10000 Add more tests for Unicode case-insensitivity in regexes. by sjrd · Pull Request #5198 · scala-js/scala-js · GitHub
[go: up one dir, main page]
Skip to content

Add more tests for Unicode case-insensitivity in regexes. #5198

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

Merged
merged 2 commits into from
Jun 25, 2025
+51 −6
Merged

Add more tests for Unicode case-insensitivity in regexes. #5198

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
43902c4
Add more tests for Unicode case-insensitivity in regexes.
sjrd Jun 16, 2025
5696a1a
Do not rely on `Formatter` in the debug prints of `RegexEngineTest`.
sjrd Jun 16, 2025
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
57 changes: 51 additions & 6 deletions ...uite/shared/src/test/scala/org/scalajs/testsuite/javalib/util/regex/RegexEngineTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,11 +54,12 @@ class RegexEngineTest {

private def debugEscape(pattern: String): String = {
pattern.flatMap {
case '\t' => "`t"
case '\n' => "`n"
case '\r' => "`r"
case c if c < ' ' => "`x%02X".format(c.toInt)
case c => c.toString()
case '\t' => "`t"
case '\n' => "`n"
case '\r' => "`r"
case c if c < 0x10 => "`x0" + c.toInt.toHexString
case c if c < ' ' => "`x" + c.toInt.toHexString
case c => c.toString()
}
}

Expand Down Expand Up @@ -1976,8 +1977,52 @@ class RegexEngineTest {
val s = compile("s", CaseInsensitive | UnicodeCase)
assertMatches(s, "s")
assertMatches(s, "S")
assertMatches(s, "\u017F") // ſ LATIN SMALL LETTER LONG S
assertMatches(s, "\u017F") // ſ LATIN SMALL LETTER LONG S; 017F folds to 's'
assertNotMatches(s, "t")

val ranges = compile("[g-l\uFB00\u0175-\u0182\u0540-\u0550\u1F68-\u1F8E\u1FAA-\u1FAF\u2126]",
CaseInsensitive | UnicodeCase)
// g-l
assertMatches(ranges, "H")
assertMatches(ranges, "\u212A") // K KELVIN SIGN, folds to 'k'
// FB00
assertMatches(ranges, "\uFB00") // ff LATIN SMALL LIGATURE FF
// 0175-0182 (contains 017F which folds to 's')
if (!executingInJVM) {
// https://bugs.openjdk.org/browse/JDK-8360459
assertMatches(ranges, "s")
assertMatches(ranges, "S")
}
assertMatches(ranges, "\u017F")
assertMatches(ranges, "\u0180") // in range; does not participate in case folding
// 0540-0550
assertMatches(ranges, "\u0547") // in range
assertMatches(ranges, "\u0577") // 0547 folds to 0577
// 1F68-1F8E
assertMatches(ranges, "\u1F65") // 1F6D folds to 1F65
assertMatches(ranges, "\u1F6D") // in range
assertMatches(ranges, "\u1F82") // 1F8A folds to 1F82, and 1F82 is also in range
// 1FAA-1FAF
assertMatches(ranges, "\u1FA4") // 1FAC folds to 1FA4 only in simple case folding
// 2126
assertMatches(ranges, "\u2126") // in the set
assertMatches(ranges, "\u03C9") // 2126 folds to 03C9
assertMatches(ranges, "\u03A9") // 03A9 also folds to 03C9
// No matches
assertNotMatches(ranges, "t")
assertNotMatches(ranges, "ff") // ff FB00 would only match with full case folding

// Demonstrate that the JVM recognizes 017F as folding to 's' if the range is ASCII
val rangeWithASCII_S = compile("[P-U]", CaseInsensitive | UnicodeCase)
assertMatches(rangeWithASCII_S, "s")
assertMatches(rangeWithASCII_S, "S")
assertMatches(rangeWithASCII_S, "\u017F")

// Demonstrate that the JVM recognizes 017F as folding to 's' if it is not a range
val nonRangeWith_017F = compile("[\u017F\u0184]", CaseInsensitive | UnicodeCase)
assertMatches(nonRangeWith_017F, "s")
assertMatches(nonRangeWith_017F, "S")
assertMatches(nonRangeWith_017F, "\u017F")
}

@Test def wordBoundary(): Unit = {
Expand Down
0