Skip to content
Snippets Groups Projects
Normal view Permalink
results_to_netscape 4.87 KiB
Newer Older
tjc's avatar
java2 version
tjc committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 
#!/bin/sh -

# This script will send a file to netscape with database IDs linked to SRS.
# To customize this script edit the $DATABASES and $SRS_SERVER variable in the
# perl code below and the NETSCAPE variable at the top of the script.

# To enable this in Artemis, sanger_options must be set to true in the options
# file.

NETSCAPE=/usr/bin/X11/real-netscape

if [ -f "$DIANA_ENVIRONMENT_FILE" ]
then
   . $DIANA_ENVIRONMENT_FILE
fi

if [ $# = 0 ]
then
    echo no argument given 1>&2
    exit 1
fi

file_arg=$1

unique_bit=$$.`hostname`

# sanger hack:
file_arg=`echo $file_arg | sed 's@^/tmp_mnt/nfs/@/nfs/@' | sed 's@^/tmp_mnt/tmp_nfs/@/nfs/@'`
# fix for pcs3:
file_arg=`echo $file_arg | sed 's@^/yeastpub4/@/nfs/disk222/yeastpub4/@'`


if [ -f ./$file_arg ]
then
    # the file is in the current directory - we need the full path so netscape
    # can find the file
    new_file=$PWD/$file_arg.$unique_bit.html
else
    new_file=$file_arg.$unique_bit.html
fi

cat <<EOF > $new_file
<HTML>
 <HEAD>
  <TITLE>
  Results for $file_arg
 </TITLE>
 </HEAD>
 <BODY>
<PRE>
EOF

perl -e '
BEGIN {
  # change these variable to list the databases to search for the IDs - the
  # database names should be separated by spaces
  $PROTEIN_DATABASES = "swall";
  $DNA_DATABASES = "embl";

  # change this to point to the wgetz script of your SRS server
  $SRS_SERVER = "www.sanger.ac.uk/srs6bin/cgi-bin/wgetz?-e+";

  $PROTEIN_DATABASES =~ s/ /%20/g;
  $DNA_DATABASES =~ s/ /%20/g;

  %GENEDB_PATTERNS = (tryp => q!Tb\d+\.\d+\.\d+|TRYP_\S+!,
                      leish => q!LmjF\d+.\d+!);

  $GENEDB_PATTERN = join ("|", values %GENEDB_PATTERNS);

  $BLAST_START_LINE = "Sequences producing High-scoring Segment Pairs|" .
    "Sequences producing significant alignments:";
  $FASTA_START_LINE = "The best scores are";

  # the list of IDs we have seen so far
  @ids = ();

  # the list of IDs we have made anchors for so far
  @anchored_ids = ();

  $db_type = "unknown";
}

sub hyperlink_to_anchor
{
  $id = shift;
  qq(<a href="#$id">$id</a>);
}

sub hyperlink_id
{
  $id = shift;

  if ($db_type eq "dna") {
    $r = qq#<a href="http://$SRS_SERVER\[\{$DNA_DATABASES\}-ID:$id*]|[\{$DNA_DATABASES\}-AccNumber:$id*]">$id</a>#;
  } else {
    for my $org (keys %GENEDB_PATTERNS) {
      my $pattern = $GENEDB_PATTERNS{$org};

      if ($id =~ /$pattern/) {
        $r = qq#<a href="http://www.genedb.org/genedb/Search?organism=$org&name=$id">$id</a>#;
        return $r
      }
    }

    $r = qq#<a href="http://$SRS_SERVER\[\{$PROTEIN_DATABASES\}-ID:$id*]|[\{$PROTEIN_DATABASES\}-AccNumber:$id*]">$id</a>#;
  }
  return $r
}

$file_name = $ARGV[0];

if ($file_name =~ /\.gz$/) {
  open IN_FILE, "gzip -d < $file_name |" or die "failed to open $file_name\n";
} else {
  open IN_FILE, "$file_name" or die "failed to open $file_name\n";
}

while (<IN_FILE>) {
  if ($. == 1) {
    if (/^\s*([^\s]+)/) {
      if (lc $1 eq "blastn" or lc $1 eq "tblastn" or lc $1 eq "tblastx") {
        $db_type = "dna";
      } else {
        if (lc $1 eq "fasta" or lc $1 eq "blastp" or lc $1 eq "blastx") {
          $db_type = "protein";
        } else {
          print "\nWARNING: could not identify file type: $1\n";
        }
      }
    } else {
      print "\nWARNING: could not identify file type\n";
    }
  }


  # ignore header lines
  if (1..m/$BLAST_START_LINE|$FASTA_START_LINE/) {
    print;
    next;
  }

  if (@ids && /^\s*$/) {
    $summary_finished = 1;
  }

  if (/^(?:(?:>?>?(?:[A-Z]+:)?)(\w+)|($GENEDB_PATTERN)) /) {
    $id = $1;

    if (!defined $id) {
      $id = $2;
    }

    if ($summary_finished) {
      if ((grep {$_ eq $id} @ids) && (!grep {$_ eq $id} @anchored_ids)) {
        # not anchored yet so make it an anchor
        if (s/\b$id\b/"<a name=\"$id\">" . (hyperlink_id($id)) . "<\/a>"/e) {
          push @anchored_ids, $id;
        }
      }
    } else {
      if (!grep {$_ eq $id} @ids) {
        push @ids, $id;
      }

      s/$id/hyperlink_to_anchor($id)/ei;

      if (!s/ $id/" " . hyperlink_id($id)/ei) {
        # if the id occurs once in the line put a link at end of line
        s/$/"  LINK:" . hyperlink_id($id)/e;
      }
    }
  }
  print;
}

' $file_arg >> $new_file

cat <<EOF >> $new_file;
</PRE>
  </BODY>
</HTML>
EOF

# delete it at some point
echo "rm -f $new_file > /dev/null 2>&1" | at now + 36 hours

if $NETSCAPE -remote "openURL($new_file)"
then
    exit 0
else
    echo starting new netscape 2>&1
    # netscape isn't running - so start it
    ($NETSCAPE &)&

    # now send the URL.  we do things this way so that the script doesn't exit
    # until netscape has successfully shown the URL

    sleep 1

    # don't exit the script until the file is successfully displayed or until
    # 40 seconds is up
    for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
    do
        if $NETSCAPE -remote "openURL($new_file)" 2> /dev/null
        then
            exit 0
        else
            sleep 2
        fi
    done

    exit 1
fi