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.

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

1 files changed, 13 insertions, 3 deletions

diff --git a/src/libcoretest/char.rs b/src/libcoretest/char.rs
index c8906fed3d2..e01f83ed70a 100644
--- a/src/libcoretest/char.rs
+++ b/src/libcoretest/char.rs
@@ -142,18 +142,28 @@ fn test_escape_default() {
     assert_eq!(s, "a");
     let s = string('~');
     assert_eq!(s, "~");
+    let s = string('é');
+    assert_eq!(s, "é");
     let s = string('\x00');
     assert_eq!(s, "\\u{0}");
     let s = string('\x1f');
     assert_eq!(s, "\\u{1f}");
     let s = string('\x7f');
     assert_eq!(s, "\\u{7f}");
+    let s = string('\u{80}');
+    assert_eq!(s, "\\u{80}");
     let s = string('\u{ff}');
-    assert_eq!(s, "\\u{ff}");
+    assert_eq!(s, "\u{ff}");
     let s = string('\u{11b}');
-    assert_eq!(s, "\\u{11b}");
+    assert_eq!(s, "\u{11b}");
     let s = string('\u{1d4b6}');
-    assert_eq!(s, "\\u{1d4b6}");
+    assert_eq!(s, "\u{1d4b6}");
+    let s = string('\u{200b}'); // zero width space
+    assert_eq!(s, "\\u{200b}");
+    let s = string('\u{e000}'); // private use 1
+    assert_eq!(s, "\\u{e000}");
+    let s = string('\u{100000}'); // private use 2
+    assert_eq!(s, "\\u{100000}");
 }
 
 #[test]