summaryrefslogtreecommitdiffstats
path: root/vendor/unicode-security/src/confusable_detection.rs
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-17 12:02:58 +0000
commit698f8c2f01ea549d77d7dc3338a12e04c11057b9 (patch)
tree173a775858bd501c378080a10dca74132f05bc50 /vendor/unicode-security/src/confusable_detection.rs
parentInitial commit. (diff)
downloadrustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.tar.xz
rustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.zip
Adding upstream version 1.64.0+dfsg1.upstream/1.64.0+dfsg1
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'vendor/unicode-security/src/confusable_detection.rs')
-rw-r--r--vendor/unicode-security/src/confusable_detection.rs39
1 files changed, 39 insertions, 0 deletions
diff --git a/vendor/unicode-security/src/confusable_detection.rs b/vendor/unicode-security/src/confusable_detection.rs
new file mode 100644
index 000000000..dd1a0d25d
--- /dev/null
+++ b/vendor/unicode-security/src/confusable_detection.rs
@@ -0,0 +1,39 @@
+//! [Confusable detection](https://www.unicode.org/reports/tr39/#Confusable_Detection)
+
+use core::iter;
+
+enum OnceOrMore<T, I> {
+ Once(iter::Once<T>),
+ More(I),
+}
+
+impl<T, I> Iterator for OnceOrMore<T, I>
+where
+ I: Iterator<Item = T>,
+{
+ type Item = T;
+
+ fn next(&mut self) -> Option<T> {
+ use OnceOrMore::*;
+ match self {
+ Once(v) => v.next(),
+ More(i) => i.next(),
+ }
+ }
+}
+
+type StaticSliceIterCloned = core::iter::Cloned<core::slice::Iter<'static, char>>;
+
+fn char_prototype(c: char) -> OnceOrMore<char, StaticSliceIterCloned> {
+ use crate::tables::confusable_detection::char_confusable_prototype;
+ match char_confusable_prototype(c) {
+ None => OnceOrMore::Once(iter::once(c)),
+ Some(l) => OnceOrMore::More(l.iter().cloned()),
+ }
+}
+
+/// Calculate skeleton for string, as defined by UTS 39
+pub fn skeleton(s: &str) -> impl Iterator<Item = char> + '_ {
+ use unicode_normalization::UnicodeNormalization;
+ s.chars().nfd().flat_map(char_prototype).nfd()
+}