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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
|
Author: Alexander Zangerl <az@debian.org>
Subject: binmode fix for multibyte-encoded data
--- a/MANIFEST
+++ b/MANIFEST
@@ -42,6 +42,8 @@ t/stdin.t
t/stringify.t
t/tainted.t
t/write_file_win32.t
+t/utf8.data
+t/utf8.t
xt/author/00-compile.t
xt/author/eol.t
xt/author/pod-spell.t
--- a/META.yml
+++ b/META.yml
@@ -36,6 +36,7 @@ no_index:
requires:
B: '0'
Carp: '0'
+ Digest::MD5: 0
Errno: '0'
Exporter: '5.57'
Fcntl: '0'
--- /dev/null
+++ b/t/utf8.data
@@ -0,0 +1,3 @@
+hallo grüezi blödel schaß und aus.
+Gregorian: ლრ
+Arabic: ڐڡڠڟڞ
--- /dev/null
+++ b/t/utf8.t
@@ -0,0 +1,44 @@
+#!/usr/bin/perl
+use Test::More;
+use strict;
+use File::Slurp;
+use Encode qw/encode_utf8/;
+use Digest::MD5 qw/md5_hex/;
+use Devel::Peek;
+
+BEGIN {
+ plan skip_all => "Newer Perl doesn't like sysread with utf8 binmode"
+ if $] >= 5.024000;
+}
+
+my $digest = 'e30ffef9b0c5623bc1ddd1ba73302f14';
+
+my $utf8 = read_file("t/utf8.data", binmode => ":utf8");
+my $latin = read_file("t/utf8.data");
+
+ok( Encode::is_utf8($utf8), "Reading the data file with binmode options results in UTF8 encoded string");
+ok(! Encode::is_utf8($latin), "Reading the data file without options correctly results in unencoded string");
+
+my $ctx1 = new Digest::MD5;
+ $ctx1->add(encode_utf8($utf8)); # encode_utf8 is needed, see http://search.cpan.org/dist/Digest-MD5/MD5.pm
+
+ok($ctx1->hexdigest eq $digest, "The data from the data file we just read came through intact");
+
+
+###
+# Write to a tempfile and rest
+###
+
+my $fn_utf8 = "/tmp/file-slurp-utf8.txt";
+
+write_file($fn_utf8, { binmode => ":utf8" }, $utf8);
+
+open my $fh_utf8, "$fn_utf8" or die "Could not open $fn_utf8: $!\n";
+my $ctx2 = new Digest::MD5;
+ $ctx2->addfile($fh_utf8);
+
+ok($ctx2->hexdigest eq $digest, "The data is written correctly with binmode options");
+
+unlink($fn_utf8);
+
+done_testing;
--- /dev/null
+++ b/t/utf8.t.alt
@@ -0,0 +1,19 @@
+use Test::More tests => 1;
+use strict;
+use File::Slurp;
+my $fn="/tmp/utf8.txt";
+
+my $data="hallo grezi bldel scha und aus.\n";
+open F,">$fn";
+binmode(F, ":utf8");
+print F $data;
+close F;
+
+my $x=read_file($fn,binmode=>":utf8");
+ok($x eq $data,"utf8 encoded data survives slurp");
+unlink($fn);
+
+
+
+
+
--- a/lib/File/Slurp.pm
+++ b/lib/File/Slurp.pm
@@ -897,6 +897,9 @@ set the C<binmode> option, then its valu
the opened handle. You can use this to set the file to be read in binary mode,
utf8, etc. See C<perldoc -f binmode> for more.
+Please note that using binmode :utf8 with sysread (and thus read_file)
+has been deprecated in recent versions of perl.
+
=item
blk_size
--- a/t/binmode.t
+++ b/t/binmode.t
@@ -9,7 +9,8 @@ use IO::Handle ();
use Test::More;
BEGIN {
- plan skip_all => 'Older Perl lacking unicode support' if $] < 5.008001;
+ plan skip_all => 'Older Perl lacking unicode support' if $] < 5.008001;
+ plan skip_all => "Newer Perl doesn't like sysread with utf8 binmode" if $] >= 5.024000;
}
# older EUMMs turn this on. We don't want to emit warnings.
|
