We are facing issues while storing some content, which actually is an HTML document. It has some special non ASCII chars in it and we're unable to store it in elasticsearch.
We're using elastic version 5.2.2
One of the chars for which it fails is '×'
com.cdk.dmg.lib.esindexer.exception.ESIndexingFailedException: org.elasticsearch.client.ResponseException: POST http://test.com:9200content_001/content/3b6f664c-b490-460c-bd61-dd6ca1986cdb_WIP/: HTTP/1.1 400 Bad Request
{"error":{"root_cause":[{"type":"mapper_parsing_exception","reason":"failed to parse"}],"type":"mapper_parsing_exception","reason":"failed to parse","caused_by":{"type":"i_o_exception","reason":"Invalid UTF-8 middle byte 0x3c\n at [Source: org.elasticsearch.common.bytes.BytesReference$MarkSupportingStreamInputWrapper@5f5f66a6; line: 46, column: 5660]"}},"status":400}
at com.cdk.dmg.lib.esindexer.Indexer.index(Indexer.java:52)
at com.cdk.dmg.services.sitecontent.es.integ.config.ESLibErrorTest.reproduceJsonError(ESLibErrorTest.java:34)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
at org.springframework.test.context.junit4.statements.RunBeforeTestMethodCallbacks.evaluate(RunBeforeTestMethodCallbacks.java:75)
at org.springframework.test.context.junit4.statements.RunAfterTestMethodCallbacks.evaluate(RunAfterTestMethodCallbacks.java:86)
at org.springframework.test.context.junit4.statements.SpringRepeat.evaluate(SpringRepeat.java:84)
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
at org.springframework.test.context.junit4.SpringJUnit4ClassRunner.runChild(SpringJUnit4ClassRunner.java:252)
at org.springframework.test.context.junit4.SpringJUnit4ClassRunner.runChild(SpringJUnit4ClassRunner.java:94)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
at org.springframework.test.context.junit4.statements.RunBeforeTestClassCallbacks.evaluate(RunBeforeTestClassCallbacks.java:61)
at org.springframework.test.context.junit4.statements.RunAfterTestClassCallbacks.evaluate(RunAfterTestClassCallbacks.java:70)
at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
at org.springframework.test.context.junit4.SpringJUnit4ClassRunner.run(SpringJUnit4ClassRunner.java:191)
at org.junit.runner.JUnitCore.run(JUnitCore.java:137)
at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:119)
at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:42)
at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:234)
at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:74)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:144)
Caused by: org.elasticsearch.client.ResponseException: POST http://c04ddmnitr938.dslab.ad.adp.com:9200content_001/content/3b6f664c-b490-460c-bd61-dd6ca1986cdb_WIP/: HTTP/1.1 400 Bad Request
{"error":{"root_cause":[{"type":"mapper_parsing_exception","reason":"failed to parse"}],"type":"mapper_parsing_exception","reason":"failed to parse","caused_by":{"type":"i_o_exception","reason":"Invalid UTF-8 middle byte 0x3c\n at [Source: org.elasticsearch.common.bytes.BytesReference$MarkSupportingStreamInputWrapper@5f5f66a6; line: 46, column: 5660]"}},"status":400}
at org.elasticsearch.client.RestClient$1.completed(RestClient.java:311)
at org.elasticsearch.client.RestClient$1.completed(RestClient.java:300)
at org.apache.http.concurrent.BasicFuture.completed(BasicFuture.java:119)
at org.apache.http.impl.nio.client.DefaultClientExchangeHandlerImpl.responseCompleted(DefaultClientExchangeHandlerImpl.java:177)
at org.apache.http.nio.protocol.HttpAsyncRequestExecutor.processResponse(HttpAsyncRequestExecutor.java:436)
at org.apache.http.nio.protocol.HttpAsyncRequestExecutor.inputReady(HttpAsyncRequestExecutor.java:326)
at org.apache.http.impl.nio.DefaultNHttpClientConnection.consumeInput(DefaultNHttpClientConnection.java:265)
at org.apache.http.impl.nio.client.InternalIODispatch.onInputReady(InternalIODispatch.java:81)
at org.apache.http.impl.nio.client.InternalIODispatch.onInputReady(InternalIODispatch.java:39)
at org.apache.http.impl.nio.reactor.AbstractIODispatch.inputReady(AbstractIODispatch.java:114)
at org.apache.http.impl.nio.reactor.BaseIOReactor.readable(BaseIOReactor.java:162)
at org.apache.http.impl.nio.reactor.AbstractIOReactor.processEvent(AbstractIOReactor.java:337)
at org.apache.http.impl.nio.reactor.AbstractIOReactor.processEvents(AbstractIOReactor.java:315)
at org.apache.http.impl.nio.reactor.AbstractIOReactor.execute(AbstractIOReactor.java:276)
at org.apache.http.impl.nio.reactor.BaseIOReactor.execute(BaseIOReactor.java:104)
at org.apache.http.impl.nio.reactor.AbstractMultiworkerIOReactor$Worker.run(AbstractMultiworkerIOReactor.java:588)
at java.lang.Thread.run(Thread.java:745)