Class: TBMX::Tokenizer
- Inherits:
-
Object
- Object
- TBMX::Tokenizer
- Defined in:
- lib/tbmx.rb
Instance Attribute Summary collapse
-
#text ⇒ Object
readonly
Returns the value of attribute text.
-
#tokens ⇒ Object
readonly
Returns the value of attribute tokens.
Instance Method Summary collapse
-
#initialize(text) ⇒ Tokenizer
constructor
A new instance of Tokenizer.
- #tokenize ⇒ Object
Constructor Details
#initialize(text) ⇒ Tokenizer
Returns a new instance of Tokenizer.
208 209 210 211 |
# File 'lib/tbmx.rb', line 208 def initialize(text) @text = text tokenize end |
Instance Attribute Details
#text ⇒ Object (readonly)
Returns the value of attribute text.
207 208 209 |
# File 'lib/tbmx.rb', line 207 def text @text end |
#tokens ⇒ Object (readonly)
Returns the value of attribute tokens.
207 208 209 |
# File 'lib/tbmx.rb', line 207 def tokens @tokens end |
Instance Method Details
#tokenize ⇒ Object
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 |
# File 'lib/tbmx.rb', line 213 def tokenize @tokens = [] rest = text.gsub("\r", "") while rest.length > 0 if result = BackslashToken.matches?(rest) or # Single Character Tokens result = LeftBraceToken.matches?(rest) or result = RightBraceToken.matches?(rest) or result = EmptyNewlinesToken.matches?(rest) or # String Tokens result = WhitespaceToken.matches?(rest) or result = NumberToken.matches?(rest) or result = WordToken.matches?(rest) then @tokens << result[0] rest = result[1] else raise RuntimeError, "Couldn't tokenize the remaining text." end end return @tokens end |