Enum unic_ucd::SentenceBreak

pub enum SentenceBreak {
    CR,
    LF,
    Extend,
    Sep,
    Format,
    Sp,
    Lower,
    Upper,
    OLetter,
    Numeric,
    ATerm,
    SContinue,
    STerm,
    Close,
    Other,
}

Represents the Unicode character Sentence_Break property.

References

• https://www.unicode.org/reports/tr44/#Sentence_Break
• https://www.unicode.org/reports/tr29/#Sentence_Boundaries
• https://www.unicode.org/reports/tr29/#Table_Sentence_Break_Property_Values

Variants

CR

U+000D CARRIAGE RETURN (CR)

LF

U+000A LINE FEED (LF)

Extend

Grapheme_Extend = Yes, or
U+200D ZERO WIDTH JOINER (ZWJ), or
General_Category = Spacing_Mark

Sep

U+0085 NEXT LINE (NEL)
U+2028 LINE SEPARATOR
U+2029 PARAGRAPH SEPARATOR

Format

General_Category = Format
and not U+200C ZERO WIDTH NON-JOINER (ZWNJ)
and not U+200D ZERO WIDTH JOINER (ZWJ)

Sp

White_Space = Yes
and Sentence_Break ≠ Sep
and Sentence_Break ≠ CR
and Sentence_Break ≠ LF

Lower

Lowercase = Yes
and Grapheme_Extend = No

Upper

General_Category = Titlecase_Letter, or
Uppercase = Yes

OLetter

Alphabetic = Yes, or
U+00A0 NO-BREAK SPACE (NBSP), or
U+05F3 ( ׳ ) HEBREW PUNCTUATION GERESH
and Lower = No
and Upper = No
and Sentence_Break ≠ Extend

Numeric

Line_Break = Numeric

ATerm

U+002E ( . ) FULL STOP
U+2024 ( ․ ) ONE DOT LEADER
U+FE52 ( ﹒ ) SMALL FULL STOP
U+FF0E ( ． ) FULLWIDTH FULL STOP

SContinue

U+002C ( , ) COMMA
U+002D ( - ) HYPHEN-MINUS
U+003A ( : ) COLON
U+055D ( ՝ ) ARMENIAN COMMA
U+060C ( ، ) ARABIC COMMA
U+060D ( ‎؍‎ ) ARABIC DATE SEPARATOR
U+07F8 ( ߸ ) NKO COMMA
U+1802 ( ᠂ ) MONGOLIAN COMMA
U+1808 ( ᠈ ) MONGOLIAN MANCHU COMMA
U+2013 ( – ) EN DASH
U+2014 ( — ) EM DASH
U+3001 ( 、 ) IDEOGRAPHIC COMMA
U+FE10 ( ︐ ) PRESENTATION FORM FOR VERTICAL COMMA
U+FE11 ( ︑ ) PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA
U+FE13 ( ︓ ) PRESENTATION FORM FOR VERTICAL COLON
U+FE31 ( ︱ ) PRESENTATION FORM FOR VERTICAL EM DASH
U+FE32 ( ︲ ) PRESENTATION FORM FOR VERTICAL EN DASH
U+FE50 ( ﹐ ) SMALL COMMA
U+FE51 ( ﹑ ) SMALL IDEOGRAPHIC COMMA
U+FE55 ( ﹕ ) SMALL COLON
U+FE58 ( ﹘ ) SMALL EM DASH
U+FE63 ( ﹣ ) SMALL HYPHEN-MINUS
U+FF0C ( ， ) FULLWIDTH COMMA
U+FF0D ( － ) FULLWIDTH HYPHEN-MINUS
U+FF1A ( ： ) FULLWIDTH COLON
U+FF64 ( ､ ) HALFWIDTH IDEOGRAPHIC COMMA

STerm

Sentence_Terminal = Yes

Close

General_Category = Open_Punctuation, or
General_Category = Close_Punctuation, or
Line_Break = Quotation
and not U+05F3 ( ׳ ) HEBREW PUNCTUATION GERESH
and ATerm = No
and STerm = No

Other

All other characters

Methods

impl SentenceBreak

fn of(ch: char) -> SentenceBreak

Find the character Sentence_Break property value.

Trait Implementations

impl Debug for SentenceBreak

fn fmt(&self, __arg_0: &mut Formatter) -> Result<(), Error>

impl EnumeratedCharProperty for SentenceBreak

fn all_values() -> &'static [SentenceBreak]

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

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

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

impl PartialEq<SentenceBreak> for SentenceBreak

fn eq(&self, __arg_0: &SentenceBreak) -> bool

impl FromStr for SentenceBreak

type Err = ()

fn from_str(s: &str) -> Result<SentenceBreak, <SentenceBreak as FromStr>::Err>

impl Clone for SentenceBreak

fn clone(&self) -> SentenceBreak

impl Copy for SentenceBreak

impl Hash for SentenceBreak

fn hash<__H>(&self, __arg_0: &mut __H) where
    __H: Hasher, 

impl TotalCharProperty for SentenceBreak

fn of(ch: char) -> SentenceBreak

impl CharProperty for SentenceBreak

fn prop_abbr_name() -> &'static str

fn prop_long_name() -> &'static str

fn prop_human_name() -> &'static str

impl Eq for SentenceBreak

impl Display for SentenceBreak

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

impl Default for SentenceBreak

fn default() -> SentenceBreak