Skip to content

[SPARK-48435][SQL] UNICODE collation should not support binary equality #46772

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
uros-db wants to merge 9 commits into from
Closed

[SPARK-48435][SQL] UNICODE collation should not support binary equality #46772

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
c0737f1
Initial commit
uros-db May 28, 2024
1e6bee0
Use TERTIARY strength
uros-db May 28, 2024
bfd7e60
Fix tests
uros-db May 28, 2024
319d0a8
Fix tests
uros-db May 28, 2024
b5501e8
Merge branch 'master' into fix-unicode
uros-db May 28, 2024
26fc209
Update CollationFactorySuite.scala
uros-db May 29, 2024
d0b741c
Merge branch 'master' into fix-unicode
uros-db May 29, 2024
6bf6e4e
Merge branch 'apache:master' into fix-unicode
uros-db May 30, 2024
fcf122a
Fix tests
uros-db May 30, 2024
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
2 changes: 1 addition & 1 deletion common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,7 +351,7 @@ public static int lowercaseIndexOf(final UTF8String target, final UTF8String pat

public static int indexOf(final UTF8String target, final UTF8String pattern,
final int start, final int collationId) {
if (pattern.numBytes() == 0) return 0;
if (pattern.numBytes() == 0) return target.indexOfEmpty(start);
if (target.numBytes() == 0) return MATCH_NOT_FOUND;

StringSearch stringSearch = CollationFactory.getStringSearch(target, pattern, collationId);
Expand Down
5 changes: 3 additions & 2 deletions common/unsafe/src/test/scala/org/apache/spark/unsafe/types/CollationFactorySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ class CollationFactorySuite extends AnyFunSuite with Matchers { // scalastyle:ig
assert(UNICODE_COLLATION_ID == (1 << 29))
val unicode = fetchCollation(UNICODE_COLLATION_ID)
assert(unicode.collationName == "UNICODE")
assert(!unicode.supportsBinaryEquality);
assert(!unicode.supportsBinaryEquality)

assert(UNICODE_CI_COLLATION_ID == ((1 << 29) | (1 << 17)))
val unicodeCi = fetchCollation(UNICODE_CI_COLLATION_ID)
Expand Down Expand Up @@ -146,7 +146,8 @@ class CollationFactorySuite extends AnyFunSuite with Matchers { // scalastyle:ig
CollationTestCase("UNICODE_CI", "aaa", "aaa", true),
CollationTestCase("UNICODE_CI", "aaa", "AAA", true),
CollationTestCase("UNICODE_CI", "aaa", "bbb", false),
CollationTestCase("UNICODE_CI", "å", "a\u030A", true)
CollationTestCase("UNICODE_CI", "å", "a\u030A", true),
CollationTestCase("UNICODE_CI", "Å", "a\u030A", true)
)

checks.foreach(testCase => {
Expand Down
8 changes: 4 additions & 4 deletions ...t/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollationExpressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,10 +174,10 @@ class CollationExpressionSuite extends SparkFunSuite with ExpressionEvalHelper {
("aa", "UTF8_BINARY_LCASE", UTF8String.fromString("aa").getBytes),
("AA", "UTF8_BINARY_LCASE", UTF8String.fromString("aa").getBytes),
("aA", "UTF8_BINARY_LCASE", UTF8String.fromString("aa").getBytes),
("", "UNICODE", UTF8String.fromString("").getBytes),
("aa", "UNICODE", UTF8String.fromString("aa").getBytes),
("AA", "UNICODE", UTF8String.fromString("AA").getBytes),
("aA", "UNICODE", UTF8String.fromString("aA").getBytes),
("", "UNICODE", Array[Byte](1, 1, 0)),
("aa", "UNICODE", Array[Byte](42, 42, 1, 6, 1, 6, 0)),
("AA", "UNICODE", Array[Byte](42, 42, 1, 6, 1, -36, -36, 0)),
("aA", "UNICODE", Array[Byte](42, 42, 1, 6, 1, -59, -36, 0)),
("", "UNICODE_CI", Array[Byte](1, 0)),
("aa", "UNICODE_CI", Array[Byte](42, 42, 1, 6, 0)),
("AA", "UNICODE_CI", Array[Byte](42, 42, 1, 6, 0)),
Expand Down