nordic-dev.net/rust
nordic-dev.net/rust
2
0
Fork 0
mirror of https://github.com/rust-lang/rust.git synced 2024-11-22 14:55:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

auto merge of #12759 : lucab/rust/char-doc, r=alexcrichton

Browse Source 
This is mostly a reaction to #12730. If we are going to keep calling them `char`, at least make it clear that they aren't characters but codepoint/scalar.
This commit is contained in:
bors 2014-03-08 17:31:57 -08:00
commit e1681df892
1 changed files with 60 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

89
src/libstd/char.rs
View File

@ -8,7 +8,21 @@
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Unicode characters manipulation (`char` type)
//! Character manipulation (`char` type, Unicode Scalar Value)
//!
//! This module provides the `Char` trait, as well as its implementation
//! for the primitive `char` type, in order to allow basic character manipulation.
//!
//! A `char` actually represents a
//! *[Unicode Scalar Value](http://www.unicode.org/glossary/#unicode_scalar_value)*,
//! as it can contain any Unicode code point except high-surrogate and
//! low-surrogate code points.
//!
//! As such, only values in the ranges \[0x0,0xD7FF\] and \[0xE000,0x10FFFF\]
//! (inclusive) are allowed. A `char` can always be safely cast to a `u32`;
//! however the converse is not always true due to the above range limits
//! and, as such, should be performed via the `from_u32` function..
use cast::transmute;
use option::{None, Option, Some};
@ -66,7 +80,7 @@ static TAG_FOUR_B: uint = 240u;
/// The highest valid code point
pub static MAX: char = '\U0010ffff';
/// Convert from `u32` to a character.
/// Converts from `u32` to a `char`
#[inline]
pub fn from_u32(i: u32) -> Option<char> {
// catch out-of-bounds and surrogates
@ -77,31 +91,44 @@ pub fn from_u32(i: u32) -> Option<char> {
}
}
/// Returns whether the specified character is considered a unicode alphabetic
/// character
/// Returns whether the specified `char` is considered a Unicode alphabetic
/// code point
pub fn is_alphabetic(c: char) -> bool { derived_property::Alphabetic(c) }
#[allow(missing_doc)]
/// Returns whether the specified `char` satisfies the 'XID_Start' Unicode property
///
/// 'XID_Start' is a Unicode Derived Property specified in
/// [UAX #31](http://unicode.org/reports/tr31/#NFKC_Modifications),
/// mostly similar to ID_Start but modified for closure under NFKx.
pub fn is_XID_start(c: char) -> bool { derived_property::XID_Start(c) }
#[allow(missing_doc)]
/// Returns whether the specified `char` satisfies the 'XID_Continue' Unicode property
///
/// 'XID_Continue' is a Unicode Derived Property specified in
/// [UAX #31](http://unicode.org/reports/tr31/#NFKC_Modifications),
/// mostly similar to 'ID_Continue' but modified for closure under NFKx.
pub fn is_XID_continue(c: char) -> bool { derived_property::XID_Continue(c) }
///
/// Indicates whether a character is in lower case, defined
/// in terms of the Unicode Derived Core Property 'Lowercase'.
/// Indicates whether a `char` is in lower case
///
/// This is defined according to the terms of the Unicode Derived Core Property 'Lowercase'.
///
#[inline]
pub fn is_lowercase(c: char) -> bool { derived_property::Lowercase(c) }
///
/// Indicates whether a character is in upper case, defined
/// in terms of the Unicode Derived Core Property 'Uppercase'.
/// Indicates whether a `char` is in upper case
///
/// This is defined according to the terms of the Unicode Derived Core Property 'Uppercase'.
///
#[inline]
pub fn is_uppercase(c: char) -> bool { derived_property::Uppercase(c) }
///
/// Indicates whether a character is whitespace. Whitespace is defined in
/// terms of the Unicode Property 'White_Space'.
/// Indicates whether a `char` is whitespace
///
/// Whitespace is defined in terms of the Unicode Property 'White_Space'.
///
#[inline]
pub fn is_whitespace(c: char) -> bool {
@ -112,9 +139,10 @@ pub fn is_whitespace(c: char) -> bool {
}
///
/// Indicates whether a character is alphanumeric. Alphanumericness is
/// defined in terms of the Unicode General Categories 'Nd', 'Nl', 'No'
/// and the Derived Core Property 'Alphabetic'.
/// Indicates whether a `char` is alphanumeric
///
/// Alphanumericness is defined in terms of the Unicode General Categories
/// 'Nd', 'Nl', 'No' and the Derived Core Property 'Alphabetic'.
///
#[inline]
pub fn is_alphanumeric(c: char) -> bool {
@ -125,14 +153,15 @@ pub fn is_alphanumeric(c: char) -> bool {
}
///
/// Indicates whether a character is a control character. Control
/// characters are defined in terms of the Unicode General Category
/// Indicates whether a `char` is a control code point
///
/// Control code points are defined in terms of the Unicode General Category
/// 'Cc'.
///
#[inline]
pub fn is_control(c: char) -> bool { general_category::Cc(c) }
/// Indicates whether the character is numeric (Nd, Nl, or No)
/// Indicates whether the `char` is numeric (Nd, Nl, or No)
#[inline]
pub fn is_digit(c: char) -> bool {
general_category::Nd(c)
@ -141,7 +170,8 @@ pub fn is_digit(c: char) -> bool {
}
///
/// Checks if a character parses as a numeric digit in the given radix.
/// Checks if a `char` parses as a numeric digit in the given radix
///
/// Compared to `is_digit()`, this function only recognizes the
/// characters `0-9`, `a-z` and `A-Z`.
///
@ -167,13 +197,13 @@ pub fn is_digit_radix(c: char, radix: uint) -> bool {
}
///
/// Convert a char to the corresponding digit.
/// Converts a `char` to the corresponding digit
///
/// # Return value
///
/// If `c` is between '0' and '9', the corresponding value
/// between 0 and 9. If `c` is 'a' or 'A', 10. If `c` is
/// 'b' or 'B', 11, etc. Returns none if the char does not
/// 'b' or 'B', 11, etc. Returns none if the `char` does not
/// refer to a digit in the given radix.
///
/// # Failure
@ -196,7 +226,7 @@ pub fn to_digit(c: char, radix: uint) -> Option<uint> {
}
///
/// Converts a number to the character representing it.
/// Converts a number to the character representing it
///
/// # Return value
///
@ -254,7 +284,7 @@ fn decompose_hangul(s: char, f: |char|) {
}
}
/// Returns the canonical decomposition of a character.
/// Returns the canonical decomposition of a character
pub fn decompose_canonical(c: char, f: |char|) {
if (c as uint) < S_BASE || (c as uint) >= (S_BASE + S_COUNT) {
decompose::canonical(c, f);
@ -263,7 +293,7 @@ pub fn decompose_canonical(c: char, f: |char|) {
}
}
/// Returns the compatibility decomposition of a character.
/// Returns the compatibility decomposition of a character
pub fn decompose_compatible(c: char, f: |char|) {
if (c as uint) < S_BASE || (c as uint) >= (S_BASE + S_COUNT) {
decompose::compatibility(c, f);
@ -273,7 +303,7 @@ pub fn decompose_compatible(c: char, f: |char|) {
}
///
/// Return the hexadecimal unicode escape of a char.
/// Returns the hexadecimal Unicode escape of a `char`
///
/// The rules are as follows:
///
@ -301,7 +331,7 @@ pub fn escape_unicode(c: char, f: |char|) {
}
///
/// Return a 'default' ASCII and C++11-like char-literal escape of a char.
/// Returns a 'default' ASCII and C++11-like literal escape of a `char`
///
/// 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
@ -325,7 +355,7 @@ pub fn escape_default(c: char, f: |char|) {
}
}
/// Returns the amount of bytes this character would need if encoded in utf8
/// Returns the amount of bytes this `char` would need if encoded in UTF-8
pub fn len_utf8_bytes(c: char) -> uint {
static MAX_ONE_B: uint = 128u;
static MAX_TWO_B: uint = 2048u;
@ -360,8 +390,9 @@ pub trait Char {
fn escape_default(&self, f: |char|);
fn len_utf8_bytes(&self) -> uint;
/// Encodes this character as utf-8 into the provided byte-buffer. The
/// buffer must be at least 4 bytes long or a runtime failure will occur.
/// Encodes this `char` as utf-8 into the provided byte-buffer
///
/// The buffer must be at least 4 bytes long or a runtime failure will occur.
///
/// This will then return the number of characters written to the slice.
fn encode_utf8(&self, dst: &mut [u8]) -> uint;