Auto merge of #46798 - Diggsey:debug-osstr, r=dtolnay

Add lossless debug implementation for unix OsStrs

Fixes #22766

Invalid utf8 byte sequences are replaced with `\xFF` style escape codes, while valid utf8 goes through the normal `Debug` implementation.

This is necessarily different from the windows Debug implementation, which uses `\u{xxxx}` style escape sequences for unpaired surrogates, but both implementations are consistent in that they are both lossless, and display invalid sequences in the way most similar to existing language syntax.

r? @dtolnay

Author: bors

Diff for: src/libstd/sys/redox/os_str.rs

@@ -18,6 +18,7 @@ use mem;
 use rc::Rc;
 use sync::Arc;
 use sys_common::{AsInner, IntoInner};
+use sys_common::bytestring::debug_fmt_bytestring;
 use std_unicode::lossy::Utf8Lossy;
 
 #[derive(Clone, Hash)]
@@ -31,7 +32,7 @@ pub struct Slice {
 
 impl fmt::Debug for Slice {
     fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
-        fmt::Debug::fmt(&Utf8Lossy::from_bytes(&self.inner), formatter)
+        debug_fmt_bytestring(&self.inner, formatter)
     }
 }
 

Diff for: src/libstd/sys/unix/os_str.rs

@@ -18,6 +18,7 @@ use mem;
 use rc::Rc;
 use sync::Arc;
 use sys_common::{AsInner, IntoInner};
+use sys_common::bytestring::debug_fmt_bytestring;
 use std_unicode::lossy::Utf8Lossy;
 
 #[derive(Clone, Hash)]
@@ -31,7 +32,7 @@ pub struct Slice {
 
 impl fmt::Debug for Slice {
     fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
-        fmt::Debug::fmt(&Utf8Lossy::from_bytes(&self.inner), formatter)
+        debug_fmt_bytestring(&self.inner, formatter)
     }
 }
 

Diff for: src/libstd/sys/wasm/os_str.rs

@@ -18,6 +18,7 @@ use mem;
 use rc::Rc;
 use sync::Arc;
 use sys_common::{AsInner, IntoInner};
+use sys_common::bytestring::debug_fmt_bytestring;
 use std_unicode::lossy::Utf8Lossy;
 
 #[derive(Clone, Hash)]
@@ -31,7 +32,7 @@ pub struct Slice {
 
 impl fmt::Debug for Slice {
     fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
-        fmt::Debug::fmt(&Utf8Lossy::from_bytes(&self.inner), formatter)
+        debug_fmt_bytestring(&self.inner, formatter)
     }
 }
 

Diff for: src/libstd/sys_common/bytestring.rs

@@ -0,0 +1,56 @@
+// Copyright 2014 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+#![allow(dead_code)]
+
+use fmt::{Formatter, Result, Write};
+use std_unicode::lossy::{Utf8Lossy, Utf8LossyChunk};
+
+pub fn debug_fmt_bytestring(slice: &[u8], f: &mut Formatter) -> Result {
+    // Writes out a valid unicode string with the correct escape sequences
+    fn write_str_escaped(f: &mut Formatter, s: &str) -> Result {
+        for c in s.chars().flat_map(|c| c.escape_debug()) {
+            f.write_char(c)?
+        }
+        Ok(())
+    }
+
+    f.write_str("\"")?;
+    for Utf8LossyChunk { valid, broken } in Utf8Lossy::from_bytes(slice).chunks() {
+        write_str_escaped(f, valid)?;
+        for b in broken {
+            write!(f, "\\x{:02X}", b)?;
+        }
+    }
+    f.write_str("\"")
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use fmt::{Formatter, Result, Debug};
+
+    #[test]
+    fn smoke() {
+        struct Helper<'a>(&'a [u8]);
+
+        impl<'a> Debug for Helper<'a> {
+            fn fmt(&self, f: &mut Formatter) -> Result {
+                debug_fmt_bytestring(self.0, f)
+            }
+        }
+
+        let input =      b"\xF0hello,\tworld";
+        let expected = r#""\xF0hello,\tworld""#;
+        let output = format!("{:?}", Helper(input));
+
+        assert!(output == expected);
+    }
+}

Diff for: src/libstd/sys_common/mod.rs

@@ -43,6 +43,7 @@ pub mod thread_info;
 pub mod thread_local;
 pub mod util;
 pub mod wtf8;
+pub mod bytestring;
 
 cfg_if! {
     if #[cfg(any(target_os = "redox", target_os = "l4re"))] {