3a103914b717293d5a2723c2306db20a889a31c7
hiram
  Fri Feb 14 14:47:59 2020 -0800
now with new path names for download access refs #23891

diff --git src/hg/makeDb/doc/asmHubs/mkAsmStats.pl src/hg/makeDb/doc/asmHubs/mkAsmStats.pl
index 06f6e58..c8613fc 100755
--- src/hg/makeDb/doc/asmHubs/mkAsmStats.pl
+++ src/hg/makeDb/doc/asmHubs/mkAsmStats.pl
@@ -8,30 +8,32 @@
 if ($argc != 2) {
   printf STDERR "mkAsmStats Name asmName\n";
   printf STDERR "e.g.: mkAsmStats Mammals mammals\n";
   exit 255;
 }
 my $Name = shift;
 my $asmHubName = shift;
 
 my $home = $ENV{'HOME'};
 my $toolsDir = "$home/kent/src/hg/makeDb/doc/asmHubs";
 
 my $commonNameList = "$asmHubName.asmId.commonName.tsv";
 my $commonNameOrder = "$asmHubName.commonName.asmId.orderList.tsv";
 my @orderList;	# asmId of the assemblies in order from the *.list files
 # the order to read the different .list files:
+my %betterName;	# key is asmId, value is better common name than found in
+		# assembly_report
 
 my $assemblyTotal = 0;	# complete list of assemblies in this group
 my $asmCount = 0;	# count of assemblies completed and in the table
 my $overallNucleotides = 0;
 my $overallSeqCount = 0;
 my $overallGapSize = 0;
 my $overallGapCount = 0;
 
 ##############################################################################
 # from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters:
 ##############################################################################
 sub commify($) {
     my $text = reverse $_[0];
     $text =~ s/(\d\d\d)(?=\d)(?!\d*\.)/$1,/g;
     return scalar reverse $text
@@ -91,63 +93,73 @@
 ### end the table output
 ##############################################################################
 sub endTable() {
 
 my $commaNuc = commify($overallNucleotides);
 my $commaSeqCount = commify($overallSeqCount);
 my $commaGapSize = commify($overallGapSize);
 my $commaGapCount = commify($overallGapCount);
 
 my $percentDone = 100.0 * $asmCount / $assemblyTotal;
 my $doneMsg = "";
 if ($asmCount < $assemblyTotal) {
   $doneMsg = sprintf(" (%d build completed, %.2f %% finished)", $asmCount, $percentDone);
 }
 
+if ($assemblyTotal > 1) {
   print <<"END"
 
 </tbody>
 <tfoot><tr><th>TOTALS:</th><td align=center colspan=3>total assembly count&nbsp;${assemblyTotal}${doneMsg}</td>
   <td align=right>$commaSeqCount</td>
   <td align=right>$commaNuc</td>
   <td align=right>$commaGapCount</td>
   <td align=right>$commaGapSize</td>
   <td colspan=1>&nbsp;</td>
   </tr></tfoot>
 </table>
 END
+} else {
+  print <<"END"
+
+</tbody>
+</table>
+END
 }
+}	#	sub endTable()
 
 ##############################################################################
 ### end the HTML output
 ##############################################################################
 sub endHtml() {
 
+if ($asmHubName ne "viral") {
   printf "<p>\nOther assembly hubs available:<br>\n<table border='1'><thead>\n<tr>";
 
   printf "<th><a href='../primates/asmStatsPrimates.html'>Primates</a></th>\n"
     if ($asmHubName ne "primates");
   printf "<th><a href='../mammals/asmStatsMammals.html'>Mammals</a></th>\n"
     if ($asmHubName ne "mammals");
   printf "<th><a href='../birds/asmStatsBirds.html'>Birds</a></th>\n"
     if ($asmHubName ne "birds");
   printf "<th><a href='../fish/asmStatsFish.html'>Fish</a></th>\n"
     if ($asmHubName ne "fish");
   printf "<th><a href='../vertebrate/asmStatsVertebrate.html'>other vertebrates</a></th>\n"
     if ($asmHubName ne "vertebrate");
 
   printf "</tr></thead>\n</table>\n</p>\n";
+}
 
 print <<"END"
 </div><!-- closing gbsPage from gbPageStartHardcoded.html -->
 </div><!-- closing container-fluid from gbPageStartHardcoded.html -->
 <!--#include virtual="\$ROOT/inc/gbFooterHardcoded.html"-->
 <script type="text/javascript" src="/js/sorttable.js"></script>
 </body></html>
 END
 }
 
 sub asmCounts($) {
   my ($chromSizes) = @_;
   my ($sequenceCount, $totalSize) = split('\s+', `ave -col=2 $chromSizes | egrep "^count|^total" | awk '{printf "%d\\n", \$NF}' | xargs echo`);
   return ($sequenceCount, $totalSize);
 }
@@ -174,39 +186,39 @@
   my $gapBed = "$buildDir/trackData/allGaps/$asmId.allGaps.bed.gz";
   my $gapCount = 0;
   if ( -s "$gapBed" ) {
     $gapCount = `zcat $gapBed | awk '{print \$3-\$2}' | ave stdin | grep '^count' | awk '{print \$2}'`;
   }
   chomp $gapCount;
   return ($gapCount);
 }
 
 ##############################################################################
 ### tableContents()
 ##############################################################################
 sub tableContents() {
 
   foreach my $asmId (reverse(@orderList)) {
+    my ($gcPrefix, $asmAcc, $asmName) = split('_', $asmId, 3);
+    my $accessionId = sprintf("%s_%s", $gcPrefix, $asmAcc);
     my $accessionDir = substr($asmId, 0 ,3);
     $accessionDir .= "/" . substr($asmId, 4 ,3);
     $accessionDir .= "/" . substr($asmId, 7 ,3);
     $accessionDir .= "/" . substr($asmId, 10 ,3);
-    $accessionDir .= "/" . $asmId;
-    my $buildDir = "/hive/data/genomes/asmHubs/refseqBuild/$accessionDir";
+    my $buildDir = "/hive/data/genomes/asmHubs/refseqBuild/$accessionDir/$asmId";
     my $asmReport="$buildDir/download/${asmId}_assembly_report.txt";
     next if (! -s "$asmReport");
-    my ($gcPrefix, $asmAcc, $asmName) = split('_', $asmId, 3);
     my $chromSizes = "${buildDir}/${asmId}.chrom.sizes";
     my $twoBit = "${buildDir}/trackData/addMask/${asmId}.masked.2bit";
     next if (! -s "$twoBit");
     my $faSizeTxt = "${buildDir}/${asmId}.faSize.txt";
     if ( ! -s "$faSizeTxt" ) {
        printf STDERR "twoBitToFa $twoBit stdout | faSize stdin > $faSizeTxt\n";
        print `twoBitToFa $twoBit stdout | faSize stdin > $faSizeTxt`;
     }
     my ($gapSize, $maskPerCent) = maskStats($faSizeTxt);
     $overallGapSize += $gapSize;
     my ($seqCount, $totalSize) = asmCounts($chromSizes);
     $overallSeqCount += $seqCount;
 #    my $totalSize=`ave -col=2 $chromSizes | grep "^total" | awk '{printf "%d", \$NF}'`;
     $overallNucleotides += $totalSize;
     my $gapCount = gapStats($buildDir, $asmId);
@@ -237,59 +249,61 @@
            $bioSample =~ s/.*:\s+//;
         }
       } elsif ($line =~ m/BioProject:/) {
         if ($bioProject =~ m/notFound/) {
            ++$itemsFound;
            $bioProject = $line;
            $bioProject =~ s/.*:\s+//;
         }
       } elsif ($line =~ m/Organism name:/) {
         if ($sciName =~ m/notFound/) {
            ++$itemsFound;
            $commonName = $line;
            $sciName = $line;
            $commonName =~ s/.*\(//;
            $commonName =~ s/\)//;
+           $commonName = $betterName{$asmId} if (exists($betterName{$asmId}));
            $sciName =~ s/.*:\s+//;
            $sciName =~ s/\s+\(.*//;
         }
       } elsif ($line =~ m/Taxid:/) {
         if ($taxId =~ m/notFound/) {
            ++$itemsFound;
            $taxId = $line;
            $taxId =~ s/.*:\s+//;
         }
       }
     }
     close (FH);
-    my $hubUrl = "https://hgdownload.soe.ucsc.edu/hubs/$accessionDir";
+    my $hubUrl = "https://hgdownload.soe.ucsc.edu/hubs/$accessionDir/$accessionId";
     printf "<tr><td align=right>%d</td>\n", ++$asmCount;
-    printf "<td align=center><a href='https://genome.ucsc.edu/cgi-bin/hgGateway?hubUrl=%s/%s.hub.txt&amp;genome=%s&amp;position=lastDbPos' target=_blank>%s</a></td>\n", $hubUrl, $asmId, $asmId, $commonName;
-    printf "    <td align=center><a href='https://hgdownload.soe.ucsc.edu/hubs/%s/genomes/%s/' target=_blank>%s</a></td>\n", $asmHubName, $asmId, $sciName;
-    printf "    <td align=left><a href='https://www.ncbi.nlm.nih.gov/assembly/%s_%s/' target=_blank>%s</a></td>\n", $gcPrefix, $asmAcc, $asmId;
+    printf "<td align=center><a href='https://genome.ucsc.edu/cgi-bin/hgGateway?hubUrl=%s/hub.txt&amp;genome=%s&amp;position=lastDbPos' target=_blank>%s</a></td>\n", $hubUrl, $asmId, $commonName;
+    printf "    <td align=center><a href='%s/' target=_blank>%s</a></td>\n", $hubUrl, $sciName;
+    printf "    <td align=left><a href='https://www.ncbi.nlm.nih.gov/assembly/%s/' target=_blank>%s</a></td>\n", $accessionId, $asmId;
     printf "    <td align=right>%s</td>\n", commify($seqCount);
     printf "    <td align=right>%s</td>\n", commify($totalSize);
     printf "    <td align=right>%s</td>\n", commify($gapCount);
     printf "    <td align=right>%s</td>\n", commify($gapSize);
     printf "    <td align=right>%.2f</td>\n", $maskPerCent;
     printf "</tr>\n";
   }
 }
 
 ##############################################################################
 ### main()
 ##############################################################################
 
 open (FH, "<$toolsDir/${commonNameOrder}") or die "can not read ${commonNameOrder}";
 while (my $line = <FH>) {
   chomp $line;
   my ($commonName, $asmId) = split('\t', $line);
   push @orderList, $asmId;
+  $betterName{$asmId} = $commonName;
   ++$assemblyTotal;
 }
 close (FH);
 
 startHtml();
 startTable();
 tableContents();
 endTable();
 endHtml();