3 //! The `char` type represents a single character. More specifically, since
4 //! 'character' isn't a well-defined concept in Unicode, `char` is a '[Unicode
5 //! scalar value]', which is similar to, but not the same as, a '[Unicode code
8 //! [Unicode scalar value]: http://www.unicode.org/glossary/#unicode_scalar_value
9 //! [Unicode code point]: http://www.unicode.org/glossary/#code_point
11 //! This module exists for technical reasons, the primary documentation for
12 //! `char` is directly on [the `char` primitive type](../../std/primitive.char.html)
15 //! This module is the home of the iterator implementations for the iterators
16 //! implemented on `char`, as well as some useful constants and conversion
17 //! functions that convert various types to `char`.
19 #![allow(non_snake_case)]
20 #![stable(feature = "core_char", since = "1.2.0")]
27 #[stable(feature = "char_from_unchecked", since = "1.5.0")]
28 pub use self::convert::from_u32_unchecked;
29 #[stable(feature = "try_from", since = "1.34.0")]
30 pub use self::convert::CharTryFromError;
31 #[stable(feature = "char_from_str", since = "1.20.0")]
32 pub use self::convert::ParseCharError;
33 #[stable(feature = "rust1", since = "1.0.0")]
34 pub use self::convert::{from_digit, from_u32};
35 #[stable(feature = "decode_utf16", since = "1.9.0")]
36 pub use self::decode::{decode_utf16, DecodeUtf16, DecodeUtf16Error};
37 #[stable(feature = "unicode_version", since = "1.45.0")]
38 pub use crate::unicode::UNICODE_VERSION;
40 use crate::fmt::{self, Write};
41 use crate::iter::FusedIterator;
43 // UTF-8 ranges and tags for encoding characters
44 const TAG_CONT: u8 = 0b1000_0000;
45 const TAG_TWO_B: u8 = 0b1100_0000;
46 const TAG_THREE_B: u8 = 0b1110_0000;
47 const TAG_FOUR_B: u8 = 0b1111_0000;
48 const MAX_ONE_B: u32 = 0x80;
49 const MAX_TWO_B: u32 = 0x800;
50 const MAX_THREE_B: u32 = 0x10000;
53 Lu Uppercase_Letter an uppercase letter
54 Ll Lowercase_Letter a lowercase letter
55 Lt Titlecase_Letter a digraphic character, with first part uppercase
56 Lm Modifier_Letter a modifier letter
57 Lo Other_Letter other letters, including syllables and ideographs
58 Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
59 Mc Spacing_Mark a spacing combining mark (positive advance width)
60 Me Enclosing_Mark an enclosing combining mark
61 Nd Decimal_Number a decimal digit
62 Nl Letter_Number a letterlike numeric character
63 No Other_Number a numeric character of other type
64 Pc Connector_Punctuation a connecting punctuation mark, like a tie
65 Pd Dash_Punctuation a dash or hyphen punctuation mark
66 Ps Open_Punctuation an opening punctuation mark (of a pair)
67 Pe Close_Punctuation a closing punctuation mark (of a pair)
68 Pi Initial_Punctuation an initial quotation mark
69 Pf Final_Punctuation a final quotation mark
70 Po Other_Punctuation a punctuation mark of other type
71 Sm Math_Symbol a symbol of primarily mathematical use
72 Sc Currency_Symbol a currency sign
73 Sk Modifier_Symbol a non-letterlike modifier symbol
74 So Other_Symbol a symbol of other type
75 Zs Space_Separator a space character (of various non-zero widths)
76 Zl Line_Separator U+2028 LINE SEPARATOR only
77 Zp Paragraph_Separator U+2029 PARAGRAPH SEPARATOR only
78 Cc Control a C0 or C1 control code
79 Cf Format a format control character
80 Cs Surrogate a surrogate code point
81 Co Private_Use a private-use character
82 Cn Unassigned a reserved unassigned code point or a noncharacter
85 /// The highest valid code point a `char` can have.
87 /// A [`char`] is a [Unicode Scalar Value], which means that it is a [Code
88 /// Point], but only ones within a certain range. `MAX` is the highest valid
89 /// code point that's a valid [Unicode Scalar Value].
91 /// [`char`]: ../../std/primitive.char.html
92 /// [Unicode Scalar Value]: http://www.unicode.org/glossary/#unicode_scalar_value
93 /// [Code Point]: http://www.unicode.org/glossary/#code_point
94 #[stable(feature = "rust1", since = "1.0.0")]
95 pub const MAX: char = '\u{10ffff}';
97 /// `U+FFFD REPLACEMENT CHARACTER` (�) is used in Unicode to represent a
100 /// It can occur, for example, when giving ill-formed UTF-8 bytes to
101 /// [`String::from_utf8_lossy`](../../std/string/struct.String.html#method.from_utf8_lossy).
102 #[stable(feature = "decode_utf16", since = "1.9.0")]
103 pub const REPLACEMENT_CHARACTER: char = '\u{FFFD}';
105 /// Returns an iterator that yields the hexadecimal Unicode escape of a
106 /// character, as `char`s.
108 /// This `struct` is created by the [`escape_unicode`] method on [`char`]. See
109 /// its documentation for more.
111 /// [`escape_unicode`]: ../../std/primitive.char.html#method.escape_unicode
112 /// [`char`]: ../../std/primitive.char.html
113 #[derive(Clone, Debug)]
114 #[stable(feature = "rust1", since = "1.0.0")]
115 pub struct EscapeUnicode {
117 state: EscapeUnicodeState,
119 // The index of the next hex digit to be printed (0 if none),
120 // i.e., the number of remaining hex digits to be printed;
121 // increasing from the least significant digit: 0x543210
122 hex_digit_idx: usize,
125 // The enum values are ordered so that their representation is the
126 // same as the remaining length (besides the hexadecimal digits). This
127 // likely makes `len()` a single load from memory) and inline-worth.
128 #[derive(Clone, Debug)]
129 enum EscapeUnicodeState {
138 #[stable(feature = "rust1", since = "1.0.0")]
139 impl Iterator for EscapeUnicode {
142 fn next(&mut self) -> Option<char> {
144 EscapeUnicodeState::Backslash => {
145 self.state = EscapeUnicodeState::Type;
148 EscapeUnicodeState::Type => {
149 self.state = EscapeUnicodeState::LeftBrace;
152 EscapeUnicodeState::LeftBrace => {
153 self.state = EscapeUnicodeState::Value;
156 EscapeUnicodeState::Value => {
157 let hex_digit = ((self.c as u32) >> (self.hex_digit_idx * 4)) & 0xf;
158 let c = from_digit(hex_digit, 16).unwrap();
159 if self.hex_digit_idx == 0 {
160 self.state = EscapeUnicodeState::RightBrace;
162 self.hex_digit_idx -= 1;
166 EscapeUnicodeState::RightBrace => {
167 self.state = EscapeUnicodeState::Done;
170 EscapeUnicodeState::Done => None,
175 fn size_hint(&self) -> (usize, Option<usize>) {
181 fn count(self) -> usize {
185 fn last(self) -> Option<char> {
187 EscapeUnicodeState::Done => None,
189 EscapeUnicodeState::RightBrace
190 | EscapeUnicodeState::Value
191 | EscapeUnicodeState::LeftBrace
192 | EscapeUnicodeState::Type
193 | EscapeUnicodeState::Backslash => Some('}'),
198 #[stable(feature = "exact_size_escape", since = "1.11.0")]
199 impl ExactSizeIterator for EscapeUnicode {
201 fn len(&self) -> usize {
202 // The match is a single memory access with no branching
205 EscapeUnicodeState::Done => 0,
206 EscapeUnicodeState::RightBrace => 1,
207 EscapeUnicodeState::Value => 2,
208 EscapeUnicodeState::LeftBrace => 3,
209 EscapeUnicodeState::Type => 4,
210 EscapeUnicodeState::Backslash => 5,
215 #[stable(feature = "fused", since = "1.26.0")]
216 impl FusedIterator for EscapeUnicode {}
218 #[stable(feature = "char_struct_display", since = "1.16.0")]
219 impl fmt::Display for EscapeUnicode {
220 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
221 for c in self.clone() {
228 /// An iterator that yields the literal escape code of a `char`.
230 /// This `struct` is created by the [`escape_default`] method on [`char`]. See
231 /// its documentation for more.
233 /// [`escape_default`]: ../../std/primitive.char.html#method.escape_default
234 /// [`char`]: ../../std/primitive.char.html
235 #[derive(Clone, Debug)]
236 #[stable(feature = "rust1", since = "1.0.0")]
237 pub struct EscapeDefault {
238 state: EscapeDefaultState,
241 #[derive(Clone, Debug)]
242 enum EscapeDefaultState {
246 Unicode(EscapeUnicode),
249 #[stable(feature = "rust1", since = "1.0.0")]
250 impl Iterator for EscapeDefault {
253 fn next(&mut self) -> Option<char> {
255 EscapeDefaultState::Backslash(c) => {
256 self.state = EscapeDefaultState::Char(c);
259 EscapeDefaultState::Char(c) => {
260 self.state = EscapeDefaultState::Done;
263 EscapeDefaultState::Done => None,
264 EscapeDefaultState::Unicode(ref mut iter) => iter.next(),
269 fn size_hint(&self) -> (usize, Option<usize>) {
275 fn count(self) -> usize {
279 fn nth(&mut self, n: usize) -> Option<char> {
281 EscapeDefaultState::Backslash(c) if n == 0 => {
282 self.state = EscapeDefaultState::Char(c);
285 EscapeDefaultState::Backslash(c) if n == 1 => {
286 self.state = EscapeDefaultState::Done;
289 EscapeDefaultState::Backslash(_) => {
290 self.state = EscapeDefaultState::Done;
293 EscapeDefaultState::Char(c) => {
294 self.state = EscapeDefaultState::Done;
296 if n == 0 { Some(c) } else { None }
298 EscapeDefaultState::Done => None,
299 EscapeDefaultState::Unicode(ref mut i) => i.nth(n),
303 fn last(self) -> Option<char> {
305 EscapeDefaultState::Unicode(iter) => iter.last(),
306 EscapeDefaultState::Done => None,
307 EscapeDefaultState::Backslash(c) | EscapeDefaultState::Char(c) => Some(c),
312 #[stable(feature = "exact_size_escape", since = "1.11.0")]
313 impl ExactSizeIterator for EscapeDefault {
314 fn len(&self) -> usize {
316 EscapeDefaultState::Done => 0,
317 EscapeDefaultState::Char(_) => 1,
318 EscapeDefaultState::Backslash(_) => 2,
319 EscapeDefaultState::Unicode(ref iter) => iter.len(),
324 #[stable(feature = "fused", since = "1.26.0")]
325 impl FusedIterator for EscapeDefault {}
327 #[stable(feature = "char_struct_display", since = "1.16.0")]
328 impl fmt::Display for EscapeDefault {
329 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
330 for c in self.clone() {
337 /// An iterator that yields the literal escape code of a `char`.
339 /// This `struct` is created by the [`escape_debug`] method on [`char`]. See its
340 /// documentation for more.
342 /// [`escape_debug`]: ../../std/primitive.char.html#method.escape_debug
343 /// [`char`]: ../../std/primitive.char.html
344 #[stable(feature = "char_escape_debug", since = "1.20.0")]
345 #[derive(Clone, Debug)]
346 pub struct EscapeDebug(EscapeDefault);
348 #[stable(feature = "char_escape_debug", since = "1.20.0")]
349 impl Iterator for EscapeDebug {
351 fn next(&mut self) -> Option<char> {
354 fn size_hint(&self) -> (usize, Option<usize>) {
359 #[stable(feature = "char_escape_debug", since = "1.20.0")]
360 impl ExactSizeIterator for EscapeDebug {}
362 #[stable(feature = "fused", since = "1.26.0")]
363 impl FusedIterator for EscapeDebug {}
365 #[stable(feature = "char_escape_debug", since = "1.20.0")]
366 impl fmt::Display for EscapeDebug {
367 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
368 fmt::Display::fmt(&self.0, f)
372 /// Returns an iterator that yields the lowercase equivalent of a `char`.
374 /// This `struct` is created by the [`to_lowercase`] method on [`char`]. See
375 /// its documentation for more.
377 /// [`to_lowercase`]: ../../std/primitive.char.html#method.to_lowercase
378 /// [`char`]: ../../std/primitive.char.html
379 #[stable(feature = "rust1", since = "1.0.0")]
380 #[derive(Debug, Clone)]
381 pub struct ToLowercase(CaseMappingIter);
383 #[stable(feature = "rust1", since = "1.0.0")]
384 impl Iterator for ToLowercase {
386 fn next(&mut self) -> Option<char> {
389 fn size_hint(&self) -> (usize, Option<usize>) {
394 #[stable(feature = "fused", since = "1.26.0")]
395 impl FusedIterator for ToLowercase {}
397 #[stable(feature = "exact_size_case_mapping_iter", since = "1.35.0")]
398 impl ExactSizeIterator for ToLowercase {}
400 /// Returns an iterator that yields the uppercase equivalent of a `char`.
402 /// This `struct` is created by the [`to_uppercase`] method on [`char`]. See
403 /// its documentation for more.
405 /// [`to_uppercase`]: ../../std/primitive.char.html#method.to_uppercase
406 /// [`char`]: ../../std/primitive.char.html
407 #[stable(feature = "rust1", since = "1.0.0")]
408 #[derive(Debug, Clone)]
409 pub struct ToUppercase(CaseMappingIter);
411 #[stable(feature = "rust1", since = "1.0.0")]
412 impl Iterator for ToUppercase {
414 fn next(&mut self) -> Option<char> {
417 fn size_hint(&self) -> (usize, Option<usize>) {
422 #[stable(feature = "fused", since = "1.26.0")]
423 impl FusedIterator for ToUppercase {}
425 #[stable(feature = "exact_size_case_mapping_iter", since = "1.35.0")]
426 impl ExactSizeIterator for ToUppercase {}
428 #[derive(Debug, Clone)]
429 enum CaseMappingIter {
430 Three(char, char, char),
436 impl CaseMappingIter {
437 fn new(chars: [char; 3]) -> CaseMappingIter {
438 if chars[2] == '\0' {
439 if chars[1] == '\0' {
440 CaseMappingIter::One(chars[0]) // Including if chars[0] == '\0'
442 CaseMappingIter::Two(chars[0], chars[1])
445 CaseMappingIter::Three(chars[0], chars[1], chars[2])
450 impl Iterator for CaseMappingIter {
452 fn next(&mut self) -> Option<char> {
454 CaseMappingIter::Three(a, b, c) => {
455 *self = CaseMappingIter::Two(b, c);
458 CaseMappingIter::Two(b, c) => {
459 *self = CaseMappingIter::One(c);
462 CaseMappingIter::One(c) => {
463 *self = CaseMappingIter::Zero;
466 CaseMappingIter::Zero => None,
470 fn size_hint(&self) -> (usize, Option<usize>) {
471 let size = match self {
472 CaseMappingIter::Three(..) => 3,
473 CaseMappingIter::Two(..) => 2,
474 CaseMappingIter::One(_) => 1,
475 CaseMappingIter::Zero => 0,
481 impl fmt::Display for CaseMappingIter {
482 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
484 CaseMappingIter::Three(a, b, c) => {
489 CaseMappingIter::Two(b, c) => {
493 CaseMappingIter::One(c) => f.write_char(c),
494 CaseMappingIter::Zero => Ok(()),
499 #[stable(feature = "char_struct_display", since = "1.16.0")]
500 impl fmt::Display for ToLowercase {
501 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
502 fmt::Display::fmt(&self.0, f)
506 #[stable(feature = "char_struct_display", since = "1.16.0")]
507 impl fmt::Display for ToUppercase {
508 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
509 fmt::Display::fmt(&self.0, f)