Rollup merge of #120580 - HTGAzureX1212:HTGAzureX1212/issue-45795, r=m-ou-se

Add `MAX_LEN_UTF8` and `MAX_LEN_UTF16` Constants

This pull request adds the `MAX_LEN_UTF8` and `MAX_LEN_UTF16` constants as per #45795, gated behind the `char_max_len` feature.

The constants are currently applied in the `alloc`, `core` and `std` libraries.

library/alloc/src/lib.rs

@@ -105,6 +105,7 @@
 #![feature(box_uninit_write)]
 #![feature(bstr)]
 #![feature(bstr_internals)]
+#![feature(char_max_len)]
 #![feature(clone_to_uninit)]
 #![feature(coerce_unsized)]
 #![feature(const_eval_select)]

library/alloc/src/string.rs

@@ -1419,7 +1419,9 @@ impl String {
     pub fn push(&mut self, ch: char) {
         match ch.len_utf8() {
             1 => self.vec.push(ch as u8),
-            _ => self.vec.extend_from_slice(ch.encode_utf8(&mut [0; 4]).as_bytes()),
+            _ => {
+                self.vec.extend_from_slice(ch.encode_utf8(&mut [0; char::MAX_LEN_UTF8]).as_bytes())
+            }
         }
     }
 
@@ -1716,7 +1718,7 @@ impl String {
     #[rustc_confusables("set")]
     pub fn insert(&mut self, idx: usize, ch: char) {
         assert!(self.is_char_boundary(idx));
-        let mut bits = [0; 4];
+        let mut bits = [0; char::MAX_LEN_UTF8];
         let bits = ch.encode_utf8(&mut bits).as_bytes();
 
         unsafe {
@@ -2797,7 +2799,7 @@ impl SpecToString for core::ascii::Char {
 impl SpecToString for char {
     #[inline]
     fn spec_to_string(&self) -> String {
-        String::from(self.encode_utf8(&mut [0; 4]))
+        String::from(self.encode_utf8(&mut [0; char::MAX_LEN_UTF8]))
     }
 }
 

library/alloc/tests/lib.rs

@@ -3,6 +3,7 @@
 #![feature(iter_array_chunks)]
 #![feature(assert_matches)]
 #![feature(btree_extract_if)]
+#![feature(char_max_len)]
 #![feature(cow_is_borrowed)]
 #![feature(core_intrinsics)]
 #![feature(downcast_unchecked)]

library/alloc/tests/str.rs

@@ -2,6 +2,7 @@
 
 use std::assert_matches::assert_matches;
 use std::borrow::Cow;
+use std::char::MAX_LEN_UTF8;
 use std::cmp::Ordering::{Equal, Greater, Less};
 use std::str::{from_utf8, from_utf8_unchecked};
 
@@ -1231,7 +1232,7 @@ fn test_to_uppercase_rev_iterator() {
 #[test]
 #[cfg_attr(miri, ignore)] // Miri is too slow
 fn test_chars_decoding() {
-    let mut bytes = [0; 4];
+    let mut bytes = [0; MAX_LEN_UTF8];
     for c in (0..0x110000).filter_map(std::char::from_u32) {
         let s = c.encode_utf8(&mut bytes);
         if Some(c) != s.chars().next() {
@@ -1243,7 +1244,7 @@ fn test_chars_decoding() {
 #[test]
 #[cfg_attr(miri, ignore)] // Miri is too slow
 fn test_chars_rev_decoding() {
-    let mut bytes = [0; 4];
+    let mut bytes = [0; MAX_LEN_UTF8];
     for c in (0..0x110000).filter_map(std::char::from_u32) {
         let s = c.encode_utf8(&mut bytes);
         if Some(c) != s.chars().rev().next() {