Class: CompactData::Tokeniser::Context

Inherits:
Object
  • Object
show all
Defined in:
lib/compactdata/tokeniser/context.rb

Overview

A parsing context for a CompactData String

Constant Summary collapse

WS = 
" \t\r\n"
INTEGER_REGEX = 
'^-?(?:0|[1-9]\d*)$'
FLOAT_REGEX = 
'^-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?$'
NON_STRING_TOKENS = 
'[]();"=`'

Instance Method Summary collapse

Constructor Details

#initialize(str) ⇒ Context

Returns a new instance of Context.



12
13
14
15
16
 
# File 'lib/compactdata/tokeniser/context.rb', line 12

def initialize(str)
  @str = str
  @tokens = []
  @tok_start = 0
end

Instance Method Details

#escaped?(str, pos) ⇒ Boolean

Returns:

  • (Boolean) 


112
113
114
 
# File 'lib/compactdata/tokeniser/context.rb', line 112

def escaped?(str, pos)
  pos >= 0 && (str[pos] == '~' || str[pos] == '\\')
end

#next_token ⇒ Object 



24
25
26
27
28
29
30
31
32
33
34
35
36
37
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
 
# File 'lib/compactdata/tokeniser/context.rb', line 24

def next_token
  while @tok_start < @str.length
    break unless WS.include?(@str[@tok_start])

    @tok_start += 1
  end

  return false if @tok_start >= @str.length

  case @str[@tok_start]
  when '('
    tok_type = :lparen
    tok_end = @tok_start + 1
  when ')'
    tok_type = :rparen
    tok_end = @tok_start + 1
  when '['
    tok_type = :lbracket
    tok_end = @tok_start + 1
  when ']'
    tok_type = :rbracket
    tok_end = @tok_start + 1
  when ';'
    tok_type = :struct_sep
    tok_end = @tok_start + 1
  when '='
    tok_type = :equals
    tok_end = @tok_start + 1
  when '"'
    tok_type = :quoted
    tok_end = scan_to_end_of_quoted(@str, @tok_start, '"')
  when '`'
    tok_type = :quoted
    tok_end = scan_to_end_of_quoted(@str, @tok_start, '`')
  when '{'
    ## Braced strings must include the braces in the string
    tok_type = :quoted
    tok_end = scan_to_end_of_quoted(@str, @tok_start, '}')
  else
    tok_type = :string
    tok_end = scan_to_end_of_string(@str, @tok_start)
  end

  tok_value = @str[@tok_start..(tok_end - 1)].strip

  if tok_value.match? INTEGER_REGEX
    number = tok_value.to_i
    @tokens.push Token.new(:integer, number, @tok_start, tok_end)
  elsif tok_value.match? FLOAT_REGEX
    number = tok_value.to_f
    @tokens.push Token.new(:float, number, @tok_start, tok_end)
  elsif tok_value == 'null'
    @tokens.push Token.new(:null, nil, @tok_start, tok_end)
  elsif tok_value == 'true'
    @tokens.push Token.new(true, true, @tok_start, tok_end)
  elsif tok_value == 'false'
    @tokens.push Token.new(false, false, @tok_start, tok_end)
  else
    @tokens.push Token.new(tok_type, tok_value, @tok_start, tok_end)
  end

  @tok_start = tok_end
  tok_end < @str.length
end

#parse ⇒ Object 



18
19
20
21
22
 
# File 'lib/compactdata/tokeniser/context.rb', line 18

def parse
  while next_token
  end
  @tokens
end

#scan_to_end_of_quoted(str, start, quote_char) ⇒ Object 



89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'lib/compactdata/tokeniser/context.rb', line 89

def scan_to_end_of_quoted(str, start, quote_char)
  end_str = start + 1
  while end_str < str.length
    end_char = str[end_str]
    prev_char = str[end_str - 1]

    break if end_char == quote_char && prev_char != '\\' && prev_char != '~'

    end_str += 1
  end
  end_str + 1
end

#scan_to_end_of_string(str, start) ⇒ Object 



102
103
104
105
106
107
108
109
110
 
# File 'lib/compactdata/tokeniser/context.rb', line 102

def scan_to_end_of_string(str, start)
  end_str = start + 1
  while end_str < str.length
    break if NON_STRING_TOKENS.include?(str[end_str]) && !escaped?(str, end_str - 1)

    end_str += 1
  end
  end_str
end