Skip to content

Commit

Permalink
Solr 9 configs. (#32)
Browse files Browse the repository at this point in the history
  • Loading branch information
@rosiel
rosiel authored Mar 6, 2024
1 parent c1c8c5b commit 8e3d245
Show file tree
Hide file tree
Showing 9 changed files with 162 additions and 105 deletions.
1 change: 1 addition & 0 deletions drupal/rootfs/opt/solr/server/solr/default/conf/protwords_und.txt
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@

75 changes: 40 additions & 35 deletions drupal/rootfs/opt/solr/server/solr/default/conf/schema.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@
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
https://solr.apache.org/guide/solr/latest/indexing-guide/schema-elements.html
PERFORMANCE NOTE: this schema includes many optional features and should not
be used for benchmarking. To improve performance one could
Expand All @@ -49,7 +49,7 @@
that avoids logging every request
-->

<schema name="drupal-4.2.9-solr-8.x-0" version="1.6">
<schema name="drupal-4.3.2-solr-9.x-0" version="1.6">
<!-- 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.
Expand Down Expand Up @@ -122,7 +122,9 @@
<!-- points to the root document of a block of nested documents. Required for nested
document support, may be removed otherwise
-->
<field name="_root_" type="string" indexed="true" stored="false" docValues="false"/>
<field name="_root_" type="string" indexed="true" stored="true" docValues="false" />
<fieldType name="_nest_path_" class="solr.NestPathField" />
<field name="_nest_path_" type="_nest_path_" />

<!-- Only remove the "id" field if you have a very good reason to. While not strictly
required, it is highly recommended. A <uniqueKey> is present in almost all Solr
Expand Down Expand Up @@ -156,7 +158,7 @@

<!-- Currently the suggester context filter query (suggest.cfq) accesses the tags using the stored values, neither the indexed terms nor the docValues.
Therefore the dynamicField sm_* isn't suitable at the moment -->
<field name="sm_context_tags" type="string" indexed="true" stored="true" multiValued="true" docValues="false"/>
<field name="sm_context_tags" type="strings" indexed="true" stored="true" docValues="false"/>

<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
Expand All @@ -170,56 +172,56 @@
the last letter is 's' for single valued, 'm' for multi-valued -->

<!-- We use plong for integer since 64 bit ints are now common in PHP. -->
<dynamicField name="is_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="im_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="is_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
<dynamicField name="im_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
<!-- List of floats can be saved in a regular float field -->
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="fm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
<dynamicField name="fm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
<!-- List of doubles can be saved in a regular double field -->
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="pm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
<dynamicField name="pm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
<!-- List of booleans can be saved in a regular boolean field -->
<dynamicField name="bm_*" type="boolean" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="bm_*" type="booleans" indexed="true" stored="false" docValues="true" termVectors="true"/>
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" docValues="true" termVectors="true"/>
<!-- Regular text (without processing) can be stored in a string field-->
<dynamicField name="ss_*" type="string" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="ss_*" type="string" indexed="true" stored="false" docValues="true" termVectors="true"/>
<!-- For field types using SORTED_SET, multiple identical entries are collapsed into a single value.
Thus if I insert values 4, 5, 2, 4, 1, my return will be 1, 2, 4, 5 when enabling docValues.
If you need to preserve the order and duplicate entries, consider to store the values as zm_* (twice). -->
<dynamicField name="sm_*" type="string" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="sm_*" type="strings" indexed="true" stored="false" docValues="true" termVectors="true"/>
<!-- Special-purpose text fields -->
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>

<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="dm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
<dynamicField name="dm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
<!-- This field is used to store date ranges -->
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true" multiValued="false"/>
<dynamicField name="drm_*" type="date_range" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true"/>
<dynamicField name="drm_*" type="date_ranges" indexed="true" stored="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="its_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
<dynamicField name="itm_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ftm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ptm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="its_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
<dynamicField name="itm_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
<dynamicField name="ftm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
<dynamicField name="ptm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
a small image in a search result using the data URI scheme -->
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="ddm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
<dynamicField name="ddm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="hm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" docValues="true"/>
<dynamicField name="hm_*" type="pints" indexed="true" stored="false" docValues="true"/>
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
<dynamicField name="htm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" docValues="true"/>
<dynamicField name="htm_*" type="pints" indexed="true" stored="false" docValues="true"/>

<!-- Unindexed string fields that can be used to store values that won't be searchable -->
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
<dynamicField name="zs_*" type="string" indexed="false" stored="true"/>
<dynamicField name="zm_*" type="strings" indexed="false" stored="true"/>

<!-- Fields for location searches.
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
Expand Down Expand Up @@ -264,9 +266,11 @@
single-valued and either required or have a default value.
-->
<fieldType name="string" class="solr.StrField"/>
<fieldType name="strings" class="solr.StrField" multiValued="true"/>

<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField"/>
<fieldType name="booleans" class="solr.BoolField" multiValued="true"/>

<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
currently supported on types that are sorted internally as strings
Expand Down Expand Up @@ -331,6 +335,7 @@

<!-- A date range field -->
<fieldType name="date_range" class="solr.DateRangeField"/>
<fieldType name="date_ranges" class="solr.DateRangeField" multiValued="true"/>

<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldType name="binary" class="solr.BinaryField"/>
Expand Down Expand Up @@ -369,7 +374,7 @@
-->

<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100" storeOffsetsWithPositions="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
Expand Down
Loading

0 comments on commit 8e3d245

Please sign in to comment.