bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

auto merge of #6597 : bjz/rust/core-char, r=brson

Browse source
This commit is contained in:
bors 2013-05-18 17:13:27 -07:00
commit 24c2be3323
2 changed files with 277 additions and 184 deletions
Download patch file Download diff file Expand all files Collapse all files

460
src/libcore/char.rs
View file

@ -10,138 +10,144 @@
//! Utilities for manipulating the char type
#[cfg(not(test))]
use cmp::Ord;
use option::{None, Option, Some};
use str;
#[cfg(stage0)]
use str::StrSlice;
#[cfg(not(stage0))]
use str::{StrSlice, OwnedStr};
use u32;
use uint;
use unicode::{derived_property, general_category};
#[cfg(not(test))] use cmp::Eq;
#[cfg(not(test))]
use cmp::{Eq, Ord};
/*
Lu Uppercase_Letter an uppercase letter
Ll Lowercase_Letter a lowercase letter
Lt Titlecase_Letter a digraphic character, with first part uppercase
Lm Modifier_Letter a modifier letter
Lo Other_Letter other letters, including syllables and ideographs
Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
Mc Spacing_Mark a spacing combining mark (positive advance width)
Me Enclosing_Mark an enclosing combining mark
Nd Decimal_Number a decimal digit
Nl Letter_Number a letterlike numeric character
No Other_Number a numeric character of other type
Lu Uppercase_Letter an uppercase letter
Ll Lowercase_Letter a lowercase letter
Lt Titlecase_Letter a digraphic character, with first part uppercase
Lm Modifier_Letter a modifier letter
Lo Other_Letter other letters, including syllables and ideographs
Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
Mc Spacing_Mark a spacing combining mark (positive advance width)
Me Enclosing_Mark an enclosing combining mark
Nd Decimal_Number a decimal digit
Nl Letter_Number a letterlike numeric character
No Other_Number a numeric character of other type
Pc Connector_Punctuation a connecting punctuation mark, like a tie
Pd Dash_Punctuation a dash or hyphen punctuation mark
Ps Open_Punctuation an opening punctuation mark (of a pair)
Pe Close_Punctuation a closing punctuation mark (of a pair)
Pd Dash_Punctuation a dash or hyphen punctuation mark
Ps Open_Punctuation an opening punctuation mark (of a pair)
Pe Close_Punctuation a closing punctuation mark (of a pair)
Pi Initial_Punctuation an initial quotation mark
Pf Final_Punctuation a final quotation mark
Po Other_Punctuation a punctuation mark of other type
Sm Math_Symbol a symbol of primarily mathematical use
Sc Currency_Symbol a currency sign
Sk Modifier_Symbol a non-letterlike modifier symbol
So Other_Symbol a symbol of other type
Zs Space_Separator a space character (of various non-zero widths)
Zl Line_Separator U+2028 LINE SEPARATOR only
Pf Final_Punctuation a final quotation mark
Po Other_Punctuation a punctuation mark of other type
Sm Math_Symbol a symbol of primarily mathematical use
Sc Currency_Symbol a currency sign
Sk Modifier_Symbol a non-letterlike modifier symbol
So Other_Symbol a symbol of other type
Zs Space_Separator a space character (of various non-zero widths)
Zl Line_Separator U+2028 LINE SEPARATOR only
Zp Paragraph_Separator U+2029 PARAGRAPH SEPARATOR only
Cc Control a C0 or C1 control code
Cf Format a format control character
Cs Surrogate a surrogate code point
Co Private_Use a private-use character
Cn Unassigned a reserved unassigned code point or a noncharacter
Cc Control a C0 or C1 control code
Cf Format a format control character
Cs Surrogate a surrogate code point
Co Private_Use a private-use character
Cn Unassigned a reserved unassigned code point or a noncharacter
*/
pub fn is_alphabetic(c: char) -> bool { derived_property::Alphabetic(c) }
pub fn is_XID_start(c: char) -> bool { derived_property::XID_Start(c) }
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 General Category 'Ll'
*/
///
/// Indicates whether a character is in lower case, defined
/// in terms of the Unicode General Category 'Ll'
///
#[inline(always)]
pub fn is_lowercase(c: char) -> bool {
return general_category::Ll(c);
}
pub fn is_lowercase(c: char) -> bool { general_category::Ll(c) }
/**
* Indicates whether a character is in upper case, defined
* in terms of the Unicode General Category 'Lu'.
*/
///
/// Indicates whether a character is in upper case, defined
/// in terms of the Unicode General Category 'Lu'.
///
#[inline(always)]
pub fn is_uppercase(c: char) -> bool {
return general_category::Lu(c);
}
pub fn is_uppercase(c: char) -> bool { general_category::Lu(c) }
/**
* Indicates whether a character is whitespace. Whitespace is defined in
* terms of the Unicode General Categories 'Zs', 'Zl', 'Zp'
* additional 'Cc'-category control codes in the range [0x09, 0x0d]
*/
///
/// Indicates whether a character is whitespace. Whitespace is defined in
/// terms of the Unicode General Categories 'Zs', 'Zl', 'Zp'
/// additional 'Cc'-category control codes in the range [0x09, 0x0d]
///
#[inline(always)]
pub fn is_whitespace(c: char) -> bool {
return ('\x09' <= c && c <= '\x0d')
('\x09' <= c && c <= '\x0d')
|| general_category::Zs(c)
|| general_category::Zl(c)
|| general_category::Zp(c);
|| general_category::Zp(c)
}
/**
* 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 character is alphanumeric. Alphanumericness is
/// defined in terms of the Unicode General Categories 'Nd', 'Nl', 'No'
/// and the Derived Core Property 'Alphabetic'.
///
#[inline(always)]
pub fn is_alphanumeric(c: char) -> bool {
return derived_property::Alphabetic(c) ||
general_category::Nd(c) ||
general_category::Nl(c) ||
general_category::No(c);
derived_property::Alphabetic(c)
|| general_category::Nd(c)
|| general_category::Nl(c)
|| general_category::No(c)
}
/// Indicates whether the character is numeric (Nd, Nl, or No)
#[inline(always)]
pub fn is_digit(c: char) -> bool {
return general_category::Nd(c) ||
general_category::Nl(c) ||
general_category::No(c);
general_category::Nd(c)
|| general_category::Nl(c)
|| general_category::No(c)
}
/**
* Checks if a character 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`.
*
* Returns `true` if `c` is a valid digit under `radix`, and `false`
* otherwise.
*
* Fails if given a `radix` > 36.
*
* Note: This just wraps `to_digit()`.
*/
///
/// Checks if a character 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`.
///
/// # Return value
///
/// Returns `true` if `c` is a valid digit under `radix`, and `false`
/// otherwise.
///
/// # Failure
///
/// Fails if given a `radix` > 36.
///
/// # Note
///
/// This just wraps `to_digit()`.
///
#[inline(always)]
pub fn is_digit_radix(c: char, radix: uint) -> bool {
match to_digit(c, radix) {
Some(_) => true,
None => false
None => false,
}
}
/**
* Convert 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
* refer to a digit in the given radix.
*
* # Failure
* Fails if given a `radix` outside the range `[0..36]`.
*/
///
/// Convert 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
/// refer to a digit in the given radix.
///
/// # Failure
///
/// Fails if given a `radix` outside the range `[0..36]`.
///
#[inline]
pub fn to_digit(c: char, radix: uint) -> Option<uint> {
if radix > 36 {
@ -151,20 +157,24 @@ pub fn to_digit(c: char, radix: uint) -> Option<uint> {
'0' .. '9' => c as uint - ('0' as uint),
'a' .. 'z' => c as uint + 10u - ('a' as uint),
'A' .. 'Z' => c as uint + 10u - ('A' as uint),
_ => return None
_ => return None,
};
if val < radix { Some(val) }
else { None }
}
/**
* Converts a number to the character representing it.
*
* Returns `Some(char)` if `num` represents one digit under `radix`,
* using one character of `0-9` or `a-z`, or `None` if it doesn't.
*
* Fails if given an `radix` > 36.
*/
///
/// Converts a number to the character representing it.
///
/// # Return value
///
/// Returns `Some(char)` if `num` represents one digit under `radix`,
/// using one character of `0-9` or `a-z`, or `None` if it doesn't.
///
/// # Failure
///
/// Fails if given an `radix` > 36.
///
#[inline]
pub fn from_digit(num: uint, radix: uint) -> Option<char> {
if radix > 36 {
@ -181,15 +191,7 @@ pub fn from_digit(num: uint, radix: uint) -> Option<char> {
}
}
/**
* Return the hexadecimal unicode escape of a char.
*
* The rules are as follows:
*
* - chars in [0,0xff] get 2-digit escapes: `\\xNN`
* - chars in [0x100,0xffff] get 4-digit escapes: `\\uNNNN`
* - chars above 0x10000 get 8-digit escapes: `\\UNNNNNNNN`
*/
#[cfg(stage0)]
pub fn escape_unicode(c: char) -> ~str {
let s = u32::to_str_radix(c as u32, 16u);
let (c, pad) = (if c <= '\xff' { ('x', 2u) }
@ -204,32 +206,59 @@ pub fn escape_unicode(c: char) -> ~str {
out
}
/**
* Return a 'default' ASCII and C++11-like char-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
* 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 unicode escapes; see `escape_unicode`.
*/
///
/// Return the hexadecimal unicode escape of a char.
///
/// The rules are as follows:
///
/// - chars in [0,0xff] get 2-digit escapes: `\\xNN`
/// - chars in [0x100,0xffff] get 4-digit escapes: `\\uNNNN`
/// - chars above 0x10000 get 8-digit escapes: `\\UNNNNNNNN`
///
#[cfg(not(stage0))]
pub fn escape_unicode(c: char) -> ~str {
let s = u32::to_str_radix(c as u32, 16u);
let (c, pad) = cond!(
(c <= '\xff') { ('x', 2u) }
(c <= '\uffff') { ('u', 4u) }
_ { ('U', 8u) }
);
assert!(s.len() <= pad);
let mut out = ~"\\";
out.push_str(str::from_char(c));
for uint::range(s.len(), pad) |_| {
out.push_str("0");
}
out.push_str(s);
out
}
///
/// Return a 'default' ASCII and C++11-like char-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
/// 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 unicode escapes; see `escape_unicode`.
///
pub fn escape_default(c: char) -> ~str {
match c {
'\t' => ~"\\t",
'\r' => ~"\\r",
'\n' => ~"\\n",
'\\' => ~"\\\\",
'\'' => ~"\\'",
'"' => ~"\\\"",
'\x20' .. '\x7e' => str::from_char(c),
_ => escape_unicode(c)
'\t' => ~"\\t",
'\r' => ~"\\r",
'\n' => ~"\\n",
'\\' => ~"\\\\",
'\'' => ~"\\'",
'"' => ~"\\\"",
'\x20' .. '\x7e' => str::from_char(c),
_ => c.escape_unicode(),
}
}
/// Returns the amount of bytes this character would need if encoded in utf8
#[cfg(stage0)]
pub fn len_utf8_bytes(c: char) -> uint {
static max_one_b: uint = 128u;
static max_two_b: uint = 2048u;
@ -244,6 +273,71 @@ pub fn len_utf8_bytes(c: char) -> uint {
else { fail!("invalid character!") }
}
/// Returns the amount of bytes this character would need if encoded in utf8
#[cfg(not(stage0))]
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;
cond!(
(code < MAX_ONE_B) { 1u }
(code < MAX_TWO_B) { 2u }
(code < MAX_THREE_B) { 3u }
(code < MAX_FOUR_B) { 4u }
_ { fail!("invalid character!") }
)
}
pub trait Char {
fn is_alphabetic(&self) -> bool;
fn is_XID_start(&self) -> bool;
fn is_XID_continue(&self) -> bool;
fn is_lowercase(&self) -> bool;
fn is_uppercase(&self) -> bool;
fn is_whitespace(&self) -> bool;
fn is_alphanumeric(&self) -> bool;
fn is_digit(&self) -> bool;
fn is_digit_radix(&self, radix: uint) -> bool;
fn to_digit(&self, radix: uint) -> Option<uint>;
fn from_digit(num: uint, radix: uint) -> Option<char>;
fn escape_unicode(&self) -> ~str;
fn escape_default(&self) -> ~str;
fn len_utf8_bytes(&self) -> uint;
}
impl Char for char {
fn is_alphabetic(&self) -> bool { is_alphabetic(*self) }
fn is_XID_start(&self) -> bool { is_XID_start(*self) }
fn is_XID_continue(&self) -> bool { is_XID_continue(*self) }
fn is_lowercase(&self) -> bool { is_lowercase(*self) }
fn is_uppercase(&self) -> bool { is_uppercase(*self) }
fn is_whitespace(&self) -> bool { is_whitespace(*self) }
fn is_alphanumeric(&self) -> bool { is_alphanumeric(*self) }
fn is_digit(&self) -> bool { is_digit(*self) }
fn is_digit_radix(&self, radix: uint) -> bool { is_digit_radix(*self, radix) }
fn to_digit(&self, radix: uint) -> Option<uint> { to_digit(*self, radix) }
fn from_digit(num: uint, radix: uint) -> Option<char> { from_digit(num, radix) }
fn escape_unicode(&self) -> ~str { escape_unicode(*self) }
fn escape_default(&self) -> ~str { escape_default(*self) }
fn len_utf8_bytes(&self) -> uint { len_utf8_bytes(*self) }
}
#[cfg(not(test))]
impl Eq for char {
#[inline(always)]
@ -266,84 +360,82 @@ impl Ord for char {
#[test]
fn test_is_lowercase() {
assert!(is_lowercase('a'));
assert!(is_lowercase('ö'));
assert!(is_lowercase('ß'));
assert!(!is_lowercase('Ü'));
assert!(!is_lowercase('P'));
assert!('a'.is_lowercase());
assert!('ö'.is_lowercase());
assert!('ß'.is_lowercase());
assert!(!'Ü'.is_lowercase());
assert!(!'P'.is_lowercase());
}
#[test]
fn test_is_uppercase() {
assert!(!is_uppercase('h'));
assert!(!is_uppercase('ä'));
assert!(!is_uppercase('ß'));
assert!(is_uppercase('Ö'));
assert!(is_uppercase('T'));
assert!(!'h'.is_uppercase());
assert!(!'ä'.is_uppercase());
assert!(!'ß'.is_uppercase());
assert!('Ö'.is_uppercase());
assert!('T'.is_uppercase());
}
#[test]
fn test_is_whitespace() {
assert!(is_whitespace(' '));
assert!(is_whitespace('\u2007'));
assert!(is_whitespace('\t'));
assert!(is_whitespace('\n'));
assert!(!is_whitespace('a'));
assert!(!is_whitespace('_'));
assert!(!is_whitespace('\u0000'));
assert!(' '.is_whitespace());
assert!('\u2007'.is_whitespace());
assert!('\t'.is_whitespace());
assert!('\n'.is_whitespace());
assert!(!'a'.is_whitespace());
assert!(!'_'.is_whitespace());
assert!(!'\u0000'.is_whitespace());
}
#[test]
fn test_to_digit() {
assert_eq!(to_digit('0', 10u), Some(0u));
assert_eq!(to_digit('1', 2u), Some(1u));
assert_eq!(to_digit('2', 3u), Some(2u));
assert_eq!(to_digit('9', 10u), Some(9u));
assert_eq!(to_digit('a', 16u), Some(10u));
assert_eq!(to_digit('A', 16u), Some(10u));
assert_eq!(to_digit('b', 16u), Some(11u));
assert_eq!(to_digit('B', 16u), Some(11u));
assert_eq!(to_digit('z', 36u), Some(35u));
assert_eq!(to_digit('Z', 36u), Some(35u));
assert!(to_digit(' ', 10u).is_none());
assert!(to_digit('$', 36u).is_none());
assert_eq!('0'.to_digit(10u), Some(0u));
assert_eq!('1'.to_digit(2u), Some(1u));
assert_eq!('2'.to_digit(3u), Some(2u));
assert_eq!('9'.to_digit(10u), Some(9u));
assert_eq!('a'.to_digit(16u), Some(10u));
assert_eq!('A'.to_digit(16u), Some(10u));
assert_eq!('b'.to_digit(16u), Some(11u));
assert_eq!('B'.to_digit(16u), Some(11u));
assert_eq!('z'.to_digit(36u), Some(35u));
assert_eq!('Z'.to_digit(36u), Some(35u));
assert_eq!(' '.to_digit(10u), None);
assert_eq!('$'.to_digit(36u), None);
}
#[test]
fn test_is_digit() {
assert!(is_digit('2'));
assert!(is_digit('7'));
assert!(! is_digit('c'));
assert!(! is_digit('i'));
assert!(! is_digit('z'));
assert!(! is_digit('Q'));
assert!('2'.is_digit());
assert!('7'.is_digit());
assert!(!'c'.is_digit());
assert!(!'i'.is_digit());
assert!(!'z'.is_digit());
assert!(!'Q'.is_digit());
}
#[test]
fn test_escape_default() {
assert_eq!(escape_default('\n'), ~"\\n");
assert_eq!(escape_default('\r'), ~"\\r");
assert_eq!(escape_default('\''), ~"\\'");
assert_eq!(escape_default('"'), ~"\\\"");
assert_eq!(escape_default(' '), ~" ");
assert_eq!(escape_default('a'), ~"a");
assert_eq!(escape_default('~'), ~"~");
assert_eq!(escape_default('\x00'), ~"\\x00");
assert_eq!(escape_default('\x1f'), ~"\\x1f");
assert_eq!(escape_default('\x7f'), ~"\\x7f");
assert_eq!(escape_default('\xff'), ~"\\xff");
assert_eq!(escape_default('\u011b'), ~"\\u011b");
assert_eq!(escape_default('\U0001d4b6'), ~"\\U0001d4b6");
assert_eq!('\n'.escape_default(), ~"\\n");
assert_eq!('\r'.escape_default(), ~"\\r");
assert_eq!('\''.escape_default(), ~"\\'");
assert_eq!('"'.escape_default(), ~"\\\"");
assert_eq!(' '.escape_default(), ~" ");
assert_eq!('a'.escape_default(), ~"a");
assert_eq!('~'.escape_default(), ~"~");
assert_eq!('\x00'.escape_default(), ~"\\x00");
assert_eq!('\x1f'.escape_default(), ~"\\x1f");
assert_eq!('\x7f'.escape_default(), ~"\\x7f");
assert_eq!('\xff'.escape_default(), ~"\\xff");
assert_eq!('\u011b'.escape_default(), ~"\\u011b");
assert_eq!('\U0001d4b6'.escape_default(), ~"\\U0001d4b6");
}
#[test]
fn test_escape_unicode() {
assert_eq!(escape_unicode('\x00'), ~"\\x00");
assert_eq!(escape_unicode('\n'), ~"\\x0a");
assert_eq!(escape_unicode(' '), ~"\\x20");
assert_eq!(escape_unicode('a'), ~"\\x61");
assert_eq!(escape_unicode('\u011b'), ~"\\u011b");
assert_eq!(escape_unicode('\U0001d4b6'), ~"\\U0001d4b6");
assert_eq!('\x00'.escape_unicode(), ~"\\x00");
assert_eq!('\n'.escape_unicode(), ~"\\x0a");
assert_eq!(' '.escape_unicode(), ~"\\x20");
assert_eq!('a'.escape_unicode(), ~"\\x61");
assert_eq!('\u011b'.escape_unicode(), ~"\\u011b");
assert_eq!('\U0001d4b6'.escape_unicode(), ~"\\U0001d4b6");
}

1
src/libcore/prelude.rs
View file

@ -29,6 +29,7 @@ pub use io::{print, println};
pub use clone::{Clone, DeepClone};
pub use cmp::{Eq, ApproxEq, Ord, TotalEq, TotalOrd, Ordering, Less, Equal, Greater, Equiv};
pub use char::Char;
pub use container::{Container, Mutable, Map, Set};
pub use hash::Hash;
pub use old_iter::{BaseIter, ReverseIter, MutableIter, ExtendedIter, EqIter};