Mercurial > repos > bgruening > text_processing
diff easyjoin.xml @ 4:56e80527c482 draft
Uploaded
author | bgruening |
---|---|
date | Wed, 07 Jan 2015 11:10:52 -0500 |
parents | 7068d1548234 |
children | 8928e6d1e7ba |
line wrap: on
line diff
--- a/easyjoin.xml Sun Oct 06 08:22:36 2013 -0400 +++ b/easyjoin.xml Wed Jan 07 11:10:52 2015 -0500 @@ -1,41 +1,51 @@ -<tool id="tp_easyjoin_tool" name="Join" version="0.1.1"> - <requirements> - <requirement type="package" version="8.21">gnu_coreutils</requirement> - </requirements> +<tool id="tp_easyjoin_tool" name="Join" version="@BASE_VERSION@.0"> <description>two files</description> - <command interpreter="perl">easyjoin $jointype - -t ' ' - $header - -e '$empty_string_filler' - -o auto - $ignore_case - -1 '$column1' - -2 '$column2' - "$input1" "$input2" - > '$output' + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"> + <requirement type="set_environment">TP_SCRIPT_PATH</requirement> + </expand> + <version_command>join --version | head -n 1</version_command> + <command> +<![CDATA[ + cp \$TP_SCRIPT_PATH/sort-header ./ && + chmod +x sort-header && + perl \$TP_SCRIPT_PATH/easyjoin + $jointype + -t ' ' + $header + -e '$empty_string_filler' + -o auto + $ignore_case + -1 '$column1' + -2 '$column2' + "$infile1" + "$infile2" + > '$output' +]]> </command> + <inputs> + <param name="infile1" format="tabular" type="data" label="1st file" /> + <param name="column1" label="Column to use from 1st file" type="data_column" data_ref="infile1" accept_default="true" /> - <inputs> - <param format="txt" name="input1" type="data" label="1st file" /> - <param name="column1" label="Column to use from 1st file" type="data_column" data_ref="input1" accept_default="true" /> - - <param format="txt" name="input2" type="data" label="2nd File" /> - <param name="column2" label="Column to use from 2nd file" type="data_column" data_ref="input2" accept_default="true" /> + <param name="infile2" format="txt" type="data" label="2nd File" /> + <param name="column2" label="Column to use from 2nd file" type="data_column" data_ref="infile2" accept_default="true" /> <param name="jointype" type="select" label="Output lines appearing in"> - <option value=" ">BOTH 1st & 2nd file.</option> - <option value="-v 1">1st but not in 2nd file. [-v 1]</option> - <option value="-v 2">2nd but not in 1st file. [-v 2]</option> - <option value="-a 1">both 1st & 2nd file, plus unpairable lines from 1st file. [-a 1]</option> - <option value="-a 2">both 1st & 2nd file, plus unpairable lines from 2st file. [-a 2]</option> - <option value="-a 1 -a 2">All Lines [-a 1 -a 2]</option> + <option value=" " selected="True">Both 1st & 2nd file.</option> + <option value="-v 1">1st but not in 2nd file. (-v 1)</option> + <option value="-v 2">2nd but not in 1st file. (-v 2)</option> + <option value="-a 1">Both 1st & 2nd file, plus unpairable lines from 1st file. (-a 1)</option> + <option value="-a 2">Both 1st & 2nd file, plus unpairable lines from 2st file. (-a 2)</option> + <option value="-a 1 -a 2">All lines [-a 1 -a 2]</option> <option value="-v 1 -v 2">All unpairable lines [-v 1 -v 2]</option> </param> - <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." /> - - <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." /> - + <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." /> + <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." /> <param name="empty_string_filler" type="text" size="20" value="0" label="Value to put in unpaired (empty) fields"> <sanitizer> <valid initial="string.printable"> @@ -43,13 +53,23 @@ </valid> </sanitizer> </param> - - </inputs> - <outputs> - <data name="output" format="input" metadata_source="input1"/> - </outputs> - -<help> + </inputs> + <outputs> + <data name="output" format="input" metadata_source="infile1"/> + </outputs> + <tests> + <test> + <param name="infile1" value="easyjoin1.tabular" /> + <param name="column1" value="1" /> + <param name="infile2" value="easyjoin2.tabular" /> + <param name="column2" value="1" /> + <param name="header" value="True" /> + <param name="jointype" value="-a 1 -a 2" /> + <output name="output" file="easyjoin_result1.tabular" /> + </test> + </tests> + <help> +<![CDATA[ **What it does** This tool joins two tabular files based on a common key column. @@ -83,13 +103,13 @@ Melon green . Orange orange 7 -# Input files need not be sorted. -# The header line (**Fruit Color Price**) was joined and kept as first line. -# Missing values ( Avocado's color, missing from the first file ) are replaced with a period character. +.. class:: infomark ------ + * Input files need not be sorted. + * The header line (**Fruit Color Price**) was joined and kept as first line. + * Missing values ( Avocado's color, missing from the first file ) are replaced with a period character. -*easyjoin* was written by A. Gordon - -</help> +@REFERENCES@ +]]> + </help> </tool>