thr3ads.net - dovecot - Solr [Jan 2019]

If this information is useful, please help other people find it:
Share via:

Joan Moreau

2019-Jan-02 07:22 UTC

Solr

Refinement of the schema.xml (below) 

THis however does not solve the "no results" and "Out of
range" errors
in Dovecot and Solr 

<?xml version="1.0" encoding="UTF-8"?>
<schema name="dovecot" version="2.0">
<uniqueKey>id</uniqueKey>
<fieldType name="booleans" class="solr.BoolField"
sortMissingLast="true"
multiValued="true"/>
<fieldType name="gjlong" class="solr.LongPointField"
positionIncrementGap="0"/>
<fieldType name="gjtext" class="solr.TextField"
autoGeneratePhraseQueries="true"
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterGraphFilterFactory"
catenateNumbers="1"
generateNumberParts="1" splitOnCaseChange="1"
generateWordParts="1"
splitOnNumerics="1" catenateAll="1"
catenateWords="1"
preserveOriginal="1"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="gjfield" class="solr.TextField"
autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.NGramTokenizerFactory"
maxGramSize="25"
minGramSize="3" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType> 

<fieldType name="string" class="solr.StrField"/>
<field name="_version_" type="string"
indexed="true" stored="true"/>
<field name="bcc" type="string" indexed="false"
stored="false"/>
<field name="body" type="gjtext" indexed="true"
stored="false"/>
<field name="box" type="string" indexed="true"
required="true"
stored="true"/>
<field name="cc" type="gjfield" indexed="true"
stored="false"/>
<field name="from" type="gjfield"
indexed="true" stored="false"/>
<field name="hdr" type="string" indexed="false"
stored="false"/>
<field name="id" type="string" indexed="true"
required="true"
stored="true"/>
<field name="subject" type="gjtext"
indexed="true" stored="false"/>
<field name="to" type="gjfield" indexed="true"
stored="false"/>
<field name="uid" type="string" indexed="true"
required="true"
stored="true"/>
<field name="user" type="string" indexed="true"
required="true"
stored="true"/>
</schema>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<https://dovecot.org/pipermail/dovecot/attachments/20190102/a72ad4ae/attachment-0001.html>

Joan Moreau

2019-Jan-02 10:00 UTC

head link

Solr

Another bug appearing today: 

Jan 02 09:59:08
indexer-worker(jom at
grosjo.net)<6777><MOgFATKLLFwPHAAA0thIag:oLJjJjKLLFx5GgAA0thIag>:
Warning: FTS-SOLR(JOM at GROSJO.NET): Mailbox XXXXXX UID=121635 HEADER SIZE
IS HUGE, TRUNCATING 

header of the said email has nothing of "huge"

On 2019-01-02 15:22, Joan Moreau via dovecot wrote:
> Refinement of the schema.xml (below) 
> 
> THis however does not solve the "no results" and "Out of
range" errors in Dovecot and Solr
> 
> <?xml version="1.0" encoding="UTF-8"?>
> <schema name="dovecot" version="2.0">
> <uniqueKey>id</uniqueKey>
> <fieldType name="booleans" class="solr.BoolField"
sortMissingLast="true" multiValued="true"/>
> <fieldType name="gjlong" class="solr.LongPointField"
positionIncrementGap="0"/>
> <fieldType name="gjtext" class="solr.TextField"
autoGeneratePhraseQueries="true"
positionIncrementGap="100">
> <analyzer type="index">
> <tokenizer class="solr.StandardTokenizerFactory"/>
> <filter class="solr.WordDelimiterGraphFilterFactory"
catenateNumbers="1" generateNumberParts="1"
splitOnCaseChange="1" generateWordParts="1"
splitOnNumerics="1" catenateAll="1"
catenateWords="1" preserveOriginal="1"/>
> <filter class="solr.FlattenGraphFilterFactory"/>
> <filter class="solr.LowerCaseFilterFactory"/>
> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
> </analyzer>
> <analyzer type="query">
> <tokenizer class="solr.KeywordTokenizerFactory"/>
> </analyzer>
> </fieldType>
> <fieldType name="gjfield" class="solr.TextField"
autoGeneratePhraseQueries="true">
> <analyzer type="index">
> <tokenizer class="solr.NGramTokenizerFactory"
maxGramSize="25" minGramSize="3" />
> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
> </analyzer>
> <analyzer type="query">
> <tokenizer class="solr.KeywordTokenizerFactory"/>
> </analyzer>
> </fieldType> 
> 
> <fieldType name="string" class="solr.StrField"/>
> <field name="_version_" type="string"
indexed="true" stored="true"/>
> <field name="bcc" type="string"
indexed="false" stored="false"/>
> <field name="body" type="gjtext"
indexed="true" stored="false"/>
> <field name="box" type="string"
indexed="true" required="true" stored="true"/>
> <field name="cc" type="gjfield"
indexed="true" stored="false"/>
> <field name="from" type="gjfield"
indexed="true" stored="false"/>
> <field name="hdr" type="string"
indexed="false" stored="false"/>
> <field name="id" type="string"
indexed="true" required="true" stored="true"/>
> <field name="subject" type="gjtext"
indexed="true" stored="false"/>
> <field name="to" type="gjfield"
indexed="true" stored="false"/>
> <field name="uid" type="string"
indexed="true" required="true" stored="true"/>
> <field name="user" type="string"
indexed="true" required="true" stored="true"/>
> </schema>-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<https://dovecot.org/pipermail/dovecot/attachments/20190102/6e764f9b/attachment.html>

Joan Moreau

2019-Jan-02 10:10 UTC

head link

Solr

In the code, it says 

#define SOLR_HEADER_MAX_SIZE (1024*1024) 

and line 620 

if (!ctx->truncate_header &&
str_len(ctx->cur_value) >= SOLR_HEADER_MAX_SIZE) {
/* a large header */ 

so this is a 1Mo header. This is of course completely wrong. 

Maybe this is not the root cause of the errors of fts_solr, but maybe
this will help 

On 2019-01-02 18:00, Joan Moreau via dovecot wrote:
> Another bug appearing today: 
> 
> Jan 02 09:59:08 indexer-worker(jom at
grosjo.net)<6777><MOgFATKLLFwPHAAA0thIag:oLJjJjKLLFx5GgAA0thIag>:
Warning: FTS-SOLR(JOM at GROSJO.NET): Mailbox XXXXXX UID=121635 HEADER SIZE IS
HUGE, TRUNCATING
> 
> header of the said email has nothing of "huge"
> 
> On 2019-01-02 15:22, Joan Moreau via dovecot wrote:
> 
>> Refinement of the schema.xml (below) 
>> 
>> THis however does not solve the "no results" and "Out of
range" errors in Dovecot and Solr
>> 
>> <?xml version="1.0" encoding="UTF-8"?>
>> <schema name="dovecot" version="2.0">
>> <uniqueKey>id</uniqueKey>
>> <fieldType name="booleans"
class="solr.BoolField" sortMissingLast="true"
multiValued="true"/>
>> <fieldType name="gjlong"
class="solr.LongPointField" positionIncrementGap="0"/>
>> <fieldType name="gjtext" class="solr.TextField"
autoGeneratePhraseQueries="true"
positionIncrementGap="100">
>> <analyzer type="index">
>> <tokenizer class="solr.StandardTokenizerFactory"/>
>> <filter class="solr.WordDelimiterGraphFilterFactory"
catenateNumbers="1" generateNumberParts="1"
splitOnCaseChange="1" generateWordParts="1"
splitOnNumerics="1" catenateAll="1"
catenateWords="1" preserveOriginal="1"/>
>> <filter class="solr.FlattenGraphFilterFactory"/>
>> <filter class="solr.LowerCaseFilterFactory"/>
>> <filter
class="solr.RemoveDuplicatesTokenFilterFactory"/>
>> </analyzer>
>> <analyzer type="query">
>> <tokenizer class="solr.KeywordTokenizerFactory"/>
>> </analyzer>
>> </fieldType>
>> <fieldType name="gjfield" class="solr.TextField"
autoGeneratePhraseQueries="true">
>> <analyzer type="index">
>> <tokenizer class="solr.NGramTokenizerFactory"
maxGramSize="25" minGramSize="3" />
>> <filter
class="solr.RemoveDuplicatesTokenFilterFactory"/>
>> </analyzer>
>> <analyzer type="query">
>> <tokenizer class="solr.KeywordTokenizerFactory"/>
>> </analyzer>
>> </fieldType> 
>> 
>> <fieldType name="string"
class="solr.StrField"/>
>> <field name="_version_" type="string"
indexed="true" stored="true"/>
>> <field name="bcc" type="string"
indexed="false" stored="false"/>
>> <field name="body" type="gjtext"
indexed="true" stored="false"/>
>> <field name="box" type="string"
indexed="true" required="true" stored="true"/>
>> <field name="cc" type="gjfield"
indexed="true" stored="false"/>
>> <field name="from" type="gjfield"
indexed="true" stored="false"/>
>> <field name="hdr" type="string"
indexed="false" stored="false"/>
>> <field name="id" type="string"
indexed="true" required="true" stored="true"/>
>> <field name="subject" type="gjtext"
indexed="true" stored="false"/>
>> <field name="to" type="gjfield"
indexed="true" stored="false"/>
>> <field name="uid" type="string"
indexed="true" required="true" stored="true"/>
>> <field name="user" type="string"
indexed="true" required="true" stored="true"/>
>> </schema>-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<https://dovecot.org/pipermail/dovecot/attachments/20190102/b794e24d/attachment.html>

Stephan Bosch

2019-Jan-05 00:35 UTC

head link

Solr

Op 02/01/2019 om 11:00 schreef Joan Moreau via dovecot:>
> Another bug appearing today:
>
> Jan 02 09:59:08 
> indexer-worker(jom at
grosjo.net)<6777><MOgFATKLLFwPHAAA0thIag:oLJjJjKLLFx5GgAA0thIag>:
> Warning:*fts-solr(jom at grosjo.net)*: Mailbox XXXXXX UID=121635*header 
> size is huge, truncating*
>
> header of the said email has nothing of "huge"
>Does this happen consistently with that same message? Can you show it to me?

Regards,

Stephan.


>
> On 2019-01-02 15:22, Joan Moreau via dovecot wrote:
>
>> Refinement of the schema.xml (below)
>>
>>
>> THis however does not solve the "no results" and "Out of
range"
>> errors in Dovecot and Solr
>>
>>
>> <?xml version="1.0" encoding="UTF-8"?>
>> <schema name="dovecot" version="2.0">
>> <uniqueKey>id</uniqueKey>
>> <fieldType name="booleans"
class="solr.BoolField"
>> sortMissingLast="true" multiValued="true"/>
>> <fieldType name="gjlong"
class="solr.LongPointField"
>> positionIncrementGap="0"/>
>> <fieldType name="gjtext" class="solr.TextField" 
>> autoGeneratePhraseQueries="true"
positionIncrementGap="100">
>> <analyzer type="index">
>> <tokenizer class="solr.StandardTokenizerFactory"/>
>> <filter class="solr.WordDelimiterGraphFilterFactory" 
>> catenateNumbers="1" generateNumberParts="1"
splitOnCaseChange="1"
>> generateWordParts="1" splitOnNumerics="1"
catenateAll="1"
>> catenateWords="1" preserveOriginal="1"/>
>> <filter class="solr.FlattenGraphFilterFactory"/>
>> <filter class="solr.LowerCaseFilterFactory"/>
>> <filter
class="solr.RemoveDuplicatesTokenFilterFactory"/>
>> </analyzer>
>> <analyzer type="query">
>> <tokenizer class="solr.KeywordTokenizerFactory"/>
>> </analyzer>
>> </fieldType>
>> <fieldType name="gjfield" class="solr.TextField"
>> autoGeneratePhraseQueries="true">
>> <analyzer type="index">
>> <tokenizer class="solr.NGramTokenizerFactory"
maxGramSize="25"
>> minGramSize="3" />
>> <filter
class="solr.RemoveDuplicatesTokenFilterFactory"/>
>> </analyzer>
>> <analyzer type="query">
>> <tokenizer class="solr.KeywordTokenizerFactory"/>
>> </analyzer>
>> </fieldType>
>>
>> <fieldType name="string"
class="solr.StrField"/>
>> <field name="_version_" type="string"
indexed="true" stored="true"/>
>> <field name="bcc" type="string"
indexed="false" stored="false"/>
>> <field name="body" type="gjtext"
indexed="true" stored="false"/>
>> <field name="box" type="string"
indexed="true" required="true"
>> stored="true"/>
>> <field name="cc" type="gjfield"
indexed="true" stored="false"/>
>> <field name="from" type="gjfield"
indexed="true" stored="false"/>
>> <field name="hdr" type="string"
indexed="false" stored="false"/>
>> <field name="id" type="string"
indexed="true" required="true"
>> stored="true"/>
>> <field name="subject" type="gjtext"
indexed="true" stored="false"/>
>> <field name="to" type="gjfield"
indexed="true" stored="false"/>
>> <field name="uid" type="string"
indexed="true" required="true"
>> stored="true"/>
>> <field name="user" type="string"
indexed="true" required="true"
>> stored="true"/>
>> </schema>
>>
>>

Reasonably Related Threads

Search for more seemingly similar threads

dovecot - Jan 2019 - Solr

Solr

Solr

Solr

Solr

Reasonably Related Threads