Mercurial > repos > bgruening > text_processing

comparison multijoin.xml @ 0:5314e5d6f040 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author bgruening
date Thu, 29 Jan 2015 07:53:17 -0500
parents
children 37e1eb05b1b4
comparison
equal deleted inserted replaced
-1:000000000000 0:5314e5d6f040
1 <tool id="tp_multijoin_tool" name="Multi-Join" version="@BASE_VERSION@.0">
2 <description>(combine multiple files)</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements">
7 <requirement type="package" version="5.18.1">perl</requirement>
8 <requirement type="package" version="1.0">text_processing_perl_packages</requirement>
9 </expand>
10 <command interpreter="perl">
11 <![CDATA[
12 multijoin
13 --key '$key_column'
14 --values '$value_columns'
15 --filler '$filler'
16 $ignore_dups
17 $output_header
18 $input_header
19 $first_file
20 #for $file in $files:
21 '$file'
22 #end for
23 > '$outfile'
24 ]]>
25 </command>
26 <inputs>
27 <param name="first_file" type="data" format="txt" label="File to join"/>
28 <param name="files" multiple="True" type="data" format="txt" label="add additional file" />
29
30 <param name="key_column" label="Common key column" type="integer"
31 value="1" help="Usually gene-ID or other common value" />
32
33 <param name="value_columns" label="Column with values to preserve"
34 type="data_column" data_ref="first_file" accept_default="true" multiple="True" display="checkboxes"/>
35
36 <param name="output_header" type="boolean" checked="false" truevalue="--out-header" falsevalue="" label="Add header line to the output file" help="" />
37 <param name="input_header" type="boolean" checked="false" truevalue="--in-header" falsevalue="" label="Input files contain a header line (as first line)" help="" />
38 <param name="ignore_dups" type="boolean" checked="false" truevalue="--ignore-dups" falsevalue="" label="Ignore duplicated keys" help="If not set, duplicated keys in the same file will cause an error." />
39 <param name="filler" type="text" size="20" value="0" label="Value to put in unpaired (empty) fields">
40 <sanitizer>
41 <valid initial="string.printable">
42 <remove value="&apos;"/>
43 </valid>
44 </sanitizer>
45 </param>
46 </inputs>
47 <outputs>
48 <data name="outfile" format_source="first_file" metadata_source="first_file" />
49 </outputs>
50 <tests>
51 <test>
52 <param name="first_file" value="multijoin1.txt" />
53 <param name="files" value="multijoin2.txt,multijoin3.txt" />
54 <param name="key_column" value="4" />
55 <param name="value_columns" value="c7,c8,c9" />
56 <param name="output_header" value="True" />
57 <output name="outfile" file="multijoin_result1.txt" />
58 </test>
59 </tests>
60 <help>
61 <![CDATA[
62 **What it does**
63
64 This tool joins multiple tabular files based on a common key column.
65
66 -----
67
68 **Example**
69
70 To join three files, based on the 4th column, and keeping the 7th,8th,9th columns:
71
72 **First file (AAA)**::
73
74 chr4 888449 890171 FBtr0308778 0 + 266 1527 1722
75 chr4 972167 979017 FBtr0310651 0 - 3944 6428 6850
76 chr4 972186 979017 FBtr0089229 0 - 3944 6428 6831
77 chr4 972186 979017 FBtr0089231 0 - 3944 6428 6831
78 chr4 972186 979017 FBtr0089233 0 - 3944 6428 6831
79 chr4 995793 996435 FBtr0111046 0 + 7 166 642
80 chr4 995793 997931 FBtr0111044 0 + 28 683 2138
81 chr4 995793 997931 FBtr0111045 0 + 28 683 2138
82 chr4 1034029 1047719 FBtr0089223 0 - 5293 13394 13690
83 ...
84
85
86 **Second File (BBB)**::
87
88 chr4 90286 134453 FBtr0309803 0 + 657 29084 44167
89 chr4 251355 266499 FBtr0089116 0 + 56 1296 15144
90 chr4 252050 266506 FBtr0308086 0 + 56 1296 14456
91 chr4 252050 266506 FBtr0308087 0 + 56 1296 14456
92 chr4 252053 266528 FBtr0300796 0 + 56 1296 14475
93 chr4 252053 266528 FBtr0300800 0 + 56 1296 14475
94 chr4 252055 266528 FBtr0300798 0 + 56 1296 14473
95 chr4 252055 266528 FBtr0300799 0 + 56 1296 14473
96 chr4 252541 266528 FBtr0300797 0 + 56 1296 13987
97 ...
98
99 **Third file (CCC)**::
100
101 chr4 972167 979017 FBtr0310651 0 - 9927 6738 6850
102 chr4 972186 979017 FBtr0089229 0 - 9927 6738 6831
103 chr4 972186 979017 FBtr0089231 0 - 9927 6738 6831
104 chr4 972186 979017 FBtr0089233 0 - 9927 6738 6831
105 chr4 995793 996435 FBtr0111046 0 + 5 304 642
106 chr4 995793 997931 FBtr0111044 0 + 17 714 2138
107 chr4 995793 997931 FBtr0111045 0 + 17 714 2138
108 chr4 1034029 1047719 FBtr0089223 0 - 17646 13536 13690
109 ...
110
111
112 **Joining** the files, using **key column 4**, **value columns 7,8,9** and a **header line**, will return::
113
114 key AAA__V7 AAA__V8 AAA__V9 BBB__V7 BBB__V8 BBB__V9 CCC__V7 CCC__V8 CCC__V9
115 FBtr0089116 0 0 0 56 1296 15144 0 0 0
116 FBtr0089223 5293 13394 13690 0 0 0 17646 13536 13690
117 FBtr0089229 3944 6428 6831 0 0 0 9927 6738 6831
118 FBtr0089231 3944 6428 6831 0 0 0 9927 6738 6831
119 FBtr0089233 3944 6428 6831 0 0 0 9927 6738 6831
120 FBtr0111044 28 683 2138 0 0 0 17 714 2138
121 FBtr0111045 28 683 2138 0 0 0 17 714 2138
122 FBtr0111046 7 166 642 0 0 0 5 304 642
123 FBtr0300796 0 0 0 56 1296 14475 0 0 0
124 ...
125
126 .. class:: infomark
127
128 Input files need not be sorted.
129
130 @REFERENCES@
131 ]]>
132 </help>
133 </tool>