about summary refs log tree commit diff
path: root/src/librustc_unicode
diff options
context:
space:
mode:
authorbors <bors@rust-lang.org>2016-07-28 11:20:33 -0700
committerGitHub <noreply@github.com>2016-07-28 11:20:33 -0700
commitd1df3fecdf8dc959fbd8901603a16e5bc0bfa21d (patch)
tree52351065a422a440701808df99b4f476058eb2fb /src/librustc_unicode
parent748ecb1235d1cfa1aeaa0e5424c454837089f6cc (diff)
parent3d09b4a0d58200da84fe19cd3b0003d61e5b1791 (diff)
downloadrust-d1df3fecdf8dc959fbd8901603a16e5bc0bfa21d.tar.gz
rust-d1df3fecdf8dc959fbd8901603a16e5bc0bfa21d.zip
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/
Diffstat (limited to 'src/librustc_unicode')
-rw-r--r--src/librustc_unicode/char.rs37
-rw-r--r--src/librustc_unicode/lib.rs1
2 files changed, 37 insertions, 1 deletions
diff --git a/src/librustc_unicode/char.rs b/src/librustc_unicode/char.rs
index 1ea0f8d70a8..81856cb87c7 100644
--- a/src/librustc_unicode/char.rs
+++ b/src/librustc_unicode/char.rs
@@ -36,7 +36,7 @@ use tables::{conversions, derived_property, general_category, property};
 #[stable(feature = "rust1", since = "1.0.0")]
 pub use core::char::{MAX, from_digit, from_u32, from_u32_unchecked};
 #[stable(feature = "rust1", since = "1.0.0")]
-pub use core::char::{EncodeUtf16, EncodeUtf8, EscapeDefault, EscapeUnicode};
+pub use core::char::{EncodeUtf16, EncodeUtf8, EscapeDebug, EscapeDefault, EscapeUnicode};
 
 // unstable reexports
 #[unstable(feature = "decode_utf8", issue = "33906")]
@@ -269,6 +269,41 @@ impl char {
 
     /// Returns an iterator that yields the literal escape code of a `char`.
     ///
+    /// This will escape the characters similar to the `Debug` implementations
+    /// of `str` or `char`.
+    ///
+    /// # Examples
+    ///
+    /// Basic usage:
+    ///
+    /// ```
+    /// for i in '\n'.escape_default() {
+    ///     println!("{}", i);
+    /// }
+    /// ```
+    ///
+    /// This prints:
+    ///
+    /// ```text
+    /// \
+    /// n
+    /// ```
+    ///
+    /// Collecting into a `String`:
+    ///
+    /// ```
+    /// let quote: String = '\n'.escape_default().collect();
+    ///
+    /// assert_eq!(quote, "\\n");
+    /// ```
+    #[unstable(feature = "char_escape_debug", issue = "35068")]
+    #[inline]
+    pub fn escape_debug(self) -> EscapeDebug {
+        C::escape_debug(self)
+    }
+
+    /// Returns an iterator that yields the literal escape code of a `char`.
+    ///
     /// The default is chosen with a bias toward producing literals that are
     /// legal in a variety of languages, including C++11 and similar C-family
     /// languages. The exact rules are:
diff --git a/src/librustc_unicode/lib.rs b/src/librustc_unicode/lib.rs
index f91a754ab57..3ae905eba27 100644
--- a/src/librustc_unicode/lib.rs
+++ b/src/librustc_unicode/lib.rs
@@ -32,6 +32,7 @@
 #![cfg_attr(not(stage0), deny(warnings))]
 #![no_std]
 
+#![feature(char_escape_debug)]
 #![feature(core_char_ext)]
 #![feature(decode_utf8)]
 #![feature(lang_items)]