[SPARK-34402][SQL] Group exception about data format schema

### What changes were proposed in this pull request? Group exception about data format schema of different format, orc/parquet ### Why are the changes needed? group exception ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Not need Closes #33296 from AngersZhuuuu/SPARK-34402. Authored-by: Angerszhuuuu <angers.zhu@gmail.com> Signed-off-by: Wenchen Fan <wenchen@databricks.com>
apache · Jul 26, 2021 · a63802f · a63802f
1 parent e5616e3
commit a63802f
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 9 deletions.
diff --git a/...ain/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala b/...ain/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaConverter.scala
@@ -586,11 +586,9 @@ private[sql] object ParquetSchemaConverter {
 
   def checkFieldName(name: String): Unit = {
     // ,;{}()\n\t= and space are special characters in Parquet schema
-    checkConversionRequirement(
-      !name.matches(".*[ ,;{}()\n\t=].*"),
-      s"""Attribute name "$name" contains invalid character(s) among " ,;{}()\\n\\t=".
-         |Please use alias to rename it.
-       """.stripMargin.split("\n").mkString(" ").trim)
+    if (name.matches(".*[ ,;{}()\n\t=].*")) {
+      throw QueryCompilationErrors.columnNameContainsInvalidCharactersError(name)
+    }
   }
 
   def checkFieldNames(schema: StructType): Unit = {

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
@@ -3002,8 +3002,8 @@ class HiveDDLSuite
           spark.sql(s"INSERT OVERWRITE LOCAL DIRECTORY '${path.getCanonicalPath}' " +
             s"STORED AS PARQUET SELECT ID, if(1=1, 1, 0), abs(id), '^-' FROM v")
         }.getMessage
-        assert(e.contains("Attribute name \"(IF((1 = 1), 1, 0))\" contains" +
-          " invalid character(s) among \" ,;{}()\\n\\t=\". Please use alias to rename it."))
+        assert(e.contains("Column name \"(IF((1 = 1), 1, 0))\" contains invalid character(s). " +
+          "Please use alias to rename it."))
       }
     }
   }
@@ -3022,8 +3022,8 @@ class HiveDDLSuite
                |FROM v
                """.stripMargin)
         }.getMessage
-        assert(e.contains("Attribute name \"IF(ID=1,ID,0)\" contains" +
-          " invalid character(s) among \" ,;{}()\\n\\t=\". Please use alias to rename it."))
+        assert(e.contains("Column name \"IF(ID=1,ID,0)\" contains" +
+          " invalid character(s). Please use alias to rename it."))
       }
     }
   }