line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
=head1 NAME |
2
|
|
|
|
|
|
|
|
3
|
|
|
|
|
|
|
Scalar::String - string aspects of scalars |
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
=head1 SYNOPSIS |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
use Scalar::String |
8
|
|
|
|
|
|
|
qw(sclstr_is_upgraded sclstr_is_downgraded); |
9
|
|
|
|
|
|
|
|
10
|
|
|
|
|
|
|
if(sclstr_is_upgraded($value)) { ... |
11
|
|
|
|
|
|
|
if(sclstr_is_downgraded($value)) { ... |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
use Scalar::String qw( |
14
|
|
|
|
|
|
|
sclstr_upgrade_inplace sclstr_upgraded |
15
|
|
|
|
|
|
|
sclstr_downgrade_inplace sclstr_downgraded |
16
|
|
|
|
|
|
|
); |
17
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
sclstr_upgrade_inplace($value); |
19
|
|
|
|
|
|
|
$value = sclstr_upgraded($value); |
20
|
|
|
|
|
|
|
sclstr_downgrade_inplace($value); |
21
|
|
|
|
|
|
|
$value = sclstr_downgraded($value); |
22
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
=head1 DESCRIPTION |
24
|
|
|
|
|
|
|
|
25
|
|
|
|
|
|
|
This module is about the string part of plain Perl scalars. A scalar has |
26
|
|
|
|
|
|
|
a string value, which is notionally a sequence of Unicode codepoints, but |
27
|
|
|
|
|
|
|
may be internally encoded in either ISO-8859-1 or UTF-8. In places, and |
28
|
|
|
|
|
|
|
more so in older versions of Perl, the internal encoding shows through. |
29
|
|
|
|
|
|
|
To fully understand Perl strings it is necessary to understand these |
30
|
|
|
|
|
|
|
implementation details. |
31
|
|
|
|
|
|
|
|
32
|
|
|
|
|
|
|
This module provides functions to classify a string by encoding and to |
33
|
|
|
|
|
|
|
encode a string in a desired way. |
34
|
|
|
|
|
|
|
|
35
|
|
|
|
|
|
|
This module is implemented in XS, with a pure Perl backup version for |
36
|
|
|
|
|
|
|
systems that can't handle XS. |
37
|
|
|
|
|
|
|
|
38
|
|
|
|
|
|
|
=head1 STRING ENCODING |
39
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
ISO-8859-1 is a simple 8-bit character encoding, which represents the |
41
|
|
|
|
|
|
|
first 256 Unicode characters (codepoints 0x00 to 0xff) in one octet each. |
42
|
|
|
|
|
|
|
This is how strings were historically represented in Perl. A string |
43
|
|
|
|
|
|
|
represented this way is referred to as "downgraded". |
44
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
UTF-8 is a variable-width character encoding, which represents all |
46
|
|
|
|
|
|
|
possible Unicode codepoints in differing numbers of octets. A design |
47
|
|
|
|
|
|
|
feature of UTF-8 is that ASCII characters (codepoints 0x00 to 0x7f) |
48
|
|
|
|
|
|
|
are each represented in a single octet, identically to their ISO-8859-1 |
49
|
|
|
|
|
|
|
encoding. Perl has its own variant of UTF-8, which can handle a wider |
50
|
|
|
|
|
|
|
range of codepoints than Unicode formally allows. A string represented |
51
|
|
|
|
|
|
|
in this variant UTF-8 is referred to as "upgraded". |
52
|
|
|
|
|
|
|
|
53
|
|
|
|
|
|
|
A Perl string is physically represented as a string of octets along with |
54
|
|
|
|
|
|
|
a flag that says whether the string is downgraded or upgraded. At this |
55
|
|
|
|
|
|
|
level, to determine the Unicode codepoints that are represented requires |
56
|
|
|
|
|
|
|
examining both parts of the representation. If the string contains only |
57
|
|
|
|
|
|
|
ASCII characters then the octet sequence is identical in either encoding, |
58
|
|
|
|
|
|
|
but Perl still maintains an encoding flag on such a string. A string |
59
|
|
|
|
|
|
|
is always either downgraded or upgraded; it is never both or neither. |
60
|
|
|
|
|
|
|
|
61
|
|
|
|
|
|
|
When handling string input, it is good form to operate only on the Unicode |
62
|
|
|
|
|
|
|
characters represented by the string, ignoring the manner in which they |
63
|
|
|
|
|
|
|
are encoded. Basic string operations such as concatenation work this way |
64
|
|
|
|
|
|
|
(except for a bug in perl 5.6.0), so simple code written in pure Perl is |
65
|
|
|
|
|
|
|
generally safe on this front. Pieces of character-based code can pass |
66
|
|
|
|
|
|
|
around strings among themselves, and always get consistent behaviour, |
67
|
|
|
|
|
|
|
without worrying about the way in which the characters are encoded. |
68
|
|
|
|
|
|
|
|
69
|
|
|
|
|
|
|
However, due to an historical accident, a lot of C code that interfaces |
70
|
|
|
|
|
|
|
with Perl looks at the octets used to represent a string without also |
71
|
|
|
|
|
|
|
examining the encoding flag. Such code gives inconsistent behaviour for |
72
|
|
|
|
|
|
|
the same character sequence represented in the different ways. In perl |
73
|
|
|
|
|
|
|
5.6, many pure Perl operations (such as regular expression matching) |
74
|
|
|
|
|
|
|
also work this way, though some of them can be induced to work correctly |
75
|
|
|
|
|
|
|
by using the L pragma. In perl 5.8, regular expression matching |
76
|
|
|
|
|
|
|
is character-based by default, but many I/O functions (such as C) |
77
|
|
|
|
|
|
|
are still octet-based. |
78
|
|
|
|
|
|
|
|
79
|
|
|
|
|
|
|
Where code that operates on the octets of a string must be used by code |
80
|
|
|
|
|
|
|
that operates on characters, the latter needs to pay attention to the |
81
|
|
|
|
|
|
|
encoding of its strings. Commonly, the octet-based code expects its |
82
|
|
|
|
|
|
|
input to be represented in a particular encoding, in which case the |
83
|
|
|
|
|
|
|
character-based code must oblige by forcing strings to that encoding |
84
|
|
|
|
|
|
|
before they are passed in. There are other usage patterns too. |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
You will be least confused if you think about a Perl string as a character |
87
|
|
|
|
|
|
|
sequence plus an encoding flag. You should normally operate on the |
88
|
|
|
|
|
|
|
character sequence and not care about the encoding flag. Occasionally you |
89
|
|
|
|
|
|
|
must pay attention to the flag in addition to the characters. Unless you |
90
|
|
|
|
|
|
|
are writing C code, you should try not to think about a string the other |
91
|
|
|
|
|
|
|
way round, as an octet sequence plus encoding flag. |
92
|
|
|
|
|
|
|
|
93
|
|
|
|
|
|
|
=cut |
94
|
|
|
|
|
|
|
|
95
|
|
|
|
|
|
|
package Scalar::String; |
96
|
|
|
|
|
|
|
|
97
|
2
|
|
|
2
|
|
76722
|
{ use 5.006; } |
|
2
|
|
|
|
|
7
|
|
98
|
2
|
|
|
2
|
|
11
|
use warnings; |
|
2
|
|
|
|
|
5
|
|
|
2
|
|
|
|
|
67
|
|
99
|
2
|
|
|
2
|
|
12
|
use strict; |
|
2
|
|
|
|
|
4
|
|
|
2
|
|
|
|
|
76
|
|
100
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
our $VERSION = "0.003"; |
102
|
|
|
|
|
|
|
|
103
|
2
|
|
|
2
|
|
978
|
use parent "Exporter"; |
|
2
|
|
|
|
|
593
|
|
|
2
|
|
|
|
|
13
|
|
104
|
|
|
|
|
|
|
our @EXPORT_OK = qw( |
105
|
|
|
|
|
|
|
sclstr_is_upgraded sclstr_is_downgraded |
106
|
|
|
|
|
|
|
sclstr_upgrade_inplace sclstr_upgraded |
107
|
|
|
|
|
|
|
sclstr_downgrade_inplace sclstr_downgraded |
108
|
|
|
|
|
|
|
); |
109
|
|
|
|
|
|
|
|
110
|
|
|
|
|
|
|
eval { local $SIG{__DIE__}; |
111
|
|
|
|
|
|
|
require XSLoader; |
112
|
|
|
|
|
|
|
XSLoader::load(__PACKAGE__, $VERSION); |
113
|
|
|
|
|
|
|
}; |
114
|
|
|
|
|
|
|
|
115
|
|
|
|
|
|
|
if($@ eq "") { |
116
|
|
|
|
|
|
|
close(DATA); |
117
|
|
|
|
|
|
|
} else { |
118
|
|
|
|
|
|
|
(my $filename = __FILE__) =~ tr# -~##cd; |
119
|
|
|
|
|
|
|
local $/ = undef; |
120
|
|
|
|
|
|
|
my $pp_code = "#line 128 \"$filename\"\n".; |
121
|
|
|
|
|
|
|
close(DATA); |
122
|
|
|
|
|
|
|
{ |
123
|
|
|
|
|
|
|
local $SIG{__DIE__}; |
124
|
|
|
|
|
|
|
eval $pp_code; |
125
|
|
|
|
|
|
|
} |
126
|
|
|
|
|
|
|
die $@ if $@ ne ""; |
127
|
|
|
|
|
|
|
} |
128
|
|
|
|
|
|
|
|
129
|
1
|
|
|
1
|
|
5
|
1; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
53
|
|
130
|
1
|
50
|
|
1
|
|
620
|
|
|
1
|
|
|
|
|
285
|
|
131
|
|
|
|
|
|
|
__DATA__ |