1 // Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT
2 // file at the top-level directory of this distribution and at
3 // http://rust-lang.org/COPYRIGHT.
5 // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
6 // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
7 // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
8 // option. This file may not be copied, modified, or distributed
9 // except according to those terms.
11 //! Character manipulation.
13 //! For more details, see ::rustc_unicode::char (a.k.a. std::char)
15 #![allow(non_snake_case)]
16 #![stable(feature = "core_char", since = "1.2.0")]
20 use option::Option::{None, Some};
24 // UTF-8 ranges and tags for encoding characters
25 const TAG_CONT: u8 = 0b1000_0000;
26 const TAG_TWO_B: u8 = 0b1100_0000;
27 const TAG_THREE_B: u8 = 0b1110_0000;
28 const TAG_FOUR_B: u8 = 0b1111_0000;
29 const MAX_ONE_B: u32 = 0x80;
30 const MAX_TWO_B: u32 = 0x800;
31 const MAX_THREE_B: u32 = 0x10000;
34 Lu Uppercase_Letter an uppercase letter
35 Ll Lowercase_Letter a lowercase letter
36 Lt Titlecase_Letter a digraphic character, with first part uppercase
37 Lm Modifier_Letter a modifier letter
38 Lo Other_Letter other letters, including syllables and ideographs
39 Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
40 Mc Spacing_Mark a spacing combining mark (positive advance width)
41 Me Enclosing_Mark an enclosing combining mark
42 Nd Decimal_Number a decimal digit
43 Nl Letter_Number a letterlike numeric character
44 No Other_Number a numeric character of other type
45 Pc Connector_Punctuation a connecting punctuation mark, like a tie
46 Pd Dash_Punctuation a dash or hyphen punctuation mark
47 Ps Open_Punctuation an opening punctuation mark (of a pair)
48 Pe Close_Punctuation a closing punctuation mark (of a pair)
49 Pi Initial_Punctuation an initial quotation mark
50 Pf Final_Punctuation a final quotation mark
51 Po Other_Punctuation a punctuation mark of other type
52 Sm Math_Symbol a symbol of primarily mathematical use
53 Sc Currency_Symbol a currency sign
54 Sk Modifier_Symbol a non-letterlike modifier symbol
55 So Other_Symbol a symbol of other type
56 Zs Space_Separator a space character (of various non-zero widths)
57 Zl Line_Separator U+2028 LINE SEPARATOR only
58 Zp Paragraph_Separator U+2029 PARAGRAPH SEPARATOR only
59 Cc Control a C0 or C1 control code
60 Cf Format a format control character
61 Cs Surrogate a surrogate code point
62 Co Private_Use a private-use character
63 Cn Unassigned a reserved unassigned code point or a noncharacter
66 /// The highest valid code point
67 #[stable(feature = "rust1", since = "1.0.0")]
68 pub const MAX: char = '\u{10ffff}';
70 /// Converts a `u32` to an `Option<char>`.
77 /// assert_eq!(char::from_u32(0x2764), Some('❤'));
78 /// assert_eq!(char::from_u32(0x110000), None); // invalid character
81 #[stable(feature = "rust1", since = "1.0.0")]
82 pub fn from_u32(i: u32) -> Option<char> {
83 // catch out-of-bounds and surrogates
84 if (i > MAX as u32) || (i >= 0xD800 && i <= 0xDFFF) {
87 Some(unsafe { from_u32_unchecked(i) })
91 /// Converts a `u32` to an `char`, not checking whether it is a valid unicode
94 #[stable(feature = "char_from_unchecked", since = "1.5.0")]
95 pub unsafe fn from_u32_unchecked(i: u32) -> char {
99 /// Converts a number to the character representing it.
103 /// Returns `Some(char)` if `num` represents one digit under `radix`,
104 /// using one character of `0-9` or `a-z`, or `None` if it doesn't.
108 /// Panics if given an `radix` > 36.
115 /// let c = char::from_digit(4, 10);
117 /// assert_eq!(c, Some('4'));
120 #[stable(feature = "rust1", since = "1.0.0")]
121 pub fn from_digit(num: u32, radix: u32) -> Option<char> {
123 panic!("from_digit: radix is too high (maximum 36)");
128 Some((b'0' + num) as char)
130 Some((b'a' + num - 10) as char)
137 // NB: the stabilization and documentation for this trait is in
138 // unicode/char.rs, not here
139 #[allow(missing_docs)] // docs in libunicode/u_char.rs
141 #[unstable(feature = "core_char_ext",
142 reason = "the stable interface is `impl char` in later crate",
145 fn is_digit(self, radix: u32) -> bool;
146 fn to_digit(self, radix: u32) -> Option<u32>;
147 fn escape_unicode(self) -> EscapeUnicode;
148 fn escape_default(self) -> EscapeDefault;
149 fn len_utf8(self) -> usize;
150 fn len_utf16(self) -> usize;
151 fn encode_utf8(self, dst: &mut [u8]) -> Option<usize>;
152 fn encode_utf16(self, dst: &mut [u16]) -> Option<usize>;
155 impl CharExt for char {
157 fn is_digit(self, radix: u32) -> bool {
158 self.to_digit(radix).is_some()
162 fn to_digit(self, radix: u32) -> Option<u32> {
164 panic!("to_digit: radix is too high (maximum 36)");
166 let val = match self {
167 '0' ... '9' => self as u32 - '0' as u32,
168 'a' ... 'z' => self as u32 - 'a' as u32 + 10,
169 'A' ... 'Z' => self as u32 - 'A' as u32 + 10,
172 if val < radix { Some(val) }
177 fn escape_unicode(self) -> EscapeUnicode {
178 EscapeUnicode { c: self, state: EscapeUnicodeState::Backslash }
182 fn escape_default(self) -> EscapeDefault {
183 let init_state = match self {
184 '\t' => EscapeDefaultState::Backslash('t'),
185 '\r' => EscapeDefaultState::Backslash('r'),
186 '\n' => EscapeDefaultState::Backslash('n'),
187 '\\' | '\'' | '"' => EscapeDefaultState::Backslash(self),
188 '\x20' ... '\x7e' => EscapeDefaultState::Char(self),
189 _ => EscapeDefaultState::Unicode(self.escape_unicode())
191 EscapeDefault { state: init_state }
195 fn len_utf8(self) -> usize {
196 let code = self as u32;
197 if code < MAX_ONE_B {
199 } else if code < MAX_TWO_B {
201 } else if code < MAX_THREE_B {
209 fn len_utf16(self) -> usize {
210 let ch = self as u32;
211 if (ch & 0xFFFF) == ch { 1 } else { 2 }
215 fn encode_utf8(self, dst: &mut [u8]) -> Option<usize> {
216 encode_utf8_raw(self as u32, dst)
220 fn encode_utf16(self, dst: &mut [u16]) -> Option<usize> {
221 encode_utf16_raw(self as u32, dst)
225 /// Encodes a raw u32 value as UTF-8 into the provided byte buffer,
226 /// and then returns the number of bytes written.
228 /// If the buffer is not large enough, nothing will be written into it
229 /// and a `None` will be returned.
231 #[unstable(feature = "char_internals",
232 reason = "this function should not be exposed publicly",
235 pub fn encode_utf8_raw(code: u32, dst: &mut [u8]) -> Option<usize> {
236 // Marked #[inline] to allow llvm optimizing it away
237 if code < MAX_ONE_B && !dst.is_empty() {
240 } else if code < MAX_TWO_B && dst.len() >= 2 {
241 dst[0] = (code >> 6 & 0x1F) as u8 | TAG_TWO_B;
242 dst[1] = (code & 0x3F) as u8 | TAG_CONT;
244 } else if code < MAX_THREE_B && dst.len() >= 3 {
245 dst[0] = (code >> 12 & 0x0F) as u8 | TAG_THREE_B;
246 dst[1] = (code >> 6 & 0x3F) as u8 | TAG_CONT;
247 dst[2] = (code & 0x3F) as u8 | TAG_CONT;
249 } else if dst.len() >= 4 {
250 dst[0] = (code >> 18 & 0x07) as u8 | TAG_FOUR_B;
251 dst[1] = (code >> 12 & 0x3F) as u8 | TAG_CONT;
252 dst[2] = (code >> 6 & 0x3F) as u8 | TAG_CONT;
253 dst[3] = (code & 0x3F) as u8 | TAG_CONT;
260 /// Encodes a raw u32 value as UTF-16 into the provided `u16` buffer,
261 /// and then returns the number of `u16`s written.
263 /// If the buffer is not large enough, nothing will be written into it
264 /// and a `None` will be returned.
266 #[unstable(feature = "char_internals",
267 reason = "this function should not be exposed publicly",
270 pub fn encode_utf16_raw(mut ch: u32, dst: &mut [u16]) -> Option<usize> {
271 // Marked #[inline] to allow llvm optimizing it away
272 if (ch & 0xFFFF) == ch && !dst.is_empty() {
273 // The BMP falls through (assuming non-surrogate, as it should)
276 } else if dst.len() >= 2 {
277 // Supplementary planes break into surrogates.
279 dst[0] = 0xD800 | ((ch >> 10) as u16);
280 dst[1] = 0xDC00 | ((ch as u16) & 0x3FF);
287 /// An iterator over the characters that represent a `char`, as escaped by
288 /// Rust's unicode escaping rules.
290 #[stable(feature = "rust1", since = "1.0.0")]
291 pub struct EscapeUnicode {
293 state: EscapeUnicodeState
297 enum EscapeUnicodeState {
306 #[stable(feature = "rust1", since = "1.0.0")]
307 impl Iterator for EscapeUnicode {
310 fn next(&mut self) -> Option<char> {
312 EscapeUnicodeState::Backslash => {
313 self.state = EscapeUnicodeState::Type;
316 EscapeUnicodeState::Type => {
317 self.state = EscapeUnicodeState::LeftBrace;
320 EscapeUnicodeState::LeftBrace => {
322 while (self.c as u32) >> (4 * (n + 1)) != 0 {
325 self.state = EscapeUnicodeState::Value(n);
328 EscapeUnicodeState::Value(offset) => {
329 let c = from_digit(((self.c as u32) >> (offset * 4)) & 0xf, 16).unwrap();
331 self.state = EscapeUnicodeState::RightBrace;
333 self.state = EscapeUnicodeState::Value(offset - 1);
337 EscapeUnicodeState::RightBrace => {
338 self.state = EscapeUnicodeState::Done;
341 EscapeUnicodeState::Done => None,
345 fn size_hint(&self) -> (usize, Option<usize>) {
347 while (self.c as usize) >> (4 * (n + 1)) != 0 {
350 let n = match self.state {
351 EscapeUnicodeState::Backslash => n + 5,
352 EscapeUnicodeState::Type => n + 4,
353 EscapeUnicodeState::LeftBrace => n + 3,
354 EscapeUnicodeState::Value(offset) => offset + 2,
355 EscapeUnicodeState::RightBrace => 1,
356 EscapeUnicodeState::Done => 0,
362 /// An iterator over the characters that represent a `char`, escaped
363 /// for maximum portability.
365 #[stable(feature = "rust1", since = "1.0.0")]
366 pub struct EscapeDefault {
367 state: EscapeDefaultState
371 enum EscapeDefaultState {
375 Unicode(EscapeUnicode),
378 #[stable(feature = "rust1", since = "1.0.0")]
379 impl Iterator for EscapeDefault {
382 fn next(&mut self) -> Option<char> {
384 EscapeDefaultState::Backslash(c) => {
385 self.state = EscapeDefaultState::Char(c);
388 EscapeDefaultState::Char(c) => {
389 self.state = EscapeDefaultState::Done;
392 EscapeDefaultState::Done => None,
393 EscapeDefaultState::Unicode(ref mut iter) => iter.next(),
397 fn size_hint(&self) -> (usize, Option<usize>) {
399 EscapeDefaultState::Char(_) => (1, Some(1)),
400 EscapeDefaultState::Backslash(_) => (2, Some(2)),
401 EscapeDefaultState::Unicode(ref iter) => iter.size_hint(),
402 EscapeDefaultState::Done => (0, Some(0)),