forked from D-Net/dnet-hadoop
549 lines
28 KiB
HTML
549 lines
28 KiB
HTML
<?xml version="1.0" encoding="UTF-8" ?>
|
|
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
|
|
<xsl:output omit-xml-declaration="yes" indent="yes"/>
|
|
|
|
<xsl:template match="//FIELDS">
|
|
|
|
<xsl:param name="textFieldType" select="string('text_common')"/>
|
|
<xsl:variable name="smallcase" select="'abcdefghijklmnopqrstuvwxyz'"/>
|
|
<xsl:variable name="uppercase" select="'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"/>
|
|
|
|
<!--
|
|
D-Net index schema template
|
|
|
|
CHANGELOG
|
|
|
|
0.1 : first release
|
|
0.2 : added preserveOriginal="1" for text field type in the index analyzer and catenateWords="1" for the query analyzer
|
|
0.3 : changed language for SnowballPorterFilterFactory to language="German2" (index/query) in the text field type
|
|
0.4 : added solr.ASCIIFoldingFilterFactory filter (index/query) in the text field type
|
|
0.5 : added long_keyword field type, to be used for objIdentifiers
|
|
0.6 : added field types for spellchecking
|
|
0.7 : added parameter for text field type
|
|
0.8 : added field _version_, needed by Solr 4.0.0 for the transaction log
|
|
0.9 : added type: text_en_splitting
|
|
0.91 : added type: ngramtext
|
|
0.92 : added schema optimizations, removing unnecessary stored fields
|
|
0.93 : added attribute preserveOriginal="1" to fieldtype ngramtext (query analysis) to improve matches
|
|
0.94 : updated and simplified ngramtext fieldtype
|
|
0.95 : update to solr 4.4, removed attribute "compress" from field definition, ngramfield doesn't support NGramFilterFactory anymore
|
|
0.96 : update to solr 4.9
|
|
0.97 : introduced field type string_ci supporting case insensitivity.
|
|
1.0 : updated to solr 6.6.0
|
|
-->
|
|
<schema name="dnet" version="1.0">
|
|
|
|
<!-- Valid attributes for fields:
|
|
name: mandatory - the name for the field
|
|
type: mandatory - the name of a field type from the
|
|
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
|
|
useful (required, if you are using *Point fields) for faceting,
|
|
grouping, sorting and function queries. Doc values will make the index
|
|
faster to load, more NRT-friendly and more memory-efficient.
|
|
They however come with some limitations: they are currently only
|
|
supported by StrField, UUIDField, all Trie*Fields and *PointFields,
|
|
and depending on the field type, they might require the field to be
|
|
single-valued, be required or have a default value (check the
|
|
documentation of the field type you're interested in for more information)
|
|
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.
|
|
Norms are omitted for primitive (non-analyzed) types by default.
|
|
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.
|
|
required: The field is required. It will throw an error if the
|
|
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
|
|
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.
|
|
-->
|
|
|
|
<xsl:for-each select="./FIELD">
|
|
<xsl:variable name="fieldname" select="translate(@name, $uppercase, $smallcase)"/>
|
|
<xsl:variable name="fieldtype">
|
|
<xsl:choose>
|
|
<xsl:when test="@type"><xsl:value-of select="@type"/></xsl:when>
|
|
<xsl:when test="@tokenizable='false'">string</xsl:when>
|
|
<xsl:otherwise>
|
|
<xsl:value-of select="$textFieldType"/>
|
|
</xsl:otherwise>
|
|
</xsl:choose>
|
|
</xsl:variable>
|
|
<xsl:variable name="isMultivalued">
|
|
<xsl:choose>
|
|
<xsl:when test="@multivalued='false'">false</xsl:when>
|
|
<xsl:otherwise>true</xsl:otherwise>
|
|
</xsl:choose>
|
|
</xsl:variable>
|
|
<xsl:variable name="isStored">
|
|
<xsl:choose>
|
|
<xsl:when test="@stored='true'">true</xsl:when>
|
|
<xsl:otherwise>false</xsl:otherwise>
|
|
</xsl:choose>
|
|
</xsl:variable>
|
|
|
|
<field name="{$fieldname}" type="{$fieldtype}" indexed="{@indexable}" stored="{normalize-space($isStored)}" multiValued="{normalize-space($isMultivalued)}"/>
|
|
</xsl:for-each>
|
|
|
|
<field name="__indexrecordidentifier" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
|
|
|
|
<field name="__deleted" type="boolean" indexed="true" stored="false" default="false" omitNorms="true" omitTermFreqAndPositions="true"/>
|
|
|
|
<field name="__dsid" type="string" indexed="true" stored="true" omitNorms="true" omitTermFreqAndPositions="true"/>
|
|
|
|
<field name="__dsversion" type="pdate" indexed="true" stored="true" omitNorms="true" omitTermFreqAndPositions="true"/>
|
|
|
|
<field name="__result" type="string" indexed="false" stored="true" multiValued="false" docValues="false"/>
|
|
|
|
<field name="__all" type="{$textFieldType}" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
|
|
|
|
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
|
|
|
|
<!-- field for ping -->
|
|
<field name="text" type="{$textFieldType}" indexed="false" stored="false"/>
|
|
|
|
<!-- Field to use to determine and enforce document uniqueness.
|
|
Unless this field is marked with required="false", it will be a required field
|
|
-->
|
|
<uniqueKey>__indexrecordidentifier</uniqueKey>
|
|
|
|
<xsl:for-each select="./FIELD[@copy = 'true']">
|
|
<xsl:variable name="fieldname" select="translate(@name, $uppercase, $smallcase)"/>
|
|
<copyField source="{$fieldname}" dest="__all"/>
|
|
</xsl:for-each>
|
|
|
|
<!-- 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"/>
|
|
-->
|
|
|
|
<!-- field type definitions. The "name" attribute is
|
|
just a label to be used by field definitions. The "class"
|
|
attribute and any other attributes determine the real
|
|
behavior of the fieldType.
|
|
Class names starting with "solr" refer to java classes in a
|
|
standard package such as org.apache.solr.analysis
|
|
-->
|
|
|
|
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
|
It supports doc values but in that case the field needs to be
|
|
single-valued and either required or have a default value.
|
|
-->
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" 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", "int", "float", "long", "date", "double",
|
|
including the "Trie" and "Point" 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).
|
|
- 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.
|
|
-->
|
|
|
|
<!--
|
|
Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
|
|
search time and at index time, but some features are still not supported.
|
|
Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
|
|
-->
|
|
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
|
|
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
|
|
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
|
|
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
|
|
|
|
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
|
|
|
|
<!--
|
|
Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
|
|
tint/tfloat/tlong/tdouble types.
|
|
-->
|
|
<fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<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
|
|
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.
|
|
|
|
Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
|
|
-->
|
|
<fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
|
<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
|
|
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 TrieDateField javadocs for more information.
|
|
-->
|
|
<!-- KD-tree versions of date fields -->
|
|
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
|
|
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
|
|
|
<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"/>
|
|
|
|
<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"/>
|
|
|
|
<!-- 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
|
|
or function 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 field name in the request.
|
|
-->
|
|
<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.
|
|
Example:
|
|
<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 -->
|
|
<!-- <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/> -->
|
|
|
|
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="ngramtext" class="solr.TextField">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="25"/>
|
|
<filter class="solr.TrimFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<fieldType name="personName" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory" />
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="personNamePrefix" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
<filter class="solr.NGramFilterFactory" minGramSize="1" maxGramSize="30" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<!-- A general text field that has reasonable, generic
|
|
cross-language defaults: it tokenizes with StandardTokenizer,
|
|
removes stop words from case-insensitive "stopwords.txt"
|
|
(empty by default), and down cases. At query time only, it
|
|
also applies synonyms.
|
|
-->
|
|
<fieldType name="text_common" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<!-- in this example, we will only use synonyms at query time
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.FlattenGraphFilterFactory"/>
|
|
-->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<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
|
|
WordDelimiterGraphFilter 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"/>
|
|
<!-- in this example, we will only use synonyms at query time
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
-->
|
|
<!-- Case insensitive stop word removal.
|
|
-->
|
|
<filter class="solr.StopFilterFactory"
|
|
ignoreCase="true"
|
|
words="stopwords.txt"
|
|
/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory"
|
|
ignoreCase="true"
|
|
words="stopwords.txt"
|
|
/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
|
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
|
<!-- <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 type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
|
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
|
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Just like text_common except it reverses the characters of
|
|
each token, to enable more efficient leading wildcard queries.
|
|
-->
|
|
<!-- <dynamicField name="*_txt_rev" type="text_common_rev" indexed="true" stored="true"/> -->
|
|
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
|
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/> -->
|
|
<fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!--
|
|
Example of using PathHierarchyTokenizerFactory at index time, so
|
|
queries for paths match documents at that path, or in descendent paths
|
|
-->
|
|
<!-- <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" />
|
|
|
|
<!-- This point type indexes the coordinates as separate fields (subFields)
|
|
If subFieldType is defined, it references a type, and a dynamic field
|
|
definition is created matching *___<typename>. Alternately, if
|
|
subFieldSuffix is defined, that is used to create the subFields.
|
|
Example: if subFieldType="double", then the coordinates would be
|
|
indexed in fields myloc_0___double,myloc_1___double.
|
|
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
|
in fields myloc_0_d,myloc_1_d
|
|
The subFields are an implementation detail of the fieldType, and end
|
|
users normally should not need to know about them.
|
|
-->
|
|
<!-- <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 filters and distance sorting. -->
|
|
<fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
|
|
|
|
<!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
|
|
For more information about this and other Spatial fields new to Solr 4, see:
|
|
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
|
|
-->
|
|
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
|
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
|
|
|
|
</schema>
|
|
</xsl:template>
|
|
</xsl:stylesheet> |