|
0
|
1 <tool id="tp_sorted_uniq" name="Unique" version="@BASE_VERSION@.0">
|
|
|
2 <description>occurrences of each record</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <version_command>sort --version | head -n 1</version_command>
|
|
|
8 <command>
|
|
|
9 <![CDATA[
|
|
|
10 sort -u
|
|
|
11 $ignore_case
|
|
|
12 $is_numeric
|
|
|
13 -t ' '
|
|
|
14 #if $adv_opts.adv_opts_selector == "advanced":
|
|
|
15 -k$adv_opts.column_start,$adv_opts.column_end
|
|
|
16 #end if
|
|
|
17 -o "$outfile"
|
|
|
18 "$infile"
|
|
|
19 ]]>
|
|
|
20 </command>
|
|
|
21 <inputs>
|
|
|
22 <param name="infile" type="data" format="tabular" label="File to scan for unique values" />
|
|
|
23 <param name="ignore_case" type="boolean" truevalue="-f" falsevalue="" checked="False"
|
|
|
24 label="Ignore differences in case when comparing" help="(-f)"/>
|
|
|
25 <param name="is_numeric" type="boolean" truevalue="-n" falsevalue="" checked="False"
|
|
|
26 label="Column only contains numeric values" help="(-n)" />
|
|
|
27 <conditional name="adv_opts">
|
|
|
28 <param name="adv_opts_selector" type="select" label="Advanced Options">
|
|
|
29 <option value="basic" selected="True">Hide Advanced Options</option>
|
|
|
30 <option value="advanced">Show Advanced Options</option>
|
|
|
31 </param>
|
|
|
32 <when value="basic" />
|
|
|
33 <when value="advanced">
|
|
|
34 <param name="column_start" type="data_column" data_ref="infile" label="Column start" help="Unique on specific column range"/>
|
|
|
35 <param name="column_end" type="data_column" data_ref="infile" label="Column end" help="Unique on specific column range"/>
|
|
|
36 </when>
|
|
|
37 </conditional>
|
|
|
38 </inputs>
|
|
|
39 <outputs>
|
|
|
40 <data name="outfile" format_source="infile" metadata_source="infile"/>
|
|
|
41 </outputs>
|
|
|
42 <tests>
|
|
|
43 <test>
|
|
|
44 <param name="infile" value="1.bed"/>
|
|
|
45 <param name="is_numeric" value="True"/>
|
|
|
46 <param name="ignore_case" value="True"/>
|
|
|
47 <param name="adv_opts_selector" value="advanced"/>
|
|
|
48 <param name="column_start" value="2"/>
|
|
|
49 <param name="column_end" value="3"/>
|
|
|
50 <output name="outfile" file="unique_results1.bed"/>
|
|
|
51 </test>
|
|
|
52 </tests>
|
|
|
53 <help>
|
|
|
54 <![CDATA[
|
|
|
55 .. class:: infomark
|
|
|
56
|
|
|
57 **Syntax**
|
|
|
58
|
|
|
59 This tool returns all unique lines using the 'sort -u' command. It can be used with unsorted files.
|
|
|
60 If you need additional options, like grouping or counting your unique results, please use the 'Unique lines from sorted file' tool.
|
|
|
61
|
|
|
62 -----
|
|
|
63
|
|
|
64 .. class:: infomark
|
|
|
65
|
|
|
66 The input file needs to be tab separated. Please convert your file if necessary.
|
|
|
67
|
|
|
68 -----
|
|
|
69
|
|
|
70 **Example**
|
|
|
71
|
|
|
72 - Input file::
|
|
|
73
|
|
|
74 chr1 10 100 gene1
|
|
|
75 chr1 105 200 gene2
|
|
|
76 chr1 10 100 gene1
|
|
|
77 chr2 10 100 gene4
|
|
|
78 chr2 1000 1900 gene5
|
|
|
79 chr3 15 1656 gene6
|
|
|
80 chr2 10 100 gene4
|
|
|
81
|
|
|
82 - Unique lines will result in::
|
|
|
83
|
|
|
84 chr1 10 100 gene1
|
|
|
85 chr1 105 200 gene2
|
|
|
86 chr2 10 100 gene4
|
|
|
87 chr2 1000 1900 gene5
|
|
|
88 chr3 15 1656 gene6
|
|
|
89
|
|
|
90 @REFERENCES@
|
|
|
91 ]]>
|
|
|
92 </help>
|
|
|
93 </tool>
|
