Auto merge of #34485 - tbu-:pr_unicode_debug_str, r=alexcrichton

Escape fewer Unicode codepoints in `Debug` impl of `str`

Use the same procedure as Python to determine whether a character is
printable, described in [PEP 3138]. In particular, this means that the
following character classes are escaped:

- Cc (Other, Control)
- Cf (Other, Format)
- Cs (Other, Surrogate), even though they can't appear in Rust strings
- Co (Other, Private Use)
- Cn (Other, Not Assigned)
- Zl (Separator, Line)
- Zp (Separator, Paragraph)
- Zs (Separator, Space), except for the ASCII space `' '` `0x20`

This allows for user-friendly inspection of strings that are not
English (e.g. compare `"\u{e9}\u{e8}\u{ea}"` to `"éèê"`).

Fixes #34318.
CC #34422.

[PEP 3138]: https://www.python.org/dev/peps/pep-3138/

src/libstd/lib.rs

@@ -218,8 +218,9 @@
 #![feature(associated_consts)]
 #![feature(borrow_state)]
 #![feature(box_syntax)]
-#![feature(cfg_target_vendor)]
 #![feature(cfg_target_thread_local)]
+#![feature(cfg_target_vendor)]
+#![feature(char_escape_debug)]
 #![feature(char_internals)]
 #![feature(collections)]
 #![feature(collections_bound)]
@@ -229,10 +230,10 @@
 #![feature(dropck_parametricity)]
 #![feature(float_extras)]
 #![feature(float_from_str_radix)]
-#![feature(fnbox)]
 #![feature(fn_traits)]
-#![feature(heap_api)]
+#![feature(fnbox)]
 #![feature(hashmap_hasher)]
+#![feature(heap_api)]
 #![feature(inclusive_range)]
 #![feature(int_error_internals)]
 #![feature(into_cow)]
@@ -242,6 +243,7 @@
 #![feature(linkage)]
 #![feature(macro_reexport)]
 #![cfg_attr(test, feature(map_values_mut))]
+#![feature(needs_panic_runtime)]
 #![feature(num_bits_bytes)]
 #![feature(old_wrapping)]
 #![feature(on_unimplemented)]
@@ -249,10 +251,11 @@
 #![feature(optin_builtin_traits)]
 #![feature(panic_unwind)]
 #![feature(placement_in_syntax)]
+#![feature(question_mark)]
 #![feature(rand)]
 #![feature(raw)]
-#![feature(repr_simd)]
 #![feature(reflect_marker)]
+#![feature(repr_simd)]
 #![feature(rustc_attrs)]
 #![feature(shared)]
 #![feature(sip_hash_13)]
@@ -266,6 +269,7 @@
 #![feature(str_utf16)]
 #![feature(test, rustc_private)]
 #![feature(thread_local)]
+#![feature(try_from)]
 #![feature(unboxed_closures)]
 #![feature(unicode)]
 #![feature(unique)]
@@ -273,9 +277,6 @@
 #![feature(unwind_attributes)]
 #![feature(vec_push_all)]
 #![feature(zero_one)]
-#![feature(question_mark)]
-#![feature(try_from)]
-#![feature(needs_panic_runtime)]
 
 // Issue# 30592: Systematically use alloc_system during stage0 since jemalloc
 // might be unavailable or disabled

src/libstd/sys/common/wtf8.rs

@@ -390,7 +390,7 @@ impl fmt::Debug for Wtf8 {
     fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
         fn write_str_escaped(f: &mut fmt::Formatter, s: &str) -> fmt::Result {
             use fmt::Write;
-            for c in s.chars().flat_map(|c| c.escape_default()) {
+            for c in s.chars().flat_map(|c| c.escape_debug()) {
                 f.write_char(c)?
             }
             Ok(())
@@ -1064,9 +1064,9 @@ mod tests {
 
     #[test]
     fn wtf8buf_show() {
-        let mut string = Wtf8Buf::from_str("a\té 💩\r");
+        let mut string = Wtf8Buf::from_str("a\té \u{7f}💩\r");
         string.push(CodePoint::from_u32(0xD800).unwrap());
-        assert_eq!(format!("{:?}", string), r#""a\t\u{e9} \u{1f4a9}\r\u{D800}""#);
+        assert_eq!(format!("{:?}", string), "\"a\\té \\u{7f}\u{1f4a9}\\r\\u{D800}\"");
     }
 
     #[test]