Gremlin---导入json数据出现Illegal unqu
2017-11-29 本文已影响36人
zlcook
org.apache.tinkerpop.shaded.jackson.core.JsonParseException: Illegal unquoted character ((CTRL-CHAR, code 28)): has to be escaped using backslash to be included in string value
at [Source: java.io.ByteArrayInputStream@60856961; line: 1, column: 381]
java.lang.RuntimeException: org.apache.tinkerpop.shaded.jackson.core.JsonParseException: Illegal unquoted character ((CTRL-CHAR, code 28)): has to be escaped using backslash to be included in string value
at [Source: java.io.ByteArrayInputStream@60856961; line: 1, column: 381]
at org.apache.tinkerpop.gremlin.util.function.FunctionUtils.lambda$wrapFunction$0(FunctionUtils.java:40)
at java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at java.util.Iterator.forEachRemaining(Iterator.java:116)
at java.util.Spliterators$IteratorSpliterator.forEachRemaining(Spliterators.java:1801)
at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:481)
at java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:471)
at java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:151)
at java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:174)
at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
at java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:418)
at org.apache.tinkerpop.gremlin.structure.io.graphson.GraphSONReader.readGraph(GraphSONReader.java:104)
at org.apache.tinkerpop.gremlin.structure.io.graphson.GraphSONIo.readGraph(GraphSONIo.java:96)
at com.jd.jr.graph.data.JsonVerifyTest$$anonfun$1.apply$mcV$sp(JsonVerifyTest.scala:18)
at com.jd.jr.graph.data.JsonVerifyTest$$anonfun$1.apply(JsonVerifyTest.scala:16)
at com.jd.jr.graph.data.JsonVerifyTest$$anonfun$1.apply(JsonVerifyTest.scala:16)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FlatSpecLike$$anon$1.apply(FlatSpecLike.scala:1682)
at org.scalatest.TestSuite$class.withFixture(TestSuite.scala:196)
at org.scalatest.FlatSpec.withFixture(FlatSpec.scala:1685)
at org.scalatest.FlatSpecLike$class.invokeWithFixture$1(FlatSpecLike.scala:1679)
at org.scalatest.FlatSpecLike$$anonfun$runTest$1.apply(FlatSpecLike.scala:1692)
at org.scalatest.FlatSpecLike$$anonfun$runTest$1.apply(FlatSpecLike.scala:1692)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
at org.scalatest.FlatSpecLike$class.runTest(FlatSpecLike.scala:1692)
at org.scalatest.FlatSpec.runTest(FlatSpec.scala:1685)
at org.scalatest.FlatSpecLike$$anonfun$runTests$1.apply(FlatSpecLike.scala:1750)
at org.scalatest.FlatSpecLike$$anonfun$runTests$1.apply(FlatSpecLike.scala:1750)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:373)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:410)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
at org.scalatest.FlatSpecLike$class.runTests(FlatSpecLike.scala:1750)
at org.scalatest.FlatSpec.runTests(FlatSpec.scala:1685)
at org.scalatest.Suite$class.run(Suite.scala:1147)
at org.scalatest.FlatSpec.org$scalatest$FlatSpecLike$$super$run(FlatSpec.scala:1685)
at org.scalatest.FlatSpecLike$$anonfun$run$1.apply(FlatSpecLike.scala:1795)
at org.scalatest.FlatSpecLike$$anonfun$run$1.apply(FlatSpecLike.scala:1795)
at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
at org.scalatest.FlatSpecLike$class.run(FlatSpecLike.scala:1795)
at org.scalatest.FlatSpec.run(FlatSpec.scala:1685)
at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45)
at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340)
at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1334)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334)
at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011)
at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010)
at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500)
at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010)
at org.scalatest.tools.Runner$.run(Runner.scala:850)
at org.scalatest.tools.Runner.run(Runner.scala)
at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2(ScalaTestRunner.java:138)
at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:28)
Caused by: org.apache.tinkerpop.shaded.jackson.core.JsonParseException: Illegal unquoted character ((CTRL-CHAR, code 28)): has to be escaped using backslash to be included in string value
at [Source: java.io.ByteArrayInputStream@60856961; line: 1, column: 381]
at org.apache.tinkerpop.shaded.jackson.core.JsonParser._constructError(JsonParser.java:1702)
at org.apache.tinkerpop.shaded.jackson.core.base.ParserMinimalBase._reportError(ParserMinimalBase.java:558)
at org.apache.tinkerpop.shaded.jackson.core.base.ParserMinimalBase._throwUnquotedSpace(ParserMinimalBase.java:522)
at org.apache.tinkerpop.shaded.jackson.core.json.UTF8StreamJsonParser._finishString2(UTF8StreamJsonParser.java:2540)
at org.apache.tinkerpop.shaded.jackson.core.json.UTF8StreamJsonParser._finishAndReturnString(UTF8StreamJsonParser.java:2469)
at org.apache.tinkerpop.shaded.jackson.core.json.UTF8StreamJsonParser.getText(UTF8StreamJsonParser.java:315)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.deserialize(UntypedObjectDeserializer.java:513)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.mapObject(UntypedObjectDeserializer.java:637)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.deserialize(UntypedObjectDeserializer.java:495)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.mapArray(UntypedObjectDeserializer.java:586)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.deserialize(UntypedObjectDeserializer.java:509)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.mapObject(UntypedObjectDeserializer.java:652)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.UntypedObjectDeserializer$Vanilla.deserialize(UntypedObjectDeserializer.java:495)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.MapDeserializer._readAndBindStringKeyMap(MapDeserializer.java:517)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.MapDeserializer.deserialize(MapDeserializer.java:362)
at org.apache.tinkerpop.shaded.jackson.databind.deser.std.MapDeserializer.deserialize(MapDeserializer.java:27)
at org.apache.tinkerpop.shaded.jackson.databind.ObjectMapper._readMapAndClose(ObjectMapper.java:3798)
at org.apache.tinkerpop.shaded.jackson.databind.ObjectMapper.readValue(ObjectMapper.java:2915)
at org.apache.tinkerpop.gremlin.structure.io.graphson.GraphSONReader.readVertex(GraphSONReader.java:176)
at org.apache.tinkerpop.gremlin.structure.io.graphson.GraphSONReader.lambda$readGraph$0(GraphSONReader.java:104)
at org.apache.tinkerpop.gremlin.util.function.FunctionUtils.lambda$wrapFunction$0(FunctionUtils.java:36)
... 62 more
-
原因是导入json中存在Ascii码值为32（十进制）以下的控制字符，如换行、文件分隔符等，需要将其替换掉。
-
如下存在文件控制符FS，其是不可见字符，但是有些软件打开时因为其使用的编码原因会显示成一些奇怪字符。文件控制符Ascill的10进制值为28，16进制值为1C
image.png
-
解决： 通过正则表达式将json中的控制符（ascill编码低于32的zif）替换掉
val inputJsonData ="graph_importer/src/test/resources/proddata.json"
val outJsonData ="graph_importer/src/test/resources/outData.json"
"Content" should " valid" in{
val invalidCharReg ="""[\u0000-\u001F]+"""
val source = Source.fromFile(inputJsonData,"UTF-8");
val lineIterator = source.getLines();
val out = new PrintWriter(outJsonData)
for( line <- lineIterator ){
var old = line.mkString
old = old.replaceAll(invalidCharReg,"")
out.println(old)
}
out.close()
}
