Skip to content

Add matching support for \p{Lc} and \p{L&} #373

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.

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
May 3, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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: 3 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
.DS_Store

# The current toolchain is dumping files in the package root, rude
*.emit-module.*

# Xcode
#
# gitignore contributors: remember to update Global/Xcode.gitignore, Objective-C.gitignore & Swift.gitignore
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -32,8 +32,8 @@ extension Source {
static private func classifyGeneralCategory(
_ str: String
) -> Unicode.ExtendedGeneralCategory? {
// This uses the aliases defined in
// https://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt.
// This uses the aliases defined in https://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt.
// Additionally, uses the `L& = Lc` alias defined by PCRE.
withNormalizedForms(str) { str in
switch str {
case "c", "other": return .other
Expand All @@ -43,7 +43,7 @@ extension Source {
case "co", "privateuse": return .privateUse
case "cs", "surrogate": return .surrogate
case "l", "letter": return .letter
case "lc", "casedletter": return .casedLetter
case "lc", "l&", "casedletter": return .casedLetter
case "ll", "lowercaseletter": return .lowercaseLetter
case "lm", "modifierletter": return .modifierLetter
case "lo", "otherletter": return .otherLetter
Expand Down
5 changes: 3 additions & 2 deletions Sources/_StringProcessing/ConsumerInterface.swift
Original file line number Diff line number Diff line change
Expand Up @@ -691,8 +691,9 @@ extension Unicode.ExtendedGeneralCategory {
])

case .casedLetter:
throw Unsupported(
"TODO: cased letter? not the property?")
return consumeScalarGCs([
.uppercaseLetter, .lowercaseLetter, .titlecaseLetter
])

case .control:
return consumeScalarGC(.control)
Expand Down
8 changes: 8 additions & 0 deletions Tests/RegexTests/MatchTests.swift
Original file line number Diff line number Diff line change
Expand Up @@ -693,6 +693,14 @@ extension RegexTests {
firstMatchTest(#"\p{gc=L}"#, input: "123abcXYZ", match: "a")
firstMatchTest(#"\p{Lu}"#, input: "123abcXYZ", match: "X")

// U+0374 GREEK NUMERAL SIGN (Lm)
// U+00AA FEMININE ORDINAL INDICATOR (Lo)
firstMatchTest(#"\p{L}"#, input: "\u{0374}\u{00AA}123abcXYZ", match: "\u{0374}")
firstMatchTest(#"\p{Lc}"#, input: "\u{0374}\u{00AA}123abcXYZ", match: "a")
firstMatchTest(#"\p{Lc}"#, input: "\u{0374}\u{00AA}123XYZ", match: "X")
firstMatchTest(#"\p{L&}"#, input: "\u{0374}\u{00AA}123abcXYZ", match: "a")
firstMatchTest(#"\p{L&}"#, input: "\u{0374}\u{00AA}123XYZ", match: "X")

firstMatchTest(
#"\P{Cc}"#, input: "\n\n\nXYZ", match: "X")
firstMatchTest(
Expand Down
3 changes: 3 additions & 0 deletions Tests/RegexTests/ParseTests.swift
Original file line number Diff line number Diff line change
Expand Up @@ -1156,6 +1156,9 @@ extension RegexTests {
#"\p{C}+"#,
oneOrMore(of: prop(.generalCategory(.other))))

// L& defined by PCRE.
parseTest(#"\p{L&}"#, prop(.generalCategory(.casedLetter)))

// UAX44-LM3 means all of the below are equivalent.
let lowercaseLetter = prop(.generalCategory(.lowercaseLetter))
parseTest(#"\p{ll}"#, lowercaseLetter)
Expand Down