auto merge of rust-lang#8231 : SimonSapin/rust/ascii-upper-lower-case, r=cmr

Original pull request: Add str.to_ascii_lower() and str.to_ascii_upper() methods in std::str.

Author: bors

src/libstd/str/ascii.rs

@@ -13,7 +13,10 @@
 use to_str::{ToStr,ToStrConsume};
 use str;
 use str::StrSlice;
+use str::OwnedStr;
+use container::Container;
 use cast;
+use ptr;
 use iterator::{Iterator, IteratorUtil};
 use vec::{CopyableVector, ImmutableVector, OwnedVector};
 use to_bytes::IterBytes;
@@ -39,27 +42,19 @@ impl Ascii {
     /// Convert to lowercase.
     #[inline]
     pub fn to_lower(self) -> Ascii {
-        if self.chr >= 65 && self.chr <= 90 {
-            Ascii{chr: self.chr | 0x20 }
-        } else {
-            self
-        }
+        Ascii{chr: ASCII_LOWER_MAP[self.chr]}
     }
 
     /// Convert to uppercase.
     #[inline]
     pub fn to_upper(self) -> Ascii {
-        if self.chr >= 97 && self.chr <= 122 {
-            Ascii{chr: self.chr & !0x20 }
-        } else {
-            self
-        }
+        Ascii{chr: ASCII_UPPER_MAP[self.chr]}
     }
 
     /// Compares two ascii characters of equality, ignoring case.
     #[inline]
     pub fn eq_ignore_case(self, other: Ascii) -> bool {
-        self.to_lower().chr == other.to_lower().chr
+        ASCII_LOWER_MAP[self.chr] == ASCII_LOWER_MAP[other.chr]
     }
 }
 
@@ -261,10 +256,124 @@ impl ToBytesConsume for ~[Ascii] {
     }
 }
 
+
+/// Convert the string to ASCII upper case:
+/// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
+/// but non-ASCII letters are unchanged.
+#[inline]
+pub fn to_ascii_upper(string: &str) -> ~str {
+    map_bytes(string, ASCII_UPPER_MAP)
+}
+
+/// Convert the string to ASCII lower case:
+/// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
+/// but non-ASCII letters are unchanged.
+#[inline]
+pub fn to_ascii_lower(string: &str) -> ~str {
+    map_bytes(string, ASCII_LOWER_MAP)
+}
+
+#[inline]
+priv fn map_bytes(string: &str, map: &'static [u8]) -> ~str {
+    let len = string.len();
+    let mut result = str::with_capacity(len);
+    unsafe {
+        do result.as_mut_buf |mut buf, _| {
+            for c in string.as_bytes().iter() {
+                *buf = map[*c];
+                buf = ptr::mut_offset(buf, 1)
+            }
+        }
+        str::raw::set_len(&mut result, len);
+    }
+    result
+}
+
+/// Check that two strings are an ASCII case-insensitive match.
+/// Same as `to_ascii_lower(a) == to_ascii_lower(b)`,
+/// but without allocating and copying temporary strings.
+#[inline]
+pub fn eq_ignore_ascii_case(a: &str, b: &str) -> bool {
+    a.len() == b.len() && a.as_bytes().iter().zip(b.as_bytes().iter()).all(
+        |(byte_a, byte_b)| ASCII_LOWER_MAP[*byte_a] == ASCII_LOWER_MAP[*byte_b])
+}
+
+priv static ASCII_LOWER_MAP: &'static [u8] = &[
+    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,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+    0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+    0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+    0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+    0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 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,
+];
+
+priv static ASCII_UPPER_MAP: &'static [u8] = &[
+    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,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+    0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+    0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+    0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
+    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+    0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+    0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
+    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+    0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 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 to_bytes::ToBytes;
+    use str::from_char;
 
     macro_rules! v2ascii (
         ( [$($e:expr),*]) => ( [$(Ascii{chr:$e}),*]);
@@ -347,4 +456,53 @@ mod tests {
 
     #[test] #[should_fail]
     fn test_ascii_fail_char_slice() { 'λ'.to_ascii(); }
+
+    #[test]
+    fn test_to_ascii_upper() {
+        assert_eq!(to_ascii_upper("url()URL()uRl()ürl"), ~"URL()URL()URL()üRL");
+        assert_eq!(to_ascii_upper("hıKß"), ~"HıKß");
+
+        let mut i = 0;
+        while i <= 500 {
+            let c = i as char;
+            let upper = if 'a' <= c && c <= 'z' { c + 'A' - 'a' } else { c };
+            assert_eq!(to_ascii_upper(from_char(i as char)), from_char(upper))
+            i += 1;
+        }
+    }
+
+    #[test]
+    fn test_to_ascii_lower() {
+        assert_eq!(to_ascii_lower("url()URL()uRl()Ürl"), ~"url()url()url()Ürl");
+        // Dotted capital I, Kelvin sign, Sharp S.
+        assert_eq!(to_ascii_lower("HİKß"), ~"hİKß");
+
+        let mut i = 0;
+        while i <= 500 {
+            let c = i as char;
+            let lower = if 'A' <= c && c <= 'Z' { c + 'a' - 'A' } else { c };
+            assert_eq!(to_ascii_lower(from_char(i as char)), from_char(lower))
+            i += 1;
+        }
+    }
+
+
+    #[test]
+    fn test_eq_ignore_ascii_case() {
+        assert!(eq_ignore_ascii_case("url()URL()uRl()Ürl", "url()url()url()Ürl"));
+        assert!(!eq_ignore_ascii_case("Ürl", "ürl"));
+        // Dotted capital I, Kelvin sign, Sharp S.
+        assert!(eq_ignore_ascii_case("HİKß", "hİKß"));
+        assert!(!eq_ignore_ascii_case("İ", "i"));
+        assert!(!eq_ignore_ascii_case("K", "k"));
+        assert!(!eq_ignore_ascii_case("ß", "s"));
+
+        let mut i = 0;
+        while i <= 500 {
+            let c = i as char;
+            let lower = if 'A' <= c && c <= 'Z' { c + 'a' - 'A' } else { c };
+            assert!(eq_ignore_ascii_case(from_char(i as char), from_char(lower)));
+            i += 1;
+        }
+    }
 }