Module: PragmaticSegmenter::Languages::Common::SubSymbolsRules

Defined in:

lib/pragmatic_segmenter/languages/common.rb

Constant Summary

Period =

Rule.new(/∯/, '.')

ArabicComma =

Rule.new(/♬/, '،')

SemiColon =

Rule.new(/♭/, ':')

FullWidthPeriod =

Rule.new(/&ᓰ&/, '。')

SpecialPeriod =

Rule.new(/&ᓱ&/, '．')

FullWidthExclamation =

Rule.new(/&ᓳ&/, '！')

ExclamationPoint =

Rule.new(/&ᓴ&/, '!')

QuestionMark =

Rule.new(/&ᓷ&/, '?')

FullWidthQuestionMark =

Rule.new(/&ᓸ&/, '？')

MixedDoubleQE =

Rule.new(/☉/, '?!')

MixedDoubleQQ =

Rule.new(/☇/, '??')

MixedDoubleEQ =

Rule.new(/☈/, '!?')

MixedDoubleEE =

Rule.new(/☄/, '!!')

LeftParens =

Rule.new(/&✂&/, '(')

RightParens =

Rule.new(/&⌬&/, ')')

TemporaryEndingPunctutation =

Rule.new('ȸ', '')

Newline =

Rule.new(/ȹ/, "\n")

All =

[ Period, ArabicComma,
SemiColon, FullWidthPeriod,
SpecialPeriod, FullWidthExclamation,
ExclamationPoint, QuestionMark,
FullWidthQuestionMark, MixedDoubleQE,
MixedDoubleQQ, MixedDoubleEQ,
MixedDoubleEE, LeftParens,
RightParens, TemporaryEndingPunctutation,
Newline ]