Class: Lrama::Lexer

Inherits:
Object
  • Object
show all
Defined in:
lib/lrama/lexer.rb,
lib/lrama/lexer/token.rb,
lib/lrama/lexer/location.rb,
lib/lrama/lexer/token/int.rb,
lib/lrama/lexer/token/str.rb,
lib/lrama/lexer/token/tag.rb,
lib/lrama/lexer/token/base.rb,
lib/lrama/lexer/token/char.rb,
lib/lrama/lexer/token/empty.rb,
lib/lrama/lexer/token/ident.rb,
lib/lrama/lexer/token/token.rb,
lib/lrama/lexer/grammar_file.rb,
lib/lrama/lexer/token/user_code.rb,
lib/lrama/lexer/token/instantiate_rule.rb

Defined Under Namespace

Modules: Token Classes: GrammarFile, Location

Constant Summary collapse

SYMBOLS =

: Array

['%{', '%}', '%%', '{', '}', '\[', '\]', '\(', '\)', '\,', ':', '\|', ';'].freeze
PERCENT_TOKENS = 
%w(
  %union
  %token
  %type
  %nterm
  %left
  %right
  %nonassoc
  %expect
  %define
  %require
  %printer
  %destructor
  %lex-param
  %parse-param
  %initial-action
  %precedence
  %prec
  %error-token
  %before-reduce
  %after-reduce
  %after-shift-error-token
  %after-shift
  %after-pop-stack
  %empty
  %code
  %rule
  %no-stdlib
  %inline
  %locations
  %categories
  %start
).freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(grammar_file) ⇒ Lexer

Returns a new instance of Lexer.



67
68
69
70
71
72
73
74
 
# File 'lib/lrama/lexer.rb', line 67

def initialize(grammar_file)
  @grammar_file = grammar_file
  @scanner = StringScanner.new(grammar_file.text)
  @head_column = @head = @scanner.pos
  @head_line = @line = 1
  @status = :initial
  @end_symbol = nil
end

Instance Attribute Details

#end_symbol ⇒ Object

: String?



29
30
31
 
# File 'lib/lrama/lexer.rb', line 29

def end_symbol
  @end_symbol
end

#head_column ⇒ Object (readonly)

: Integer



26
27
28
 
# File 'lib/lrama/lexer.rb', line 26

def head_column
  @head_column
end

#head_line ⇒ Object (readonly)

@rbs!

type token = lexer_token | c_token

type lexer_token = [String, Token::Token]  |
                 [::Symbol, Token::Tag]  |
                 [::Symbol, Token::Char] |
                 [::Symbol, Token::Str]  |
                 [::Symbol, Token::Int]  |
                 [::Symbol, Token::Ident]

type c_token = [:C_DECLARATION, Token::UserCode]


25
26
27
 
# File 'lib/lrama/lexer.rb', line 25

def head_line
  @head_line
end

#line ⇒ Object (readonly)

: Integer



27
28
29
 
# File 'lib/lrama/lexer.rb', line 27

def line
  @line
end

#status ⇒ Object

: :initial | :c_declaration



28
29
30
 
# File 'lib/lrama/lexer.rb', line 28

def status
  @status
end

Instance Method Details

#column ⇒ Object 



87
88
89
 
# File 'lib/lrama/lexer.rb', line 87

def column
  @scanner.pos - @head
end

#lex_c_code ⇒ Object

Raises:

  • (ParseError) 


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
178
179
180
181
182
183
184
185
186
187
188
189
190
 
# File 'lib/lrama/lexer.rb', line 153

def lex_c_code
  nested = 0
  code = +''
  reset_first_position

  until @scanner.eos? do
    case
    when @scanner.scan(/{/)
      code << @scanner.matched
      nested += 1
    when @scanner.scan(/}/)
      if nested == 0 && @end_symbol == '}'
        @scanner.unscan
        return [:C_DECLARATION, Lrama::Lexer::Token::UserCode.new(s_value: code, location: location)]
      else
        code << @scanner.matched
        nested -= 1
      end
    when @scanner.check(/#{@end_symbol}/)
      return [:C_DECLARATION, Lrama::Lexer::Token::UserCode.new(s_value: code, location: location)]
    when @scanner.scan(/\n/)
      code << @scanner.matched
      newline
    when @scanner.scan(/".*?"/)
      code << %Q(#{@scanner.matched})
      @line += @scanner.matched.count("\n")
    when @scanner.scan(/'.*?'/)
      code << %Q(#{@scanner.matched})
    when @scanner.scan(/[^\"'\{\}\n]+/)
      code << @scanner.matched
    when @scanner.scan(/#{Regexp.escape(@end_symbol)}/) # steep:ignore
      code << @scanner.matched
    else
      code << @scanner.getch
    end
  end
  raise ParseError, location.generate_error_message("Unexpected code: #{code}") # steep:ignore UnknownConstant
end

#lex_token ⇒ Object 



101
102
103
104
105
106
107
108
109
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
# File 'lib/lrama/lexer.rb', line 101

def lex_token
  until @scanner.eos? do
    case
    when @scanner.scan(/\n/)
      newline
    when @scanner.scan(/\s+/)
      @scanner.matched.count("\n").times { newline }
    when @scanner.scan(/\/\*/)
      lex_comment
    when @scanner.scan(/\/\/.*(?<newline>\n)?/)
      newline if @scanner[:newline]
    else
      break
    end
  end

  reset_first_position

  case
  when @scanner.eos?
    return
  when @scanner.scan(/#{SYMBOLS.join('|')}/)
    return [@scanner.matched, Lrama::Lexer::Token::Token.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/#{PERCENT_TOKENS.join('|')}/)
    return [@scanner.matched, Lrama::Lexer::Token::Token.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/[\?\+\*]/)
    return [@scanner.matched, Lrama::Lexer::Token::Token.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/<\w+>/)
    return [:TAG, Lrama::Lexer::Token::Tag.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/'.'/)
    return [:CHARACTER, Lrama::Lexer::Token::Char.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/'\\\\'|'\\b'|'\\t'|'\\f'|'\\r'|'\\n'|'\\v'|'\\13'/)
    return [:CHARACTER, Lrama::Lexer::Token::Char.new(s_value: @scanner.matched, location: location)]
  when @scanner.scan(/".*?"/)
    return [:STRING, Lrama::Lexer::Token::Str.new(s_value: %Q(#{@scanner.matched}), location: location)]
  when @scanner.scan(/\d+/)
    return [:INTEGER, Lrama::Lexer::Token::Int.new(s_value: Integer(@scanner.matched), location: location)]
  when @scanner.scan(/([a-zA-Z_.][-a-zA-Z0-9_.]*)/)
    token = Lrama::Lexer::Token::Ident.new(s_value: @scanner.matched, location: location)
    type =
      if @scanner.check(/\s*(\[\s*[a-zA-Z_.][-a-zA-Z0-9_.]*\s*\])?\s*:/)
        :IDENT_COLON
      else
        :IDENTIFIER
      end
    return [type, token]
  else
    raise ParseError, location.generate_error_message("Unexpected token") # steep:ignore UnknownConstant
  end
end

#location ⇒ Object 



92
93
94
95
96
97
98
 
# File 'lib/lrama/lexer.rb', line 92

def location
  Location.new(
    grammar_file: @grammar_file,
    first_line: @head_line, first_column: @head_column,
    last_line: line, last_column: column
  )
end

#next_token ⇒ Object 



77
78
79
80
81
82
83
84
 
# File 'lib/lrama/lexer.rb', line 77

def next_token
  case @status
  when :initial
    lex_token
  when :c_declaration
    lex_c_code
  end
end