Mercurial > repos > nml > biohansel
comparison 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 |
comparison
equal
deleted
inserted
replaced
0:c6e29bb1ab31 | 1:1f8eccf9d15d |
---|---|
8 | 8 |
9 #import re | 9 #import re |
10 | 10 |
11 ## Illumina FASTQ naming regular expression (https://github.com/phac-nml/biohansel/issues/38) | 11 ## Illumina FASTQ naming regular expression (https://github.com/phac-nml/biohansel/issues/38) |
12 #set global $ILLUMINA_REGEX = $re.compile(r'^([\w\-\_]+)_S\d+_L\d{3}_R(\d)_001\.fastq(\.gz)?$') | 12 #set global $ILLUMINA_REGEX = $re.compile(r'^([\w\-\_]+)_S\d+_L\d{3}_R(\d)_001\.fastq(\.gz)?$') |
13 #set global $FASTQ_DUMP_REGEX = $re.compile(r'^(\w+|\d+):((forward|reverse)(_\d+)?)\.fastq(\.gz|sanger)?$') | |
13 | 14 |
14 #def is_gzipped_fastq($data_input) | 15 #def is_gzipped_fastq($data_input) |
15 ## Is FASTQ data param gzipped type? i.e. either 'fastq.gz' or 'fastqsanger.gz'? | 16 ## Is FASTQ data param gzipped type? i.e. either 'fastq.gz' or 'fastqsanger.gz'? |
16 #return $data_input.is_of_type('fastqsanger.gz') or $data_input.is_of_type('fastq.gz') | 17 #return $data_input.is_of_type('fastqsanger.gz') or $data_input.is_of_type('fastq.gz') |
17 #end def | 18 #end def |
22 #end def | 23 #end def |
23 | 24 |
24 #def base_sample_name($name) | 25 #def base_sample_name($name) |
25 ## Get the base sample name and append 1/2 depending on if forward/reverse read | 26 ## Get the base sample name and append 1/2 depending on if forward/reverse read |
26 #set $illumina_match = $ILLUMINA_REGEX.match($name) | 27 #set $illumina_match = $ILLUMINA_REGEX.match($name) |
28 #set $fastq_dump_match = $FASTQ_DUMP_REGEX.match($name) | |
29 | |
27 #if $illumina_match | 30 #if $illumina_match |
28 #return $illumina_match.group(1) | 31 #return $illumina_match.group(1) |
29 #elif $re.search(r'_R(1|2)', $name): | 32 #elif $re.search(r'_R(1|2)', $name): |
30 #return $re.sub(r'(.+)_R(1|2)([^\.]*)(\..+)', r'\1\3', $name) | 33 #return $re.sub(r'(.+)_R(1|2)([^\.]*)(\..+)', r'\1\3', $name) |
31 #elif $re.match(r'.+_\d\.', $name): | 34 #elif $re.match(r'.+_\d\.', $name): |
32 #return $re.sub(r'(.+)_(\d)(\..+)', r'\1', $name) | 35 #return $re.sub(r'(.+)_(\d)(\..+)', r'\1', $name) |
33 #else | 36 #elif $fastq_dump_match |
37 #return $fastq_dump_match.group(1) | |
38 #else | |
34 #return $name | 39 #return $name |
35 #end if | 40 #end if |
36 #end def | 41 #end def |
37 | 42 |
38 #def get_paired_fastq_filename($data_input, $name=None, $is_forward=True) | 43 #def get_paired_fastq_filename($data_input, $name=None, $is_forward=True) |