equal
deleted
inserted
replaced
18 val charset_name: String = "UTF-8" |
18 val charset_name: String = "UTF-8" |
19 val charset: Charset = Charset.forName(charset_name) |
19 val charset: Charset = Charset.forName(charset_name) |
20 def codec(): Codec = Codec(charset) |
20 def codec(): Codec = Codec(charset) |
21 |
21 |
22 def bytes(s: String): Array[Byte] = s.getBytes(charset) |
22 def bytes(s: String): Array[Byte] = s.getBytes(charset) |
23 |
|
24 object Length extends Codepoint.Length |
|
25 { |
|
26 override def codepoint_length(c: Int): Int = |
|
27 if (c < 0x80) 1 |
|
28 else if (c < 0x800) 2 |
|
29 else if (c < 0x10000) 3 |
|
30 else 4 |
|
31 } |
|
32 |
23 |
33 |
24 |
34 /* permissive UTF-8 decoding */ |
25 /* permissive UTF-8 decoding */ |
35 |
26 |
36 // see also http://en.wikipedia.org/wiki/UTF-8#Description |
27 // see also http://en.wikipedia.org/wiki/UTF-8#Description |