Source code

Download source archive ↓

upstream-extended/community/tools/text_processing/text_processing/sorted_uniq.xml

1<tool id="tp_uniq_tool" name="Unique lines" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2    <description>assuming sorted input file</description>
3    <macros>
4        <import>macros.xml</import>
5    </macros>
6    <expand macro="creator"/>
7    <expand macro="requirements">
8        <requirement type="package" version="4.9">sed</requirement>
9    </expand>
10    <version_command>uniq --version | head -n 1</version_command>
11    <command>
12<![CDATA[
13        uniq
14            #if $skipfields:
15                -f $skipfields
16            #end if
17            $ignorecase
18
19            #if $grouping.grouping_select == 'yes':
20                --group=$grouping.group
21            #else:
22                $grouping.count
23                $grouping.repeated
24                $grouping.uniqueonly
25            #end if
26
27            '$infile'
28
29            #if $grouping.grouping_select == 'no' and $grouping.count:
30                ## count will print the count with spaces in front of the line and
31                ## with a space (not a tab) after the number, we need to cahnge that
32                | sed -e 's/ *//' -e 's/ /\t/'
33            #end if
34            > '$outfile'
35]]>
36    </command>
37    <inputs>
38        <param name="infile" format="tabular" type="data"
39            label="File to scan for unique values" help="Make sure you have sorted this file" />
40
41        <conditional name="grouping">
42            <param name="grouping_select" type="select" label="Do you want to group each unique group?">
43                <option value="no">No</option>
44                <option value="yes">Yes</option>
45            </param>
46            <when value="no">
47                <param name="count" type="boolean" truevalue="-c" falsevalue=""
48                    label="Counting number of occurrences" help="Prefix lines by the number of occurrences. (-c)" />
49                <param name="repeated" type="boolean" truevalue="-d" falsevalue=""
50                    label="Only print duplicate lines" help="(-d)"/>
51                <param name="uniqueonly" type="boolean" checked="True" truevalue="-u" falsevalue=""
52                    label="Only print unique lines" help="(-u)" />
53            </when>
54            <when value="yes">
55                <param name="group" type="select"
56                    label="Output all lines, and delimit each unique group" help="(--group)">
57                    <option value="">No grouping at all</option>
58                    <option value="separate">Separate unique groups with a single delimiter</option>
59                    <option value="prepend">Output a delimiter before each group of unique items</option>
60                    <option value="append">Output a delimiter after each group of unique items</option>
61                    <option value="both">Output a delimiter around each group of unique items</option>
62                </param>
63            </when>
64        </conditional>
65
66        <param name="ignorecase" type="boolean" truevalue="-i" falsevalue=""
67            label="Ignore differences in case when comparing" help="(-i)"/>
68        <param name="skipfields" type="integer" value="0"
69            label="Avoid comparing the first N fields" help="Use zero to start from the first field. (-f)" />
70    </inputs>
71    <outputs>
72        <data name="outfile" format_source="infile" metadata_source="infile"/>
73    </outputs>
74    <tests>
75        <test>
76            <param name="infile" value="sorted_uniq1.tabular" />
77            <conditional name="grouping">
78                <param name="grouping_select" value="no"/>
79                <param name="count" value="True"/>
80                <param name="uniqueonly" value="True"/>
81            </conditional>
82            <param name="ignorecase" value="True"/>
83            <output name="outfile" file="sorted_uniq_results1.tabular" />
84        </test>
85        <test>
86            <param name="infile" value="sorted_uniq1.tabular" />
87            <param name="ignorecase" value="True"/>
88            <conditional name="grouping">
89                <param name="grouping_select" value="yes"/>
90                <param name="group" value="separate"/>
91            </conditional>
92            <output name="outfile" file="sorted_uniq_results2.tabular" />
93        </test>
94    </tests>
95    <help>
96<![CDATA[
97This tool takes a sorted file and look for lines that are unique.
98
99.. class:: warningmark
100
101Please make sure your file is sorted, or else this tool will give you an erroneous output.
102
103.. class:: infomark
104
105You can sort your file using either the "Sort" tool in "Filter and Sort", or the "Sort" tool in "Unix Tools".
106
107]]>
108    </help>
109    <expand macro="citations" />
110</tool>