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 /// [Unicode Scalar Value]: http://www.unicode.org/glossary/#unicode_scalar_value
98 /// [Code Point]: http://www.unicode.org/glossary/#code_point
99 #[stable(feature = "rust1", since = "1.0.0")]
100 pub const MAX: char = char::MAX;
102 /// `U+FFFD REPLACEMENT CHARACTER` (�) is used in Unicode to represent a
105 /// It can occur, for example, when giving ill-formed UTF-8 bytes to
106 /// [`String::from_utf8_lossy`](../../std/string/struct.String.html#method.from_utf8_lossy).
107 #[stable(feature = "decode_utf16", since = "1.9.0")]
108 pub const REPLACEMENT_CHARACTER: char = char::REPLACEMENT_CHARACTER;
110 /// Returns an iterator that yields the hexadecimal Unicode escape of a
111 /// character, as `char`s.
113 /// This `struct` is created by the [`escape_unicode`] method on [`char`]. See
114 /// its documentation for more.
116 /// [`escape_unicode`]: char::escape_unicode
117 #[derive(Clone, Debug)]
118 #[stable(feature = "rust1", since = "1.0.0")]
119 pub struct EscapeUnicode {
121 state: EscapeUnicodeState,
123 // The index of the next hex digit to be printed (0 if none),
124 // i.e., the number of remaining hex digits to be printed;
125 // increasing from the least significant digit: 0x543210
126 hex_digit_idx: usize,
129 // The enum values are ordered so that their representation is the
130 // same as the remaining length (besides the hexadecimal digits). This
131 // likely makes `len()` a single load from memory) and inline-worth.
132 #[derive(Clone, Debug)]
133 enum EscapeUnicodeState {
142 #[stable(feature = "rust1", since = "1.0.0")]
143 impl Iterator for EscapeUnicode {
146 fn next(&mut self) -> Option<char> {
148 EscapeUnicodeState::Backslash => {
149 self.state = EscapeUnicodeState::Type;
152 EscapeUnicodeState::Type => {
153 self.state = EscapeUnicodeState::LeftBrace;
156 EscapeUnicodeState::LeftBrace => {
157 self.state = EscapeUnicodeState::Value;
160 EscapeUnicodeState::Value => {
161 let hex_digit = ((self.c as u32) >> (self.hex_digit_idx * 4)) & 0xf;
162 let c = from_digit(hex_digit, 16).unwrap();
163 if self.hex_digit_idx == 0 {
164 self.state = EscapeUnicodeState::RightBrace;
166 self.hex_digit_idx -= 1;
170 EscapeUnicodeState::RightBrace => {
171 self.state = EscapeUnicodeState::Done;
174 EscapeUnicodeState::Done => None,
179 fn size_hint(&self) -> (usize, Option<usize>) {
185 fn count(self) -> usize {
189 fn last(self) -> Option<char> {
191 EscapeUnicodeState::Done => None,
193 EscapeUnicodeState::RightBrace
194 | EscapeUnicodeState::Value
195 | EscapeUnicodeState::LeftBrace
196 | EscapeUnicodeState::Type
197 | EscapeUnicodeState::Backslash => Some('}'),
202 #[stable(feature = "exact_size_escape", since = "1.11.0")]
203 impl ExactSizeIterator for EscapeUnicode {
205 fn len(&self) -> usize {
206 // The match is a single memory access with no branching
209 EscapeUnicodeState::Done => 0,
210 EscapeUnicodeState::RightBrace => 1,
211 EscapeUnicodeState::Value => 2,
212 EscapeUnicodeState::LeftBrace => 3,
213 EscapeUnicodeState::Type => 4,
214 EscapeUnicodeState::Backslash => 5,
219 #[stable(feature = "fused", since = "1.26.0")]
220 impl FusedIterator for EscapeUnicode {}
222 #[stable(feature = "char_struct_display", since = "1.16.0")]
223 impl fmt::Display for EscapeUnicode {
224 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
225 for c in self.clone() {
232 /// An iterator that yields the literal escape code of a `char`.
234 /// This `struct` is created by the [`escape_default`] method on [`char`]. See
235 /// its documentation for more.
237 /// [`escape_default`]: char::escape_default
238 #[derive(Clone, Debug)]
239 #[stable(feature = "rust1", since = "1.0.0")]
240 pub struct EscapeDefault {
241 state: EscapeDefaultState,
244 #[derive(Clone, Debug)]
245 enum EscapeDefaultState {
249 Unicode(EscapeUnicode),
252 #[stable(feature = "rust1", since = "1.0.0")]
253 impl Iterator for EscapeDefault {
256 fn next(&mut self) -> Option<char> {
258 EscapeDefaultState::Backslash(c) => {
259 self.state = EscapeDefaultState::Char(c);
262 EscapeDefaultState::Char(c) => {
263 self.state = EscapeDefaultState::Done;
266 EscapeDefaultState::Done => None,
267 EscapeDefaultState::Unicode(ref mut iter) => iter.next(),
272 fn size_hint(&self) -> (usize, Option<usize>) {
278 fn count(self) -> usize {
282 fn nth(&mut self, n: usize) -> Option<char> {
284 EscapeDefaultState::Backslash(c) if n == 0 => {
285 self.state = EscapeDefaultState::Char(c);
288 EscapeDefaultState::Backslash(c) if n == 1 => {
289 self.state = EscapeDefaultState::Done;
292 EscapeDefaultState::Backslash(_) => {
293 self.state = EscapeDefaultState::Done;
296 EscapeDefaultState::Char(c) => {
297 self.state = EscapeDefaultState::Done;
299 if n == 0 { Some(c) } else { None }
301 EscapeDefaultState::Done => None,
302 EscapeDefaultState::Unicode(ref mut i) => i.nth(n),
306 fn last(self) -> Option<char> {
308 EscapeDefaultState::Unicode(iter) => iter.last(),
309 EscapeDefaultState::Done => None,
310 EscapeDefaultState::Backslash(c) | EscapeDefaultState::Char(c) => Some(c),
315 #[stable(feature = "exact_size_escape", since = "1.11.0")]
316 impl ExactSizeIterator for EscapeDefault {
317 fn len(&self) -> usize {
319 EscapeDefaultState::Done => 0,
320 EscapeDefaultState::Char(_) => 1,
321 EscapeDefaultState::Backslash(_) => 2,
322 EscapeDefaultState::Unicode(ref iter) => iter.len(),
327 #[stable(feature = "fused", since = "1.26.0")]
328 impl FusedIterator for EscapeDefault {}
330 #[stable(feature = "char_struct_display", since = "1.16.0")]
331 impl fmt::Display for EscapeDefault {
332 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
333 for c in self.clone() {
340 /// An iterator that yields the literal escape code of a `char`.
342 /// This `struct` is created by the [`escape_debug`] method on [`char`]. See its
343 /// documentation for more.
345 /// [`escape_debug`]: char::escape_debug
346 #[stable(feature = "char_escape_debug", since = "1.20.0")]
347 #[derive(Clone, Debug)]
348 pub struct EscapeDebug(EscapeDefault);
350 #[stable(feature = "char_escape_debug", since = "1.20.0")]
351 impl Iterator for EscapeDebug {
353 fn next(&mut self) -> Option<char> {
356 fn size_hint(&self) -> (usize, Option<usize>) {
361 #[stable(feature = "char_escape_debug", since = "1.20.0")]
362 impl ExactSizeIterator for EscapeDebug {}
364 #[stable(feature = "fused", since = "1.26.0")]
365 impl FusedIterator for EscapeDebug {}
367 #[stable(feature = "char_escape_debug", since = "1.20.0")]
368 impl fmt::Display for EscapeDebug {
369 fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
370 fmt::Display::fmt(&self.0, f)
374 /// Returns an iterator that yields the lowercase equivalent of a `char`.
376 /// This `struct` is created by the [`to_lowercase`] method on [`char`]. See
377 /// its documentation for more.
379 /// [`to_lowercase`]: char::to_lowercase
380 #[stable(feature = "rust1", since = "1.0.0")]
381 #[derive(Debug, Clone)]
382 pub struct ToLowercase(CaseMappingIter);
384 #[stable(feature = "rust1", since = "1.0.0")]
385 impl Iterator for ToLowercase {
387 fn next(&mut self) -> Option<char> {
390 fn size_hint(&self) -> (usize, Option<usize>) {
395 #[stable(feature = "fused", since = "1.26.0")]
396 impl FusedIterator for ToLowercase {}
398 #[stable(feature = "exact_size_case_mapping_iter", since = "1.35.0")]
399 impl ExactSizeIterator for ToLowercase {}
401 /// Returns an iterator that yields the uppercase equivalent of a `char`.
403 /// This `struct` is created by the [`to_uppercase`] method on [`char`]. See
404 /// its documentation for more.
406 /// [`to_uppercase`]: char::to_uppercase
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)