After some testsing, I managed to get proper functionning
- The schema.xml is attached below (quite different from the one
provided on teh wiki) (in bold the core differences) (NGramFilterFactory
is the class that replace the fts_squat "partial=3 full=15",
everything
else is just a big hammer to smash a tiny fly)
- One need to remove the "managed-schema" file in the
{prefix}/server/solr/dovecot/conf.
- One need to remove everything under {prefix}/server/solr/dovecot/data/
- The {prefix}/server/solr/dovecot/conf/solrconfig.xml is as below (see
diff)
- Restart Solr
- my dovecot.conf is :
fts = solr
fts_autoindex = yes
fts_enforced = yes
fts_decoder = decode2text
fts_solr = url=http://(SOLR SERVER):8983/solr/dovecot/
--- schema.xml
<?xml version="1.0" encoding="UTF-8"?>
<schema name="dovecot" version="2.0">
<uniqueKey>id</uniqueKey>
<FIELDTYPE NAME="STRING" CLASS="SOLR.STRFIELD" />
<FIELDTYPE NAME="LONG" CLASS="SOLR.TRIELONGFIELD" />
<FIELDTYPE NAME="BOOLEAN" CLASS="SOLR.BOOLFIELD" />
<fieldType name="text" class="solr.TextField"
autoGeneratePhraseQueries="true"
positionIncrementGap="100">
<analyzer type="index">
<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"/> <!--
required on index
analyzers after graph filters -->
<filter class="solr.LowerCaseFilterFactory"/>
<FILTER CLASS="SOLR.NGRAMFILTERFACTORY" MINGRAMSIZE="3"
MAXGRAMSIZE="15"
/>
<filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory"
expand="true"
ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.FlattenGraphFilterFactory"/> <!--
required on index
analyzers after graph filters -->
<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.NGRAMFILTERFACTORY" MINGRAMSIZE="3"
MAXGRAMSIZE="15"
/>
<filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<field name="_version_" type="long"
indexed="true" stored="true"/>
<field name="bcc" type="text" indexed="true"
stored="false"/>
<field name="body" type="text" indexed="true"
stored="false"/>
<field name="box" type="string" indexed="true"
required="true"
stored="true"/>
<field name="cc" type="text" indexed="true"
stored="false"/>
<field name="from" type="text" indexed="true"
stored="false"/>
<field name="hdr" type="text" indexed="true"
stored="false"/>
<field name="id" type="string" indexed="true"
required="true"
stored="true"/>
<field name="subject" type="text"
indexed="true" stored="false"/>
<field name="to" type="text" indexed="true"
stored="false"/>
<field name="uid" type="long" indexed="true"
required="true"
stored="true"/>
<field name="user" type="string" indexed="true"
required="true"
stored="true"/>
</schema>
------ diff solrconfig
--- /data/backup/solr/solrconfig.xml.joan 2018-12-08 14:31:47.716344505
+0000
+++ solrconfig.xml 2018-12-08 15:36:28.948267225 +0000
@@ -1128,6 +1128,7 @@
See http://wiki.apache.org/solr/GuessingFieldTypes
-->
+ <schemaFactory
class="ClassicIndexSchemaFactory"></schemaFactory>
<updateProcessor class="solr.UUIDUpdateProcessorFactory"
name="uuid"/>
<updateProcessor
class="solr.RemoveBlankFieldUpdateProcessorFactory"
name="remove-blank"/>
<updateProcessor
class="solr.FieldNameMutatingUpdateProcessorFactory"
name="field-name-mutating">
@@ -1158,43 +1159,8 @@
<str>yyyy-MM-dd</str>
</arr>
</updateProcessor>
- <updateProcessor
class="solr.AddSchemaFieldsUpdateProcessorFactory"
name="add-schema-fields">
- <lst name="typeMapping">
- <str name="valueClass">java.lang.String</str>
- <str name="fieldType">text_general</str>
- <lst name="copyField">
- <str name="dest">*_str</str>
- <int name="maxChars">256</int>
- </lst>
- <!-- Use as default mapping instead of defaultFieldType -->
- <bool name="default">true</bool>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">pdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">plongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">pdoubles</str>
- </lst>
- </updateProcessor>
<!-- The update.autoCreateFields property can be turned to false to
disable schemaless mode -->
- <updateRequestProcessorChain
name="add-unknown-fields-to-the-schema"
default="${update.autoCreateFields:true}"
-
processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
- <processor class="solr.LogUpdateProcessorFactory"/>
- <processor class="solr.DistributedUpdateProcessorFactory"/>
- <processor class="solr.RunUpdateProcessorFactory"/>
- </updateRequestProcessorChain>
<!-- Deduplication
@@ -1273,7 +1239,6 @@
<!-- The following response writers are implicitly configured unless
overridden...
-->
- <!--
<queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
@@ -1284,7 +1249,6 @@
<queryResponseWriter name="phps"
class="solr.PHPSerializedResponseWriter"/>
<queryResponseWriter name="csv"
class="solr.CSVResponseWriter"/>
<queryResponseWriter name="schema.xml"
class="solr.SchemaXmlResponseWriter"/>
- -->
<queryResponseWriter name="json"
class="solr.JSONResponseWriter">
<!-- For the purposes of the tutorial, JSON responses are written as
@@ -1293,7 +1257,7 @@
-->
<str name="content-type">text/plain; charset=UTF-8</str>
</queryResponseWriter>
-
+
<!--
Custom response writers can be declared as needed...
-->
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<https://dovecot.org/pipermail/dovecot/attachments/20181208/4b09e842/attachment.html>
However, Solr crashes and Dovecot plugin ftS_solr returns multitude of errors Dec 09 09:21:09 imap(jom at grosjo.net)<3349><DiRnXpN8Lux/AAAB>: Error: fts_solr: received invalid uid '0' Dec 09 09:21:10 imap(jom at grosjo.net)<3349><DiRnXpN8Lux/AAAB>: Error: fts_solr: received invalid uid '0' And returns are totaly funny (keywords not presentin teh results) I am back to fs_squat.... On 2018-12-08 18:28, Joan Moreau via dovecot wrote:> After some testsing, I managed to get proper functionning > > - The schema.xml is attached below (quite different from the one provided on teh wiki) (in bold the core differences) (NGramFilterFactory is the class that replace the fts_squat "partial=3 full=15", everything else is just a big hammer to smash a tiny fly) > > - One need to remove the "managed-schema" file in the {prefix}/server/solr/dovecot/conf. > > - One need to remove everything under {prefix}/server/solr/dovecot/data/ > > - The {prefix}/server/solr/dovecot/conf/solrconfig.xml is as below (see diff) > > - Restart Solr > > - my dovecot.conf is : > > fts = solr > fts_autoindex = yes > fts_enforced = yes > fts_decoder = decode2text > > fts_solr = url=http://(SOLR SERVER):8983/solr/dovecot/ > > --- schema.xml > > <?xml version="1.0" encoding="UTF-8"?> > <schema name="dovecot" version="2.0"> > <uniqueKey>id</uniqueKey> > > <FIELDTYPE NAME="STRING" CLASS="SOLR.STRFIELD" /> > <FIELDTYPE NAME="LONG" CLASS="SOLR.TRIELONGFIELD" /> > <FIELDTYPE NAME="BOOLEAN" CLASS="SOLR.BOOLFIELD" /> > <fieldType name="text" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100"> > <analyzer type="index"> > <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"/> <!-- required on index analyzers after graph filters --> > <filter class="solr.LowerCaseFilterFactory"/> > <FILTER CLASS="SOLR.NGRAMFILTERFACTORY" MINGRAMSIZE="3" MAXGRAMSIZE="15" /> > <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> > <filter class="solr.PorterStemFilterFactory"/> > </analyzer> > <analyzer type="query"> > <tokenizer class="solr.StandardTokenizerFactory"/> > <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/> > <filter class="solr.FlattenGraphFilterFactory"/> <!-- required on index analyzers after graph filters --> > <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.NGRAMFILTERFACTORY" MINGRAMSIZE="3" MAXGRAMSIZE="15" /> > <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> > <filter class="solr.PorterStemFilterFactory"/> > </analyzer> > </fieldType> > > <field name="_version_" type="long" indexed="true" stored="true"/> > <field name="bcc" type="text" indexed="true" stored="false"/> > <field name="body" type="text" indexed="true" stored="false"/> > <field name="box" type="string" indexed="true" required="true" stored="true"/> > <field name="cc" type="text" indexed="true" stored="false"/> > <field name="from" type="text" indexed="true" stored="false"/> > <field name="hdr" type="text" indexed="true" stored="false"/> > <field name="id" type="string" indexed="true" required="true" stored="true"/> > <field name="subject" type="text" indexed="true" stored="false"/> > <field name="to" type="text" indexed="true" stored="false"/> > <field name="uid" type="long" indexed="true" required="true" stored="true"/> > <field name="user" type="string" indexed="true" required="true" stored="true"/> > </schema> > > ------ diff solrconfig > > --- /data/backup/solr/solrconfig.xml.joan 2018-12-08 14:31:47.716344505 +0000 > +++ solrconfig.xml 2018-12-08 15:36:28.948267225 +0000 > @@ -1128,6 +1128,7 @@ > > See http://wiki.apache.org/solr/GuessingFieldTypes > --> > + <schemaFactory class="ClassicIndexSchemaFactory"></schemaFactory> > <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/> > <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/> > <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating"> > @@ -1158,43 +1159,8 @@ > <str>yyyy-MM-dd</str> > </arr> > </updateProcessor> > - <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields"> > - <lst name="typeMapping"> > - <str name="valueClass">java.lang.String</str> > - <str name="fieldType">text_general</str> > - <lst name="copyField"> > - <str name="dest">*_str</str> > - <int name="maxChars">256</int> > - </lst> > - <!-- Use as default mapping instead of defaultFieldType --> > - <bool name="default">true</bool> > - </lst> > - <lst name="typeMapping"> > - <str name="valueClass">java.lang.Boolean</str> > - <str name="fieldType">booleans</str> > - </lst> > - <lst name="typeMapping"> > - <str name="valueClass">java.util.Date</str> > - <str name="fieldType">pdates</str> > - </lst> > - <lst name="typeMapping"> > - <str name="valueClass">java.lang.Long</str> > - <str name="valueClass">java.lang.Integer</str> > - <str name="fieldType">plongs</str> > - </lst> > - <lst name="typeMapping"> > - <str name="valueClass">java.lang.Number</str> > - <str name="fieldType">pdoubles</str> > - </lst> > - </updateProcessor> > > <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode --> > - <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}" > - processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields"> > - <processor class="solr.LogUpdateProcessorFactory"/> > - <processor class="solr.DistributedUpdateProcessorFactory"/> > - <processor class="solr.RunUpdateProcessorFactory"/> > - </updateRequestProcessorChain> > > <!-- Deduplication > > @@ -1273,7 +1239,6 @@ > <!-- The following response writers are implicitly configured unless > overridden... > --> > - <!-- > <queryResponseWriter name="xml" > default="true" > class="solr.XMLResponseWriter" /> > @@ -1284,7 +1249,6 @@ > <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/> > <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/> > <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/> > - --> > > <queryResponseWriter name="json" class="solr.JSONResponseWriter"> > <!-- For the purposes of the tutorial, JSON responses are written as > @@ -1293,7 +1257,7 @@ > --> > <str name="content-type">text/plain; charset=UTF-8</str> > </queryResponseWriter> > - > + > <!-- > Custom response writers can be declared as needed... > -->-------------- next part -------------- An HTML attachment was scrubbed... URL: <https://dovecot.org/pipermail/dovecot/attachments/20181209/25836a24/attachment-0001.html>
Hi! Thank you for your report, we'll look thru it. Aki On 9.12.2018 11.24, Joan Moreau via dovecot wrote:> > However, Solr crashes and Dovecot plugin ftS_solr returns multitude of > errors > > Dec 09 09:21:09 imap(jom at grosjo.net)<3349><DiRnXpN8Lux/AAAB>: Error: > fts_solr: received invalid uid '0' > Dec 09 09:21:10 imap(jom at grosjo.net)<3349><DiRnXpN8Lux/AAAB>: Error: > fts_solr: received invalid uid '0' > > And returns are totaly funny (keywords not presentin teh results) > > > I am back to fs_squat.... > > ? > > > On 2018-12-08 18:28, Joan Moreau via dovecot wrote: > >> After some testsing, I managed to get proper functionning >> >> - The schema.xml is attached below (quite different from the one >> provided on teh wiki) (in bold the core differences) >> (NGramFilterFactory is the class that replace the fts_squat >> "partial=3 full=15", everything else is just a big hammer to smash a >> tiny fly) >> >> - One need to remove the "managed-schema" file in the >> {prefix}/server/solr/dovecot/conf. >> >> - One need to remove everything under {prefix}/server/solr/dovecot/data/ >> >> - The {prefix}/server/solr/dovecot/conf/solrconfig.xml is as below >> (see diff) >> ? >> - Restart Solr >> ? >> - my dovecot.conf is : >> >> fts = solr >> fts_autoindex = yes >> fts_enforced = yes >> fts_decoder = decode2text >> >> fts_solr = url=http://(SOLR SERVER):8983/solr/dovecot/ >> >> >> --- schema.xml >> >> <?xml version="1.0" encoding="UTF-8"?> >> <schema name="dovecot" version="2.0"> >> <uniqueKey>id</uniqueKey> >> >> *<fieldType name="string" class="solr.StrField" />* >> *<fieldType name="long" class="solr.TrieLongField" />* >> *<fieldType name="boolean" class="solr.BoolField" />* >> <fieldType name="text" class="solr.TextField" >> autoGeneratePhraseQueries="true" positionIncrementGap="100"> >> <analyzer type="index"> >> <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"/> <!-- required on >> index analyzers after graph filters --> >> <filter class="solr.LowerCaseFilterFactory"/> >> *<filter class="solr.NGramFilterFactory" minGramSize="3" >> maxGramSize="15" />* >> <filter class="solr.KeywordMarkerFilterFactory" >> protected="protwords.txt"/> >> <filter class="solr.PorterStemFilterFactory"/> >> </analyzer> >> <analyzer type="query"> >> <tokenizer class="solr.StandardTokenizerFactory"/> >> <filter class="solr.SynonymGraphFilterFactory" expand="true" >> ignoreCase="true" synonyms="synonyms.txt"/> >> <filter class="solr.FlattenGraphFilterFactory"/> <!-- required on >> index analyzers after graph filters --> >> <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.NGramFilterFactory" minGramSize="3" >> maxGramSize="15" />* >> <filter class="solr.KeywordMarkerFilterFactory" >> protected="protwords.txt"/> >> <filter class="solr.PorterStemFilterFactory"/> >> </analyzer> >> </fieldType> >> >> <field name="_version_" type="long" indexed="true" stored="true"/> >> <field name="bcc" type="text" indexed="true" stored="false"/> >> <field name="body" type="text" indexed="true" stored="false"/> >> <field name="box" type="string" indexed="true" required="true" >> stored="true"/> >> <field name="cc" type="text" indexed="true" stored="false"/> >> <field name="from" type="text" indexed="true" stored="false"/> >> <field name="hdr" type="text" indexed="true" stored="false"/> >> <field name="id" type="string" indexed="true" required="true" >> stored="true"/> >> <field name="subject" type="text" indexed="true" stored="false"/> >> <field name="to" type="text" indexed="true" stored="false"/> >> <field name="uid" type="long" indexed="true" required="true" >> stored="true"/> >> <field name="user" type="string" indexed="true" required="true" >> stored="true"/> >> </schema> >> >> >> ------ diff solrconfig >> >> --- /data/backup/solr/solrconfig.xml.joan 2018-12-08 >> 14:31:47.716344505 +0000 >> +++ solrconfig.xml 2018-12-08 15:36:28.948267225 +0000 >> @@ -1128,6 +1128,7 @@ >> >> See http://wiki.apache.org/solr/GuessingFieldTypes >> --> >> + <schemaFactory class="ClassicIndexSchemaFactory"></schemaFactory> >> <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/> >> <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" >> name="remove-blank"/> >> <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" >> name="field-name-mutating"> >> @@ -1158,43 +1159,8 @@ >> <str>yyyy-MM-dd</str> >> </arr> >> </updateProcessor> >> - <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" >> name="add-schema-fields"> >> - <lst name="typeMapping"> >> - <str name="valueClass">java.lang.String</str> >> - <str name="fieldType">text_general</str> >> - <lst name="copyField"> >> - <str name="dest">*_str</str> >> - <int name="maxChars">256</int> >> - </lst> >> - <!-- Use as default mapping instead of defaultFieldType --> >> - <bool name="default">true</bool> >> - </lst> >> - <lst name="typeMapping"> >> - <str name="valueClass">java.lang.Boolean</str> >> - <str name="fieldType">booleans</str> >> - </lst> >> - <lst name="typeMapping"> >> - <str name="valueClass">java.util.Date</str> >> - <str name="fieldType">pdates</str> >> - </lst> >> - <lst name="typeMapping"> >> - <str name="valueClass">java.lang.Long</str> >> - <str name="valueClass">java.lang.Integer</str> >> - <str name="fieldType">plongs</str> >> - </lst> >> - <lst name="typeMapping"> >> - <str name="valueClass">java.lang.Number</str> >> - <str name="fieldType">pdoubles</str> >> - </lst> >> - </updateProcessor> >> >> <!-- The update.autoCreateFields property can be turned to false to >> disable schemaless mode --> >> - <updateRequestProcessorChain >> name="add-unknown-fields-to-the-schema" >> default="${update.autoCreateFields:true}" >> - >> processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields"> >> - <processor class="solr.LogUpdateProcessorFactory"/> >> - <processor class="solr.DistributedUpdateProcessorFactory"/> >> - <processor class="solr.RunUpdateProcessorFactory"/> >> - </updateRequestProcessorChain> >> >> <!-- Deduplication >> >> @@ -1273,7 +1239,6 @@ >> <!-- The following response writers are implicitly configured unless >> overridden... >> --> >> - <!-- >> <queryResponseWriter name="xml" >> default="true" >> class="solr.XMLResponseWriter" /> >> @@ -1284,7 +1249,6 @@ >> <queryResponseWriter name="phps" >> class="solr.PHPSerializedResponseWriter"/> >> <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/> >> <queryResponseWriter name="schema.xml" >> class="solr.SchemaXmlResponseWriter"/> >> - --> >> >> <queryResponseWriter name="json" class="solr.JSONResponseWriter"> >> <!-- For the purposes of the tutorial, JSON responses are written as >> @@ -1293,7 +1257,7 @@ >> --> >> <str name="content-type">text/plain; charset=UTF-8</str> >> </queryResponseWriter> >> - >> + >> <!-- >> Custom response writers can be declared as needed... >> --> >> >> >> >>-------------- next part -------------- An HTML attachment was scrubbed... URL: <https://dovecot.org/pipermail/dovecot/attachments/20181210/859615b0/attachment.html>