[PATCH common v4 2/5] section config: prepare for supporting UTF-8 encoded configurations

[Fiona Ebner]

Configurations registered as UTF-8 will be decoded after reading to
Perl's internal string format and thus may contain wide characters.
The Digest::SHA::sha1_hex() function croaks on wide characters, so
encode again before calling the function.

Signed-off-by: Fiona Ebner <f.eb...@proxmox.com>
---

Changes in v4:
* rather than searching for wide characters, tell parse_config()
  directly whether the file was registered as UTF-8

 src/PVE/SectionConfig.pm | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/src/PVE/SectionConfig.pm b/src/PVE/SectionConfig.pm
index 84ff81a..9ff91ee 100644
--- a/src/PVE/SectionConfig.pm
+++ b/src/PVE/SectionConfig.pm
@@ -103,6 +103,7 @@ use warnings;
 
 use Carp;
 use Digest::SHA;
+use Encode qw(encode);
 
 use PVE::Exception qw(raise_param_exc);
 use PVE::JSONSchema qw(get_standard_option);
@@ -1103,10 +1104,10 @@ sub get_property_schema {
 
 =head3 $base->parse_config(...)
 
-=head3 $base->parse_config($filename, $raw [, $allow_unknown ])
+=head3 $base->parse_config($filename, $raw [, $allow_unknown [, $options ]])
 
-    $config = PVE::Example::BasePlugin->parse_config($filename, $raw, 
$allow_unknown)
-    $config = $class->parse_config($filename, $raw, $allow_unknown)
+    $config = PVE::Example::BasePlugin->parse_config($filename, $raw, 
$allow_unknown, $options)
+    $config = $class->parse_config($filename, $raw, $allow_unknown, $options)
 
 Parses the contents of a file as C<L<PVE::SectionConfig>>, returning the parsed
 data annotated with additional information (see below).
@@ -1127,6 +1128,18 @@ The raw content of C<$filename>.
 
 Whether to allow parsing unknown I<types>.
 
+=item C<$options> (optional)
+
+Further options:
+
+=over
+
+=item C<$utf8>
+
+The config file was registered as UTF-8 encoded.
+
+=back
+
 =back
 
 The returned hash is structured as follows:
@@ -1205,7 +1218,7 @@ The error.
 =cut
 
 sub parse_config {
-    my ($class, $filename, $raw, $allow_unknown) = @_;
+    my ($class, $filename, $raw, $allow_unknown, $options) = @_;
 
     my $pdata = $class->private();
 
@@ -1214,7 +1227,13 @@ sub parse_config {
 
     $raw = '' if !defined($raw);
 
-    my $digest = Digest::SHA::sha1_hex($raw);
+    my $bytes = $raw;
+    if ($options && $options->{utf8}) {
+        # Digest::SHA croaks on wide characters
+        $bytes = encode('UTF-8', $raw);
+    }
+
+    my $digest = Digest::SHA::sha1_hex($bytes);
 
     my $pri = 1;
 
-- 
2.47.3