[Solr] Use fixed, recommended schema but add EdgeNGramFilterFactory

master
andryyy 2019-03-10 09:36:33 +01:00
parent 73f836f83e
commit c7c115d63a
No known key found for this signature in database
GPG Key ID: 8EC34FF2794E25EF
5 changed files with 366 additions and 372 deletions

View File

@ -1,9 +1,8 @@
FROM solr:7-alpine
FROM solr:7.7-alpine
USER root
COPY docker-entrypoint.sh /
RUN apk --no-cache add su-exec curl tzdata \
&& chmod +x /docker-entrypoint.sh \
&& /docker-entrypoint.sh --bootstrap
&& chmod +x /docker-entrypoint.sh
ENTRYPOINT ["/docker-entrypoint.sh"]

View File

@ -26,395 +26,51 @@ fi
# run the optional initdb
. /opt/docker-solr/scripts/run-initdb
function solr_config() {
curl -XPOST http://localhost:8983/solr/dovecot/schema -H 'Content-type:application/json' -d '{
"add-field-type":{
"name":"long",
"class":"solr.TrieLongField"
},
"add-field-type":{
"name":"dovecot_text",
"class":"solr.TextField",
"autoGeneratePhraseQueries":true,
"positionIncrementGap":100,
"indexAnalyser":{
"charFilter":{
"class":"solr.MappingCharFilterFactory",
"mapping":"mapping-FoldToASCII.txt"
},
"charFilter":{
"class":"solr.MappingCharFilterFactory",
"mapping":"mapping-ISOLatin1Accent.txt"
},
"charFilter":{
"class":"solr.HTMLStripCharFilterFactory"
},
"tokenizer":{
"class":"solr.StandardTokenizerFactory"
},
"filter":{
"class":"solr.StopFilterFactory",
"words":"stopwords.txt",
"ignoreCase":true
},
"filter":{
"class":"solr.WordDelimiterGraphFilterFactory",
"generateWordParts":1,
"generateNumberParts":1,
"splitOnCaseChange":1,
"splitOnNumerics":1,
"catenateWords":1,
"catenateNumbers":1,
"catenateAll":1
},
"filter":{
"class":"solr.FlattenGraphFilterFactory"
},
"filter":{
"class":"solr.LowerCaseFilterFactory"
},
"filter":{
"class":"solr.KeywordMarkerFilterFactory",
"protected":"protwords.txt"
},
"filter":{
"class":"solr.PorterStemFilterFactory"
}
},
"queryAnalyzer":{
"tokenizer":{
"class":"solr.StandardTokenizerFactory"
},
"filter":{
"class":"solr.SynonymGraphFilterFactory",
"expand":true,
"ignoreCase":true,
"synonyms":synonyms.txt
},
"filter":{
"class":"solr.FlattenGraphFilterFactory"
},
"filter":{
"class":"solr.StopFilterFactory",
"words":"stopwords.txt",
"ignoreCase":true
},
"filter":{
"class":"solr.WordDelimiterGraphFilterFactory",
"generateWordParts":1,
"generateNumberParts":1,
"splitOnCaseChange":1,
"splitOnNumerics":1,
"catenateWords":1,
"catenateNumbers":1,
"catenateAll":1
},
"filter":{
"class":"solr.LowerCaseFilterFactory"
},
"filter":{
"class":"solr.KeywordMarkerFilterFactory",
"protected":"protwords.txt"
},
"filter":{
"class":"solr.PorterStemFilterFactory"
}
}
},
"add-field":{
"name":"uid",
"type":"long",
"indexed":true,
"stored":true,
"required":true
},
"add-field":{
"name":"box",
"type":"string",
"indexed":true,
"stored":true,
"required":true
},
"add-field":{
"name":"user",
"type":"string",
"indexed":true,
"stored":true,
"required":true
},
"add-field":{
"name":"hdr",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"body",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"from",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"to",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"cc",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"bcc",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"add-field":{
"name":"subject",
"type":"dovecot_text",
"indexed":true,
"stored":false
}
}'
curl -XPOST http://localhost:8983/solr/dovecot/schema -H 'Content-type:application/json' -d '{
"replace-field-type":{
"name":"long",
"class":"solr.TrieLongField"
},
"replace-field-type":{
"name":"dovecot_text",
"class":"solr.TextField",
"autoGeneratePhraseQueries":true,
"positionIncrementGap":100,
"indexAnalyser":{
"charFilter":{
"class":"solr.MappingCharFilterFactory",
"mapping":"mapping-FoldToASCII.txt"
},
"charFilter":{
"class":"solr.MappingCharFilterFactory",
"mapping":"mapping-ISOLatin1Accent.txt"
},
"charFilter":{
"class":"solr.HTMLStripCharFilterFactory"
},
"tokenizer":{
"class":"solr.StandardTokenizerFactory"
},
"filter":{
"class":"solr.StopFilterFactory",
"words":"stopwords.txt",
"ignoreCase":true
},
"filter":{
"class":"solr.WordDelimiterGraphFilterFactory",
"generateWordParts":1,
"generateNumberParts":1,
"splitOnCaseChange":1,
"splitOnNumerics":1,
"catenateWords":1,
"catenateNumbers":1,
"catenateAll":1
},
"filter":{
"class":"solr.FlattenGraphFilterFactory"
},
"filter":{
"class":"solr.LowerCaseFilterFactory"
},
"filter":{
"class":"solr.KeywordMarkerFilterFactory",
"protected":"protwords.txt"
},
"filter":{
"class":"solr.PorterStemFilterFactory"
}
},
"queryAnalyzer":{
"tokenizer":{
"class":"solr.StandardTokenizerFactory"
},
"filter":{
"class":"solr.SynonymGraphFilterFactory",
"expand":true,
"ignoreCase":true,
"synonyms":synonyms.txt
},
"filter":{
"class":"solr.FlattenGraphFilterFactory"
},
"filter":{
"class":"solr.StopFilterFactory",
"words":"stopwords.txt",
"ignoreCase":true
},
"filter":{
"class":"solr.WordDelimiterGraphFilterFactory",
"generateWordParts":1,
"generateNumberParts":1,
"splitOnCaseChange":1,
"splitOnNumerics":1,
"catenateWords":1,
"catenateNumbers":1,
"catenateAll":1
},
"filter":{
"class":"solr.LowerCaseFilterFactory"
},
"filter":{
"class":"solr.KeywordMarkerFilterFactory",
"protected":"protwords.txt"
},
"filter":{
"class":"solr.PorterStemFilterFactory"
}
}
},
"replace-field":{
"name":"uid",
"type":"long",
"indexed":true,
"stored":true,
"required":true
},
"replace-field":{
"name":"box",
"type":"string",
"indexed":true,
"stored":true,
"required":true
},
"replace-field":{
"name":"user",
"type":"string",
"indexed":true,
"stored":true,
"required":true
},
"replace-field":{
"name":"hdr",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"body",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"from",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"to",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"cc",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"bcc",
"type":"dovecot_text",
"indexed":true,
"stored":false
},
"replace-field":{
"name":"subject",
"type":"dovecot_text",
"indexed":true,
"stored":false
}
}'
curl -XPOST http://localhost:8983/solr/dovecot/config -H 'Content-type:application/json' -d '{
"update-requesthandler":{
"name":"/select",
"class":"solr.SearchHandler",
"defaults":{
"wt":"xml"
}
}
}'
curl -XPOST http://localhost:8983/solr/dovecot/config/updateHandler -d '{
"set-property": {
"updateHandler.autoSoftCommit.maxDocs":500,
"updateHandler.autoSoftCommit.maxTime":120000,
"updateHandler.autoCommit.maxDocs":200,
"updateHandler.autoCommit.maxTime":1800000,
"updateHandler.autoCommit.openSearcher":false
}
}'
}
# fixing volume permission
[[ -d /opt/solr/server/solr/dovecot/data ]] && chown -R solr:solr /opt/solr/server/solr/dovecot/data
[[ -d /opt/solr/server/solr/dovecot-fts/data ]] && chown -R solr:solr /opt/solr/server/solr/dovecot-fts/data
if [[ "${1}" != "--bootstrap" ]]; then
sed -i '/SOLR_HEAP=/c\SOLR_HEAP="'${SOLR_HEAP:-1024}'m"' /opt/solr/bin/solr.in.sh
else
sed -i '/SOLR_HEAP=/c\SOLR_HEAP="256m"' /opt/solr/bin/solr.in.sh
fi
# start a Solr so we can use the Schema API, but only on localhost,
# so that clients don't see Solr until we have configured it.
echo "Starting local Solr instance to setup configuration"
su-exec solr start-local-solr
# keep a sentinel file so we don't try to create the core a second time
# for example when we restart a container.
# todo: check if a core exists without sentinel file
SENTINEL=/opt/docker-solr/core_created
SENTINEL=/opt/docker-solr/fts_core_created
if [[ -f ${SENTINEL} ]]; then
echo "skipping core creation"
else
echo "Creating core \"dovecot\""
su-exec solr /opt/solr/bin/solr create -c "dovecot"
echo "Starting local Solr instance to setup configuration"
su-exec solr start-local-solr
echo "Creating core \"dovecot-fts\""
su-exec solr /opt/solr/bin/solr create -c "dovecot-fts"
# See https://github.com/docker-solr/docker-solr/issues/27
echo "Checking core"
while ! wget -O - 'http://localhost:8983/solr/admin/cores?action=STATUS' | grep -q instanceDir; do
echo "Could not find any cores, waiting..."
sleep 5
sleep 3
done
echo "Created core \"dovecot\""
echo "Created core \"dovecot-fts\""
touch ${SENTINEL}
echo "Stopping local Solr"
su-exec solr stop-local-solr
fi
echo "Starting configuration"
while ! wget -O - 'http://localhost:8983/solr/admin/cores?action=STATUS' | grep -q instanceDir; do
echo "Waiting for Solr..."
sleep 5
done
solr_config
echo "Stopping local Solr"
su-exec solr stop-local-solr
rm -f /opt/solr/server/solr/dovecot-fts/conf/schema.xml
rm -f /opt/solr/server/solr/dovecot-fts/conf/managed-schema
rm -f /opt/solr/server/solr/dovecot-fts/conf/solrconfig.xml
if [[ "${1}" == "--bootstrap" ]]; then
exit 0
else
exec su-exec solr solr-foreground
fi
cp /etc/solr/solr-config-7.7.0.xml /opt/solr/server/solr/dovecot-fts/conf/solrconfig.xml
cp /etc/solr/solr-schema-7.7.0.xml /opt/solr/server/solr/dovecot-fts/conf/schema.xml
chown -R solr:solr /opt/solr/server/solr/dovecot-fts/conf/{schema.xml,solrconfig.xml}
exec su-exec solr solr-foreground

View File

@ -0,0 +1,289 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!-- This is the default config with stuff non-essential to Dovecot removed. -->
<config>
<!-- Controls what version of Lucene various components of Solr
adhere to. Generally, you want to use the latest version to
get all bug fixes and improvements. It is highly recommended
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
<luceneMatchVersion>7.7.0</luceneMatchVersion>
<!-- A 'dir' option by itself adds any files found in the directory
to the classpath, this is useful for including all jars in a
directory.
When a 'regex' is specified in addition to a 'dir', only the
files in that directory which completely match the regex
(anchored on both ends) will be included.
If a 'dir' option (with or without a regex) is used and nothing
is found that matches, a warning will be logged.
The examples below can be used to load some solr-contribs along
with their external dependencies.
-->
<lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
<!-- Data Directory
Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home. If
replication is in use, this should match the replication
configuration.
-->
<dataDir>${solr.data.dir:}</dataDir>
<!-- The default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<!-- Enables a transaction log, used for real-time get, durability, and
and solr cloud replica recovery. The log can grow as big as
uncommitted changes to the index, so use of a hard autoCommit
is recommended (see below).
"dir" - the target directory for transaction logs, defaults to the
solr data directory.
"numVersionBuckets" - sets the number of buckets used to keep
track of max version values when checking for re-ordered
updates; increase this value to reduce the cost of
synchronizing access to version buckets during high-volume
indexing, this requires 8 bytes (long) * numVersionBuckets
of heap space per Solr core.
-->
<updateLog>
<str name="dir">${solr.ulog.dir:}</str>
<int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
</updateLog>
<!-- AutoCommit
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
when adding documents.
http://wiki.apache.org/solr/UpdateXmlMessages
maxDocs - Maximum number of documents to add since the last
commit before automatically triggering a new commit.
maxTime - Maximum amount of time in ms that is allowed to pass
since a document was added before automatically
triggering a new commit.
openSearcher - if false, the commit causes recent index changes
to be flushed to stable storage, but does not cause a new
searcher to be opened to make those changes visible.
If the updateLog is enabled, then it's highly recommended to
have some sort of hard autoCommit to limit the log size.
-->
<autoCommit>
<maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
<openSearcher>false</openSearcher>
</autoCommit>
<!-- softAutoCommit is like autoCommit except it causes a
'soft' commit which only ensures that changes are visible
but does not ensure that data is synced to disk. This is
faster and more near-realtime friendly than a hard commit.
-->
<autoSoftCommit>
<maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
</autoSoftCommit>
<!-- Update Related Event Listeners
Various IndexWriter related events can trigger Listeners to
take actions.
postCommit - fired after every commit or optimize command
postOptimize - fired after every optimize command
-->
</updateHandler>
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Query section - these settings control query time things like caches
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<query>
<!-- Solr Internal Query Caches
There are two implementations of cache available for Solr,
LRUCache, based on a synchronized LinkedHashMap, and
FastLRUCache, based on a ConcurrentHashMap.
FastLRUCache has faster gets and slower puts in single
threaded operation and thus is generally faster than LRUCache
when the hit ratio of the cache is high (> 75%), and may be
faster under other scenarios on multi-cpu systems.
-->
<!-- Filter Cache
Cache used by SolrIndexSearcher for filters (DocSets),
unordered sets of *all* documents that match a query. When a
new searcher is opened, its caches may be prepopulated or
"autowarmed" using data from caches in the old searcher.
autowarmCount is the number of items to prepopulate. For
LRUCache, the autowarmed items will be the most recently
accessed items.
Parameters:
class - the SolrCache implementation LRUCache or
(LRUCache or FastLRUCache)
size - the maximum number of entries in the cache
initialSize - the initial capacity (number of entries) of
the cache. (see java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
and old cache.
maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
to occupy. Note that when this option is specified, the size
and initialSize parameters are ignored.
-->
<filterCache class="solr.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- Query Result Cache
Caches results of searches - ordered lists of document ids
(DocList) based on a query, a sort, and the range of documents requested.
Additional supported parameter by LRUCache:
maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
to occupy
-->
<queryResultCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- Document Cache
Caches Lucene Document objects (the stored fields for each
document). Since Lucene internal document ids are transient,
this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- custom cache currently used by block join -->
<cache name="perSegFilter"
class="solr.search.LRUCache"
size="10"
initialSize="0"
autowarmCount="10"
regenerator="solr.NoOpRegenerator" />
<!-- Lazy Field Loading
If true, stored fields that are not requested will be loaded
lazily. This can result in a significant speed improvement
if the usual case is to not load all stored fields,
especially if the skipped fields are large compressed text
fields.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!-- Result Window Size
An optimization for use with the queryResultCache. When a search
is requested, a superset of the requested number of document ids
are collected. For example, if a search for a particular query
requests matching documents 10 through 19, and queryWindowSize is 50,
then documents 0 through 49 will be collected and cached. Any further
requests in that range can be satisfied via the cache.
-->
<queryResultWindowSize>20</queryResultWindowSize>
<!-- Maximum number of documents to cache for any entry in the
queryResultCache.
-->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<!-- Use Cold Searcher
If a search request comes in and there is no current
registered searcher, then immediately register the still
warming searcher and use it. If "false" then all requests
will block until the first searcher is done warming.
-->
<useColdSearcher>false</useColdSearcher>
</query>
<!-- Request Dispatcher
This section contains instructions for how the SolrDispatchFilter
should behave when processing requests for this SolrCore.
-->
<requestDispatcher>
<httpCaching never304="true" />
</requestDispatcher>
<!-- Request Handlers
http://wiki.apache.org/solr/SolrRequestHandler
Incoming queries will be dispatched to a specific handler by name
based on the path specified in the request.
If a Request Handler is declared with startup="lazy", then it will
not be initialized until the first request that uses it.
-->
<!-- SearchHandler
http://wiki.apache.org/solr/SearchHandler
For processing Search Queries, the primary Request Handler
provided with Solr is "SearchHandler" It delegates to a sequent
of SearchComponents (see below) and supports distributed
queries across multiple shards
-->
<requestHandler name="/select" class="solr.SearchHandler">
<!-- default values for query parameters can be specified, these
will be overridden by parameters in the request
-->
<lst name="defaults">
<str name="echoParams">explicit</str>
<int name="rows">10</int>
</lst>
</requestHandler>
<initParams path="/update/**,/select">
<lst name="defaults">
<str name="df">_text_</str>
</lst>
</initParams>
<!-- Response Writers
http://wiki.apache.org/solr/QueryResponseWriter
Request responses will be written using the writer specified by
the 'wt' request parameter matching the name of a registered
writer.
The "default" writer is the default and will be used if 'wt' is
not specified in the request.
-->
<queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
</config>

View File

@ -0,0 +1,50 @@
<?xml version="1.0" encoding="UTF-8"?>
<schema name="dovecot" version="2.0">
<fieldType name="string" class="solr.StrField" omitNorms="true" sortMissingLast="true"/>
<fieldType name="long" class="solr.LongPointField" positionIncrementGap="0"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldType name="text" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="20"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" splitOnNumerics="1" catenateAll="1" catenateWords="1"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="20"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" splitOnNumerics="1" catenateAll="1" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<field name="id" type="string" indexed="true" required="true" stored="true"/>
<field name="uid" type="long" indexed="true" required="true" stored="true"/>
<field name="box" type="string" indexed="true" required="true" stored="true"/>
<field name="user" type="string" indexed="true" required="true" stored="true"/>
<field name="hdr" type="text" indexed="true" stored="false"/>
<field name="body" type="text" indexed="true" stored="false"/>
<field name="from" type="text" indexed="true" stored="false"/>
<field name="to" type="text" indexed="true" stored="false"/>
<field name="cc" type="text" indexed="true" stored="false"/>
<field name="bcc" type="text" indexed="true" stored="false"/>
<field name="subject" type="text" indexed="true" stored="false"/>
<!-- Used by Solr internally: -->
<field name="_version_" type="long" indexed="true" stored="true"/>
<uniqueKey>id</uniqueKey>
</schema>

View File

@ -1477,7 +1477,7 @@ function solr_status() {
$endpoint = 'http://solr:8983/solr/admin/cores';
$params = array(
'action' => 'STATUS',
'core' => 'dovecot',
'core' => 'dovecot-fts',
'indexInfo' => 'true'
);
$url = $endpoint . '?' . http_build_query($params);
@ -1494,7 +1494,7 @@ function solr_status() {
else {
curl_close($curl);
$status = json_decode($response, true);
return (!empty($status['status']['dovecot'])) ? $status['status']['dovecot'] : false;
return (!empty($status['status']['dovecot-fts'])) ? $status['status']['dovecot-fts'] : false;
}
return false;
}