Class: Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/rdparse.rb

Defined Under Namespace

Classes: LexToken, ParseError

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(language_name, debug_bool, locale, &block) ⇒ Parser 



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

def initialize(language_name, debug_bool, locale, &block)
  @debug_mode = debug_bool
  @logger = Logger.new(STDOUT) if @debug_mode
  @lex_tokens = []
  @rules = {}
  @start = nil
  @language_name = language_name
  @file_string = ''

  create_tokens_from_locale(locale)

  false_value = @token_list['(false|true)'].split('|')[0]# Hacky solution to convoluted tokens
  true_value = @token_list['(false|true)'].split('|')[1]
  true_value = true_value[0..-2]
  false_value = false_value[1..]

  ScopeManager.new(true_value, false_value) # Hacky solution to convoluted tokens

  instance_eval(&block)
end

Instance Attribute Details

#logger ⇒ Object (readonly)

Returns the value of attribute logger.



123
124
125
 
# File 'lib/rdparse.rb', line 123

def logger
  @logger
end

#pos ⇒ Object

Returns the value of attribute pos.



122
123
124
 
# File 'lib/rdparse.rb', line 122

def pos
  @pos
end

#rules ⇒ Object (readonly)

Returns the value of attribute rules.



123
124
125
 
# File 'lib/rdparse.rb', line 123

def rules
  @rules
end

#string ⇒ Object (readonly)

Returns the value of attribute string.



123
124
125
 
# File 'lib/rdparse.rb', line 123

def string
  @string
end

Instance Method Details

#convert_regex_sensitive_token(token) ⇒ Object 



190
191
192
193
194
195
196
197
198
199
200
201
202
 
# File 'lib/rdparse.rb', line 190

def convert_regex_sensitive_token(token)
    token = @token_list['end'] if token == :STOP    # fulhack pga :END påstods inte funka för länge sen
    token = '[(]' if token == '('
    token = '[)]' if token == ')'
    token = '[+]' if token == '+'
    token = '[-]' if token == '-'
    token = '[*]' if token == '*'
    token = '[/]' if token == '/'
    token = "#{@token_list['(not|!)'].split('|')[0][1..]}" if token == :NOT
    token = "#{@token_list['(and|&&)'].split('|')[0][1..]}" if token == :AND
    token = "#{@token_list['(or|\|\|)'].split('|')[0][1..]}" if token == :OR
    token
end

#create_tokens_from_locale(locale) ⇒ Object

Recreate the tokenlist using the chosen locale file



150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'lib/rdparse.rb', line 150

def create_tokens_from_locale(locale)
  if locale == 'default'
    lang_file = File.read("#{LOCALES_PATH}/#{locale}")
    token_pairs = File.readlines("#{LOCALES_PATH}/#{lang_file}")
  else
    token_pairs = File.readlines("#{LOCALES_PATH}/#{locale}")
  end
  @token_list = Hash.new
  token_pairs.each do |pair|
    default_value, locale_value = pair.split(' ')
    @token_list[default_value] = locale_value
  end
end

#expect(tok) ⇒ Object

Return the next token in the queue



274
275
276
277
278
279
280
281
282
283
284
 
# File 'lib/rdparse.rb', line 274

def expect(tok)
  return tok if tok == :empty
  t = next_token
  if @pos - 1 > @max_pos
    @max_pos = @pos - 1
    @expected = []
  end
  return t if tok === t
  @expected << tok if @max_pos == @pos - 1 && !@expected.include?(tok)
  return nil
end

#find_faulty_line ⇒ Object

Raises:



224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
 
# File 'lib/rdparse.rb', line 224

def find_faulty_line
  tokens_before_problem = find_surrounding_code(@max_pos - 1)
  file_as_array_without_whitespaces = translate_tokens_array(tokens_before_problem)

  pattern = file_as_array_without_whitespaces.join('\s*')
  regex = Regexp.new(pattern)

  cleaned_string = @file_string.gsub(/;;.*/, '')

  match_data = regex.match(cleaned_string)
  num_lines = match_data[0].count("\n") + 1

  problem = @tokens[@max_pos]
  problem = @token_list[problem.to_s.downcase] unless @token_list[problem.to_s.downcase].is_a?(NilClass)

  raise ParseError, "There is a problem around line #{num_lines}. Found <#{problem}>"
end

#find_surrounding_code(problem_pos) ⇒ Object 



214
215
216
217
218
219
220
221
222
 
# File 'lib/rdparse.rb', line 214

def find_surrounding_code(problem_pos)
  tokens_before_problem = []
  temp = problem_pos
  while temp >= 0
    tokens_before_problem << @tokens[temp]
    temp -= 1
  end
  tokens_before_problem.reverse
end

#next_token ⇒ Object 



268
269
270
271
 
# File 'lib/rdparse.rb', line 268

def next_token
  @pos += 1
  return @tokens[@pos - 1]
end

#parse(string) ⇒ Object 



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
 
# File 'lib/rdparse.rb', line 242

def parse(string)
  # First, split the string according to the "token" instructions given.
  # Afterwards @tokens contains all tokens that are to be parsed.
  @file_string = string
  tokenize(string)

  # These variables are used to match if the total number of tokens
  # are consumed by the parser
  @pos = 0
  @max_pos = 0
  @expected = []
  # Parse (and evaluate) the tokens received
  result = @start.parse
  # If there are unparsed extra tokens, signal error
  if @pos != @tokens.size

    if @tokens[@max_pos] == '(' || @tokens[@max_pos] == ')'
      raise ParseError, 'Mismatched parenthesis! In Emacs: M-x check-parens RET'
    end

    # raise ParseError, "Parse error. expected: '#{@expected.join(', ')}', found '#{@tokens[@max_pos]}'"
    return find_faulty_line
  end
  return result
end

#to_s ⇒ Object 



286
287
288
 
# File 'lib/rdparse.rb', line 286

def to_s
  "Parser for #{@language_name}"
end

#tokenize(string) ⇒ Object

Tokenize the string into small pieces



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
 
# File 'lib/rdparse.rb', line 165

def tokenize(string)
  @tokens = []
  @string = string.clone
  until string.empty?
    # Unless any of the valid tokens of our language are the prefix of
    # 'string', we fail with an exception
    raise ParseError, "unable to lex '#{string}" unless @lex_tokens.any? do |tok|
      match = tok.pattern.match(string)
      # The regular expression of a token has matched the beginning of 'string'
      if match
        @logger.debug("Token #{match[0]} consumed as #{match[0]}") if @debug_mode
        # Also, evaluate this expression by using the block
        # associated with the token
        @tokens << tok.block.call(match.to_s) if tok.block
        # consume the match and proceed with the rest of the string
        string = match.post_match
        true
      else
        # this token pattern did not match, try the next
        false
      end # if
    end # raise
  end # until
end

#translate_tokens_array(array) ⇒ Object 



204
205
206
207
208
209
210
211
212
 
# File 'lib/rdparse.rb', line 204

def translate_tokens_array(array)
  result = []
  array.each do |token|
    token = convert_regex_sensitive_token(token)
    result << token unless token.is_a?(Symbol)
    result << @token_list[token.to_s.downcase] if token.is_a?(Symbol)
  end
  result
end