Class: Psych::ScalarScanner

Inherits:
Object show all
Defined in:
lib/psych/scalar_scanner.rb

Overview

Scan scalars for built in types

Constant Summary collapse

TIME =
/^\d{4}-\d{1,2}-\d{1,2}([Tt]|\s+)\d{1,2}:\d\d:\d\d(\.\d*)?(\s*Z|[-+]\d{1,2}(:\d\d)?)?/
FLOAT =
/^(?:[-+]?([0-9][0-9_,]*)?\.[0-9]*([eE][-+][0-9]+)?(?# base 10)
|[-+]?[0-9][0-9_,]*(:[0-5]?[0-9])+\.[0-9_]*(?# base 60)
|[-+]?\.(inf|Inf|INF)(?# infinity)
|\.(nan|NaN|NAN)(?# not a number))$/x
INTEGER =
/^(?:[-+]?0b[0-1_]+          (?# base 2)
|[-+]?0[0-7_]+           (?# base 8)
|[-+]?(?:0|[1-9][0-9_]*) (?# base 10)
|[-+]?0x[0-9a-fA-F_]+    (?# base 16))$/x

Instance Method Summary collapse

Constructor Details

#initializeScalarScanner

Create a new scanner


23
24
25
26
# File 'lib/psych/scalar_scanner.rb', line 23

def initialize
  @string_cache = {}
  @symbol_cache = {}
end

Instance Method Details

#parse_int(string) ⇒ Object

Parse and return an int from string


112
113
114
115
# File 'lib/psych/scalar_scanner.rb', line 112

def parse_int string
  return unless INTEGER === string
  Integer(string)
end

#parse_time(string) ⇒ Object

Parse and return a Time from string


119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
# File 'lib/psych/scalar_scanner.rb', line 119

def parse_time string
  date, time = *(string.split(/[ tT]/, 2))
  (yy, m, dd) = date.split('-').map { |x| x.to_i }
  md = time.match(/(\d+:\d+:\d+)(?:\.(\d*))?\s*(Z|[-+]\d+(:\d\d)?)?/)

  (hh, mm, ss) = md[1].split(':').map { |x| x.to_i }
  us = (md[2] ? Rational("0.#{md[2]}") : 0) * 1000000

  time = Time.utc(yy, m, dd, hh, mm, ss, us)

  return time if 'Z' == md[3]
  return Time.at(time.to_i, us) unless md[3]

  tz = md[3].match(/^([+\-]?\d{1,2})\:?(\d{1,2})?$/)[1..-1].compact.map { |digit| Integer(digit, 10) }
  offset = tz.first * 3600

  if offset < 0
    offset -= ((tz[1] || 0) * 60)
  else
    offset += ((tz[1] || 0) * 60)
  end

  Time.at((time - offset).to_i, us)
end

#tokenize(string) ⇒ Object

Tokenize string returning the ruby object


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
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
# File 'lib/psych/scalar_scanner.rb', line 29

def tokenize string
  return nil if string.empty?
  return string if @string_cache.key?(string)
  return @symbol_cache[string] if @symbol_cache.key?(string)

  case string
  # Check for a String type, being careful not to get caught by hash keys, hex values, and
  # special floats (e.g., -.inf).
  when /^[^\d\.:-]?[A-Za-z_\[email protected]#\$%\^&\*\(\)\{\}\<\>\|\/\\~;=]+/
    if string.length > 5
      @string_cache[string] = true
      return string
    end

    case string
    when /^[^ytonf~]/i
      @string_cache[string] = true
      string
    when '~', /^null$/i
      nil
    when /^(yes|true|on)$/i
      true
    when /^(no|false|off)$/i
      false
    else
      @string_cache[string] = true
      string
    end
  when TIME
    begin
      parse_time string
    rescue ArgumentError
      string
    end
  when /^\d{4}-(?:1[012]|0\d|\d)-(?:[12]\d|3[01]|0\d|\d)$/
    require 'date'
    begin
      Date.strptime(string, '%Y-%m-%d')
    rescue ArgumentError
      string
    end
  when /^\.inf$/i
    Float::INFINITY
  when /^-\.inf$/i
    -Float::INFINITY
  when /^\.nan$/i
    Float::NAN
  when /^:./
    if string =~ /^:(["'])(.*)\1/
      @symbol_cache[string] = $2.sub(/^:/, '').to_sym
    else
      @symbol_cache[string] = string.sub(/^:/, '').to_sym
    end
  when /^[-+]?[0-9][0-9_]*(:[0-5]?[0-9])+$/
    i = 0
    string.split(':').each_with_index do |n,e|
      i += (n.to_i * 60 ** (e - 2).abs)
    end
    i
  when /^[-+]?[0-9][0-9_]*(:[0-5]?[0-9])+\.[0-9_]*$/
    i = 0
    string.split(':').each_with_index do |n,e|
      i += (n.to_f * 60 ** (e - 2).abs)
    end
    i
  when FLOAT
    if string == '.'
      @string_cache[string] = true
      string
    else
      Float(string.gsub(/[,_]|\.$/, ''))
    end
  else
    int = parse_int string.gsub(/[,_]/, '')
    return int if int

    @string_cache[string] = true
    string
  end
end