Skip to content

[SPARK-16514] [SQL] Fix various regex codegen bugs #14168

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
wants to merge 1 commit into from
Closed

[SPARK-16514] [SQL] Fix various regex codegen bugs #14168

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
48 changes: 33 additions & 15 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 @@ -108,10 +108,11 @@ case class Like(left: Expression, right: Expression)
""")
}
} else {
val rightStr = ctx.freshName("rightStr")
nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
s"""
String rightStr = ${eval2}.toString();
${patternClass} $pattern = ${patternClass}.compile($escapeFunc(rightStr));
String $rightStr = ${eval2}.toString();
${patternClass} $pattern = ${patternClass}.compile($escapeFunc($rightStr));
${ev.value} = $pattern.matcher(${eval1}.toString()).matches();
"""
})
Expand Down Expand Up @@ -157,10 +158,11 @@ case class RLike(left: Expression, right: Expression)
""")
}
} else {
val rightStr = ctx.freshName("rightStr")
nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
s"""
String rightStr = ${eval2}.toString();
${patternClass} $pattern = ${patternClass}.compile(rightStr);
String $rightStr = ${eval2}.toString();
${patternClass} $pattern = ${patternClass}.compile($rightStr);
${ev.value} = $pattern.matcher(${eval1}.toString()).find(0);
"""
})
Expand Down Expand Up @@ -259,6 +261,8 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
val classNamePattern = classOf[Pattern].getCanonicalName
val classNameStringBuffer = classOf[java.lang.StringBuffer].getCanonicalName

val matcher = ctx.freshName("matcher")

ctx.addMutableState("UTF8String", termLastRegex, s"${termLastRegex} = null;")
ctx.addMutableState(classNamePattern, termPattern, s"${termPattern} = null;")
ctx.addMutableState("String", termLastReplacement, s"${termLastReplacement} = null;")
Expand All @@ -267,6 +271,12 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
ctx.addMutableState(classNameStringBuffer,
termResult, s"${termResult} = new $classNameStringBuffer();")

val setEvNotNull = if (nullable) {
s"${ev.isNull} = false;"
} else {
""
}

nullSafeCodeGen(ctx, ev, (subject, regexp, rep) => {
s"""
if (!$regexp.equals(${termLastRegex})) {
Expand All @@ -280,14 +290,14 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
${termLastReplacement} = ${termLastReplacementInUTF8}.toString();
}
${termResult}.delete(0, ${termResult}.length());
java.util.regex.Matcher m = ${termPattern}.matcher($subject.toString());
java.util.regex.Matcher ${matcher} = ${termPattern}.matcher($subject.toString());

while (m.find()) {
m.appendReplacement(${termResult}, ${termLastReplacement});
while (${matcher}.find()) {
${matcher}.appendReplacement(${termResult}, ${termLastReplacement});
}
m.appendTail(${termResult});
${matcher}.appendTail(${termResult});
${ev.value} = UTF8String.fromString(${termResult}.toString());
${ev.isNull} = false;
$setEvNotNull
"""
})
}
Expand Down Expand Up @@ -334,26 +344,34 @@ case class RegExpExtract(subject: Expression, regexp: Expression, idx: Expressio
val termLastRegex = ctx.freshName("lastRegex")
val termPattern = ctx.freshName("pattern")
val classNamePattern = classOf[Pattern].getCanonicalName
val matcher = ctx.freshName("matcher")
val matchResult = ctx.freshName("matchResult")

ctx.addMutableState("UTF8String", termLastRegex, s"${termLastRegex} = null;")
ctx.addMutableState(classNamePattern, termPattern, s"${termPattern} = null;")

val setEvNotNull = if (nullable) {
s"${ev.isNull} = false;"
} else {
""
}

nullSafeCodeGen(ctx, ev, (subject, regexp, idx) => {
s"""
if (!$regexp.equals(${termLastRegex})) {
// regex value changed
${termLastRegex} = $regexp.clone();
${termPattern} = ${classNamePattern}.compile(${termLastRegex}.toString());
}
java.util.regex.Matcher m =
java.util.regex.Matcher ${matcher} =
${termPattern}.matcher($subject.toString());
if (m.find()) {
java.util.regex.MatchResult mr = m.toMatchResult();
${ev.value} = UTF8String.fromString(mr.group($idx));
${ev.isNull} = false;
if (${matcher}.find()) {
java.util.regex.MatchResult ${matchResult} = ${matcher}.toMatchResult();
${ev.value} = UTF8String.fromString(${matchResult}.group($idx));
$setEvNotNull
} else {
${ev.value} = UTF8String.EMPTY_UTF8;
${ev.isNull} = false;
$setEvNotNull
}"""
})
}
Expand Down
6 changes: 6 additions & 0 deletions ...yst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -631,6 +631,9 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
checkEvaluation(expr, null, row4)
checkEvaluation(expr, null, row5)
checkEvaluation(expr, null, row6)

val nonNullExpr = RegExpReplace(Literal("100-200"), Literal("(\\d+)"), Literal("num"))
checkEvaluation(nonNullExpr, "num-num", row1)
}

test("RegexExtract") {
Expand All @@ -657,6 +660,9 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {

val expr1 = new RegExpExtract(s, p)
checkEvaluation(expr1, "100", row1)

val nonNullExpr = RegExpExtract(Literal("100-200"), Literal("(\\d+)-(\\d+)"), Literal(1))
checkEvaluation(nonNullExpr, "100", row1)
}

test("SPLIT") {
Expand Down