Add non_exhaustive to most marker types (#6401)

Fixes #4673


<!--
Thank you for your pull request to ICU4X!

Reminder: try to use [Conventional
Comments](https://conventionalcomments.org/) to make comments clearer.

Please see
https://github.com/unicode-org/icu4x/blob/main/CONTRIBUTING.md for
general
information on contributing to ICU4X.
-->

Author: Manishearth

components/segmenter/src/line.rs

@@ -1065,6 +1065,7 @@ impl<'l, 's, Y: LineBreakType<'l, 's>> LineBreakIterator<'l, 's, Y> {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct LineBreakTypeUtf8;
 
 impl crate::private::Sealed for LineBreakTypeUtf8 {}
@@ -1099,6 +1100,7 @@ impl<'l, 's> LineBreakType<'l, 's> for LineBreakTypeUtf8 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct LineBreakTypePotentiallyIllFormedUtf8;
 
 impl crate::private::Sealed for LineBreakTypePotentiallyIllFormedUtf8 {}
@@ -1186,6 +1188,7 @@ where
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct LineBreakTypeLatin1;
 impl crate::private::Sealed for LineBreakTypeLatin1 {}
 
@@ -1217,6 +1220,7 @@ impl<'s> LineBreakType<'_, 's> for LineBreakTypeLatin1 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct LineBreakTypeUtf16;
 impl crate::private::Sealed for LineBreakTypeUtf16 {}
 

components/segmenter/src/rule_segmenter.rs

@@ -263,6 +263,7 @@ impl<'l, 's, Y: RuleBreakType<'l, 's> + ?Sized> RuleBreakIterator<'l, 's, Y> {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct RuleBreakTypeUtf8;
 
 impl crate::private::Sealed for RuleBreakTypeUtf8 {}
@@ -284,6 +285,7 @@ impl<'s> RuleBreakType<'_, 's> for RuleBreakTypeUtf8 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct RuleBreakTypePotentiallyIllFormedUtf8;
 
 impl crate::private::Sealed for RuleBreakTypePotentiallyIllFormedUtf8 {}
@@ -305,6 +307,7 @@ impl<'s> RuleBreakType<'_, 's> for RuleBreakTypePotentiallyIllFormedUtf8 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct RuleBreakTypeLatin1;
 
 impl crate::private::Sealed for RuleBreakTypeLatin1 {}
@@ -326,6 +329,7 @@ impl<'s> RuleBreakType<'_, 's> for RuleBreakTypeLatin1 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct RuleBreakTypeUtf16;
 
 impl crate::private::Sealed for RuleBreakTypeUtf16 {}

components/segmenter/src/word.rs

@@ -548,6 +548,7 @@ impl WordSegmenter {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct WordBreakTypeUtf8;
 impl crate::private::Sealed for WordBreakTypeUtf8 {}
 
@@ -568,6 +569,7 @@ impl<'l, 's> RuleBreakType<'l, 's> for WordBreakTypeUtf8 {
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct WordBreakTypePotentiallyIllFormedUtf8;
 impl crate::private::Sealed for WordBreakTypePotentiallyIllFormedUtf8 {}
 
@@ -643,6 +645,7 @@ where
 }
 
 #[derive(Debug)]
+#[non_exhaustive]
 pub struct WordBreakTypeUtf16;
 
 impl crate::private::Sealed for WordBreakTypeUtf16 {}

provider/core/src/buf.rs

@@ -15,7 +15,7 @@ pub use self::serde::*;
 ///
 /// The data is expected to be deserialized before it can be used; see
 /// [`DataPayload::into_deserialized`].
-#[allow(clippy::exhaustive_structs)] // marker type
+#[non_exhaustive]
 #[derive(Debug)]
 pub struct BufferMarker;
 

provider/core/src/marker.rs

@@ -560,6 +560,7 @@ pub use __data_marker_id as data_marker_id;
 macro_rules! data_marker {
     ($(#[$doc:meta])* $name:ident, $($debug:literal,)? $struct:ty $(, $(#[$meta:meta])* $info_field:ident = $info_val:expr)* $(,)?) => {
         $(#[$doc])*
+        #[non_exhaustive]
         pub struct $name;
         impl $crate::DynamicDataMarker for $name {
             type DataStruct = $struct;