bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

Deprecate str::from_utf8_lossy

Browse source 
Use `String::from_utf8_lossy` instead

[breaking-change]
This commit is contained in:
Adolfo Ochagavía 2014-07-10 18:21:16 +02:00
parent 1900abdd9b
commit c6b82c7566
11 changed files with 258 additions and 256 deletions
Download patch file Download diff file Expand all files Collapse all files

198
src/libcollections/str.rs
View file

@ -402,131 +402,10 @@ macro_rules! utf8_acc_cont_byte(
($ch:expr, $byte:expr) => (($ch << 6) | ($byte & 63u8) as u32) ($ch:expr, $byte:expr) => (($ch << 6) | ($byte & 63u8) as u32)
) )
static TAG_CONT_U8: u8 = 128u8; /// Deprecated. Use `String::from_utf8_lossy`.
#[deprecated = "Replaced by String::from_utf8_lossy"]
/// Converts a vector of bytes to a new utf-8 string.
/// Any invalid utf-8 sequences are replaced with U+FFFD REPLACEMENT CHARACTER.
///
/// # Example
///
/// ```rust
/// let input = b"Hello \xF0\x90\x80World";
/// let output = std::str::from_utf8_lossy(input);
/// assert_eq!(output.as_slice(), "Hello \uFFFDWorld");
/// ```
pub fn from_utf8_lossy<'a>(v: &'a [u8]) -> MaybeOwned<'a> { pub fn from_utf8_lossy<'a>(v: &'a [u8]) -> MaybeOwned<'a> {
if is_utf8(v) { String::from_utf8_lossy(v)
return Slice(unsafe { mem::transmute(v) })
}
static REPLACEMENT: &'static [u8] = b"\xEF\xBF\xBD"; // U+FFFD in UTF-8
let mut i = 0;
let total = v.len();
fn unsafe_get(xs: &[u8], i: uint) -> u8 {
unsafe { *xs.unsafe_ref(i) }
}
fn safe_get(xs: &[u8], i: uint, total: uint) -> u8 {
if i >= total {
0
} else {
unsafe_get(xs, i)
}
}
let mut res = String::with_capacity(total);
if i > 0 {
unsafe {
res.push_bytes(v.slice_to(i))
};
}
// subseqidx is the index of the first byte of the subsequence we're looking at.
// It's used to copy a bunch of contiguous good codepoints at once instead of copying
// them one by one.
let mut subseqidx = 0;
while i < total {
let i_ = i;
let byte = unsafe_get(v, i);
i += 1;
macro_rules! error(() => ({
unsafe {
if subseqidx != i_ {
res.push_bytes(v.slice(subseqidx, i_));
}
subseqidx = i;
res.push_bytes(REPLACEMENT);
}
}))
if byte < 128u8 {
// subseqidx handles this
} else {
let w = utf8_char_width(byte);
match w {
2 => {
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
3 => {
match (byte, safe_get(v, i, total)) {
(0xE0 , 0xA0 .. 0xBF) => (),
(0xE1 .. 0xEC, 0x80 .. 0xBF) => (),
(0xED , 0x80 .. 0x9F) => (),
(0xEE .. 0xEF, 0x80 .. 0xBF) => (),
_ => {
error!();
continue;
}
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
4 => {
match (byte, safe_get(v, i, total)) {
(0xF0 , 0x90 .. 0xBF) => (),
(0xF1 .. 0xF3, 0x80 .. 0xBF) => (),
(0xF4 , 0x80 .. 0x8F) => (),
_ => {
error!();
continue;
}
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
_ => {
error!();
continue;
}
}
}
}
if subseqidx < total {
unsafe {
res.push_bytes(v.slice(subseqidx, total))
};
}
Owned(res.into_string())
} }
/* /*
@ -2052,41 +1931,6 @@ String::from_str("\u1111\u1171\u11b6"));
assert_eq!(from_utf8(xs), None); assert_eq!(from_utf8(xs), None);
} }
#[test]
fn test_str_from_utf8_lossy() {
let xs = b"hello";
assert_eq!(from_utf8_lossy(xs), Slice("hello"));
let xs = "ศไทย中华Việt Nam".as_bytes();
assert_eq!(from_utf8_lossy(xs), Slice("ศไทย中华Việt Nam"));
let xs = b"Hello\xC2 There\xFF Goodbye";
assert_eq!(from_utf8_lossy(xs), Owned(String::from_str("Hello\uFFFD There\uFFFD Goodbye")));
let xs = b"Hello\xC0\x80 There\xE6\x83 Goodbye";
assert_eq!(from_utf8_lossy(xs),
Owned(String::from_str("Hello\uFFFD\uFFFD There\uFFFD Goodbye")));
let xs = b"\xF5foo\xF5\x80bar";
assert_eq!(from_utf8_lossy(xs), Owned(String::from_str("\uFFFDfoo\uFFFD\uFFFDbar")));
let xs = b"\xF1foo\xF1\x80bar\xF1\x80\x80baz";
assert_eq!(from_utf8_lossy(xs), Owned(String::from_str("\uFFFDfoo\uFFFDbar\uFFFDbaz")));
let xs = b"\xF4foo\xF4\x80bar\xF4\xBFbaz";
assert_eq!(from_utf8_lossy(xs),
Owned(String::from_str("\uFFFDfoo\uFFFDbar\uFFFD\uFFFDbaz")));
let xs = b"\xF0\x80\x80\x80foo\xF0\x90\x80\x80bar";
assert_eq!(from_utf8_lossy(xs), Owned(String::from_str("\uFFFD\uFFFD\uFFFD\uFFFD\
foo\U00010000bar")));
// surrogates
let xs = b"\xED\xA0\x80foo\xED\xBF\xBFbar";
assert_eq!(from_utf8_lossy(xs), Owned(String::from_str("\uFFFD\uFFFD\uFFFDfoo\
\uFFFD\uFFFD\uFFFDbar")));
}
#[test] #[test]
fn test_maybe_owned_traits() { fn test_maybe_owned_traits() {
let s = Slice("abcde"); let s = Slice("abcde");
@ -2296,42 +2140,6 @@ mod bench {
}); });
} }
#[bench]
fn from_utf8_lossy_100_ascii(b: &mut Bencher) {
let s = b"Hello there, the quick brown fox jumped over the lazy dog! \
Lorem ipsum dolor sit amet, consectetur. ";
assert_eq!(100, s.len());
b.iter(|| {
let _ = from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_100_multibyte(b: &mut Bencher) {
let s = "𐌀𐌖𐌋𐌄𐌑𐌉ปรدولة الكويتทศไทย中华𐍅𐌿𐌻𐍆𐌹𐌻𐌰".as_bytes();
assert_eq!(100, s.len());
b.iter(|| {
let _ = from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_invalid(b: &mut Bencher) {
let s = b"Hello\xC0\x80 There\xE6\x83 Goodbye";
b.iter(|| {
let _ = from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_100_invalid(b: &mut Bencher) {
let s = Vec::from_elem(100, 0xF5u8);
b.iter(|| {
let _ = from_utf8_lossy(s.as_slice());
});
}
#[bench] #[bench]
fn bench_connect(b: &mut Bencher) { fn bench_connect(b: &mut Bencher) {
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb"; let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";

259
src/libcollections/string.rs
View file

@ -21,7 +21,7 @@ use core::raw::Slice;
use {Collection, Mutable}; use {Collection, Mutable};
use hash; use hash;
use str; use str;
use str::{CharRange, StrAllocating}; use str::{CharRange, StrAllocating, MaybeOwned, Owned, Slice};
use vec::Vec; use vec::Vec;
/// A growable string stored as a UTF-8 encoded buffer. /// A growable string stored as a UTF-8 encoded buffer.
@ -92,6 +92,132 @@ impl String {
} }
} }
/// Converts a vector of bytes to a new utf-8 string.
/// Any invalid utf-8 sequences are replaced with U+FFFD REPLACEMENT CHARACTER.
///
/// # Example
///
/// ```rust
/// let input = b"Hello \xF0\x90\x80World";
/// let output = std::str::from_utf8_lossy(input);
/// assert_eq!(output.as_slice(), "Hello \uFFFDWorld");
/// ```
pub fn from_utf8_lossy<'a>(v: &'a [u8]) -> MaybeOwned<'a> {
if str::is_utf8(v) {
return Slice(unsafe { mem::transmute(v) })
}
static TAG_CONT_U8: u8 = 128u8;
static REPLACEMENT: &'static [u8] = b"\xEF\xBF\xBD"; // U+FFFD in UTF-8
let mut i = 0;
let total = v.len();
fn unsafe_get(xs: &[u8], i: uint) -> u8 {
unsafe { *xs.unsafe_ref(i) }
}
fn safe_get(xs: &[u8], i: uint, total: uint) -> u8 {
if i >= total {
0
} else {
unsafe_get(xs, i)
}
}
let mut res = String::with_capacity(total);
if i > 0 {
unsafe {
res.push_bytes(v.slice_to(i))
};
}
// subseqidx is the index of the first byte of the subsequence we're looking at.
// It's used to copy a bunch of contiguous good codepoints at once instead of copying
// them one by one.
let mut subseqidx = 0;
while i < total {
let i_ = i;
let byte = unsafe_get(v, i);
i += 1;
macro_rules! error(() => ({
unsafe {
if subseqidx != i_ {
res.push_bytes(v.slice(subseqidx, i_));
}
subseqidx = i;
res.push_bytes(REPLACEMENT);
}
}))
if byte < 128u8 {
// subseqidx handles this
} else {
let w = str::utf8_char_width(byte);
match w {
2 => {
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
3 => {
match (byte, safe_get(v, i, total)) {
(0xE0 , 0xA0 .. 0xBF) => (),
(0xE1 .. 0xEC, 0x80 .. 0xBF) => (),
(0xED , 0x80 .. 0x9F) => (),
(0xEE .. 0xEF, 0x80 .. 0xBF) => (),
_ => {
error!();
continue;
}
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
4 => {
match (byte, safe_get(v, i, total)) {
(0xF0 , 0x90 .. 0xBF) => (),
(0xF1 .. 0xF3, 0x80 .. 0xBF) => (),
(0xF4 , 0x80 .. 0x8F) => (),
_ => {
error!();
continue;
}
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
if safe_get(v, i, total) & 192u8 != TAG_CONT_U8 {
error!();
continue;
}
i += 1;
}
_ => {
error!();
continue;
}
}
}
}
if subseqidx < total {
unsafe {
res.push_bytes(v.slice(subseqidx, total))
};
}
Owned(res.into_string())
}
/// Decode a UTF-16 encoded vector `v` into a string, returning `None` /// Decode a UTF-16 encoded vector `v` into a string, returning `None`
/// if `v` contains any invalid data. /// if `v` contains any invalid data.
/// ///
@ -449,7 +575,7 @@ mod tests {
use Mutable; use Mutable;
use str; use str;
use str::{Str, StrSlice}; use str::{Str, StrSlice, MaybeOwned, Owned, Slice};
use super::String; use super::String;
#[test] #[test]
@ -458,6 +584,54 @@ mod tests {
assert_eq!(owned.as_ref().map(|s| s.as_slice()), Some("string")); assert_eq!(owned.as_ref().map(|s| s.as_slice()), Some("string"));
} }
#[test]
fn test_from_utf8() {
let xs = Vec::from_slice(b"hello");
assert_eq!(String::from_utf8(xs), Ok("hello".to_string()));
let xs = Vec::from_slice("ศไทย中华Việt Nam".as_bytes());
assert_eq!(String::from_utf8(xs), Ok("ศไทย中华Việt Nam".to_string()));
let xs = Vec::from_slice(b"hello\xFF");
assert_eq!(String::from_utf8(xs),
Err(Vec::from_slice(b"hello\xFF")));
}
#[test]
fn test_from_utf8_lossy() {
let xs = b"hello";
assert_eq!(String::from_utf8_lossy(xs), Slice("hello"));
let xs = "ศไทย中华Việt Nam".as_bytes();
assert_eq!(String::from_utf8_lossy(xs), Slice("ศไทย中华Việt Nam"));
let xs = b"Hello\xC2 There\xFF Goodbye";
assert_eq!(String::from_utf8_lossy(xs), Owned(String::from_str("Hello\uFFFD There\uFFFD Goodbye")));
let xs = b"Hello\xC0\x80 There\xE6\x83 Goodbye";
assert_eq!(String::from_utf8_lossy(xs),
Owned(String::from_str("Hello\uFFFD\uFFFD There\uFFFD Goodbye")));
let xs = b"\xF5foo\xF5\x80bar";
assert_eq!(String::from_utf8_lossy(xs), Owned(String::from_str("\uFFFDfoo\uFFFD\uFFFDbar")));
let xs = b"\xF1foo\xF1\x80bar\xF1\x80\x80baz";
assert_eq!(String::from_utf8_lossy(xs), Owned(String::from_str("\uFFFDfoo\uFFFDbar\uFFFDbaz")));
let xs = b"\xF4foo\xF4\x80bar\xF4\xBFbaz";
assert_eq!(String::from_utf8_lossy(xs),
Owned(String::from_str("\uFFFDfoo\uFFFDbar\uFFFD\uFFFDbaz")));
let xs = b"\xF0\x80\x80\x80foo\xF0\x90\x80\x80bar";
assert_eq!(String::from_utf8_lossy(xs), Owned(String::from_str("\uFFFD\uFFFD\uFFFD\uFFFD\
foo\U00010000bar")));
// surrogates
let xs = b"\xED\xA0\x80foo\xED\xBF\xBFbar";
assert_eq!(String::from_utf8_lossy(xs), Owned(String::from_str("\uFFFD\uFFFD\uFFFDfoo\
\uFFFD\uFFFD\uFFFDbar")));
}
#[test] #[test]
fn test_from_utf16() { fn test_from_utf16() {
let pairs = let pairs =
@ -547,35 +721,6 @@ mod tests {
String::from_str("\uFFFD𐒋\uFFFD")); String::from_str("\uFFFD𐒋\uFFFD"));
} }
#[bench]
fn bench_with_capacity(b: &mut Bencher) {
b.iter(|| {
String::with_capacity(100)
});
}
#[bench]
fn bench_push_str(b: &mut Bencher) {
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
b.iter(|| {
let mut r = String::new();
r.push_str(s);
});
}
#[test]
fn test_str_from_utf8() {
let xs = Vec::from_slice(b"hello");
assert_eq!(String::from_utf8(xs), Ok("hello".to_string()));
let xs = Vec::from_slice("ศไทย中华Việt Nam".as_bytes());
assert_eq!(String::from_utf8(xs), Ok("ศไทย中华Việt Nam".to_string()));
let xs = Vec::from_slice(b"hello\xFF");
assert_eq!(String::from_utf8(xs),
Err(Vec::from_slice(b"hello\xFF")));
}
#[test] #[test]
fn test_push_bytes() { fn test_push_bytes() {
let mut s = String::from_str("ABC"); let mut s = String::from_str("ABC");
@ -677,4 +822,56 @@ mod tests {
assert_eq!(b.len(), 7); assert_eq!(b.len(), 7);
assert_eq!(b.as_slice(), "1234522"); assert_eq!(b.as_slice(), "1234522");
} }
#[bench]
fn bench_with_capacity(b: &mut Bencher) {
b.iter(|| {
String::with_capacity(100)
});
}
#[bench]
fn bench_push_str(b: &mut Bencher) {
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
b.iter(|| {
let mut r = String::new();
r.push_str(s);
});
}
#[bench]
fn from_utf8_lossy_100_ascii(b: &mut Bencher) {
let s = b"Hello there, the quick brown fox jumped over the lazy dog! \
Lorem ipsum dolor sit amet, consectetur. ";
assert_eq!(100, s.len());
b.iter(|| {
let _ = String::from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_100_multibyte(b: &mut Bencher) {
let s = "𐌀𐌖𐌋𐌄𐌑𐌉ปรدولة الكويتทศไทย中华𐍅𐌿𐌻𐍆𐌹𐌻𐌰".as_bytes();
assert_eq!(100, s.len());
b.iter(|| {
let _ = String::from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_invalid(b: &mut Bencher) {
let s = b"Hello\xC0\x80 There\xE6\x83 Goodbye";
b.iter(|| {
let _ = String::from_utf8_lossy(s);
});
}
#[bench]
fn from_utf8_lossy_100_invalid(b: &mut Bencher) {
let s = Vec::from_elem(100, 0xF5u8);
b.iter(|| {
let _ = String::from_utf8_lossy(s.as_slice());
});
}
} }

2
src/librustc/back/link.rs
View file

@ -61,7 +61,7 @@ pub fn llvm_err(sess: &Session, msg: String) -> ! {
sess.fatal(msg.as_slice()); sess.fatal(msg.as_slice());
} else { } else {
let err = CString::new(cstr, true); let err = CString::new(cstr, true);
let err = str::from_utf8_lossy(err.as_bytes()); let err = String::from_utf8_lossy(err.as_bytes());
sess.fatal(format!("{}: {}", sess.fatal(format!("{}: {}",
msg.as_slice(), msg.as_slice(),
err.as_slice()).as_slice()); err.as_slice()).as_slice());

2
src/librustdoc/html/highlight.rs
View file

@ -37,7 +37,7 @@ pub fn highlight(src: &str, class: Option<&str>, id: Option<&str>) -> String {
class, class,
id, id,
&mut out).unwrap(); &mut out).unwrap();
str::from_utf8_lossy(out.unwrap().as_slice()).to_string() String::from_utf8_lossy(out.unwrap().as_slice()).into_string()
} }
/// Exhausts the `lexer` writing the output into `out`. /// Exhausts the `lexer` writing the output into `out`.

11
src/libstd/io/process.rs
View file

@ -313,7 +313,6 @@ impl Command {
/// ///
/// ``` /// ```
/// use std::io::Command; /// use std::io::Command;
/// use std::str;
/// ///
/// let output = match Command::new("cat").arg("foot.txt").output() { /// let output = match Command::new("cat").arg("foot.txt").output() {
/// Ok(output) => output, /// Ok(output) => output,
@ -321,8 +320,8 @@ impl Command {
/// }; /// };
/// ///
/// println!("status: {}", output.status); /// println!("status: {}", output.status);
/// println!("stdout: {}", str::from_utf8_lossy(output.output.as_slice())); /// println!("stdout: {}", String::from_utf8_lossy(output.output.as_slice()));
/// println!("stderr: {}", str::from_utf8_lossy(output.error.as_slice())); /// println!("stderr: {}", String::from_utf8_lossy(output.error.as_slice()));
/// ``` /// ```
pub fn output(&self) -> IoResult<ProcessOutput> { pub fn output(&self) -> IoResult<ProcessOutput> {
self.spawn().and_then(|p| p.wait_with_output()) self.spawn().and_then(|p| p.wait_with_output())
@ -353,9 +352,9 @@ impl fmt::Show for Command {
/// non-utf8 data is lossily converted using the utf8 replacement /// non-utf8 data is lossily converted using the utf8 replacement
/// character. /// character.
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
try!(write!(f, "{}", str::from_utf8_lossy(self.program.as_bytes_no_nul()))); try!(write!(f, "{}", String::from_utf8_lossy(self.program.as_bytes_no_nul())));
for arg in self.args.iter() { for arg in self.args.iter() {
try!(write!(f, " '{}'", str::from_utf8_lossy(arg.as_bytes_no_nul()))); try!(write!(f, " '{}'", String::from_utf8_lossy(arg.as_bytes_no_nul())));
} }
Ok(()) Ok(())
} }
@ -903,7 +902,7 @@ mod tests {
let new_env = vec![("RUN_TEST_NEW_ENV", "123")]; let new_env = vec![("RUN_TEST_NEW_ENV", "123")];
let prog = env_cmd().env_set_all(new_env.as_slice()).spawn().unwrap(); let prog = env_cmd().env_set_all(new_env.as_slice()).spawn().unwrap();
let result = prog.wait_with_output().unwrap(); let result = prog.wait_with_output().unwrap();
let output = str::from_utf8_lossy(result.output.as_slice()).into_string(); let output = String::from_utf8_lossy(result.output.as_slice()).into_string();
assert!(output.as_slice().contains("RUN_TEST_NEW_ENV=123"), assert!(output.as_slice().contains("RUN_TEST_NEW_ENV=123"),
"didn't find RUN_TEST_NEW_ENV inside of:\n\n{}", output); "didn't find RUN_TEST_NEW_ENV inside of:\n\n{}", output);

14
src/libstd/os.rs
View file

@ -208,7 +208,7 @@ fn with_env_lock<T>(f: || -> T) -> T {
/// Returns a vector of (variable, value) pairs, for all the environment /// Returns a vector of (variable, value) pairs, for all the environment
/// variables of the current process. /// variables of the current process.
/// ///
/// Invalid UTF-8 bytes are replaced with \uFFFD. See `str::from_utf8_lossy()` /// Invalid UTF-8 bytes are replaced with \uFFFD. See `String::from_utf8_lossy()`
/// for details. /// for details.
/// ///
/// # Example /// # Example
@ -223,8 +223,8 @@ fn with_env_lock<T>(f: || -> T) -> T {
/// ``` /// ```
pub fn env() -> Vec<(String,String)> { pub fn env() -> Vec<(String,String)> {
env_as_bytes().move_iter().map(|(k,v)| { env_as_bytes().move_iter().map(|(k,v)| {
let k = String::from_str(str::from_utf8_lossy(k.as_slice()).as_slice()); let k = String::from_utf8_lossy(k.as_slice()).into_string();
let v = String::from_str(str::from_utf8_lossy(v.as_slice()).as_slice()); let v = String::from_utf8_lossy(v.as_slice()).into_string();
(k,v) (k,v)
}).collect() }).collect()
} }
@ -316,7 +316,7 @@ pub fn env_as_bytes() -> Vec<(Vec<u8>,Vec<u8>)> {
/// None if the variable isn't set. /// None if the variable isn't set.
/// ///
/// Any invalid UTF-8 bytes in the value are replaced by \uFFFD. See /// Any invalid UTF-8 bytes in the value are replaced by \uFFFD. See
/// `str::from_utf8_lossy()` for details. /// `String::from_utf8_lossy()` for details.
/// ///
/// # Failure /// # Failure
/// ///
@ -334,7 +334,7 @@ pub fn env_as_bytes() -> Vec<(Vec<u8>,Vec<u8>)> {
/// } /// }
/// ``` /// ```
pub fn getenv(n: &str) -> Option<String> { pub fn getenv(n: &str) -> Option<String> {
getenv_as_bytes(n).map(|v| String::from_str(str::from_utf8_lossy(v.as_slice()).as_slice())) getenv_as_bytes(n).map(|v| String::from_utf8_lossy(v.as_slice()).into_string())
} }
#[cfg(unix)] #[cfg(unix)]
@ -1186,7 +1186,7 @@ fn real_args_as_bytes() -> Vec<Vec<u8>> {
fn real_args() -> Vec<String> { fn real_args() -> Vec<String> {
real_args_as_bytes().move_iter() real_args_as_bytes().move_iter()
.map(|v| { .map(|v| {
str::from_utf8_lossy(v.as_slice()).into_string() String::from_utf8_lossy(v.as_slice()).into_string()
}).collect() }).collect()
} }
@ -1244,7 +1244,7 @@ extern "system" {
/// via the command line). /// via the command line).
/// ///
/// The arguments are interpreted as utf-8, with invalid bytes replaced with \uFFFD. /// The arguments are interpreted as utf-8, with invalid bytes replaced with \uFFFD.
/// See `str::from_utf8_lossy` for details. /// See `String::from_utf8_lossy` for details.
/// # Example /// # Example
/// ///
/// ```rust /// ```rust

4
src/libstd/path/mod.rs
View file

@ -72,7 +72,7 @@ use fmt;
use iter::Iterator; use iter::Iterator;
use option::{Option, None, Some}; use option::{Option, None, Some};
use str; use str;
use str::{MaybeOwned, Str, StrSlice, from_utf8_lossy}; use str::{MaybeOwned, Str, StrSlice};
use string::String; use string::String;
use slice::Vector; use slice::Vector;
use slice::{ImmutableEqVector, ImmutableVector}; use slice::{ImmutableEqVector, ImmutableVector};
@ -483,7 +483,7 @@ impl<'a, P: GenericPath> Display<'a, P> {
/// unicode replacement char. This involves allocation. /// unicode replacement char. This involves allocation.
#[inline] #[inline]
pub fn as_maybe_owned(&self) -> MaybeOwned<'a> { pub fn as_maybe_owned(&self) -> MaybeOwned<'a> {
from_utf8_lossy(if self.filename { String::from_utf8_lossy(if self.filename {
match self.path.filename() { match self.path.filename() {
None => &[], None => &[],
Some(v) => v Some(v) => v

5
src/libtest/lib.rs
View file

@ -60,7 +60,6 @@ use std::io::stdio::StdWriter;
use std::io::{File, ChanReader, ChanWriter}; use std::io::{File, ChanReader, ChanWriter};
use std::io; use std::io;
use std::os; use std::os;
use std::str;
use std::string::String; use std::string::String;
use std::task::TaskBuilder; use std::task::TaskBuilder;
@ -636,7 +635,7 @@ impl<T: Writer> ConsoleTestState<T> {
if stdout.len() > 0 { if stdout.len() > 0 {
fail_out.push_str(format!("---- {} stdout ----\n\t", fail_out.push_str(format!("---- {} stdout ----\n\t",
f.name.as_slice()).as_slice()); f.name.as_slice()).as_slice());
let output = str::from_utf8_lossy(stdout.as_slice()); let output = String::from_utf8_lossy(stdout.as_slice());
fail_out.push_str(output.as_slice() fail_out.push_str(output.as_slice()
.replace("\n", "\n\t") .replace("\n", "\n\t")
.as_slice()); .as_slice());
@ -873,7 +872,7 @@ fn should_sort_failures_before_printing_them() {
st.write_failures().unwrap(); st.write_failures().unwrap();
let s = match st.out { let s = match st.out {
Raw(ref m) => str::from_utf8_lossy(m.get_ref()), Raw(ref m) => String::from_utf8_lossy(m.get_ref()),
Pretty(_) => unreachable!() Pretty(_) => unreachable!()
}; };

4
src/test/run-make/unicode-input/multiple_files.rs
View file

@ -8,7 +8,7 @@
// option. This file may not be copied, modified, or distributed // option. This file may not be copied, modified, or distributed
// except according to those terms. // except according to those terms.
use std::{char, os, str}; use std::{char, os};
use std::io::{File, Command}; use std::io::{File, Command};
use std::rand::{task_rng, Rng}; use std::rand::{task_rng, Rng};
@ -61,7 +61,7 @@ fn main() {
main_file.as_str() main_file.as_str()
.unwrap()).as_slice()) .unwrap()).as_slice())
.output().unwrap(); .output().unwrap();
let err = str::from_utf8_lossy(result.error.as_slice()); let err = String::from_utf8_lossy(result.error.as_slice());
// positive test so that this test will be updated when the // positive test so that this test will be updated when the
// compiler changes. // compiler changes.

4
src/test/run-make/unicode-input/span_length.rs
View file

@ -8,7 +8,7 @@
// option. This file may not be copied, modified, or distributed // option. This file may not be copied, modified, or distributed
// except according to those terms. // except according to those terms.
use std::{char, os, str}; use std::{char, os};
use std::io::{File, Command}; use std::io::{File, Command};
use std::rand::{task_rng, Rng}; use std::rand::{task_rng, Rng};
@ -57,7 +57,7 @@ fn main() {
.unwrap()).as_slice()) .unwrap()).as_slice())
.output().unwrap(); .output().unwrap();
let err = str::from_utf8_lossy(result.error.as_slice()); let err = String::from_utf8_lossy(result.error.as_slice());
// the span should end the line (e.g no extra ~'s) // the span should end the line (e.g no extra ~'s)
let expected_span = format!("^{}\n", "~".repeat(n - 1)); let expected_span = format!("^{}\n", "~".repeat(n - 1));

5
src/test/run-pass/out-of-stack.rs
View file

@ -12,7 +12,6 @@
use std::io::process::Command; use std::io::process::Command;
use std::os; use std::os;
use std::str;
// lifted from the test module // lifted from the test module
// Inlining to avoid llvm turning the recursive functions into tail calls, // Inlining to avoid llvm turning the recursive functions into tail calls,
@ -42,12 +41,12 @@ fn main() {
} else { } else {
let silent = Command::new(args[0].as_slice()).arg("silent").output().unwrap(); let silent = Command::new(args[0].as_slice()).arg("silent").output().unwrap();
assert!(!silent.status.success()); assert!(!silent.status.success());
let error = str::from_utf8_lossy(silent.error.as_slice()); let error = String::from_utf8_lossy(silent.error.as_slice());
assert!(error.as_slice().contains("has overflowed its stack")); assert!(error.as_slice().contains("has overflowed its stack"));
let loud = Command::new(args[0].as_slice()).arg("loud").output().unwrap(); let loud = Command::new(args[0].as_slice()).arg("loud").output().unwrap();
assert!(!loud.status.success()); assert!(!loud.status.success());
let error = str::from_utf8_lossy(silent.error.as_slice()); let error = String::from_utf8_lossy(silent.error.as_slice());
assert!(error.as_slice().contains("has overflowed its stack")); assert!(error.as_slice().contains("has overflowed its stack"));
} }
} }