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 // perma-unstable re-exports
41 #[unstable(feature = "char_internals", reason = "exposed only for libstd", issue = "none")]
42 pub use self::methods::encode_utf16_raw;
43 #[unstable(feature = "char_internals", reason = "exposed only for libstd", issue = "none")]
44 pub use self::methods::encode_utf8_raw;
46 use crate::fmt::{self, Write};
47 use crate::iter::FusedIterator;
49 // UTF-8 ranges and tags for encoding characters
50 const TAG_CONT: u8 = 0b1000_0000;
51 const TAG_TWO_B: u8 = 0b1100_0000;
52 const TAG_THREE_B: u8 = 0b1110_0000;
53 const TAG_FOUR_B: u8 = 0b1111_0000;
54 const MAX_ONE_B: u32 = 0x80;
55 const MAX_TWO_B: u32 = 0x800;
56 const MAX_THREE_B: u32 = 0x10000;
59 Lu Uppercase_Letter an uppercase letter
60 Ll Lowercase_Letter a lowercase letter
61 Lt Titlecase_Letter a digraphic character, with first part uppercase
62 Lm Modifier_Letter a modifier letter
63 Lo Other_Letter other letters, including syllables and ideographs
64 Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
65 Mc Spacing_Mark a spacing combining mark (positive advance width)
66 Me Enclosing_Mark an enclosing combining mark
67 Nd Decimal_Number a decimal digit
68 Nl Letter_Number a letterlike numeric character
69 No Other_Number a numeric character of other type
70 Pc Connector_Punctuation a connecting punctuation mark, like a tie
71 Pd Dash_Punctuation a dash or hyphen punctuation mark
72 Ps Open_Punctuation an opening punctuation mark (of a pair)
73 Pe Close_Punctuation a closing punctuation mark (of a pair)
74 Pi Initial_Punctuation an initial quotation mark
75 Pf Final_Punctuation a final quotation mark
76 Po Other_Punctuation a punctuation mark of other type
77 Sm Math_Symbol a symbol of primarily mathematical use
78 Sc Currency_Symbol a currency sign
79 Sk Modifier_Symbol a non-letterlike modifier symbol
80 So Other_Symbol a symbol of other type
81 Zs Space_Separator a space character (of various non-zero widths)
82 Zl Line_Separator U+2028 LINE SEPARATOR only
83 Zp Paragraph_Separator U+2029 PARAGRAPH SEPARATOR only
84 Cc Control a C0 or C1 control code
85 Cf Format a format control character
86 Cs Surrogate a surrogate code point
87 Co Private_Use a private-use character
88 Cn Unassigned a reserved unassigned code point or a noncharacter
91 /// The highest valid code point a `char` can have.
93 /// A [`char`] is a [Unicode Scalar Value], which means that it is a [Code
94 /// Point], but only ones within a certain range. `MAX` is the highest valid
95 /// code point that's a valid [Unicode Scalar Value].
97 /// [`char`]: ../../std/primitive.char.html
98 /// [Unicode Scalar Value]: http://www.unicode.org/glossary/#unicode_scalar_value
99 /// [Code Point]: http://www.unicode.org/glossary/#code_point
100 #[stable(feature = "rust1", since = "1.0.0")]
101 pub const MAX: char = char::MAX;
103 /// `U+FFFD REPLACEMENT CHARACTER` (�) is used in Unicode to represent a
106 /// It can occur, for example, when giving ill-formed UTF-8 bytes to
107 /// [`String::from_utf8_lossy`](../../std/string/struct.String.html#method.from_utf8_lossy).
108 #[stable(feature = "decode_utf16", since = "1.9.0")]
109 pub const REPLACEMENT_CHARACTER: char = char::REPLACEMENT_CHARACTER;
111 /// Returns an iterator that yields the hexadecimal Unicode escape of a
112 /// character, as `char`s.
114 /// This `struct` is created by the [`escape_unicode`] method on [`char`]. See
115 /// its documentation for more.
117 /// [`escape_unicode`]: ../../std/primitive.char.html#method.escape_unicode
118 /// [`char`]: ../../std/primitive.char.html
119 #[derive(Clone, Debug)]
120 #[stable(feature = "rust1", since = "1.0.0")]
121 pub struct EscapeUnicode {
123 state: EscapeUnicodeState,
125 // The index of the next hex digit to be printed (0 if none),
126 // i.e., the number of remaining hex digits to be printed;
127 // increasing from the least significant digit: 0x543210
128 hex_digit_idx: usize,
131 // The enum values are ordered so that their representation is the
132 // same as the remaining length (besides the hexadecimal digits). This
133 // likely makes `len()` a single load from memory) and inline-worth.
134 #[derive(Clone, Debug)]
135 enum EscapeUnicodeState {
144 #[stable(feature = "rust1", since = "1.0.0")]
145 impl Iterator for EscapeUnicode {
148 fn next(&mut self) -> Option<char> {
150 EscapeUnicodeState::Backslash => {
151 self.state = EscapeUnicodeState::Type;
154 EscapeUnicodeState::Type => {
155 self.state = EscapeUnicodeState::LeftBrace;
158 EscapeUnicodeState::LeftBrace => {
159 self.state = EscapeUnicodeState::Value;
162 EscapeUnicodeState::Value => {
163 let hex_digit = ((self.c as u32) >> (self.hex_digit_idx * 4)) & 0xf;
164 let c = from_digit(hex_digit, 16).unwrap();
165 if self.hex_digit_idx == 0 {
166 self.state = EscapeUnicodeState::RightBrace;
168 self.hex_digit_idx -= 1;
172 EscapeUnicodeState::RightBrace => {
173 self.state = EscapeUnicodeState::Done;
176 EscapeUnicodeState::Done => None,
181 fn size_hint(&self) -> (usize, Option<usize>) {
187 fn count(self) -> usize {
191 fn last(self) -> Option<char> {
193 EscapeUnicodeState::Done => None,
195 EscapeUnicodeState::RightBrace
196 | EscapeUnicodeState::Value
197 | EscapeUnicodeState::LeftBrace
198 | EscapeUnicodeState::Type
199 | EscapeUnicodeState::Backslash => Some('}'),
204 #[stable(feature = "exact_size_escape", since = "1.11.0")]
205 impl ExactSizeIterator for EscapeUnicode {
207 fn len(&self) -> usize {
208 // The match is a single memory access with no branching
211 EscapeUnicodeState::Done => 0,
212 EscapeUnicodeState::RightBrace => 1,
213 EscapeUnicodeState::Value => 2,
214 EscapeUnicodeState::LeftBrace => 3,
215 EscapeUnicodeState::Type => 4,
216 EscapeUnicodeState::Backslash => 5,
221 #[stable(feature = "fused", since = "1.26.0")]
222 impl FusedIterator for EscapeUnicode {}
224 #[stable(feature = "char_struct_display", since = "1.16.0")]
225 impl fmt::Display for EscapeUnicode {
226 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
227 for c in self.clone() {
234 /// An iterator that yields the literal escape code of a `char`.
236 /// This `struct` is created by the [`escape_default`] method on [`char`]. See
237 /// its documentation for more.
239 /// [`escape_default`]: ../../std/primitive.char.html#method.escape_default
240 /// [`char`]: ../../std/primitive.char.html
241 #[derive(Clone, Debug)]
242 #[stable(feature = "rust1", since = "1.0.0")]
243 pub struct EscapeDefault {
244 state: EscapeDefaultState,
247 #[derive(Clone, Debug)]
248 enum EscapeDefaultState {
252 Unicode(EscapeUnicode),
255 #[stable(feature = "rust1", since = "1.0.0")]
256 impl Iterator for EscapeDefault {
259 fn next(&mut self) -> Option<char> {
261 EscapeDefaultState::Backslash(c) => {
262 self.state = EscapeDefaultState::Char(c);
265 EscapeDefaultState::Char(c) => {
266 self.state = EscapeDefaultState::Done;
269 EscapeDefaultState::Done => None,
270 EscapeDefaultState::Unicode(ref mut iter) => iter.next(),
275 fn size_hint(&self) -> (usize, Option<usize>) {
281 fn count(self) -> usize {
285 fn nth(&mut self, n: usize) -> Option<char> {
287 EscapeDefaultState::Backslash(c) if n == 0 => {
288 self.state = EscapeDefaultState::Char(c);
291 EscapeDefaultState::Backslash(c) if n == 1 => {
292 self.state = EscapeDefaultState::Done;
295 EscapeDefaultState::Backslash(_) => {
296 self.state = EscapeDefaultState::Done;
299 EscapeDefaultState::Char(c) => {
300 self.state = EscapeDefaultState::Done;
302 if n == 0 { Some(c) } else { None }
304 EscapeDefaultState::Done => None,
305 EscapeDefaultState::Unicode(ref mut i) => i.nth(n),
309 fn last(self) -> Option<char> {
311 EscapeDefaultState::Unicode(iter) => iter.last(),
312 EscapeDefaultState::Done => None,
313 EscapeDefaultState::Backslash(c) | EscapeDefaultState::Char(c) => Some(c),
318 #[stable(feature = "exact_size_escape", since = "1.11.0")]
319 impl ExactSizeIterator for EscapeDefault {
320 fn len(&self) -> usize {
322 EscapeDefaultState::Done => 0,
323 EscapeDefaultState::Char(_) => 1,
324 EscapeDefaultState::Backslash(_) => 2,
325 EscapeDefaultState::Unicode(ref iter) => iter.len(),
330 #[stable(feature = "fused", since = "1.26.0")]
331 impl FusedIterator for EscapeDefault {}
333 #[stable(feature = "char_struct_display", since = "1.16.0")]
334 impl fmt::Display for EscapeDefault {
335 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
336 for c in self.clone() {
343 /// An iterator that yields the literal escape code of a `char`.
345 /// This `struct` is created by the [`escape_debug`] method on [`char`]. See its
346 /// documentation for more.
348 /// [`escape_debug`]: ../../std/primitive.char.html#method.escape_debug
349 /// [`char`]: ../../std/primitive.char.html
350 #[stable(feature = "char_escape_debug", since = "1.20.0")]
351 #[derive(Clone, Debug)]
352 pub struct EscapeDebug(EscapeDefault);
354 #[stable(feature = "char_escape_debug", since = "1.20.0")]
355 impl Iterator for EscapeDebug {
357 fn next(&mut self) -> Option<char> {
360 fn size_hint(&self) -> (usize, Option<usize>) {
365 #[stable(feature = "char_escape_debug", since = "1.20.0")]
366 impl ExactSizeIterator for EscapeDebug {}
368 #[stable(feature = "fused", since = "1.26.0")]
369 impl FusedIterator for EscapeDebug {}
371 #[stable(feature = "char_escape_debug", since = "1.20.0")]
372 impl fmt::Display for EscapeDebug {
373 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
374 fmt::Display::fmt(&self.0, f)
378 /// Returns an iterator that yields the lowercase equivalent of a `char`.
380 /// This `struct` is created by the [`to_lowercase`] method on [`char`]. See
381 /// its documentation for more.
383 /// [`to_lowercase`]: ../../std/primitive.char.html#method.to_lowercase
384 /// [`char`]: ../../std/primitive.char.html
385 #[stable(feature = "rust1", since = "1.0.0")]
386 #[derive(Debug, Clone)]
387 pub struct ToLowercase(CaseMappingIter);
389 #[stable(feature = "rust1", since = "1.0.0")]
390 impl Iterator for ToLowercase {
392 fn next(&mut self) -> Option<char> {
395 fn size_hint(&self) -> (usize, Option<usize>) {
400 #[stable(feature = "fused", since = "1.26.0")]
401 impl FusedIterator for ToLowercase {}
403 #[stable(feature = "exact_size_case_mapping_iter", since = "1.35.0")]
404 impl ExactSizeIterator for ToLowercase {}
406 /// Returns an iterator that yields the uppercase equivalent of a `char`.
408 /// This `struct` is created by the [`to_uppercase`] method on [`char`]. See
409 /// its documentation for more.
411 /// [`to_uppercase`]: ../../std/primitive.char.html#method.to_uppercase
412 /// [`char`]: ../../std/primitive.char.html
413 #[stable(feature = "rust1", since = "1.0.0")]
414 #[derive(Debug, Clone)]
415 pub struct ToUppercase(CaseMappingIter);
417 #[stable(feature = "rust1", since = "1.0.0")]
418 impl Iterator for ToUppercase {
420 fn next(&mut self) -> Option<char> {
423 fn size_hint(&self) -> (usize, Option<usize>) {
428 #[stable(feature = "fused", since = "1.26.0")]
429 impl FusedIterator for ToUppercase {}
431 #[stable(feature = "exact_size_case_mapping_iter", since = "1.35.0")]
432 impl ExactSizeIterator for ToUppercase {}
434 #[derive(Debug, Clone)]
435 enum CaseMappingIter {
436 Three(char, char, char),
442 impl CaseMappingIter {
443 fn new(chars: [char; 3]) -> CaseMappingIter {
444 if chars[2] == '\0' {
445 if chars[1] == '\0' {
446 CaseMappingIter::One(chars[0]) // Including if chars[0] == '\0'
448 CaseMappingIter::Two(chars[0], chars[1])
451 CaseMappingIter::Three(chars[0], chars[1], chars[2])
456 impl Iterator for CaseMappingIter {
458 fn next(&mut self) -> Option<char> {
460 CaseMappingIter::Three(a, b, c) => {
461 *self = CaseMappingIter::Two(b, c);
464 CaseMappingIter::Two(b, c) => {
465 *self = CaseMappingIter::One(c);
468 CaseMappingIter::One(c) => {
469 *self = CaseMappingIter::Zero;
472 CaseMappingIter::Zero => None,
476 fn size_hint(&self) -> (usize, Option<usize>) {
477 let size = match self {
478 CaseMappingIter::Three(..) => 3,
479 CaseMappingIter::Two(..) => 2,
480 CaseMappingIter::One(_) => 1,
481 CaseMappingIter::Zero => 0,
487 impl fmt::Display for CaseMappingIter {
488 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
490 CaseMappingIter::Three(a, b, c) => {
495 CaseMappingIter::Two(b, c) => {
499 CaseMappingIter::One(c) => f.write_char(c),
500 CaseMappingIter::Zero => Ok(()),
505 #[stable(feature = "char_struct_display", since = "1.16.0")]
506 impl fmt::Display for ToLowercase {
507 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
508 fmt::Display::fmt(&self.0, f)
512 #[stable(feature = "char_struct_display", since = "1.16.0")]
513 impl fmt::Display for ToUppercase {
514 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
515 fmt::Display::fmt(&self.0, f)