Skip to content

[SPARK-57932][SQL][4.2] Fix regexp_instr and regexp_replace returning wrong results for supplementary characters #57213

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sarutak wants to merge 1 commit into from
+41 −7
Closed

[SPARK-57932][SQL][4.2] Fix regexp_instr and regexp_replace returning wrong results for supplementary characters #57213

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions ...catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -740,9 +740,9 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
}
val source = s.toString()
val position = i.asInstanceOf[Int] - 1
if (position == 0 || position < source.length) {
if (position == 0 || position < source.codePointCount(0, source.length)) {
val m = pattern.matcher(source)
m.region(position, source.length)
m.region(source.offsetByCodePoints(0, position), source.length)
result.delete(0, result.length())
while (m.find) {
try {
Expand Down Expand Up @@ -795,9 +795,9 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
}
String $source = $subject.toString();
int $position = $pos - 1;
if ($position == 0 || $position < $source.length()) {
if ($position == 0 || $position < $source.codePointCount(0, $source.length())) {
$classNameStringBuilder $termResult = new $classNameStringBuilder();
$matcher.region($position, $source.length());
$matcher.region($source.offsetByCodePoints(0, $position), $source.length());

while ($matcher.find()) {
try {
Expand Down Expand Up @@ -1196,9 +1196,10 @@ case class RegExpInStr(subject: Expression, regexp: Expression, idx: Expression)

override def nullSafeEval(s: Any, r: Any, i: Any): Any = {
try {
val m = getLastMatcher(s, r)
val source = s.toString
val m = getLastMatcher(source, r)
if (m.find) {
m.toMatchResult.start() + 1
source.codePointCount(0, m.toMatchResult.start()) + 1
} else {
0
}
Expand All @@ -1212,6 +1213,7 @@ case class RegExpInStr(subject: Expression, regexp: Expression, idx: Expression)

override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
val matcher = ctx.freshName("matcher")
val source = ctx.freshName("source")
val setEvNotNull = if (nullable) {
s"${ev.isNull} = false;"
} else {
Expand All @@ -1225,7 +1227,8 @@ case class RegExpInStr(subject: Expression, regexp: Expression, idx: Expression)
| ${RegExpUtils.initLastMatcherCode(ctx, subject, regexp, matcher, prettyName,
collationId)}
| if ($matcher.find()) {
| ${ev.value} = $matcher.toMatchResult().start() + 1;
| String $source = $subject.toString();
| ${ev.value} = $source.codePointCount(0, $matcher.toMatchResult().start()) + 1;
| } else {
| ${ev.value} = 0;
| }
Expand Down
31 changes: 31 additions & 0 deletions ...yst/src/test/scala/org/apache/spark/sql/catalyst/expressions/RegexpExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -366,6 +366,26 @@ class RegexpExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
RegExpReplace(Literal("\"quote"), Literal("\"quote"), Literal("\"quote")) :: Nil)
}

test("SPARK-57932: regexp_replace position is a code-point position for supplementary chars") {
// scalastyle:off nonascii
checkEvaluation(
RegExpReplace(Literal("😀aXa"), Literal("a"), Literal("Z"), Literal(3)),
"😀aXZ")
checkEvaluation(
RegExpReplace(Literal("😀😀"), Literal("😀"),
Literal("Z"), Literal(3)),
"😀😀")
// Position beyond the string length: nothing is replaced.
checkEvaluation(
RegExpReplace(Literal("😀a"), Literal("a"), Literal("Z"), Literal(4)),
"😀a")
// Position at the last code-point.
checkEvaluation(
RegExpReplace(Literal("a😀b"), Literal("b"), Literal("Z"), Literal(3)),
"a😀Z")
// scalastyle:on nonascii
}

test("SPARK-22570: RegExpReplace should not create a lot of global variables") {
val ctx = new CodegenContext
RegExpReplace(Literal("100"), Literal("(\\d+)"), Literal("num")).genCode(ctx)
Expand Down Expand Up @@ -627,6 +647,17 @@ class RegexpExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
new RegExpInStr(Literal("\"quote"), Literal("\"quote")) :: Nil)
}

test("SPARK-57932: regexp_instr returns a code-point position for supplementary characters") {
// scalastyle:off nonascii
checkEvaluation(RegExpInStr(Literal("😀ab"), Literal("ab"), Literal(0)), 2)
checkEvaluation(RegExpInStr(Literal("a😀b"), Literal("b"), Literal(0)), 3)
checkEvaluation(
RegExpInStr(Literal("😀😁xy"), Literal("xy"), Literal(0)), 3)
// A match made up entirely of supplementary characters.
checkEvaluation(RegExpInStr(Literal("😀😁😂"), Literal("😁"), Literal(0)), 2)
// scalastyle:on nonascii
}

test("SPARK-39758: invalid regexp pattern") {
val s = $"s".string.at(0)
val p = $"p".string.at(1)
Expand Down