Add Path and OsString APIs

src/ascii.rs

@@ -0,0 +1,554 @@
+// Copyright 2013-2014 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.
+
+//! Operations on ASCII strings and characters.
+
+use core::mem;
+use core::ops::Range;
+use collections::{String, Vec};
+
+/// Extension methods for ASCII-subset only operations on string slices.
+///
+/// Be aware that operations on seemingly non-ASCII characters can sometimes
+/// have unexpected results. Consider this example:
+///
+/// ```
+/// use std::ascii::AsciiExt;
+///
+/// assert_eq!("café".to_ascii_uppercase(), "CAFÉ");
+/// assert_eq!("café".to_ascii_uppercase(), "CAFé");
+/// ```
+///
+/// In the first example, the lowercased string is represented `"cafe\u{301}"`
+/// (the last character is an acute accent [combining character]). Unlike the
+/// other characters in the string, the combining character will not get mapped
+/// to an uppercase variant, resulting in `"CAFE\u{301}"`. In the second
+/// example, the lowercased string is represented `"caf\u{e9}"` (the last
+/// character is a single Unicode character representing an 'e' with an acute
+/// accent). Since the last character is defined outside the scope of ASCII,
+/// it will not get mapped to an uppercase variant, resulting in `"CAF\u{e9}"`.
+///
+/// [combining character]: https://en.wikipedia.org/wiki/Combining_character
+pub trait AsciiExt {
+    /// Container type for copied ASCII characters.
+    type Owned;
+
+    /// Checks if the value is within the ASCII range.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let ascii = 'a';
+    /// let utf8 = '❤';
+    ///
+    /// assert!(ascii.is_ascii());
+    /// assert!(!utf8.is_ascii());
+    /// ```
+    fn is_ascii(&self) -> bool;
+
+    /// Makes a copy of the string in ASCII upper case.
+    ///
+    /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
+    /// but non-ASCII letters are unchanged.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let ascii = 'a';
+    /// let utf8 = '❤';
+    ///
+    /// assert_eq!('A', ascii.to_ascii_uppercase());
+    /// assert_eq!('❤', utf8.to_ascii_uppercase());
+    /// ```
+    fn to_ascii_uppercase(&self) -> Self::Owned;
+
+    /// Makes a copy of the string in ASCII lower case.
+    ///
+    /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
+    /// but non-ASCII letters are unchanged.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let ascii = 'A';
+    /// let utf8 = '❤';
+    ///
+    /// assert_eq!('a', ascii.to_ascii_lowercase());
+    /// assert_eq!('❤', utf8.to_ascii_lowercase());
+    /// ```
+    fn to_ascii_lowercase(&self) -> Self::Owned;
+
+    /// Checks that two strings are an ASCII case-insensitive match.
+    ///
+    /// Same as `to_ascii_lowercase(a) == to_ascii_lowercase(b)`,
+    /// but without allocating and copying temporary strings.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let ascii1 = 'A';
+    /// let ascii2 = 'a';
+    /// let ascii3 = 'A';
+    /// let ascii4 = 'z';
+    ///
+    /// assert!(ascii1.eq_ignore_ascii_case(&ascii2));
+    /// assert!(ascii1.eq_ignore_ascii_case(&ascii3));
+    /// assert!(!ascii1.eq_ignore_ascii_case(&ascii4));
+    /// ```
+    fn eq_ignore_ascii_case(&self, other: &Self) -> bool;
+
+    /// Converts this type to its ASCII upper case equivalent in-place.
+    ///
+    /// See `to_ascii_uppercase` for more information.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let mut ascii = 'a';
+    ///
+    /// ascii.make_ascii_uppercase();
+    ///
+    /// assert_eq!('A', ascii);
+    /// ```
+    fn make_ascii_uppercase(&mut self);
+
+    /// Converts this type to its ASCII lower case equivalent in-place.
+    ///
+    /// See `to_ascii_lowercase` for more information.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ascii::AsciiExt;
+    ///
+    /// let mut ascii = 'A';
+    ///
+    /// ascii.make_ascii_lowercase();
+    ///
+    /// assert_eq!('a', ascii);
+    /// ```
+    fn make_ascii_lowercase(&mut self);
+}
+
+impl AsciiExt for str {
+    type Owned = String;
+
+    #[inline]
+    fn is_ascii(&self) -> bool {
+        self.bytes().all(|b| b.is_ascii())
+    }
+
+    #[inline]
+    fn to_ascii_uppercase(&self) -> String {
+        let mut bytes = self.as_bytes().to_vec();
+        bytes.make_ascii_uppercase();
+        // make_ascii_uppercase() preserves the UTF-8 invariant.
+        unsafe { String::from_utf8_unchecked(bytes) }
+    }
+
+    #[inline]
+    fn to_ascii_lowercase(&self) -> String {
+        let mut bytes = self.as_bytes().to_vec();
+        bytes.make_ascii_lowercase();
+        // make_ascii_uppercase() preserves the UTF-8 invariant.
+        unsafe { String::from_utf8_unchecked(bytes) }
+    }
+
+    #[inline]
+    fn eq_ignore_ascii_case(&self, other: &str) -> bool {
+        self.as_bytes().eq_ignore_ascii_case(other.as_bytes())
+    }
+
+    fn make_ascii_uppercase(&mut self) {
+        let me: &mut [u8] = unsafe { mem::transmute(self) };
+        me.make_ascii_uppercase()
+    }
+
+    fn make_ascii_lowercase(&mut self) {
+        let me: &mut [u8] = unsafe { mem::transmute(self) };
+        me.make_ascii_lowercase()
+    }
+}
+
+impl AsciiExt for [u8] {
+    type Owned = Vec<u8>;
+    #[inline]
+    fn is_ascii(&self) -> bool {
+        self.iter().all(|b| b.is_ascii())
+    }
+
+    #[inline]
+    fn to_ascii_uppercase(&self) -> Vec<u8> {
+        let mut me = self.to_vec();
+        me.make_ascii_uppercase();
+        return me
+    }
+
+    #[inline]
+    fn to_ascii_lowercase(&self) -> Vec<u8> {
+        let mut me = self.to_vec();
+        me.make_ascii_lowercase();
+        return me
+    }
+
+    #[inline]
+    fn eq_ignore_ascii_case(&self, other: &[u8]) -> bool {
+        self.len() == other.len() &&
+        self.iter().zip(other).all(|(a, b)| {
+            a.eq_ignore_ascii_case(b)
+        })
+    }
+
+    fn make_ascii_uppercase(&mut self) {
+        for byte in self {
+            byte.make_ascii_uppercase();
+        }
+    }
+
+    fn make_ascii_lowercase(&mut self) {
+        for byte in self {
+            byte.make_ascii_lowercase();
+        }
+    }
+}
+
+impl AsciiExt for u8 {
+    type Owned = u8;
+    #[inline]
+    fn is_ascii(&self) -> bool { *self & 128 == 0 }
+    #[inline]
+    fn to_ascii_uppercase(&self) -> u8 { ASCII_UPPERCASE_MAP[*self as usize] }
+    #[inline]
+    fn to_ascii_lowercase(&self) -> u8 { ASCII_LOWERCASE_MAP[*self as usize] }
+    #[inline]
+    fn eq_ignore_ascii_case(&self, other: &u8) -> bool {
+        self.to_ascii_lowercase() == other.to_ascii_lowercase()
+    }
+    #[inline]
+    fn make_ascii_uppercase(&mut self) { *self = self.to_ascii_uppercase(); }
+    #[inline]
+    fn make_ascii_lowercase(&mut self) { *self = self.to_ascii_lowercase(); }
+}
+
+impl AsciiExt for char {
+    type Owned = char;
+    #[inline]
+    fn is_ascii(&self) -> bool {
+        *self as u32 <= 0x7F
+    }
+
+    #[inline]
+    fn to_ascii_uppercase(&self) -> char {
+        if self.is_ascii() {
+            (*self as u8).to_ascii_uppercase() as char
+        } else {
+            *self
+        }
+    }
+
+    #[inline]
+    fn to_ascii_lowercase(&self) -> char {
+        if self.is_ascii() {
+            (*self as u8).to_ascii_lowercase() as char
+        } else {
+            *self
+        }
+    }
+
+    #[inline]
+    fn eq_ignore_ascii_case(&self, other: &char) -> bool {
+        self.to_ascii_lowercase() == other.to_ascii_lowercase()
+    }
+
+    #[inline]
+    fn make_ascii_uppercase(&mut self) { *self = self.to_ascii_uppercase(); }
+    #[inline]
+    fn make_ascii_lowercase(&mut self) { *self = self.to_ascii_lowercase(); }
+}
+
+/// An iterator over the escaped version of a byte, constructed via
+/// `std::ascii::escape_default`.
+pub struct EscapeDefault {
+    range: Range<usize>,
+    data: [u8; 4],
+}
+
+/// Returns an iterator that produces an escaped version of a `u8`.
+///
+/// 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:
+///
+/// - Tab, CR and LF are escaped as '\t', '\r' and '\n' respectively.
+/// - Single-quote, double-quote and backslash chars are backslash-escaped.
+/// - Any other chars in the range [0x20,0x7e] are not escaped.
+/// - Any other chars are given hex escapes of the form '\xNN'.
+/// - Unicode escapes are never generated by this function.
+///
+/// # Examples
+///
+/// ```
+/// use std::ascii;
+///
+/// let escaped = ascii::escape_default(b'0').next().unwrap();
+/// assert_eq!(b'0', escaped);
+///
+/// let mut escaped = ascii::escape_default(b'\t');
+///
+/// assert_eq!(b'\\', escaped.next().unwrap());
+/// assert_eq!(b't', escaped.next().unwrap());
+/// ```
+pub fn escape_default(c: u8) -> EscapeDefault {
+    let (data, len) = match c {
+        b'\t' => ([b'\\', b't', 0, 0], 2),
+        b'\r' => ([b'\\', b'r', 0, 0], 2),
+        b'\n' => ([b'\\', b'n', 0, 0], 2),
+        b'\\' => ([b'\\', b'\\', 0, 0], 2),
+        b'\'' => ([b'\\', b'\'', 0, 0], 2),
+        b'"' => ([b'\\', b'"', 0, 0], 2),
+        b'\x20' ... b'\x7e' => ([c, 0, 0, 0], 1),
+        _ => ([b'\\', b'x', hexify(c >> 4), hexify(c & 0xf)], 4),
+    };
+
+    return EscapeDefault { range: (0.. len), data: data };
+
+    fn hexify(b: u8) -> u8 {
+        match b {
+            0 ... 9 => b'0' + b,
+            _ => b'a' + b - 10,
+        }
+    }
+}
+
+impl Iterator for EscapeDefault {
+    type Item = u8;
+    fn next(&mut self) -> Option<u8> { self.range.next().map(|i| self.data[i]) }
+    fn size_hint(&self) -> (usize, Option<usize>) { self.range.size_hint() }
+}
+impl DoubleEndedIterator for EscapeDefault {
+    fn next_back(&mut self) -> Option<u8> {
+        self.range.next_back().map(|i| self.data[i])
+    }
+}
+impl ExactSizeIterator for EscapeDefault {}
+
+static ASCII_LOWERCASE_MAP: [u8; 256] = [
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+    0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+    0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    b' ', b'!', b'"', b'#', b'$', b'%', b'&', b'\'',
+    b'(', b')', b'*', b'+', b',', b'-', b'.', b'/',
+    b'0', b'1', b'2', b'3', b'4', b'5', b'6', b'7',
+    b'8', b'9', b':', b';', b'<', b'=', b'>', b'?',
+    b'@',
+
+          b'a', b'b', b'c', b'd', b'e', b'f', b'g',
+    b'h', b'i', b'j', b'k', b'l', b'm', b'n', b'o',
+    b'p', b'q', b'r', b's', b't', b'u', b'v', b'w',
+    b'x', b'y', b'z',
+
+                      b'[', b'\\', b']', b'^', b'_',
+    b'`', b'a', b'b', b'c', b'd', b'e', b'f', b'g',
+    b'h', b'i', b'j', b'k', b'l', b'm', b'n', b'o',
+    b'p', b'q', b'r', b's', b't', b'u', b'v', b'w',
+    b'x', b'y', b'z', b'{', b'|', b'}', b'~', 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+    0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+    0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+    0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
+    0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
+    0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
+    0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
+    0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
+    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+];
+
+static ASCII_UPPERCASE_MAP: [u8; 256] = [
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+    0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+    0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    b' ', b'!', b'"', b'#', b'$', b'%', b'&', b'\'',
+    b'(', b')', b'*', b'+', b',', b'-', b'.', b'/',
+    b'0', b'1', b'2', b'3', b'4', b'5', b'6', b'7',
+    b'8', b'9', b':', b';', b'<', b'=', b'>', b'?',
+    b'@', b'A', b'B', b'C', b'D', b'E', b'F', b'G',
+    b'H', b'I', b'J', b'K', b'L', b'M', b'N', b'O',
+    b'P', b'Q', b'R', b'S', b'T', b'U', b'V', b'W',
+    b'X', b'Y', b'Z', b'[', b'\\', b']', b'^', b'_',
+    b'`',
+
+          b'A', b'B', b'C', b'D', b'E', b'F', b'G',
+    b'H', b'I', b'J', b'K', b'L', b'M', b'N', b'O',
+    b'P', b'Q', b'R', b'S', b'T', b'U', b'V', b'W',
+    b'X', b'Y', b'Z',
+
+                      b'{', b'|', b'}', b'~', 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+    0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+    0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+    0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
+    0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
+    0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
+    0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
+    0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
+    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+];
+
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use rustc_unicode::char::from_u32;
+    use collections::string::ToString;
+
+    #[test]
+    fn test_is_ascii() {
+        assert!(b"".is_ascii());
+        assert!(b"banana\0\x7F".is_ascii());
+        assert!(b"banana\0\x7F".iter().all(|b| b.is_ascii()));
+        assert!(!b"Vi\xe1\xbb\x87t Nam".is_ascii());
+        assert!(!b"Vi\xe1\xbb\x87t Nam".iter().all(|b| b.is_ascii()));
+        assert!(!b"\xe1\xbb\x87".iter().any(|b| b.is_ascii()));
+
+        assert!("".is_ascii());
+        assert!("banana\0\u{7F}".is_ascii());
+        assert!("banana\0\u{7F}".chars().all(|c| c.is_ascii()));
+        assert!(!"ประเทศไทย中华Việt Nam".chars().all(|c| c.is_ascii()));
+
+        // NOTE: This test fails for some reason.
+        assert!(!"ประเทศไทย中华ệ ".chars().any(|c| c.is_ascii()));
+    }
+
+    #[test]
+    fn test_to_ascii_uppercase() {
+        assert_eq!("url()URL()uRl()ürl".to_ascii_uppercase(), "URL()URL()URL()üRL");
+        assert_eq!("hıKß".to_ascii_uppercase(), "HıKß");
+
+        for i in 0..501 {
+            let upper = if 'a' as u32 <= i && i <= 'z' as u32 { i + 'A' as u32 - 'a' as u32 }
+                        else { i };
+            assert_eq!((from_u32(i).unwrap()).to_string().to_ascii_uppercase(),
+                       (from_u32(upper).unwrap()).to_string());
+        }
+    }
+
+    #[test]
+    fn test_to_ascii_lowercase() {
+        assert_eq!("url()URL()uRl()Ürl".to_ascii_lowercase(), "url()url()url()Ürl");
+        // Dotted capital I, Kelvin sign, Sharp S.
+        assert_eq!("HİKß".to_ascii_lowercase(), "hİKß");
+
+        for i in 0..501 {
+            let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
+                        else { i };
+            assert_eq!((from_u32(i).unwrap()).to_string().to_ascii_lowercase(),
+                       (from_u32(lower).unwrap()).to_string());
+        }
+    }
+
+    #[test]
+    fn test_make_ascii_lower_case() {
+        macro_rules! test {
+            ($from: expr, $to: expr) => {
+                {
+                    let mut x = $from;
+                    x.make_ascii_lowercase();
+                    assert_eq!(x, $to);
+                }
+            }
+        }
+        test!(b'A', b'a');
+        test!(b'a', b'a');
+        test!(b'!', b'!');
+        test!('A', 'a');
+        test!('À', 'À');
+        test!('a', 'a');
+        test!('!', '!');
+        test!(b"H\xc3\x89".to_vec(), b"h\xc3\x89");
+        test!("HİKß".to_string(), "hİKß");
+    }
+
+
+    #[test]
+    fn test_make_ascii_upper_case() {
+        macro_rules! test {
+            ($from: expr, $to: expr) => {
+                {
+                    let mut x = $from;
+                    x.make_ascii_uppercase();
+                    assert_eq!(x, $to);
+                }
+            }
+        }
+        test!(b'a', b'A');
+        test!(b'A', b'A');
+        test!(b'!', b'!');
+        test!('a', 'A');
+        test!('à', 'à');
+        test!('A', 'A');
+        test!('!', '!');
+        test!(b"h\xc3\xa9".to_vec(), b"H\xc3\xa9");
+        test!("hıKß".to_string(), "HıKß");
+
+        let mut x = "Hello".to_string();
+        x[..3].make_ascii_uppercase();  // Test IndexMut on String.
+        assert_eq!(x, "HELlo")
+    }
+
+    #[test]
+    fn test_eq_ignore_ascii_case() {
+        assert!("url()URL()uRl()Ürl".eq_ignore_ascii_case("url()url()url()Ürl"));
+        assert!(!"Ürl".eq_ignore_ascii_case("ürl"));
+        // Dotted capital I, Kelvin sign, Sharp S.
+        assert!("HİKß".eq_ignore_ascii_case("hİKß"));
+        assert!(!"İ".eq_ignore_ascii_case("i"));
+        assert!(!"K".eq_ignore_ascii_case("k"));
+        assert!(!"ß".eq_ignore_ascii_case("s"));
+
+        for i in 0..501 {
+            let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
+                        else { i };
+            assert!((from_u32(i).unwrap()).to_string().eq_ignore_ascii_case(
+                    &from_u32(lower).unwrap().to_string()));
+        }
+    }
+
+    #[test]
+    fn inference_works() {
+        let x = "a".to_string();
+        x.eq_ignore_ascii_case("A");
+    }
+}

src/ffi/mod.rs

@@ -0,0 +1,3 @@
+pub use self::os_str::{OsString, OsStr};
+
+mod os_str;

src/ffi/os_str.rs

@@ -0,0 +1,576 @@
+// Copyright 2015 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.
+
+use collections::borrow::{Borrow, Cow, ToOwned};
+use core::fmt::{self, Debug};
+use core::mem;
+use collections::String;
+use core::ops;
+use core::cmp;
+use core::hash::{Hash, Hasher};
+use collections::Vec;
+
+use sys::wtf8::{Wtf8, Wtf8Buf};
+use sys::{AsInner, IntoInner, FromInner};
+
+pub use sys::wtf8::EncodeWide;
+
+/// A type that can represent owned, mutable platform-native strings, but is
+/// cheaply inter-convertible with Rust strings.
+///
+/// The need for this type arises from the fact that:
+///
+/// * On Unix systems, strings are often arbitrary sequences of non-zero
+///   bytes, in many cases interpreted as UTF-8.
+///
+/// * On Windows, strings are often arbitrary sequences of non-zero 16-bit
+///   values, interpreted as UTF-16 when it is valid to do so.
+///
+/// * In Rust, strings are always valid UTF-8, but may contain zeros.
+///
+/// `OsString` and `OsStr` bridge this gap by simultaneously representing Rust
+/// and platform-native string values, and in particular allowing a Rust string
+/// to be converted into an "OS" string with no cost.
+#[derive(Clone)]
+pub struct OsString {
+    inner: Wtf8Buf 
+}
+
+/// Slices into OS strings (see `OsString`).
+pub struct OsStr {
+    inner: Wtf8
+}
+
+impl OsString {
+    /// Constructs a new empty `OsString`.
+    pub fn new() -> OsString {
+        OsString { inner: Wtf8Buf::from_string(String::new()) }
+    }
+
+    fn _from_bytes(vec: Vec<u8>) -> Option<OsString> {
+        String::from_utf8(vec).ok().map(OsString::from)
+    }
+
+    /// Converts to an `OsStr` slice.
+    pub fn as_os_str(&self) -> &OsStr {
+        self
+    }
+
+    /// Converts the `OsString` into a `String` if it contains valid Unicode data.
+    ///
+    /// On failure, ownership of the original `OsString` is returned.
+    pub fn into_string(self) -> Result<String, OsString> {
+        self.inner.into_string().map_err(|buf| OsString { inner: buf} )
+    }
+
+    /// Extends the string with the given `&OsStr` slice.
+    pub fn push<T: AsRef<OsStr>>(&mut self, s: T) {
+        self.inner.push_wtf8(&s.as_ref().inner)
+    }
+
+    /// Creates a new `OsString` with the given capacity.
+    ///
+    /// The string will be able to hold exactly `capacity` lenth units of other
+    /// OS strings without reallocating. If `capacity` is 0, the string will not
+    /// allocate.
+    ///
+    /// See main `OsString` documentation information about encoding.
+    pub fn with_capacity(capacity: usize) -> OsString {
+        OsString {
+            inner: Wtf8Buf::with_capacity(capacity)
+        }
+    }
+
+    /// Truncates the `OsString` to zero length.
+    pub fn clear(&mut self) {
+        self.inner.clear()
+    }
+
+    /// Returns the capacity this `OsString` can hold without reallocating.
+    ///
+    /// See `OsString` introduction for information about encoding.
+    pub fn capacity(&self) -> usize {
+        self.inner.capacity()
+    }
+
+    /// Reserves capacity for at least `additional` more capacity to be inserted
+    /// in the given `OsString`.
+    ///
+    /// The collection may reserve more space to avoid frequent reallocations.
+    pub fn reserve(&mut self, additional: usize) {
+        self.inner.reserve(additional)
+    }
+
+    /// Reserves the minimum capacity for exactly `additional` more capacity to
+    /// be inserted in the given `OsString`. Does nothing if the capacity is
+    /// already sufficient.
+    ///
+    /// Note that the allocator may give the collection more space than it
+    /// requests. Therefore capacity can not be relied upon to be precisely
+    /// minimal. Prefer reserve if future insertions are expected.
+    pub fn reserve_exact(&mut self, additional: usize) {
+        self.inner.reserve_exact(additional)
+    }
+
+    /// Creates an `OsString` from a potentially ill-formed UTF-16 slice of
+    /// 16-bit code units.
+    ///
+    /// This is lossless: calling `.encode_wide()` on the resulting string
+    /// will always return the original code units.
+    ///
+    /// NOTE: This function was copied from the windows implementation of OsStringExt
+    pub fn from_wide(wide: &[u16]) -> OsString {
+        OsString { inner: Wtf8Buf::from_wide(wide) }
+    }
+}
+
+impl From<String> for OsString {
+    fn from(s: String) -> OsString {
+        OsString { inner: Wtf8Buf::from_string(s) }
+    }
+}
+
+impl<'a, T: ?Sized + AsRef<OsStr>> From<&'a T> for OsString {
+    fn from(s: &'a T) -> OsString {
+        s.as_ref().to_os_string()
+    }
+}
+
+impl ops::Index<ops::RangeFull> for OsString {
+    type Output = OsStr;
+
+    #[inline]
+    fn index(&self, _index: ops::RangeFull) -> &OsStr {
+        OsStr::from_inner(self.inner.as_slice())
+    }
+}
+
+impl ops::Deref for OsString {
+    type Target = OsStr;
+
+    #[inline]
+    fn deref(&self) -> &OsStr {
+        &self[..]
+    }
+}
+
+impl Default for OsString {
+    #[inline]
+    fn default() -> OsString {
+        OsString::new()
+    }
+}
+
+impl Debug for OsString {
+    fn fmt(&self, formatter: &mut fmt::Formatter) -> Result<(), fmt::Error> {
+        fmt::Debug::fmt(&**self, formatter)
+    }
+}
+
+impl PartialEq for OsString {
+    fn eq(&self, other: &OsString) -> bool {
+        &**self == &**other
+    }
+}
+
+impl PartialEq<str> for OsString {
+    fn eq(&self, other: &str) -> bool {
+        &**self == other
+    }
+}
+
+impl PartialEq<OsString> for str {
+    fn eq(&self, other: &OsString) -> bool {
+        &**other == self
+    }
+}
+
+impl Eq for OsString {}
+
+impl PartialOrd for OsString {
+    #[inline]
+    fn partial_cmp(&self, other: &OsString) -> Option<cmp::Ordering> {
+        (&**self).partial_cmp(&**other)
+    }
+    #[inline]
+    fn lt(&self, other: &OsString) -> bool { &**self < &**other }
+    #[inline]
+    fn le(&self, other: &OsString) -> bool { &**self <= &**other }
+    #[inline]
+    fn gt(&self, other: &OsString) -> bool { &**self > &**other }
+    #[inline]
+    fn ge(&self, other: &OsString) -> bool { &**self >= &**other }
+}
+
+impl PartialOrd<str> for OsString {
+    #[inline]
+    fn partial_cmp(&self, other: &str) -> Option<cmp::Ordering> {
+        (&**self).partial_cmp(other)
+    }
+}
+
+impl Ord for OsString {
+    #[inline]
+    fn cmp(&self, other: &OsString) -> cmp::Ordering {
+        (&**self).cmp(&**other)
+    }
+}
+
+impl Hash for OsString {
+    #[inline]
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        (&**self).hash(state)
+    }
+}
+
+impl OsStr {
+    /// Coerces into an `OsStr` slice.
+    pub fn new<S: AsRef<OsStr> + ?Sized>(s: &S) -> &OsStr {
+        s.as_ref()
+    }
+
+    fn from_inner(inner: &Wtf8) -> &OsStr {
+        unsafe { mem::transmute(inner) }
+    }
+
+    /// Yields a `&str` slice if the `OsStr` is valid Unicode.
+    ///
+    /// This conversion may entail doing a check for UTF-8 validity.
+    pub fn to_str(&self) -> Option<&str> {
+        self.inner.as_str()
+    }
+
+    /// Converts an `OsStr` to a `Cow<str>`.
+    ///
+    /// Any non-Unicode sequences are replaced with U+FFFD REPLACEMENT CHARACTER.
+    pub fn to_string_lossy(&self) -> Cow<str> {
+        self.inner.to_string_lossy()
+    }
+
+    /// Copies the slice into an owned `OsString`.
+    pub fn to_os_string(&self) -> OsString {
+        let mut buf = Wtf8Buf::with_capacity(self.inner.len());
+        buf.push_wtf8(&self.inner);
+        OsString { inner: buf }
+    }
+
+    /// Checks whether the `OsStr` is empty.
+    pub fn is_empty(&self) -> bool {
+        self.inner.is_empty()
+    }
+
+    /// Returns the length of this `OsStr`.
+    ///
+    /// Note that this does **not** return the number of bytes in this string
+    /// as, for example, OS strings on Windows are encoded as a list of `u16`
+    /// rather than a list of bytes. This number is simply useful for passing to
+    /// other methods like `OsString::with_capacity` to avoid reallocations.
+    ///
+    /// See `OsStr` introduction for more information about encoding.
+    pub fn len(&self) -> usize {
+        self.inner.len()
+    }
+
+    /// Gets the underlying byte representation.
+    ///
+    /// Note: it is *crucial* that this API is private, to avoid
+    /// revealing the internal, platform-specific encodings.
+    fn bytes(&self) -> &[u8] {
+        unsafe { mem::transmute(&self.inner) }
+    }
+    
+    /// Re-encodes an `OsStr` as a wide character sequence,
+    /// i.e. potentially ill-formed UTF-16.
+    /// This is lossless. Note that the encoding does not include a final
+    /// null.
+    ///
+    /// NOTE: This function was copied from the windows implementation of OsStrExt
+    pub fn encode_wide(&self) -> EncodeWide {
+        self.inner.encode_wide()
+    }
+
+}
+
+impl<'a> Default for &'a OsStr {
+    #[inline]
+    fn default() -> &'a OsStr {
+        OsStr::new("")
+    }
+}
+
+impl PartialEq for OsStr {
+    fn eq(&self, other: &OsStr) -> bool {
+        self.bytes().eq(other.bytes())
+    }
+}
+
+impl PartialEq<str> for OsStr {
+    fn eq(&self, other: &str) -> bool {
+        *self == *OsStr::new(other)
+    }
+}
+
+impl PartialEq<OsStr> for str {
+    fn eq(&self, other: &OsStr) -> bool {
+        *other == *OsStr::new(self)
+    }
+}
+
+impl Eq for OsStr {}
+
+impl PartialOrd for OsStr {
+    #[inline]
+    fn partial_cmp(&self, other: &OsStr) -> Option<cmp::Ordering> {
+        self.bytes().partial_cmp(other.bytes())
+    }
+    #[inline]
+    fn lt(&self, other: &OsStr) -> bool { self.bytes().lt(other.bytes()) }
+    #[inline]
+    fn le(&self, other: &OsStr) -> bool { self.bytes().le(other.bytes()) }
+    #[inline]
+    fn gt(&self, other: &OsStr) -> bool { self.bytes().gt(other.bytes()) }
+    #[inline]
+    fn ge(&self, other: &OsStr) -> bool { self.bytes().ge(other.bytes()) }
+}
+
+impl PartialOrd<str> for OsStr {
+    #[inline]
+    fn partial_cmp(&self, other: &str) -> Option<cmp::Ordering> {
+        self.partial_cmp(OsStr::new(other))
+    }
+}
+
+// FIXME (#19470): cannot provide PartialOrd<OsStr> for str until we
+// have more flexible coherence rules.
+
+impl Ord for OsStr {
+    #[inline]
+    fn cmp(&self, other: &OsStr) -> cmp::Ordering { self.bytes().cmp(other.bytes()) }
+}
+
+macro_rules! impl_cmp {
+    ($lhs:ty, $rhs: ty) => {
+        impl<'a, 'b> PartialEq<$rhs> for $lhs {
+            #[inline]
+            fn eq(&self, other: &$rhs) -> bool { <OsStr as PartialEq>::eq(self, other) }
+        }
+
+        impl<'a, 'b> PartialEq<$lhs> for $rhs {
+            #[inline]
+            fn eq(&self, other: &$lhs) -> bool { <OsStr as PartialEq>::eq(self, other) }
+        }
+
+        impl<'a, 'b> PartialOrd<$rhs> for $lhs {
+            #[inline]
+            fn partial_cmp(&self, other: &$rhs) -> Option<cmp::Ordering> {
+                <OsStr as PartialOrd>::partial_cmp(self, other)
+            }
+        }
+
+        impl<'a, 'b> PartialOrd<$lhs> for $rhs {
+            #[inline]
+            fn partial_cmp(&self, other: &$lhs) -> Option<cmp::Ordering> {
+                <OsStr as PartialOrd>::partial_cmp(self, other)
+            }
+        }
+    }
+}
+
+impl_cmp!(OsString, OsStr);
+impl_cmp!(OsString, &'a OsStr);
+impl_cmp!(Cow<'a, OsStr>, OsStr);
+impl_cmp!(Cow<'a, OsStr>, &'b OsStr);
+impl_cmp!(Cow<'a, OsStr>, OsString);
+
+impl Hash for OsStr {
+    #[inline]
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        self.bytes().hash(state)
+    }
+}
+
+impl Debug for OsStr {
+    fn fmt(&self, formatter: &mut fmt::Formatter) -> Result<(), fmt::Error> {
+        self.inner.fmt(formatter)
+    }
+}
+
+impl Borrow<OsStr> for OsString {
+    fn borrow(&self) -> &OsStr { &self[..] }
+}
+
+impl ToOwned for OsStr {
+    type Owned = OsString;
+    fn to_owned(&self) -> OsString { self.to_os_string() }
+}
+
+impl AsRef<OsStr> for OsStr {
+    fn as_ref(&self) -> &OsStr {
+        self
+    }
+}
+
+impl AsRef<OsStr> for OsString {
+    fn as_ref(&self) -> &OsStr {
+        self
+    }
+}
+
+impl AsRef<OsStr> for str {
+    fn as_ref(&self) -> &OsStr {
+        OsStr::from_inner(Wtf8::from_str(self))
+    }
+}
+
+impl AsRef<OsStr> for String {
+    fn as_ref(&self) -> &OsStr {
+        (&**self).as_ref()
+    }
+}
+
+impl FromInner<Wtf8Buf> for OsString {
+    fn from_inner(buf: Wtf8Buf) -> OsString {
+        OsString { inner: buf }
+    }
+}
+
+impl IntoInner<Wtf8Buf> for OsString {
+    fn into_inner(self) -> Wtf8Buf {
+        self.inner
+    }
+}
+
+impl AsInner<Wtf8> for OsStr {
+    fn as_inner(&self) -> &Wtf8 {
+        &self.inner
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use sys::{AsInner, IntoInner};
+
+    #[test]
+    fn test_os_string_with_capacity() {
+        let os_string = OsString::with_capacity(0);
+        assert_eq!(0, os_string.inner.capacity());
+
+        let os_string = OsString::with_capacity(10);
+        assert_eq!(10, os_string.inner.capacity());
+
+        let mut os_string = OsString::with_capacity(0);
+        os_string.push("abc");
+        assert!(os_string.inner.capacity() >= 3);
+    }
+
+    #[test]
+    fn test_os_string_clear() {
+        let mut os_string = OsString::from("abc");
+        assert_eq!(3, os_string.inner.len());
+
+        os_string.clear();
+        assert_eq!(&os_string, "");
+        assert_eq!(0, os_string.inner.len());
+    }
+
+    #[test]
+    fn test_os_string_capacity() {
+        let os_string = OsString::with_capacity(0);
+        assert_eq!(0, os_string.capacity());
+
+        let os_string = OsString::with_capacity(10);
+        assert_eq!(10, os_string.capacity());
+
+        let mut os_string = OsString::with_capacity(0);
+        os_string.push("abc");
+        assert!(os_string.capacity() >= 3);
+    }
+
+    #[test]
+    fn test_os_string_reserve() {
+        let mut os_string = OsString::new();
+        assert_eq!(os_string.capacity(), 0);
+
+        os_string.reserve(2);
+        assert!(os_string.capacity() >= 2);
+
+        for _ in 0..16 {
+            os_string.push("a");
+        }
+
+        assert!(os_string.capacity() >= 16);
+        os_string.reserve(16);
+        assert!(os_string.capacity() >= 32);
+
+        os_string.push("a");
+
+        os_string.reserve(16);
+        assert!(os_string.capacity() >= 33)
+    }
+
+    #[test]
+    fn test_os_string_reserve_exact() {
+        let mut os_string = OsString::new();
+        assert_eq!(os_string.capacity(), 0);
+
+        os_string.reserve_exact(2);
+        assert!(os_string.capacity() >= 2);
+
+        for _ in 0..16 {
+            os_string.push("a");
+        }
+
+        assert!(os_string.capacity() >= 16);
+        os_string.reserve_exact(16);
+        assert!(os_string.capacity() >= 32);
+
+        os_string.push("a");
+
+        os_string.reserve_exact(16);
+        assert!(os_string.capacity() >= 33)
+    }
+
+    #[test]
+    fn test_os_string_default() {
+        let os_string: OsString = Default::default();
+        assert_eq!("", &os_string);
+    }
+
+    #[test]
+    fn test_os_str_is_empty() {
+        let mut os_string = OsString::new();
+        assert!(os_string.is_empty());
+
+        os_string.push("abc");
+        assert!(!os_string.is_empty());
+
+        os_string.clear();
+        assert!(os_string.is_empty());
+    }
+
+    #[test]
+    fn test_os_str_len() {
+        let mut os_string = OsString::new();
+        assert_eq!(0, os_string.len());
+
+        os_string.push("abc");
+        assert_eq!(3, os_string.len());
+
+        os_string.clear();
+        assert_eq!(0, os_string.len());
+    }
+
+    #[test]
+    fn test_os_str_default() {
+        let os_str: &OsStr = Default::default();
+        assert_eq!("", os_str);
+    }
+}

src/lib.rs

@@ -1,20 +1,35 @@
-#![feature(alloc, collections, lang_items)]
+#![feature(alloc)]
+#![feature(collections)]
+#![feature(char_escape_debug)]
+#![feature(lang_items)]
+#![feature(question_mark)]
+#![feature(slice_patterns)]
+#![feature(str_internals)]
+#![feature(unicode)]
+
 #![no_std]
+
 #![crate_type = "rlib"]
 #![crate_name = "ctru"]
 
-extern crate ctru_sys as libctru;
-
 extern crate alloc;
 extern crate collections;
+extern crate rustc_unicode;
+
+extern crate ctru_sys as libctru;
 
 pub mod console;
 pub mod srv;
 pub mod gfx;
+pub mod services;
 pub mod sdmc;
 
-pub mod services;
+pub mod ascii;
+pub mod ffi;
 pub mod panic;
+pub mod path;
+
+mod sys;
 
 pub use srv::Srv;
 pub use gfx::Gfx;

src/sys/mod.rs

@@ -0,0 +1,25 @@
+/// A trait for viewing representations from std types
+#[doc(hidden)]
+pub trait AsInner<Inner: ?Sized> {
+    fn as_inner(&self) -> &Inner;
+}
+
+/// A trait for viewing representations from std types
+#[doc(hidden)]
+pub trait AsInnerMut<Inner: ?Sized> {
+    fn as_inner_mut(&mut self) -> &mut Inner;
+}
+
+/// A trait for extracting representations from std types
+#[doc(hidden)]
+pub trait IntoInner<Inner> {
+    fn into_inner(self) -> Inner;
+}
+
+/// A trait for creating std types from internal representations
+#[doc(hidden)]
+pub trait FromInner<Inner> {
+    fn from_inner(inner: Inner) -> Self;
+}
+
+pub mod wtf8;