Mercurial > repos > greg > vsnp_sample_names

comparison vsnp_sample_names.xml @ 7:e1cb13d6a82c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_sample_names commit f85ae0f073297ca7f5dfa22ae3a24f5fc2e6bad6"
author greg
date Fri, 03 Sep 2021 17:21:52 +0000
parents fb3defef50e5
children 4f43f163c408
comparison
equal deleted inserted replaced
6:7514b1e55372 7:e1cb13d6a82c
2 <description></description> 2 <description></description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <command detect_errors="exit_code"><![CDATA[ 6 <command detect_errors="exit_code"><![CDATA[
7 #import difflib
7 #import os 8 #import os
8 #import re 9 #import re
9 10
10 #set sample_name_read2 = None 11 #if $input_type_cond.input_type == 'single':
11
12 #if $input_type_cond.input_type in ['single', 'pair']:
13 #set read1 = $input_type_cond.read1 12 #set read1 = $input_type_cond.read1
14 #set sample_name = re.sub('[^\s\w\-]', '_', str($read1.element_identifier)) 13 #set sample_name = re.sub('[^\s\w\-\\.]', '_', str($read1.element_identifier))
14 #else if $input_type_cond.input_type == 'pair':
15 #set read1 = $input_type_cond.read1
16 #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier))
17 #set read2 = $input_type_cond.read2
18 #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier))
19 #set matches = difflib.SequenceMatcher(None, read1_identifier, read2_identifier).get_matching_blocks()
20 #set match = $matches[0]
21 #set sample_name = re.sub('[^\s\w\-]', '_', str($read1_identifier[match.a:match.a + match.size]))
15 #else: 22 #else:
16 #set read1_filename = $input_type_cond.reads_collection['forward'].name 23 #set read1 = $input_type_cond.reads_collection['forward']
24 #set read1_filename = $read1.name
17 #set sample_name = re.sub('[^\s\w\-]', '_', str($read1_filename)) 25 #set sample_name = re.sub('[^\s\w\-]', '_', str($read1_filename))
18 #end if 26 #end if
19 27
20 #if $sample_name.find('_R1') >0: 28 #if $sample_name.find('_R1') >0:
21 ## Something like CMC_20E1_R1.fastq.gz 29 ## Something like CMC_20E1_R1.fastq.gz
22 #set sample_name = $sample_name.split('_R1')[0] 30 #set sample_name = $sample_name.split('_R1')[0]
23 #else if $sample_name.find(".") > 0: 31 #else if $sample_name.find(".") > 0:
24 #if $read1.is_of_type('fastqsanger.gz'): 32 #if $read1.is_of_type('fastqsanger.gz') and $sample_name.endswith('gz'):
25 ## Something like my_sample.fastq.gz 33 ## Something like my_sample.fastq.gz
26 #set sample_name = '.'.join($sample_name.split('.')[0:-2]) 34 #set sample_name = '.'.join($sample_name.split('.')[0:-2])
27 #else: 35 #else:
28 ## Something like my_sample.fastq 36 ## Something like my_sample.fastq
29 #set sample_name = $os.path.splitext($sample_name)[0] 37 #set sample_name = $os.path.splitext($sample_name)[0]
30 #end if 38 #end if
31 #else if $sample_name.find("_") > 0: 39 #else if $sample_name.find("_") > 0:
32 #if $read1.is_of_type('fastqsanger.gz'): 40 #if $read1.is_of_type('fastqsanger.gz') and $sample_name.endswith('gz'):
33 ## Something like my_sample_fastq_gz 41 ## Something like my_sample_fastq_gz
34 #set sample_name = '_'.join($sample_name.split('_')[0:-2]) 42 #set sample_name = '_'.join($sample_name.split('_')[0:-2])
35 #else: 43 #else:
36 ## Something like my_sample_fastq 44 ## Something like my_sample_fastq
37 #set sample_name = "_".join($sample_name.split("_")[0:-1]) 45 #set sample_name = "_".join($sample_name.split("_")[0:-1])
38 #end if 46 #end if
39 #end if 47 #end if
48
40 echo '$sample_name' > '$output' 49 echo '$sample_name' > '$output'
41 ]]></command> 50 ]]></command>
42 <inputs> 51 <inputs>
43 <conditional name="input_type_cond"> 52 <conditional name="input_type_cond">
44 <param name="input_type" type="select" label="Choose the category of the files to be analyzed"> 53 <param name="input_type" type="select" label="Choose the category of the files to be analyzed">
47 <option value="paired">List of dataset pairs</option> 56 <option value="paired">List of dataset pairs</option>
48 </param> 57 </param>
49 <when value="single"> 58 <when value="single">
50 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> 59 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/>
51 </when> 60 </when>
52 <when value="paired">
53 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of fastqsanger paired read files"/>
54 </when>
55 <when value="pair"> 61 <when value="pair">
56 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> 62 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/>
57 <param name="read2" type="data" format="fastqsanger.gz,fastqsanger" label="Read2 fastq file"/> 63 <param name="read2" type="data" format="fastqsanger.gz,fastqsanger" label="Read2 fastq file"/>
64 </when>
65 <when value="paired">
66 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of fastqsanger paired read files"/>
58 </when> 67 </when>
59 </conditional> 68 </conditional>
60 </inputs> 69 </inputs>
61 <outputs> 70 <outputs>
62 <data name="output" format="txt"/> 71 <data name="output" format="txt"/>
66 <test> 75 <test>
67 <param name="input_type" value="single"/> 76 <param name="input_type" value="single"/>
68 <param name="read1" value="CMC_20E1_R1.fastq.gz" dbkey="89"/> 77 <param name="read1" value="CMC_20E1_R1.fastq.gz" dbkey="89"/>
69 <output name="output" file="sample_names.txt" ftype="txt"/> 78 <output name="output" file="sample_names.txt" ftype="txt"/>
70 </test> 79 </test>
71 <!-- Paired reads --> 80 <!-- Paired reads in separate datasets -->
81 <test>
82 <param name="input_type" value="pair"/>
83 <param name="read1" value="CMC_20E1_R1.fastq.gz" dbkey="89"/>
84 <param name="read2" value="CMC_20E1_R2.fastq.gz" dbkey="89"/>
85 <output name="output" file="sample_names.txt" ftype="txt"/>
86 </test>
87 <!-- Collection of Paired reads -->
72 <test> 88 <test>
73 <param name="input_type" value="paired"/> 89 <param name="input_type" value="paired"/>
74 <param name="reads_collection"> 90 <param name="reads_collection">
75 <collection type="paired"> 91 <collection type="paired">
76 <element name="forward" value="CMC_20E1_R1.fastq.gz"/> 92 <element name="forward" value="CMC_20E1_R1.fastq.gz"/>
77 <element name="reverse" value="CMC_20E1_R2.fastq.gz"/> 93 <element name="reverse" value="CMC_20E1_R2.fastq.gz"/>
78 </collection> 94 </collection>
79 </param> 95 </param>
80 <output name="output" file="sample_names.txt" ftype="txt"/> 96 <output name="output" file="sample_names.txt" ftype="txt"/>
81 </test> 97 </test>
82 <!-- Paired reads in separate datasets --> 98 <!-- Collection of Paired reads -->
83 <test> 99 <test>
84 <param name="input_type" value="pair"/> 100 <param name="input_type" value="paired"/>
85 <param name="read1" value="CMC_20E1_R1.fastq.gz" dbkey="89"/> 101 <param name="reads_collection">
86 <param name="read2" value="CMC_20E1_R2.fastq.gz" dbkey="89"/> 102 <collection type="paired">
87 <output name="output" file="sample_names.txt" ftype="txt"/> 103 <element name="forward" value="SRR14085881_forward"/>
104 <element name="reverse" value="SRR14085881_reverse"/>
105 </collection>
106 </param>
107 <output name="output" file="sample_names2.txt" ftype="txt"/>
88 </test> 108 </test>
89 </tests> 109 </tests>
90 <help> 110 <help>
91 **What it does** 111 **What it does**
92 112