Ticket #406: fuzzyocr.diffs.txt

diff -pU10 -rU10 ./FuzzyOcr.pm /etc/mail/spamassassin/FuzzyOcr.pm
--- ./FuzzyOcr.pm       2007-07-07 21:45:20.000000000 -0700
+++ /etc/mail/spamassassin/FuzzyOcr.pm  2007-07-11 13:07:55.000000000 -0700
@@ -148,21 +148,34 @@ sub fuzzyocr_do {
             $fname =~ s/[<>]//g;
             $fname =~ tr/\@\$\%\&/_/s;
         }
 
         my $filename = $fname; $filename =~ tr{a-zA-Z0-9\-.}{_}cs;
         debuglog("fname: \"$fname\" => \"$filename\"");
         my $pdata = $p->decode();
         my $pdatalen = length($pdata);
         my $w = 0; my $h = 0;
 
-        if ( substr($pdata,0,3) eq "\x47\x49\x46" ) {
+        if ($pdata =~ /^P([1-7])\n/o) {
+           ## NETPBM File
+           if ($pdata =~ /^P[1-7]\n([0-9]+) ([0-9]+)\n/o) {
+               $w = $1;
+               $h = $2;
+           } else {
+               errorlog("Cannot find image dimensions");
+           }
+
+           $imgfiles{$filename}{ftype} = 0;
+           $imgfiles{$filename}{width}  = $w;
+           $imgfiles{$filename}{height} = $h;
+           infolog("NETPBM: [${h}x${w}] $filename ($pdatalen)");
+       } elsif ( substr($pdata,0,3) eq "\x47\x49\x46" ) {
             ## GIF File
             $imgfiles{$filename}{ftype} = 1; 
             ($w,$h) = unpack("vv",substr($pdata,6,4));
             infolog("GIF: [${h}x${w}] $filename ($pdatalen)");
             $imgfiles{$filename}{width}  = $w;
             $imgfiles{$filename}{height} = $h;
         } elsif ( substr($pdata,0,2) eq "\xff\xd8" ) {
             ## JPEG File
             my @Markers = (0xC0,0xC1,0xC2,0xC3,0xC5,0xC6,0xC7,0xC9,0xCA,0xCB,0xCD,0xCE,0xCF);
             my $pos = 2;
@@ -369,21 +382,58 @@ sub fuzzyocr_do {
 
         if($$pic{fname} =~ /\.([\w-]+)$/) {
             $suffix = $1;
         }
         if ($suffix) {
             debuglog("File has Content-Type \"$mimetype\" and File Extension \"$suffix\"");
         } else {
             debuglog("File has Content-Type \"$mimetype\" and no File Extension");
         }
 
-        if ( $$pic{ftype} == 1 ) {
+        if ( $$pic{ftype} == 0 ) {
+            infolog("Found NETPBM header name=\"$$pic{fname}\"");
+
+           if ($conf->{focr_skip_ppm}) {
+               infolog("Skipping image check");
+               next;
+           }
+
+           my $max_size;
+
+           if (defined($conf->{focr_max_size_ppm}) and ($$pic{fsize} > $conf->{focr_max_size_ppm})) {
+               infolog("PPM file size ($$pic{fsize}) exceeds maximum file size for this format, skipping...");
+               next;
+           }
+
+           if ( ($$pic{ctype} !~ /(pbm|pgm|ppm|pnm|pam)/i) and not $generic_ctype) {
+               wrong_ctype( "PPM", $$pic{ctype} );
+               $internal_score += $conf->{'focr_wrongctype_score'};
+           }
+
+            if ( $suffix and $suffix !~ /ppm/i) {
+                wrong_extension( "PPM", $suffix);
+                $internal_score += $conf->{'focr_wrongext_score'};
+            }
+
+           unless (defined $conf->{'focr_bin_ppmtopgm'}) {
+               errorlog("Cannot exec ppmtopgm, skipping image");
+               next;
+           }
+
+            printf RAWERR qq(## link($file, $pfile)\n) if ($haserr>0);
+           unless (link($file, $pfile)) {
+                printf RAWERR "?? link failed: $!\n" if ($haserr>0);
+                errorlog("link($file, $pfile) failed, skipping...");
+                ++$imgerr if $conf->{focr_keep_bad_images}>0; next;
+           }
+       }
+       elsif ( $$pic{ftype} == 1 ) {
             infolog("Found GIF header name=\"$$pic{fname}\"");
             if ($conf->{focr_skip_gif}) {
                 infolog("Skipping image check");
                 next;
             }
             if (defined($conf->{focr_max_size_gif}) and ($$pic{fsize} > $conf->{focr_max_size_gif})) {
                 infolog("GIF file size ($$pic{fsize}) exceeds maximum file size for this format, skipping...");
                 next;
             }