Skip to content
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

Jump to bottom

Revert "Disable regex tests to unblock CI (#11606)" #11612

Merged
merged 1 commit into from
Oct 16, 2024
+9 −21
Merged

Revert "Disable regex tests to unblock CI (#11606)" #11612

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
3 changes: 0 additions & 3 deletions integration_tests/src/main/python/regexp_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,7 +284,6 @@ def test_re_replace():

# We have shims to support empty strings for zero-repetition patterns
# See https://github.com/NVIDIA/spark-rapids/issues/5456
@pytest.mark.xfail(reason="https://github.com/NVIDIA/spark-rapids/issues/11600")
def test_re_replace_repetition():
gen = mk_str_gen('.{0,5}TEST[\ud720 A]{0,5}')
assert_gpu_and_cpu_are_equal_collect(
Expand Down Expand Up @@ -699,7 +698,6 @@ def test_regexp_octal_digits():
),
conf=_regexp_conf)

@pytest.mark.xfail(reason="https://github.com/NVIDIA/spark-rapids/issues/11600")
def test_regexp_replace_digit():
gen = mk_str_gen('[a-z]{0,2}[0-9]{0,2}') \
.with_special_case('䤫畍킱곂⬡❽ࢅ獰᳌蛫青') \
Expand Down Expand Up @@ -1078,7 +1076,6 @@ def test_regexp_memory_fallback():
}
)

@pytest.mark.xfail(reason="https://github.com/NVIDIA/spark-rapids/issues/11600")
def test_regexp_memory_ok():
gen = StringGen('test')
assert_gpu_and_cpu_are_equal_collect(
Expand Down
27 changes: 9 additions & 18 deletions tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -418,8 +418,7 @@ class RegularExpressionTranspilerSuite extends AnyFunSuite {

}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("replace_replace - ?, *, +, and {0, n} repetitions") {
test("replace_replace - ?, *, +, and {0, n} repetitions") {
val patterns = Seq("D?", "D*", "D+", "D{0,}", "D{0,1}", "D{0,5}", "[1a-zA-Z]{0,}",
"[1a-zA-Z]{0,2}", "A+")
val inputs = Seq("SS", "DD", "SDSDSDS", "DDDD", "DDDDDD", "ABCDEFG")
Expand Down Expand Up @@ -711,27 +710,23 @@ class RegularExpressionTranspilerSuite extends AnyFunSuite {
}
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("AST fuzz test - regexp_find") {
test("AST fuzz test - regexp_find") {
doAstFuzzTest(Some(REGEXP_LIMITED_CHARS_FIND), REGEXP_LIMITED_CHARS_FIND,
RegexFindMode)
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("AST fuzz test - regexp_replace") {
test("AST fuzz test - regexp_replace") {
doAstFuzzTest(Some(REGEXP_LIMITED_CHARS_REPLACE), REGEXP_LIMITED_CHARS_REPLACE,
RegexReplaceMode)
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("AST fuzz test - regexp_find - full unicode input") {
test("AST fuzz test - regexp_find - full unicode input") {
assume(isUnicodeEnabled())
doAstFuzzTest(None, REGEXP_LIMITED_CHARS_REPLACE,
RegexFindMode)
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("AST fuzz test - regexp_replace - full unicode input") {
test("AST fuzz test - regexp_replace - full unicode input") {
assume(isUnicodeEnabled())
doAstFuzzTest(None, REGEXP_LIMITED_CHARS_REPLACE,
RegexReplaceMode)
Expand All @@ -741,8 +736,7 @@ class RegularExpressionTranspilerSuite extends AnyFunSuite {
Charset.defaultCharset().name() == "UTF-8"
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("AST fuzz test - regexp_find - anchor focused") {
test("AST fuzz test - regexp_find - anchor focused") {
doAstFuzzTest(validDataChars = Some("\r\nabc"),
validPatternChars = "^$\\AZz\r\n()[]-", mode = RegexFindMode)
}
Expand Down Expand Up @@ -784,8 +778,7 @@ class RegularExpressionTranspilerSuite extends AnyFunSuite {
}
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("regexp_split - repetition with {0,n}, or {0,}") {
test("regexp_split - repetition with {0,n}, or {0,}") {
// see https://github.com/NVIDIA/spark-rapids/issues/6958
val patterns = Set("ba{0,}", raw"a\02{0,}", "ba{0,2}", raw"b\02{0,10}")
val data = Seq("abaa", "baba", "ba\u0002b", "ab\u0002b\u0002a")
Expand Down Expand Up @@ -839,17 +832,15 @@ class RegularExpressionTranspilerSuite extends AnyFunSuite {
}
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("string split fuzz") {
test("string split fuzz") {
val (data, patterns) = generateDataAndPatterns(Some(REGEXP_LIMITED_CHARS_REPLACE),
REGEXP_LIMITED_CHARS_REPLACE, RegexSplitMode)
for (limit <- Seq(-2, -1, 2, 5)) {
doStringSplitTest(patterns, data, limit)
}
}

// Disabling until https://github.com/NVIDIA/spark-rapids/issues/11600 is fixed
ignore("string split fuzz - anchor focused") {
test("string split fuzz - anchor focused") {
val (data, patterns) = generateDataAndPatterns(validDataChars = Some("\r\nabc"),
validPatternChars = "^$\\AZz\r\n()", RegexSplitMode)
doStringSplitTest(patterns, data, -1)
Expand Down
Loading