c8828612e3aba9e6c3072768129de10abe337878 hiram Fri May 29 11:29:04 2020 -0700 now allow orderList to be specifically stated and begin common set of html functions refs #23734 diff --git src/hg/makeDb/doc/asmHubs/mkAsmStats.pl src/hg/makeDb/doc/asmHubs/mkAsmStats.pl index 881e100..8cfdb7a 100755 --- src/hg/makeDb/doc/asmHubs/mkAsmStats.pl +++ src/hg/makeDb/doc/asmHubs/mkAsmStats.pl @@ -1,38 +1,46 @@ #!/usr/bin/env perl use strict; use warnings; +use FindBin qw($Bin); +use lib "$Bin"; +use commonHtml; use File::stat; my $argc = scalar(@ARGV); if ($argc != 3) { printf STDERR "mkAsmStats Name asmHubName [two column name list]\n"; printf STDERR "e.g.: mkAsmStats Mammals mammals mammals.asmId.commonName.tsv\n"; printf STDERR "the name list is found in \$HOME/kent/src/hg/makeDb/doc/asmHubs/\n"; printf STDERR "\nthe two columns are 1: asmId (accessionId_assemblyName)\n"; printf STDERR "column 2: common name for species, columns separated by tab\n"; exit 255; } -my $Name = shift; -my $asmHubName = shift; -my $commonNameOrder = shift; my $home = $ENV{'HOME'}; my $toolsDir = "$home/kent/src/hg/makeDb/doc/asmHubs"; -my @orderList; # asmId of the assemblies in order from the commonNameOrder file +my $Name = shift; +my $asmHubName = shift; +my $inputList = shift; +my $orderList = $inputList; +if ( ! -s "$orderList" ) { + $orderList = $toolsDir/$inputList; +} + +my @orderList; # asmId of the assemblies in order from the orderList file my %commonName; # key is asmId, value is a common name, perhaps more appropriate # than found in assembly_report file my $vgpIndex = 0; $vgpIndex = 1 if ($Name =~ m/vgp/i); 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: ############################################################################## @@ -44,45 +52,53 @@ ############################################################################## ### start the HTML output ############################################################################## sub startHtml() { my $timeStamp = `date "+%F"`; chomp $timeStamp; my $subSetMessage = "subset of $asmHubName only"; if ($asmHubName eq "vertebrate") { $subSetMessage = "subset of other ${asmHubName}s only"; } if ($vgpIndex) { + my $vgpSubset = "(set of primary assemblies)"; + if ($orderList =~ m/vgp.alternate/) { + $vgpSubset = "(set of alternate/haplotype assemblies)"; + } elsif ($orderList =~ m/vgp.trio/) { + $vgpSubset = "(set of trio assemblies, maternal/paternal)"; + } elsif ($orderList =~ m/vgp.legacy/) { + $vgpSubset = "(set of legacy/superseded assemblies)"; + } print <<"END" <!DOCTYPE HTML 4.01 Transitional> <!--#set var="TITLE" value="VGP - Vertebrate Genomes Project assembly hubs, assembly statistics" --> <!--#set var="ROOT" value="../.." --> <!--#include virtual="\$ROOT/inc/gbPageStartHardcoded.html" --> <h1>VGP - Vertebrate Genomes Project assembly hubs, assembly statistics</h1> <p> <a href='https://vertebrategenomesproject.org/' target=_blank> <img src='VGPlogo.png' width=280 alt='VGP logo'></a></p> <p> This assembly hub contains assemblies released by the <a href='https://vertebrategenomesproject.org/' target=_blank> -Vertebrate Genomes Project.</a> +Vertebrate Genomes Project.</a> $vgpSubset </p> END } else { print <<"END" <!DOCTYPE HTML 4.01 Transitional> <!--#set var="TITLE" value="$Name genomes assembly hubs, assembly statistics" --> <!--#set var="ROOT" value="../.." --> <!--#include virtual="\$ROOT/inc/gbPageStartHardcoded.html" --> <h1>$Name Genomes assembly hubs, assembly statistics</h1> <p> Assemblies from NCBI/Genbank/Refseq sources, $subSetMessage. </p> @@ -162,68 +178,33 @@ "; } else { print " </tbody> </table> "; } # $assemblyTotal <= 1 } # sub endTable() ############################################################################## ### end the HTML output ############################################################################## sub endHtml() { -# do not print these links for VGP index - -if ((0 == $vgpIndex) && ($asmHubName ne "viral")) { - printf "<p>\n<table border='1'><thead>\n"; - printf "<tr><th colspan=6 style='text-align:center;'>Additional hubs with collections of assemblies</th></tr>\n"; - printf "<tr><th>Assembly hubs index pages: </th>\n"; - printf "<th><a href='../primates/index.html'>Primates</a></th>\n"; - printf "<th><a href='../mammals/index.html'>Mammals</a></th>\n"; - printf "<th><a href='../birds/index.html'>Birds</a></th>\n"; - printf "<th><a href='../fish/index.html'>Fish</a></th>\n"; - printf "<th><a href='../vertebrate/index.html'>other vertebrates</a></th>\n"; - - printf "</tr><tr>\n"; - printf "<th>Hubs assembly statistics: </th>\n"; - printf "<th><a href='../primates/asmStats.html'>Primates</a></th>\n"; - printf "<th><a href='../mammals/asmStats.html'>Mammals</a></th>\n"; - printf "<th><a href='../birds/asmStats.html'>Birds</a></th>\n"; - printf "<th><a href='../fish/asmStats.html'>Fish</a></th>\n"; - printf "<th><a href='../vertebrate/asmStats.html'>other vertebrates</a></th>\n"; - - printf "</tr><tr>\n"; - printf "<th>Hubs track statistics: </th>\n"; - printf "<th><a href='../primates/trackData.html'>Primates</a></th>\n"; - printf "<th><a href='../mammals/trackData.html'>Mammals</a></th>\n"; - printf "<th><a href='../birds/trackData.html'>Birds</a></th>\n"; - printf "<th><a href='../fish/trackData.html'>Fish</a></th>\n"; - printf "<th><a href='../vertebrate/trackData.html'>other vertebrates</a></th>\n"; - - printf "</tr></thead>\n</table>\n</p>\n"; -} +&commonHtml::otherHubLinks($vgpIndex, $asmHubName); +&commonHtml::htmlFooter($vgpIndex, $asmHubName); -print <<"END" -</div><!-- closing gbsPage from gbPageStartHardcoded.html --> -</div><!-- closing container-fluid from gbPageStartHardcoded.html --> -<!--#include virtual="\$ROOT/inc/gbFooterHardcoded.html"--> -<script type="text/javascript" src="/js/sorttable.js"></script> -</body></html> -END } sub asmCounts($) { my ($chromSizes) = @_; my ($sequenceCount, $totalSize) = split('\s+', `ave -col=2 $chromSizes | egrep "^count|^total" | awk '{printf "%d\\n", \$NF}' | xargs echo`); return ($sequenceCount, $totalSize); } # my ($gapSize) = maskStats($faSizeTxt); sub maskStats($) { my ($faSizeFile) = @_; my $gapSize = `grep 'sequences in 1 file' $faSizeFile | awk '{print \$3}'`; chomp $gapSize; $gapSize =~ s/\(//; my $totalBases = `grep 'sequences in 1 file' $faSizeFile | awk '{print \$1}'`; @@ -349,31 +330,31 @@ 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", $maskPerCent; printf "</tr>\n"; } } # sub tableContents() ############################################################################## ### main() ############################################################################## -open (FH, "<$toolsDir/${commonNameOrder}") or die "can not read ${commonNameOrder}"; +open (FH, "<${orderList}") or die "can not read ${orderList}"; while (my $line = <FH>) { next if ($line =~ m/^#/); chomp $line; my ($asmId, $commonName) = split('\t', $line); push @orderList, $asmId; $commonName{$asmId} = $commonName; ++$assemblyTotal; } close (FH); startHtml(); startTable(); tableContents(); endTable(); endHtml();