Mercurial > repos > bgruening > text_processing

comparison easyjoin.xml @ 0:ec66f9d90ef0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
initial uploaded
author bgruening
date Thu, 05 Sep 2013 04:58:21 -0400
parents
children 7068d1548234
comparison
equal deleted inserted replaced
-1:000000000000 0:ec66f9d90ef0
1 <tool id="unixtools_easyjoin_tool" name="Join" version="0.1.1">
2 <requirements>
3 <requirement type="package" version="8.21">gnu_coreutils</requirement>
4 </requirements>
5 <description>two files</description>
6 <command interpreter="perl">easyjoin $jointype
7 -t ' '
8 $header
9 -e '$empty_string_filler'
10 -o auto
11 $ignore_case
12 -1 '$column1'
13 -2 '$column2'
14 "$input1" "$input2"
15 &gt; '$output'
16 </command>
17
18 <inputs>
19 <param format="txt" name="input1" type="data" label="1st file" />
20 <param name="column1" label="Column to use from 1st file" type="data_column" data_ref="input1" accept_default="true" />
21
22 <param format="txt" name="input2" type="data" label="2nd File" />
23 <param name="column2" label="Column to use from 2nd file" type="data_column" data_ref="input2" accept_default="true" />
24
25 <param name="jointype" type="select" label="Output lines appearing in">
26 <option value=" ">BOTH 1st &amp; 2nd file.</option>
27 <option value="-v 1">1st but not in 2nd file. [-v 1]</option>
28 <option value="-v 2">2nd but not in 1st file. [-v 2]</option>
29 <option value="-a 1">both 1st &amp; 2nd file, plus unpairable lines from 1st file. [-a 1]</option>
30 <option value="-a 2">both 1st &amp; 2nd file, plus unpairable lines from 2st file. [-a 2]</option>
31 <option value="-a 1 -a 2">All Lines [-a 1 -a 2]</option>
32 <option value="-v 1 -v 2">All unpairable lines [-v 1 -v 2]</option>
33 </param>
34
35 <param name="header" type="boolean" checked="false" truevalue="--header" falsevalue="" label="First line is a header line" help="Use if first line contains column headers. It will not be sorted." />
36
37 <param name="ignore_case" type="boolean" checked="false" truevalue="-i" falsevalue="" label="Ignore case" help="Sort and Join key column values regardless of upper/lower case letters." />
38
39 <param name="empty_string_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
47 </inputs>
48 <outputs>
49 <data name="output" format="input" metadata_source="input1"/>
50 </outputs>
51
52 <help>
53 **What it does**
54
55 This tool joins two tabular files based on a common key column.
56
57 -----
58
59 **Example**
60
61 **First file**::
62
63 Fruit Color
64 Apple red
65 Banana yellow
66 Orange orange
67 Melon green
68
69 **Second File**::
70
71 Fruit Price
72 Orange 7
73 Avocado 8
74 Apple 4
75 Banana 3
76
77 **Joining** both files, using **key column 1** and a **header line**, will return::
78
79 Fruit Color Price
80 Apple red 4
81 Avocado . 8
82 Banana yellow 3
83 Melon green .
84 Orange orange 7
85
86 # Input files need not be sorted.
87 # The header line (**Fruit Color Price**) was joined and kept as first line.
88 # Missing values ( Avocado's color, missing from the first file ) are replaced with a period character.
89
90 -----
91
92 *easyjoin* was written by A. Gordon
93
94 </help>
95 </tool>