Skip to content

V
venjob_nth
Commit edd8e6cc by Ngô Trung Hưng
Options

fix method sub_space_params!

parent 8d2405f1
Pipeline #1071 canceled with stages
in 0 seconds
Showing with 612 additions and 16 deletions
app/common/indexed_job.rb 0 → 100644
# frozen_string_literal: true
class IndexedJob
attr_accessor :job
def initialize(job)
@job = job
end
def do
index_strategy = Sync::Entities::Job.new(job)
Sync::Indexer.new.do(index_strategy)
end
end
db/solr/data-config.xml 0 → 100644
<dataConfig>
<dataSource type="JdbcDataSource"
driver="com.mysql.jdbc.Driver"
batchSize="-1"
url="jdbc:mysql://127.0.0.1:3306/hungnt_development"
user="root"
password="Trunghung5055@"/>
<document>
<entity name="jobs"
pk="id"
query="SELECT jobs.*, companies.name AS company_name FROM jobs, companies WHERE jobs.company_id = companies.id">
<field column="id" name="id"/>
<field column="name" name="name"/>
<field column="company_name" name="company_name"/>
<field column="salary" name="salary"/>
<field column="description" name="description"/>
<!-- QUERY INDUSTRIES -->
<entity name="industries"
query="SELECT industries.id AS industry_id, industries.name AS industry_name FROM industries, industry_jobs, jobs WHERE jobs.id = industry_jobs.job_id AND industry_jobs.industry_id = industries.id AND jobs.id='${jobs.id}'">
<field column="industry_name" name="industries" />
<field column="industry_id" name="industry_id" />
</entity>
<!-- QUERY CITIES -->
<entity name="cities"
query="SELECT cities.id AS location_id, cities.name AS location_name FROM cities, city_jobs, jobs WHERE jobs.id = city_jobs.job_id AND city_jobs.city_id = cities.id AND jobs.id='${jobs.id}'">
<field column="location_name" name="locations" />
<field column="location_id" name="location_id" />
</entity>
</entity>
</document>
</dataConfig>
db/solr/managed-schema 0 → 100644
<?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"/>
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
</analyzer>
</fieldType>
<fieldType name="binary" class="solr.BinaryField"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
<fieldType name="delimited_payloads_float" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldType>
<fieldType name="delimited_payloads_int" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
</analyzer>
</fieldType>
<fieldType name="delimited_payloads_string" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
</analyzer>
</fieldType>
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/>
<fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
<fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
<fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true"/>
<fieldType name="rank" class="solr.RankField"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true"/>
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" docValues="true" multiValued="true"/>
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ar.txt" ignoreCase="true"/>
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_bg.txt" ignoreCase="true"/>
<filter class="solr.BulgarianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ca.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ca.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
</analyzer>
</fieldType>
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.CJKWidthFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_cz.txt" ignoreCase="true"/>
<filter class="solr.CzechStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
</analyzer>
</fieldType>
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
<filter class="solr.GermanNormalizationFilterFactory"/>
<filter class="solr.GermanLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_el.txt" ignoreCase="false"/>
<filter class="solr.GreekStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<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.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
<filter class="solr.SpanishLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_et.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
</analyzer>
</fieldType>
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_eu.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
</analyzer>
</fieldType>
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<charFilter class="solr.PersianCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.PersianNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_fa.txt" ignoreCase="true"/>
</analyzer>
</fieldType>
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
</analyzer>
</fieldType>
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_fr.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
<filter class="solr.FrenchLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ga.txt" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
<filter class="solr.IrishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ga.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
</analyzer>
</fieldType>
<fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_gl.txt" ignoreCase="true"/>
<filter class="solr.GalicianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_hi.txt" ignoreCase="true"/>
<filter class="solr.HindiStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
</analyzer>
</fieldType>
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_hy.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
</analyzer>
</fieldType>
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_id.txt" ignoreCase="true"/>
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
</analyzer>
</fieldType>
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt" ignoreCase="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
<filter class="solr.ItalianLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/>
<filter class="solr.CJKWidthFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ja.txt" ignoreCase="true"/>
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KoreanTokenizerFactory" outputUnknownUnigrams="false" decompoundMode="discard"/>
<filter class="solr.KoreanPartOfSpeechStopFilterFactory"/>
<filter class="solr.KoreanReadingFormFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_lv.txt" ignoreCase="true"/>
<filter class="solr.LatvianStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
</analyzer>
</fieldType>
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
</analyzer>
</fieldType>
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
<filter class="solr.PortugueseLightStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_ro.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
</analyzer>
</fieldType>
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
</analyzer>
</fieldType>
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
</analyzer>
</fieldType>
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.ThaiTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_th.txt" ignoreCase="true"/>
</analyzer>
</fieldType>
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="lang/stopwords_tr.txt" ignoreCase="false"/>
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
</analyzer>
</fieldType>
<fieldType name="text_vi" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
<filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
</analyzer>
</fieldType>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<field name="_nest_path_" type="_nest_path_"/>
<field name="_root_" type="string" docValues="false" indexed="true" stored="false"/>
<field name="_text_" type="text_general" multiValued="true" indexed="true" stored="false"/>
<field name="_version_" type="plong" indexed="false" stored="false"/>
<field name="company_name" type="text_vi" uninvertible="false" indexed="true" stored="true"/>
<field name="description" type="string" uninvertible="false" indexed="false" stored="true"/>
<field name="id" type="string" multiValued="false" indexed="true" required="true" stored="true"/>
<field name="industries" type="text_vi" uninvertible="false" multiValued="true" indexed="true" stored="true"/>
<field name="industry_id" type="strings" uninvertible="false" docValues="false" multiValued="true" indexed="true" stored="true"/>
<field name="location_id" type="strings" uninvertible="false" multiValued="true" indexed="true" stored="true"/>
<field name="locations" type="text_vi" uninvertible="false" multiValued="true" indexed="true" stored="true"/>
<field name="name" type="text_vi" uninvertible="false" indexed="true" stored="true" termVectors="true"/>
<field name="salary" type="string" uninvertible="false" indexed="false" stored="true"/>
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
<dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
<dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
<dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored"/>
<dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
<dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
<dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
<dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
<dynamicField name="random_*" type="random"/>
<dynamicField name="*_t_sort" type="text_gen_sort" multiValued="false" indexed="true" stored="true"/>
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
<dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
<dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
<dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
<dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
<dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
<dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
<dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
<dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
<dynamicField name="*_txt_et" type="text_et" indexed="true" stored="true"/>
<dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
<dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
<dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
<dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
<dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
<dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
<dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
<dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
<dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
<dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
<dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
<dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
<dynamicField name="*_txt_ko" type="text_ko" indexed="true" stored="true"/>
<dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
<dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
<dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
<dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
<dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
<dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
<dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
<dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
<dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
<dynamicField name="*_point" type="point" indexed="true" stored="true"/>
<dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
<dynamicField name="attr_*" type="text_general" multiValued="true" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_str" type="strings" docValues="true" indexed="false" stored="false" useDocValuesAsStored="false"/>
<dynamicField name="*_dts" type="pdate" multiValued="true" indexed="true" stored="true"/>
<dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
<dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
<dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
<dynamicField name="*_is" type="pints" indexed="true" stored="true"/>
<dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
<dynamicField name="*_ls" type="plongs" indexed="true" stored="true"/>
<dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
<dynamicField name="*_fs" type="pfloats" indexed="true" stored="true"/>
<dynamicField name="*_ds" type="pdoubles" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/>
<dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
<dynamicField name="*_i" type="pint" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="plong" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text_general" multiValued="false" indexed="true" stored="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="pfloat" indexed="true" stored="true"/>
<dynamicField name="*_d" type="pdouble" indexed="true" stored="true"/>
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
</schema>
\ No newline at end of file
lib/service/import_data.rb
......@@ -52,8 +52,7 @@ class ImportData
end
if record.new_record?
record.save
index_strategy = Sync::Entities::Job.new(record)
Sync::Indexer.new.do(index_strategy)
IndexedJob.new(job).do
end
rescue StandardError => e
logger.error "Import_jobs: #{e}"
......
lib/solr/searches/query.rb
# frozen_string_literal: true
module Searches
class Query
class Query
def search(params)
solr = connect_solr
# Escape input & Convert space to asterisks
data = sub_space_params!(params[:search][:keyword], params[:search][:industry_id], params[:search][:city_id])
query = if [params[:search][:keyword], params[:search][:industry_id], params[:search][:city_id]].all? { |v| v.blank?}
query = if [params[:search][:keyword], params[:search][:industry_id], params[:search][:city_id]].all?(&:blank?)
'*:*'
else
"solr((name: #{data[:keyword]}) OR (company_name: #{data[:keyword]})) AND (industry_id: #{data[:industry_id]}) AND (location_id: #{data[:location_id]})"
end
response = solr.paginate(params[:page], Settings.number_result_search_in_page, 'select', params: { q: query })
results = Kaminari.paginate_array(response['response']['docs'], total_count: response['response']['numFound']).page(params[:page]).per(Settings.number_result_search_in_page)
Kaminari.paginate_array(response['response']['docs'], total_count: response['response']['numFound']).page(params[:page]).per(Settings.number_result_search_in_page)
end
def sub_space_params!(keyword, industry_id, location_id)
arr_params = {}
arr_params[:keyword] = RSolr.solr_escape(keyword)
arr_params[:industry_id] = RSolr.solr_escape(industry_id)
arr_params[:location_id] = RSolr.solr_escape(location_id)
arr_params[:keyword] = RSolr.solr_escape(keyword || '')
arr_params[:industry_id] = RSolr.solr_escape(industry_id || '')
arr_params[:location_id] = RSolr.solr_escape(location_id || '')
arr_params.each_value { |val| val.sub!('', '*') if val.blank? }
end
private
def connect_solr
SolrSetting::SolrServer.connection
end
end
end
\ No newline at end of file
end
lib/solr/sync/entities/job.rb
......@@ -9,9 +9,9 @@ module Sync::Entities
data[:company_name] = job.company.name
data[:salary] = job.salary
data[:description] = job.description
data[:industries] = job.industry_jobs.map(&:industry).map(&:name)
data[:industries] = job.industries.pluck(:name)
data[:industry_id] = job.industry_jobs.map(&:industry_id)
data[:locations] = job.city_jobs.map(&:city).map(&:name)
data[:locations] = job.cities.pluck(:name)
data[:location_id] = job.city_jobs.map(&:city_id)
data
end
......
lib/src/crawler_job.rb
......@@ -57,8 +57,7 @@ class CrawlerJob < Crawler
create_industry_relation(data[:industry_name], job)
create_city_relation(data[:city_name], job)
# Index data to solr
index_strategy = Sync::Entities::Job.new(job)
Sync::Indexer.new.do(index_strategy)
IndexedJob.new(job).do
rescue StandardError => e
logger.error "Crawler data jobs has error: #{e}"
end
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment