Struct WordBreak 

pub struct WordBreak(/* private fields */);

Enumerated property Word_Break.

See “Default Word Boundary Specification” in UAX #29 for the summary of each property value: https://www.unicode.org/reports/tr29/#Default_Word_Boundaries.

Note: Use icu::segmenter for an all-in-one break iterator implementation.

Example

use icu::properties::{CodePointMapData, props::WordBreak};

assert_eq!(
    CodePointMapData::<WordBreak>::new().get('.'),
    WordBreak::MidNumLet
); // U+002E: Full Stop
assert_eq!(
    CodePointMapData::<WordBreak>::new().get('，'),
    WordBreak::MidNum
); // U+FF0C: Fullwidth Comma

Implementations

impl WordBreak

pub const Other: Self

pub const XX: Self = Self::Other

pub const ALetter: Self

pub const LE: Self = Self::ALetter

pub const Format: Self

pub const FO: Self = Self::Format

pub const Katakana: Self

pub const KA: Self = Self::Katakana

pub const MidLetter: Self

pub const ML: Self = Self::MidLetter

pub const MidNum: Self

pub const MN: Self = Self::MidNum

pub const Numeric: Self

pub const NU: Self = Self::Numeric

pub const ExtendNumLet: Self

pub const EX: Self = Self::ExtendNumLet

pub const CR: Self

pub const Extend: Self

pub const LF: Self

pub const MidNumLet: Self

pub const MB: Self = Self::MidNumLet

pub const Newline: Self

pub const NL: Self = Self::Newline

pub const RegionalIndicator: Self

pub const RI: Self = Self::RegionalIndicator

pub const HebrewLetter: Self

pub const HL: Self = Self::HebrewLetter

pub const SingleQuote: Self

pub const SQ: Self = Self::SingleQuote

pub const DoubleQuote: Self

pub const DQ: Self = Self::DoubleQuote

pub const EBase: Self

pub const EB: Self = Self::EBase

pub const EBaseGAZ: Self

pub const EBG: Self = Self::EBaseGAZ

pub const EModifier: Self

pub const EM: Self = Self::EModifier

pub const GlueAfterZwj: Self

pub const GAZ: Self = Self::GlueAfterZwj

pub const ZWJ: Self

pub const WSegSpace: Self

impl WordBreak

pub const ALL_VALUES: &'static [Self]

👎Deprecated

Deprecated

impl WordBreak

pub const fn to_icu4c_value(self) -> u8

👎Deprecated since 2.3.0:

please comment on https://github.com/unicode-org/icu4x/issues/6067 if you need this

Returns an ICU4C UWordBreak value.

pub const fn from_icu4c_value(value: u8) -> Self

👎Deprecated since 2.3.0:

please comment on https://github.com/unicode-org/icu4x/issues/6067 if you need this

Constructor from an ICU4C UWordBreak value.

Trait Implementations

impl AsULE for WordBreak

type ULE = u8

The ULE type corresponding to Self.

fn to_unaligned(self) -> Self::ULE

Converts from Self to Self::ULE.

fn from_unaligned(unaligned: Self::ULE) -> Self

Converts from Self::ULE to Self.

impl Clone for WordBreak

fn clone(&self) -> WordBreak

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for WordBreak

impl Debug for WordBreak

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for WordBreak

fn default() -> Self

Returns the “default value” for a type.

impl EnumeratedProperty for WordBreak

const NAME: &'static [u8]

The name of this property

const SHORT_NAME: &'static [u8]

The abbreviated name of this property, if it exists, otherwise the name

fn for_char(ch: char) -> Self

Convenience method for CodePointMapData::new().get(ch)

impl Eq for WordBreak

impl From<WordBreak> for u16

fn from(other: WordBreak) -> Self

Converts to this type from the input type.

impl Hash for WordBreak

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, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl NamedEnumeratedProperty for WordBreak

fn try_from_str(s: &str) -> Option<Self>

Convenience method for PropertyParser::new().get_loose(s)

fn long_name(&self) -> &'static str

Convenience method for PropertyNamesLong::new().get(*self).unwrap()

fn short_name(&self) -> &'static str

Convenience method for PropertyNamesShort::new().get(*self).unwrap()

impl Ord for WordBreak

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

This method returns an Ordering between self and other.

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

where Self: Sized,

Compares and returns the maximum of two values.

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

where Self: Sized,

Compares and returns the minimum of two values.

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

where Self: Sized,

Restrict a value to a certain interval.

impl ParseableEnumeratedProperty for WordBreak

impl PartialEq for WordBreak

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

Equality operator ==.

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

Inequality operator !=.

impl PartialOrd for WordBreak

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

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

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

Tests less than (for self and other) and is used by the < operator.

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

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

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

Tests greater than (for self and other) and is used by the > operator.

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

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

impl StructuralPartialEq for WordBreak

impl TrieValue for WordBreak

type TryFromU32Error = TryFromIntError

Last-resort fallback value to return if we cannot read data from the trie.

fn try_from_u32(i: u32) -> Result<Self, Self::TryFromU32Error>

A parsing function that is primarily motivated by deserialization contexts. When the serialization type width is smaller than 32 bits, then it is expected that the call site will widen the value to a u32 first.

fn to_u32(self) -> u32

A method for converting back to a u32 that can roundtrip through Self::try_from_u32(). The default implementation of this trait method panics in debug mode and returns 0 in release mode.