Skip to content

Commit

Permalink
Cleanup unneeded core config
Browse files Browse the repository at this point in the history
  • Loading branch information
@alastair
alastair committed Nov 27, 2022
1 parent a81a761 commit 1ebff31
Show file tree
Hide file tree
Showing 2 changed files with 30 additions and 85 deletions.
2 changes: 2 additions & 0 deletions utils/search/backends/solr9pysolr.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,8 @@ def search_process_filter(self, query_filter, only_sounds_within_ids=False, only
# Add type suffix to human-readable audio analyzer descriptor names which is needed for solr dynamic fields
query_filter = solr555pysolr.add_solr_suffix_to_dynamic_fieldnames_in_filter(query_filter)

# When filtering by the created field, use the `created_range` DateRangeType field instead
# which include the ability to filter on exact values and ranges of values.
if 'created:' in query_filter:
query_filter = query_filter.replace('created:', 'created_range:')

Expand Down
113 changes: 28 additions & 85 deletions utils/search/solr9.0.0/cores/freesound/schema.xml
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<!-- Solr managed schema - automatically generated - DO NOT EDIT -->
<schema name="default-config" version="1.6">
<uniqueKey>id</uniqueKey>
<fieldType name="_nest_path_" class="solr.NestPathField" maxCharsForDocValues="-1" omitNorms="true" omitTermFreqAndPositions="true" stored="false" multiValued="false"/>
Expand Down Expand Up @@ -133,15 +132,7 @@
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
<fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_et.txt"/>
<filter name="snowballPorter" language="Estonian"/>
</analyzer>
</fieldType>
<fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt"/>
Expand All @@ -154,89 +145,41 @@
<filter name="lowercase"/>
</analyzer>
</fieldType>
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt"/>
<filter ignoreCase="true" synonyms="synonyms.txt" name="synonymGraph" expand="true"/>
<filter name="lowercase"/>

<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token -->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive -->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
</analyzer>
</fieldType>
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<fieldType name="freesound_text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt"/>
<filter name="lowercase"/>
<filter name="reversedWildcard" maxPosQuestion="2" withOriginal="true" maxPosAsterisk="3" maxFractionAsterisk="0.33"/>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer name="standard"/>
<filter ignoreCase="true" synonyms="synonyms.txt" name="synonymGraph" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer name="whitespace"/>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>

<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back refrences to portions of the orriginal
string matched by the pattern.
See the Java Regular Expression documentation for more
infomation on pattern and replacement string syntax.
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
-->
<!-- <filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>-->
</analyzer>
</fieldType>
<fieldType name="freesound_text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>


<field name="_nest_path_" type="_nest_path_"/>

Expand Down

0 comments on commit 1ebff31

Please sign in to comment.