Mercurial > repos > artbio > concatenate_multiple_datasets

comparison catWrapper.xml @ 0:122dbfdf0826 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/concat_multi_datasets commit 75811bd85c9d175d9bc7b2c4fd723adc3a361f0f
author artbio
date Tue, 09 Jul 2019 09:51:52 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:122dbfdf0826
1 <tool id="cat_multi_datasets" name="Concatenate multiple datasets" version="1.4.1">
2 <description>tail-to-head by specifying how</description>
3 <command><![CDATA[
4 #if $headers == 0:
5 #set $concat_command = "cat"
6 #else:
7 #set $concat_command = 'tail -q -n +'+ str(int($headers)+1)
8 #end if
9 printf "Concatenating files:\n" &&
10 #if $global_condition.input_type == "singles":
11 #if $dataset_names == "No":
12 #for $file in $global_condition.inputs
13 printf "${file.element_identifier}..." &&
14 #if $file.ext:
15 #if $file.ext[-2:] == "gz" and $headers != 0:
16 gzip -dc '$file' | $concat_command | gzip -c >> '$out_file1' &&
17 #else:
18 $concat_command '$file' >> '$out_file1' &&
19 #end if
20 #else:
21 $concat_command '$file' >> '$out_file1' &&
22 #end if
23 printf "Done\n" &&
24 #end for
25 sleep 1
26 #else:
27 #for $file in $global_condition.inputs
28 printf "${file.element_identifier}..." &&
29 #if $file.ext[-2:] == "gz" and $headers != 0:
30 printf "# ${file.element_identifier}\n" | gzip -c >> '$out_file1' &&
31 gzip -dc "$file" | $concat_command |gzip -c >> '$out_file1' &&
32 #else:
33 printf "# ${file.element_identifier}\n" >> '$out_file1' &&
34 $concat_command "$file" >> '$out_file1' &&
35 #end if
36 printf "Done\n" &&
37 #end for
38 sleep 1
39 #end if
40 #else if $global_condition.input_type == "simple_collections":
41 mkdir concatenated &&
42 #if $dataset_names == "No":
43 #for $x, $y in zip($global_condition.input_1, $global_condition.input_2):
44 printf "${x.element_identifier} and ${y.element_identifier}..." &&
45 #if $x.ext[-2:] == "gz" and $headers != 0:
46 gzip -dc '$x' | $concat_command | gzip -c > concatenated/'${x.element_identifier}.listed.${x.ext}.listed' &&
47 gzip -dc '$y' | $concat_command | gzip -c >> concatenated/'${x.element_identifier}.listed.${x.ext}.listed' &&
48 #else:
49 $concat_command '$x' '$y' > concatenated/'${x.element_identifier}.listed.${x.ext}.listed' &&
50 #end if
51 printf "Done\n" &&
52 #end for
53 sleep 1
54 #else:
55 #for $x, $y in zip($global_condition.input_1, $global_condition.input_2)
56 printf "${x.element_identifier} and ${y.element_identifier}..." &&
57 #if $x.ext[-2:] == "gz" and $headers != 0:
58 printf "# ${x.element_identifier}\n" | gzip -c > concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
59 gzip -dc '$x' | $concat_command | gzip -c >> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
60 printf "# ${y.element_identifier}\n" | gzip -c >> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
61 gzip -dc '$y' | $concat_command | gzip -c >> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
62 #else:
63 printf "# ${x.element_identifier}\n" > concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
64 $concat_command '$x'>> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
65 printf "# ${y.element_identifier}\n" >> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
66 $concat_command '$y' >> concatenated/'${x.element_identifier}_${y.element_identifier}.listed.${x.ext}.listed' &&
67 #end if
68 printf "Done\n" &&
69 #end for
70 sleep 1
71 #end if
72 #else if $global_condition.input_type == "paired_collection":
73 #if $global_condition.paired_cat_type == "by_strand":
74 mkdir concatenated &&
75 #if $dataset_names == "No":
76 #for $file in $global_condition.inputs
77 printf "${file.element_identifier}- forward and reverse..." &&
78 #if $file['forward'].ext[-2:] == "gz" and $headers != 0:
79 gzip -dc $file['forward'] | $concat_command | gzip -c >> concatenated/forward.listed.${file['forward'].ext}.listed &&
80 gzip -dc $file['reverse'] | $concat_command | gzip -c >> concatenated/reverse.listed.${file['reverse'].ext}.listed &&
81 #else:
82 $concat_command $file['forward'] >> concatenated/forward.listed.${file['forward'].ext}.listed &&
83 $concat_command $file['reverse'] >> concatenated/reverse.listed.${file['reverse'].ext}.listed &&
84 #end if
85 printf "Done\n" &&
86 #end for
87 sleep 1
88 #else:
89 #for $file in $global_condition.inputs.keys():
90 printf "$file - forward and reverse..." &&
91 #if $global_condition.inputs[$file]['forward'].ext[-2:] == "gz" and $headers != 0:
92 printf "# ${file}_forward\n" | gzip -c >> concatenated/forward.listed.${global_condition.inputs[$file]['forward'].ext}.listed &&
93 gzip -dc $global_condition.inputs[$file]['forward'] | $concat_command | gzip -c >> concatenated/forward.listed.${global_condition.inputs[$file]['forward'].ext}.listed &&
94 printf "# ${file}_reverse\n" | gzip -c >> concatenated/reverse.listed.${global_condition.inputs[$file]['reverse'].ext}.listed &&
95 gzip -dc $global_condition.inputs[$file]['reverse'] | $concat_command | gzip -c >> concatenated/reverse.listed.${global_condition.inputs[$file]['reverse'].ext}.listed &&
96 #else:
97 printf "# ${file}_forward\n" >> concatenated/forward.listed.${global_condition.inputs[$file]['forward'].ext}.listed &&
98 $concat_command $global_condition.inputs[$file]['forward'] >> concatenated/forward.listed.${global_condition.inputs[$file]['forward'].ext}.listed &&
99 printf "# ${file}_reverse\n" >> concatenated/reverse.listed.${global_condition.inputs[$file]['reverse'].ext}.listed &&
100 $concat_command $global_condition.inputs[$file]['reverse'] >> concatenated/reverse.listed.${global_condition.inputs[$file]['reverse'].ext}.listed &&
101 #end if
102 printf "Done\n" &&
103 #end for
104 sleep 1
105 #end if
106 #else if $global_condition.paired_cat_type == "by_pair":
107 mkdir concatenated &&
108 #if $dataset_names == "No":
109 #for $file in $global_condition.inputs.keys():
110 printf "$file - forward and reverse..." &&
111 #if $global_condition.inputs[$file]['forward'].ext[-2:] == "gz" and $headers != 0:
112 gzip -dc $global_condition.inputs[$file]['forward'] | $concat_command | gzip -c
113 > concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
114 gzip -dc $global_condition.inputs[$file]['reverse'] | $concat_command | gzip -c
115 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
116 #else:
117 $concat_command $global_condition.inputs[$file]['forward']
118 > concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
119 $concat_command $global_condition.inputs[$file]['reverse']
120 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
121 #end if
122 printf "Done\n" &&
123 #end for
124 sleep 1
125 #else:
126 #for $file in $global_condition.inputs.keys():
127 printf "$file - forward and reverse..." &&
128 #if $global_condition.inputs[$file]['reverse'].ext[-2:] == "gz" and $headers != 0:
129 printf "# ${file}_forward\n" | gzip -c > concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
130 gzip -dc $global_condition.inputs[$file]['forward'] | $concat_command | gzip -c
131 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
132 printf "# ${file}_reverse\n" | gzip -c >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
133 gzip -dc $global_condition.inputs[$file]['reverse'] | $concat_command | gzip -c
134 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
135 #else:
136 printf "# ${file}_forward\n" > concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
137 $concat_command $global_condition.inputs[$file]['forward']
138 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
139 printf "# ${file}_reverse\n" >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
140 $concat_command $global_condition.inputs[$file]['reverse']
141 >> concatenated/'${file}.listed.${global_condition.inputs[$file]['reverse'].ext}.listed' &&
142 #end if
143 printf "Done\n" &&
144 #end for
145 sleep 1
146 #end if
147 #else if $global_condition.paired_cat_type == "all":
148 mkdir concatenated &&
149 #set $base_name=$global_condition.inputs.element_identifier
150 #set $extention=$global_condition.inputs[$global_condition.inputs.keys()[0]]['forward'].ext
151 #if $dataset_names == "No":
152 #for $file in $global_condition.inputs.keys():
153 printf "$file - forward and reverse..." &&
154 #if $global_condition.inputs[$file]['forward'].ext[-2:] == "gz" and $headers != 0:
155 gzip -dc $global_condition.inputs[$file]['forward'] | $concat_command | gzip -c >> c'$paired_out_file' &&
156 gzip -dc $global_condition.inputs[$file]['reverse'] | $concat_command | gzip -c >> '$paired_out_file' &&
157 #else:
158 $concat_command
159 $global_condition.inputs[$file]['forward']
160 >> '$paired_out_file' &&
161 $concat_command
162 $global_condition.inputs[$file]['reverse']
163 >> '$paired_out_file' &&
164 #end if
165 printf "Done\n" &&
166 #end for
167 sleep 1
168 #else:
169 #for $file in $global_condition.inputs.keys():
170 printf "$file - forward and reverse..." &&
171 #if $global_condition.inputs[$file]['forward'].ext[-2:] == "gz" and $headers != 0:
172 printf "# ${file}_forward\n" | gzip -c > '$paired_out_file' &&
173 gzip -dc $global_condition.inputs[$file]['forward'] | $concat_command | gzip -c >> '$paired_out_file' &&
174 printf "# ${file}_reverse\n" | gzip -c >> '$paired_out_file' &&
175 gzip -dc $global_condition.inputs[$file]['reverse'] | $concat_command | gzip -c >> '$paired_out_file' &&
176 #else:
177 printf "# ${file}_forward\n" > '$paired_out_file' &&
178 $concat_command
179 $global_condition.inputs[$file]['forward']
180 >> '$paired_out_file' &&
181 printf "# ${file}_reverse\n" >> '$paired_out_file' &&
182 $concat_command
183 $global_condition.inputs[$file]['reverse']
184 >> '$paired_out_file' &&
185 #end if
186 printf "Done\n" &&
187 #end for
188 sleep 1
189 #end if
190 #end if
191 #else if $global_condition.input_type == "nested_collection":
192 mkdir concatenated &&
193 #if $dataset_names == "No":
194 #for $sub_list in $global_condition.inputs:
195 #set $file_base_name=$sub_list.element_identifier
196 #for $sub_list_element in $sub_list:
197 printf "${file_base_name} - ${sub_list_element.element_identifier}..." &&
198 #if $sub_list_element.ext[-2:] == "gz" and $headers != 0:
199 gzip -dc ${sub_list_element} | $concat_command | gzip -c >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
200 #else:
201 $concat_command ${sub_list_element} >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
202 #end if
203 printf "Done\n" &&
204 #end for
205 #end for
206 sleep 1
207 #else:
208 #for $sub_list in $global_condition.inputs:
209 #set $file_base_name=$sub_list.element_identifier
210 #for $sub_list_element in $sub_list:
211 printf "${file_base_name} - ${sub_list_element.element_identifier}..." &&
212 #if $sub_list_element.ext[-2:] == "gz" and $headers != 0:
213 printf "# ${sub_list_element.element_identifier}\n" | gzip -c >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
214 gzip -dc ${sub_list_element} | $concat_command | gzip -c >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
215 #else:
216 printf "# ${sub_list_element.element_identifier}\n" >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
217 $concat_command ${sub_list_element} >> concatenated/'${file_base_name}.listed.${sub_list_element.ext}.listed' &&
218 #end if
219 printf "Done\n" &&
220 #end for
221 #end for
222 sleep 1
223 #end if
224 #end if
225 ]]>
226 </command>
227 <inputs>
228 <conditional name="global_condition">
229 <param name="input_type" type="select" label="What type of data do you wish to concatenate?" help="Depending on the type of input selected the concatenation options will differ">
230 <option value="singles">Single datasets</option>
231 <option value="simple_collections">2 Collections</option>
232 <option value="paired_collection">Paired collection</option>
233 <option value="nested_collection">Nested collection</option>
234 </param>
235 <when value="singles">
236 <param name="inputs" type="data" label="Concatenate Datasets" multiple="True" help="All inputed datasets will be concatenated tail-to-head."/>
237 </when>
238 <when value="paired_collection">
239 <param name="inputs" type="data_collection" collection_type="list:paired" label="Input paired collection to concatenate"/>
240 <param name="paired_cat_type" type="select" label="What type of concatenation do you wish to perform?">
241 <option value="by_strand">Concatenate all datsets of same strand (outputs a single pair of datasets)</option>
242 <option value="by_pair">Concatenate pairs of datasets (outputs an unpaired collection of datasets)</option>
243 <option value="all">Concatenate all datasets into a single file regardless of strand (outputs a single file)</option>
244 </param>
245 </when>
246 <when value="simple_collections">
247 <param name="input_1" type="data_collection" collection_type="list" label="Input first collection" help="The first collection contains the datasets that will be written first in the concatenated file" />
248 <param name="input_2" type="data_collection" collection_type="list" label="Input second collection" help="The second collection contains the datasets that will be written last in the concatenated file" />
249 </when>
250 <when value="nested_collection">
251 <param name="inputs" type="data_collection" collection_type="list:list" label="Input nested collection" help="The Nested collection which items you want to concatenate." />
252 </when>
253 </conditional>
254 <param name="dataset_names" type="boolean" label="Include dataset names?" truevalue="Yes" falsevalue="No" checked="false" help="If 'Yes' is selected '#name of dataset' will be added when concatenating."/>
255 <param name="headers" type="integer" label="Number of lines to skip at the beginning of each concatenation:" value="0" help="This paremeter exists so as to not concatenate comments or headers contained at the start of the files."/>
256 </inputs>
257 <outputs>
258 <data name="out_file1" format_source="inputs" metadata_source="inputs" label="Concatenated datasets">
259 <filter>global_condition['input_type'] == 'singles'</filter>
260 </data>
261 <data name="paired_out_file" label="${global_condition.inputs.element_identifier}" auto_format="true">
262 <filter>global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'all'</filter>
263 </data>
264 <collection name="paired_output" type="paired" label="Concatenation by strtand">
265 <discover_datasets pattern="(?P&lt;name&gt;.*)\.listed\.(?P&lt;ext&gt;.*)\.listed" visible="false" directory="concatenated"/>
266 <filter>global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'by_strand'</filter>
267 </collection>
268 <collection name="list_output" type="list" label="Concatenation by pairs">
269 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*)\.listed\.(?P&lt;ext&gt;.*)\.listed" visible="false" directory="concatenated"/>
270 <filter>(global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'by_pair') or (global_condition['input_type'] == 'simple_collections') or (global_condition['input_type'] == 'nested_collection')</filter>
271 </collection>
272 </outputs>
273 <tests>
274 <!-- Single files concatenation -->
275 <test> <!-- Test 2 single files concatenation with no other option -->
276 <param name="input_type" value="singles" />
277 <param name="inputs" value="1.bed,2.bed"/>
278 <param name="dataset_names" value="No" />
279 <param name="headers" value="0" />
280 <output name="out_file1" file="cat_wrapper_out1.bed"/>
281 </test>
282 <test> <!-- Test 2 single files concatenation with dataset names activated -->
283 <param name="input_type" value="singles" />
284 <param name="inputs" value="1.bed,2.bed"/>
285 <param name="dataset_names" value="Yes" />
286 <param name="headers" value="0" />
287 <output name="out_file1" file="cat_wrapper_out2.bed"/>
288 </test>
289 <test> <!-- Test 2 single files concatenation skipping 1 line -->
290 <param name="input_type" value="singles" />
291 <param name="inputs" value="1.bed,2.bed"/>
292 <param name="dataset_names" value="No" />
293 <param name="headers" value="1" />
294 <output name="out_file1" file="cat_wrapper_out3.bed"/>
295 </test>
296 <test> <!-- Test gz handling with no options -->
297 <param name="input_type" value="singles" />
298 <param name="inputs" value="1_f.fastq.gz,1_r.fastq.gz"/>
299 <param name="dataset_names" value="No" />
300 <param name="headers" value="0" />
301 <output name="out_file1" file="1.fastq.gz" decompress="True"/>
302 </test>
303 <test> <!-- Test gz handling with options -->
304 <param name="input_type" value="singles" />
305 <param name="inputs" value="1_f.fastq.gz,1_r.fastq.gz"/>
306 <param name="dataset_names" value="Yes" />
307 <param name="headers" value="4" />
308 <output name="out_file1" file="1_options.fastq.gz" decompress="True"/>
309 </test>
310 <!-- Test paired options -->
311 <test> <!-- Test paired collection concatenation by_pair with no other option -->
312 <param name="input_type" value="paired_collection" />
313 <param name="paired_cat_type" value="by_pair"/>
314 <param name="inputs">
315 <collection type="list:paired">
316 <element name="2">
317 <collection type="paired">
318 <element name="forward" value="2_f.fastq"/>
319 <element name="reverse" value="2_r.fastq"/>
320 </collection>
321 </element>
322 <element name="3">
323 <collection type="paired">
324 <element name="forward" value="3_f.fastq"/>
325 <element name="reverse" value="3_r.fastq"/>
326 </collection>
327 </element>
328 <element name="4">
329 <collection type="paired">
330 <element name="forward" value="4_f.fastq"/>
331 <element name="reverse" value="4_r.fastq"/>
332 </collection>
333 </element>
334 </collection>
335 </param>
336 <param name="dataset_names" value="No" />
337 <param name="headers" value="0" />
338 <output_collection name="list_output" type="list" >
339 <element name="2" file="2.fastq"/>
340 <element name="3" file="3.fastq"/>
341 <element name="4" file="4.fastq"/>
342 </output_collection>
343 </test>
344 <test> <!-- Test paired collection concatenation by_strand with no other option -->
345 <param name="input_type" value="paired_collection" />
346 <param name="paired_cat_type" value="by_strand"/>
347 <param name="inputs">
348 <collection type="list:paired">
349 <element name="2">
350 <collection type="paired">
351 <element name="forward" value="2_f.fastq"/>
352 <element name="reverse" value="2_r.fastq"/>
353 </collection>
354 </element>
355 <element name="3">
356 <collection type="paired">
357 <element name="forward" value="3_f.fastq"/>
358 <element name="reverse" value="3_r.fastq"/>
359 </collection>
360 </element>
361 <element name="4">
362 <collection type="paired">
363 <element name="forward" value="4_f.fastq"/>
364 <element name="reverse" value="4_r.fastq"/>
365 </collection>
366 </element>
367 </collection>
368 </param>
369 <param name="dataset_names" value="No" />
370 <param name="headers" value="0" />
371 <output_collection name="paired_output" type="paired" >
372 <element name="forward" file="f.fastq"/>
373 <element name="reverse" file="r.fastq"/>
374 </output_collection>
375 </test>
376 <test> <!-- Test 2 collections concatenation -->
377 <param name="input_type" value="simple_collections" />
378 <param name="collection_cat_type" value="two_collections"/>
379 <param name="input_1">
380 <collection type="list">
381 <element name="2" value="2_f.fastq"/>
382 <element name="3" value="3_f.fastq"/>
383 <element name="4" value="4_f.fastq"/>
384 </collection>
385 </param>
386 <param name="input_2">
387 <collection type="list">
388 <element name="2" value="2_r.fastq"/>
389 <element name="3" value="3_r.fastq"/>
390 <element name="4" value="4_r.fastq"/>
391 </collection>
392 </param>
393 <param name="dataset_names" value="No" />
394 <param name="headers" value="0" />
395 <output_collection name="list_output" type="list" count="3" >
396 <element name="2" file="2.fastq"/>
397 <element name="3" file="3.fastq"/>
398 <element name="4" file="4.fastq"/>
399 </output_collection>
400 </test>
401 <test> <!-- Test 2 collections concatenation with other options-->
402 <param name="input_type" value="simple_collections" />
403 <param name="collection_cat_type" value="two_collections"/>
404 <param name="input_1">
405 <collection type="list">
406 <element name="1_f.fastq.gz" value="1_f.fastq.gz"/>
407 </collection>
408 </param>
409 <param name="input_2">
410 <collection type="list">
411 <element name="1_r.fastq.gz" value="1_r.fastq.gz"/>
412 </collection>
413 </param>
414 <param name="dataset_names" value="Yes" />
415 <param name="headers" value="4" />
416 <output_collection name="list_output" type="list" count="1" >
417 <element name="1_f.fastq.gz_1_r.fastq.gz" file="1_options.fastq.gz" decompress="True"/>
418 </output_collection>
419 </test>
420 <test> <!-- Test nested collections concatenation -->
421 <param name="input_type" value="nested_collection" />
422 <param name="inputs">
423 <collection type="list:list">
424 <element name="2">
425 <collection type="list">
426 <element name="2_f" value="2_f.fastq" ftype="fastq"/>
427 <element name="2_r" value="2_r.fastq" ftype="fastq"/>
428 </collection>
429 </element>
430 <element name="3">
431 <collection type="list">
432 <element name="3" value="3.fastq" ftype="fastq"/>
433 </collection>
434 </element>
435 </collection>
436 </param>
437 <param name="dataset_names" value="No" />
438 <param name="headers" value="0" />
439 <output_collection name="list_output" type="list" count="2" >
440 <element name="2" file="2.fastq"/>
441 <element name="3" file="3.fastq"/>
442 </output_collection>
443 </test>
444 <test> <!-- Test nested collections concatenation with options and gzip-->
445 <param name="input_type" value="nested_collection" />
446 <param name="inputs">
447 <collection type="list:list">
448 <element name="1">
449 <collection type="list">
450 <element name="1_f.fastq.gz" value="1_f.fastq.gz" ftype="fastq.gz"/>
451 <element name="1_r.fastq.gz" value="1_r.fastq.gz" ftype="fastq.gz"/>
452 </collection>
453 </element>
454 </collection>
455 </param>
456 <param name="dataset_names" value="Yes" />
457 <param name="headers" value="4" />
458 <output_collection name="list_output" type="list" count="1" >
459 <element name="1" file="1_options.fastq.gz" decompress="True"/>
460 </output_collection>
461 </test>
462 </tests>
463 <help>
464
465 .. class:: warningmark
466
467 **WARNINGS:**
468
469 - This tool does not check if the datasets being concatenated are in the same format.
470 - When concatenating 2 collections make sure the first collection is the one with the most items.
471 - This tool can't handle nested collection deeper than list:list.
472
473 -----
474
475 **What it does**
476
477 Concatenates datasets and paired collections with multiple options:
478
479 - When the input is a paired collection:
480
481 - concatenation by strand : forward and reverse datasets are concatenated separately and a list with a single forward - reverse dataset pair is returned
482
483 - concatenation by pair : forward - reverse dataset pairs are concatenated and a simple dataset collection is returned
484
485 - whole collection concatenation : all datasets in the collection are concatenated and a single dataset is returned
486
487 - When the inputs are 2 collections: datasets are concatenated in a pairwise combination and a single dataset collection is returned
488
489 - When nested collection concatenation: datasets in each sub-collection are concatenated and a simple dataset collection is returned
490
491 - Skipping lines before concatenation to avoid headers
492
493 - Add the name of the concatenated files as separator
494
495 -----
496
497 **Single datasets concatenation example**
498
499 Concatenating Dataset::
500
501 chrX 151087187 151087355 A 0 -
502 chrX 151572400 151572481 B 0 +
503
504 with Dataset1::
505
506 chr1 151242630 151242955 X 0 +
507 chr1 151271715 151271999 Y 0 +
508 chr1 151278832 151279227 Z 0 -
509
510 and with Dataset2::
511
512 chr2 100000030 200000955 P 0 +
513 chr2 100000015 200000999 Q 0 +
514
515 will result in the following::
516
517 chrX 151087187 151087355 A 0 -
518 chrX 151572400 151572481 B 0 +
519 chr1 151242630 151242955 X 0 +
520 chr1 151271715 151271999 Y 0 +
521 chr1 151278832 151279227 Z 0 -
522 chr2 100000030 200000955 P 0 +
523 chr2 100000015 200000999 Q 0 +
524
525 -----
526
527 **2 Collections concatenation**
528
529 1rst collection::
530
531 a
532 b
533 c
534 d
535
536 2nd collection::
537
538 1
539 2
540 3
541 4
542
543 Concatenation result::
544
545 A single collection containing:
546
547 a concatenated with 1
548 b concatenated with 2
549 c concatenated with 3
550 d concatenated with 4
551
552 -----
553
554 **Paired collection concatenation example**
555
556 1rst pair::
557
558 forward - reverse
559
560 2nd pair::
561
562 forward - reverse
563
564 - Concatenation by strand::
565
566 concatenates:
567
568 1rst forward + 2nd forward
569 1rst reverse + 2nd reverse
570
571 outputs:
572
573 1 pair
574
575 - Concatenation by pair::
576
577 concatenates:
578
579 1rst forward + 1rst reverse
580 2nd forward + 2nd reverse
581
582 outputs:
583
584 2 datasets
585
586 - Concatenate all::
587
588 concatenates:
589
590 1rst forward + 1rst reverse + 2nd forward + 2nd reverse
591
592 outputs:
593
594 1 dataset
595
596 -----
597
598 **Nested collection concatenation example**
599
600 Nested collection:
601
602 - Experiment
603
604 - Sample_1
605
606 - Sample_1_file_1
607 - Sample_1_file_2
608
609 - Sample_2
610
611 - Sample_2_file_1
612 - Sample_2_file_2
613 - Sample_2_file_3
614
615 Concatenation result::
616
617 A single collection containing:
618
619 - Sample_1: (Sample_1_file_1 + Sample_1_file_2)
620 - Sample_2: (Sample_2_file_1 + Sample_2_file_2 + Sample_2_file_3)
621
622 -----
623
624 **When selecting "Include dataset names" when concatenating files**:
625
626 1rst file name="first_tabular"::
627
628 chrX 151087187 151087355 A 0 -
629 chrX 151572400 151572481 B 0 +
630
631 2nd file name="second_tabular"::
632
633 chr1 151242630 151242955 X 0 +
634 chr1 151271715 151271999 Y 0 +
635 chr1 151278832 151279227 Z 0 -
636
637 output::
638
639 # first_tabular
640 chrX 151087187 151087355 A 0 -
641 chrX 151572400 151572481 B 0 +
642 # second_tabular
643 chr1 151242630 151242955 X 0 +
644 chr1 151271715 151271999 Y 0 +
645 chr1 151278832 151279227 Z 0 -
646
647 -----
648
649 **Skiping lines**
650
651 1rst file::
652
653 chrX 151087187 151087355 A 0 -
654 chrX 151572400 151572481 B 0 +
655
656 2nd file::
657
658 chr1 151242630 151242955 X 0 +
659 chr1 151271715 151271999 Y 0 +
660 chr1 151278832 151279227 Z 0 -
661
662 skipping 1 line
663
664 output::
665
666 chrX 151572400 151572481 B 0 +
667 chr1 151271715 151271999 Y 0 +
668 chr1 151278832 151279227 Z 0 -
669
670 -----
671
672 Adapted from galaxy's catWrapper.xml to allow multiple input files.
673
674 </help>
675 </tool>