ecc8358a1e03a67aba51417799cca013f98eacc5 hiram Mon Feb 17 16:38:17 2020 -0800 correct construction of name index file from the gtfToGenePred infoOut.txt newer format refs #23891 diff --git src/hg/utils/automation/doEnsGeneUpdate.pl src/hg/utils/automation/doEnsGeneUpdate.pl index a6a6445..6451c8c 100755 --- src/hg/utils/automation/doEnsGeneUpdate.pl +++ src/hg/utils/automation/doEnsGeneUpdate.pl @@ -536,32 +536,34 @@ genePredToBed $db.allGenes.gp.gz stdout | sort -k1,1 -k2,2n > $db.ensGene.bed _EOF_ ); if (-s "$chromSizes") { $bossScript->add(<<_EOF_ bedToBigBed -extraIndex=name $db.ensGene.bed $chromSizes bbi/$db.ensGene.bb _EOF_ ); } else { $bossScript->add(<<_EOF_ bedToBigBed -extraIndex=name $db.ensGene.bed ../../../chrom.sizes bbi/$db.ensGene.bb _EOF_ ); } $bossScript->add(<<_EOF_ -grep -v "^#" infoOut.txt | awk '{printf "%s\\t%s,%s,%s,%s,%s\\n", \$1,\$2,\$3,\$8,\$9,\$10}' > $db.ensGene.nameIndex.txt -ixIxx $db.ensGene.nameIndex.txt $db.ensGene.name.ix $db.ensGene.name.ixx +grep -v "^#" infoOut.txt \\ + | awk -F\$'\\t' '{printf "%s\\t%s,%s,%s,%s\\n", \$1,\$2,\$8,\$9,\$10}' \\ + | sed -e 's/,,/,/g; s/,\$//;' > $db.ensGene.nameIndex.txt +ixIxx $db.ensGene.nameIndex.txt $db.ensGene.ix $db.ensGene.ixx _EOF_ ); } $bossScript->execute() if (! $opt_debug); } # doProcess ######################################################################### # * step: download [dbHost] sub doDownload { my $runDir = "$buildDir/download"; # check if been already done if (-s "$runDir/$ensGtfFile" && -s "$runDir/$ensPepFile" ) { &HgAutomate::verbose(1, "# step download is already completed, continuing...\n");