module TextUtil

Extended Modules

• TextUtil

Defined in:

util/text_util.cr

Constant Summary

BR_RE = /\<br\s*\/?\>|\s{4,+}/i

FIX_MARKS = {"òa" => "oà", "óa" => "oá", "ỏa" => "oả", "õa" => "oã", "ọa" => "oạ", "òe" => "oè", "óe" => "oé", "ỏe" => "oẻ", "õe" => "oẽ", "ọe" => "oẹ", "ùy" => "uỳ", "úy" => "uý", "ủy" => "uỷ", "ũy" => "uỹ", "ụy" => "uỵ"}

MARK_RE = Regex.new(FIX_MARKS.keys.join('|'))

Instance Method Summary

• #canon_clean(input : String, upcase : Bool = false) : String

  convert all halfwidth to fullwidth and group similar characters

• #capitalize(input : String) : String

  smart capitalize: - don't downcase extra characters - treat unicode alphanumeric chars as upcase-able

• #clean_and_trim(input : String) : String
• #clean_spaces(input : String) : String
• #fix_viet(str : String)
• #normalize(input : String) : String

  Convert chinese punctuations to english punctuations and full width characters to ascii characters

• #normalize(input : Array(Char)) : Array(Char)

  Convert chinese punctuations to english punctuations and full width characters to ascii characters

• #slugify(input : String, tones = false) : String

  make url friendly string

• #split_html(input : String, fix_br : Bool = true) : Array(String)
• #split_spaces(input : String)
• #split_text(input : String, spaces_as_newline = true) : Array(String)
• #titleize(input : String) : String

  capitalize all words

• #tokenize(input : String, tones = false) : Array(String)

  split input to words

• #truncate(input : String, limit = 100)
• #unaccent(input : String) : String

  strip vietnamese accents

• #uniformize(input : String, upcase : Bool = false) : String

  convert all halfwidth to fullwidth and group similar characters

Instance Method Detail