我写了一个脚本,我在 UTF-8 编码的 HTML 文件中啜饮,然后将其解析为带有HTML::Tree
. 问题是解析字符串后不再标记为 UTF-8。
由于_utf8_on()
不推荐设置标志的方法,我正在寻找正确的方法。
我的简化代码示例:
#!/usr/bin/perl
use strict;
use warnings;
use 5.010;
use utf8::all;
use autodie;
use HTML::Tree;
use Encode qw/is_utf8/;
my $file = shift;
my $tree;
if ($file) {
my $content = slurp_in( 'file' => $file );
$tree = html_tree('content' => $content);
} else {
die "no file";
}
my $title = $tree->look_down(_tag => 'title');
$title = $title->as_HTML('');
if ( is_utf8( $title ) ) {
say "OK: $title";
} else {
say "NOT OK: $title";
}
## SUBS
##
sub slurp_in {
my %v = @_;
open(my $fh, "<:utf8", $v{file}) || die "no $v{file}: $!";
local $/;
my $content = (<$fh>);
close $fh;
if ($content) {
return $content;
} else {
die "no content in $v{file} !";
}
}
sub html_tree {
my %v = @_;
my $tree = HTML::Tree->new();
$tree->utf8_mode(1); ## wrong call here, no such method, but no warnings on it!
$tree->parse( $v{content} );
if ($tree) {
return $tree;
} else {
die "no tree here";
}
}