19d33fe8c7b5b90b7faa514185c79eb6af0d8d8b
hiram
Tue Jan 21 13:22:47 2020 -0800
now using new style GCF path names and separate hubs for each assembly refs #24748
diff --git src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl
index cb3d393..d8414ae 100755
--- src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl
+++ src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl
@@ -1,25 +1,26 @@
#!/usr/bin/env perl
use strict;
use warnings;
use File::stat;
my $home = $ENV{'HOME'};
my $srcDocDir = "primateAsmHub";
my $asmHubDocDir = "$home/kent/src/hg/makeDb/doc/$srcDocDir";
my $asmHubName = "primates";
+my $Name = "Primate";
my $commonNameList = "primates.asmId.commonName.tsv";
my $commonNameOrder = "primates.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 $assemblyCount = 0;
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:
##############################################################################
@@ -27,46 +28,46 @@
my $text = reverse $_[0];
$text =~ s/(\d\d\d)(?=\d)(?!\d*\.)/$1,/g;
return scalar reverse $text
}
##############################################################################
### start the HTML output
##############################################################################
sub startHtml() {
my $timeStamp = `date "+%F"`;
chomp $timeStamp;
print <<"END"
-
+
-Primate Genomes assembly hubs
+$Name Genomes assembly hubs
-Assemblies from NCBI/Genbank/Refseq sources
+Assemblies from NCBI/Genbank/Refseq sources, subset of $asmHubName only.
-
-
-
+
Data resource links
-NOTE: Click on the column headers to sort the table by that column
+NOTE: Click on the column headers to sort the table by that column
+The link to genome browser will attach only that single assembly to
+the genome browser.
END
}
##############################################################################
### start the table output
##############################################################################
sub startTable() {
print <<"END"
| count |
common name
link to genome browser |
scientific name
and data download |
NCBI assembly |
sequence
count | genome size
nucleotides |
gap
count | unknown bases
(gap size sum) | masking
percent |
@@ -214,31 +215,31 @@
$sciName = $line;
$commonName =~ s/.*\(//;
$commonName =~ s/\)//;
$sciName =~ s/.*:\s+//;
$sciName =~ s/\s+\(.*//;
}
} elsif ($line =~ m/Taxid:/) {
if ($taxId =~ m/notFound/) {
++$itemsFound;
$taxId = $line;
$taxId =~ s/.*:\s+//;
}
}
}
close (FH);
- printf "
|---|
| %d | %s | \n", ++$asmCount, $asmHubName, $asmId, $commonName;
+ printf "
|---|
| %d | %s | \n", ++$asmCount, $asmId, $asmId, $asmId, $commonName;
printf " %s | \n", $asmHubName, $asmId, $sciName;
printf " %s | \n", $gcPrefix, $asmAcc, $asmId;
printf " %s | \n", commify($seqCount);
printf " %s | \n", commify($totalSize);
printf " %s | \n", commify($gapCount);
printf " %s | \n", commify($gapSize);
printf " %.2f | \n", $maskPerCent;
printf "
|---|
\n";
}
}
##############################################################################
### main()
##############################################################################