You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by yo...@apache.org on 2016/07/08 19:45:58 UTC
[2/4] lucene-solr:branch_6x: SOLR-9163: sync basic_configs w/
data_driven_schema_configs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/managed-schema b/solr/server/solr/configsets/basic_configs/conf/managed-schema
index ba24bf1..95a9027 100644
--- a/solr/server/solr/configsets/basic_configs/conf/managed-schema
+++ b/solr/server/solr/configsets/basic_configs/conf/managed-schema
@@ -27,10 +27,26 @@
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 ConcurrentUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
-->
-<schema name="example" version="1.6">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
+<schema name="example-basic" version="1.6">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
version="x.y" is Solr's version number for the schema syntax and
semantics. It should not normally be changed by applications.
@@ -46,13 +62,12 @@
1.5: omitNorms defaults to true for primitive field types
(int, float, boolean, string...)
1.6: useDocValuesAsStored defaults to true.
- -->
-
+ -->
- <!-- Valid attributes for fields:
+ <!-- Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a field type from the
- fieldTypes
+ fieldTypes section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
docValues: true if this field should have doc values. Doc values are
@@ -82,99 +97,104 @@
value does not exist
default: a value that should be used if no value is specified
when adding a document.
- -->
+ -->
- <!-- field names should consist of alphanumeric or underscore characters only and
+ <!-- field names should consist of alphanumeric or underscore characters only and
not start with a digit. This is not currently strictly enforced,
but other field names will not have first class support from all components
and back compatibility is not guaranteed. Names with both leading and
trailing underscores (e.g. _version_) are reserved.
- -->
+ -->
- <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
- or Solr won't start. _version_ and update log are required for SolrCloud
- -->
- <field name="_version_" type="long" indexed="true" stored="false" />
-
- <!-- points to the root document of a block of nested documents. Required for nested
- document support, may be removed otherwise
- -->
- <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
-
- <!-- Only remove the "id" field if you have a very good reason to. While not strictly
- required, it is highly recommended. A <uniqueKey> is present in almost all Solr
- installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
- Do NOT change the type and apply index-time analysis to the <uniqueKey> as it will likely
- make routing in SolrCloud and document replacement in general fail. Limited _query_ time
- analysis is possible as long as the indexing process is guaranteed to index the term
- in a compatible way. Any analysis applied to the <uniqueKey> should _not_ produce multiple
- tokens
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
-
- <!-- Dynamic field definitions allow using convention over configuration
+ <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+ id, _version_, and _text_. All other fields will be type guessed and added via the
+ "add-unknown-fields-to-the-schema" update request processor chain declared
+ in solrconfig.xml.
+
+ Note that many dynamic fields are also defined - you can use them to specify a
+ field's type via field naming conventions - see below.
+
+ WARNING: The _text_ catch-all field will significantly increase your index size.
+ If you don't need it, consider removing it and the corresponding copyField directive.
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="_version_" type="long" indexed="true" stored="false"/>
+ <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+ <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <!-- <copyField source="*" dest="_text_"/> -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
for fields via the specification of patterns to match field names.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end. -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
-
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" useDocValuesAsStored="false" />
-
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
-
- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
+
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
+ <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" useDocValuesAsStored="false" />
+
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
+ <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields for faster range queries -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+ <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+ unknown fields indexed and/or stored by default
+
+ NB: use of "*" dynamic fields will disable field type guessing and adding
+ unknown fields to the schema. -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
- <!-- Field to use to determine and enforce document uniqueness.
+ <!-- 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>
+ -->
+ <uniqueKey>id</uniqueKey>
- <!-- 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 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="sourceFieldName" dest="destinationFieldName"/>
+ -->
- <!--
- <copyField source="title" dest="text"/>
- <copyField source="body" dest="text"/>
- -->
-
<!-- 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
@@ -188,15 +208,18 @@
single-valued and either required or have a default value.
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+ <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
currently supported on types that are sorted internally as strings
and on numeric types.
- This includes "string","boolean", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" variants.
+ This includes "string","boolean", and, as of 3.5 (and 4.x),
+ int, float, long, date, double, including the "Trie" variants.
- 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).
@@ -219,6 +242,11 @@
<fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
@@ -233,6 +261,11 @@
<fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+ <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
<!-- 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
@@ -257,10 +290,13 @@
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+ <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldType name="binary" class="solr.BinaryField"/>
@@ -299,6 +335,7 @@
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -307,10 +344,11 @@
<!-- A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases. At query time only, it
- also applies synonyms. -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms.
+ -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
@@ -332,6 +370,7 @@
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
+ <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
@@ -343,13 +382,13 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
+ -->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
@@ -358,26 +397,27 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
+ -->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -389,7 +429,7 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -401,7 +441,7 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -411,6 +451,7 @@
<!-- 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. -->
+ <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -427,14 +468,16 @@
</fieldType>
<!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries. -->
+ each token, to enable more efficient leading wildcard queries.
+ -->
+ <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
@@ -444,40 +487,16 @@
</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">
+ <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
+ <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back references to portions of the original
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- information on pattern and replacement string syntax.
-
- http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
+ <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
@@ -485,6 +504,34 @@
</analyzer>
</fieldType>
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
@@ -500,6 +547,7 @@
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
+ <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
@@ -510,16 +558,9 @@
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
-->
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
- special relevancy modes: score=overlapRatio|area|area2D (local-param to the query). DocValues is recommended for
- relevancy. -->
- <fieldType name="bbox" class="solr.BBoxField"
- geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
- <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" useDocValuesAsStored="false" stored="false"/>
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
@@ -529,7 +570,436 @@
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
+ -->
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes \ufeef to \ufef1, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your query
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ OR if you would like to optimize for recall (default).
+ -->
+ <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (\u8f9e\u66f8\u5f62) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ThaiTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/params.json b/solr/server/solr/configsets/basic_configs/conf/params.json
new file mode 100644
index 0000000..06114ef
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/params.json
@@ -0,0 +1,20 @@
+{"params":{
+ "query":{
+ "defType":"edismax",
+ "q.alt":"*:*",
+ "rows":"10",
+ "fl":"*,score",
+ "":{"v":0}
+ },
+ "facets":{
+ "facet":"on",
+ "facet.mincount": "1",
+ "":{"v":0}
+ },
+ "velocity":{
+ "wt": "velocity",
+ "v.template":"browse",
+ "v.layout": "layout",
+ "":{"v":0}
+ }
+}}
\ No newline at end of file