obitools/obitools3
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 66 Wiki Activity

obi import: Skipping sequences is now done through the iterators so that

Browse Source 
sequences are not uselessly parsed
This commit is contained in:
Celine Mercier
2017-07-10 17:02:30 +02:00
parent b94ec9557f
commit b6b95f26b6
3 changed files with 73 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
python/obitools3/commands/import.pyx
View File

@ -155,12 +155,12 @@ def run(config):
if config['import']['seqinformat']=='fasta':
get_quality = False
NUC_SEQS_view = True
iseq = fastaIterator(inputs)
iseq = fastaIterator(inputs, skip=config['import']['skip'])
view = View_NUC_SEQS.new(d, config['import']['destview'], quality=get_quality)
elif config['import']['seqinformat']=='fastq':
get_quality = True
NUC_SEQS_view = True
iseq = fastqIterator(inputs)
iseq = fastqIterator(inputs, skip=config['import']['skip'])
view = View_NUC_SEQS.new(d, config['import']['destview'], quality=get_quality)
else:
raise RuntimeError('File format not handled')
@ -175,12 +175,9 @@ def run(config):
dcols = {}
skipping = 0
i = 0
for seq in iseq :
if skipping < config['import']['skip'] : # TODO not efficient because sequences are parsed
skipping+=1
elif i == config['import']['only'] :
if i == config['import']['only'] :
break
else :
pb(i)