Github user clockfly commented on a diff in the pull request: https://github.com/apache/spark/pull/14929#discussion_r77416301 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala --- @@ -62,8 +68,39 @@ class JacksonParser( throw new RuntimeException(s"Malformed line in FAILFAST mode: $record") } if (options.dropMalformed) { - logWarning(s"Dropping malformed line: $record") + if (!isWarningPrintedForMalformedRecord) { + logWarning( + s"""Found at least one malformed records (sample: $record). The JSON reader will drop + |all malformed records in current $DROP_MALFORMED_MODE parser mode. To find out which + |corrupted records have been dropped, please switch the parser mode to $PERMISSIVE_MODE + |mode and use the default inferred schema. + | + |Code example to print all malformed records (scala): + |=================================================== + |// The corrupted record exists in column ${columnNameOfCorruptRecord} + |val parsedJson = spark.read.json("/path/to/json/file/test.json") + | + """.stripMargin) + isWarningPrintedForMalformedRecord = true + } Nil + } else if (schema.getFieldIndex(columnNameOfCorruptRecord).isEmpty) { + if (!isWarningPrintedForMalformedRecord) { + logWarning( + s"""Found at least one malformed records (sample: $record). The JSON reader will replace --- End diff -- It is different, although similar.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org