Anonymous user
Character codes: Difference between revisions
→{{header|Scala}}
Line 882:
[[Category:Scala Implementations]]
{{libheader|Scala}}
Scala supports unicode characters, but each character is UTF-16, so there is not a 1-to-1 relationship for supplementary character sets.
===In a REPL session===
<lang scala>scala> 'a' toInt
res2: Int = 97
Line 897 ⟶ 895:
scala> "\uD869\uDEA5"
res5: String = 𪚥</lang>
===Full swing workout===
Taken the supplemental character sets in account.
<lang scala>import java.lang.Character._; import scala.annotation.tailrec
object CharacterCode extends App {
def intToChars(n: Int): Array[Char] = java.lang.Character.toChars(n)
def UnicodeToList(UTFstring: String) = {
@tailrec
def inner(str: List[Char], acc: List[String], surrogateHalf: Option[Char]): List[String] = {
(str, surrogateHalf) match {
case (Nil, _) => acc
case (ch :: rest, None) => if (ch.isSurrogate) inner(rest, acc, Some(ch))
else inner(rest, acc :+ ch.toString, None)
case (ch :: rest, Some(f)) => inner(rest, (acc :+ (f.toString + ch)), None)
}
}
inner(UTFstring.toList, Nil, None)
}
def UnicodeToInt(utf: String) = {
def charToInt(high: Char, low: Char) =
{ if (isSurrogatePair(high, low)) toCodePoint(high, low) else high.toInt }
charToInt(utf(0), if (utf.size > 1) utf(1) else 0)
}
def UTFtoHexString(utf: String) = { utf.map(ch => f"${ch.toInt}%04X").mkString("\"\\u", "\\u", "\"") }
def flags(ch: String) = { // Testing Unicode character properties
(if (ch matches "\\p{M}") "Y" else "N") + (if (ch matches "\\p{Mn}") "Y" else "N")
}
val str = '\uFEFF' /*big-endian BOM*/ + "\u0301a" +
"$áabcde¢£¤¥©ÇßIJijŁłʒλπक्तु•₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵℃←→⇒∙⌘☃☹☺☻ア字文𠀀" + intToChars(173733).mkString
println(s"Example string: $str")
println(""" | Chr C/C++/Java source Code Point Hex Dec Mn Name
!----+ --- ------------------------- ------- -------- -- """.stripMargin('!') + "-" * 27)
(UnicodeToList(str)).zipWithIndex.map {
case (coll, nr) =>
f"$nr%4d: $coll\t${UTFtoHexString(coll)}%27s U+${UnicodeToInt(coll)}%05X" +
f"${"(" + UnicodeToInt(coll).toString}%8s) ${flags(coll)} ${getName(coll(0).toInt)} "
}.foreach(println)
}</lang>
{{Output}}
<pre style="height:20ex;overflow:scroll">Example string: ́a$áabcde¢£¤¥©ÇßIJijŁłʒλπक्तु•₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵℃←→⇒∙⌘☃☹☺☻ア字文𠀀𪚥
| Chr C/C++/Java source Code Point Hex Dec Mn Name
----+ --- ------------------------- ------- -------- -- ---------------------------
0: "\uFEFF" U+0FEFF (65279) NN ZERO WIDTH NO-BREAK SPACE
1: ́ "\u0301" U+00301 (769) YY COMBINING ACUTE ACCENT
2: a "\u0061" U+00061 (97) NN LATIN SMALL LETTER A
3: $ "\u0024" U+00024 (36) NN DOLLAR SIGN
4: á "\u00E1" U+000E1 (225) NN LATIN SMALL LETTER A WITH ACUTE
5: a "\u0061" U+00061 (97) NN LATIN SMALL LETTER A
6: b "\u0062" U+00062 (98) NN LATIN SMALL LETTER B
7: c "\u0063" U+00063 (99) NN LATIN SMALL LETTER C
8: d "\u0064" U+00064 (100) NN LATIN SMALL LETTER D
9: e "\u0065" U+00065 (101) NN LATIN SMALL LETTER E
10: ¢ "\u00A2" U+000A2 (162) NN CENT SIGN
11: £ "\u00A3" U+000A3 (163) NN POUND SIGN
12: ¤ "\u00A4" U+000A4 (164) NN CURRENCY SIGN
13: ¥ "\u00A5" U+000A5 (165) NN YEN SIGN
14: © "\u00A9" U+000A9 (169) NN COPYRIGHT SIGN
15: Ç "\u00C7" U+000C7 (199) NN LATIN CAPITAL LETTER C WITH CEDILLA
16: ß "\u00DF" U+000DF (223) NN LATIN SMALL LETTER SHARP S
17: IJ "\u0132" U+00132 (306) NN LATIN CAPITAL LIGATURE IJ
18: ij "\u0133" U+00133 (307) NN LATIN SMALL LIGATURE IJ
19: Ł "\u0141" U+00141 (321) NN LATIN CAPITAL LETTER L WITH STROKE
20: ł "\u0142" U+00142 (322) NN LATIN SMALL LETTER L WITH STROKE
21: ʒ "\u0292" U+00292 (658) NN LATIN SMALL LETTER EZH
22: λ "\u03BB" U+003BB (955) NN GREEK SMALL LETTER LAMDA
23: π "\u03C0" U+003C0 (960) NN GREEK SMALL LETTER PI
24: क "\u0915" U+00915 (2325) NN DEVANAGARI LETTER KA
25: ् "\u094D" U+0094D (2381) YY DEVANAGARI SIGN VIRAMA
26: त "\u0924" U+00924 (2340) NN DEVANAGARI LETTER TA
27: ु "\u0941" U+00941 (2369) YY DEVANAGARI VOWEL SIGN U
28: • "\u2022" U+02022 (8226) NN BULLET
29: ₠ "\u20A0" U+020A0 (8352) NN EURO-CURRENCY SIGN
30: ₡ "\u20A1" U+020A1 (8353) NN COLON SIGN
31: ₢ "\u20A2" U+020A2 (8354) NN CRUZEIRO SIGN
32: ₣ "\u20A3" U+020A3 (8355) NN FRENCH FRANC SIGN
33: ₤ "\u20A4" U+020A4 (8356) NN LIRA SIGN
34: ₥ "\u20A5" U+020A5 (8357) NN MILL SIGN
35: ₦ "\u20A6" U+020A6 (8358) NN NAIRA SIGN
36: ₧ "\u20A7" U+020A7 (8359) NN PESETA SIGN
37: ₨ "\u20A8" U+020A8 (8360) NN RUPEE SIGN
38: ₩ "\u20A9" U+020A9 (8361) NN WON SIGN
39: ₪ "\u20AA" U+020AA (8362) NN NEW SHEQEL SIGN
40: ₫ "\u20AB" U+020AB (8363) NN DONG SIGN
41: € "\u20AC" U+020AC (8364) NN EURO SIGN
42: ₭ "\u20AD" U+020AD (8365) NN KIP SIGN
43: ₮ "\u20AE" U+020AE (8366) NN TUGRIK SIGN
44: ₯ "\u20AF" U+020AF (8367) NN DRACHMA SIGN
45: ₰ "\u20B0" U+020B0 (8368) NN GERMAN PENNY SIGN
46: ₱ "\u20B1" U+020B1 (8369) NN PESO SIGN
47: ₲ "\u20B2" U+020B2 (8370) NN GUARANI SIGN
48: ₳ "\u20B3" U+020B3 (8371) NN AUSTRAL SIGN
49: ₴ "\u20B4" U+020B4 (8372) NN HRYVNIA SIGN
50: ₵ "\u20B5" U+020B5 (8373) NN CEDI SIGN
51: ℃ "\u2103" U+02103 (8451) NN DEGREE CELSIUS
52: ← "\u2190" U+02190 (8592) NN LEFTWARDS ARROW
53: → "\u2192" U+02192 (8594) NN RIGHTWARDS ARROW
54: ⇒ "\u21D2" U+021D2 (8658) NN RIGHTWARDS DOUBLE ARROW
55: ∙ "\u2219" U+02219 (8729) NN BULLET OPERATOR
56: ⌘ "\u2318" U+02318 (8984) NN PLACE OF INTEREST SIGN
57: ☃ "\u2603" U+02603 (9731) NN SNOWMAN
58: ☹ "\u2639" U+02639 (9785) NN WHITE FROWNING FACE
59: ☺ "\u263A" U+0263A (9786) NN WHITE SMILING FACE
60: ☻ "\u263B" U+0263B (9787) NN BLACK SMILING FACE
61: ア "\u30A2" U+030A2 (12450) NN KATAKANA LETTER A
62: 字 "\u5B57" U+05B57 (23383) NN CJK UNIFIED IDEOGRAPHS 5B57
63: 文 "\u6587" U+06587 (25991) NN CJK UNIFIED IDEOGRAPHS 6587
64: "\uF8FF" U+0F8FF (63743) NN PRIVATE USE AREA F8FF
65: 𠀀 "\uD840\uDC00" U+20000 (131072) NN HIGH SURROGATES D840
66: 𪚥 "\uD869\uDEA5" U+2A6A5 (173733) NN HIGH SURROGATES D869</pre>[http://illegalargumentexception.blogspot.nl/2009/05/java-rough-guide-to-character-encoding.html More background info: "Java: a rough guide to character encoding"]
=={{header|Scheme}}==
| |||