Mercurial > repos > mvdbeek > collection_column_join

comparison collection_column_join.xml @ 0:944ffc0fd3b5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/collection_column_join commit ac5a5dcefafe63a842e0b04b733cc5ee1177acba-dirty"
author mvdbeek
date Mon, 07 Sep 2020 12:42:31 +0000
parents
children 179d302a60c9
comparison
equal deleted inserted replaced
-1:000000000000 0:944ffc0fd3b5
1 <tool id="collection_column_join" name="Column Join" version="0.0.3">
2 <description>on Collections</description>
3 <requirements>
4 <requirement type="package" version="8.25">coreutils</requirement>
5 </requirements>
6 <command detect_errors="exit_code"><![CDATA[
7 #if 'output_shell_script' in str( $include_outputs ).split( "," ):
8 cp '${collection_column_join_script}' '${script_output}' &&
9 #end if
10 sh '${collection_column_join_script}'
11 ]]>
12 </command>
13 <configfiles>
14 <configfile name="collection_column_join_script"><![CDATA[
15 #!/bin/sh
16 touch header0.tmp &&
17 touch output0.tmp &&
18 #set $delimiter = '\t'
19 #set $left_identifier_column = $identifier_column
20 #set $tail_offset = int( str( $has_header ) ) + 1
21 #for $i, $tabular_item in enumerate( $input_tabular ):
22 #if $old_col_in_header:
23 #if $has_header:
24 head -n ${has_header} "${tabular_item}" | awk '{ n = split(\$0,arr,"${delimiter}"); ctr=1; for(i=1;i<=n;i++){ if( i != $identifier_column ){ if( ctr > 1) {printf("${delimiter}")}; printf( "${tabular_item.element_identifier}_%s", arr[i] ); ctr++ } }; printf( "\n" ); }' > input_header.tmp &&
25 tail -n +${tail_offset} "${tabular_item}" | LC_ALL=C sort -t "${delimiter}" -k $identifier_column > input_file.tmp &&
26 #else:
27 awk '{ n = split(\$0,arr,"${delimiter}"); ctr=1; for(i=1;i<=n;i++){ if( i != $identifier_column ){ if( ctr > 1) {printf("${delimiter}")}; printf( "${tabular_item.element_identifier}_%s", i ); ctr++ } }; exit }' "${tabular_item}" > input_header.tmp &&
28 LC_ALL=C sort -t "${delimiter}" -k $identifier_column "${tabular_item}" > input_file.tmp &&
29 #end if
30 #else:
31 #if $has_header:
32 head -n ${has_header} "${tabular_item}" | awk '{ n = split(\$0,arr,"${delimiter}"); ctr=1; for(i=1;i<=n;i++){ if( i != $identifier_column ){ if( ctr > 1) {printf("${delimiter}")}; printf( "${tabular_item.element_identifier}" ); ctr++ } }; printf( "\n" ); }' > input_header.tmp &&
33 tail -n +${tail_offset} "${tabular_item}" | LC_ALL=C sort -t "${delimiter}" -k $identifier_column > input_file.tmp &&
34 #else:
35 awk '{ n = split(\$0,arr,"${delimiter}"); ctr=1; for(i=1;i<=n;i++){ if( i != $identifier_column ){ if( ctr > 1) {printf("${delimiter}")}; printf( "${tabular_item.element_identifier}"); ctr++ } }; exit }' "${tabular_item}" > input_header.tmp &&
36 LC_ALL=C sort -t "${delimiter}" -k $identifier_column "${tabular_item}" > input_file.tmp &&
37 #end if
38 #end if
39 #if $i == 0:
40 mv input_file.tmp output${ ( $i + 1 ) % 2 }.tmp &&
41 #if $has_header:
42 awk '{ printf \$${identifier_column}; exit }' "${tabular_item}" > header${ $i % 2 }.tmp &&
43 #else:
44 echo "#KEY" > header${ $i % 2 }.tmp &&
45 #end if
46 #else:
47 LC_ALL=C join -o auto -a 1 -a 2 -1 ${left_identifier_column} -2 ${identifier_column} -t "${delimiter}" -e "${fill_char}" output${ $i % 2 }.tmp input_file.tmp > output${ ( $i + 1 ) % 2 }.tmp &&
48 #set $left_identifier_column = 1
49 #end if
50 paste -d "${delimiter}" header${ $i % 2 }.tmp input_header.tmp > header${ ( $i + 1 ) % 2 }.tmp &&
51 #end for
52 cat header${ ( $i + 1 ) % 2 }.tmp output${ ( $i + 1 ) % 2 }.tmp > "${tabular_output}"
53 ]]>
54 </configfile>
55 </configfiles>
56 <inputs>
57 <param name="input_tabular" type="data" format="tabular" multiple="True" optional="False" label="Tabular files"/>
58 <!-- <param name="identifier_column" type="data_column" data_ref="input_tabular" value="0" min="0" optional="False" label="Identifier column"/> -->
59 <param name="identifier_column" type="integer" value="1" min="0" optional="False" label="Identifier column" help="The column that will be used to join the input datasets"/>
60 <param name="has_header" type="integer" value="0" min="0" optional="False" label="Number of header lines in each input file" help="If this is set to 0, a header line will be added containing column names as follows: the identifier column will be named #KEY and the other columns are named by the input dataset names/columns. If you have one or more header lines in your input, set this to the number of header lines."/>
61 <param name="old_col_in_header" type="boolean" checked="true" label="Add column name to header" help="Disable if you want column headers to only be composed of the input file names, for example, if you want headers like file1 and not file1_column1, see Help section below. Default: Yes"/>
62 <param name="fill_char" type="text" value="." optional="False" label="Fill character"/>
63 <param name="include_outputs" type="select" multiple="True" label="Additional datasets to create">
64 <option value="output_shell_script" selected="false">Shell script</option>
65 </param>
66 </inputs>
67 <outputs>
68 <data format="tabular" name="tabular_output"/>
69 <data format="txt" name="script_output">
70 <filter>include_outputs and "output_shell_script" in include_outputs</filter>
71 </data>
72 </outputs>
73 <tests>
74 <test>
75 <param name="input_tabular" value="in_1.tabular,in_2.tabular,in_3.tabular" ftype="tabular"/>
76 <param name="identifier_column" value="1"/>
77 <param name="has_header" value="1"/>
78 <param name="old_col_in_header" value="true"/>
79 <param name="fill_char" value="."/>
80 <param name="include_outputs" />
81 <output name="tabular_output" file="out_1.tabular" ftype="tabular"/>
82 </test>
83 <test>
84 <param name="input_tabular" value="in_1_headerless.tabular,in_2_headerless.tabular,in_3_headerless.tabular" ftype="tabular"/>
85 <param name="identifier_column" value="1"/>
86 <param name="has_header" value="0"/>
87 <param name="old_col_in_header" value="true"/>
88 <param name="fill_char" value="."/>
89 <param name="include_outputs" />
90 <output name="tabular_output" file="out_2.tabular" ftype="tabular"/>
91 </test>
92 <test>
93 <param name="input_tabular" value="in_1.tabular,in_2.tabular,in_3.tabular" ftype="tabular"/>
94 <param name="identifier_column" value="1"/>
95 <param name="has_header" value="1"/>
96 <param name="old_col_in_header" value="false"/>
97 <param name="fill_char" value="."/>
98 <param name="include_outputs" />
99 <output name="tabular_output" file="out_3.tabular" ftype="tabular"/>
100 </test>
101 <test>
102 <param name="input_tabular" value="in_1_headerless.tabular,in_2_headerless.tabular,in_3_headerless.tabular" ftype="tabular"/>
103 <param name="identifier_column" value="1"/>
104 <param name="has_header" value="0"/>
105 <param name="old_col_in_header" value="false"/>
106 <param name="fill_char" value="."/>
107 <param name="include_outputs" />
108 <output name="tabular_output" file="out_4.tabular" ftype="tabular"/>
109 </test>
110 </tests>
111 <help>
112 <![CDATA[
113 Joins lists of tabular datasets together on a field.
114
115 -----
116
117 **Example**
118
119 To join three files, with headers, based on the first column:
120
121 **First file (in_1)**::
122
123 #KEY c2 c3 c4
124 one 1-1 1-2 1-3
125 two 1-4 1-5 1-6
126 three 1-7 1-8 1-9
127
128
129 **Second File (in_2)**::
130
131 #KEY c2 c3 c4
132 one 2-1 2-2 2-3
133 two 2-4 2-5 2-6
134 three 2-7 2-8 2-9
135
136 **Third file (in_3)**::
137
138 #KEY c2 c3 c4
139 one 3-3 3-2 3-3
140 two 3-4 3-5 3-6
141 three 3-7 3-8 3-9
142
143
144 **Joining** the files, using **identifier column of 1** and a **header lines of 1**, will return::
145
146 #KEY in_1_c2 in_1_c3 in_1_c4 in_2_c2 in_2_c3 in_2_c4 in_3_c2 in_3_c3 in_3_c4
147 one 1-1 1-2 1-3 2-1 2-2 2-3 3-3 3-2 3-3
148 three 1-7 1-8 1-9 2-7 2-8 2-9 3-7 3-8 3-9
149 two 1-4 1-5 1-6 2-4 2-5 2-6 3-4 3-5 3-6
150
151
152 **Joining** the files, using **identifier column of 1** and a **header lines of 1**, but disabling **Add column name to header**, will return::
153
154 #KEY in_1 in_1 in_1 in_2 in_2 in_2 in_3 in_3 in_3
155 one 1-1 1-2 1-3 2-1 2-2 2-3 3-3 3-2 3-3
156 three 1-7 1-8 1-9 2-7 2-8 2-9 3-7 3-8 3-9
157 two 1-4 1-5 1-6 2-4 2-5 2-6 3-4 3-5 3-6
158
159 ]]>
160 </help>
161 <citations>
162 </citations>
163 </tool>