Class: CodeRay::Scanners::Java

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

Direct Known Subclasses

Groovy

Defined Under Namespace

Modules: BuiltinTypes

Constant Summary collapse

KEYWORDS =

java.sun.com/docs/books/tutorial/java/nutsandbolts/_keywords.html

%w[
  assert break case catch continue default do else
  finally for if instanceof import new package
  return switch throw try typeof while
  debugger export
]
RESERVED = 
%w[ const goto ]
CONSTANTS = 
%w[ false null true ]
MAGIC_VARIABLES = 
%w[ this super ]
TYPES = 
%w[
  boolean byte char class double enum float int interface long
  short void
] << '[]'
DIRECTIVES =

because int[] should be highlighted as a type

%w[
  abstract extends final implements native private protected public
  static strictfp synchronized throws transient volatile
]
IDENT_KIND = 
WordList.new(:ident).
add(KEYWORDS, :keyword).
add(RESERVED, :reserved).
add(CONSTANTS, :pre_constant).
add(MAGIC_VARIABLES, :local_variable).
add(TYPES, :type).
add(BuiltinTypes::List, :pre_type).
add(BuiltinTypes::List.select { |builtin| builtin[/(Error|Exception)$/] }, :exception).
add(DIRECTIVES, :directive)
ESCAPE = 
/ [bfnrtv\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
STRING_CONTENT_PATTERN = 
{
  "'" => /[^\\']+/,
  '"' => /[^\\"]+/,
  '/' => /[^\\\/]+/,
}
IDENT = 
/[a-zA-Z_][A-Za-z_0-9]*/

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 



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
 
# File 'lib/coderay/scanners/java.rb', line 48

def scan_tokens tokens, options

  state = :initial
  string_delimiter = nil
  import_clause = class_name_follows = last_token_dot = false

  until eos?

    kind = nil
    match = nil
    
    case state

    when :initial

      if match = scan(/ \s+ | \\\n /x)
        tokens << [match, :space]
        next
      
      elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
        tokens << [match, :comment]
        next
      
      elsif import_clause && scan(/ #{IDENT} (?: \. #{IDENT} )* /ox)
        kind = :include
      
      elsif match = scan(/ #{IDENT} | \[\] /ox)
        kind = IDENT_KIND[match]
        if last_token_dot
          kind = :ident
        elsif class_name_follows
          kind = :class
          class_name_follows = false
        else
          import_clause = true if match == 'import'
          class_name_follows = true if match == 'class' || match == 'interface'
        end
      
      elsif scan(/ \.(?!\d) | [,?:()\[\]}] | -- | \+\+ | && | \|\| | \*\*=? | [-+*\/%^~&|<>=!]=? | <<<?=? | >>>?=? /x)
        kind = :operator
      
      elsif scan(/;/)
        import_clause = false
        kind = :operator
      
      elsif scan(/\{/)
        class_name_follows = false
        kind = :operator
      
      elsif check(/[\d.]/)
        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+[lL]?/)
          kind = :integer
        end

      elsif match = scan(/["']/)
        tokens << [:open, :string]
        state = :string
        string_delimiter = match
        kind = :delimiter

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

      else
        getch
        kind = :error

      end

    when :string
      if scan(STRING_CONTENT_PATTERN[string_delimiter])
        kind = :content
      elsif match = scan(/["'\/]/)
        tokens << [match, :delimiter]
        tokens << [:close, state]
        string_delimiter = nil
        state = :initial
        next
      elsif state == :string && (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
        if string_delimiter == "'" && !(match == "\\\\" || match == "\\'")
          kind = :content
        else
          kind = :char
        end
      elsif scan(/\\./m)
        kind = :content
      elsif scan(/ \\ | $ /x)
        tokens << [:close, :delimiter]
        kind = :error
        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_dot = match == '.'
    
    tokens << [match, kind]

  end

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

  tokens
end