操作系统:Ubuntu 22.10Java: openjdk版本"19.0.1";2022-10-18scala: 2.13.10Apache Lucene: 9.4.2
我将Lucene文档示例转换为Scala程序:
package test
import org.apache.lucene.analysis.standard.StandardAnalyzer
import org.apache.lucene.document.{Document, Field, TextField}
import org.apache.lucene.index.{DirectoryReader, IndexWriter, IndexWriterConfig}
import org.apache.lucene.queryparser.classic.QueryParser
import org.apache.lucene.search.{IndexSearcher, Query, ScoreDoc}
import org.apache.lucene.store.FSDirectory
import java.nio.file.{Files, Path}
object Test extends App {
val analyzer: StandardAnalyzer = new StandardAnalyzer()
val indexPath: Path = Files.createTempDirectory("tempIndex")
val directory: FSDirectory = FSDirectory.open(indexPath)
val config: IndexWriterConfig = new IndexWriterConfig(analyzer)
val iwriter: IndexWriter = new IndexWriter(directory, config)
val doc: Document = new Document()
val text: String = "This is the text to be indexed."
doc.add(new Field("fieldname", text, TextField.TYPE_STORED))
iwriter.addDocument(doc)
iwriter.close()
// Now search the index:
val ireader: DirectoryReader = DirectoryReader.open(directory)
val isearcher: IndexSearcher = new IndexSearcher(ireader)
// Parse a simple query that searches for "text":
val parser: QueryParser = new QueryParser("fieldname", analyzer)
val query: Query = parser.parse("text")
val hits: Array[ScoreDoc] = isearcher.search(query, 10).scoreDocs
assert (hits.length == 1)
// Iterate through the results:
for (i <- hits.indices) {
val hitDoc = isearcher.doc(hits(i).doc)
assert("This is the text to be indexed.".equals(hitDoc.get("fieldname")))
}
ireader.close()
directory.close()
println("The end!")
}
如果我使用下面的sbt文件:
ThisBuild / version := "0.1.0-SNAPSHOT"
ThisBuild / scalaVersion := "2.13.10"
lazy val root = (project in file("."))
.settings(
name := "Test"
)
val luceneVersion = "9.4.2"
libraryDependencies ++= Seq(
"org.apache.lucene" % "lucene-core" % luceneVersion,
"org.apache.lucene" % "lucene-queryparser" % luceneVersion
)
编译给了我错误:
[error] Deduplicate found different file contents in the following:
[error] Jar name = lucene-core-9.4.2.jar, jar org = org.apache.lucene, entry target = module-info.class
[error] Jar name = lucene-queries-9.4.2.jar, jar org = org.apache.lucene, entry target = module-info.class
[error] Jar name = lucene-queryparser-9.4.2.jar, jar org = org.apache.lucene, entry target = module-info.class
[error] Jar name = lucene-sandbox-9.4.2.jar, jar org = org.apache.lucene, entry target = module-info.class
所以我在sbt文件中包含:
assembly / assemblyMergeStrategy := {
case PathList("META-INF", xs @ _*) => MergeStrategy.discard
case _ => MergeStrategy.first
}
之后，程序的编译和执行是ok的:
sbt "runMain test.Test"
但是如果我想创建一个fat jar文件并执行它，我会得到以下异常:
插件。sbt:
addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "2.1.0")
java -cp target/scala-2.13/Test-assembly-0.1.0-SNAPSHOT.jar test.Test
Exception in thread "main" java.lang.ExceptionInInitializerError
at org.apache.lucene.codecs.Codec.getDefault(Codec.java:141)
at org.apache.lucene.index.LiveIndexWriterConfig.<init>(LiveIndexWriterConfig.java:128)
at org.apache.lucene.index.IndexWriterConfig.<init>(IndexWriterConfig.java:145)
at test.Test$.delayedEndpoint$test$Test$1(Test.scala:17)
at test.Test$delayedInit$body.apply(Test.scala:12)
at scala.Function0.apply$mcV$sp(Function0.scala:42)
at scala.Function0.apply$mcV$sp$(Function0.scala:42)
at scala.runtime.AbstractFunction0.apply$mcV$sp(AbstractFunction0.scala:17)
at scala.App.$anonfun$main$1(App.scala:98)
at scala.App.$anonfun$main$1$adapted(App.scala:98)
at scala.collection.IterableOnceOps.foreach(IterableOnce.scala:575)
at scala.collection.IterableOnceOps.foreach$(IterableOnce.scala:573)
at scala.collection.AbstractIterable.foreach(Iterable.scala:933)
at scala.App.main(App.scala:98)
at scala.App.main$(App.scala:96)
at test.Test$.main(Test.scala:12)
at test.Test.main(Test.scala)
Caused by: java.lang.IllegalArgumentException: An SPI class of type org.apache.lucene.codecs.Codec with name 'Lucene94' does not exist. You need to add the corresponding JAR file supporting this SPI to your classpath. The current classpath supports the following names: []
at org.apache.lucene.util.NamedSPILoader.lookup(NamedSPILoader.java:113)
at org.apache.lucene.codecs.Codec$Holder.<clinit>(Codec.java:58)
... 17 more
那么，我做错了什么?谢谢。
case PathList("META-INF", xs @ _*) => MergeStrategy.discard表示忽略所有META-INF目录(其全部内容)。这很危险。依赖项lucene-core和lucene-sandbox的META-INF中有服务文件。你应该对你忽略的东西更有选择性。尝试只忽略Java 9+文件module-info.class
assembly / assemblyMergeStrategy := {
case x if x.endsWith("module-info.class") => MergeStrategy.discard
case x =>
val oldStrategy = (assembly / assemblyMergeStrategy).value
oldStrategy(x)
}
或至少取消忽略META-INF/services子目录
assembly / assemblyMergeStrategy := {
case PathList("META-INF", "services", xs @ _*) => MergeStrategy.concat
case PathList("META-INF", xs @ _*) => MergeStrategy.discard
case _ => MergeStrategy.first
}
Drools fat jar空指针KieServices
从fat jar运行Drools Kie项目