Mercurial > repos > nml > biohansel
diff biohansel.xml @ 1:1f8eccf9d15d draft
planemo upload for repository https://github.com/phac-nml/biohansel commit b0060acc515bac2a79f60bb3c9d1f3243a5769f3
author | nml |
---|---|
date | Mon, 05 Nov 2018 16:18:22 -0500 |
parents | c6e29bb1ab31 |
children | aaab9b598c9e |
line wrap: on
line diff
--- a/biohansel.xml Wed Aug 15 10:34:50 2018 -0400 +++ b/biohansel.xml Mon Nov 05 16:18:22 2018 -0500 @@ -10,6 +10,7 @@ ## Illumina FASTQ naming regular expression (https://github.com/phac-nml/biohansel/issues/38) #set global $ILLUMINA_REGEX = $re.compile(r'^([\w\-\_]+)_S\d+_L\d{3}_R(\d)_001\.fastq(\.gz)?$') +#set global $FASTQ_DUMP_REGEX = $re.compile(r'^(\w+|\d+):((forward|reverse)(_\d+)?)\.fastq(\.gz|sanger)?$') #def is_gzipped_fastq($data_input) ## Is FASTQ data param gzipped type? i.e. either 'fastq.gz' or 'fastqsanger.gz'? @@ -24,13 +25,17 @@ #def base_sample_name($name) ## Get the base sample name and append 1/2 depending on if forward/reverse read #set $illumina_match = $ILLUMINA_REGEX.match($name) + #set $fastq_dump_match = $FASTQ_DUMP_REGEX.match($name) + #if $illumina_match #return $illumina_match.group(1) #elif $re.search(r'_R(1|2)', $name): #return $re.sub(r'(.+)_R(1|2)([^\.]*)(\..+)', r'\1\3', $name) #elif $re.match(r'.+_\d\.', $name): #return $re.sub(r'(.+)_(\d)(\..+)', r'\1', $name) - #else + #elif $fastq_dump_match + #return $fastq_dump_match.group(1) + #else #return $name #end if #end def