Stop URLs at " too. Thanks to Vincent Lefevre (Closes: #766354).

[debbugs.git] / Debbugs / Log.pm

diff --git a/Debbugs/Log.pm b/Debbugs/Log.pm
index e58d84ae486bf9d2892fbd7b54940e50c2df09d9..551fd392a36fafea8b452377e30f19dbdc20d266 100644 (file)
--- a/Debbugs/Log.pm
+++ b/Debbugs/Log.pm
@@ -39,7 +39,7 @@ use Carp;
 
 use Debbugs::Common qw(getbuglocation getbugcomponent make_list);
 use Params::Validate qw(:types validate_with);
-use Encode qw(encode);
+use Encode qw(encode encode_utf8 is_utf8);
 
 =head1 NAME
 
@@ -51,6 +51,11 @@ The Debbugs::Log module provides a convenient way for scripts to read and
 write the .log files used by debbugs to store the complete textual records
 of all bug transactions.
 
+Debbugs::Log does not decode utf8 into perl's internal encoding or
+encode into utf8 from perl's internal encoding. For html records and
+all recips, this should probably be done. For other records, this should
+not be needed.
+
 =head2 The .log File Format
 
 .log files consist of a sequence of records, of one of the following four
@@ -201,7 +206,6 @@ sub new
              die "Unable to open bug log $bug_log for reading: $!";
     }
 
-    binmode($self->{logfh},':utf8');
     $self->{state} = 'kill-init';
     $self->{linenum} = 0;
     return $self;
@@ -384,7 +388,14 @@ sub write_log_records
     for my $record (@records) {
        my $type = $record->{type};
        croak "record type '$type' with no text field" unless defined $record->{text};
-       my ($text) = escape_log($record->{text});
+       # I am not sure if we really want to croak here; but this is
+       # almost certainly a bug if is_utf8 is on.
+        my $text = $record->{text};
+        if (is_utf8($text)) {
+            carp('Record text was in the wrong encoding (perl internal instead of utf8 octets)');
+            $text = encode_utf8($text)
+        }
+       ($text) = escape_log($text);
        if ($type eq 'autocheck') {
            print {$logfh} "\01\n$text\03\n" or
                die "Unable to write to logfile: $!";
@@ -394,6 +405,15 @@ sub write_log_records
            if (defined $recips) {
                croak "recips not undef or array"
                    unless ref($recips) eq 'ARRAY';
+                my $wrong_encoding = 0;
+                my @recips =
+                    map { if (is_utf8($_)) {
+                        $wrong_encoding=1;
+                        encode_utf8($_);
+                    } else {
+                        $_;
+                    }} @$recips;
+                carp('Recipients was in the wrong encoding (perl internal instead of utf8 octets') if $wrong_encoding;
                print {$logfh} join("\04", @$recips) . "\n" or
                    die "Unable to write to logfile: $!";
            } else {
@@ -428,7 +448,7 @@ Applies the log escape regex to the passed logfile.
 
 sub escape_log {
        my @log = @_;
-       return map { eval {$_ = encode("utf8",$_,Encode::FB_CROAK)}; s/^([\01-\07\030])/\030$1/gm; $_ } @log;
+       return map {s/^([\01-\07\030])/\030$1/gm; $_ } @log;
 }