Module: PragmaticTokenizer::Languages::Common

Included in:

Arabic, Bulgarian, Catalan, Czech, Danish, Deutsch, Dutch, English, Finnish, French, Greek, Indonesian, Italian, Latvian, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Turkish

Defined in:

lib/pragmatic_tokenizer/languages/common.rb

Defined Under Namespace

Classes: SingleQuotes

Constant Summary

PUNCTUATION_MAP =

{ "。" => "♳", "．" => "♴", "." => "♵", "！" => "♶", "!" => "♷", "?" => "♸", "？" => "♹", "、" => "♺", "¡" => "⚀", "¿" => "⚁", "„" => "⚂", "“" => "⚃", "[" => "⚄", "]" => "⚅", "\"" => "☇", "#" => "☈", "$" => "☉", "%" => "☊", "&" => "☋", "(" => "☌", ")" => "☍", "*" => "☠", "+" => "☢", "," => "☣", ":" => "☤", ";" => "☥", "<" => "☦", "=" => "☧", ">" => "☀", "@" => "☁", "^" => "☂", "_" => "☃", "`" => "☄", "'" => "☮", "{" => "♔", "|" => "♕", "}" => "♖", "~" => "♗", "-" => "♘", "«" => "♙", "»" => "♚", "”" => "⚘", "‘" => "⚭" }.freeze

ABBREVIATIONS =

Set.new([]).freeze

STOP_WORDS =

Set.new([]).freeze

CONTRACTIONS =

{}.freeze