mirror of https://github.com/apache/lucene.git
371 lines
19 KiB
XML
371 lines
19 KiB
XML
<?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
|
|
|
|
NOTE: this schema includes many optional features and should not
|
|
be used for benchmarking.
|
|
-->
|
|
|
|
<schema name="example" 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: omitTf attribute introduced, true by default -->
|
|
|
|
<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"/>
|
|
|
|
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
|
currently supported on types that are sorted internally as strings.
|
|
- 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 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="integer" class="solr.IntField" omitNorms="true"/>
|
|
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
|
|
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
|
|
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
|
|
|
|
|
|
<!-- 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 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.
|
|
-->
|
|
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
|
|
|
<!--
|
|
Numeric field types that manipulate the value into trie encoded strings which are not
|
|
human readable in the internal form. Range searches on such fields use the fast Trie Range Queries
|
|
which are much faster than range searches on the SortableNumberField types.
|
|
|
|
For the fast range search to work, trie fields must be indexed. Trie fields are <b>not</b> sortable
|
|
in numerical order. Also, they cannot be used in function queries. If one needs sorting as well as
|
|
fast range search, one should create a copy field specifically for sorting. Same workaround is
|
|
suggested for using trie fields in function queries as well.
|
|
|
|
For each number being added to this field, multiple terms are generated as per the algorithm described in
|
|
org.apache.lucene.search.trie package description. The possible number of terms depend on the precisionStep
|
|
attribute and increase dramatically with higher precision steps (factor 2**precisionStep). The default
|
|
value of precisionStep is 8.
|
|
|
|
Note that if you use a precisionStep of 32 for int/float and 64 for long/double, then multiple terms
|
|
will not be generated, range search will be no faster than any other number field,
|
|
but sorting will be possible.
|
|
-->
|
|
<fieldType name="tint" class="solr.TrieField" type="integer" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
<fieldType name="tfloat" class="solr.TrieField" type="float" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
<fieldType name="tlong" class="solr.TrieField" type="long" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
<fieldType name="tdouble" class="solr.TrieField" type="double" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
|
|
<fieldType name="tdouble4" class="solr.TrieField" type="double" precisionStep="4" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
|
|
<!--
|
|
This date field manipulates the value into a trie encoded strings for fast range searches. They follow the
|
|
same format and semantics as the normal DateField and support the date math syntax except that they are
|
|
not sortable and cannot be used in function queries.
|
|
-->
|
|
<fieldType name="tdate" class="solr.TrieField" type="date" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
|
|
|
|
|
|
<!-- The "RandomSortField" is not used to store or search any
|
|
data. You can declare fields of this type it in your schema
|
|
to generate psuedo-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 differend 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.
|
|
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
|
|
WordDelim parts) are removed.
|
|
-->
|
|
<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"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</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"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</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"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!--
|
|
Setup simple analysis for spell checking
|
|
-->
|
|
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- charFilter + "CharStream aware" WhitespaceTokenizer -->
|
|
<!--
|
|
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
|
|
<analyzer>
|
|
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
|
<tokenizer class="solr.CharStreamAwareWhitespaceTokenizerFactory"/>
|
|
</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 refrences to portions of the orriginal
|
|
string matched by the pattern.
|
|
|
|
See the Java Regular Expression documentation for more
|
|
infomation 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>
|
|
|
|
|
|
<!-- 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" class="solr.StrField" />
|
|
|
|
</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.
|
|
-->
|
|
|
|
<field name="messageId" type="string" indexed="true" stored="true" required="true" omitNorms="true" />
|
|
<field name="subject" type="string" indexed="true" stored="true" omitNorms="true" />
|
|
<field name="from" type="string" indexed="true" stored="true" omitNorms="true"/>
|
|
<field name="sentDate" type="date" indexed="true" stored="true"/>
|
|
<field name="xMailer" type="string" indexed="true" stored="true" omitNorms="true"/>
|
|
|
|
<field name="allTo" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
<field name="flags" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
<field name="content" type="text" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
<field name="attachment" type="text" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
<field name="attachmentNames" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
|
|
<field name="catchAllField" type="text" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
|
|
</fields>
|
|
|
|
<copyField source="content" dest="catchAllField"/>
|
|
<copyField source="attachmentNames" dest="catchAllField"/>
|
|
<copyField source="attachment" dest="catchAllField"/>
|
|
<copyField source="subject" dest="catchAllField"/>
|
|
<copyField source="allTo" dest="catchAllField"/>
|
|
|
|
<!-- The unique key, Note that some mail servers may not send the message-id or they may send duplicate ones -->
|
|
<uniqueKey>messageId</uniqueKey>
|
|
|
|
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
|
<defaultSearchField>catchAllField</defaultSearchField>
|
|
|
|
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
|
<solrQueryParser defaultOperator="OR"/>
|
|
|
|
</schema>
|