1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
// Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT // file at the top-level directory of this distribution and at // http://rust-lang.org/COPYRIGHT. // // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your // option. This file may not be copied, modified, or distributed // except according to those terms. //! Character manipulation. //! //! For more details, see ::unicode::char (a.k.a. std::char) #![allow(non_snake_case)] #![doc(primitive = "char")] use mem::transmute; use option::{None, Option, Some}; use iter::range_step; use slice::SlicePrelude; // UTF-8 ranges and tags for encoding characters static TAG_CONT: u8 = 0b1000_0000u8; static TAG_TWO_B: u8 = 0b1100_0000u8; static TAG_THREE_B: u8 = 0b1110_0000u8; static TAG_FOUR_B: u8 = 0b1111_0000u8; static MAX_ONE_B: u32 = 0x80u32; static MAX_TWO_B: u32 = 0x800u32; static MAX_THREE_B: u32 = 0x10000u32; /* 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) 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 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 */ /// The highest valid code point pub const MAX: char = '\U0010ffff'; /// Converts from `u32` to a `char` #[inline] pub fn from_u32(i: u32) -> Option<char> { // catch out-of-bounds and surrogates if (i > MAX as u32) || (i >= 0xD800 && i <= 0xDFFF) { None } else { Some(unsafe { transmute(i) }) } } /// /// 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`. /// /// # Return value /// /// Returns `true` if `c` is a valid digit under `radix`, and `false` /// otherwise. /// /// # Panics /// /// Panics if given a `radix` > 36. /// /// # Note /// /// This just wraps `to_digit()`. /// #[inline] pub fn is_digit_radix(c: char, radix: uint) -> bool { match to_digit(c, radix) { Some(_) => true, None => false, } } /// /// 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 /// refer to a digit in the given radix. /// /// # Panics /// /// Panics if given a `radix` outside the range `[0..36]`. /// #[inline] pub fn to_digit(c: char, radix: uint) -> Option<uint> { if radix > 36 { panic!("to_digit: radix is too high (maximum 36)"); } let val = match c { '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, }; if val < radix { Some(val) } else { None } } /// /// 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. /// /// # Panics /// /// Panics if given an `radix` > 36. /// #[inline] pub fn from_digit(num: uint, radix: uint) -> Option<char> { if radix > 36 { panic!("from_digit: radix is to high (maximum 36)"); } if num < radix { unsafe { if num < 10 { Some(transmute(('0' as uint + num) as u32)) } else { Some(transmute(('a' as uint + num - 10u) as u32)) } } } else { None } } /// /// Returns 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` /// pub fn escape_unicode(c: char, f: |char|) { // avoid calling str::to_str_radix because we don't really need to allocate // here. f('\\'); let pad = match () { _ if c <= '\x7f' => { f('x'); 2 } _ if c <= '\uffff' => { f('u'); 4 } _ => { f('U'); 8 } }; for offset in range_step::<i32>(4 * (pad - 1), -1, -4) { let offset = offset as uint; unsafe { match ((c as i32) >> offset) & 0xf { i @ 0 ... 9 => { f(transmute('0' as i32 + i)); } i => { f(transmute('a' as i32 + (i - 10))); } } } } } /// /// 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 /// 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, f: |char|) { match c { '\t' => { f('\\'); f('t'); } '\r' => { f('\\'); f('r'); } '\n' => { f('\\'); f('n'); } '\\' => { f('\\'); f('\\'); } '\'' => { f('\\'); f('\''); } '"' => { f('\\'); f('"'); } '\x20' ... '\x7e' => { f(c); } _ => c.escape_unicode(f), } } /// Returns the amount of bytes this `char` would need if encoded in UTF-8 #[inline] pub fn len_utf8_bytes(c: char) -> uint { let code = c as u32; match () { _ if code < MAX_ONE_B => 1u, _ if code < MAX_TWO_B => 2u, _ if code < MAX_THREE_B => 3u, _ => 4u, } } /// Basic `char` manipulations. pub trait Char { /// 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`. /// /// # Return value /// /// Returns `true` if `c` is a valid digit under `radix`, and `false` /// otherwise. /// /// # Panics /// /// Panics if given a radix > 36. fn is_digit_radix(&self, radix: uint) -> bool; /// Converts a character 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 character does not refer to a digit in the given radix. /// /// # Panics /// /// Panics if given a radix outside the range [0..36]. fn to_digit(&self, radix: uint) -> Option<uint>; /// 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. /// /// # Panics /// /// Panics if given a radix > 36. fn from_digit(num: uint, radix: uint) -> Option<Self>; /// Returns the hexadecimal Unicode escape of a character. /// /// The rules are as follows: /// /// * Characters in [0,0xff] get 2-digit escapes: `\\xNN` /// * Characters in [0x100,0xffff] get 4-digit escapes: `\\uNNNN`. /// * Characters above 0x10000 get 8-digit escapes: `\\UNNNNNNNN`. fn escape_unicode(&self, f: |char|); /// Returns a 'default' ASCII and C++11-like literal escape of a /// character. /// /// 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`. fn escape_default(&self, f: |char|); /// Returns the amount of bytes this character would need if encoded in /// UTF-8. fn len_utf8_bytes(&self) -> uint; /// Encodes this character as UTF-8 into the provided byte buffer, /// and then returns the number of bytes written. /// /// If the buffer is not large enough, nothing will be written into it /// and a `None` will be returned. fn encode_utf8(&self, dst: &mut [u8]) -> Option<uint>; /// Encodes this character as UTF-16 into the provided `u16` buffer, /// and then returns the number of `u16`s written. /// /// If the buffer is not large enough, nothing will be written into it /// and a `None` will be returned. fn encode_utf16(&self, dst: &mut [u16]) -> Option<uint>; } impl Char for char { 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, f: |char|) { escape_unicode(*self, f) } fn escape_default(&self, f: |char|) { escape_default(*self, f) } #[inline] fn len_utf8_bytes(&self) -> uint { len_utf8_bytes(*self) } #[inline] fn encode_utf8<'a>(&self, dst: &'a mut [u8]) -> Option<uint> { // Marked #[inline] to allow llvm optimizing it away let code = *self as u32; if code < MAX_ONE_B && dst.len() >= 1 { dst[0] = code as u8; Some(1) } else if code < MAX_TWO_B && dst.len() >= 2 { dst[0] = (code >> 6u & 0x1F_u32) as u8 | TAG_TWO_B; dst[1] = (code & 0x3F_u32) as u8 | TAG_CONT; Some(2) } else if code < MAX_THREE_B && dst.len() >= 3 { dst[0] = (code >> 12u & 0x0F_u32) as u8 | TAG_THREE_B; dst[1] = (code >> 6u & 0x3F_u32) as u8 | TAG_CONT; dst[2] = (code & 0x3F_u32) as u8 | TAG_CONT; Some(3) } else if dst.len() >= 4 { dst[0] = (code >> 18u & 0x07_u32) as u8 | TAG_FOUR_B; dst[1] = (code >> 12u & 0x3F_u32) as u8 | TAG_CONT; dst[2] = (code >> 6u & 0x3F_u32) as u8 | TAG_CONT; dst[3] = (code & 0x3F_u32) as u8 | TAG_CONT; Some(4) } else { None } } #[inline] fn encode_utf16(&self, dst: &mut [u16]) -> Option<uint> { // Marked #[inline] to allow llvm optimizing it away let mut ch = *self as u32; if (ch & 0xFFFF_u32) == ch && dst.len() >= 1 { // The BMP falls through (assuming non-surrogate, as it should) dst[0] = ch as u16; Some(1) } else if dst.len() >= 2 { // Supplementary planes break into surrogates. ch -= 0x1_0000_u32; dst[0] = 0xD800_u16 | ((ch >> 10) as u16); dst[1] = 0xDC00_u16 | ((ch as u16) & 0x3FF_u16); Some(2) } else { None } } }