Skip to content
Snippets Groups Projects
Commit e24f2062 authored by Robert Bossy's avatar Robert Bossy
Browse files

fixed bug some entries contain tab character, added check step

parent 3489bde1
No related branches found
No related tags found
No related merge requests found
taxa+id_microorganisms.txt
_attic/
output/
.snakemake/
......
<alvisnlp-plan id="check-taxonomy">
<param name="taxo">
<alias module="read-taxonomy" param="dictFile"/>
</param>
<param name="finish">
<alias module="finish" param="corpusFile"/>
</param>
<read-taxonomy class="TabularProjector">
<targetLayerName>__dummy</targetLayerName>
<valueFeatures>,taxid,canonical-name,path,pos,rank,species-taxid,species-name</valueFeatures>
</read-taxonomy>
<finish class="TabularExport">
<outDir>.</outDir>
<lines>$</lines>
<columns>"checked"</columns>
</finish>
</alvisnlp-plan>
......@@ -77,7 +77,7 @@ class BacDiveEntry:
for sne in self.root.iterfind('./strain_availability/strains/list-item/strain_number'):
if sne.text is None:
continue
yield from (snt.strip() for snt in re.split('[,\n]', sne.text))
yield from (' '.join(snt.strip().split()) for snt in re.split('[,\n]', sne.text))
desig = self.root.findtext('./taxonomy_name/strains/list-item/designation')
if desig is not None and desig != '':
for d in re.split('[,;]', desig):
......
configfile: 'config.yaml'
rule check:
input:
config['OUTDIR'] + '/taxa+id_microorganisms.txt'
output:
config['OUTDIR'] + '/finish.txt'
shell:
'''{config[ALVISNLP]} -J-Xmx12G -alias taxo {input} -alias finish {output} check-taxonomy.plan'''
rule microorganisms:
output:
config['OUTDIR'] + '/taxa+id_microorganisms.txt'
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment