maropu commented on a change in pull request #28041: [SPARK-30564][SQL]
Improved extra new line and comment remove
URL: https://github.com/apache/spark/pull/28041#discussion_r399891562
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeFormatter.scala
##########
@@ -95,9 +95,128 @@ object CodeFormatter {
new CodeAndComment(code.result().trim(), map)
}
- def stripExtraNewLinesAndComments(input: String): String = {
+ def stripExtraNewLinesAndCommentsUsingRegexp(input: String): String = {
extraNewLinesRegexp.replaceAllIn(commentRegexp.replaceAllIn(input, ""),
"\n")
}
+
+ private object State extends Enumeration {
+ val TEXT, SEPARATOR, SEPARATOR_WITH_NEWLINE, MAYBE_COMMENT, LINE_COMMENT,
BLOCK_COMMENT,
+ BLOCK_COMMENT_WITH_NEWLINE, MAYBE_BLOCK_COMMENT_CLOSING,
+ MAYBE_BLOCK_COMMENT_WITH_NEWLINE_CLOSING = Value
+ }
+
Review comment:
Could you leave some comments here about why we need to replace the existing
regex with this the custom parser?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
