Class: CodeRay::Scanners::Groovy

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

Constant Summary collapse

KEYWORDS =

TODO: Check this!

Java::KEYWORDS + %w[
  as assert def in
]
KEYWORDS_EXPECTING_VALUE = 
WordList.new.add %w[
  case instanceof new return throw typeof while as assert in
]
MAGIC_VARIABLES = 
Java::MAGIC_VARIABLES + %w[ it ]
IDENT_KIND =

DIRECTIVES = %w[

abstract extends final implements native private protected public
static strictfp synchronized threadsafe throws transient volatile

]

WordList.new(:ident).
add(KEYWORDS, :keyword).
add(MAGIC_VARIABLES, :local_variable).
add(TYPES, :type).
add(BuiltinTypes::List, :pre_type).
add(DIRECTIVES, :directive)
ESCAPE = 
/ [bfnrtv$\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE =

no 4-byte unicode chars? U8

/ u[a-fA-F0-9]{4} /x
REGEXP_ESCAPE = 
/ [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} | \d | [bBdDsSwW\/] /x
STRING_CONTENT_PATTERN =

TODO: interpretation inside ‘, “, /

{
  "'" => /(?>\\[^\\'\n]+|[^\\'\n]+)+/,
  '"' => /[^\\$"\n]+/,
  "'''" => /(?>[^\\']+|'(?!''))+/,
  '"""' => /(?>[^\\$"]+|"(?!""))+/,
  '/' => /[^\\$\/\n]+/,
}

Constants inherited from Java

Java::DIRECTIVES, Java::IDENT, Java::TYPES

Constants inherited from Scanner

Scanner::DEFAULT_OPTIONS, Scanner::ScanError

Instance Method Summary collapse

Methods inherited from Scanner

#column, #each, file_extension, #initialize, #line, 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 



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
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
 
# File 'lib/coderay/scanners/groovy.rb', line 45

def scan_tokens tokens, options

  state = :initial
  inline_block_stack = []
  inline_block_paren_depth = nil
  string_delimiter = nil
  import_clause = class_name_follows = last_token = after_def = false
  value_expected = true

  until eos?

    kind = nil
    match = nil
    
    case state

    when :initial

      if match = scan(/ \s+ | \\\n /x)
        tokens << [match, :space]
        if match.index ?\n
          import_clause = after_def = false
          value_expected = true unless value_expected
        end
        next
      
      elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
        value_expected = true
        after_def = false
        kind = :comment
      
      elsif bol? && scan(/ \#!.* /x)
        kind = :doctype
      
      elsif import_clause && scan(/ (?!as) #{IDENT} (?: \. #{IDENT} )* (?: \.\* )? /ox)
        after_def = value_expected = false
        kind = :include
      
      elsif match = scan(/ #{IDENT} | \[\] /ox)
        kind = IDENT_KIND[match]
        value_expected = (kind == :keyword) && KEYWORDS_EXPECTING_VALUE[match]
        if last_token == '.'
          kind = :ident
        elsif class_name_follows
          kind = :class
          class_name_follows = false
        elsif after_def && check(/\s*[({]/)
          kind = :method
          after_def = false
        elsif kind == :ident && last_token != '?' && check(/:/)
          kind = :key
        else
          class_name_follows = true if match == 'class' || (import_clause && match == 'as')
          import_clause = match == 'import'
          after_def = true if match == 'def'
        end
      
      elsif scan(/;/)
        import_clause = after_def = false
        value_expected = true
        kind = :operator
      
      elsif scan(/\{/)
        class_name_follows = after_def = false
        value_expected = true
        kind = :operator
        if !inline_block_stack.empty?
          inline_block_paren_depth += 1
        end
      
      # TODO: ~'...', ~"..." and ~/.../ style regexps
      elsif match = scan(/ \.\.<? | \*?\.(?!\d)@? | \.& | \?:? | [,?:(\[] | -[->] | \+\+ |
          && | \|\| | \*\*=? | ==?~ | <=?>? | [-+*%^~&|>=!]=? | <<<?=? | >>>?=? /x)
        value_expected = true
        value_expected = :regexp if match == '~'
        after_def = false
        kind = :operator
      
      elsif match = scan(/ [)\]}] /x)
        value_expected = after_def = false
        if !inline_block_stack.empty? && match == '}'
          inline_block_paren_depth -= 1
          if inline_block_paren_depth == 0  # closing brace of inline block reached
            tokens << [match, :inline_delimiter]
            tokens << [:close, :inline]
            state, string_delimiter, inline_block_paren_depth = inline_block_stack.pop
            next
          end
        end
      
      elsif check(/[\d.]/)
        after_def = value_expected = false
        if scan(/0[xX][0-9A-Fa-f]+/)
          kind = :hex
        elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
          kind = :oct
        elsif scan(/\d+[fFdD]|\d*\.\d+(?:[eE][+-]?\d+)?[fFdD]?|\d+[eE][+-]?\d+[fFdD]?/)
          kind = :float
        elsif scan(/\d+[lLgG]?/)
          kind = :integer
        end

      elsif match = scan(/'''|"""/)
        after_def = value_expected = false
        state = :multiline_string
        tokens << [:open, :string]
        string_delimiter = match
        kind = :delimiter
      
      # TODO: record.'name'
      elsif match = scan(/["']/)
        after_def = value_expected = false
        state = match == '/' ? :regexp : :string
        tokens << [:open, state]
        string_delimiter = match
        kind = :delimiter

      elsif value_expected && (match = scan(/\//))
        after_def = value_expected = false
        tokens << [:open, :regexp]
        state = :regexp
        string_delimiter = '/'
        kind = :delimiter

      elsif scan(/ @ #{IDENT} /ox)
        after_def = value_expected = false
        kind = :annotation

      elsif scan(/\//)
        after_def = false
        value_expected = true
        kind = :operator
      
      else
        getch
        kind = :error

      end

    when :string, :regexp, :multiline_string
      if scan(STRING_CONTENT_PATTERN[string_delimiter])
        kind = :content
        
      elsif match = scan(state == :multiline_string ? /'''|"""/ : /["'\/]/)
        tokens << [match, :delimiter]
        if state == :regexp
          # TODO: regexp modifiers? s, m, x, i?
          modifiers = scan(/[ix]+/)
          tokens << [modifiers, :modifier] if modifiers && !modifiers.empty?
        end
        state = :string if state == :multiline_string
        tokens << [:close, state]
        string_delimiter = nil
        after_def = value_expected = false
        state = :initial
        next
      
      elsif (state == :string || state == :multiline_string) &&
          (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
        if string_delimiter[0] == ?' && !(match == "\\\\" || match == "\\'")
          kind = :content
        else
          kind = :char
        end
      elsif state == :regexp && scan(/ \\ (?: #{REGEXP_ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
        kind = :char
      
      elsif match = scan(/ \$ #{IDENT} /mox)
        tokens << [:open, :inline]
        tokens << ['$', :inline_delimiter]
        match = match[1..-1]
        tokens << [match, IDENT_KIND[match]]
        tokens << [:close, :inline]
        next
      elsif match = scan(/ \$ \{ /x)
        tokens << [:open, :inline]
        tokens << ['${', :inline_delimiter]
        inline_block_stack << [state, string_delimiter, inline_block_paren_depth]
        inline_block_paren_depth = 1
        state = :initial
        next
      
      elsif scan(/ \$ /mx)
        kind = :content
      
      elsif scan(/ \\. /mx)
        kind = :content
      
      elsif scan(/ \\ | \n /x)
        tokens << [:close, state]
        kind = :error
        after_def = value_expected = false
        state = :initial
      
      else
        raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
      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
    
    last_token = match unless [:space, :comment, :doctype].include? kind
    
    tokens << [match, kind]

  end

  if [:multiline_string, :string, :regexp].include? state
    tokens << [:close, state]
  end

  tokens
end