HyukjinKwon commented on a change in pull request #29412: URL: https://github.com/apache/spark/pull/29412#discussion_r468989223
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFiltersBase.scala ########## @@ -67,18 +65,12 @@ trait OrcFiltersBase { } } - val primitiveFields = getPrimitiveFields(schema.fields) - if (caseSensitive) { - primitiveFields.toMap - } else { - // Don't consider ambiguity here, i.e. more than one field are matched in case insensitive - // mode, just skip pushdown for these fields, they will trigger Exception when reading, - // See: SPARK-25175. - val dedupPrimitiveFields = primitiveFields - .groupBy(_._1.toLowerCase(Locale.ROOT)) - .filter(_._2.size == 1) - .mapValues(_.head._2) - CaseInsensitiveMap(dedupPrimitiveFields) - } + // Different with Parquet case, for case insensitive analysis, we will set + // `OrcConf.IS_SCHEMA_EVOLUTION_CASE_SENSITIVE`. So we don't need to worry about Review comment: Out of curiosity, do we have one test to verify the case sensitivity vs insensitivity? Other changes look good ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org