user0/rust
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Cleaned up case related functions a bit

Browse source
This commit is contained in:
Marvin Löbel 2013-04-18 10:01:23 +02:00
parent ae3b8690c1
commit 276293af7c
2 changed files with 35 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/libcore/char.rs
View file

@ -1,4 +1,4 @@
// Copyright 2012 The Rust Project Developers. See the COPYRIGHT
// Copyright 2012-2013 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
@ -234,6 +234,21 @@ pub fn escape_default(c: char) -> ~str {
}
}
/// Returns the amount of bytes this character would need if encoded in utf8
pub fn len_utf8_bytes(c: char) -> uint {
static max_one_b: uint = 128u;
static max_two_b: uint = 2048u;
static max_three_b: uint = 65536u;
static max_four_b: uint = 2097152u;
let code = c as uint;
if code < max_one_b { 1u }
else if code < max_two_b { 2u }
else if code < max_three_b { 3u }
else if code < max_four_b { 4u }
else { fail!(~"invalid character!") }
}
/**
* Compare two chars
*
@ -334,7 +349,6 @@ fn test_escape_default() {
assert_eq!(escape_default('\U0001d4b6'), ~"\\U0001d4b6");
}
#[test]
fn test_escape_unicode() {
assert_eq!(escape_unicode('\x00'), ~"\\x00");

41
src/libcore/str.rs
View file

@ -1,4 +1,4 @@
// Copyright 2012 The Rust Project Developers. See the COPYRIGHT
// Copyright 2012-2013 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
@ -789,16 +789,18 @@ pub fn each_split_within<'a>(ss: &'a str,
/// Convert a string to lowercase. ASCII only
pub fn to_lower(s: &str) -> ~str {
map(s,
|c| unsafe{(libc::tolower(c as libc::c_char)) as char}
)
do map(s) |c| {
assert!(char::is_ascii(c));
(unsafe{libc::tolower(c as libc::c_char)}) as char
}
}
/// Convert a string to uppercase. ASCII only
pub fn to_upper(s: &str) -> ~str {
map(s,
|c| unsafe{(libc::toupper(c as libc::c_char)) as char}
)
do map(s) |c| {
assert!(char::is_ascii(c));
(unsafe{libc::toupper(c as libc::c_char)}) as char
}
}
/**
@ -3096,12 +3098,11 @@ mod tests {
#[test]
fn test_to_lower() {
unsafe {
assert!(~"" == map(~"",
|c| libc::tolower(c as c_char) as char));
assert!(~"ymca" == map(~"YMCA",
|c| libc::tolower(c as c_char) as char));
}
// libc::tolower, and hence str::to_lower
// are culturally insensitive: they only work for ASCII
// (see Issue #1347)
assert!(~"" == to_lower(""));
assert!(~"ymca" == to_lower("YMCA"));
}
#[test]
@ -3666,12 +3667,8 @@ mod tests {
#[test]
fn test_map() {
unsafe {
assert!(~"" == map(~"", |c|
libc::toupper(c as c_char) as char));
assert!(~"YMCA" == map(~"ymca",
|c| libc::toupper(c as c_char) as char));
}
assert!(~"" == map(~"", |c| unsafe {libc::toupper(c as c_char)} as char));
assert!(~"YMCA" == map(~"ymca", |c| unsafe {libc::toupper(c as c_char)} as char));
}
#[test]
@ -3685,11 +3682,11 @@ mod tests {
#[test]
fn test_any() {
assert!(false == any(~"", char::is_uppercase));
assert!(false == any(~"", char::is_uppercase));
assert!(false == any(~"ymca", char::is_uppercase));
assert!(true == any(~"YMCA", char::is_uppercase));
assert!(true == any(~"yMCA", char::is_uppercase));
assert!(true == any(~"Ymcy", char::is_uppercase));
assert!(true == any(~"yMCA", char::is_uppercase));
assert!(true == any(~"Ymcy", char::is_uppercase));
}
#[test]