You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@allura.apache.org by jo...@apache.org on 2013/05/10 23:00:56 UTC
[01/11] git commit: [#3854] Fix mongo version check and venv path
Updated Branches:
refs/heads/master 2251ba045 -> 16ea2661b
[#3854] Fix mongo version check and venv path
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/01771658
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/01771658
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/01771658
Branch: refs/heads/master
Commit: 017716583a3452500da28b711952cfea2bc52f13
Parents: 48604f1
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Tue Apr 30 00:29:11 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
vagrant/allura_setup.sh | 2 +-
vagrant/start_allura | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/01771658/vagrant/allura_setup.sh
----------------------------------------------------------------------
diff --git a/vagrant/allura_setup.sh b/vagrant/allura_setup.sh
index e382fac..4da7f8d 100755
--- a/vagrant/allura_setup.sh
+++ b/vagrant/allura_setup.sh
@@ -21,7 +21,7 @@
MONGODB_VERSION=2.2.3
MONGODB_PKG_URL="deb http://downloads-distro.mongodb.org/repo/ubuntu-upstart dist 10gen"
MONGODB_SRC_LST=/etc/apt/sources.list.d/10gen.list
-if [ $(mongo --version 2>/dev/null | sed 's/.*: //') != $MONGODB_VERSION ]
+if [ "$(mongo --version 2>/dev/null | sed 's/.*: //')" != "$MONGODB_VERSION" ]
then
echo "Installing Mongodb $MONGODB_VERSION..."
sudo apt-get -y -q purge mongodb mongodb-clients mongodb-server mongodb-dev
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/01771658/vagrant/start_allura
----------------------------------------------------------------------
diff --git a/vagrant/start_allura b/vagrant/start_allura
index 758a4bd..c396f7a 100755
--- a/vagrant/start_allura
+++ b/vagrant/start_allura
@@ -20,7 +20,7 @@
# Starts Allura platform services
# Activate Allura virtualenv
-. /home/vagrant/anvil/bin/activate
+. /home/vagrant/env-allura/bin/activate
# Create log dir
if [ ! -d /var/log/allura ]
[04/11] [#3854] Simplify solr setup and upgrade to 4.2.1
Posted by jo...@apache.org.
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/forge-schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/forge-schema.xml b/solr_config/forge-schema.xml
deleted file mode 100644
index 45aca76..0000000
--- a/solr_config/forge-schema.xml
+++ /dev/null
@@ -1,1080 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the StreamingUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
-<schema name="forge" version="1.5">
- <!-- 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...)
- -->
-
- <fields>
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- <types> fieldType section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful for faceting, grouping, sorting and function queries. Although not
- required, 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
- and all Trie*Fields, and depending on the field type, they might
- require the field to be single-valued, be required or have a default
- value (check the documentation of the field type you're interested in
- for more information)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- Norms are omitted for primitive (non-analyzed) types by default.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
- <!-- Required field values for SOLR, DO NOT REMOVE -->
- <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <field name="text" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <!-- END of required field values -->
-
- <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
- <field name="description" type="text_general" indexed="true" stored="true" />
- <field name="group_id" type="tint" indexed="true" stored="true"/>
- <field name="group_ranking" type="tint" indexed="true" stored="true"/>
- <field name="has_file" type="tint" indexed="true" stored="true"/>
- <field name="help_wanted" type="boolean" indexed="true" stored="true" />
- <field name="latest_file_date" type="date" indexed="true" stored="true" />
- <field name="license" type="string" indexed="true" stored="true" />
- <field name="license_other" type="string" indexed="true" stored="true" />
- <field name="name" type="text_general" indexed="true" stored="true"/>
- <field name="num_developers" type="tint" indexed="true" stored="true"/>
- <field name="num_downloads" type="tint" indexed="true" stored="true"/>
- <field name="num_downloads_week" type="tint" indexed="true" stored="true"/>
- <field name="num_services" type="tint" indexed="true" stored="true"/>
- <field name="percentile" type="float" indexed="true" stored="true"/>
- <field name="project_type" type="tint" indexed="true" stored="true" />
- <field name="project_doc_id" type="string" indexed="true" stored="true" />
- <field name="registration_date" type="date" indexed="true" stored="true" />
- <field name="screenshot_url" type="string" indexed="true" stored="true" />
- <field name="trove" type="text_general" indexed="true" stored="true" />
- <field name="unix_group_name" type="string" indexed="true" stored="true" />
- <field name="source" type="string" indexed="true" stored="true" />
- <field name="rating" type="float" indexed="true" stored="true" />
- <field name="review_count" type="tint" indexed="true" stored="true" />
-
- <!-- Common metadata fields, named specifically to match up with
- SolrCell metadata when parsing rich documents such as Word, PDF.
- Some fields are multiValued only because Tika currently may return
- multiple values for them. Some metadata is parsed from the documents,
- but there are some which come from the client context:
- "content_type": From the HTTP headers of incoming stream
- "resourcename": From SolrCell request param resource.name
- -->
- <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <field name="subject" type="text_general" indexed="true" stored="true"/>
- <field name="comments" type="text_general" indexed="true" stored="true"/>
- <field name="author" type="text_general" indexed="true" stored="true"/>
- <field name="keywords" type="text_general" indexed="true" stored="true"/>
- <field name="category" type="text_general" indexed="true" stored="true"/>
- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="last_modified" type="date" indexed="true" stored="true"/>
- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
-
- <!-- Main body of document extracted by SolrCell.
- NOTE: This field is not indexed by default, since it is also copied to "text"
- using copyField below. This is to save space. Use this field for returning and
- highlighting document content. Use the "text" field to search the content. -->
-
-
- <!-- catchall field, containing all other searchable text fields (implemented
- via copyField further on in this schema -->
-
- <!-- catchall text field that indexes tokens both normally and in reverse for efficient
- leading wildcard queries. -->
-
- <!-- non-tokenized version of manufacturer to make it easier to sort or group
- results by manufacturer. copied from "manu" via copyField -->
- <!--
- Some fields such as popularity and manu_exact could be modified to
- leverage doc values:
- <field name="popularity" type="int" indexed="true" stored="true" docValues="true" default="0" />
- <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" default="" />
-
- Although it would make indexing slightly slower and the index bigger, it
- would also make the index faster to load, more memory-efficient and more
- NRT-friendly.
- -->
-
- <!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end. -->
-
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
-
- <!-- some trie-coded dynamic fields for faster range queries -->
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
- <dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-
- </fields>
-
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
-
- <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
- parsing a query string that isn't explicit about the field. Machine (non-user)
- generated queries are best made explicit, or they can use the "df" request parameter
- which takes precedence over this.
- Note: Un-commenting defaultSearchField will be insufficient if your request handler
- in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
- <defaultSearchField>text</defaultSearchField> -->
-
- <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
- when parsing a query string to determine if a clause of the query should be marked as
- required or optional, assuming the clause isn't already marked by some operator.
- The default is OR, which is generally assumed so it is not a good idea to change it
- globally here. The "q.op" request parameter takes precedence over this.
- <solrQueryParser defaultOperator="OR"/> -->
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching. -->
-
- <!-- Above, multiple source fields are copied to the [text] field.
- Another way to map multiple source fields to the same
- destination field is to use the dynamic field syntax.
- copyField also supports a maxChars to copy setting. -->
-
- <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
-
- <!-- copy name to alphaNameSort, a field designed for sorting by name -->
- <!-- <copyField source="name" dest="alphaNameSort"/> -->
-
- <types>
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in a
- standard package such as org.apache.solr.analysis
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" variants.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-
- These fields support doc values, but they require the field to be
- single-valued and either be required or have a default value.
- -->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
- -->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the DateField javadocs for more information.
-
- Note: For faster range queries, consider the tdate type
- -->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
-
- <!-- A Trie based date field for faster date range queries and date faceting. -->
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
-
-
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldtype name="binary" class="solr.BinaryField"/>
-
- <!--
- Note:
- These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
- Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
-
- Plain numeric field types that store and index the text
- value verbatim (and hence don't correctly support range queries, since the
- lexicographic ordering isn't equal to the numeric ordering)
- -->
- <fieldType name="pint" class="solr.IntField"/>
- <fieldType name="plong" class="solr.LongField"/>
- <fieldType name="pfloat" class="solr.FloatField"/>
- <fieldType name="pdouble" class="solr.DoubleField"/>
- <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- 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" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general text field that has reasonable, generic
- cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases. At query time only, it
- also applies synonyms. -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English: it
- tokenizes with StandardTokenizer, removes English stop words
- (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
- finally applies Porter's stemming. The query time analyzer
- also applies synonyms from synonyms.txt. -->
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- add enablePositionIncrements=true in both the index and query
- analyzers to leave a 'gap' for more accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- add enablePositionIncrements=true in both the index and query
- analyzers to leave a 'gap' for more accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries. -->
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back references to portions of the original
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- information on pattern and replacement string syntax.
-
- http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldtype>
-
- <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!--
- The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
- Attributes of the DelimitedPayloadTokenFilterFactory :
- "delimiter" - a one character delimiter. Default is | (pipe)
- "encoder" - how to encode the following value into a playload
- float -> org.apache.lucene.analysis.payloads.FloatEncoder,
- integer -> o.a.l.a.p.IntegerEncoder
- identity -> o.a.l.a.p.IdentityEncoder
- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
- -->
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldtype>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
- <fieldtype name="ignored" stored="false" indexed="false" 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.
- -->
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
-
- <!-- 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="0.000009" units="degrees" />
-
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- 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.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- for any non-arabic -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
- <!-- normalizes ﻯ to ﻱ, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
- <filter class="solr.BulgarianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Catalan -->
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
- </analyzer>
- </fieldType>
-
- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- for any non-CJK -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CJKBigramFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
- <filter class="solr.CzechStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Danish -->
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
- </analyzer>
- </fieldType>
-
- <!-- German -->
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.GermanNormalizationFilterFactory"/>
- <filter class="solr.GermanLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Greek -->
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- greek specific lowercase for sigma -->
- <filter class="solr.GreekLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
- <filter class="solr.GreekStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Spanish -->
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SpanishLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Basque -->
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
- </analyzer>
- </fieldType>
-
- <!-- Persian -->
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <!-- for ZWNJ -->
- <charFilter class="solr.PersianCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.PersianNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Finnish -->
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- French -->
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.FrenchLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Irish -->
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes d', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
- <!-- removes n-, etc. position increments is intentionally false! -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
- </analyzer>
- </fieldType>
-
- <!-- Galician -->
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
- <filter class="solr.GalicianStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Hindi -->
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes unicode representation -->
- <filter class="solr.IndicNormalizationFilterFactory"/>
- <!-- normalizes variation in spelling -->
- <filter class="solr.HindiNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
- <filter class="solr.HindiStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Hungarian -->
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Armenian -->
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
- </analyzer>
- </fieldType>
-
- <!-- Indonesian -->
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Italian -->
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.ItalianLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
-
- NOTE: If you want to optimize search for precision, use default operator AND in your query
- parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
- OR if you would like to optimize for recall (default).
- -->
- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
- <analyzer>
- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
-
- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
- is used to segment compounds into its parts and the compound itself is kept as synonym.
-
- Valid values for attribute mode are:
- normal: regular segmentation
- search: segmentation useful for search with synonyms compounds (default)
- extended: same as search mode, but unigrams unknown words (experimental)
-
- For some applications it might be good to use search mode for indexing and normal mode for
- queries to reduce recall and prevent parts of compounds from being matched and highlighted.
- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
-
- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
- model with your own entries for segmentation, part-of-speech tags and readings without a need
- to specify weights. Notice that user dictionaries have not been subject to extensive testing.
-
- User dictionary attributes are:
- userDictionary: user dictionary filename
- userDictionaryEncoding: user dictionary encoding (default is UTF-8)
-
- See lang/userdict_ja.txt for a sample user dictionary file.
-
- Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
-
- See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
- -->
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
- <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Removes tokens with certain part-of-speech tags -->
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
- <!-- Lower-cases romaji characters -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Latvian -->
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
- <filter class="solr.LatvianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Dutch -->
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
- </analyzer>
- </fieldType>
-
- <!-- Norwegian -->
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.PortugueseLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Romanian -->
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
- </analyzer>
- </fieldType>
-
- <!-- Russian -->
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Swedish -->
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Thai -->
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ThaiWordFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
- </analyzer>
- </fieldType>
-
- </types>
-
- <!-- 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>
[05/11] git commit: [#3854] Simplify solr setup and upgrade to 4.2.1
Posted by jo...@apache.org.
[#3854] Simplify solr setup and upgrade to 4.2.1
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/87108f04
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/87108f04
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/87108f04
Branch: refs/heads/master
Commit: 87108f042cac2505588d26e8d0533f8cb1115ff5
Parents: 634ed76
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Fri Apr 26 10:19:16 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
solr_config/core0/conf/mapping-ISOLatin1Accent.txt | 246 ----
solr_config/core0/conf/protwords.txt | 21 -
solr_config/core0/conf/schema.xml | 503 -------
solr_config/core0/conf/solrconfig.xml | 40 -
solr_config/core0/conf/spellings.txt | 2 -
solr_config/core0/conf/stopwords.txt | 58 -
solr_config/core0/conf/synonyms.txt | 31 -
solr_config/core1/conf/mapping-ISOLatin1Accent.txt | 246 ----
solr_config/core1/conf/protwords.txt | 21 -
solr_config/core1/conf/schema.xml | 503 -------
solr_config/core1/conf/solrconfig.xml | 40 -
solr_config/core1/conf/spellings.txt | 2 -
solr_config/core1/conf/stopwords.txt | 58 -
solr_config/core1/conf/synonyms.txt | 31 -
solr_config/forge-schema.xml | 1080 ---------------
solr_config/schema.xml | 1080 +++++++++++++++
solr_config/solr.xml | 7 -
vagrant/allura_setup.sh | 12 +-
vagrant/start_allura | 4 +-
19 files changed, 1087 insertions(+), 2898 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/mapping-ISOLatin1Accent.txt
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/mapping-ISOLatin1Accent.txt b/solr_config/core0/conf/mapping-ISOLatin1Accent.txt
deleted file mode 100644
index ede7742..0000000
--- a/solr_config/core0/conf/mapping-ISOLatin1Accent.txt
+++ /dev/null
@@ -1,246 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Syntax:
-# "source" => "target"
-# "source".length() > 0 (source cannot be empty.)
-# "target".length() >= 0 (target can be empty.)
-
-# example:
-# "À" => "A"
-# "\u00C0" => "A"
-# "\u00C0" => "\u0041"
-# "ß" => "ss"
-# "\t" => " "
-# "\n" => ""
-
-# À => A
-"\u00C0" => "A"
-
-# Á => A
-"\u00C1" => "A"
-
-# Â => A
-"\u00C2" => "A"
-
-# Ã => A
-"\u00C3" => "A"
-
-# Ä => A
-"\u00C4" => "A"
-
-# Å => A
-"\u00C5" => "A"
-
-# Æ => AE
-"\u00C6" => "AE"
-
-# Ç => C
-"\u00C7" => "C"
-
-# È => E
-"\u00C8" => "E"
-
-# É => E
-"\u00C9" => "E"
-
-# Ê => E
-"\u00CA" => "E"
-
-# Ë => E
-"\u00CB" => "E"
-
-# Ì => I
-"\u00CC" => "I"
-
-# Í => I
-"\u00CD" => "I"
-
-# Î => I
-"\u00CE" => "I"
-
-# Ï => I
-"\u00CF" => "I"
-
-# IJ => IJ
-"\u0132" => "IJ"
-
-# Ð => D
-"\u00D0" => "D"
-
-# Ñ => N
-"\u00D1" => "N"
-
-# Ò => O
-"\u00D2" => "O"
-
-# Ó => O
-"\u00D3" => "O"
-
-# Ô => O
-"\u00D4" => "O"
-
-# Õ => O
-"\u00D5" => "O"
-
-# Ö => O
-"\u00D6" => "O"
-
-# Ø => O
-"\u00D8" => "O"
-
-# Π=> OE
-"\u0152" => "OE"
-
-# Þ
-"\u00DE" => "TH"
-
-# Ù => U
-"\u00D9" => "U"
-
-# Ú => U
-"\u00DA" => "U"
-
-# Û => U
-"\u00DB" => "U"
-
-# Ü => U
-"\u00DC" => "U"
-
-# Ý => Y
-"\u00DD" => "Y"
-
-# Ÿ => Y
-"\u0178" => "Y"
-
-# à => a
-"\u00E0" => "a"
-
-# á => a
-"\u00E1" => "a"
-
-# â => a
-"\u00E2" => "a"
-
-# ã => a
-"\u00E3" => "a"
-
-# ä => a
-"\u00E4" => "a"
-
-# å => a
-"\u00E5" => "a"
-
-# æ => ae
-"\u00E6" => "ae"
-
-# ç => c
-"\u00E7" => "c"
-
-# è => e
-"\u00E8" => "e"
-
-# é => e
-"\u00E9" => "e"
-
-# ê => e
-"\u00EA" => "e"
-
-# ë => e
-"\u00EB" => "e"
-
-# ì => i
-"\u00EC" => "i"
-
-# í => i
-"\u00ED" => "i"
-
-# î => i
-"\u00EE" => "i"
-
-# ï => i
-"\u00EF" => "i"
-
-# ij => ij
-"\u0133" => "ij"
-
-# ð => d
-"\u00F0" => "d"
-
-# ñ => n
-"\u00F1" => "n"
-
-# ò => o
-"\u00F2" => "o"
-
-# ó => o
-"\u00F3" => "o"
-
-# ô => o
-"\u00F4" => "o"
-
-# õ => o
-"\u00F5" => "o"
-
-# ö => o
-"\u00F6" => "o"
-
-# ø => o
-"\u00F8" => "o"
-
-# œ => oe
-"\u0153" => "oe"
-
-# ß => ss
-"\u00DF" => "ss"
-
-# þ => th
-"\u00FE" => "th"
-
-# ù => u
-"\u00F9" => "u"
-
-# ú => u
-"\u00FA" => "u"
-
-# û => u
-"\u00FB" => "u"
-
-# ü => u
-"\u00FC" => "u"
-
-# ý => y
-"\u00FD" => "y"
-
-# ÿ => y
-"\u00FF" => "y"
-
-# ff => ff
-"\uFB00" => "ff"
-
-# fi => fi
-"\uFB01" => "fi"
-
-# fl => fl
-"\uFB02" => "fl"
-
-# ffi => ffi
-"\uFB03" => "ffi"
-
-# ffl => ffl
-"\uFB04" => "ffl"
-
-# ſt => ft
-"\uFB05" => "ft"
-
-# st => st
-"\uFB06" => "st"
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/protwords.txt b/solr_config/core0/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr_config/core0/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/schema.xml b/solr_config/core0/conf/schema.xml
deleted file mode 100644
index e2e0d79..0000000
--- a/solr_config/core0/conf/schema.xml
+++ /dev/null
@@ -1,503 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
--->
-
-<schema name="example" version="1.1">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- Applications should change this to reflect the nature of the search collection.
- version="1.1" 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 -->
-
- <types>
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in the
- org.apache.solr.analysis package.
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- - StrField and TextField support an optional compressThreshold which
- limits compression (if enabled in the derived fields) to values which
- exceed a certain size (in characters).
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- The optional sortMissingLast and sortMissingFirst attributes are
- currently supported on types that are sorted internally as strings.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
-
- <!-- numeric field types that store and index the text
- value verbatim (and hence don't support range queries, since the
- lexicographic ordering isn't equal to the numeric ordering) -->
- <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
- <fieldType name="int" class="solr.IntField" omitNorms="true"/>
- <fieldType name="long" class="solr.LongField" omitNorms="true"/>
- <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
- <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
-
-
- <!-- Numeric field types that manipulate the value into
- a string value that isn't human-readable in its internal form,
- but with a lexicographic ordering the same as the numeric ordering,
- so that range queries work correctly. -->
- <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
- -->
- <!--
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- -->
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the DateField javadocs for more information.
- -->
- <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
-
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate psuedo-random orderings of your docs for sorting
- purposes. The ordering is generated based on the field name
- and the version of the index, As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want differend psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the name
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
- so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
- Synonyms and stopwords are customized by external files, and stemming is enabled.
- Duplicate tokens at the same position (which may result from Stemmed Synonyms or
- WordDelim parts) are removed.
- -->
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- enablePositionIncrements=true ensures that a 'gap' is left to
- allow for accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general unstemmed text field - good if one does not know the language of the field -->
- <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general unstemmed text field that indexes tokens normally and also
- reversed (via ReversedWildcardFilterFactory), to enable more efficient
- leading wildcard queries. -->
- <!--
- <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
-
- <!--
- <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldtype>
- -->
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Setup simple analysis for spell checking
- -->
- <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back refrences to portions of the orriginal
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- infomation on pattern and replacement string syntax.
-
- http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed, any data added to
- them will be ignored outright
- -->
- <fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
-
- </types>
-
-
- <fields>
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a previously defined type from the <types> section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- compressed: [false] if this field should be stored using gzip compression
- (this will only apply if the field type is compressable; among
- the standard field types, only TextField and StrField are)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- termVectors: [false] set to true to store the term vector for a given field.
- When using MoreLikeThis, fields used for similarity should be stored for
- best performance.
- -->
-
- <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
- <field name="description" type="text" indexed="true" stored="true" />
- <field name="group_id" type="integer" indexed="true" stored="true"/>
- <field name="group_ranking" type="integer" indexed="true" stored="true"/>
- <field name="has_file" type="integer" indexed="true" stored="true"/>
- <field name="help_wanted" type="boolean" indexed="true" stored="true" />
- <field name="latest_file_date" type="date" indexed="true" stored="true" />
- <field name="license" type="string" indexed="true" stored="true" />
- <field name="license_other" type="string" indexed="true" stored="true" />
- <field name="name" type="text" indexed="true" stored="true"/>
- <field name="num_developers" type="integer" indexed="true" stored="true"/>
- <field name="num_downloads" type="integer" indexed="true" stored="true"/>
- <field name="num_downloads_week" type="integer" indexed="true" stored="true"/>
- <field name="num_services" type="integer" indexed="true" stored="true"/>
- <field name="percentile" type="float" indexed="true" stored="true"/>
- <field name="project_type" type="integer" indexed="true" stored="true" />
- <field name="project_doc_id" type="string" indexed="true" stored="true" />
- <field name="registration_date" type="date" indexed="true" stored="true" />
- <field name="screenshot_url" type="string" indexed="true" stored="true" />
- <field name="trove" type="text" indexed="true" stored="true" />
- <field name="unix_group_name" type="string" indexed="true" stored="true" />
- <field name="source" type="string" indexed="true" stored="true" />
- <field name="rating" type="float" indexed="true" stored="true" />
- <field name="review_count" type="integer" indexed="true" stored="true" />
-
- <field name="id" type="string" indexed="true" stored="true" required="true" />
- <field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
- <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
- <field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
- <field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
- <field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
-
- <field name="weight" type="float" indexed="true" stored="true"/>
- <field name="price" type="float" indexed="true" stored="true"/>
- <field name="popularity" type="int" indexed="true" stored="true" />
- <field name="inStock" type="boolean" indexed="true" stored="true" />
-
- <!-- Common metadata fields, named specifically to match up with
- SolrCell metadata when parsing rich documents such as Word, PDF.
- Some fields are multiValued only because Tika currently may return
- multiple values for them.
- -->
- <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
- <field name="comments" type="text" indexed="true" stored="true"/>
- <field name="author" type="textgen" indexed="true" stored="true"/>
- <field name="keywords" type="textgen" indexed="true" stored="true"/>
- <field name="category" type="textgen" indexed="true" stored="true"/>
- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="last_modified" type="date" indexed="true" stored="true"/>
- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
-
-
- <!-- catchall field, containing all other searchable text fields (implemented
- via copyField further on in this schema -->
- <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
-
- <!-- catchall text field that indexes tokens both normally and in reverse for efficient
- leading wildcard queries. -->
- <!--
- <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
- -->
-
- <!-- non-tokenized version of manufacturer to make it easier to sort or group
- results by manufacturer. copied from "manu" via copyField -->
- <field name="manu_exact" type="string" indexed="true" stored="false"/>
-
- <!--
- <field name="payloads" type="payloads" indexed="true" stored="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.
- -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <!--
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
-
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
- -->
-
- </fields>
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
- <defaultSearchField>text</defaultSearchField>
-
- <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
- <solrQueryParser defaultOperator="OR"/>
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching. -->
-
- <copyField source="cat" dest="text"/>
- <copyField source="name" dest="text"/>
- <copyField source="manu" dest="text"/>
- <copyField source="features" dest="text"/>
- <copyField source="includes" dest="text"/>
- <copyField source="manu" dest="manu_exact"/>
-
-</schema>
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/solrconfig.xml b/solr_config/core0/conf/solrconfig.xml
deleted file mode 100644
index 0864ca2..0000000
--- a/solr_config/core0/conf/solrconfig.xml
+++ /dev/null
@@ -1,40 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is a stripped down config file used for a simple example...
- It is *not* a good example to work from.
--->
-<config>
- <updateHandler class="solr.DirectUpdateHandler2" />
-
- <requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
- </requestDispatcher>
-
- <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
- <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
- <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
-
- <!-- config for the admin interface -->
- <admin>
- <defaultQuery>solr</defaultQuery>
- </admin>
-
-</config>
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/spellings.txt
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/spellings.txt b/solr_config/core0/conf/spellings.txt
deleted file mode 100644
index d7ede6f..0000000
--- a/solr_config/core0/conf/spellings.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-pizza
-history
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/stopwords.txt b/solr_config/core0/conf/stopwords.txt
deleted file mode 100644
index b5824da..0000000
--- a/solr_config/core0/conf/stopwords.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-#Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-s
-such
-t
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core0/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr_config/core0/conf/synonyms.txt b/solr_config/core0/conf/synonyms.txt
deleted file mode 100644
index b0e31cb..0000000
--- a/solr_config/core0/conf/synonyms.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaa => aaaa
-bbb => bbbb1 bbbb2
-ccc => cccc1,cccc2
-a\=>a => b\=>b
-a\,a => b\,b
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/mapping-ISOLatin1Accent.txt
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/mapping-ISOLatin1Accent.txt b/solr_config/core1/conf/mapping-ISOLatin1Accent.txt
deleted file mode 100644
index ede7742..0000000
--- a/solr_config/core1/conf/mapping-ISOLatin1Accent.txt
+++ /dev/null
@@ -1,246 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Syntax:
-# "source" => "target"
-# "source".length() > 0 (source cannot be empty.)
-# "target".length() >= 0 (target can be empty.)
-
-# example:
-# "À" => "A"
-# "\u00C0" => "A"
-# "\u00C0" => "\u0041"
-# "ß" => "ss"
-# "\t" => " "
-# "\n" => ""
-
-# À => A
-"\u00C0" => "A"
-
-# Á => A
-"\u00C1" => "A"
-
-# Â => A
-"\u00C2" => "A"
-
-# Ã => A
-"\u00C3" => "A"
-
-# Ä => A
-"\u00C4" => "A"
-
-# Å => A
-"\u00C5" => "A"
-
-# Æ => AE
-"\u00C6" => "AE"
-
-# Ç => C
-"\u00C7" => "C"
-
-# È => E
-"\u00C8" => "E"
-
-# É => E
-"\u00C9" => "E"
-
-# Ê => E
-"\u00CA" => "E"
-
-# Ë => E
-"\u00CB" => "E"
-
-# Ì => I
-"\u00CC" => "I"
-
-# Í => I
-"\u00CD" => "I"
-
-# Î => I
-"\u00CE" => "I"
-
-# Ï => I
-"\u00CF" => "I"
-
-# IJ => IJ
-"\u0132" => "IJ"
-
-# Ð => D
-"\u00D0" => "D"
-
-# Ñ => N
-"\u00D1" => "N"
-
-# Ò => O
-"\u00D2" => "O"
-
-# Ó => O
-"\u00D3" => "O"
-
-# Ô => O
-"\u00D4" => "O"
-
-# Õ => O
-"\u00D5" => "O"
-
-# Ö => O
-"\u00D6" => "O"
-
-# Ø => O
-"\u00D8" => "O"
-
-# Π=> OE
-"\u0152" => "OE"
-
-# Þ
-"\u00DE" => "TH"
-
-# Ù => U
-"\u00D9" => "U"
-
-# Ú => U
-"\u00DA" => "U"
-
-# Û => U
-"\u00DB" => "U"
-
-# Ü => U
-"\u00DC" => "U"
-
-# Ý => Y
-"\u00DD" => "Y"
-
-# Ÿ => Y
-"\u0178" => "Y"
-
-# à => a
-"\u00E0" => "a"
-
-# á => a
-"\u00E1" => "a"
-
-# â => a
-"\u00E2" => "a"
-
-# ã => a
-"\u00E3" => "a"
-
-# ä => a
-"\u00E4" => "a"
-
-# å => a
-"\u00E5" => "a"
-
-# æ => ae
-"\u00E6" => "ae"
-
-# ç => c
-"\u00E7" => "c"
-
-# è => e
-"\u00E8" => "e"
-
-# é => e
-"\u00E9" => "e"
-
-# ê => e
-"\u00EA" => "e"
-
-# ë => e
-"\u00EB" => "e"
-
-# ì => i
-"\u00EC" => "i"
-
-# í => i
-"\u00ED" => "i"
-
-# î => i
-"\u00EE" => "i"
-
-# ï => i
-"\u00EF" => "i"
-
-# ij => ij
-"\u0133" => "ij"
-
-# ð => d
-"\u00F0" => "d"
-
-# ñ => n
-"\u00F1" => "n"
-
-# ò => o
-"\u00F2" => "o"
-
-# ó => o
-"\u00F3" => "o"
-
-# ô => o
-"\u00F4" => "o"
-
-# õ => o
-"\u00F5" => "o"
-
-# ö => o
-"\u00F6" => "o"
-
-# ø => o
-"\u00F8" => "o"
-
-# œ => oe
-"\u0153" => "oe"
-
-# ß => ss
-"\u00DF" => "ss"
-
-# þ => th
-"\u00FE" => "th"
-
-# ù => u
-"\u00F9" => "u"
-
-# ú => u
-"\u00FA" => "u"
-
-# û => u
-"\u00FB" => "u"
-
-# ü => u
-"\u00FC" => "u"
-
-# ý => y
-"\u00FD" => "y"
-
-# ÿ => y
-"\u00FF" => "y"
-
-# ff => ff
-"\uFB00" => "ff"
-
-# fi => fi
-"\uFB01" => "fi"
-
-# fl => fl
-"\uFB02" => "fl"
-
-# ffi => ffi
-"\uFB03" => "ffi"
-
-# ffl => ffl
-"\uFB04" => "ffl"
-
-# ſt => ft
-"\uFB05" => "ft"
-
-# st => st
-"\uFB06" => "st"
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/protwords.txt b/solr_config/core1/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr_config/core1/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/schema.xml b/solr_config/core1/conf/schema.xml
deleted file mode 100644
index e2e0d79..0000000
--- a/solr_config/core1/conf/schema.xml
+++ /dev/null
@@ -1,503 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
--->
-
-<schema name="example" version="1.1">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- Applications should change this to reflect the nature of the search collection.
- version="1.1" 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 -->
-
- <types>
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in the
- org.apache.solr.analysis package.
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- - StrField and TextField support an optional compressThreshold which
- limits compression (if enabled in the derived fields) to values which
- exceed a certain size (in characters).
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- The optional sortMissingLast and sortMissingFirst attributes are
- currently supported on types that are sorted internally as strings.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
-
- <!-- numeric field types that store and index the text
- value verbatim (and hence don't support range queries, since the
- lexicographic ordering isn't equal to the numeric ordering) -->
- <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
- <fieldType name="int" class="solr.IntField" omitNorms="true"/>
- <fieldType name="long" class="solr.LongField" omitNorms="true"/>
- <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
- <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
-
-
- <!-- Numeric field types that manipulate the value into
- a string value that isn't human-readable in its internal form,
- but with a lexicographic ordering the same as the numeric ordering,
- so that range queries work correctly. -->
- <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
- -->
- <!--
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- -->
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the DateField javadocs for more information.
- -->
- <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
-
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate psuedo-random orderings of your docs for sorting
- purposes. The ordering is generated based on the field name
- and the version of the index, As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want differend psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the name
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
- so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
- Synonyms and stopwords are customized by external files, and stemming is enabled.
- Duplicate tokens at the same position (which may result from Stemmed Synonyms or
- WordDelim parts) are removed.
- -->
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- enablePositionIncrements=true ensures that a 'gap' is left to
- allow for accurate phrase queries.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general unstemmed text field - good if one does not know the language of the field -->
- <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general unstemmed text field that indexes tokens normally and also
- reversed (via ReversedWildcardFilterFactory), to enable more efficient
- leading wildcard queries. -->
- <!--
- <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- enablePositionIncrements="true"
- />
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
-
- <!--
- <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldtype>
- -->
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Setup simple analysis for spell checking
- -->
- <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back refrences to portions of the orriginal
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- infomation on pattern and replacement string syntax.
-
- http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed, any data added to
- them will be ignored outright
- -->
- <fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
-
- </types>
-
-
- <fields>
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a previously defined type from the <types> section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- compressed: [false] if this field should be stored using gzip compression
- (this will only apply if the field type is compressable; among
- the standard field types, only TextField and StrField are)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- termVectors: [false] set to true to store the term vector for a given field.
- When using MoreLikeThis, fields used for similarity should be stored for
- best performance.
- -->
-
- <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
- <field name="description" type="text" indexed="true" stored="true" />
- <field name="group_id" type="integer" indexed="true" stored="true"/>
- <field name="group_ranking" type="integer" indexed="true" stored="true"/>
- <field name="has_file" type="integer" indexed="true" stored="true"/>
- <field name="help_wanted" type="boolean" indexed="true" stored="true" />
- <field name="latest_file_date" type="date" indexed="true" stored="true" />
- <field name="license" type="string" indexed="true" stored="true" />
- <field name="license_other" type="string" indexed="true" stored="true" />
- <field name="name" type="text" indexed="true" stored="true"/>
- <field name="num_developers" type="integer" indexed="true" stored="true"/>
- <field name="num_downloads" type="integer" indexed="true" stored="true"/>
- <field name="num_downloads_week" type="integer" indexed="true" stored="true"/>
- <field name="num_services" type="integer" indexed="true" stored="true"/>
- <field name="percentile" type="float" indexed="true" stored="true"/>
- <field name="project_type" type="integer" indexed="true" stored="true" />
- <field name="project_doc_id" type="string" indexed="true" stored="true" />
- <field name="registration_date" type="date" indexed="true" stored="true" />
- <field name="screenshot_url" type="string" indexed="true" stored="true" />
- <field name="trove" type="text" indexed="true" stored="true" />
- <field name="unix_group_name" type="string" indexed="true" stored="true" />
- <field name="source" type="string" indexed="true" stored="true" />
- <field name="rating" type="float" indexed="true" stored="true" />
- <field name="review_count" type="integer" indexed="true" stored="true" />
-
- <field name="id" type="string" indexed="true" stored="true" required="true" />
- <field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
- <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
- <field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
- <field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
- <field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
-
- <field name="weight" type="float" indexed="true" stored="true"/>
- <field name="price" type="float" indexed="true" stored="true"/>
- <field name="popularity" type="int" indexed="true" stored="true" />
- <field name="inStock" type="boolean" indexed="true" stored="true" />
-
- <!-- Common metadata fields, named specifically to match up with
- SolrCell metadata when parsing rich documents such as Word, PDF.
- Some fields are multiValued only because Tika currently may return
- multiple values for them.
- -->
- <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
- <field name="comments" type="text" indexed="true" stored="true"/>
- <field name="author" type="textgen" indexed="true" stored="true"/>
- <field name="keywords" type="textgen" indexed="true" stored="true"/>
- <field name="category" type="textgen" indexed="true" stored="true"/>
- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="last_modified" type="date" indexed="true" stored="true"/>
- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
-
-
- <!-- catchall field, containing all other searchable text fields (implemented
- via copyField further on in this schema -->
- <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
-
- <!-- catchall text field that indexes tokens both normally and in reverse for efficient
- leading wildcard queries. -->
- <!--
- <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
- -->
-
- <!-- non-tokenized version of manufacturer to make it easier to sort or group
- results by manufacturer. copied from "manu" via copyField -->
- <field name="manu_exact" type="string" indexed="true" stored="false"/>
-
- <!--
- <field name="payloads" type="payloads" indexed="true" stored="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.
- -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <!--
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
-
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
- -->
-
- </fields>
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
- <defaultSearchField>text</defaultSearchField>
-
- <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
- <solrQueryParser defaultOperator="OR"/>
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching. -->
-
- <copyField source="cat" dest="text"/>
- <copyField source="name" dest="text"/>
- <copyField source="manu" dest="text"/>
- <copyField source="features" dest="text"/>
- <copyField source="includes" dest="text"/>
- <copyField source="manu" dest="manu_exact"/>
-
-</schema>
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/solrconfig.xml b/solr_config/core1/conf/solrconfig.xml
deleted file mode 100644
index 0864ca2..0000000
--- a/solr_config/core1/conf/solrconfig.xml
+++ /dev/null
@@ -1,40 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is a stripped down config file used for a simple example...
- It is *not* a good example to work from.
--->
-<config>
- <updateHandler class="solr.DirectUpdateHandler2" />
-
- <requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
- </requestDispatcher>
-
- <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
- <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
- <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
-
- <!-- config for the admin interface -->
- <admin>
- <defaultQuery>solr</defaultQuery>
- </admin>
-
-</config>
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/spellings.txt
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/spellings.txt b/solr_config/core1/conf/spellings.txt
deleted file mode 100644
index d7ede6f..0000000
--- a/solr_config/core1/conf/spellings.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-pizza
-history
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/stopwords.txt b/solr_config/core1/conf/stopwords.txt
deleted file mode 100644
index b5824da..0000000
--- a/solr_config/core1/conf/stopwords.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-#Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-s
-such
-t
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
-
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/core1/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr_config/core1/conf/synonyms.txt b/solr_config/core1/conf/synonyms.txt
deleted file mode 100644
index b0e31cb..0000000
--- a/solr_config/core1/conf/synonyms.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaa => aaaa
-bbb => bbbb1 bbbb2
-ccc => cccc1,cccc2
-a\=>a => b\=>b
-a\,a => b\,b
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
[11/11] git commit: [#4321] Change solr type of 'labels' field
Posted by jo...@apache.org.
[#4321] Change solr type of 'labels' field
Change to white-space-tokenized string field instead of text
field to get exact whole-word matching without stemming.
Copyfield added to solr schema to create new _ws on the fly
during reindexing, while still allowing the existing code
to work with the existing _t field.
After reindexing is complete, do a global
s/labels_t/labels_ws/ on the project (already tested).
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/16ea2661
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/16ea2661
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/16ea2661
Branch: refs/heads/master
Commit: 16ea2661b75dbeb0677ae2cc25f9c188e54058c7
Parents: 8a76480
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Thu May 2 08:12:28 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:01 2013 +0000
----------------------------------------------------------------------
Allura/allura/model/artifact.py | 7 ++--
Allura/allura/tests/unit/test_artifact.py | 29 +++++++++++++++
ForgeTracker/forgetracker/tracker_main.py | 4 +-
ForgeTracker/forgetracker/widgets/ticket_search.py | 2 +-
solr_config/schema.xml | 2 +
vagrant/start_allura | 2 +-
6 files changed, 38 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/Allura/allura/model/artifact.py
----------------------------------------------------------------------
diff --git a/Allura/allura/model/artifact.py b/Allura/allura/model/artifact.py
index 681ac26..2acd9d8 100644
--- a/Allura/allura/model/artifact.py
+++ b/Allura/allura/model/artifact.py
@@ -111,10 +111,9 @@ class Artifact(MappedClass):
@classmethod
def translate_query(cls, q, fields):
for f in fields:
- if f[-2] == '_':
- base = f[:-2]
- actual = f
- q = q.replace(base+':', actual+':')
+ if '_' in f:
+ base, typ = f.rsplit('_', 1)
+ q = q.replace(base + ':', f + ':')
return q
@LazyProperty
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/Allura/allura/tests/unit/test_artifact.py
----------------------------------------------------------------------
diff --git a/Allura/allura/tests/unit/test_artifact.py b/Allura/allura/tests/unit/test_artifact.py
new file mode 100644
index 0000000..6e470c0
--- /dev/null
+++ b/Allura/allura/tests/unit/test_artifact.py
@@ -0,0 +1,29 @@
+# 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.
+
+import unittest
+
+from allura import model as M
+
+
+class TestArtifact(unittest.TestCase):
+
+ def test_translate_query(self):
+ fields = ['foo_s', 'bar_ws']
+ query = 'foo:1 AND bar:2 AND foo_bar_baz:3'
+ q = M.Artifact.translate_query(query, fields)
+ self.assertEqual(q, 'foo_s:1 AND bar_ws:2 AND foo_bar_baz:3')
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/ForgeTracker/forgetracker/tracker_main.py
----------------------------------------------------------------------
diff --git a/ForgeTracker/forgetracker/tracker_main.py b/ForgeTracker/forgetracker/tracker_main.py
index 3f64528..f76cf74 100644
--- a/ForgeTracker/forgetracker/tracker_main.py
+++ b/ForgeTracker/forgetracker/tracker_main.py
@@ -113,7 +113,7 @@ def _mongo_col_to_solr_col(name):
elif name == 'mod_date':
return 'mod_date_dt'
elif name == 'labels':
- return 'labels_s'
+ return 'labels_t'
else:
for field in c.app.globals.sortable_custom_fields_shown_in_search():
if name == field['name']:
@@ -458,7 +458,7 @@ def solr_columns():
label='Updated',
active=c.app.globals.show_in_search['mod_date']),
dict(name='labels',
- sort_name='labels_s',
+ sort_name='labels_t',
label='Labels',
active=c.app.globals.show_in_search['labels']),
]
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/ForgeTracker/forgetracker/widgets/ticket_search.py
----------------------------------------------------------------------
diff --git a/ForgeTracker/forgetracker/widgets/ticket_search.py b/ForgeTracker/forgetracker/widgets/ticket_search.py
index 0417094..4444a60 100644
--- a/ForgeTracker/forgetracker/widgets/ticket_search.py
+++ b/ForgeTracker/forgetracker/widgets/ticket_search.py
@@ -122,7 +122,7 @@ class SearchHelp(ffw.Lightbox):
<h2>Sorting search results</h2>
<p>Ticket search results can be sorted by clicking the header of the column you want to sort by. The first click will sort the results in ascending order. Clicking the header again will sort the column in descending order. In addition to sorting by the column headers, you can manually sort on these properties:</p>
<ul>
-<li>Labels assigned to the ticket - labels_s</li>
+<li>Labels assigned to the ticket - labels_t</li>
<li>Milestone the ticket is assigned to - _milestone_s</li>
<li>Last modified date - mod_date_dt</li>
<li>Body of the ticket - text_s</li>
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/solr_config/schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/schema.xml b/solr_config/schema.xml
index 45aca76..005eab0 100644
--- a/solr_config/schema.xml
+++ b/solr_config/schema.xml
@@ -203,6 +203,7 @@
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
</fields>
@@ -240,6 +241,7 @@
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
<!-- <copyField source="name" dest="alphaNameSort"/> -->
+ <copyField source="labels_t" dest="labels_ws"/>
<types>
<!-- field type definitions. The "name" attribute is
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/16ea2661/vagrant/start_allura
----------------------------------------------------------------------
diff --git a/vagrant/start_allura b/vagrant/start_allura
index c396f7a..c3f7016 100755
--- a/vagrant/start_allura
+++ b/vagrant/start_allura
@@ -31,7 +31,7 @@ fi
echo "Logs are in /var/log/allura"
# Start solr
-if pgrep -f solr.*start.jar >/dev/null
+if pgrep -f start.jar >/dev/null
then
echo "Solr is running."
else
[06/11] git commit: [#3854] Add new solr schema from siteops
Posted by jo...@apache.org.
[#3854] Add new solr schema from siteops
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/3b02a00c
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/3b02a00c
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/3b02a00c
Branch: refs/heads/master
Commit: 3b02a00cfcff85d74bd7490beb132f75cfa1fcaf
Parents: 2251ba0
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Thu Apr 25 20:56:59 2013 +0000
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
solr_config/forge-schema.xml | 1080 +++++++++++++++++++++++++++++++++++++
1 files changed, 1080 insertions(+), 0 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/3b02a00c/solr_config/forge-schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/forge-schema.xml b/solr_config/forge-schema.xml
new file mode 100644
index 0000000..1337ba3
--- /dev/null
+++ b/solr_config/forge-schema.xml
@@ -0,0 +1,1080 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking. To improve performance one could
+ - set stored="false" for all fields possible (esp large fields) when you
+ only need to search on the field but don't need to return the original
+ value.
+ - set indexed="false" if you don't need to search on the field, but only
+ return the field as a result of searching on other indexed fields.
+ - remove all unneeded copyField statements
+ - for best index size and searching performance, set "index" to false
+ for all general text fields, use copyField to copy them to the
+ catchall "text" field, and use that for searching.
+ - For maximum indexing performance, use the StreamingUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="forge" version="1.5">
+ <!-- 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...)
+ -->
+
+ <fields>
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ <types> fieldType section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful for faceting, grouping, sorting and function queries. Although not
+ required, 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
+ and all Trie*Fields, and depending on the field type, they might
+ require the field to be single-valued, be required or have a default
+ value (check the documentation of the field type you're interested in
+ for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+ <!-- Required field values for SOLR, DO NOT REMOVE -->
+ <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
+ <!-- END of required field values -->
+
+ <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
+ <field name="description" type="text_general" indexed="true" stored="true" />
+ <field name="group_id" type="tint" indexed="true" stored="true"/>
+ <field name="group_ranking" type="tint" indexed="true" stored="true"/>
+ <field name="has_file" type="tint" indexed="true" stored="true"/>
+ <field name="help_wanted" type="boolean" indexed="true" stored="true" />
+ <field name="latest_file_date" type="date" indexed="true" stored="true" />
+ <field name="license" type="string" indexed="true" stored="true" />
+ <field name="license_other" type="string" indexed="true" stored="true" />
+ <field name="name" type="text_general" indexed="true" stored="true"/>
+ <field name="num_developers" type="tint" indexed="true" stored="true"/>
+ <field name="num_downloads" type="tint" indexed="true" stored="true"/>
+ <field name="num_downloads_week" type="tint" indexed="true" stored="true"/>
+ <field name="num_services" type="tint" indexed="true" stored="true"/>
+ <field name="percentile" type="float" indexed="true" stored="true"/>
+ <field name="project_type" type="tint" indexed="true" stored="true" />
+ <field name="project_doc_id" type="string" indexed="true" stored="true" />
+ <field name="registration_date" type="date" indexed="true" stored="true" />
+ <field name="screenshot_url" type="string" indexed="true" stored="true" />
+ <field name="trove" type="text_general" indexed="true" stored="true" />
+ <field name="unix_group_name" type="string" indexed="true" stored="true" />
+ <field name="source" type="string" indexed="true" stored="true" />
+ <field name="rating" type="float" indexed="true" stored="true" />
+ <field name="review_count" type="tint" indexed="true" stored="true" />
+
+ <!-- Common metadata fields, named specifically to match up with
+ SolrCell metadata when parsing rich documents such as Word, PDF.
+ Some fields are multiValued only because Tika currently may return
+ multiple values for them. Some metadata is parsed from the documents,
+ but there are some which come from the client context:
+ "content_type": From the HTTP headers of incoming stream
+ "resourcename": From SolrCell request param resource.name
+ -->
+ <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
+ <field name="subject" type="text_general" indexed="true" stored="true"/>
+ <field name="comments" type="text_general" indexed="true" stored="true"/>
+ <field name="author" type="text_general" indexed="true" stored="true"/>
+ <field name="keywords" type="text_general" indexed="true" stored="true"/>
+ <field name="category" type="text_general" indexed="true" stored="true"/>
+ <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="last_modified" type="date" indexed="true" stored="true"/>
+ <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
+
+ <!-- Main body of document extracted by SolrCell.
+ NOTE: This field is not indexed by default, since it is also copied to "text"
+ using copyField below. This is to save space. Use this field for returning and
+ highlighting document content. Use the "text" field to search the content. -->
+
+
+ <!-- catchall field, containing all other searchable text fields (implemented
+ via copyField further on in this schema -->
+
+ <!-- catchall text field that indexes tokens both normally and in reverse for efficient
+ leading wildcard queries. -->
+
+ <!-- non-tokenized version of manufacturer to make it easier to sort or group
+ results by manufacturer. copied from "manu" via copyField -->
+ <!--
+ Some fields such as popularity and manu_exact could be modified to
+ leverage doc values:
+ <field name="popularity" type="int" indexed="true" stored="true" docValues="true" default="0" />
+ <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" default="" />
+
+ Although it would make indexing slightly slower and the index bigger, it
+ would also make the index faster to load, more memory-efficient and more
+ NRT-friendly.
+ -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
+
+ <!-- some trie-coded dynamic fields for faster range queries -->
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+
+ </fields>
+
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
+ parsing a query string that isn't explicit about the field. Machine (non-user)
+ generated queries are best made explicit, or they can use the "df" request parameter
+ which takes precedence over this.
+ Note: Un-commenting defaultSearchField will be insufficient if your request handler
+ in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
+ <defaultSearchField>text</defaultSearchField> -->
+
+ <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
+ when parsing a query string to determine if a clause of the query should be marked as
+ required or optional, assuming the clause isn't already marked by some operator.
+ The default is OR, which is generally assumed so it is not a good idea to change it
+ globally here. The "q.op" request parameter takes precedence over this.
+ <solrQueryParser defaultOperator="OR"/> -->
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching. -->
+
+ <!-- Above, multiple source fields are copied to the [text] field.
+ Another way to map multiple source fields to the same
+ destination field is to use the dynamic field syntax.
+ copyField also supports a maxChars to copy setting. -->
+
+ <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
+
+ <!-- copy name to alphaNameSort, a field designed for sorting by name -->
+ <!-- <copyField source="name" dest="alphaNameSort"/> -->
+
+ <types>
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", and, as of 3.5 (and 4.x),
+ int, float, long, date, double, including the "Trie" variants.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+
+ These fields support doc values, but they require the field to be
+ single-valued and either be required or have a default value.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the DateField javadocs for more information.
+
+ Note: For faster range queries, consider the tdate type
+ -->
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
+
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldtype name="binary" class="solr.BinaryField"/>
+
+ <!--
+ Note:
+ These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
+ Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
+
+ Plain numeric field types that store and index the text
+ value verbatim (and hence don't correctly support range queries, since the
+ lexicographic ordering isn't equal to the numeric ordering)
+ -->
+ <fieldType name="pint" class="solr.IntField"/>
+ <fieldType name="plong" class="solr.LongField"/>
+ <fieldType name="pfloat" class="solr.FloatField"/>
+ <fieldType name="pdouble" class="solr.DoubleField"/>
+ <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ 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" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms. -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries. -->
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- charFilter + WhitespaceTokenizer -->
+ <!--
+ <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
+ <analyzer>
+ <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ -->
+
+ <!-- This is an example of using the KeywordTokenizer along
+ With various TokenFilterFactories to produce a sortable field
+ that does not include some properties of the source text
+ -->
+ <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+ <analyzer>
+ <!-- KeywordTokenizer does no actual tokenizing, so the entire
+ input string is preserved as a single token
+ -->
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <!-- The LowerCase TokenFilter does what you expect, which can be
+ when you want your sorting to be case insensitive
+ -->
+ <filter class="solr.LowerCaseFilterFactory" />
+ <!-- The TrimFilter removes any leading or trailing whitespace -->
+ <filter class="solr.TrimFilterFactory" />
+ <!-- The PatternReplaceFilter gives you the flexibility to use
+ Java Regular expression to replace any sequence of characters
+ matching a pattern with an arbitrary replacement string,
+ which may include back references to portions of the original
+ string matched by the pattern.
+
+ See the Java Regular Expression documentation for more
+ information on pattern and replacement string syntax.
+
+ http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
+ -->
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-z])" replacement="" replace="all"
+ />
+ </analyzer>
+ </fieldType>
+
+ <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+ </analyzer>
+ </fieldtype>
+
+ <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!--
+ The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
+ a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
+ Attributes of the DelimitedPayloadTokenFilterFactory :
+ "delimiter" - a one character delimiter. Default is | (pipe)
+ "encoder" - how to encode the following value into a playload
+ float -> org.apache.lucene.analysis.payloads.FloatEncoder,
+ integer -> o.a.l.a.p.IntegerEncoder
+ identity -> o.a.l.a.p.IdentityEncoder
+ Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
+ -->
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+ </analyzer>
+ </fieldtype>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldtype name="ignored" stored="false" indexed="false" 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.
+ -->
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
+ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
+
+ <!-- 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="0.000009" units="degrees" />
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ 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.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your query
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ OR if you would like to optimize for recall (default).
+ -->
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ThaiWordFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ </types>
+
+ <!-- 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>
[09/11] git commit: [#3854] Update Solr install instructions in README
Posted by jo...@apache.org.
[#3854] Update Solr install instructions in README
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/b93f82e5
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/b93f82e5
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/b93f82e5
Branch: refs/heads/master
Commit: b93f82e5b317ada1f9465163537db1e7e6e4e20c
Parents: 0177165
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Tue Apr 30 16:33:08 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:01 2013 +0000
----------------------------------------------------------------------
README.markdown | 12 ++++++------
1 files changed, 6 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/b93f82e5/README.markdown
----------------------------------------------------------------------
diff --git a/README.markdown b/README.markdown
index 95d46cf..70c2ba4 100644
--- a/README.markdown
+++ b/README.markdown
@@ -101,13 +101,13 @@ The Allura forge consists of several components, all of which need to be running
We have a custom config ready for use.
(anvil)~$ cd ~/src
- (anvil)~/src$ wget http://archive.apache.org/dist/lucene/solr/1.4.1/apache-solr-1.4.1.tgz
- (anvil)~/src$ tar xf apache-solr-1.4.1.tgz
- (anvil)~/src$ cd apache-solr-1.4.1/example/
- (anvil)~/src/apache-solr-1.4.1/example/$ mkdir -p ~/src/allura/solr_config/conf
- (anvil)~/src/apache-solr-1.4.1/example/$ cp solr/conf/solrconfig.xml ~/src/allura/solr_config/conf/
+ (anvil)~/src$ wget -nv http://archive.apache.org/dist/lucene/solr/4.2.1/solr-4.2.1.tgz
+ (anvil)~/src$ tar xf solr-4.2.1.tgz && rm -f solr-4.2.1.tgz
+ (anvil)~/src$ cp -f allura/solr_config/schema.xml solr-4.2.1/example/solr/collection1/conf
+
+ (anvil)~/src$ cd solr-4.2.1/example/
(anvil)~/src/apache-solr-1.4.1/example/$ mkdir ~/logs/
- (anvil)~/src/apache-solr-1.4.1/example/$ nohup java -Dsolr.solr.home=$(cd;pwd)/src/allura/solr_config -jar start.jar > ~/logs/solr.log &
+ (anvil)~/src/apache-solr-1.4.1/example/$ nohup java -jar start.jar > ~/logs/solr.log &
### Allura task processing
[07/11] git commit: [#3854] Install non-default version of mongo
during vm build
Posted by jo...@apache.org.
[#3854] Install non-default version of mongo during vm build
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/48604f10
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/48604f10
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/48604f10
Branch: refs/heads/master
Commit: 48604f106cccf064b885a145806f6ded518b4b5e
Parents: ac0b252
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Mon Apr 29 22:32:01 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
vagrant/allura_setup.sh | 18 ++++++++++++++++++
vagrant/manifests/ubuntu-1204-server-amd64.pp | 1 -
2 files changed, 18 insertions(+), 1 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/48604f10/vagrant/allura_setup.sh
----------------------------------------------------------------------
diff --git a/vagrant/allura_setup.sh b/vagrant/allura_setup.sh
index d744829..e382fac 100755
--- a/vagrant/allura_setup.sh
+++ b/vagrant/allura_setup.sh
@@ -17,6 +17,24 @@
# specific language governing permissions and limitations
# under the License.
+# Install mongodb
+MONGODB_VERSION=2.2.3
+MONGODB_PKG_URL="deb http://downloads-distro.mongodb.org/repo/ubuntu-upstart dist 10gen"
+MONGODB_SRC_LST=/etc/apt/sources.list.d/10gen.list
+if [ $(mongo --version 2>/dev/null | sed 's/.*: //') != $MONGODB_VERSION ]
+then
+ echo "Installing Mongodb $MONGODB_VERSION..."
+ sudo apt-get -y -q purge mongodb mongodb-clients mongodb-server mongodb-dev
+ sudo apt-get -y -q purge mongodb-10gen
+ sudo apt-get -y -q autoremove
+ rm -rf /var/lib/mongodb/* 2>/dev/null
+ apt-key adv --keyserver keyserver.ubuntu.com --recv 7F0CEB10
+ grep -q "$MONGODB_PKG_URL" $MONGODB_SRC_LST || echo "$MONGODB_PKG_URL" >> $MONGODB_SRC_LST
+ apt-get -y -q update
+ apt-get -y -q install mongodb-10gen=$MONGODB_VERSION
+ echo "mongodb-10gen hold" | dpkg --set-selections
+fi
+
# Install Solr
cd /home/vagrant/src
if [ ! -d solr-4.2.1 ]
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/48604f10/vagrant/manifests/ubuntu-1204-server-amd64.pp
----------------------------------------------------------------------
diff --git a/vagrant/manifests/ubuntu-1204-server-amd64.pp b/vagrant/manifests/ubuntu-1204-server-amd64.pp
index 4031084..e90d374 100644
--- a/vagrant/manifests/ubuntu-1204-server-amd64.pp
+++ b/vagrant/manifests/ubuntu-1204-server-amd64.pp
@@ -38,7 +38,6 @@ $packages = [
"libsasl2-dev",
"libjpeg8-dev",
"zlib1g-dev",
- "mongodb-server",
"python-pip",
"libfreetype6-dev",
"libpng-dev"
[02/11] git commit: [#3854] Update solr url
Posted by jo...@apache.org.
[#3854] Update solr url
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/ac0b252c
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/ac0b252c
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/ac0b252c
Branch: refs/heads/master
Commit: ac0b252c78ec06ce28ca1379d8f06a4c3c5845ba
Parents: 87108f0
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Fri Apr 26 16:34:47 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
Allura/development.ini | 5 +----
1 files changed, 1 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/ac0b252c/Allura/development.ini
----------------------------------------------------------------------
diff --git a/Allura/development.ini b/Allura/development.ini
index b2ac7bf..737a08b 100644
--- a/Allura/development.ini
+++ b/Allura/development.ini
@@ -177,10 +177,7 @@ amqp.enabled = false
openid.realm = http://localhost:8080/
# SOLR setup
-# comma-separated list of servers to push changes to
-solr.server = http://localhost:8983/solr/core0
-# server to read from. Uses solr.server[0] if not specified.
-# solr.query_server =
+solr.server = http://localhost:8983/solr
# commit on every add/delete?
solr.commit = false
# commit add operations within N ms
[03/11] [#3854] Simplify solr setup and upgrade to 4.2.1
Posted by jo...@apache.org.
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/schema.xml b/solr_config/schema.xml
new file mode 100644
index 0000000..45aca76
--- /dev/null
+++ b/solr_config/schema.xml
@@ -0,0 +1,1080 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking. To improve performance one could
+ - set stored="false" for all fields possible (esp large fields) when you
+ only need to search on the field but don't need to return the original
+ value.
+ - set indexed="false" if you don't need to search on the field, but only
+ return the field as a result of searching on other indexed fields.
+ - remove all unneeded copyField statements
+ - for best index size and searching performance, set "index" to false
+ for all general text fields, use copyField to copy them to the
+ catchall "text" field, and use that for searching.
+ - For maximum indexing performance, use the StreamingUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="forge" version="1.5">
+ <!-- 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...)
+ -->
+
+ <fields>
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ <types> fieldType section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful for faceting, grouping, sorting and function queries. Although not
+ required, 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
+ and all Trie*Fields, and depending on the field type, they might
+ require the field to be single-valued, be required or have a default
+ value (check the documentation of the field type you're interested in
+ for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+ <!-- Required field values for SOLR, DO NOT REMOVE -->
+ <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="text" type="text_general" indexed="true" stored="true" multiValued="true"/>
+ <!-- END of required field values -->
+
+ <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
+ <field name="description" type="text_general" indexed="true" stored="true" />
+ <field name="group_id" type="tint" indexed="true" stored="true"/>
+ <field name="group_ranking" type="tint" indexed="true" stored="true"/>
+ <field name="has_file" type="tint" indexed="true" stored="true"/>
+ <field name="help_wanted" type="boolean" indexed="true" stored="true" />
+ <field name="latest_file_date" type="date" indexed="true" stored="true" />
+ <field name="license" type="string" indexed="true" stored="true" />
+ <field name="license_other" type="string" indexed="true" stored="true" />
+ <field name="name" type="text_general" indexed="true" stored="true"/>
+ <field name="num_developers" type="tint" indexed="true" stored="true"/>
+ <field name="num_downloads" type="tint" indexed="true" stored="true"/>
+ <field name="num_downloads_week" type="tint" indexed="true" stored="true"/>
+ <field name="num_services" type="tint" indexed="true" stored="true"/>
+ <field name="percentile" type="float" indexed="true" stored="true"/>
+ <field name="project_type" type="tint" indexed="true" stored="true" />
+ <field name="project_doc_id" type="string" indexed="true" stored="true" />
+ <field name="registration_date" type="date" indexed="true" stored="true" />
+ <field name="screenshot_url" type="string" indexed="true" stored="true" />
+ <field name="trove" type="text_general" indexed="true" stored="true" />
+ <field name="unix_group_name" type="string" indexed="true" stored="true" />
+ <field name="source" type="string" indexed="true" stored="true" />
+ <field name="rating" type="float" indexed="true" stored="true" />
+ <field name="review_count" type="tint" indexed="true" stored="true" />
+
+ <!-- Common metadata fields, named specifically to match up with
+ SolrCell metadata when parsing rich documents such as Word, PDF.
+ Some fields are multiValued only because Tika currently may return
+ multiple values for them. Some metadata is parsed from the documents,
+ but there are some which come from the client context:
+ "content_type": From the HTTP headers of incoming stream
+ "resourcename": From SolrCell request param resource.name
+ -->
+ <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
+ <field name="subject" type="text_general" indexed="true" stored="true"/>
+ <field name="comments" type="text_general" indexed="true" stored="true"/>
+ <field name="author" type="text_general" indexed="true" stored="true"/>
+ <field name="keywords" type="text_general" indexed="true" stored="true"/>
+ <field name="category" type="text_general" indexed="true" stored="true"/>
+ <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="last_modified" type="date" indexed="true" stored="true"/>
+ <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
+
+ <!-- Main body of document extracted by SolrCell.
+ NOTE: This field is not indexed by default, since it is also copied to "text"
+ using copyField below. This is to save space. Use this field for returning and
+ highlighting document content. Use the "text" field to search the content. -->
+
+
+ <!-- catchall field, containing all other searchable text fields (implemented
+ via copyField further on in this schema -->
+
+ <!-- catchall text field that indexes tokens both normally and in reverse for efficient
+ leading wildcard queries. -->
+
+ <!-- non-tokenized version of manufacturer to make it easier to sort or group
+ results by manufacturer. copied from "manu" via copyField -->
+ <!--
+ Some fields such as popularity and manu_exact could be modified to
+ leverage doc values:
+ <field name="popularity" type="int" indexed="true" stored="true" docValues="true" default="0" />
+ <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" default="" />
+
+ Although it would make indexing slightly slower and the index bigger, it
+ would also make the index faster to load, more memory-efficient and more
+ NRT-friendly.
+ -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
+
+ <!-- some trie-coded dynamic fields for faster range queries -->
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+
+ </fields>
+
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
+ parsing a query string that isn't explicit about the field. Machine (non-user)
+ generated queries are best made explicit, or they can use the "df" request parameter
+ which takes precedence over this.
+ Note: Un-commenting defaultSearchField will be insufficient if your request handler
+ in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
+ <defaultSearchField>text</defaultSearchField> -->
+
+ <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
+ when parsing a query string to determine if a clause of the query should be marked as
+ required or optional, assuming the clause isn't already marked by some operator.
+ The default is OR, which is generally assumed so it is not a good idea to change it
+ globally here. The "q.op" request parameter takes precedence over this.
+ <solrQueryParser defaultOperator="OR"/> -->
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching. -->
+
+ <!-- Above, multiple source fields are copied to the [text] field.
+ Another way to map multiple source fields to the same
+ destination field is to use the dynamic field syntax.
+ copyField also supports a maxChars to copy setting. -->
+
+ <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
+
+ <!-- copy name to alphaNameSort, a field designed for sorting by name -->
+ <!-- <copyField source="name" dest="alphaNameSort"/> -->
+
+ <types>
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", and, as of 3.5 (and 4.x),
+ int, float, long, date, double, including the "Trie" variants.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+
+ These fields support doc values, but they require the field to be
+ single-valued and either be required or have a default value.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the DateField javadocs for more information.
+
+ Note: For faster range queries, consider the tdate type
+ -->
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
+
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldtype name="binary" class="solr.BinaryField"/>
+
+ <!--
+ Note:
+ These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
+ Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
+
+ Plain numeric field types that store and index the text
+ value verbatim (and hence don't correctly support range queries, since the
+ lexicographic ordering isn't equal to the numeric ordering)
+ -->
+ <fieldType name="pint" class="solr.IntField"/>
+ <fieldType name="plong" class="solr.LongField"/>
+ <fieldType name="pfloat" class="solr.FloatField"/>
+ <fieldType name="pdouble" class="solr.DoubleField"/>
+ <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ 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" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms. -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries. -->
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- charFilter + WhitespaceTokenizer -->
+ <!--
+ <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
+ <analyzer>
+ <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ -->
+
+ <!-- This is an example of using the KeywordTokenizer along
+ With various TokenFilterFactories to produce a sortable field
+ that does not include some properties of the source text
+ -->
+ <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+ <analyzer>
+ <!-- KeywordTokenizer does no actual tokenizing, so the entire
+ input string is preserved as a single token
+ -->
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <!-- The LowerCase TokenFilter does what you expect, which can be
+ when you want your sorting to be case insensitive
+ -->
+ <filter class="solr.LowerCaseFilterFactory" />
+ <!-- The TrimFilter removes any leading or trailing whitespace -->
+ <filter class="solr.TrimFilterFactory" />
+ <!-- The PatternReplaceFilter gives you the flexibility to use
+ Java Regular expression to replace any sequence of characters
+ matching a pattern with an arbitrary replacement string,
+ which may include back references to portions of the original
+ string matched by the pattern.
+
+ See the Java Regular Expression documentation for more
+ information on pattern and replacement string syntax.
+
+ http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
+ -->
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-z])" replacement="" replace="all"
+ />
+ </analyzer>
+ </fieldType>
+
+ <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+ </analyzer>
+ </fieldtype>
+
+ <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!--
+ The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
+ a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
+ Attributes of the DelimitedPayloadTokenFilterFactory :
+ "delimiter" - a one character delimiter. Default is | (pipe)
+ "encoder" - how to encode the following value into a playload
+ float -> org.apache.lucene.analysis.payloads.FloatEncoder,
+ integer -> o.a.l.a.p.IntegerEncoder
+ identity -> o.a.l.a.p.IdentityEncoder
+ Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
+ -->
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+ </analyzer>
+ </fieldtype>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldtype name="ignored" stored="false" indexed="false" 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.
+ -->
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
+ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
+
+ <!-- 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="0.000009" units="degrees" />
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ 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.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your query
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ OR if you would like to optimize for recall (default).
+ -->
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ThaiWordFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ </types>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
+
+</schema>
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/solr_config/solr.xml
----------------------------------------------------------------------
diff --git a/solr_config/solr.xml b/solr_config/solr.xml
deleted file mode 100644
index 1010eca..0000000
--- a/solr_config/solr.xml
+++ /dev/null
@@ -1,7 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<solr persistent="false">
- <cores adminPath="/admin/cores">
- <core name="core0" instanceDir="core0" />
- <core name="core1" instanceDir="core1" />
- </cores>
-</solr>
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/vagrant/allura_setup.sh
----------------------------------------------------------------------
diff --git a/vagrant/allura_setup.sh b/vagrant/allura_setup.sh
index 6a38b74..d744829 100755
--- a/vagrant/allura_setup.sh
+++ b/vagrant/allura_setup.sh
@@ -19,15 +19,13 @@
# Install Solr
cd /home/vagrant/src
-if [ ! -d apache-solr-1.4.1 ]
+if [ ! -d solr-4.2.1 ]
then
echo "Installing Solr..."
- wget -nv http://archive.apache.org/dist/lucene/solr/1.4.1/apache-solr-1.4.1.tgz
- tar xf apache-solr-1.4.1.tgz && rm -f apache-solr-1.4.1.tgz
- cd apache-solr-1.4.1/example/
- mkdir -p /home/vagrant/src/allura/solr_config/conf
- cp solr/conf/solrconfig.xml /home/vagrant/src/allura/solr_config/conf/
- chown -R vagrant:vagrant /home/vagrant/src/apache-solr* /home/vagrant/src/allura/solr_config/conf/
+ wget -nv http://archive.apache.org/dist/lucene/solr/4.2.1/solr-4.2.1.tgz
+ tar xf solr-4.2.1.tgz && rm -f solr-4.2.1.tgz
+ cp -f allura/solr_config/schema.xml solr-4.2.1/example/solr/collection1/conf
+ chown -R vagrant:vagrant /home/vagrant/src/solr-4.2.1
fi
# Create startup script
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/87108f04/vagrant/start_allura
----------------------------------------------------------------------
diff --git a/vagrant/start_allura b/vagrant/start_allura
index 84a9c46..758a4bd 100755
--- a/vagrant/start_allura
+++ b/vagrant/start_allura
@@ -36,8 +36,8 @@ then
echo "Solr is running."
else
echo "Starting Solr..."
- cd /home/vagrant/src/apache-solr-1.4.1/example
- nohup java -Dsolr.solr.home=/home/vagrant/src/allura/solr_config -jar start.jar >/var/log/allura/solr.log 2>&1 &
+ cd /home/vagrant/src/solr-4.2.1/example
+ nohup java -jar start.jar >/var/log/allura/solr.log 2>&1 &
fi
cd /home/vagrant/src/allura/Allura
[10/11] git commit: [#3854] Add instructions for installing MongoDB
2.2.3
Posted by jo...@apache.org.
[#3854] Add instructions for installing MongoDB 2.2.3
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/8a76480b
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/8a76480b
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/8a76480b
Branch: refs/heads/master
Commit: 8a76480b40196da5d4d37ceb93b688f652ae5479
Parents: b93f82e
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Tue Apr 30 17:00:39 2013 -0400
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:01 2013 +0000
----------------------------------------------------------------------
README.markdown | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/8a76480b/README.markdown
----------------------------------------------------------------------
diff --git a/README.markdown b/README.markdown
index 70c2ba4..0bf5187 100644
--- a/README.markdown
+++ b/README.markdown
@@ -36,16 +36,18 @@ We'll use [VirtualBox](http://www.virtualbox.org) and [Ubuntu 12.04](http://ubun
Before we begin, you'll need to install some system packages. [Use google if you need additional PIL/jpeg help.](http://www.google.com/search?q=ubuntu+pil+jpeg+virtualenv)
- ~$ sudo aptitude install mongodb-server git-core default-jre-headless python-dev libssl-dev libldap2-dev libsasl2-dev libjpeg8-dev zlib1g-dev
+ ~$ sudo aptitude install git-core default-jre-headless python-dev libssl-dev libldap2-dev libsasl2-dev libjpeg8-dev zlib1g-dev
~$ sudo ln -s /usr/lib/x86_64-linux-gnu/libz.so /usr/lib
~$ sudo ln -s /usr/lib/x86_64-linux-gnu/libjpeg.so /usr/lib
+To install MongoDB 2.2.3, follow the instructions here:
+
+ <http://docs.mongodb.org/manual/tutorial/install-mongodb-on-ubuntu/>
+
Optional, for SVN support:
~$ sudo aptitude install subversion python-svn
-If you are using a different base system, make sure you have Mongo 1.8 or better. If you need to upgrade, you can download the latest from <http://www.mongodb.org/downloads>
-
## Setting up a virtual python environment
The first step to installing the Allura platform is installing a virtual environment via `virtualenv`. This helps keep our distribution python installation clean.
[08/11] git commit: [#3854] Apply change from 5b2dfd3d
Posted by jo...@apache.org.
[#3854] Apply change from 5b2dfd3d
Signed-off-by: Tim Van Steenburgh <tv...@gmail.com>
Project: http://git-wip-us.apache.org/repos/asf/incubator-allura/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-allura/commit/634ed766
Tree: http://git-wip-us.apache.org/repos/asf/incubator-allura/tree/634ed766
Diff: http://git-wip-us.apache.org/repos/asf/incubator-allura/diff/634ed766
Branch: refs/heads/master
Commit: 634ed76612d247845c8836dad0e48b638d59680b
Parents: 3b02a00
Author: Tim Van Steenburgh <tv...@gmail.com>
Authored: Thu Apr 25 20:58:55 2013 +0000
Committer: Cory Johns <cj...@slashdotmedia.com>
Committed: Fri May 10 20:34:00 2013 +0000
----------------------------------------------------------------------
solr_config/forge-schema.xml | 214 ++++++++++++++++++------------------
1 files changed, 107 insertions(+), 107 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-allura/blob/634ed766/solr_config/forge-schema.xml
----------------------------------------------------------------------
diff --git a/solr_config/forge-schema.xml b/solr_config/forge-schema.xml
index 1337ba3..45aca76 100644
--- a/solr_config/forge-schema.xml
+++ b/solr_config/forge-schema.xml
@@ -16,10 +16,10 @@
limitations under the License.
-->
-<!--
+<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
+ (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.
@@ -47,26 +47,26 @@
<schema name="forge" version="1.5">
<!-- 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
+ 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
+ 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
+ 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
+ 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
+ 1.5: omitNorms defaults to true for primitive field types
(int, float, boolean, string...)
-->
<fields>
<!-- Valid attributes for fields:
name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
+ type: mandatory - the name of a field type from the
<types> fieldType section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
@@ -89,9 +89,9 @@
given field.
When using MoreLikeThis, fields used for similarity should be
stored for best performance.
- termPositions: Store position information with the term vector.
+ termPositions: Store position information with the term vector.
This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
+ termOffsets: Store offset information with the term vector. This
will increase storage costs.
required: The field is required. It will throw an error if the
value does not exist
@@ -108,10 +108,10 @@
<!-- Required field values for SOLR, DO NOT REMOVE -->
<field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
+ <field name="text" type="text_general" indexed="true" stored="true" multiValued="true"/>
<!-- END of required field values -->
- <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
+ <field name="admin_subscribed" type="boolean" indexed="false" stored="true" />
<field name="description" type="text_general" indexed="true" stored="true" />
<field name="group_id" type="tint" indexed="true" stored="true"/>
<field name="group_ranking" type="tint" indexed="true" stored="true"/>
@@ -158,7 +158,7 @@
NOTE: This field is not indexed by default, since it is also copied to "text"
using copyField below. This is to save space. Use this field for returning and
highlighting document content. Use the "text" field to search the content. -->
-
+
<!-- catchall field, containing all other searchable text fields (implemented
via copyField further on in this schema -->
@@ -180,19 +180,19 @@
-->
<!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
+ for fields via the specification of patterns to match field names.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end. -->
-
+
<!-- Type used to index the lat and lon components for the "location" FieldType -->
<!-- some trie-coded dynamic fields for faster range queries -->
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default -->
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default -->
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
<dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
@@ -203,11 +203,11 @@
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-
+
</fields>
- <!-- Field to use to determine and enforce document uniqueness.
+ <!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
@@ -231,16 +231,16 @@
is added to the index. It's used either to index the same field differently,
or to add multiple fields to the same field for easier/faster searching. -->
- <!-- Above, multiple source fields are copied to the [text] field.
- Another way to map multiple source fields to the same
- destination field is to use the dynamic field syntax.
+ <!-- Above, multiple source fields are copied to the [text] field.
+ Another way to map multiple source fields to the same
+ destination field is to use the dynamic field syntax.
copyField also supports a maxChars to copy setting. -->
-
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
<!-- <copyField source="name" dest="alphaNameSort"/> -->
-
+
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
@@ -273,7 +273,7 @@
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
- -->
+ -->
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
@@ -303,7 +303,7 @@
<!-- 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
+ 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.
@@ -318,7 +318,7 @@
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
-
+
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
@@ -336,7 +336,7 @@
Note:
These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
-
+
Plain numeric field types that store and index the text
value verbatim (and hence don't correctly support range queries, since the
lexicographic ordering isn't equal to the numeric ordering)
@@ -349,11 +349,11 @@
<!-- 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
+ 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.
+ 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.
@@ -562,13 +562,13 @@
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
+ matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
-
+
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
-
+
http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
@@ -576,7 +576,7 @@
/>
</analyzer>
</fieldType>
-
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
@@ -590,7 +590,7 @@
<!--
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 :
+ 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,
@@ -610,7 +610,7 @@
</analyzer>
</fieldType>
- <!--
+ <!--
Example of using PathHierarchyTokenizerFactory at index time, so
queries for paths match documents at that path, or in descendent paths
-->
@@ -622,7 +622,7 @@
<tokenizer class="solr.KeywordTokenizerFactory" />
</analyzer>
</fieldType>
- <!--
+ <!--
Example of using PathHierarchyTokenizerFactory at query time, so
queries for paths match documents at that path, or in ancestor paths
-->
@@ -636,12 +636,12 @@
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
+ 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
+ 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.
@@ -674,14 +674,14 @@
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
-->
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
+
<!-- some examples for different languages (generally ordered by ISO code) -->
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
@@ -694,26 +694,26 @@
<!-- Bulgarian -->
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
- <filter class="solr.BulgarianStemFilterFactory"/>
+ <filter class="solr.BulgarianStemFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
</analyzer>
</fieldType>
-
+
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
<analyzer>
@@ -728,27 +728,27 @@
<!-- Czech -->
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
- <filter class="solr.CzechStemFilterFactory"/>
+ <filter class="solr.CzechStemFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Danish -->
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
</analyzer>
</fieldType>
-
+
<!-- German -->
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
@@ -758,10 +758,10 @@
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
</analyzer>
</fieldType>
-
+
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
@@ -769,10 +769,10 @@
<filter class="solr.GreekStemFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Spanish -->
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
@@ -780,17 +780,17 @@
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
</analyzer>
</fieldType>
-
+
<!-- Basque -->
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
</analyzer>
</fieldType>
-
+
<!-- Persian -->
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
<analyzer>
@@ -803,10 +803,10 @@
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
</analyzer>
</fieldType>
-
+
<!-- Finnish -->
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
@@ -814,10 +814,10 @@
<!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
@@ -828,10 +828,10 @@
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
</analyzer>
</fieldType>
-
+
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
@@ -842,10 +842,10 @@
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
</analyzer>
</fieldType>
-
+
<!-- Galician -->
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
@@ -853,10 +853,10 @@
<!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!-- normalizes unicode representation -->
@@ -867,31 +867,31 @@
<filter class="solr.HindiStemFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Hungarian -->
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Armenian -->
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
</analyzer>
</fieldType>
-
+
<!-- Indonesian -->
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
@@ -899,10 +899,10 @@
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
</analyzer>
</fieldType>
-
+
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
@@ -912,11 +912,11 @@
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
</analyzer>
</fieldType>
-
+
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
NOTE: If you want to optimize search for precision, use default operator AND in your query
- parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
OR if you would like to optimize for recall (default).
-->
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
@@ -965,20 +965,20 @@
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Latvian -->
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
<filter class="solr.LatvianStemFilterFactory"/>
</analyzer>
</fieldType>
-
+
<!-- Dutch -->
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
@@ -986,10 +986,10 @@
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
</analyzer>
</fieldType>
-
+
<!-- Norwegian -->
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
@@ -998,10 +998,10 @@
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Portuguese -->
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
@@ -1011,20 +1011,20 @@
<!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Romanian -->
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
</analyzer>
</fieldType>
-
+
<!-- Russian -->
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
@@ -1032,10 +1032,10 @@
<!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Swedish -->
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
@@ -1043,20 +1043,20 @@
<!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
-
+
<!-- Thai -->
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ThaiWordFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
</analyzer>
</fieldType>
-
+
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
@@ -1065,10 +1065,10 @@
</fieldType>
</types>
-
+
<!-- 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.
+ 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
-->
<!--