sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1423270340
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:
##########
@@ -604,6 +606,24 @@ class XmlTokenizer(
return Some(str)
}
} catch {
Review Comment:
Consider this to avoid reader.close repetitions:
```
def next(): Option[String] = {
var nextString: Option[String] = None
try {
if (readUntilStartElement()) {
buffer.append(currentStartTag)
// Don't check whether the end element was found. Even if not,
return everything
// that was read, which will invariably cause a parse error later
readUntilEndElement(currentStartTag.endsWith(">"))
nextString = buffer.toString()
buffer = new StringBuilder()
}
} catch {
case e: FileNotFoundException if options.ignoreMissingFiles =>
logWarning(
"Skipping the rest of" +
" the content in the missing file during schema inference",
e)
case NonFatal(e) =>
ExceptionUtils.getRootCause(e) match {
case _: RuntimeException | _: IOException if
options.ignoreCorruptFiles =>
logWarning(
"Skipping the rest of" +
" the content in the corrupted file during schema inference",
e
)
}
} finally {
if (var == None) {
reader.close()
reader = null
}
}
nextStr
}
```
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
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
