[pmg-devel] [PATCH pmg-api v2 2/2] ruledb: content-type: add flag for matching only based on magic/content

[Stoiko Ivanov <s.ivanov@proxmox.com>]

our current content-type matching is sensibly quite cautious in
matching if any available information indicates a potential match:
* mime-type detection based on file contents
* mime-type detection based on file suffix
* content-type header

Sometimes this can lead to surprises (e.g. when a MUA sets the
filetype of a pdf to application/octet-stream (the default type if no
information is available), or a filter for zip-files matching
docx-files.

This change gives users the option to restrict matching only on the
content as detected by xdg_mime_get_mime_type_for_data.

This is a fix for the intial request in #2691 and addresses the
suggestion from Friedrich from:
https://bugzilla.proxmox.com/show_bug.cgi?id=5618#c2

matches on the other items can be created with Match Field objects
(for the content-type header) and Filename (for the match based on the
provided filename - combinations of those should give us the complete
flexibility.

inspired by the changes for disclaimer released with PMG 8.1:
51d1507 ("fix #2430: ruledb disclaimer: make separator configurable")

Signed-off-by: Stoiko Ivanov <s.ivanov@proxmox.com>
---
would be grateful for suggestions that are a better fit than 'only-content'!

 src/PMG/RuleDB/ContentTypeFilter.pm | 75 ++++++++++++++++++++++++++---
 1 file changed, 68 insertions(+), 7 deletions(-)

diff --git a/src/PMG/RuleDB/ContentTypeFilter.pm b/src/PMG/RuleDB/ContentTypeFilter.pm
index 0199311..550a880 100644
--- a/src/PMG/RuleDB/ContentTypeFilter.pm
+++ b/src/PMG/RuleDB/ContentTypeFilter.pm
@@ -26,7 +26,7 @@ sub otype_text {
 }
 
 sub new {
-    my ($type, $fvalue, $ogroup) = @_;
+    my ($type, $fvalue, $ogroup, $only_content) = @_;
 
     my $class = ref($type) || $type;
 
@@ -36,6 +36,7 @@ sub new {
     }
 
     my $self = $class->SUPER::new('content-type', $fvalue, $ogroup);
+    $self->{only_content} = $only_content;
 
     return $self;
 }
@@ -52,9 +53,50 @@ sub load_attr {
 	$obj->{field_value} = $nt;
     }
 
+    my $sth = $ruledb->{dbh}->prepare(
+	"SELECT * FROM Attribut WHERE Object_ID = ?");
+
+    $sth->execute($id);
+
+    $obj->{only_content} = 0;
+
+    while (my $ref = $sth->fetchrow_hashref()) {
+	if ($ref->{name} eq 'only_content') {
+	    $obj->{only_content} = $ref->{value};
+	}
+    }
+
+    $sth->finish();
+
+    $obj->{id} = $id;
+
+    $obj->{digest} = Digest::SHA::sha1_hex( $id, $value, $ogroup, $obj->{only_content});
+
     return $obj;
 }
 
+sub save {
+    my ($self, $ruledb) = @_;
+
+    if (defined($self->{id})) {
+	#update - clean old attribut entries
+	$ruledb->{dbh}->do(
+	    "DELETE FROM Attribut WHERE Object_ID = ?",
+	    undef, $self->{id});
+    }
+
+    $self->{id} = $self->SUPER::save($ruledb);
+
+    if (defined($self->{only_content})) {
+	$ruledb->{dbh}->do(
+	    "INSERT INTO Attribut (Value, Name, Object_ID) VALUES (?, 'only_content', ?) ".
+	    "ON CONFLICT(Object_ID, Name) DO UPDATE SET Value = Excluded.Value ",
+	    undef, $self->{only_content},  $self->{id});
+    }
+
+    return $self->{id};
+}
+
 sub parse_entity {
     my ($self, $entity) = @_;
 
@@ -78,12 +120,16 @@ sub parse_entity {
 
 	my $glob_ct = $entity->{PMX_glob_ct};
 
-	if ($header_ct && $header_ct =~ m|$self->{field_value}|) {
-	    push @$res, $id;
-	} elsif ($magic_ct && $magic_ct =~ m|$self->{field_value}|) {
-	    push @$res, $id;
-	} elsif ($glob_ct && $glob_ct =~ m|$self->{field_value}|) {
+	my $check_only_content = ${self}->{only_content} // 1;
+
+	if ($magic_ct && $magic_ct =~ m|$self->{field_value}|) {
 	    push @$res, $id;
+	} elsif (!$check_only_content) {
+	    if ($header_ct && $header_ct =~ m|$self->{field_value}|) {
+		push @$res, $id;
+	    } elsif ($glob_ct && $glob_ct =~ m|$self->{field_value}|) {
+		push @$res, $id;
+	    }
 	}
     }
 
@@ -112,19 +158,34 @@ sub properties {
 	    pattern => '[0-9a-zA-Z\/\\\[\]\+\-\.\*\_]+',
 	    maxLength => 1024,
 	},
+	'only-content' => {
+	    description => "use content-type from scanning only (ignore filename and header)",
+	    type => 'boolean',
+	    optional => 1,
+	    default => 0,
+	},
     };
 }
 
 sub get {
     my ($self) = @_;
 
-    return { contenttype => $self->{field_value} };
+    return {
+	contenttype => $self->{field_value},
+	'only-content' => $self->{only_content},
+    };
 }
 
 sub update {
     my ($self, $param) = @_;
 
     $self->{field_value} = $param->{contenttype};
+
+    if (defined($param->{'only-content'}) && $param->{'only-content'} == 1) {
+	$self->{only_content} = 1;
+    } else {
+	delete $self->{only_content};
+    }
 }
 
 1;
-- 
2.39.5



_______________________________________________
pmg-devel mailing list
pmg-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pmg-devel