philo-he commented on code in PR #13278:
URL: https://github.com/apache/gluten/pull/13278#discussion_r4397484750
##########
gluten-substrait/src/main/scala/org/apache/gluten/expression/ExpressionConverter.scala:
##########
@@ -949,6 +979,33 @@ object ExpressionConverter extends SQLConfHelper with
Logging {
}
}
+ /**
+ * Translates the pattern argument of a regex expression to RE2 syntax
before it is written into
+ * the Substrait literal. If the pattern is a string literal, Java Unicode
escapes (backslash-u
+ * followed by 4 hex digits) are converted to RE2's `\x{XXXX}` form.
Patterns that contain
+ * constructs with no RE2 equivalent (lookaheads, lookbehinds,
backreferences) throw
+ * [[GlutenNotSupportException]] to trigger graceful fallback. Non-literal
(column-referenced)
+ * patterns, and all patterns on backends that do not use RE2, are passed
through unchanged.
+ */
+ private def withRe2PatternTranslation(
+ patternChild: Expression,
+ attributeSeq: Seq[Attribute],
+ expressionsMap: Map[Class[_], String]): ExpressionTransformer = {
+ patternChild match {
+ case Literal(patStr: UTF8String, StringType)
+ if
BackendsApiManager.getSparkPlanExecApiInstance.needsRe2PatternTranslation =>
+ val translated = Re2PatternUtils
+ .translateJavaPatternToRe2(patStr.toString)
+ .getOrElse(throw new GlutenNotSupportException(
+ s"Regex pattern
${Re2PatternUtils.describePattern(patStr.toString)} uses " +
+ s"constructs (lookahead/lookbehind/backreference) or unpaired
surrogates " +
+ s"that RE2 cannot handle. Falling back to Spark."))
+ LiteralTransformer(Literal(UTF8String.fromString(translated),
StringType))
+ case other =>
+ replaceWithExpressionTransformer0(other, attributeSeq, expressionsMap)
Review Comment:
Can we move this code to backend API? Then we only keep that and can remove
needsRe2PatternTranslation.
```
// VeloxSparkPlanExecApi (and BoltSparkPlanExecApi)
override def rewriteRegexPattern(pattern: Expression): Expression = pattern
match {
case Literal(p: UTF8String, StringType) =>
val translated = Re2PatternUtils
.translateJavaPatternToRe2(p.toString)
.getOrElse(throw new GlutenNotSupportException(
s"Regex pattern ${Re2PatternUtils.describePattern(p.toString)} uses
constructs " +
"that RE2 cannot handle. Falling back to Spark."))
Literal(UTF8String.fromString(translated), StringType)
case other => other
}
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
