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/

1 files changed, 3 insertions, 3 deletions

diff --git a/src/libstd/sys/common/wtf8.rs b/src/libstd/sys/common/wtf8.rs
index 2c1a656290f..c0e6ec46b55 100644
--- a/src/libstd/sys/common/wtf8.rs
+++ b/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]