Method: DomainName::Punycode.encode
- Defined in:
- lib/domain_name/punycode.rb
.encode(string) ⇒ Object
Encode a string
in Punycode
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 |
# File 'lib/domain_name/punycode.rb', line 101 def encode(string) input = string.unpack('U*') output = '' # Initialize the state n = INITIAL_N delta = 0 bias = INITIAL_BIAS # Handle the basic code points input.each { |cp| output << cp.chr if cp < 0x80 } h = b = output.length # h is the number of code points that have been handled, b is the # number of basic code points, and out is the number of characters # that have been output. output << DELIMITER if b > 0 # Main encoding loop while h < input.length # All non-basic code points < n have been handled already. Find # the next larger one m = MAXINT input.each { |cp| m = cp if (n...m) === cp } # Increase delta enough to advance the decoder's <n,i> state to # <m,0>, but guard against overflow delta += (m - n) * (h + 1) raise BufferOverflowError if delta > MAXINT n = m input.each { |cp| # AMC-ACE-Z can use this simplified version instead if cp < n delta += 1 raise BufferOverflowError if delta > MAXINT elsif cp == n # Represent delta as a generalized variable-length integer q = delta k = BASE loop { t = k <= bias ? TMIN : k - bias >= TMAX ? TMAX : k - bias break if q < t q, r = (q - t).divmod(BASE - t) output << ENCODE_DIGIT[t + r, false] k += BASE } output << ENCODE_DIGIT[q, false] # Adapt the bias delta = h == b ? delta / DAMP : delta >> 1 delta += delta / (h + 1) bias = 0 while delta > CUTOFF delta /= LOBASE bias += BASE end bias += (LOBASE + 1) * delta / (delta + SKEW) delta = 0 h += 1 end } delta += 1 n += 1 end output end |