Class: Lisp::Tokenizer

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

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(src) ⇒ Tokenizer 



7
8
9
10
11
12
 
# File 'lib/rubylisp/tokenizer.rb', line 7

def initialize(src)
  @lookahead_token = 0
  @lookahead_literal = ''
  @source = src
  @position = 0
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

Instance Method Details

#almost_eof? ⇒ Boolean 



22
23
24
 
# File 'lib/rubylisp/tokenizer.rb', line 22

def almost_eof?
  @position == @source.length - 1
end

#consume_token ⇒ Object 



280
281
282
283
 
# File 'lib/rubylisp/tokenizer.rb', line 280

def consume_token
  @lookahead_token, @lookahead_literal = read_next_token
  consume_token if @lookahead_token == :COMMENT
end

#digit?(ch) ⇒ Boolean 



38
39
40
 
# File 'lib/rubylisp/tokenizer.rb', line 38

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

#divider?(ch) ⇒ Boolean 



152
153
154
 
# File 'lib/rubylisp/tokenizer.rb', line 152

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

#eof? ⇒ Boolean 



18
19
20
 
# File 'lib/rubylisp/tokenizer.rb', line 18

def eof?
  @position >= @source.length
end

#hex?(ch) ⇒ Boolean 



34
35
36
 
# File 'lib/rubylisp/tokenizer.rb', line 34

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

#init ⇒ Object 



285
286
287
288
 
# File 'lib/rubylisp/tokenizer.rb', line 285

def init
  @line_number = 0
  consume_token
end

#letter?(ch) ⇒ Boolean 



30
31
32
 
# File 'lib/rubylisp/tokenizer.rb', line 30

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

#next_char ⇒ Object 



26
27
28
 
# File 'lib/rubylisp/tokenizer.rb', line 26

def next_char
  almost_eof? ? nil : @source[@position + 1]
end

#next_token ⇒ Object 



14
15
16
 
# File 'lib/rubylisp/tokenizer.rb', line 14

def next_token
  return @lookahead_token, @lookahead_literal
end

#number?(ch) ⇒ Boolean 



42
43
44
 
# File 'lib/rubylisp/tokenizer.rb', line 42

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

#process_escapes(str) ⇒ Object 



110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
# File 'lib/rubylisp/tokenizer.rb', line 110

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 



157
158
159
160
161
162
163
164
165
166
 
# File 'lib/rubylisp/tokenizer.rb', line 157

def read_character
  @position += 2
  start = @position
  @position += 1
  while !eof? && !divider?(@source[@position])
    @position += 1
  end

  return :CHARACTER, @source[start...@position]
end

#read_next_token ⇒ Object 



169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
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
 
# File 'lib/rubylisp/tokenizer.rb', line 169

def read_next_token
  return :EOF, '' if eof?

  while space?(@source[@position])
    @line_number += 1 if @source[@position] == ?\n
    @position += 1
    return :EOF, '' if eof?
  end

  current_ch = @source[@position]
  next_ch = @source[@position + 1] unless almost_eof?

  if letter?(current_ch) || ('*._'.include?(current_ch) && letter?(next_ch))
    return read_symbol
  elsif number?(current_ch)
    return read_number
  elsif current_ch == ?- && number?(next_ch)
    return read_number
  elsif current_ch == ?# && next_ch == ?x
    return read_number
  elsif current_ch == ?"
    return read_string
  elsif current_ch == ?# && next_ch == ?\\
    return read_character
  elsif current_ch == ?'
    @position += 1
    return :QUOTE, "'"
  elsif current_ch == ?`
    @position += 1
    return :BACKQUOTE, "`"
  elsif current_ch == ?, && next_ch == ?@
    @position += 2
    return :COMMAAT, ",@"
  elsif current_ch == ?,
    @position += 1
    return :COMMA, ","
  elsif current_ch == ?(
    @position += 1
    return :LPAREN, "("
  elsif current_ch == ?)
    @position += 1
    return :RPAREN, ")"
  elsif current_ch == ?{
    @position += 1
    return :LBRACE, "{"
  elsif current_ch == ?}
    @position += 1
    return :RBRACE, "}"
  elsif current_ch == ?[
    @position += 1
    return :LBRACKET, "["
  elsif current_ch == ?]
    @position += 1
    return :RBRACKET, "]"
  elsif current_ch == ?.
    @position += 1
    return :PERIOD, "."
  elsif current_ch == ?/ && next_ch == ?=
    @position += 2
    return :SYMBOL, "!="
  elsif current_ch == ?- && next_ch == ?>
    @position += 2
    return :SYMBOL, "->"
  elsif current_ch == ?= && next_ch == ?>
    @position += 2
    return :SYMBOL, "=>"
  elsif "+-*/%".include?(current_ch)
    @position += 1
    return :SYMBOL, current_ch.to_s
  elsif current_ch == ?< && next_ch == ?=
    @position += 2
    return :SYMBOL, "<="
  elsif current_ch == ?<
    @position += 1
    return :SYMBOL, "<"
  elsif current_ch == ?> && next_ch == ?=
    @position += 2
    return :SYMBOL, ">="
  elsif current_ch == ?>
    @position += 1
    return :SYMBOL, ">"
  elsif current_ch == ?= && next_ch == ?=
    @position += 2
    return :SYMBOL, "="
  elsif current_ch == ?=
    @position += 1
    return :SYMBOL, "="
  elsif current_ch == ?! && next_ch == ?=
    @position += 2
    return :SYMBOL, "!="
  elsif current_ch == ?!
    @position += 1
    return :SYMBOL, "!"
  elsif current_ch == ?# && next_ch == ?t
    @position += 2
    return :TRUE, "#t"
  elsif current_ch == ?# && next_ch == ?f
    @position += 2
    return :FALSE, "#f"
  elsif current_ch == ?;
    start = @position
    while true
      return :COMMENT, @source[start..-1] if eof?
      return :COMMENT, @source[start...@position] if @source[@position] == ?\n
      @position += 1
    end
  else
    return :ILLEGAL, ''
  end
end

#read_number ⇒ Object 



85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
# File 'lib/rubylisp/tokenizer.rb', line 85

def read_number
  start = @position
  @position += 1 if @source[@position] == '-'
  hex = @source[@position, 2] == "#x"
  is_float = false
  @position += 2 if hex
  ch = @source[@position]
  while !eof? && (digit?(ch) || (hex && hex?(ch)) || (!hex && !is_float && ch == ?.))
    is_float ||= (ch == ?.)
    @position += 1
    ch = @source[@position]
  end

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

  return tok, @source[start...@position]
end

#read_string ⇒ Object 



139
140
141
142
143
144
145
146
147
148
149
 
# File 'lib/rubylisp/tokenizer.rb', line 139

def read_string
  start = @position
  @position += 1
  while !eof? && @source[@position] != ?"
    @position += 1
  end

  return :EOF, '' if eof?
  @position += 1
  return :STRING, process_escapes(@source[start...@position])
end

#read_symbol ⇒ Object 



58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
 
# File 'lib/rubylisp/tokenizer.rb', line 58

def read_symbol
  start = @position
  tok = nil
  if @source[@position] == '.'
    @position += 1
    tok = :FFI_SEND_SYMBOL
  end

  while !eof? && (symbol_character?(@source[@position]) ||
                  (@source[@position] == '.' && !symbol_character?(@source[@position+1]) && tok.nil?) ||
                  (@source[@position] == '/' && symbol_character?(@source[@position+1])))
    tok ||= :FFI_NEW_SYMBOL if @source[@position] == '.'
    tok = :FFI_STATIC_SYMBOL if @source[@position] == '/'
    @position += 1
  end

  tok ||= :SYMBOL
  return tok, case tok
              when :SYMBOL, :FFI_STATIC_SYMBOL
                @source[start...@position]
              when :FFI_SEND_SYMBOL
                @source[start+1...@position]
              when :FFI_NEW_SYMBOL
                @source[start...@position-1]
              end
end

#space?(ch) ⇒ Boolean 



47
48
49
 
# File 'lib/rubylisp/tokenizer.rb', line 47

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

#symbol_character?(ch) ⇒ Boolean 



52
53
54
55
56
 
# File 'lib/rubylisp/tokenizer.rb', line 52

def symbol_character?(ch)
  return true if letter?(ch)
  return true if (?0..?9).include?(ch)
  return "-_?!:*=<>".include?(ch)
end