Skip to content

feat: add simple_icufolding analyzer #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

feat: add simple_icufolding analyzer #40

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6dd988d
feat: add simple_icufolding analyzer
klaemo Apr 7, 2021
5f8f50f
add lucene-analyzers-icu as a dep
klaemo Apr 7, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,11 @@
<artifactId>lucene-analyzers-kuromoji</artifactId>
<version>${lucene-version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-icu</artifactId>
<version>${lucene-version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-facet</artifactId>
Expand Down
8 changes: 8 additions & 0 deletions src/main/scala/com/cloudant/clouseau/SupportedAnalyzers.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ import org.apache.lucene.analysis.tr.TurkishAnalyzer
// Extras
import org.apache.lucene.analysis.ja.JapaneseTokenizer
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter
import org.apache.lucene.analysis.icu.ICUFoldingFilter
import org.apache.lucene.analysis.core.LowerCaseFilter
import org.apache.lucene.analysis.core.LetterTokenizer

Expand Down Expand Up @@ -120,6 +121,13 @@ object SupportedAnalyzers {
new TokenStreamComponents(tokenizer, new ASCIIFoldingFilter(new LowerCaseFilter(IndexService.version, tokenizer)))
}
})
case "simple_icufolding" =>
Some(new Analyzer() {
def createComponents(fieldName: String, reader: Reader): TokenStreamComponents = {
val tokenizer: Tokenizer = new LetterTokenizer(IndexService.version, reader);
new TokenStreamComponents(tokenizer, new ICUFoldingFilter(tokenizer))
}
})
case "arabic" =>
options.get("stopwords") match {
case Some(stopwords: List[String]) =>
Expand Down
4 changes: 4 additions & 0 deletions src/test/scala/com/cloudant/clouseau/AnalyzerServiceSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,10 @@ class AnalyzerServiceSpec extends SpecificationWithJUnit {
"demonstrate simple_asciifolding tokenization" in new analyzer_service {
service.handleCall(null, ('analyze, "simple_asciifolding", "Ayşegül Özbayır")) must be equalTo (('ok, List("aysegul", "ozbayir")))
}

"demonstrate simple_icufolding tokenization" in new analyzer_service {
service.handleCall(null, ('analyze, "simple_icufolding", "Ayşegül Özbayır")) must be equalTo (('ok, List("aysegul", "ozbayir")))
}
}
}

Expand Down
3 changes: 3 additions & 0 deletions src/test/scala/com/cloudant/clouseau/SupportedAnalyzersSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,9 @@ class SupportedAnalyzersSpec extends SpecificationWithJUnit {
"simple_asciifolding" in {
createAnalyzer("simple_asciifolding") must haveClass[Some[Analyzer]]
}
"simple_icufolding" in {
createAnalyzer("simple_icufolding") must haveClass[Some[Analyzer]]
}
"email" in {
createAnalyzer("email") must haveClass[Some[UAX29URLEmailAnalyzer]]
}
Expand Down