Class: Lisp::Tokenizer

Inherits:
Object show all
Defined in:
lib/rubylisp/tokenizer.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(src, absorb_space = true) ⇒ Tokenizer

Returns a new instance of Tokenizer.



15
16
17
18
19
20
21
22
23
24
25
26
27
 
# File 'lib/rubylisp/tokenizer.rb', line 15

def initialize(src, absorb_space=true)
  @absorb_whitespace = absorb_space
  @source = src
  @position = 0
  @lookahead_token = nil
  @lookahead_literal = ''
  @eof = false
  @almost_eof = false
  @curent_ch = nil
  @next_ch = nil
  @next_next_ch = nil
  init
end

Instance Attribute Details

#line_number ⇒ Object (readonly)

Returns the value of attribute line_number.



5
6
7
 
# File 'lib/rubylisp/tokenizer.rb', line 5

def line_number
  @line_number
end

Class Method Details

.from_file(f) ⇒ Object 



11
12
13
 
# File 'lib/rubylisp/tokenizer.rb', line 11

def self.from_file(f)
  self.new(f)
end

.from_string(str, absorb_space = true) ⇒ Object 



7
8
9
 
# File 'lib/rubylisp/tokenizer.rb', line 7

def self.from_string(str, absorb_space=true)
  self.new(StringIO.new(str, "r"), absorb_space)
end

Instance Method Details

#advance ⇒ Object 



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
 
# File 'lib/rubylisp/tokenizer.rb', line 30

def advance
  if @source.eof?
    @eof = true
    @almost_eof = true
    @current_ch = nil
    @next_ch = nil
  else
    @current_ch = @source.readchar
    if @source.eof?
      @almost_eof = true
      @next_ch = nil
    else
      @next_ch = @source.readchar
      if @source.eof?
        @next_next_ch = nil
      else
        @next_next_ch = @source.readchar
        @source.ungetc(@next_next_ch)
      end
      @source.ungetc(@next_ch)
    end
  end
end

#almost_eof? ⇒ Boolean

Returns:



62
63
64
 
# File 'lib/rubylisp/tokenizer.rb', line 62

def almost_eof?
  @almost_eof
end

#consume_token ⇒ Object 



313
314
315
316
317
 
# File 'lib/rubylisp/tokenizer.rb', line 313

def consume_token
  @position = @source.pos
  @lookahead_token, @lookahead_literal = self.read_next_token
  consume_token if @lookahead_token == :COMMENT
end

#digit?(ch) ⇒ Boolean

Returns:



74
75
76
 
# File 'lib/rubylisp/tokenizer.rb', line 74

def digit?(ch)
  ch =~ /[[:digit:]]/
end

#divider?(ch) ⇒ Boolean

Returns:



193
194
195
 
# File 'lib/rubylisp/tokenizer.rb', line 193

def divider?(ch)
  ch =~ /[[[:space:]]\(\)\{\}<>\[\]]/
end

#eof? ⇒ Boolean

Returns:



58
59
60
 
# File 'lib/rubylisp/tokenizer.rb', line 58

def eof?
  @eof
end

#graph?(ch) ⇒ Boolean

Returns:



88
89
90
 
# File 'lib/rubylisp/tokenizer.rb', line 88

def graph?(ch)
  ch =~ /[[:graph:]]/
end

#hex?(ch) ⇒ Boolean

Returns:



70
71
72
 
# File 'lib/rubylisp/tokenizer.rb', line 70

def hex?(ch)
  ch =~ /[abcdefABCDEF]/
end

#init ⇒ Object 



319
320
321
322
323
 
# File 'lib/rubylisp/tokenizer.rb', line 319

def init
  @line_number = 0
  advance
  consume_token
end

#letter?(ch) ⇒ Boolean

Returns:



66
67
68
 
# File 'lib/rubylisp/tokenizer.rb', line 66

def letter?(ch)
  ch =~ /[[:alpha:]]/
end

#next_token ⇒ Object 



54
55
56
 
# File 'lib/rubylisp/tokenizer.rb', line 54

def next_token
  return @position, @lookahead_token, @lookahead_literal
end

#number?(ch) ⇒ Boolean

Returns:



78
79
80
 
# File 'lib/rubylisp/tokenizer.rb', line 78

def number?(ch)
  digit?(ch) || (ch == '-' && digit?(@next_ch))
end

#process_escapes(str) ⇒ Object 



151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
 
# File 'lib/rubylisp/tokenizer.rb', line 151

def process_escapes(str)
  i = 0
  processed_str = ""
  while i < str.length
    if str[i] == '\\'
      processed_str << if i < (str.length - 1)
                         i += 1
                         case (str[i])
                         when 'n'
                           "\n"
                         when 't'
                           "\t"
                         when '\\'
                           "\\"
                         else
                           "\\#{str[i]}"
                         end
                       else
                         "\\"
                       end
    else
      processed_str << str[i]
    end
    i += 1
  end
  processed_str
end

#read_character ⇒ Object 



198
199
200
201
202
203
204
205
206
207
208
 
# File 'lib/rubylisp/tokenizer.rb', line 198

def read_character
  lit = ""
  lit << @current_ch
  advance
  while !eof? && !divider?(@current_ch)
    lit << @current_ch
    advance
  end

  return :CHARACTER, lit
end

#read_next_token ⇒ Object 



211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
 
# File 'lib/rubylisp/tokenizer.rb', line 211

def read_next_token
  return :EOF, '' if eof?

  if @absorb_whitespace
    while space?(@current_ch)
      @line_number += 1 if @current_ch == "\n"
      advance
      @position = @source.pos
      return :EOF, '' if eof?
    end
  end
  
  if !@absorb_whitespace && space?(@current_ch)
    @line_number += 1 if @current_ch == "\n"
    advance
    return :WHITESPACE, " "
  elsif number?(@current_ch)
    return read_number(false)
  elsif @current_ch == '-' && number?(@next_ch)
    return read_number(false)
  elsif @current_ch == '#' && @next_ch == 'x'
    advance
    advance
    return read_number(true)
  elsif @current_ch == '"'
    advance
    return read_string
  elsif @current_ch == '#' && @next_ch == '\\'
    advance
    advance
    return read_character
  elsif @current_ch == '\'' && @next_ch == '{'
    advance
    advance
    return :QUOTE_LBRACE, "'{"
  elsif @current_ch == '\'' && @next_ch == '#' && @next_next_ch == '('
    advance
    advance
    advance
    return :QUOTE_HASH_LPAREN, "'#("
  elsif @current_ch == '\''
    advance
    return :QUOTE, "'"
  elsif @current_ch == '`'
    advance
    return :BACKQUOTE, "`"
  elsif @current_ch == ',' && @next_ch == '@'
    advance
    advance
    return :COMMAAT, ",@"
  elsif @current_ch == ','
    advance
    return :COMMA, ","
  elsif @current_ch == '('
    advance
    return :LPAREN, "("
  elsif @current_ch == '#' && @next_ch == '('
    advance
    advance
    return :HASH_LPAREN, "#("
  elsif @current_ch == ')'
    advance
    return :RPAREN, ")"
  elsif @current_ch == '{'
    advance
    return :LBRACE, "{"
  elsif @current_ch == '}'
    advance
    return :RBRACE, "}"
  elsif @current_ch == '['
    advance
    return :LBRACKET, "["
  elsif @current_ch == ']'
    advance
    return :RBRACKET, "]"
  elsif @current_ch == '.' && space?(@next_ch)
    advance
    return :PERIOD, "."
  elsif @current_ch == '.' && symbol_character?(@next_ch)
    return read_symbol
    elsif symbol_character?(@current_ch)
      return read_symbol
    elsif @current_ch == '#' && @next_ch == 't'
    advance
    advance
    return :TRUE, "#t"
  elsif @current_ch == '#' && @next_ch == 'f'
    advance
    advance
    return :FALSE, "#f"
  elsif @current_ch == ';'
    lit = ""
    while true
      return :COMMENT, lit if eof? || @current_ch == "\n"
      lit << @current_ch
      advance
    end
  else
    return :ILLEGAL, @current_ch
  end
end

#read_number(hex) ⇒ Object 



126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/rubylisp/tokenizer.rb', line 126

def read_number(hex)
  lit = ""
  if @current_ch == '-'
    lit << @current_ch
    advance
  end
  is_float = false
  while !eof? && (digit?(@current_ch) || (hex && hex?(@current_ch)) || (!hex && !is_float && @current_ch == '.'))
    is_float ||= !hex && (@current_ch == '.')
    lit << @current_ch
    advance
  end

  tok = if hex
          :HEXNUMBER
        elsif is_float
          :FLOAT
        else
          :NUMBER
        end

  return tok, lit
end

#read_string ⇒ Object 



180
181
182
183
184
185
186
187
188
189
190
 
# File 'lib/rubylisp/tokenizer.rb', line 180

def read_string
  lit = ""
  while !eof? && @current_ch != '"'
    lit << @current_ch
    advance
  end

  return :EOF, '' if eof?
  advance
  return :STRING, process_escapes(lit)
end

#read_symbol ⇒ Object 



97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
 
# File 'lib/rubylisp/tokenizer.rb', line 97

def read_symbol
  lit = ""
  tok = nil
  if @current_ch == '.'
    lit << @current_ch
    advance
    tok = :FFI_SEND_SYMBOL
  end

  while !eof? && ((@current_ch == '.' && !symbol_character?(@next_ch) && tok.nil?) ||
                  (@current_ch == '/' && symbol_character?(@next_ch)) ||
                  (symbol_character?(@current_ch)))
    tok ||= :FFI_NEW_SYMBOL if @current_ch == '.' && !lit.empty?
    tok = :FFI_STATIC_SYMBOL if @current_ch == '/' && !lit.empty?
    lit << @current_ch
    advance
  end

  tok ||= :SYMBOL
  return tok, case tok
              when :SYMBOL, :FFI_STATIC_SYMBOL
                lit
              when :FFI_SEND_SYMBOL
                lit[1..-1]
              when :FFI_NEW_SYMBOL
                lit[0..-2]
              end
end

#space?(ch) ⇒ Boolean

Returns:



83
84
85
 
# File 'lib/rubylisp/tokenizer.rb', line 83

def space?(ch)
  ch =~ /[[:space:]]/
end

#symbol_character?(ch) ⇒ Boolean

Returns:



93
94
95
 
# File 'lib/rubylisp/tokenizer.rb', line 93

def symbol_character?(ch)
  graph?(ch) && !("();\"'`|[]{}#,.".include?(ch))
end