Struct encode_unicode::Utf8Char

pub struct Utf8Char { /* fields omitted */ }

An unicode codepoint stored as UTF-8.

It can be borrowed as a str, and has the same size as char.

Methods

impl Utf8Char

pub fn from_str_start(src: &str) -> Result<(Self, usize), EmptyStrError>

Create an Utf8Char from the first codepoint in a str.

Returns an error if the str is empty.

Examples

use encode_unicode::Utf8Char;

assert_eq!(Utf8Char::from_str_start("a"), Ok((Utf8Char::from('a'),1)));
assert_eq!(Utf8Char::from_str_start("ab"), Ok((Utf8Char::from('a'),1)));
assert_eq!(Utf8Char::from_str_start("🂠 "), Ok((Utf8Char::from('🂠'),4)));
assert_eq!(Utf8Char::from_str_start("é"), Ok((Utf8Char::from('e'),1)));// 'e'+u301 combining mark
assert!(Utf8Char::from_str_start("").is_err());

pub fn from_slice_start(src: &[u8]) -> Result<(Self, usize), InvalidUtf8Slice>

Create an Utf8Char of the first codepoint in an UTF-8 slice.
Also returns the length of the UTF-8 sequence for the codepoint.

If the slice is from a str, use ::from_str_start() to skip UTF-8 validation.

Errors

Returns an Err if the slice is empty, doesn't start with a valid UTF-8 sequence or is too short for the sequence.

Examples

use encode_unicode::Utf8Char;
use encode_unicode::error::InvalidUtf8Slice::*;
use encode_unicode::error::InvalidUtf8::*;

assert_eq!(Utf8Char::from_slice_start(&[b'A', b'B', b'C']), Ok((Utf8Char::from('A'),1)));
assert_eq!(Utf8Char::from_slice_start(&[0xdd, 0xbb]), Ok((Utf8Char::from('\u{77b}'),2)));

assert_eq!(Utf8Char::from_slice_start(&[]), Err(TooShort(1)));
assert_eq!(Utf8Char::from_slice_start(&[0xf0, 0x99]), Err(TooShort(4)));
assert_eq!(Utf8Char::from_slice_start(&[0xee, b'F', 0x80]), Err(Utf8(NotAContinuationByte(1))));
assert_eq!(Utf8Char::from_slice_start(&[0xee, 0x99, 0x0f]), Err(Utf8(NotAContinuationByte(2))));

pub unsafe fn from_slice_start_unchecked(src: &[u8]) -> (Self, usize)

A from_slice_start() that doesn't validate the codepoint.

Safety

The slice must be non-empty and start with a valid UTF-8 codepoint.
Invalid or incomplete values might cause reads of uninitalized memory.

pub fn from_array(utf8: [u8; 4]) -> Result<Self, InvalidUtf8Array>

Create an Utf8Char from a byte array after validating it.

The codepoint must start at the first byte.
Unused bytes are set to zero by this function and so can be anything.

Errors

Returns an Err if the array doesn't start with a valid UTF-8 sequence.

Examples

use encode_unicode::Utf8Char;
use encode_unicode::error::InvalidUtf8Array::*;
use encode_unicode::error::InvalidUtf8::*;
use encode_unicode::error::InvalidCodepoint::*;

assert_eq!(Utf8Char::from_array([b'A', 0, 0, 0]), Ok(Utf8Char::from('A')));
assert_eq!(Utf8Char::from_array([0xf4, 0x8b, 0xbb, 0xbb]), Ok(Utf8Char::from('\u{10befb}')));
assert_eq!(Utf8Char::from_array([b'A', b'B', b'C', b'D']), Ok(Utf8Char::from('A')));
assert_eq!(Utf8Char::from_array([0, 0, 0xcc, 0xbb]), Ok(Utf8Char::from('\0')));

assert_eq!(Utf8Char::from_array([0xef, b'F', 0x80, 0x80]), Err(Utf8(NotAContinuationByte(1))));
assert_eq!(Utf8Char::from_array([0xc1, 0x80, 0, 0]), Err(Utf8(OverLong)));
assert_eq!(Utf8Char::from_array([0xf7, 0xaa, 0x99, 0x88]), Err(Codepoint(TooHigh)));

pub unsafe fn from_array_unchecked(utf8: [u8; 4]) -> Self

Zero-cost constructor.

Safety

Must contain a valid codepoint starting at the first byte, with the unused bytes zeroed.
Bad values can easily lead to undefined behavior.

pub fn from_ascii(ascii: u8) -> Result<Self, NonAsciiError>

Create an Utf8Char from a single byte.

The byte must be an ASCII character.

Errors

Returns NonAsciiError if the byte greater than 127.

Examples

assert_eq!(Utf8Char::from_ascii(b'a').unwrap(), 'a');
assert!(Utf8Char::from_ascii(128).is_err());

pub unsafe fn from_ascii_unchecked(ascii: u8) -> Self

Create an Utf8Char from a single byte without checking that it's a valid codepoint on its own, which is only true for ASCII characters.

Safety

The byte must be less than 128.

pub fn len(self) -> usize

The number of bytes this character needs.

Is between 1 and 4 (inclusive) and identical to .as_ref().len() or .as_char().len_utf8().

pub fn is_ascii(&self) -> bool

Checks that the codepoint is an ASCII character.

pub fn eq_ignore_ascii_case(&self, other: &Self) -> bool

Checks that two characters are an ASCII case-insensitive match.

Is equivalent to a.to_ascii_lowercase() == b.to_ascii_lowercase().

pub fn to_ascii_uppercase(&self) -> Self

Converts the character to its ASCII upper case equivalent.

ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', but non-ASCII letters are unchanged.

pub fn to_ascii_lowercase(&self) -> Self

Converts the character to its ASCII lower case equivalent.

ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', but non-ASCII letters are unchanged.

pub fn make_ascii_uppercase(&mut self)

Converts the character to its ASCII upper case equivalent in-place.

ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', but non-ASCII letters are unchanged.

pub fn make_ascii_lowercase(&mut self)

Converts the character to its ASCII lower case equivalent in-place.

ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', but non-ASCII letters are unchanged.

pub fn to_char(self) -> char

Convert from UTF-8 to UTF-32

pub fn to_slice(self, dst: &mut [u8]) -> usize

Write the internal representation to a slice, and then returns the number of bytes written.

Panics

Will panic the buffer is too small; You can get the required length from .len(), but a buffer of length four is always large enough.

pub fn to_array(self) -> ([u8; 4], usize)

Expose the internal array and the number of used bytes.

pub fn as_str(&self) -> &str

Return a str view of the array the codepoint is stored as.

Is an unambiguous version of .as_ref().

Trait Implementations

impl From<Utf16Char> for Utf8Char

fn from(utf16: Utf16Char) -> Utf8Char

Performs the conversion.

impl From<char> for Utf8Char

fn from(c: char) -> Self

Performs the conversion.

impl From<Utf8Char> for char

fn from(uc: Utf8Char) -> char

Performs the conversion.

impl From<AsciiChar> for Utf8Char

Requires the feature "ascii".

fn from(ac: AsciiChar) -> Self

Performs the conversion.

impl From<Utf8Char> for Utf8Iterator

fn from(uc: Utf8Char) -> Self

Performs the conversion.

impl From<Utf8Char> for Utf16Char

fn from(utf8: Utf8Char) -> Utf16Char

Performs the conversion.

impl Ord for Utf8Char

fn cmp(&self, other: &Utf8Char) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

🔬 This is a nightly-only experimental API. (clamp)

Restrict a value to a certain interval.

impl Extend<Utf8Char> for Vec<u8>

fn extend<I: IntoIterator<Item = Utf8Char>>(&mut self, iter: I)

Extends a collection with the contents of an iterator.

impl<'a> Extend<&'a Utf8Char> for Vec<u8>

fn extend<I: IntoIterator<Item = &'a Utf8Char>>(&mut self, iter: I)

Extends a collection with the contents of an iterator.

impl Extend<Utf8Char> for String

fn extend<I: IntoIterator<Item = Utf8Char>>(&mut self, iter: I)

Extends a collection with the contents of an iterator.

impl<'a> Extend<&'a Utf8Char> for String

fn extend<I: IntoIterator<Item = &'a Utf8Char>>(&mut self, iter: I)

Extends a collection with the contents of an iterator.

impl PartialOrd<Utf8Char> for Utf8Char

fn partial_cmp(&self, other: &Utf8Char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Utf8Char) -> bool

This method tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Utf8Char) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Utf8Char) -> bool

This method tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Utf8Char) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<char> for Utf8Char

fn partial_cmp(&self, u32c: &char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<Utf8Char> for char

fn partial_cmp(&self, u8c: &Utf8Char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<Utf16Char> for Utf8Char

fn partial_cmp(&self, u16c: &Utf16Char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<AsciiChar> for Utf8Char

Utf8Chars that are not ASCII always compare greater.

fn partial_cmp(&self, ascii: &AsciiChar) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<Utf8Char> for AsciiChar

Utf8Chars that are not ASCII always compare greater.

fn partial_cmp(&self, u8c: &Utf8Char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialOrd<Utf8Char> for Utf16Char

fn partial_cmp(&self, u8c: &Utf8Char) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

#[must_use] fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

#[must_use] fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

#[must_use] fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

#[must_use] fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl PartialEq<Utf8Char> for Utf8Char

fn eq(&self, other: &Utf8Char) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Utf8Char) -> bool

This method tests for !=.

impl PartialEq<char> for Utf8Char

fn eq(&self, u32c: &char) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<Utf8Char> for char

fn eq(&self, u8c: &Utf8Char) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<Utf16Char> for Utf8Char

fn eq(&self, u16c: &Utf16Char) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<u8> for Utf8Char

Only considers the byte equal if both it and the Utf8Char represents ASCII characters.

There is no impl in the opposite direction, as this should only be used to compare Utf8Chars against constants.

Examples

assert!(Utf8Char::from('8') == b'8');
assert!(Utf8Char::from_array([0xf1,0x80,0x80,0x80]).unwrap() != 0xf1);
assert!(Utf8Char::from('\u{ff}') != 0xff);
assert!(Utf8Char::from('\u{80}') != 0x80);

fn eq(&self, byte: &u8) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<AsciiChar> for Utf8Char

Utf8Chars that are not ASCII never compare equal.

fn eq(&self, ascii: &AsciiChar) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<Utf8Char> for AsciiChar

Utf8Chars that are not ASCII never compare equal.

fn eq(&self, u8c: &Utf8Char) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl PartialEq<Utf8Char> for Utf16Char

fn eq(&self, u8c: &Utf8Char) -> bool

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl Default for Utf8Char

fn default() -> Utf8Char

Returns the "default value" for a type.

impl IntoIterator for Utf8Char

type Item = u8

The type of the elements being iterated over.

type IntoIter = Utf8Iterator

Which kind of iterator are we turning this into?

Important traits for Utf8Iterator

impl Iterator for Utf8Iterator type Item = u8;impl Read for Utf8Iterator

fn into_iter(self) -> Utf8Iterator

Iterate over the byte values.

impl Clone for Utf8Char

fn clone(&self) -> Utf8Char

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Eq for Utf8Char

impl Copy for Utf8Char

impl AsRef<[u8]> for Utf8Char

fn as_ref(&self) -> &[u8]

Performs the conversion.

impl AsRef<str> for Utf8Char

fn as_ref(&self) -> &str

Performs the conversion.

impl Display for Utf8Char

fn fmt(&self, fmtr: &mut Formatter) -> Result

Formats the value using the given formatter.

impl Debug for Utf8Char

fn fmt(&self, fmtr: &mut Formatter) -> Result

Formats the value using the given formatter.

impl Deref for Utf8Char

type Target = str

The resulting type after dereferencing.

fn deref(&self) -> &Self::Target

Dereferences the value.

impl Hash for Utf8Char

fn hash<H: Hasher>(&self, state: &mut H)

Feeds this value into the given [Hasher].

fn hash_slice<H>(data: &[Self], state: &mut H) where
    H: Hasher, 

Feeds a slice of this type into the given [Hasher].

impl FromIterator<Utf8Char> for String

fn from_iter<I: IntoIterator<Item = Utf8Char>>(iter: I) -> String

Creates a value from an iterator.

impl<'a> FromIterator<&'a Utf8Char> for String

fn from_iter<I: IntoIterator<Item = &'a Utf8Char>>(iter: I) -> String

Creates a value from an iterator.

impl FromIterator<Utf8Char> for Vec<u8>

fn from_iter<I: IntoIterator<Item = Utf8Char>>(iter: I) -> Self

Creates a value from an iterator.

impl<'a> FromIterator<&'a Utf8Char> for Vec<u8>

fn from_iter<I: IntoIterator<Item = &'a Utf8Char>>(iter: I) -> Self

Creates a value from an iterator.

impl FromStr for Utf8Char

type Err = FromStrError

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, FromStrError>

Create an Utf8Char from a string slice. The string must contain exactly one codepoint.

Examples

use encode_unicode::error::FromStrError::*;
use encode_unicode::Utf8Char;
use std::str::FromStr;

assert_eq!(Utf8Char::from_str("a"), Ok(Utf8Char::from('a')));
assert_eq!(Utf8Char::from_str("🂠"), Ok(Utf8Char::from('🂠')));
assert_eq!(Utf8Char::from_str(""), Err(Empty));
assert_eq!(Utf8Char::from_str("ab"), Err(MultipleCodepoints));
assert_eq!(Utf8Char::from_str("é"), Err(MultipleCodepoints));// 'e'+u301 combining mark

impl Borrow<[u8]> for Utf8Char

fn borrow(&self) -> &[u8]

Immutably borrows from an owned value.

impl Borrow<str> for Utf8Char

fn borrow(&self) -> &str

Immutably borrows from an owned value.

impl AsciiExt for Utf8Char

type Owned = Utf8Char

Deprecated since 1.26.0:

use inherent methods instead

Container type for copied ASCII characters.

fn is_ascii(&self) -> bool

Deprecated since 1.26.0:

use inherent methods instead

Checks if the value is within the ASCII range.

fn eq_ignore_ascii_case(&self, other: &Self) -> bool

Deprecated since 1.26.0:

use inherent methods instead

Checks that two values are an ASCII case-insensitive match.

fn to_ascii_uppercase(&self) -> Self::Owned

Deprecated since 1.26.0:

use inherent methods instead

Makes a copy of the value in its ASCII upper case equivalent.

fn to_ascii_lowercase(&self) -> Self::Owned

Deprecated since 1.26.0:

use inherent methods instead

Makes a copy of the value in its ASCII lower case equivalent.

fn make_ascii_uppercase(&mut self)

Deprecated since 1.26.0:

use inherent methods instead

Converts this type to its ASCII upper case equivalent in-place.

fn make_ascii_lowercase(&mut self)

Deprecated since 1.26.0:

use inherent methods instead

Converts this type to its ASCII lower case equivalent in-place.

impl ToAsciiChar for Utf8Char

Requires the feature "ascii".

fn to_ascii_char(self) -> Result<AsciiChar, ToAsciiCharError>

Convert to AsciiChar.

unsafe fn to_ascii_char_unchecked(self) -> AsciiChar

Convert to AsciiChar without checking that it is an ASCII character.