Module: LangScan::C

Defined in:
lib/langscan/c.rb,
ext/langscan/c/c/c.c

Defined Under Namespace

Classes: Tokenizer

Constant Summary collapse

Keywords = 
%w(
  auto break case char const continue default do
  double else enum extern float for goto if int
  long register return short signed sizeof static
  struct switch typedef union unsigned void volatile
  while
)
KeywordsHash = 
{}
Types = 
%w(char double float int long short void)
TypesHash = 
{}
IdentType = 
Hash.new(:ident)

Class Method Summary collapse

Class Method Details

.abbrev ⇒ Object 



23
24
25
 
# File 'lib/langscan/c.rb', line 23

def abbrev
  "c"
end

.each_fragment(input) ⇒ Object

for debug



134
135
136
137
138
139
 
# File 'lib/langscan/c.rb', line 134

def C.each_fragment(input)
  tokenizer = LangScan::C::Tokenizer.new(input)
  while t = tokenizer.get_token
    yield t
  end
end

.extnames ⇒ Object 



27
28
29
 
# File 'lib/langscan/c.rb', line 27

def extnames
  [".c", ".h", ".cc", ".cpp"]
end

.name ⇒ Object 



19
20
21
 
# File 'lib/langscan/c.rb', line 19

def name
  "C/C++"
end

.scan(input, &block) ⇒ Object

LangScan::C.scan iterates over C program. It yields for each Fragment.



33
34
35
36
 
# File 'lib/langscan/c.rb', line 33

def scan(input, &block)
  sorter = PairMatcher.fragmentsorter(block)
  scan_unsorted(input, &sorter)
end

.scan_unsorted(input, &block) ⇒ Object 



38
39
40
41
42
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
 
# File 'lib/langscan/c.rb', line 38

def scan_unsorted(input, &block)
  pm = LangScan::PairMatcher.new(3,2,2,2)
  pm.define_intertoken_fragment :space, nil
  pm.define_intertoken_fragment :comment, nil
  pm.define_pair :paren, :punct, "(", :punct, ")"
  pm.define_pair :brace, :punct, "{", :punct, "}"
  pm.define_pair :bracket, :punct, "[", :punct, "]"
  pm.define_pair :preproc, :preproc_beg, "#", :preproc_end, "\n"
  pm.parse(LangScan::C::Tokenizer.new(input), lambda {|f|
    if f.type == :ident
      f.type = IdentType[f.text]
    end
    yield f
  }) {|pair|
    if pair.pair_type == :paren
      if 1 <= pair.before_open_length
        fun = pair.around_open(-1)
        if fun.type == :ident && IdentType[fun.text] == :ident
          # ident(...)
          if (outer = pair.outer) && pair.outmost.pair_type == :paren
            # type ident(type (*arg)());
          elsif outer &&
             outer.pair_type == :preproc &&
             2 <= outer.after_open_length &&
             outer.around_open(1).type == :ident && /\Adefine\z/ =~ outer.around_open(1).text &&
             outer.around_open(2) == pair.around_open(-1)
            # #define ident(...)
            # #define ident (...)
            if pair.around_open(-1).end_byteno == pair.open_token.beg_byteno
              # #define ident(...)
              fun.type = :fundef
            end
          elsif !outer ||
                (!outer.outer && # extern "C" { ... }
                 outer.pair_type == :brace &&
                 2 <= outer.before_open_length &&
                 outer.around_open(-2).type == :ident && /\Aextern\z/ =~ outer.around_open(-2).text &&
                 outer.around_open(-1).type == :string && /\A"C"\z/ =~ outer.around_open(-1).text)
            if 2 <= pair.before_open_length &&
               pair.around_open(1).type == :punct && pair.around_open(1).text == '(' &&
               pair.around_close(-1).type == :punct && pair.around_close(-1).text == ')' &&
               pair.around_open(-2).type == :ident && IdentType[pair.around_open(-2).text] == :ident
              # ident ident((...))
              pair.around_open(-2).type = :fundecl
            elsif 1 <= pair.after_close_length &&
                  pair.around_close(1).type == :punct && /\A;\z/ =~ pair.around_close(1).text
              # ident(...);
              fun.type = :fundecl
            elsif 1 <= pair.after_close_length &&
                  ((pair.around_close(1).type == :punct && /\A\{\z/ =~ pair.around_close(1).text) || # }
                   (pair.around_close(1).type == :ident))
              # name(...) { ... }
              # name(...) int arg; { ... }
              # name(...) struct tag *arg; { ... }
              # name(...) typedefed_type arg; { ... }
              fun.type = :fundef
            else
              fun.type = :funcall
            end
          else
            if /\Adefined\z/ =~ fun.text &&
               (outer = pair.outer) &&
               !outer.outer &&
               outer.pair_type == :preproc &&
               1 <= outer.after_open_length &&
               /\Aif\z/ =~ outer.around_open(1).text
              # #if ... defined(...)
            else
              fun.type = :funcall
            end
          end
        end
      end
    end
  }
end