Class: CodeRay::Scanners::C

Inherits:
Scanner
  • Object
show all
Includes:
CodeRay::Streamable
Defined in:
lib/coderay/scanners/c.rb

Constant Summary collapse

RESERVED_WORDS = 
[
  'asm', 'break', 'case', 'continue', 'default', 'do',
  'else', 'enum', 'for', 'goto', 'if', 'return',
  'sizeof', 'struct', 'switch', 'typedef', 'union', 'while',
  'restrict',  # added in C99
]
PREDEFINED_TYPES = 
[
  'int', 'long', 'short', 'char',
  'signed', 'unsigned', 'float', 'double',
  'bool', 'complex',  # added in C99
]
PREDEFINED_CONSTANTS = 
[
  'EOF', 'NULL',
  'true', 'false',  # added in C99
]
DIRECTIVES = 
[
  'auto', 'extern', 'register', 'static', 'void',
  'const', 'volatile',  # added in C89
  'inline',  # added in C99
]
IDENT_KIND = 
WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_TYPES, :pre_type).
add(DIRECTIVES, :directive).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = 
/ [rbfntv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = 
/ u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x

Constants inherited from Scanner

Scanner::DEFAULT_OPTIONS, Scanner::KINDS_NOT_LOC, Scanner::ScanError

Instance Method Summary collapse

Methods inherited from Scanner

#column, #each, file_extension, #initialize, #line, #marshal_dump, #marshal_load, normify, #reset, streamable?, #streaming?, #string=, #tokenize, #tokens

Methods included from Plugin

#helper, #included, #plugin_host, #plugin_id, #register_for, #title

Constructor Details

This class inherits a constructor from CodeRay::Scanners::Scanner

Instance Method Details

#scan_tokens(tokens, options) ⇒ Object 



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
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
84
85
86
87
88
89
90
91
92
93
94
95
96
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
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
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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'lib/coderay/scanners/c.rb', line 43

def scan_tokens tokens, options

  state = :initial
  label_expected = true
  case_expected = false
  label_expected_before_preproc_line = nil
  in_preproc_line = false

  until eos?

    kind = nil
    match = nil
    
    case state

    when :initial

      if match = scan(/ \s+ | \\\n /x)
        if in_preproc_line && match != "\\\n" && match.index(?\n)
          in_preproc_line = false
          label_expected = label_expected_before_preproc_line
        end
        tokens << [match, :space]
        next

      elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
        kind = :comment

      elsif match = scan(/ \# \s* if \s* 0 /x)
        match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
        kind = :comment

      elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
        label_expected = match =~ /[;\{\}]/
        if case_expected
          label_expected = true if match == ':'
          case_expected = false
        end
        kind = :operator

      elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
        kind = IDENT_KIND[match]
        if kind == :ident && label_expected && !in_preproc_line && scan(/:(?!:)/)
          kind = :label
          match << matched
        else
          label_expected = false
          if kind == :reserved
            case match
            when 'case', 'default'
              case_expected = true
            end
          end
        end

      elsif scan(/\$/)
        kind = :ident
      
      elsif match = scan(/L?"/)
        tokens << [:open, :string]
        if match[0] == ?L
          tokens << ['L', :modifier]
          match = '"'
        end
        state = :string
        kind = :delimiter

      elsif scan(/#[ \t]*(\w*)/)
        kind = :preprocessor
        in_preproc_line = true
        label_expected_before_preproc_line = label_expected
        state = :include_expected if self[1] == 'include'

      elsif scan(/ L?' (?: [^\'\n\\] | \\ #{ESCAPE} )? '? /ox)
        label_expected = false
        kind = :char

      elsif scan(/0[xX][0-9A-Fa-f]+/)
        label_expected = false
        kind = :hex

      elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
        label_expected = false
        kind = :oct

      elsif scan(/(?:\d+)(?![.eEfF])L?L?/)
        label_expected = false
        kind = :integer

      elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
        label_expected = false
        kind = :float

      else
        getch
        kind = :error

      end

    when :string
      if scan(/[^\\\n"]+/)
        kind = :content
      elsif scan(/"/)
        tokens << ['"', :delimiter]
        tokens << [:close, :string]
        state = :initial
        label_expected = false
        next
      elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
        kind = :char
      elsif scan(/ \\ | $ /x)
        tokens << [:close, :string]
        kind = :error
        state = :initial
        label_expected = false
      else
        raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
      end

    when :include_expected
      if scan(/<[^>\n]+>?|"[^"\n\\]*(?:\\.[^"\n\\]*)*"?/)
        kind = :include
        state = :initial

      elsif match = scan(/\s+/)
        kind = :space
        state = :initial if match.index ?\n

      else
        state = :initial
        next

      end

    else
      raise_inspect 'Unknown state', tokens

    end

    match ||= matched
    if $DEBUG and not kind
      raise_inspect 'Error token %p in line %d' %
        [[match, kind], line], tokens
    end
    raise_inspect 'Empty token', tokens unless match

    tokens << [match, kind]

  end

  if state == :string
    tokens << [:close, :string]
  end

  tokens
end