Hi, Nutch 1.14 will support Solr 6.6.0, see https://issues.apache.org/jira/browse/NUTCH-2400
Thanks, Sebastian On 09/15/2017 05:48 AM, Hiran CHAUDHURI wrote: > Attachements are obviously not forwarded by the list manager. So I will try > it inline. > > So whoever wants to follow this tutorial: > https://wiki.apache.org/nutch/NutchTutorial#Setup_Solr_for_search > > Make sure you apply this patch file or Solr 6.6 won't like it (you get > various error messages when creating the core): > > -----8<------------------------------------------------------------- > --- dist/apache-nutch-1.13/conf/schema.xml 2017-03-29 00:05:21.000000000 > -0400 > +++ solr/schema.xml 2017-09-05 16:14:12.515950452 -0400 > @@ -56,7 +56,9 @@ > <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="tlongs" class="solr.TrieLongField" docValues="true" > precisionStep="8" positionIncrementGap="0" multiValued="true"/> > <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" > omitNorms="true" positionIncrementGap="0"/> > + <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" > precisionStep="8" positionIncrementGap="0" multiValued="true"/> > > <!-- 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 > @@ -86,6 +88,7 @@ > > <!-- A Trie based date field for faster date range queries and date > faceting. --> > <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" > precisionStep="6" positionIncrementGap="0"/> > + <fieldType name="tdates" class="solr.TrieDateField" docValues="true" > precisionStep="6" positionIncrementGap="0" multiValued="true"/> > > > <!-- solr.TextField allows the specification of custom text analyzers > @@ -108,7 +111,7 @@ > <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" /> > + <filter class="solr.StopFilterFactory" ignoreCase="true" > words="stopwords.txt" /> > <!-- in this example, we will only use synonyms at query time > <filter class="solr.SynonymFilterFactory" > synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> > --> > @@ -116,7 +119,7 @@ > </analyzer> > <analyzer type="query"> > <tokenizer class="solr.StandardTokenizerFactory"/> > - <filter class="solr.StopFilterFactory" ignoreCase="true" > words="stopwords.txt" enablePositionIncrements="true" /> > + <filter class="solr.StopFilterFactory" ignoreCase="true" > words="stopwords.txt" /> > <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" > ignoreCase="true" expand="true"/> > <filter class="solr.LowerCaseFilterFactory"/> > </analyzer> > @@ -140,7 +143,6 @@ > <filter class="solr.StopFilterFactory" > ignoreCase="true" > words="stopwords.txt" > - enablePositionIncrements="true" > /> > <filter class="solr.LowerCaseFilterFactory"/> > <filter class="solr.EnglishPossessiveFilterFactory"/> > @@ -156,7 +158,6 @@ > <filter class="solr.StopFilterFactory" > ignoreCase="true" > words="stopwords.txt" > - enablePositionIncrements="true" > /> > <filter class="solr.LowerCaseFilterFactory"/> > <filter class="solr.EnglishPossessiveFilterFactory"/> > @@ -193,7 +194,6 @@ > <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"/> > @@ -206,7 +206,6 @@ > <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="1"/> > <filter class="solr.LowerCaseFilterFactory"/> > @@ -237,7 +236,7 @@ > <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.StopFilterFactory" ignoreCase="true" > words="stopwords.txt" /> > <filter class="solr.LowerCaseFilterFactory"/> > <filter class="solr.ReversedWildcardFilterFactory" > withOriginal="true" > maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> > @@ -245,7 +244,7 @@ > <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.StopFilterFactory" ignoreCase="true" > words="stopwords.txt" /> > <filter class="solr.LowerCaseFilterFactory"/> > </analyzer> > </fieldType> > @@ -303,7 +302,9 @@ > <fieldtype name="ignored" stored="false" indexed="false" > multiValued="true" class="solr.StrField" /> > > <!-- boolean type: "true" or "false" --> > - <fieldType name="boolean" class="solr.BoolField" > sortMissingLast="true"/> > + <fieldType name="boolean" class="solr.BoolField" > sortMissingLast="true"/> > + > + <fieldType name="booleans" class="solr.BoolField" > sortMissingLast="true" multiValued="true"/> > > <!-- sortMissingLast and sortMissingFirst attributes are optional > attributes are > currently supported on types that are sorted internally as strings > @@ -414,8 +415,7 @@ > > </fields> > <uniqueKey>id</uniqueKey> > - <defaultSearchField>text</defaultSearchField> > - <solrQueryParser defaultOperator="OR"/> > + <solrQueryParser/> > > <!-- 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,-------------------------------------------------->8---------------- > > Hiran > > -----Original Message----- > From: BlackIce [mailto:[email protected]] > Sent: 14 September 2017 21:47 > To: [email protected] > Subject: [EXT] Re: Nutch 1.13 release and Solr 6.6 > > Sure, that would be most excellent! > > On Sep 14, 2017 9:41 PM, "Hiran CHAUDHURI" <[email protected]> > wrote: > >> Hi there. >> >> >> >> When I tried to setup Nutch 1.13 to connect to Solr 6.6 I found out >> that the Nutch schema shipped in .../conf/schema.xml needs quite some >> tweaking before Solr can use it. >> >> The reason may be that Nutch is developed against a different (older?) >> version of Solr. It might be nice if that information were shared, as >> otherwise it is quite frustrating - especially for new users to that >> technology. >> >> >> >> Meanwhile I can provide a diff of what of the tweak to make Solr 6.6 >> spin up - if someone's interested? >> >> >> >> Hiran >> >> >> >> >> >> *Hiran Chaudhuri* >> * Principal Support Engineer* >> >> Service Reliability Engineering - Custom >> >> Amadeus Data Processing GmbH >> Berghamer Strasse 6 >> <https://maps.google.com/?q=Berghamer+Strasse+6+%0D+85435+Erding&entry >> =gmail&source=g> >> 85435 Erding >> T: +49-8122-43x3662 <+49%208122%2043> >> [email protected] >> * http://amadeus.com <http://amadeus.com/>* >> >> >>
