uFB05" => "ft"
-
-# st => st
-"\uFB06" => "st"
+++ /dev/null
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the StreamingUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
-<schema name="Local Unified Index" version="1.2">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- Applications should change this to reflect the nature of the search collection.
- version="1.2" is Solr's version number for the schema syntax and semantics. It should
- not normally be changed by applications.
- 1.0: multiValued attribute did not exist, all fields are multiValued by nature
- 1.1: multiValued attribute introduced, false by default
- 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
- -->
-
- <types>
- <!-- 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 the
- org.apache.solr.analysis package.
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- - StrField and TextField support an optional compressThreshold which
- limits compression (if enabled in the derived fields) to values which
- exceed a certain size (in characters).
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldtype name="binary" class="solr.BinaryField"/>
-
- <!-- The optional sortMissingLast and sortMissingFirst attributes are
- currently supported on types that are sorted internally as strings.
- This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
- -->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" 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" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-
- <!-- 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
- 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.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the DateField javadocs for more information.
-
- Note: For faster range queries, consider the tdate type
- -->
- <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
-
- <!-- A Trie based date field for faster date range queries and date faceting. -->
- <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
-
- <!-- Test of new facet type that would support case-insensitive facetting -->
- <fieldType name="facet" 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" />
- </analyzer>
- </fieldType>
-
- <!--
- Note:
- These should only be used for compatibility with existing indexes (created with older Solr versions)
- or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
-
- Plain numeric field types that store and index the text
- value verbatim (and hence don't support range queries, since the
- lexicographic ordering isn't equal to the numeric ordering)
- -->
- <fieldType name="pint" class="solr.IntField" omitNorms="true"/>
- <fieldType name="plong" class="solr.LongField" omitNorms="true"/>
- <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
- <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
- <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
-
-
- <!--
- Note:
- These should only be used for compatibility with existing indexes (created with older Solr versions)
- or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
-
- Numeric field types that manipulate the value into
- a string value that isn't human-readable in its internal form,
- but with a lexicographic ordering the same as the numeric ordering,
- so that range queries work correctly.
- -->
- <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
-
-
- <!-- 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
- purposes. The ordering is generated based on the field name
- and the version of the index, As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the name
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- 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 field that uses WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
- so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
- Synonyms and stopwords are customized by external files, and stemming is enabled.
- -->
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
- <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="stopwords.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.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- 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.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- </analyzer>
- </fieldType>
-
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- A general unstemmed text field - good if one does not know the language of the field -->
- <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- A general unstemmed text field that indexes tokens normally and also
- reversed (via ReversedWildcardFilterFactory), to enable more efficient
- leading wildcard queries. -->
- <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="textCharNorm" 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://java.sun.com/j2se/1.5.0/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>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </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" />
-
- <!-- subject -->
- <fieldType name="subject" class="solr.StrField" positionIncrementGap="100">
-<!--
- <analyzer>
- <tokenizer class="solr.PatternTokenizerFactory" pattern=";" />
- <filter class="solr.StandardFilterFactory" />
- <filter class="solr.TrimFilterFactory" />
- </analyzer>
--->
- </fieldType>
-
- <!-- Author type -->
- <fieldType name="author" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.PatternTokenizerFactory" pattern=";" />
- <filter class="solr.StandardFilterFactory" />
- <filter class="solr.TrimFilterFactory" />
-<!--
- <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
--->
- </analyzer>
- </fieldType>
-
-
- </types>
-
-
- <fields>
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a previously defined type from the
- <types> section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- compressed: [false] if this field should be stored using gzip compression
- (this will only apply if the field type is compressable; among
- the standard field types, only TextField and StrField are)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
-<!--
--->
- <field name="id" type="string" indexed="true" stored="true" required="true" />
-
- <field name="author" type="text" indexed="true" stored="true" multiValued="true" compressed="false" omitNorms="true"/>
- <field name="author_exact" type="facet" indexed="true" stored="true" multiValued="true" compressed="false" omitNorms="true"/>
- <field name="author-date" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="author-title" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="corporate-date" type="text" indexed="true" stored="true" omitNorms="true"/>
- <field name="corporate-location" type="text" indexed="true" stored="true" omitNorms="true"/>
- <field name="corporate-name" type="text" indexed="true" stored="true" omitNorms="true"/>
-
- <field name="callnumber" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="citation" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
-
- <field name="date" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="description" type="text_ws" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
-
- <field name="edition" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="electronic-format-instruction" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="electronic-format-type" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="electronic-note" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
- <field name="electronic-text" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
- <field name="electronic-url" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="isbn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="issn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="lccn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="medium" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
- <field name="medium_exact" type="facet" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="meeting-date" type="text" indexed="true" stored="true" omitNorms="true"/>
- <field name="meeting-location" type="text" indexed="true" stored="true" omitNorms="true"/>
- <field name="meeting-name" type="text" indexed="true" stored="true" omitNorms="true"/>
-
- <field name="series-title" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="subject" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
- <field name="subject_exact" type="facet" indexed="true" stored="true" multiValued="true" omitNorms="true" />
- <field name="subject-long" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
-
- <field name="system-control-nr" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
-
- <field name="tech-rep-nr" type="text" indexed="true" multiValued="true" stored="true"/>
-
- <field name="title" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
- <field name="title-complete" type="text" indexed="true" multiValued="true" compressed="true" stored="true"/>
- <field name="title-dates" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-medium" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-number-section" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-remainder" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-responsibility" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-uniform" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-uniform-key" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-uniform-media" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-uniform-partname" type="text" indexed="true" multiValued="true" stored="true"/>
- <field name="title-uniform-parts" type="text" indexed="true" multiValued="true" stored="true"/>
-
- <field name="journal-title" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
- <field name="journal-title_exact" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
-
- <field name="physical-accomp" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-dimensions" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-extent" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-format" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-specified" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-unitsize" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="physical-unittype" type="text" indexed="true" stored="true" multiValued="true" />
-
- <field name="publication-date" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="publication-name" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="publication-place" type="text" indexed="true" stored="true" multiValued="true" />
-
-
- <!-- Common metadata fields, named specifically to match up with
- SolrCell metadata when parsing rich documents such as Word, PDF.
- Some fields are multiValued only because Tika currently may return
- multiple values for them.
- -->
-<!--
- <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
- <field name="description" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="comments" type="text" indexed="true" stored="true"/>
- <field name="author" type="textgen" indexed="true" stored="true"/>
- <field name="keywords" type="textgen" indexed="true" stored="true"/>
- <field name="category" type="textgen" indexed="true" stored="true"/>
- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="last_modified" type="date" indexed="true" stored="true"/>
- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
--->
-
- <!-- catchall field, containing all other searchable text fields (implemented
- via copyField further on in this schema -->
- <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
-
- <!-- catchall text field that indexes tokens both normally and in reverse for efficient
- leading wildcard queries. -->
- <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
-
- <field name="payloads" type="payloads" indexed="true" stored="true"/>
-
- <!-- Uncommenting the following will create a "timestamp" field using
- a default value of "NOW" to indicate when each document was indexed.
- -->
- <!--
- <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
- -->
-
-
- <!-- Dynamic field definitions. If a field name is not found, dynamicFields
- will be used if the name matches any of the patterns.
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- Longer patterns will be matched first. if equal size patterns
- both match, the first appearing in the schema will be used. -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" 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="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="textgen" 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="text" multiValued="true" />
-
- </fields>
-
- <!-- 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>
-
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
- <defaultSearchField>text</defaultSearchField>
-
- <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
- <solrQueryParser defaultOperator="AND"/>
-
- <!-- 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. -->
-
- <copyField source="author" dest="author_exact"/>
- <copyField source="subject" dest="subject_exact"/>
- <copyField source="medium" dest="medium_exact"/>
- <copyField source="journal-title" dest="journal-title_exact"/>
-
- <!-- Above, multiple source fields are copied to the [text] field.
- Another way to map multiple source fields to the same
- destination field is to use the dynamic field syntax.
- copyField also supports a maxChars to copy setting. -->
-
- <copyField source="*" dest="text" maxChars="10000"/>
-
- <!-- copy name to alphaNameSort, a field designed for sorting by name -->
- <!-- <copyField source="name" dest="alphaNameSort"/> -->
-
-
- <!-- Similarity is the scoring routine for each document vs. a query.
- A custom similarity may be specified here, but the default is fine
- for most applications. -->
- <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
- <!-- ... OR ...
- Specify a SimilarityFactory class name implementation
- allowing parameters to be used.
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
- <str name="paramkey">param value</str>
- </similarity>
- -->
-</schema>
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Set this to 'false' if you want solr to continue working after
- it has encountered an severe configuration error. In a
- production environment, you may want solr to keep working even
- if one handler is mis-configured.
-
- You may also set this to false using by setting the system
- property:
-
- -Dsolr.abortOnConfigurationError=false
- -->
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>LUCENE_33</luceneMatchVersion>
-
- <!-- lib directives can be used to instruct Solr to load an Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- 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 to
- the classpath, this is useful for including all jars in a
- directory.
- -->
- <lib dir="../../contrib/extraction/lib" />
- <!-- When a regex is specified in addition to a directory, 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="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
- <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
-
- <!-- If a dir option (with or without a regex) is used and nothing
- is found that matches, it will be ignored
- -->
- <lib dir="../../contrib/clustering/lib/" />
- <lib dir="/total/crap/dir/ignored" />
- <!-- an exact path can be used to specify a specific 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" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:/home/dennis/proj/lui-solr/data}</dataDir>
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory, the default, is filesystem
- based. solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
-
-
- <!-- Index Defaults
-
- Values here affect all index writers and act as a default
- unless overridden.
-
- WARNING: See also the <mainIndex> section below for parameters
- that overfor Solr's main Lucene index.
- -->
- <indexDefaults>
-
- <useCompoundFile>false</useCompoundFile>
-
- <mergeFactor>10</mergeFactor>
- <!-- Sets the amount of RAM that may be used by Lucene indexing
- for buffering added documents and deletions before they are
- flushed to the Directory. -->
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <maxFieldLength>10000</maxFieldLength>
- <writeLockTimeout>1000</writeLockTimeout>
- <commitLockTimeout>10000</commitLockTimeout>
-
- <!-- Expert: Merge Policy
-
- The Merge Policy in Lucene controls how merging is handled by
- Lucene. The default in Solr 3.3 is TieredMergePolicy.
-
- The default in 2.3 was the LogByteSizeMergePolicy,
- previous versions used LogDocMergePolicy.
-
- LogByteSizeMergePolicy chooses segments to merge based on
- their size. The Lucene 2.2 default, LogDocMergePolicy chose
- when to merge based on number of documents
-
- Other implementations of MergePolicy must have a no-argument
- constructor
- -->
- <!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
- -->
-
- <!-- Expert: Merge Scheduler
-
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- 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
-
- 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.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- (For backwards compatibility with Solr 1.2, 'simple' is the
- default if not specified.)
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>native</lockType>
-
- <!-- Expert: Controls how often Lucene loads terms into memory
- Default is 128 and is likely good for most everyone.
- -->
- <!-- <termIndexInterval>256</termIndexInterval> -->
- </indexDefaults>
-
- <!-- Main Index
-
- Values here override the values in the <indexDefaults> section
- for the main on disk index.
- -->
- <mainIndex>
-
- <useCompoundFile>false</useCompoundFile>
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <mergeFactor>10</mergeFactor>
-
- <!-- Unlock On Startup
-
- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be used
- with care.
-
- This is not needed if lock type is 'none' or 'single'
- -->
- <unlockOnStartup>false</unlockOnStartup>
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened.
- -->
- <reopenReaders>true</reopenReaders>
-
- <!-- Commit Deletion Policy
-
- Custom deletion policies can specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
-
- The standard 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="maxCommitsToKeep">1</str>
- <!-- The number of optimized commit points to be kept -->
- <str name="maxOptimizedCommitsToKeep">0</str>
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <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>
-
- </mainIndex>
-
- <!-- 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
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- AutoCommit
-
- Perform a <commit/> automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time that is allowed to pass
- since a document was added before automaticly
- triggering a new commit.
- -->
- <!--
- <autoCommit>
- <maxDocs>10000</maxDocs>
- <maxTime>1000</maxTime>
- </autoCommit>
- -->
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- 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.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
- </indexReaderFactory >
- -->
-
-
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- 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>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- 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.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="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.
- -->
- <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.
- -->
- <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.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- 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.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- 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.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- 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.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <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.
-
- Recommend values of 1-2 for read-only slaves, higher for
- masters w/o cache warming.
- -->
- <maxWarmingSearchers>10</maxWarmingSearchers>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect affects the behavior of requests such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and will result in consistent error handling and
- formatting for all types of requests.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests and fallback to using the legacy
- SolrServlet and it's Solr 1.1 style error formatting
- -->
- <requestDispatcher handleSelect="true" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- 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"
- multipartUploadLimitInKB="2048000" />
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- 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>
- </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.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- incoming queries will be dispatched to the correct handler
- based on the path or the qt (query type) param.
-
- Names starting with a '/' are accessed with the a path equal to
- the registered name. Names without a leading '/' are accessed
- with: http://host/app/[core/]select?qt=name
-
- If a /select request is processed with out a qt param
- specified, the requestHandler that declares default="true" will
- be used.
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="search" class="solr.SearchHandler" default="true">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="spellcheck.dictionary">text</str>
- <!-- omp = Only More Popular -->
- <str name="spellcheck.onlyMorePopular">false</str>
- <!-- exr = Extended Results -->
- <str name="spellcheck.extendedResults">true</str>
- <!-- The number of suggestions to return -->
- <str name="spellcheck.count">5</str>
- <str name="spellcheck">true</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
-
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
- <str name="title">Solritas</str>
-
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- <str name="mlt.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="mlt.fl">text,features,name,sku,id,manu,cat</str>
- <int name="mlt.count">3</int>
-
- <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="facet">on</str>
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">ipod</str>
- <str name="facet.query">GB</str>
- <str name="facet.mincount">1</str>
- <str name="facet.pivot">cat,inStock</str>
- <str name="facet.range">price</str>
- <int name="f.price.facet.range.start">0</int>
- <int name="f.price.facet.range.end">600</int>
- <int name="f.price.facet.range.gap">50</int>
- <str name="f.price.facet.range.other">after</str>
- <str name="facet.range">manufacturedate_dt</str>
- <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
- <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
- <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
- <str name="f.manufacturedate_dt.facet.range.other">before</str>
- <str name="f.manufacturedate_dt.facet.range.other">after</str>
-
-
- <!-- Highlighting defaults -->
- <str name="hl">on</str>
- <str name="hl.fl">text features name</str>
- <str name="f.name.hl.fragsize">0</str>
- <str name="f.name.hl.alternateField">name</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- <!--
- <str name="url-scheme">httpx</str>
- -->
- </requestHandler>
-
- <!-- XML Update Request Handler.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- The canonical Request Handler for Modifying the Index through
- commands specified using XML.
-
- 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'
- -->
- <requestHandler name="/update"
- class="solr.XmlUpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
- on each Update Request
- -->
- <!--
- <lst name="defaults">
- <str name="update.chain">dedupe</str>
- </lst>
- -->
- </requestHandler>
- <!-- Binary Update Request Handler
- http://wiki.apache.org/solr/javabin
- -->
- <requestHandler name="/update/javabin"
- class="solr.BinaryUpdateRequestHandler" />
-
- <!-- CSV Update Request Handler
- http://wiki.apache.org/solr/UpdateCSV
- -->
- <requestHandler name="/update/csv"
- class="solr.CSVRequestHandler"
- startup="lazy" />
-
- <!-- JSON Update Request Handler
- http://wiki.apache.org/solr/UpdateJSON
- -->
- <requestHandler name="/update/json"
- class="solr.JsonUpdateRequestHandler"
- startup="lazy" />
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <!-- All the main content goes into "text"... if you need to return
- the extracted text or do highlighting, use a stored field. -->
- <str name="fmap.content">text</str>
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided docuemnts. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- 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".
- -->
- <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="defaults">
- <str name="qt">search</str>
- <str name="q">solrpingquery</str>
- <str name="echoParams">all</str>
- </lst>
- </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="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "salves" 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/replication</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- </requestHandler>
- -->
-
- <!-- Search Components
-
- 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>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- 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"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text</str>
-
- <lst name="spellchecker">
- <str name="classname">solr.IndexBasedSpellChecker</str>
- <str name="name">text</str>
- <str name="field">text</str>
- <str name="buildOnOptimize">true</str>
- <str name="spellcheckIndexDir">./spellchecker</str>
- <!-- uncomment this to require terms to occur in 1% of the documents in order to be included in the dictionary
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- <str name="spellcheckIndexDir">spellcheckerJaro</str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="spellcheckIndexDir">spellcheckerFreq</str>
- <str name="comparatorClass">freq</str>
- <str name="buildOnCommit">true</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- 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
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- 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.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="spellcheck.onlyMorePopular">false</str>
- <str name="spellcheck.extendedResults">false</str>
- <str name="spellcheck.count">1</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector 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="tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- This relies on third party jars which are notincluded in the
- release. To use this component (and the "/clustering" handler)
- Those jars will need to be downloaded, and you'll need to set
- the solr.cluster.enabled system property when running solr...
-
- 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>
-
- <!-- 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
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- default="true"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <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"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- 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.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- -->
- <!--
- Custom response writers can be declared as needed...
- -->
- <!--
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
- -->
-
- <!-- 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.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
-
- <!-- configure a healthcheck file for servers behind a
- loadbalancer
- -->
- <!--
- <healthcheck type="file">server-enabled</healthcheck>
- -->
- </admin>
-
-</config>
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Set this to 'false' if you want solr to continue working after
- it has encountered an severe configuration error. In a
- production environment, you may want solr to keep working even
- if one handler is mis-configured.
-
- You may also set this to false using by setting the system
- property:
-
- -Dsolr.abortOnConfigurationError=false
- -->
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>LUCENE_33</luceneMatchVersion>
-
- <!-- lib directives can be used to instruct Solr to load an Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- 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 to
- the classpath, this is useful for including all jars in a
- directory.
- -->
- <lib dir="../../contrib/extraction/lib" />
- <!-- When a regex is specified in addition to a directory, 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="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
- <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
-
- <!-- If a dir option (with or without a regex) is used and nothing
- is found that matches, it will be ignored
- -->
- <lib dir="../../contrib/clustering/lib/" />
- <lib dir="/total/crap/dir/ignored" />
- <!-- an exact path can be used to specify a specific 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" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:/var/lib/masterkey/lui/solr/master}</dataDir>
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory, the default, is filesystem
- based. solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
-
-
- <!-- Index Defaults
-
- Values here affect all index writers and act as a default
- unless overridden.
-
- WARNING: See also the <mainIndex> section below for parameters
- that overfor Solr's main Lucene index.
- -->
- <indexDefaults>
-
- <useCompoundFile>false</useCompoundFile>
-
- <mergeFactor>10</mergeFactor>
- <!-- Sets the amount of RAM that may be used by Lucene indexing
- for buffering added documents and deletions before they are
- flushed to the Directory. -->
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <maxFieldLength>10000</maxFieldLength>
- <writeLockTimeout>1000</writeLockTimeout>
- <commitLockTimeout>10000</commitLockTimeout>
-
- <!-- Expert: Merge Policy
-
- The Merge Policy in Lucene controls how merging is handled by
- Lucene. The default in Solr 3.3 is TieredMergePolicy.
-
- The default in 2.3 was the LogByteSizeMergePolicy,
- previous versions used LogDocMergePolicy.
-
- LogByteSizeMergePolicy chooses segments to merge based on
- their size. The Lucene 2.2 default, LogDocMergePolicy chose
- when to merge based on number of documents
-
- Other implementations of MergePolicy must have a no-argument
- constructor
- -->
- <!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
- -->
-
- <!-- Expert: Merge Scheduler
-
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- 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
-
- 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.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- (For backwards compatibility with Solr 1.2, 'simple' is the
- default if not specified.)
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>native</lockType>
-
- <!-- Expert: Controls how often Lucene loads terms into memory
- Default is 128 and is likely good for most everyone.
- -->
- <!-- <termIndexInterval>256</termIndexInterval> -->
- </indexDefaults>
-
- <!-- Main Index
-
- Values here override the values in the <indexDefaults> section
- for the main on disk index.
- -->
- <mainIndex>
-
- <useCompoundFile>false</useCompoundFile>
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <mergeFactor>10</mergeFactor>
-
- <!-- Unlock On Startup
-
- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be used
- with care.
-
- This is not needed if lock type is 'none' or 'single'
- -->
- <unlockOnStartup>false</unlockOnStartup>
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened.
- -->
- <reopenReaders>true</reopenReaders>
-
- <!-- Commit Deletion Policy
-
- Custom deletion policies can specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
-
- The standard 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="maxCommitsToKeep">1</str>
- <!-- The number of optimized commit points to be kept -->
- <str name="maxOptimizedCommitsToKeep">0</str>
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <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>
-
- </mainIndex>
-
- <!-- 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
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- AutoCommit
-
- Perform a <commit/> automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time that is allowed to pass
- since a document was added before automaticly
- triggering a new commit.
- -->
- <!--
- <autoCommit>
- <maxDocs>10000</maxDocs>
- <maxTime>1000</maxTime>
- </autoCommit>
- -->
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- 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.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
- </indexReaderFactory >
- -->
-
-
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- 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>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- 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.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="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.
- -->
- <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.
- -->
- <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.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- 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.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- 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.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- 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.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <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.
-
- Recommend values of 1-2 for read-only slaves, higher for
- masters w/o cache warming.
- -->
- <maxWarmingSearchers>2</maxWarmingSearchers>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect affects the behavior of requests such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and will result in consistent error handling and
- formatting for all types of requests.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests and fallback to using the legacy
- SolrServlet and it's Solr 1.1 style error formatting
- -->
- <requestDispatcher handleSelect="true" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- 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"
- multipartUploadLimitInKB="2048000" />
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- 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>
- </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.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- incoming queries will be dispatched to the correct handler
- based on the path or the qt (query type) param.
-
- Names starting with a '/' are accessed with the a path equal to
- the registered name. Names without a leading '/' are accessed
- with: http://host/app/[core/]select?qt=name
-
- If a /select request is processed with out a qt param
- specified, the requestHandler that declares default="true" will
- be used.
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="search" class="solr.SearchHandler" default="true">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="spellcheck.dictionary">text</str>
- <!-- omp = Only More Popular -->
- <str name="spellcheck.onlyMorePopular">false</str>
- <!-- exr = Extended Results -->
- <str name="spellcheck.extendedResults">true</str>
- <!-- The number of suggestions to return -->
- <str name="spellcheck.count">5</str>
- <str name="spellcheck">true</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
-
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
- <str name="title">Solritas</str>
-
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- <str name="mlt.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="mlt.fl">text,features,name,sku,id,manu,cat</str>
- <int name="mlt.count">3</int>
-
- <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="facet">on</str>
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">ipod</str>
- <str name="facet.query">GB</str>
- <str name="facet.mincount">1</str>
- <str name="facet.pivot">cat,inStock</str>
- <str name="facet.range">price</str>
- <int name="f.price.facet.range.start">0</int>
- <int name="f.price.facet.range.end">600</int>
- <int name="f.price.facet.range.gap">50</int>
- <str name="f.price.facet.range.other">after</str>
- <str name="facet.range">manufacturedate_dt</str>
- <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
- <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
- <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
- <str name="f.manufacturedate_dt.facet.range.other">before</str>
- <str name="f.manufacturedate_dt.facet.range.other">after</str>
-
-
- <!-- Highlighting defaults -->
- <str name="hl">on</str>
- <str name="hl.fl">text features name</str>
- <str name="f.name.hl.fragsize">0</str>
- <str name="f.name.hl.alternateField">name</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- <!--
- <str name="url-scheme">httpx</str>
- -->
- </requestHandler>
-
- <!-- XML Update Request Handler.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- The canonical Request Handler for Modifying the Index through
- commands specified using XML.
-
- 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'
- -->
- <requestHandler name="/update"
- class="solr.XmlUpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
- on each Update Request
- -->
- <!--
- <lst name="defaults">
- <str name="update.chain">dedupe</str>
- </lst>
- -->
- </requestHandler>
- <!-- Binary Update Request Handler
- http://wiki.apache.org/solr/javabin
- -->
- <requestHandler name="/update/javabin"
- class="solr.BinaryUpdateRequestHandler" />
-
- <!-- CSV Update Request Handler
- http://wiki.apache.org/solr/UpdateCSV
- -->
- <requestHandler name="/update/csv"
- class="solr.CSVRequestHandler"
- startup="lazy" />
-
- <!-- JSON Update Request Handler
- http://wiki.apache.org/solr/UpdateJSON
- -->
- <requestHandler name="/update/json"
- class="solr.JsonUpdateRequestHandler"
- startup="lazy" />
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <!-- All the main content goes into "text"... if you need to return
- the extracted text or do highlighting, use a stored field. -->
- <str name="fmap.content">text</str>
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided docuemnts. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- 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".
- -->
- <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="defaults">
- <str name="qt">search</str>
- <str name="q">solrpingquery</str>
- <str name="echoParams">all</str>
- </lst>
- </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="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "salves" 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/replication</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- -->
-
- </requestHandler>
-
-
- <!-- Search Components
-
- 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>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- 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"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text</str>
-
- <lst name="spellchecker">
- <str name="classname">solr.IndexBasedSpellChecker</str>
- <str name="name">text</str>
- <str name="field">text</str>
- <str name="buildOnOptimize">true</str>
- <str name="spellcheckIndexDir">./spellchecker</str>
- <!-- uncomment this to require terms to occur in 1% of the documents in order to be included in the dictionary
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- <str name="spellcheckIndexDir">spellcheckerJaro</str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="spellcheckIndexDir">spellcheckerFreq</str>
- <str name="comparatorClass">freq</str>
- <str name="buildOnCommit">true</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- 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
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- 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.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="spellcheck.onlyMorePopular">false</str>
- <str name="spellcheck.extendedResults">false</str>
- <str name="spellcheck.count">1</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector 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="tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- This relies on third party jars which are notincluded in the
- release. To use this component (and the "/clustering" handler)
- Those jars will need to be downloaded, and you'll need to set
- the solr.cluster.enabled system property when running solr...
-
- 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>
-
- <!-- 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
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- default="true"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <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"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- 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.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- -->
- <!--
- Custom response writers can be declared as needed...
- -->
- <!--
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
- -->
-
- <!-- 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.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
-
- <!-- configure a healthcheck file for servers behind a
- loadbalancer
- -->
- <!--
- <healthcheck type="file">server-enabled</healthcheck>
- -->
- </admin>
-
-</config>
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Set this to 'false' if you want solr to continue working after
- it has encountered an severe configuration error. In a
- production environment, you may want solr to keep working even
- if one handler is mis-configured.
-
- You may also set this to false using by setting the system
- property:
-
- -Dsolr.abortOnConfigurationError=false
- -->
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>LUCENE_33</luceneMatchVersion>
-
- <!-- lib directives can be used to instruct Solr to load an Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- 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 to
- the classpath, this is useful for including all jars in a
- directory.
- -->
- <lib dir="../../contrib/extraction/lib" />
- <!-- When a regex is specified in addition to a directory, 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="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
- <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
-
- <!-- If a dir option (with or without a regex) is used and nothing
- is found that matches, it will be ignored
- -->
- <lib dir="../../contrib/clustering/lib/" />
- <lib dir="/total/crap/dir/ignored" />
- <!-- an exact path can be used to specify a specific 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" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:/var/lib/masterkey/lui/solr/data}</dataDir>
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory, the default, is filesystem
- based. solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
-
-
- <!-- Index Defaults
-
- Values here affect all index writers and act as a default
- unless overridden.
-
- WARNING: See also the <mainIndex> section below for parameters
- that overfor Solr's main Lucene index.
- -->
- <indexDefaults>
-
- <useCompoundFile>false</useCompoundFile>
-
- <mergeFactor>10</mergeFactor>
- <!-- Sets the amount of RAM that may be used by Lucene indexing
- for buffering added documents and deletions before they are
- flushed to the Directory. -->
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <maxFieldLength>10000</maxFieldLength>
- <writeLockTimeout>1000</writeLockTimeout>
- <commitLockTimeout>10000</commitLockTimeout>
-
- <!-- Expert: Merge Policy
-
- The Merge Policy in Lucene controls how merging is handled by
- Lucene. The default in Solr 3.3 is TieredMergePolicy.
-
- The default in 2.3 was the LogByteSizeMergePolicy,
- previous versions used LogDocMergePolicy.
-
- LogByteSizeMergePolicy chooses segments to merge based on
- their size. The Lucene 2.2 default, LogDocMergePolicy chose
- when to merge based on number of documents
-
- Other implementations of MergePolicy must have a no-argument
- constructor
- -->
- <!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
- -->
-
- <!-- Expert: Merge Scheduler
-
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- 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
-
- 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.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- (For backwards compatibility with Solr 1.2, 'simple' is the
- default if not specified.)
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>native</lockType>
-
- <!-- Expert: Controls how often Lucene loads terms into memory
- Default is 128 and is likely good for most everyone.
- -->
- <!-- <termIndexInterval>256</termIndexInterval> -->
- </indexDefaults>
-
- <!-- Main Index
-
- Values here override the values in the <indexDefaults> section
- for the main on disk index.
- -->
- <mainIndex>
-
- <useCompoundFile>false</useCompoundFile>
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <mergeFactor>10</mergeFactor>
-
- <!-- Unlock On Startup
-
- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be used
- with care.
-
- This is not needed if lock type is 'none' or 'single'
- -->
- <unlockOnStartup>false</unlockOnStartup>
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened.
- -->
- <reopenReaders>true</reopenReaders>
-
- <!-- Commit Deletion Policy
-
- Custom deletion policies can specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
-
- The standard 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="maxCommitsToKeep">1</str>
- <!-- The number of optimized commit points to be kept -->
- <str name="maxOptimizedCommitsToKeep">0</str>
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <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>
-
- </mainIndex>
-
- <!-- 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
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- AutoCommit
-
- Perform a <commit/> automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time that is allowed to pass
- since a document was added before automaticly
- triggering a new commit.
- -->
- <!--
- <autoCommit>
- <maxDocs>10000</maxDocs>
- <maxTime>1000</maxTime>
- </autoCommit>
- -->
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- 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.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
- </indexReaderFactory >
- -->
-
-
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- 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>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- 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.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="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.
- -->
- <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.
- -->
- <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.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- 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.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- 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.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- 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.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <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.
-
- Recommend values of 1-2 for read-only slaves, higher for
- masters w/o cache warming.
- -->
- <maxWarmingSearchers>2</maxWarmingSearchers>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect affects the behavior of requests such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and will result in consistent error handling and
- formatting for all types of requests.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests and fallback to using the legacy
- SolrServlet and it's Solr 1.1 style error formatting
- -->
- <requestDispatcher handleSelect="true" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- 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"
- multipartUploadLimitInKB="2048000" />
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- 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>
- </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.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- incoming queries will be dispatched to the correct handler
- based on the path or the qt (query type) param.
-
- Names starting with a '/' are accessed with the a path equal to
- the registered name. Names without a leading '/' are accessed
- with: http://host/app/[core/]select?qt=name
-
- If a /select request is processed with out a qt param
- specified, the requestHandler that declares default="true" will
- be used.
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="search" class="solr.SearchHandler" default="true">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="spellcheck.dictionary">text</str>
- <!-- omp = Only More Popular -->
- <str name="spellcheck.onlyMorePopular">false</str>
- <!-- exr = Extended Results -->
- <str name="spellcheck.extendedResults">true</str>
- <!-- The number of suggestions to return -->
- <str name="spellcheck.count">5</str>
- <str name="spellcheck">true</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
-
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
- <str name="title">Solritas</str>
-
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- <str name="mlt.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="mlt.fl">text,features,name,sku,id,manu,cat</str>
- <int name="mlt.count">3</int>
-
- <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="facet">on</str>
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">ipod</str>
- <str name="facet.query">GB</str>
- <str name="facet.mincount">1</str>
- <str name="facet.pivot">cat,inStock</str>
- <str name="facet.range">price</str>
- <int name="f.price.facet.range.start">0</int>
- <int name="f.price.facet.range.end">600</int>
- <int name="f.price.facet.range.gap">50</int>
- <str name="f.price.facet.range.other">after</str>
- <str name="facet.range">manufacturedate_dt</str>
- <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
- <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
- <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
- <str name="f.manufacturedate_dt.facet.range.other">before</str>
- <str name="f.manufacturedate_dt.facet.range.other">after</str>
-
-
- <!-- Highlighting defaults -->
- <str name="hl">on</str>
- <str name="hl.fl">text features name</str>
- <str name="f.name.hl.fragsize">0</str>
- <str name="f.name.hl.alternateField">name</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- <!--
- <str name="url-scheme">httpx</str>
- -->
- </requestHandler>
-
- <!-- XML Update Request Handler.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- The canonical Request Handler for Modifying the Index through
- commands specified using XML.
-
- 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'
- -->
- <requestHandler name="/update"
- class="solr.XmlUpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
- on each Update Request
- -->
- <!--
- <lst name="defaults">
- <str name="update.chain">dedupe</str>
- </lst>
- -->
- </requestHandler>
- <!-- Binary Update Request Handler
- http://wiki.apache.org/solr/javabin
- -->
- <requestHandler name="/update/javabin"
- class="solr.BinaryUpdateRequestHandler" />
-
- <!-- CSV Update Request Handler
- http://wiki.apache.org/solr/UpdateCSV
- -->
- <requestHandler name="/update/csv"
- class="solr.CSVRequestHandler"
- startup="lazy" />
-
- <!-- JSON Update Request Handler
- http://wiki.apache.org/solr/UpdateJSON
- -->
- <requestHandler name="/update/json"
- class="solr.JsonUpdateRequestHandler"
- startup="lazy" />
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <!-- All the main content goes into "text"... if you need to return
- the extracted text or do highlighting, use a stored field. -->
- <str name="fmap.content">text</str>
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided docuemnts. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- 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".
- -->
- <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="defaults">
- <str name="qt">search</str>
- <str name="q">solrpingquery</str>
- <str name="echoParams">all</str>
- </lst>
- </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="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "salves" 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/replication</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- </requestHandler>
- -->
-
- <!-- Search Components
-
- 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>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- 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"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text</str>
-
- <lst name="spellchecker">
- <str name="classname">solr.IndexBasedSpellChecker</str>
- <str name="name">text</str>
- <str name="field">text</str>
- <str name="buildOnOptimize">true</str>
- <str name="spellcheckIndexDir">./spellchecker</str>
- <!-- uncomment this to require terms to occur in 1% of the documents in order to be included in the dictionary
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- <str name="spellcheckIndexDir">spellcheckerJaro</str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="spellcheckIndexDir">spellcheckerFreq</str>
- <str name="comparatorClass">freq</str>
- <str name="buildOnCommit">true</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- 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
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- 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.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="spellcheck.onlyMorePopular">false</str>
- <str name="spellcheck.extendedResults">false</str>
- <str name="spellcheck.count">1</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector 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="tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- This relies on third party jars which are notincluded in the
- release. To use this component (and the "/clustering" handler)
- Those jars will need to be downloaded, and you'll need to set
- the solr.cluster.enabled system property when running solr...
-
- 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>
-
- <!-- 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
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- default="true"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <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"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- 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.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- -->
- <!--
- Custom response writers can be declared as needed...
- -->
- <!--
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
- -->
-
- <!-- 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.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
-
- <!-- configure a healthcheck file for servers behind a
- loadbalancer
- -->
- <!--
- <healthcheck type="file">server-enabled</healthcheck>
- -->
- </admin>
-
-</config>
+++ /dev/null
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Set this to 'false' if you want solr to continue working after
- it has encountered an severe configuration error. In a
- production environment, you may want solr to keep working even
- if one handler is mis-configured.
-
- You may also set this to false using by setting the system
- property:
-
- -Dsolr.abortOnConfigurationError=false
- -->
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>LUCENE_33</luceneMatchVersion>
-
- <!-- lib directives can be used to instruct Solr to load an Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- 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 to
- the classpath, this is useful for including all jars in a
- directory.
- -->
- <lib dir="../../contrib/extraction/lib" />
- <!-- When a regex is specified in addition to a directory, 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="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
- <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
-
- <!-- If a dir option (with or without a regex) is used and nothing
- is found that matches, it will be ignored
- -->
- <lib dir="../../contrib/clustering/lib/" />
- <lib dir="/total/crap/dir/ignored" />
- <!-- an exact path can be used to specify a specific 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" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:/var/lib/masterkey/lui/solr/slave}</dataDir>
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory, the default, is filesystem
- based. solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
-
-
- <!-- Index Defaults
-
- Values here affect all index writers and act as a default
- unless overridden.
-
- WARNING: See also the <mainIndex> section below for parameters
- that overfor Solr's main Lucene index.
- -->
- <indexDefaults>
-
- <useCompoundFile>false</useCompoundFile>
-
- <mergeFactor>10</mergeFactor>
- <!-- Sets the amount of RAM that may be used by Lucene indexing
- for buffering added documents and deletions before they are
- flushed to the Directory. -->
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <maxFieldLength>10000</maxFieldLength>
- <writeLockTimeout>1000</writeLockTimeout>
- <commitLockTimeout>10000</commitLockTimeout>
-
- <!-- Expert: Merge Policy
-
- The Merge Policy in Lucene controls how merging is handled by
- Lucene. The default in Solr 3.3 is TieredMergePolicy.
-
- The default in 2.3 was the LogByteSizeMergePolicy,
- previous versions used LogDocMergePolicy.
-
- LogByteSizeMergePolicy chooses segments to merge based on
- their size. The Lucene 2.2 default, LogDocMergePolicy chose
- when to merge based on number of documents
-
- Other implementations of MergePolicy must have a no-argument
- constructor
- -->
- <!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
- -->
-
- <!-- Expert: Merge Scheduler
-
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- 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
-
- 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.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- (For backwards compatibility with Solr 1.2, 'simple' is the
- default if not specified.)
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>native</lockType>
-
- <!-- Expert: Controls how often Lucene loads terms into memory
- Default is 128 and is likely good for most everyone.
- -->
- <!-- <termIndexInterval>256</termIndexInterval> -->
- </indexDefaults>
-
- <!-- Main Index
-
- Values here override the values in the <indexDefaults> section
- for the main on disk index.
- -->
- <mainIndex>
-
- <useCompoundFile>false</useCompoundFile>
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <mergeFactor>10</mergeFactor>
-
- <!-- Unlock On Startup
-
- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be used
- with care.
-
- This is not needed if lock type is 'none' or 'single'
- -->
- <unlockOnStartup>false</unlockOnStartup>
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened.
- -->
- <reopenReaders>true</reopenReaders>
-
- <!-- Commit Deletion Policy
-
- Custom deletion policies can specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
-
- The standard 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="maxCommitsToKeep">1</str>
- <!-- The number of optimized commit points to be kept -->
- <str name="maxOptimizedCommitsToKeep">0</str>
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <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>
-
- </mainIndex>
-
- <!-- 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
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- AutoCommit
-
- Perform a <commit/> automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time that is allowed to pass
- since a document was added before automaticly
- triggering a new commit.
- -->
- <!--
- <autoCommit>
- <maxDocs>10000</maxDocs>
- <maxTime>1000</maxTime>
- </autoCommit>
- -->
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- 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.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
- </indexReaderFactory >
- -->
-
-
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- 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>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- 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.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="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.
- -->
- <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.
- -->
- <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.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- 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.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- 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.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- 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.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <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.
-
- Recommend values of 1-2 for read-only slaves, higher for
- masters w/o cache warming.
- -->
- <maxWarmingSearchers>2</maxWarmingSearchers>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect affects the behavior of requests such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and will result in consistent error handling and
- formatting for all types of requests.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests and fallback to using the legacy
- SolrServlet and it's Solr 1.1 style error formatting
- -->
- <requestDispatcher handleSelect="true" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- 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"
- multipartUploadLimitInKB="2048000" />
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- 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>
- </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.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- incoming queries will be dispatched to the correct handler
- based on the path or the qt (query type) param.
-
- Names starting with a '/' are accessed with the a path equal to
- the registered name. Names without a leading '/' are accessed
- with: http://host/app/[core/]select?qt=name
-
- If a /select request is processed with out a qt param
- specified, the requestHandler that declares default="true" will
- be used.
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="search" class="solr.SearchHandler" default="true">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="spellcheck.dictionary">text</str>
- <!-- omp = Only More Popular -->
- <str name="spellcheck.onlyMorePopular">false</str>
- <!-- exr = Extended Results -->
- <str name="spellcheck.extendedResults">true</str>
- <!-- The number of suggestions to return -->
- <str name="spellcheck.count">5</str>
- <str name="spellcheck">true</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
-
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
- <str name="title">Solritas</str>
-
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- <str name="mlt.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="mlt.fl">text,features,name,sku,id,manu,cat</str>
- <int name="mlt.count">3</int>
-
- <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="facet">on</str>
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">ipod</str>
- <str name="facet.query">GB</str>
- <str name="facet.mincount">1</str>
- <str name="facet.pivot">cat,inStock</str>
- <str name="facet.range">price</str>
- <int name="f.price.facet.range.start">0</int>
- <int name="f.price.facet.range.end">600</int>
- <int name="f.price.facet.range.gap">50</int>
- <str name="f.price.facet.range.other">after</str>
- <str name="facet.range">manufacturedate_dt</str>
- <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
- <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
- <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
- <str name="f.manufacturedate_dt.facet.range.other">before</str>
- <str name="f.manufacturedate_dt.facet.range.other">after</str>
-
-
- <!-- Highlighting defaults -->
- <str name="hl">on</str>
- <str name="hl.fl">text features name</str>
- <str name="f.name.hl.fragsize">0</str>
- <str name="f.name.hl.alternateField">name</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- <!--
- <str name="url-scheme">httpx</str>
- -->
- </requestHandler>
-
- <!-- XML Update Request Handler.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- The canonical Request Handler for Modifying the Index through
- commands specified using XML.
-
- 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'
- -->
- <requestHandler name="/update"
- class="solr.XmlUpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
- on each Update Request
- -->
- <!--
- <lst name="defaults">
- <str name="update.chain">dedupe</str>
- </lst>
- -->
- </requestHandler>
- <!-- Binary Update Request Handler
- http://wiki.apache.org/solr/javabin
- -->
- <requestHandler name="/update/javabin"
- class="solr.BinaryUpdateRequestHandler" />
-
- <!-- CSV Update Request Handler
- http://wiki.apache.org/solr/UpdateCSV
- -->
- <requestHandler name="/update/csv"
- class="solr.CSVRequestHandler"
- startup="lazy" />
-
- <!-- JSON Update Request Handler
- http://wiki.apache.org/solr/UpdateJSON
- -->
- <requestHandler name="/update/json"
- class="solr.JsonUpdateRequestHandler"
- startup="lazy" />
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <!-- All the main content goes into "text"... if you need to return
- the extracted text or do highlighting, use a stored field. -->
- <str name="fmap.content">text</str>
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided docuemnts. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- 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".
- -->
- <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="defaults">
- <str name="qt">search</str>
- <str name="q">solrpingquery</str>
- <str name="echoParams">all</str>
- </lst>
- </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="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "salves" 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/replication</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- </requestHandler>
-
-
- <!-- Search Components
-
- 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>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- 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"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text</str>
-
- <lst name="spellchecker">
- <str name="classname">solr.IndexBasedSpellChecker</str>
- <str name="name">text</str>
- <str name="field">text</str>
- <str name="buildOnOptimize">true</str>
- <str name="spellcheckIndexDir">./spellchecker</str>
- <!-- uncomment this to require terms to occur in 1% of the documents in order to be included in the dictionary
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- <str name="spellcheckIndexDir">spellcheckerJaro</str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="spellcheckIndexDir">spellcheckerFreq</str>
- <str name="comparatorClass">freq</str>
- <str name="buildOnCommit">true</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- 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
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- 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.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="spellcheck.onlyMorePopular">false</str>
- <str name="spellcheck.extendedResults">false</str>
- <str name="spellcheck.count">1</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector 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="tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- This relies on third party jars which are notincluded in the
- release. To use this component (and the "/clustering" handler)
- Those jars will need to be downloaded, and you'll need to set
- the solr.cluster.enabled system property when running solr...
-
- 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>
-
- <!-- 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
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- default="true"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <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"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- 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.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- -->
- <!--
- Custom response writers can be declared as needed...
- -->
- <!--
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
- -->
-
- <!-- 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.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
-
- <!-- configure a healthcheck file for servers behind a
- loadbalancer
- -->
- <!--
- <healthcheck type="file">server-enabled</healthcheck>
- -->
- </admin>
-
-</config>
+++ /dev/null
-pizza
-history
\ No newline at end of file
+++ /dev/null
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-#Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-s
-such
-t
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
-
+++ /dev/null
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaa => aaaa
-bbb => bbbb1 bbbb2
-ccc => cccc1,cccc2
-a\=>a => b\=>b
-a\,a => b\,b
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
projects / lui-solr.git / commitdiff