1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
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
88
89
90
91
92
93
94
95
96
97
98
|
%**<title>The Haskell 98 Library Report: Character Utilities</title>
%**~header
\section{Character Utilities}
\outline{
\inputHS{headers/Char}
}
\indextt{isAscii}
\indextt{isLatin1}
\indextt{isControl}
\indextt{isPrint}
\indextt{isSpace}
\indextt{isUpper}
\indextt{isLower}
\indextt{isAlpha}
\indextt{isDigit}
\indextt{isOctDigit}
\indextt{isHexDigit}
\indextt{isAlphaNum}
\indextt{toUpper}
\indextt{toLower}
This library provides a limited set of operations on the Unicode
character set.
The first 128 entries of this character set are identical to the
ASCII set; with the next 128 entries comes the remainder of the
Latin-1 character set.
This module offers only a limited view of the
full Unicode character set; the full set of Unicode character
attributes is not accessible in this library.
Unicode characters may be divided into five general categories:
non-printing, lower case alphabetic, other alphabetic, numeric digits, and
other printable characters. For the purposes of Haskell, any
alphabetic character which is not lower case is treated as upper case
(Unicode actually has three cases: upper, lower, and title). Numeric
digits may be part of identifiers but digits outside the ASCII range are not
used by the reader to represent numbers.
For each sort of Unicode character, here are the predicates which
return @True@:
\begin{center}
\begin{tabular}{|l|llll|}
\hline
Character Type & Predicates & & & \\
\hline
Lower Case Alphabetic & @isPrint@ & @isAlphaNum@ & @isAlpha@ & @isLower@ \\
Other Alphabetic & @isPrint@ & @isAlphaNum@ & @isAlpha@ & @isUpper@ \\
Digits & @isPrint@ & @isAlphaNum@ & & \\
Other Printable & @isPrint@ & & & \\
Non-printing & & & &\\
\hline
\end{tabular}
\end{center}
The @isDigit@, @isOctDigit@, and @isHexDigit@ functions select only
ASCII characters. @intToDigit@ and @digitToInt@ convert between
a single digit @Char@ and the corresponding @Int@.
@digitToInt@ operates fails unless its argument satisfies @isHexDigit@,
but recognises both upper and lower-case hexadecimal digits (i.e. @'0'@..@'9'@,
@'a'@..@'f'@, @'A'@..@'F'@). @intToDigit@ fails unless its argument is in the range
@0@..@15@, and generates lower-case hexadecimal digits.
The @isSpace@ function recognizes only white characters in the Latin-1
range.
The function @showLitChar@ converts a character to a string using
only printable characters, using Haskell source-language escape conventions.
The function @lexLitChar@ does the reverse, returning the sequence of characters
that encode the character.
The function @readLitChar@ does the same, but in addition converts the
to the character that it encodes. For example:
\bprog
@
showLitChar '\n' s = "\\n" ++ s
lexLitChar "\\nHello" = [("\\n", "Hello")]
readLitChar "\\nHello" = [('\n', "Hello")]
@
\eprog
Function @toUpper@ converts a letter to the corresponding
upper-case letter, leaving any other character unchanged. Any
Unicode letter which has an upper-case equivalent is transformed.
Similarly, @toLower@ converts a letter to the
corresponding lower-case letter, leaving any other character
unchanged.
The @ord@ and @chr@ functions are @fromEnum@ and @toEnum@
restricted to the type @Char@.
\clearpage
\subsection{Library {\tt Char}}
\label{Char}
\inputHS{code/Char}
%**~footer
|
