bachir/solr-materio
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

created tow cores, one for base, one for autocomplete, since sapi solr does not support mutliple index per core

Browse Source
This commit is contained in:
Bachir Soussi Chiadmi 2020-02-18 15:44:12 +01:00
parent dbba1da4e8
commit a84090562c
25 changed files with 2695 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
materio/core.properties
View File

@ -1 +1,6 @@
name=materio
#Written by CorePropertiesLocator
#Tue Feb 18 14:12:52 UTC 2020
schema=schema.xml
dataDir=data
name=materio_base
config=solrconfig.xml

164
materio_autocomplete/conf/accents_en.txt Normal file
View File

@ -0,0 +1,164 @@
# À => A
"\u00C0" => "A"
# Á => A
"\u00C1" => "A"
# Â => A
"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Ą => A
"\u0104" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
"\u00C7" => "C"
# Ć => C
"\U0106" => "C"
# È => E
"\u00C8" => "E"
# É => E
"\u00C9" => "E"
# Ê => E
"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ę => E
"\u0118" => "E"
# Ì => I
"\u00CC" => "I"
# Í => I
"\u00CD" => "I"
# Î => I
"\u00CE" => "I"
# Ï => I
"\u00CF" => "I"
# IJ => IJ
"\u0132" => "IJ"
# Ð => D
"\u00D0" => "D"
# Ł => L
"\u0141" => "L"
# Ñ => N
"\u00D1" => "N"
# Ń => N
"\u0143" => "N"
# Ò => O
"\u00D2" => "O"
# Ó => O
"\u00D3" => "O"
# Ô => O
"\u00D4" => "O"
# Õ => O
"\u00D5" => "O"
# Ö => O
"\u00D6" => "O"
# Ø => O
"\u00D8" => "O"
# Π=> OE
"\u0152" => "OE"
# Þ
"\u00DE" => "TH"
# Ù => U
"\u00D9" => "U"
# Ú => U
"\u00DA" => "U"
# Û => U
"\u00DB" => "U"
# Ü => U
"\u00DC" => "U"
# Ý => Y
"\u00DD" => "Y"
# Ÿ => Y
"\u0178" => "Y"
# à => a
"\u00E0" => "a"
# á => a
"\u00E1" => "a"
# â => a
"\u00E2" => "a"
# ã => a
"\u00E3" => "a"
# ä => a
"\u00E4" => "a"
# å => a
"\u00E5" => "a"
# æ => ae
"\u00E6" => "ae"
# ç => c
"\u00E7" => "c"
# è => e
"\u00E8" => "e"
# é => e
"\u00E9" => "e"
# ê => e
"\u00EA" => "e"
# ë => e
"\u00EB" => "e"
# ì => i
"\u00EC" => "i"
# í => i
"\u00ED" => "i"
# î => i
"\u00EE" => "i"
# ï => i
"\u00EF" => "i"
# ij => ij
"\u0133" => "ij"
# ð => d
"\u00F0" => "d"
# ñ => n
"\u00F1" => "n"
# ò => o
"\u00F2" => "o"
# ó => o
"\u00F3" => "o"
# ô => o
"\u00F4" => "o"
# õ => o
"\u00F5" => "o"
# ö => o
"\u00F6" => "o"
# ø => o
"\u00F8" => "o"
# œ => oe
"\u0153" => "oe"
# ß => ss
"\u00DF" => "ss"
# Ś => S
"\u015a" => "S"
# þ => th
"\u00FE" => "th"
# ù => u
"\u00F9" => "u"
# ú => u
"\u00FA" => "u"
# û => u
"\u00FB" => "u"
# ü => u
"\u00FC" => "u"
# ý => y
"\u00FD" => "y"
# ÿ => y
"\u00FF" => "y"
# Ź => Z
"\u0179" => "Z"
# Ż => Z
"\u017b" => "Z"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => st
"\uFB05" => "st"
# st => st
"\uFB06" => "st"

164
materio_autocomplete/conf/accents_fr.txt Normal file
View File

@ -0,0 +1,164 @@
# À => A
#"\u00C0" => "A"
# Á => A
#"\u00C1" => "A"
# Â => A
#"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Ą => A
"\u0104" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
#"\u00C7" => "C"
# Ć => C
"\U0106" => "C"
# È => E
#"\u00C8" => "E"
# É => E
#"\u00C9" => "E"
# Ê => E
#"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ę => E
"\u0118" => "E"
# Ì => I
#"\u00CC" => "I"
# Í => I
#"\u00CD" => "I"
# Î => I
#"\u00CE" => "I"
# Ï => I
"\u00CF" => "I"
# IJ => IJ
"\u0132" => "IJ"
# Ð => D
"\u00D0" => "D"
# Ł => L
"\u0141" => "L"
# Ñ => N
"\u00D1" => "N"
# Ń => N
"\u0143" => "N"
# Ò => O
#"\u00D2" => "O"
# Ó => O
#"\u00D3" => "O"
# Ô => O
#"\u00D4" => "O"
# Õ => O
"\u00D5" => "O"
# Ö => O
"\u00D6" => "O"
# Ø => O
"\u00D8" => "O"
# Π=> OE
"\u0152" => "OE"
# Þ
"\u00DE" => "TH"
# Ù => U
#"\u00D9" => "U"
# Ú => U
#"\u00DA" => "U"
# Û => U
#"\u00DB" => "U"
# Ü => U
"\u00DC" => "U"
# Ý => Y
#"\u00DD" => "Y"
# Ÿ => Y
"\u0178" => "Y"
# à => a
#"\u00E0" => "a"
# á => a
#"\u00E1" => "a"
# â => a
#"\u00E2" => "a"
# ã => a
"\u00E3" => "a"
# ä => a
"\u00E4" => "a"
# å => a
"\u00E5" => "a"
# æ => ae
"\u00E6" => "ae"
# ç => c
#"\u00E7" => "c"
# è => e
#"\u00E8" => "e"
# é => e
#"\u00E9" => "e"
# ê => e
#"\u00EA" => "e"
# ë => e
"\u00EB" => "e"
# ì => i
#"\u00EC" => "i"
# í => i
#"\u00ED" => "i"
# î => i
#"\u00EE" => "i"
# ï => i
"\u00EF" => "i"
# ij => ij
"\u0133" => "ij"
# ð => d
"\u00F0" => "d"
# ñ => n
"\u00F1" => "n"
# ò => o
#"\u00F2" => "o"
# ó => o
#"\u00F3" => "o"
# ô => o
#"\u00F4" => "o"
# õ => o
"\u00F5" => "o"
# ö => o
"\u00F6" => "o"
# ø => o
"\u00F8" => "o"
# œ => oe
"\u0153" => "oe"
# ß => ss
"\u00DF" => "ss"
# Ś => S
"\u015a" => "S"
# þ => th
"\u00FE" => "th"
# ù => u
#"\u00F9" => "u"
# ú => u
#"\u00FA" => "u"
# û => u
#"\u00FB" => "u"
# ü => u
"\u00FC" => "u"
# ý => y
#"\u00FD" => "y"
# ÿ => y
"\u00FF" => "y"
# Ź => Z
"\u0179" => "Z"
# Ż => Z
"\u017b" => "Z"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => st
"\uFB05" => "st"
# st => st
"\uFB06" => "st"

148
materio_autocomplete/conf/accents_und.txt Normal file
View File

@ -0,0 +1,148 @@
# À => A
"\u00C0" => "A"
# Á => A
"\u00C1" => "A"
# Â => A
"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
"\u00C7" => "C"
# È => E
"\u00C8" => "E"
# É => E
"\u00C9" => "E"
# Ê => E
"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ì => I
"\u00CC" => "I"
# Í => I
"\u00CD" => "I"
# Î => I
"\u00CE" => "I"
# Ï => I
"\u00CF" => "I"
# IJ => IJ
"\u0132" => "IJ"
# Ð => D
"\u00D0" => "D"
# Ñ => N
"\u00D1" => "N"
# Ò => O
"\u00D2" => "O"
# Ó => O
"\u00D3" => "O"
# Ô => O
"\u00D4" => "O"
# Õ => O
"\u00D5" => "O"
# Ö => O
"\u00D6" => "O"
# Ø => O
"\u00D8" => "O"
# Π=> OE
"\u0152" => "OE"
# Þ
"\u00DE" => "TH"
# Ù => U
"\u00D9" => "U"
# Ú => U
"\u00DA" => "U"
# Û => U
"\u00DB" => "U"
# Ü => U
"\u00DC" => "U"
# Ý => Y
"\u00DD" => "Y"
# Ÿ => Y
"\u0178" => "Y"
# à => a
"\u00E0" => "a"
# á => a
"\u00E1" => "a"
# â => a
"\u00E2" => "a"
# ã => a
"\u00E3" => "a"
# ä => a
"\u00E4" => "a"
# å => a
"\u00E5" => "a"
# æ => ae
"\u00E6" => "ae"
# ç => c
"\u00E7" => "c"
# è => e
"\u00E8" => "e"
# é => e
"\u00E9" => "e"
# ê => e
"\u00EA" => "e"
# ë => e
"\u00EB" => "e"
# ì => i
"\u00EC" => "i"
# í => i
"\u00ED" => "i"
# î => i
"\u00EE" => "i"
# ï => i
"\u00EF" => "i"
# ij => ij
"\u0133" => "ij"
# ð => d
"\u00F0" => "d"
# ñ => n
"\u00F1" => "n"
# ò => o
"\u00F2" => "o"
# ó => o
"\u00F3" => "o"
# ô => o
"\u00F4" => "o"
# õ => o
"\u00F5" => "o"
# ö => o
"\u00F6" => "o"
# ø => o
"\u00F8" => "o"
# œ => oe
"\u0153" => "oe"
# ß => ss
"\u00DF" => "ss"
# þ => th
"\u00FE" => "th"
# ù => u
"\u00F9" => "u"
# ú => u
"\u00FA" => "u"
# û => u
"\u00FB" => "u"
# ü => u
"\u00FC" => "u"
# ý => y
"\u00FD" => "y"
# ÿ => y
"\u00FF" => "y"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => st
"\uFB05" => "st"
# st => st
"\uFB06" => "st"

27
materio_autocomplete/conf/elevate.xml Normal file
View File

@ -0,0 +1,27 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!--
This file allows you to boost certain search items to the top of search
results. You can find out an item's ID by searching directly on the Solr
server. Search API generally constructs item IDs (esp. for entities) as:
$document->id = "$site_hash-$index_id-$datasource:$entity_id:$language_id";
If you want this file to be automatically re-loaded when a Solr commit takes
place (e.g., if you have an automatic script active which updates elevate.xml
according to newly-indexed data), place it into Solr's data/ directory.
Otherwise, place it with the other configuration files into the conf/
directory.
See http://wiki.apache.org/solr/QueryElevationComponent for more information.
-->
<elevate>
<!-- Example for ranking the node #789 first in searches for "example query": -->
<!--
<query text="example query">
<doc id="ab12cd34-site_index-entity:789:en" />
</query>
-->
<!-- Multiple <query> elements can be specified, contained in one <elevate>. -->
<!-- <query text="...">...</query> -->
</elevate>

1
materio_autocomplete/conf/nouns_fr.txt Normal file
View File

@ -0,0 +1 @@

1
materio_autocomplete/conf/protwords_en.txt Normal file
View File

@ -0,0 +1 @@

1
materio_autocomplete/conf/protwords_fr.txt Normal file
View File

@ -0,0 +1 @@

1
materio_autocomplete/conf/protwords_und.txt Normal file
View File

@ -0,0 +1 @@

474
materio_autocomplete/conf/schema.xml Normal file
View File

@ -0,0 +1,474 @@
<?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.
-->
<!DOCTYPE schema [
<!ENTITY extrafields SYSTEM "schema_extra_fields.xml">
<!ENTITY extratypes SYSTEM "schema_extra_types.xml">
]>
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
PERFORMANCE NOTE: this schema includes many optional features and should not
be used for benchmarking. To improve performance one could
- set stored="false" for all fields possible (esp large fields) when you
only need to search on the field but don't need to return the original
value.
- set indexed="false" if you don't need to search on the field, but only
return the field as a result of searching on other indexed fields.
- remove all unneeded copyField statements
- for best index size and searching performance, set "index" to false
for all general text fields, use copyField to copy them to the
catchall "text" field, and use that for searching.
- For maximum indexing performance, use the ConcurrentUpdateSolrServer
java client.
- Remember to run the JVM in server mode, and use a higher logging level
that avoids logging every request
-->
<schema name="drupal-8.3.8-solr-8.x" 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.
1.0: multiValued attribute did not exist, all fields are multiValued
by nature
1.1: multiValued attribute introduced, false by default
1.2: omitTermFreqAndPositions attribute introduced, true by default
except for text fields.
1.3: removed optional field compress feature
1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
behavior when a single string produces multiple tokens. Defaults
to off for version >= 1.4
1.5: omitNorms defaults to true for primitive field types
(int, float, boolean, string...)
1.6: useDocValuesAsStored defaults to true.
-->
<!-- Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a field type from the
fieldTypes
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 *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.
termPayloads: Store payload 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.
-->
<!-- 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
-->
<!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
<field name="_version_" type="plong" indexed="false" 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".
-->
<!-- The document id is usually derived from a site-specific key (hash) and the
entity type and ID like:
Search Api 7.x:
The format used is $document->id = $index_id . '-' . $item_id
Search Api 8.x:
The format used is $document->id = $site_hash . '-' . $index_id . '-' . $item_id
Apache Solr Search Integration 7.x:
The format used is $document->id = $site_hash . '/' . $entity_type . '/' . $entity->id;
-->
<!-- The Highlighter Component requires the id field to be "stored" even if docValues are set. -->
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" docValues="true"/>
<!-- Search Api specific fields -->
<!-- index_id is the machine name of the search index this entry belongs to. -->
<field name="index_id" type="string" indexed="true" stored="false" multiValued="false" docValues="true"/>
<!-- Here, default is used to create a "timestamp" field indicating
when each document was indexed.-->
<field name="timestamp" type="pdate" indexed="true" stored="false" default="NOW" multiValued="false" docValues="true"/>
<field name="site" type="string" indexed="true" stored="false" multiValued="false" docValues="true"/>
<field name="hash" type="string" indexed="true" stored="false" multiValued="false" docValues="true"/>
<field name="boost_document" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
<field name="boost_term" type="boost_term_payload" indexed="true" stored="false" multiValued="true"/>
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
Longer patterns will be matched first. if equal size patterns
both match, the first appearing in the schema will be used. -->
<!-- For 2 and 3 letter prefix dynamic fields, the 1st letter indicates the data type and
the last letter is 's' for single valued, 'm' for multi-valued -->
<!-- We use plong for integer since 64 bit ints are now common in PHP. -->
<dynamicField name="is_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="im_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<!-- List of floats can be saved in a regular float field -->
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="fm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- List of doubles can be saved in a regular double field -->
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="pm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- List of booleans can be saved in a regular boolean field -->
<dynamicField name="bm_*" type="boolean" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<!-- Regular text (without processing) can be stored in a string field-->
<dynamicField name="ss_*" type="string" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<!-- For field types using SORTED_SET, multiple identical entries are collapsed into a single value.
Thus if I insert values 4, 5, 2, 4, 1, my return will be 1, 2, 4, 5 when enabling docValues.
If you need to preserve the order and duplicate entries, consider to store the values as zm_* (twice). -->
<dynamicField name="sm_*" type="string" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<!-- Special-purpose text fields -->
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="dm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- This field is used to store date ranges -->
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="drm_*" type="date_range" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="its_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="itm_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ftm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ptm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
a small image in a search result using the data URI scheme -->
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ddm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="hm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="htm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- Unindexed string fields that can be used to store values that won't be searchable -->
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
<!-- Fields for location searches.
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
<dynamicField name="points_*" type="point" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="pointm_*" type="point" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="locs_*" type="location" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="locm_*" type="location" indexed="true" stored="true" multiValued="true"/>
<!-- GeoHash fields are deprecated. LatLonPointSpatial fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="geos_*" type="location" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="geom_*" type="location" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="bboxs_*" type="bbox" indexed="true" stored="true" multiValued="false" />
<dynamicField name="bboxm_*" type="bbox" indexed="true" stored="true" multiValued="true" />
<dynamicField name="rpts_*" type="location_rpt" indexed="true" stored="true" multiValued="false" />
<dynamicField name="rptm_*" type="location_rpt" indexed="true" stored="true" multiValued="true" />
<!-- External file fields -->
<dynamicField name="eff_*" type="file"/>
<!-- A random sort field -->
<dynamicField name="random_*" type="random" indexed="true" stored="true"/>
<!-- This field is used to store access information (e.g. node access grants), as opposed to field data -->
<dynamicField name="access_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
<!-- The following causes solr 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" />
<!-- 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"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField"/>
<!-- 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", "pint", "pfloat", "plong", "pdate", "pdouble".
- 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 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"/>
<!--
The ExternalFileField type gets values from an external file instead of the
index. This is useful for data such as rankings that might change frequently
and require different update frequencies than the documents they are
associated with.
-->
<fieldType name="file" keyField="id" defVal="1" stored="false" indexed="false" class="solr.ExternalFileField"/>
<!-- 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 DatePointField 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"/>
<!-- A date range field -->
<fieldType name="date_range" class="solr.DateRangeField"/>
<!--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 -->
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="boost_term_payload" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. Alternately, if
subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<!-- In Drupal we only use prefixes for dynmaic fields. Tht might change in
the future but for now we keep this pattern.
-->
<fieldType name="point" class="solr.PointType" dimension="2" subFieldType="pdouble"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
<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" />
<!-- 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.DoublePointField" docValues="true" stored="false"/>
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
amountLongSuffix: Required. Refers to a dynamic field for the raw amount sub-field.
The dynamic field must have a field type that extends LongValueFieldType.
Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
codeStrSuffix: Required. Refers to a dynamic field for the currency code sub-field.
The dynamic field must have a field type that extends StrField.
Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
providerClass: Lets you plug in other exchange provider backend:
solr.FileExchangeRateProvider is the default and takes one parameter:
currencyConfig: name of an xml file holding exchange rates
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
-->
<!-- <fieldType name="currency" class="solr.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns"
defaultCurrency="USD" currencyConfig="currency.xml" /> -->
<!-- Following is a dynamic way to include other fields, added by other contrib modules -->
&extrafields;
<!-- Following is a dynamic way to include other types, added by other contrib modules -->
&extratypes;
<!-- 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>
<!-- 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>

102
materio_autocomplete/conf/schema_extra_fields.xml Normal file
View File

@ -0,0 +1,102 @@
<dynamicField name="tcedgestrings_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcedgestrings_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcedgestringm_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcedgestringm_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocedgestrings_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocedgestrings_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocedgestringm_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tocedgestringm_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucedgestrings_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucedgestrings_*" type="text_edgenstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucedgestringm_X3b_und_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tucedgestringm_*" type="text_edgenstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcedges_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcedges_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcedgem_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcedgem_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocedges_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocedges_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocedgem_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tocedgem_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucedges_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucedges_*" type="text_edge" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucedgem_X3b_und_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tucedgem_*" type="text_edge" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="ts_X3b_en_*" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tm_X3b_en_*" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tos_X3b_en_*" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tom_X3b_en_*" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tus_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tum_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="sort_X3b_en_*" type="collated_en" stored="false" indexed="false" docValues="true" />
<dynamicField name="ts_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tm_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tos_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tom_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tus_X3b_fr_*" type="text_unstemmed_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tum_X3b_fr_*" type="text_unstemmed_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="sort_X3b_fr_*" type="collated_fr" stored="false" indexed="false" docValues="true" />
<dynamicField name="tcphonetics_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcphonetics_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcphoneticm_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcphoneticm_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocphonetics_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocphonetics_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocphoneticm_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tocphoneticm_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucphonetics_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucphonetics_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucphoneticm_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tucphoneticm_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcphonetics_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcphoneticm_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocphonetics_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocphoneticm_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucphonetics_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucphoneticm_X3b_en_*" type="text_phonetic_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcphonetics_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcphoneticm_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocphonetics_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocphoneticm_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucphonetics_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucphoneticm_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="ts_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="ts_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tm_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tm_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tos_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tos_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tom_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tom_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tus_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tus_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tum_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tum_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="spellcheck_und*" type="text_spell_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="spellcheck_*" type="text_spell_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="sort_X3b_und_*" type="collated_und" stored="false" indexed="false" docValues="true" />
<dynamicField name="sort_*" type="collated_und" stored="false" indexed="false" docValues="true" />
<dynamicField name="tcngramstrings_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcngramstrings_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcngramstringm_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcngramstringm_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocngramstrings_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocngramstrings_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocngramstringm_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tocngramstringm_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucngramstrings_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucngramstrings_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucngramstringm_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tucngramstringm_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcngrams_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcngrams_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tcngramm_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tcngramm_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tocngrams_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocngrams_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tocngramm_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tocngramm_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tucngrams_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucngrams_*" type="text_ngram" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tucngramm_X3b_und_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tucngramm_*" type="text_ngram" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />

307
materio_autocomplete/conf/schema_extra_types.xml Normal file
View File

@ -0,0 +1,307 @@
<!--
Edge NGram String Field
6.0.0
-->
<fieldType name="text_edgenstring" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Edge NGram Text Field
7.0.0
-->
<fieldType name="text_edge" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
English Text Field
7.0.0
-->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
English Text Field collated
7.0.0
-->
<fieldType name="collated_en" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
<!--
English Text Field unstemmed
7.0.0
-->
<fieldType name="text_unstemmed_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
French Text Field
7.0.0
-->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
French Text Field collated
7.0.0
-->
<fieldType name="collated_fr" class="solr.ICUCollationField" locale="fr" strength="primary" caseLevel="false"/>
<!--
French Text Field unstemmed
7.0.0
-->
<fieldType name="text_unstemmed_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Fulltext Phonetic
7.0.0
-->
<fieldType name="text_phonetic_und" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="auto" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="auto" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Fulltext Phonetic English
7.0.0
-->
<fieldType name="text_phonetic_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="english" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="english" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Fulltext Phonetic French
7.0.0
-->
<fieldType name="text_phonetic_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="french" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
<filter class="solr.BeiderMorseFilterFactory" languageSet="french" nameType="GENERIC" ruleType="APPROX" concat="true"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Language Undefined Text Field
7.0.0
-->
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_und.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Language Undefined Text Field spellcheck
7.0.0
-->
<fieldType name="text_spell_und" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Language Undefined Text Field collated
7.0.0
-->
<fieldType name="collated_und" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
<!--
NGram String Field
6.0.0
-->
<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
NGram Text Field
7.0.0
-->
<fieldType name="text_ngram" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>

811
materio_autocomplete/conf/solrconfig.xml Normal file
View File

@ -0,0 +1,811 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE config [
<!ENTITY extra SYSTEM "solrconfig_extra.xml">
<!ENTITY index SYSTEM "solrconfig_index.xml">
<!ENTITY query SYSTEM "solrconfig_query.xml">
<!ENTITY requestdispatcher SYSTEM "solrconfig_requestdispatcher.xml">
]>
<!--
For more details about configurations options that may appear in
this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<config name="drupal-8.3.8-solr-8.x" >
<!-- In all configuration below, a prefix of "solr." for class names
is an alias that causes solr to search appropriate packages,
including org.apache.solr.(search|update|request|core|analysis)
You may also specify a fully qualified Java classname if you
have your own custom plugins.
-->
<!-- Set this to 'false' if you want solr to continue working after
it has encountered an severe configuration error. In a
production environment, you may want solr to keep working even
if one handler is mis-configured.
You may also set this to false using by setting the system
property:
-Dsolr.abortOnConfigurationError=false
-->
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<!-- Controls what version of Lucene various components of Solr
adhere to. Generally, you want to use the latest version to
get all bug fixes and improvements. It is highly recommended
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
<luceneMatchVersion>${solr.luceneMatchVersion:LUCENE_70}</luceneMatchVersion>
<!-- <lib/> directives can be used to instruct Solr to load any Jars
identified and use them to resolve any "plugins" specified in
your solrconfig.xml or schema.xml (ie: Analyzers, Request
Handlers, etc...).
All directories and paths are resolved relative to the
instanceDir.
Please note that <lib/> directives are processed in the order
that they appear in your solrconfig.xml file, and are "stacked"
on top of each other when building a ClassLoader - so if you have
plugin jars with dependencies on other jars, the "lower level"
dependency jars should be loaded first.
If a "./lib" directory exists in your instanceDir, all files
found in it are included as if you had used the following
syntax...
<lib dir="./lib" />
-->
<!-- A 'dir' option by itself adds any files found in the directory
to the classpath, this is useful for including all jars in a
directory.
When a 'regex' is specified in addition to a 'dir', only the
files in that directory which completely match the regex
(anchored on both ends) will be included.
If a 'dir' option (with or without a regex) is used and nothing
is found that matches, a warning will be logged.
The examples below can be used to load some solr-contribs along
with their external dependencies.
-->
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-analysis-extras-\d.*\.jar" />
<!-- an exact 'path' can be used instead of a 'dir' to specify a
specific jar file. This will cause a serious error to be logged
if it can't be loaded.
-->
<!--
<lib path="../a-jar-that-does-not-exist.jar" />
-->
<!-- Data Directory
Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home. If
replication is in use, this should match the replication
configuration.
-->
<dataDir>${solr.data.dir:}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory is filesystem
based and tries to pick the best implementation for the current
JVM and platform. solr.NRTCachingDirectoryFactory, the default,
wraps solr.StandardDirectoryFactory and caches small files in memory
for better NRT performance.
One can force a particular implementation via solr.MMapDirectoryFactory,
solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
solr.RAMDirectoryFactory is memory based and not persistent.
-->
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
<!-- These will be used if you are using the solr.HdfsDirectoryFactory,
otherwise they will be ignored. If you don't plan on using hdfs,
you can safely remove this section. -->
<!-- The root directory that collection data should be written to. -->
<str name="solr.hdfs.home">${solr.hdfs.home:}</str>
<!-- The hadoop configuration files to use for the hdfs client. -->
<str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
<!-- Enable/Disable the hdfs cache. -->
<str name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str>
<!-- Enable/Disable using one global cache for all SolrCores.
The settings used will be from the first HdfsDirectoryFactory created. -->
<str name="solr.hdfs.blockcache.global">${solr.hdfs.blockcache.global:true}</str>
</directoryFactory>
<!-- The CodecFactory for defining the format of the inverted index.
The default implementation is SchemaCodecFactory, which is the official Lucene
index format, but hooks into the schema to provide per-field customization of
the postings lists and per-document values in the fieldType element
(postingsFormat/docValuesFormat). Note that most of the alternative implementations
are experimental, so if you choose to customize the index format, it's a good
idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
before upgrading to a newer version to avoid unnecessary reindexing.
-->
<codecFactory class="solr.SchemaCodecFactory"/>
<!-- To enable dynamic schema REST APIs, remove the following <schemaFactory>.
-->
<schemaFactory class="ClassicIndexSchemaFactory"/>
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Index Config - These settings control low-level behavior of indexing
Most example settings here show the default value, but are commented
out, to more easily see where customizations have been made.
Note: This replaces <indexDefaults> and <mainIndex> from older versions
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<indexConfig>
<!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
LimitTokenCountFilterFactory in your fieldType definition. E.g.
<filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
-->
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
<!-- <writeLockTimeout>1000</writeLockTimeout> -->
<!-- Expert: Enabling compound file will use less files for the index,
using fewer file descriptors on the expense of performance decrease.
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
<!-- <useCompoundFile>false</useCompoundFile> -->
<!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
indexing for buffering added documents and deletions before they are
flushed to the Directory.
maxBufferedDocs sets a limit on the number of documents buffered
before flushing.
If both ramBufferSizeMB and maxBufferedDocs is set, then
Lucene will flush based on whichever limit is hit first.
The default is 100 MB. -->
<!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
<!-- Expert: Merge Policy
The Merge Policy in Lucene controls how merging of segments is done.
The default since Solr/Lucene 3.3 is TieredMergePolicy.
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
Even older versions of Lucene used LogDocMergePolicy.
-->
<!--
<mergePolicyFactory class="solr.TieredMergePolicyFactory">
<int name="maxMergeAtOnce">10</int>
<int name="segmentsPerTier">10</int>
</mergePolicyFactory>
-->
<!-- Expert: Merge Scheduler
The Merge Scheduler in Lucene controls how merges are
performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
can perform merges in the background using separate threads.
The SerialMergeScheduler (Lucene 2.2 default) does not.
-->
<!--
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
-->
<!-- LockFactory
This option specifies which Lucene LockFactory implementation
to use.
single = SingleInstanceLockFactory - suggested for a
read-only index or when there is no possibility of
another process trying to modify the index.
native = NativeFSLockFactory - uses OS native file locking.
Do not use when multiple solr webapps in the same
JVM are attempting to share a single index.
simple = SimpleFSLockFactory - uses a plain file for locking
Defaults: 'native' is default for Solr3.6 and later, otherwise
'simple' is the default
More details on the nuances of each LockFactory...
http://wiki.apache.org/lucene-java/AvailableLockFactories
-->
<lockType>${solr.lock.type:native}</lockType>
<!-- Commit Deletion Policy
Custom deletion policies can be specified here. The class must
implement org.apache.lucene.index.IndexDeletionPolicy.
The default Solr IndexDeletionPolicy implementation supports
deleting index commit points on number of commits, age of
commit point and optimized status.
The latest commit point should always be preserved regardless
of the criteria.
-->
<!--
<deletionPolicy class="solr.SolrDeletionPolicy">
-->
<!-- The number of commit points to be kept -->
<!-- <str name="maxCommitsToKeep">1</str> -->
<!-- The number of optimized commit points to be kept -->
<!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
<!--
Delete all commit points once they have reached the given age.
Supports DateMathParser syntax e.g.
-->
<!--
<str name="maxCommitAge">30MINUTES</str>
<str name="maxCommitAge">1DAY</str>
-->
<!--
</deletionPolicy>
-->
<!-- Lucene Infostream
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
Setting the value to true will instruct the underlying Lucene
IndexWriter to write its info stream to solr's log. By default,
this is enabled here, and controlled through log4j2.xml
-->
<infoStream>true</infoStream>
<!-- Let the config generator easily inject additional stuff. -->
&index;
</indexConfig>
<!-- The default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<!-- Enables a transaction log, used for real-time get, durability, and
and solr cloud replica recovery. The log can grow as big as
uncommitted changes to the index, so use of a hard autoCommit
is recommended (see below).
"dir" - the target directory for transaction logs, defaults to the
solr data directory. -->
<updateLog>
<str name="dir">${solr.ulog.dir:}</str>
</updateLog>
<!-- AutoCommit
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
when adding documents.
http://wiki.apache.org/solr/UpdateXmlMessages
maxDocs - Maximum number of documents to add since the last
commit before automatically triggering a new commit.
maxTime - Maximum amount of time in ms that is allowed to pass
since a document was added before automatically
triggering a new commit.
openSearcher - if false, the commit causes recent index changes
to be flushed to stable storage, but does not cause a new
searcher to be opened to make those changes visible.
If the updateLog is enabled, then it's highly recommended to
have some sort of hard autoCommit to limit the log size.
-->
<autoCommit>
<maxDocs>${solr.autoCommit.MaxDocs:-1}</maxDocs>
<maxTime>${solr.autoCommit.MaxTime:15000}</maxTime>
<openSearcher>false</openSearcher>
</autoCommit>
<!-- softAutoCommit is like autoCommit except it causes a
'soft' commit which only ensures that changes are visible
but does not ensure that data is synced to disk. This is
faster and more near-realtime friendly than a hard commit.
-->
<autoSoftCommit>
<maxDocs>${solr.autoSoftCommit.MaxDocs:-1}</maxDocs>
<maxTime>${solr.autoSoftCommit.MaxTime:-1}</maxTime>
</autoSoftCommit>
<!-- Update Related Event Listeners
Various IndexWriter related events can trigger Listeners to
take actions.
postCommit - fired after every commit or optimize command
postOptimize - fired after every optimize command
-->
<!-- The RunExecutableListener executes an external command from a
hook such as postCommit or postOptimize.
exe - the name of the executable to run
dir - dir to use as the current working directory. (default=".")
wait - the calling thread waits until the executable returns.
(default="true")
args - the arguments to pass to the program. (default is none)
env - environment variables to set. (default is none)
-->
<!-- This example shows how RunExecutableListener could be used
with the script based replication...
http://wiki.apache.org/solr/CollectionDistribution
-->
<!--
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">solr/bin/snapshooter</str>
<str name="dir">.</str>
<bool name="wait">true</bool>
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
<arr name="env"> <str>MYVAR=val1</str> </arr>
</listener>
-->
</updateHandler>
<!-- IndexReaderFactory
Use the following format to specify a custom IndexReaderFactory,
which allows for alternate IndexReader implementations.
** Experimental Feature **
Please note - Using a custom IndexReaderFactory may prevent
certain other features from working. The API to
IndexReaderFactory may change without warning or may even be
removed from future releases if the problems cannot be
resolved.
** Features that may not work with custom IndexReaderFactory **
The ReplicationHandler assumes a disk-resident index. Using a
custom IndexReader implementation may cause incompatibility
with ReplicationHandler and may cause replication to not work
correctly. See SOLR-1366 for details.
-->
<!--
<indexReaderFactory name="IndexReaderFactory" class="package.class">
<str name="someArg">Some Value</str>
</indexReaderFactory >
-->
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Query section - these settings control query time things like caches
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<query>
<!-- Let the config generator easily inject additional stuff. -->
&query;
<!-- Query Related Event Listeners
Various IndexSearcher related events can trigger Listeners to
take actions.
newSearcher - fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka
registered). It can be used to prime certain caches to
prevent long request times for certain requests.
firstSearcher - fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from.
-->
<!-- QuerySenderListener takes an array of NamedList and executes a
local query request for each NamedList in sequence.
-->
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<!--
<lst><str name="q">solr</str><str name="sort">price asc</str></lst>
<lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
-->
</arr>
</listener>
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst>
<str name="q">static firstSearcher warming in solrconfig.xml</str>
</lst>
</arr>
</listener>
<!-- Use Cold Searcher
If a search request comes in and there is no current
registered searcher, then immediately register the still
warming searcher and use it. If "false" then all requests
will block until the first searcher is done warming.
-->
<useColdSearcher>false</useColdSearcher>
</query>
<!-- Request Dispatcher
This section contains instructions for how the SolrDispatchFilter
should behave when processing requests for this SolrCore.
-->
<requestDispatcher>
<!-- Request Parsing
These settings indicate how Solr Requests may be parsed, and
what restrictions may be placed on the ContentStreams from
those requests
enableRemoteStreaming - enables use of the stream.file
and stream.url parameters for specifying remote streams.
multipartUploadLimitInKB - specifies the max size (in KiB) of
Multipart File Uploads that Solr will allow in a Request.
formdataUploadLimitInKB - specifies the max size (in KiB) of
form data (application/x-www-form-urlencoded) sent via
POST. You can use POST to pass request parameters not
fitting into the URL.
addHttpRequestToContext - if set to true, it will instruct
the requestParsers to include the original HttpServletRequest
object in the context map of the SolrQueryRequest under the
key "httpRequest". It will not be used by any of the existing
Solr components, but may be useful when developing custom
plugins.
*** WARNING ***
Before enabling remote streaming, you should make sure your
system has authentication enabled.
<requestParsers enableRemoteStreaming="false"
multipartUploadLimitInKB="-1"
formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
-->
<!-- Let the config generator easily inject additional stuff. -->
&requestdispatcher;
</requestDispatcher>
<!-- Search Components
Search components are registered to SolrCore and used by
instances of SearchHandler (which can access them by name)
By default, the following components are available:
<searchComponent name="query" class="solr.QueryComponent" />
<searchComponent name="facet" class="solr.FacetComponent" />
<searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
<searchComponent name="highlight" class="solr.HighlightComponent" />
<searchComponent name="stats" class="solr.StatsComponent" />
<searchComponent name="debug" class="solr.DebugComponent" />
Default configuration in a requestHandler would look like:
<arr name="components">
<str>query</str>
<str>facet</str>
<str>mlt</str>
<str>highlight</str>
<str>stats</str>
<str>debug</str>
</arr>
If you register a searchComponent to one of the standard names,
that will be used instead of the default.
To insert components before or after the 'standard' components, use:
<arr name="first-components">
<str>myFirstComponentName</str>
</arr>
<arr name="last-components">
<str>myLastComponentName</str>
</arr>
NOTE: The component registered with the name "debug" will
always be executed after the "last-components"
-->
<!-- Following is a dynamic way to include other components or any customized solrconfig.xml stuff, added by other contrib modules -->
&extra;
<!-- Highlighting Component
http://wiki.apache.org/solr/HighlightingParameters
-->
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<!-- This could most likely be commented out in the "default" case -->
<fragmenter name="gap"
default="true"
class="solr.highlight.GapFragmenter">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<!-- A regular-expression-based fragmenter
(for sentence extraction)
-->
<fragmenter name="regex"
class="solr.highlight.RegexFragmenter">
<lst name="defaults">
<!-- slightly smaller fragsizes work better because of slop -->
<int name="hl.fragsize">70</int>
<!-- allow 50% slop on fragment sizes -->
<float name="hl.regex.slop">0.5</float>
<!-- a basic sentence pattern -->
<str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html"
default="true"
class="solr.highlight.HtmlFormatter">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
<!-- Configure the standard encoder -->
<encoder name="html"
class="solr.highlight.HtmlEncoder" />
<!-- Configure the standard fragListBuilder -->
<fragListBuilder name="simple"
class="solr.highlight.SimpleFragListBuilder"/>
<!-- Configure the single fragListBuilder -->
<fragListBuilder name="single"
class="solr.highlight.SingleFragListBuilder"/>
<!-- Configure the weighted fragListBuilder -->
<fragListBuilder name="weighted"
default="true"
class="solr.highlight.WeightedFragListBuilder"/>
<!-- default tag FragmentsBuilder -->
<fragmentsBuilder name="default"
default="true"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<!--
<lst name="defaults">
<str name="hl.multiValuedSeparatorChar">/</str>
</lst>
-->
</fragmentsBuilder>
<!-- multi-colored tag FragmentsBuilder -->
<fragmentsBuilder name="colored"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<lst name="defaults">
<str name="hl.tag.pre"><![CDATA[
<b style="background:yellow">,<b style="background:lawgreen">,
<b style="background:aquamarine">,<b style="background:magenta">,
<b style="background:palegreen">,<b style="background:coral">,
<b style="background:wheat">,<b style="background:khaki">,
<b style="background:lime">,<b style="background:deepskyblue">]]></str>
<str name="hl.tag.post"><![CDATA[</b>]]></str>
</lst>
</fragmentsBuilder>
<boundaryScanner name="default"
default="true"
class="solr.highlight.SimpleBoundaryScanner">
<lst name="defaults">
<str name="hl.bs.maxScan">10</str>
<str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
</lst>
</boundaryScanner>
<boundaryScanner name="breakIterator"
class="solr.highlight.BreakIteratorBoundaryScanner">
<lst name="defaults">
<!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
<str name="hl.bs.type">WORD</str>
<!-- language and country are used when constructing Locale object. -->
<!-- And the Locale object will be used when getting instance of BreakIterator -->
<str name="hl.bs.language">en</str>
<str name="hl.bs.country">US</str>
</lst>
</boundaryScanner>
</highlighting>
</searchComponent>
<!-- Update Processors
Chains of Update Processor Factories for dealing with Update
Requests can be declared, and then used by name in Update
Request Processors
http://wiki.apache.org/solr/UpdateRequestProcessor
-->
<!-- Deduplication
An example dedup update processor that creates the "id" field
on the fly based on the hash code of some other fields. This
example has overwriteDupes set to false since we are using the
id field as the signatureField and Solr will maintain
uniqueness based on that anyway.
-->
<!--
<updateRequestProcessorChain name="dedupe">
<processor class="solr.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">true</bool>
<str name="signatureField">id</str>
<bool name="overwriteDupes">false</bool>
<str name="fields">name,features,cat</str>
<str name="signatureClass">solr.processor.Lookup3Signature</str>
</processor>
<processor class="solr.LogUpdateProcessorFactory" />
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Language identification
This example update chain identifies the language of the incoming
documents using the langid contrib. The detected language is
written to field language_s. No field name mapping is done.
The fields used for detection are text, title, subject and description,
making this example suitable for detecting languages form full-text
rich documents injected via ExtractingRequestHandler.
See more about langId at http://wiki.apache.org/solr/LanguageDetection
-->
<!--
<updateRequestProcessorChain name="langid">
<processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
<str name="langid.fl">text,title,subject,description</str>
<str name="langid.langField">language_s</str>
<str name="langid.fallback">en</str>
</processor>
<processor class="solr.LogUpdateProcessorFactory" />
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Script update processor
This example hooks in an update processor implemented using JavaScript.
See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
-->
<!--
<updateRequestProcessorChain name="script">
<processor class="solr.StatelessScriptUpdateProcessorFactory">
<str name="script">update-script.js</str>
<lst name="params">
<str name="config_param">example config parameter</str>
</lst>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
-->
<!-- Response Writers
http://wiki.apache.org/solr/QueryResponseWriter
Request responses will be written using the writer specified by
the 'wt' request parameter matching the name of a registered
writer.
The "default" writer is the default and will be used if 'wt' is
not specified in the request.
-->
<!-- The following response writers are implicitly configured unless
overridden...
-->
<!--
<queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
<queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
<queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
<queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
<queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
<queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
-->
<queryResponseWriter name="json" class="solr.JSONResponseWriter">
</queryResponseWriter>
<!--
Custom response writers can be declared as needed...
-->
<!-- The solr.velocity.enabled flag is used by Solr's test cases so that this response writer is not
loaded (causing an error if contrib/velocity has not been built fully) -->
<!--
<queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
<str name="template.base.dir">${velocity.template.base.dir:}</str>
</queryResponseWriter>
-->
<!-- XSLT response writer transforms the XML output by any xslt file found
in Solr's conf/xslt directory. Changes to xslt files are checked for
every xsltCacheLifetimeSeconds.
-->
<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
<int name="xsltCacheLifetimeSeconds">5</int>
</queryResponseWriter>
<!-- Query Parsers
https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
Multiple QParserPlugins can be registered by name, and then
used in either the "defType" param for the QueryComponent (used
by SearchHandler) or in LocalParams
-->
<!-- example of registering a query parser -->
<!--
<queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
-->
<!-- Function Parsers
http://wiki.apache.org/solr/FunctionQuery
Multiple ValueSourceParsers can be registered by name, and then
used as function names when using the "func" QParser.
-->
<!-- example of registering a custom function parser -->
<!--
<valueSourceParser name="myfunc"
class="com.mycompany.MyValueSourceParser" />
-->
<!-- Document Transformers
http://wiki.apache.org/solr/DocTransformers
-->
<!--
Could be something like:
<transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
<int name="connection">jdbc://....</int>
</transformer>
To add a constant value to all docs, use:
<transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<int name="value">5</int>
</transformer>
If you want the user to still be able to change it with _value:something_ use this:
<transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
<double name="defaultValue">5</double>
</transformer>
If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
EditorialMarkerFactory will do exactly that:
<transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
-->
</config>

214
materio_autocomplete/conf/solrconfig_extra.xml Normal file
View File

@ -0,0 +1,214 @@
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<lst name="spellchecker">
<str name="name">en</str>
<str name="field">spellcheck_en</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">internal</str>
<str name="accuracy">0.5</str>
<str name="maxEdits">2</str>
<str name="minPrefix">1</str>
<str name="maxInspections">5</str>
<str name="minQueryLength">4</str>
<str name="maxQueryFrequency">0.01</str>
<str name="thresholdTokenFrequency">.01</str>
<str name="onlyMorePopular">true</str>
</lst>
<lst name="spellchecker">
<str name="name">fr</str>
<str name="field">spellcheck_fr</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">internal</str>
<str name="accuracy">0.5</str>
<str name="maxEdits">2</str>
<str name="minPrefix">1</str>
<str name="maxInspections">5</str>
<str name="minQueryLength">4</str>
<str name="maxQueryFrequency">0.01</str>
<str name="thresholdTokenFrequency">.01</str>
<str name="onlyMorePopular">true</str>
</lst>
<lst name="spellchecker">
<str name="name">und</str>
<str name="field">spellcheck_und</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">internal</str>
<str name="accuracy">0.5</str>
<str name="maxEdits">2</str>
<str name="minPrefix">1</str>
<str name="maxInspections">5</str>
<str name="minQueryLength">4</str>
<str name="maxQueryFrequency">0.01</str>
<str name="thresholdTokenFrequency">.01</str>
<str name="onlyMorePopular">true</str>
</lst>
</searchComponent>
<searchComponent name="suggest" class="solr.SuggestComponent">
<lst name="suggester">
<str name="name">en</str>
<str name="lookupImpl">AnalyzingInfixLookupFactory</str>
<str name="dictionaryImpl">DocumentDictionaryFactory</str>
<str name="field">twm_suggest</str>
<str name="suggestAnalyzerFieldType">text_en</str>
<str name="contextField">sm_context_tags</str>
<str name="buildOnCommit">true</str>
<str name="buildOnStartup">false</str>
</lst>
<lst name="suggester">
<str name="name">fr</str>
<str name="lookupImpl">AnalyzingInfixLookupFactory</str>
<str name="dictionaryImpl">DocumentDictionaryFactory</str>
<str name="field">twm_suggest</str>
<str name="suggestAnalyzerFieldType">text_fr</str>
<str name="contextField">sm_context_tags</str>
<str name="buildOnCommit">true</str>
<str name="buildOnStartup">false</str>
</lst>
<lst name="suggester">
<str name="name">und</str>
<str name="lookupImpl">AnalyzingInfixLookupFactory</str>
<str name="dictionaryImpl">DocumentDictionaryFactory</str>
<str name="field">twm_suggest</str>
<str name="suggestAnalyzerFieldType">text_und</str>
<str name="contextField">sm_context_tags</str>
<str name="buildOnCommit">true</str>
<str name="buildOnStartup">false</str>
</lst>
</searchComponent>
<!--
Autocomplete
7.0.0
-->
<requestHandler name="/autocomplete" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="terms">false</str>
<str name="distrib">false</str>
<str name="spellcheck">false</str>
<str name="spellcheck.onlyMorePopular">true</str>
<str name="spellcheck.extendedResults">false</str>
<str name="spellcheck.count">1</str>
<str name="suggest">false</str>
<str name="suggest.count">10</str>
</lst>
<arr name="components">
<str>terms</str>
<str>spellcheck</str>
<str>suggest</str>
</arr>
</requestHandler>
<!--
Extract
7.0.0
-->
<requestHandler name="/update/extract" class="solr.extraction.ExtractingRequestHandler" startup="lazy">
<lst name="defaults">
<str name="lowernames">true</str>
<str name="uprefix">ignored_</str>
<str name="captureAttr">true</str>
<str name="fmap.a">links</str>
<str name="fmap.div">ignored_</str>
</lst>
</requestHandler>
<!--
More Like This
7.0.0
-->
<requestHandler name="/mlt" class="solr.MoreLikeThisHandler">
<lst name="defaults">
<str name="mlt.mintf">1</str>
<str name="mlt.mindf">1</str>
<str name="mlt.match.include">false</str>
<str name="timeAllowed">${solr.mlt.timeAllowed:2000}</str>
</lst>
</requestHandler>
<!--
Select
7.0.0
-->
<requestHandler name="/select" class="solr.SearchHandler">
<lst name="defaults">
<str name="defType">lucene</str>
<str name="df">id</str>
<str name="echoParams">explicit</str>
<str name="omitHeader">true</str>
<str name="timeAllowed">${solr.selectSearchHandler.timeAllowed:-1}</str>
<str name="spellcheck">false</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
<str>elevator</str>
</arr>
</requestHandler>
<!--
Spellcheck
7.0.0
-->
<requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="df">id</str>
<str name="spellcheck.dictionary">und</str>
<str name="spellcheck">on</str>
<str name="spellcheck.onlyMorePopular">false</str>
<str name="spellcheck.extendedResults">false</str>
<str name="spellcheck.count">1</str>
<str name="spellcheck.alternativeTermCount">5</str>
<str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
<str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">10</str>
<str name="spellcheck.maxCollations">5</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<!--
Suggester
7.0.0
-->
<requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="suggest">true</str>
<str name="suggest.dictionary">und</str>
<str name="suggest.dictionary">10</str>
</lst>
<arr name="components">
<str>suggest</str>
</arr>
</requestHandler>
<!--
Term Vector
7.0.0
-->
<requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="df">id</str>
<str name="tv">true</str>
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<!--
Special configs for Elevator
7.0.0
-->
<searchComponent name="elevator" class="solr.QueryElevationComponent">
<str name="queryFieldType">string</str>
<str name="config-file">elevate.xml</str>
</searchComponent>
<!--
Special configs for Term Vector
7.0.0
-->
<searchComponent name="tvComponent" class="solr.TermVectorComponent"/>

0
materio_autocomplete/conf/solrconfig_index.xml Normal file
View File

47
materio_autocomplete/conf/solrconfig_query.xml Normal file
View File

@ -0,0 +1,47 @@
<!--
Document Cache
7.0.0
-->
<documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
Field Value Cache
7.0.0
-->
<fieldValueCache class="solr.FastLRUCache" size="512" autowarmCount="128" showItems="32"/>
<!--
Filter Cache
7.0.0
-->
<filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
Per Segment Filter Cache
7.0.0
-->
<cache name="perSegFilter" class="solr.search.LRUCache" size="10" initialSize="0" autowarmCount="10" regenerator="solr.NoOpRegenerator"/>
<!--
Query Result Cache
7.0.0
-->
<queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
Special configs for Field Value Cache
7.0.0
-->
<query name="enableLazyFieldLoading">true</query>
<!--
Special configs for Filter Cache
7.0.0
-->
<query name="useFilterForSortedQuery">false</query>
<!--
Special configs for Query Result Cache
7.0.0
-->
<query name="queryResultWindowSize">20</query>
<query name="queryResultMaxDocsCached">200</query>
<query name="maxBooleanClauses">1024</query>

6
materio_autocomplete/conf/solrconfig_requestdispatcher.xml Normal file
View File

@ -0,0 +1,6 @@
<!--
HTTP Cache Never
7.0.0
-->
<httpCaching never304="true"/>

13
materio_autocomplete/conf/solrcore.properties Normal file
View File

@ -0,0 +1,13 @@
solr.replication.master=false
solr.replication.slave=false
solr.replication.pollInterval=00:00:60
solr.replication.masterUrl=http://localhost:8985/solr
solr.replication.confFiles=schema.xml,schema_extra_types.xml,schema_extra_fields.xml,elevate.xml,stopwords_en.txt,synonyms_en.txt,protwords_en.txt,accents_en.txt,stopwords_fr.txt,synonyms_fr.txt,nouns_fr.txt,protwords_fr.txt,accents_fr.txt,stopwords_und.txt,synonyms_und.txt,protwords_und.txt,accents_und.txt
solr.mlt.timeAllowed=2000
solr.luceneMatchVersion=8.0
solr.selectSearchHandler.timeAllowed=-1
solr.autoCommit.MaxDocs=-1
solr.autoCommit.MaxTime=15000
solr.autoSoftCommit.MaxDocs=-1
solr.autoSoftCommit.MaxTime=-1
solr.install.dir=../../..

35
materio_autocomplete/conf/stopwords_en.txt Normal file
View File

@ -0,0 +1,35 @@
a
an
and
are
as
at
be
but
by
for
if
in
into
is
it
no
not
of
on
or
s
such
t
that
the
their
then
there
these
they
this
to
was
will
with

163
materio_autocomplete/conf/stopwords_fr.txt Normal file
View File

@ -0,0 +1,163 @@
au
aux
avec
ce
ces
dans
de
des
du
elle
en
et
eux
il
je
la
le
leur
lui
ma
mais
me
même
mes
moi
mon
ne
nos
notre
nous
on
ou
par
pas
pour
qu
que
qui
sa
se
ses
son
sur
ta
te
tes
toi
ton
tu
un
une
vos
votre
vous
c
d
j
l
à
m
n
s
t
y
été
étée
étées
étés
étant
suis
es
est
sommes
êtes
sont
serai
seras
sera
serons
serez
seront
serais
serait
serions
seriez
seraient
étais
était
étions
étiez
étaient
fus
fut
fûmes
fûtes
furent
sois
soit
soyons
soyez
soient
fusse
fusses
fût
fussions
fussiez
fussent
ayant
eu
eue
eues
eus
ai
as
avons
avez
ont
aurai
auras
aura
aurons
aurez
auront
aurais
aurait
aurions
auriez
auraient
avais
avait
avions
aviez
avaient
eut
eûmes
eûtes
eurent
aie
aies
ait
ayons
ayez
aient
eusse
eusses
eût
eussions
eussiez
eussent
ceci
celà
cet
cette
ici
ils
les
leurs
quel
quels
quelle
quelles
sans
soi

1
materio_autocomplete/conf/stopwords_und.txt Normal file
View File

@ -0,0 +1 @@

1
materio_autocomplete/conf/synonyms_en.txt Normal file
View File

@ -0,0 +1 @@
drupal, durpal

1
materio_autocomplete/conf/synonyms_fr.txt Normal file
View File

@ -0,0 +1 @@
drupal, durpal

1
materio_autocomplete/conf/synonyms_und.txt Normal file
View File

@ -0,0 +1 @@
drupal, durpal

6
materio_autocomplete/core.properties Normal file
View File

@ -0,0 +1,6 @@
#Written by CorePropertiesLocator
#Tue Feb 18 14:08:41 UTC 2020
schema=schema.xml
dataDir=data
name=materio_autocomplete
config=solrconfig.xml