Mercurial > repos > bgruening > text_processing
annotate multijoin.xml @ 13:3c685c4106b3 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
| author | bgruening |
|---|---|
| date | Wed, 23 Nov 2016 15:59:02 -0500 |
| parents | 062ed2bb4f2e |
| children | 7725ab6dab67 |
| rev | line source |
|---|---|
| 6 | 1 <tool id="tp_multijoin_tool" name="Multi-Join" version="@BASE_VERSION@.0"> |
| 4 | 2 <description>(combine multiple files)</description> |
| 3 <macros> | |
| 4 <import>macros.xml</import> | |
| 5 </macros> | |
|
13
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
6 <requirements> |
| 5 | 7 <requirement type="package" version="5.18.1">perl</requirement> |
|
13
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
8 </requirements> |
|
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
9 <command> |
| 4 | 10 <![CDATA[ |
|
13
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
11 perl '$__tool_directory__/multijoin' |
| 0 | 12 --key '$key_column' |
| 13 --values '$value_columns' | |
| 14 --filler '$filler' | |
| 15 $ignore_dups | |
| 16 $output_header | |
| 17 $input_header | |
| 4 | 18 $first_file |
| 19 #for $file in $files: | |
| 20 '$file' | |
| 0 | 21 #end for |
| 4 | 22 > '$outfile' |
| 23 ]]> | |
| 24 </command> | |
| 25 <inputs> | |
| 26 <param name="first_file" type="data" format="txt" label="File to join"/> | |
| 27 <param name="files" multiple="True" type="data" format="txt" label="add additional file" /> | |
| 0 | 28 |
| 4 | 29 <param name="key_column" label="Common key column" type="integer" |
| 30 value="1" help="Usually gene-ID or other common value" /> | |
| 2 | 31 |
| 7 | 32 <param name="value_columns" label="Column with values to preserve" |
| 4 | 33 type="data_column" data_ref="first_file" accept_default="true" multiple="True" display="checkboxes"/> |
| 0 | 34 |
| 4 | 35 <param name="output_header" type="boolean" checked="false" truevalue="--out-header" falsevalue="" label="Add header line to the output file" help="" /> |
| 36 <param name="input_header" type="boolean" checked="false" truevalue="--in-header" falsevalue="" label="Input files contain a header line (as first line)" help="" /> | |
| 37 <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." /> | |
|
10
c78b1767db2b
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 10052765d6b712cf7d38356af4251fcc38a339b6-dirty
bgruening
parents:
7
diff
changeset
|
38 <param name="filler" type="text" value="0" label="Value to put in unpaired (empty) fields"> |
| 4 | 39 <sanitizer> |
| 40 <valid initial="string.printable"> | |
| 41 <remove value="'"/> | |
| 42 </valid> | |
| 43 </sanitizer> | |
| 44 </param> | |
| 45 </inputs> | |
| 46 <outputs> | |
| 6 | 47 <data name="outfile" format_source="first_file" metadata_source="first_file" /> |
| 4 | 48 </outputs> |
| 49 <tests> | |
| 6 | 50 <test> |
| 51 <param name="first_file" value="multijoin1.txt" /> | |
| 52 <param name="files" value="multijoin2.txt,multijoin3.txt" /> | |
| 53 <param name="key_column" value="4" /> | |
| 54 <param name="value_columns" value="c7,c8,c9" /> | |
| 55 <param name="output_header" value="True" /> | |
|
12
062ed2bb4f2e
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit f8896018f5b980a456c4ceaffe0ed457dc80b5a8
bgruening
parents:
10
diff
changeset
|
56 <output name="outfile" file="multijoin_result1.txt" lines_diff="2" /> |
| 4 | 57 </test> |
| 58 </tests> | |
| 59 <help> | |
| 60 <![CDATA[ | |
| 0 | 61 **What it does** |
| 62 | |
| 63 This tool joins multiple tabular files based on a common key column. | |
| 64 | |
| 65 ----- | |
| 66 | |
| 67 **Example** | |
| 68 | |
| 69 To join three files, based on the 4th column, and keeping the 7th,8th,9th columns: | |
| 70 | |
| 71 **First file (AAA)**:: | |
| 72 | |
| 73 chr4 888449 890171 FBtr0308778 0 + 266 1527 1722 | |
| 74 chr4 972167 979017 FBtr0310651 0 - 3944 6428 6850 | |
| 75 chr4 972186 979017 FBtr0089229 0 - 3944 6428 6831 | |
| 76 chr4 972186 979017 FBtr0089231 0 - 3944 6428 6831 | |
| 77 chr4 972186 979017 FBtr0089233 0 - 3944 6428 6831 | |
| 78 chr4 995793 996435 FBtr0111046 0 + 7 166 642 | |
| 79 chr4 995793 997931 FBtr0111044 0 + 28 683 2138 | |
| 80 chr4 995793 997931 FBtr0111045 0 + 28 683 2138 | |
| 81 chr4 1034029 1047719 FBtr0089223 0 - 5293 13394 13690 | |
| 82 ... | |
| 83 | |
| 84 | |
| 85 **Second File (BBB)**:: | |
| 86 | |
| 87 chr4 90286 134453 FBtr0309803 0 + 657 29084 44167 | |
| 88 chr4 251355 266499 FBtr0089116 0 + 56 1296 15144 | |
| 89 chr4 252050 266506 FBtr0308086 0 + 56 1296 14456 | |
| 90 chr4 252050 266506 FBtr0308087 0 + 56 1296 14456 | |
| 91 chr4 252053 266528 FBtr0300796 0 + 56 1296 14475 | |
| 92 chr4 252053 266528 FBtr0300800 0 + 56 1296 14475 | |
| 93 chr4 252055 266528 FBtr0300798 0 + 56 1296 14473 | |
| 94 chr4 252055 266528 FBtr0300799 0 + 56 1296 14473 | |
| 95 chr4 252541 266528 FBtr0300797 0 + 56 1296 13987 | |
| 96 ... | |
| 97 | |
| 98 **Third file (CCC)**:: | |
| 99 | |
| 100 chr4 972167 979017 FBtr0310651 0 - 9927 6738 6850 | |
| 101 chr4 972186 979017 FBtr0089229 0 - 9927 6738 6831 | |
| 102 chr4 972186 979017 FBtr0089231 0 - 9927 6738 6831 | |
| 103 chr4 972186 979017 FBtr0089233 0 - 9927 6738 6831 | |
| 104 chr4 995793 996435 FBtr0111046 0 + 5 304 642 | |
| 105 chr4 995793 997931 FBtr0111044 0 + 17 714 2138 | |
| 106 chr4 995793 997931 FBtr0111045 0 + 17 714 2138 | |
| 107 chr4 1034029 1047719 FBtr0089223 0 - 17646 13536 13690 | |
| 108 ... | |
| 109 | |
| 110 | |
| 111 **Joining** the files, using **key column 4**, **value columns 7,8,9** and a **header line**, will return:: | |
| 112 | |
| 113 key AAA__V7 AAA__V8 AAA__V9 BBB__V7 BBB__V8 BBB__V9 CCC__V7 CCC__V8 CCC__V9 | |
| 114 FBtr0089116 0 0 0 56 1296 15144 0 0 0 | |
| 115 FBtr0089223 5293 13394 13690 0 0 0 17646 13536 13690 | |
| 116 FBtr0089229 3944 6428 6831 0 0 0 9927 6738 6831 | |
| 117 FBtr0089231 3944 6428 6831 0 0 0 9927 6738 6831 | |
| 118 FBtr0089233 3944 6428 6831 0 0 0 9927 6738 6831 | |
| 119 FBtr0111044 28 683 2138 0 0 0 17 714 2138 | |
| 120 FBtr0111045 28 683 2138 0 0 0 17 714 2138 | |
| 121 FBtr0111046 7 166 642 0 0 0 5 304 642 | |
| 122 FBtr0300796 0 0 0 56 1296 14475 0 0 0 | |
| 123 ... | |
| 124 | |
| 4 | 125 .. class:: infomark |
| 0 | 126 |
| 4 | 127 Input files need not be sorted. |
| 0 | 128 |
| 4 | 129 @REFERENCES@ |
| 130 ]]> | |
| 131 </help> | |
| 0 | 132 </tool> |