refs #18664
Arvados-DCO-1.1-Signed-off-by: Tom Clegg <tom@curii.com>
dumped, err := ioutil.ReadFile(dumpdir + "/variants.csv")
c.Assert(err, check.IsNil)
c.Logf("%s", dumped)
dumped, err := ioutil.ReadFile(dumpdir + "/variants.csv")
c.Assert(err, check.IsNil)
c.Logf("%s", dumped)
- c.Check(string(dumped), check.Matches, `(?ms).*\n6,1,1,chr2,349,AAAACTG.*`)
+ c.Check("\n"+string(dumped), check.Matches, `(?ms).*\n6,1,1,chr2,349,AAAACTG.*`)
}
c.Log("=== slice-numpy ===")
}
c.Log("=== slice-numpy ===")
}
type importStats struct {
}
type importStats struct {
- InputFile string
- InputLabel string
- InputLength int
- InputCoverage int
- PathLength int
- DroppedOutOfOrderTiles int
+ InputFile string
+ InputLabel string
+ InputLength int
+ InputCoverage int
+ PathLength int
+ DroppedRepeatedTags int
+ DroppedOutOfOrderTags int
}
func (tilelib *tileLibrary) TileFasta(filelabel string, rdr io.Reader, matchChromosome *regexp.Regexp, isRef bool) (tileSeq, []importStats, error) {
}
func (tilelib *tileLibrary) TileFasta(filelabel string, rdr io.Reader, matchChromosome *regexp.Regexp, isRef bool) (tileSeq, []importStats, error) {
log.Warnf("%s %s no tags found", filelabel, job.label)
}
log.Warnf("%s %s no tags found", filelabel, job.label)
}
if !tilelib.useDups {
// Remove any tags that appeared more than once
dup := map[tagID]bool{}
if !tilelib.useDups {
// Remove any tags that appeared more than once
dup := map[tagID]bool{}
- skipped += len(found) - dst
+ droppedDup = len(found) - dst
+ log.Infof("%s %s dropping %d non-unique tags", filelabel, job.label, droppedDup)
- log.Infof("%s %s keeping longest increasing subsequence", filelabel, job.label)
keep := longestIncreasingSubsequence(len(found), func(i int) int { return int(found[i].tagid) })
for i, x := range keep {
found[i] = found[x]
}
keep := longestIncreasingSubsequence(len(found), func(i int) int { return int(found[i].tagid) })
for i, x := range keep {
found[i] = found[x]
}
- skipped += len(found) - len(keep)
+ droppedOOO = len(found) - len(keep)
+ log.Infof("%s %s dropping %d out-of-order tags", filelabel, job.label, droppedOOO)
found = found[:len(keep)]
}
found = found[:len(keep)]
}
ret[job.label] = pathcopy
basesIn := countBases(job.fasta)
ret[job.label] = pathcopy
basesIn := countBases(job.fasta)
- log.Infof("%s %s fasta in %d coverage in %d path len %d low-quality %d skipped-out-of-order %d", filelabel, job.label, len(job.fasta), basesIn, len(path), lowquality, skipped)
+ log.Infof("%s %s fasta in %d coverage in %d path len %d low-quality %d", filelabel, job.label, len(job.fasta), basesIn, len(path), lowquality)
stats = append(stats, importStats{
stats = append(stats, importStats{
- InputFile: filelabel,
- InputLabel: job.label,
- InputLength: len(job.fasta),
- InputCoverage: basesIn,
- PathLength: len(path),
- DroppedOutOfOrderTiles: skipped,
+ InputFile: filelabel,
+ InputLabel: job.label,
+ InputLength: len(job.fasta),
+ InputCoverage: basesIn,
+ PathLength: len(path),
+ DroppedOutOfOrderTags: droppedOOO,
+ DroppedRepeatedTags: droppedDup,
})
totalPathLen += len(path)
})
totalPathLen += len(path)