Mercurial > repos > artbio > concatenate_multiple_datasets
diff catWrapper.xml @ 1:3a4694d4354f draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/concat_multi_datasets commit 618a7892f6af26278364a75ab23b3c6d8cdc73db
| author | artbio |
|---|---|
| date | Wed, 20 Mar 2019 07:17:16 -0400 |
| parents | 6f54dc6b37da |
| children | 1fe4d165ac0e |
line wrap: on
line diff
--- a/catWrapper.xml Sun Mar 11 18:19:40 2018 -0400 +++ b/catWrapper.xml Wed Mar 20 07:17:16 2019 -0400 @@ -1,43 +1,246 @@ -<tool id="cat_multi_datasets" name="Concatenate multiple datasets" version="0.3"> - <description>tail-to-head</description> +<tool id="cat_multi_datasets" name="Concatenate multiple datasets" version="1.0"> + <description>tail-to-head by specifying how</description> <command><![CDATA[ - #if $headers == "No": - cat - #for $file in $input - "$file" - #end for - > "$out_file1" + #if $headers == 0: + #set $concat_command = "cat" #else: - #for $file in $input - printf "# ${file.element_identifier}\n" >> "$out_file1" && - cat "$file" >> "$out_file1" && - #end for - sleep 1 + #set $concat_command = 'tail -q -n +'+ str(int($headers)+1) + #end if + #if $global_condition.input_type == "singles": + #if $dataset_names == "No": + $concat_command + #for $file in $global_condition.inputs + '$file' + #end for + > '$out_file1' + #else: + #for $file in $global_condition.inputs + #if $file.ext[-2:] == "gz": + printf "# ${file.element_identifier}\n" | gzip -c >> '$out_file1' && + gzip -dc "$file" | $concat_command |gzip -c >> '$out_file1' && + #else: + printf "# ${file.element_identifier}\n" >> '$out_file1' && + $concat_command "$file" >> '$out_file1' && + #end if + #end for + sleep 1 + #end if + #else if $global_condition.input_type == "paired_collection": + #if $global_condition.paired_cat_type == "by_strand": + #if $dataset_names == "No": + #for $file in $global_condition.inputs + $concat_command + $file['forward'] + >> '$forward' && + $concat_command + $file['reverse'] + >> '$reverse' && + #end for + sleep 1 + #else: + #for $file in $global_condition.inputs.keys() + printf "# ${file}_forward\n" >> '$forward' && + $concat_command + $global_condition.inputs[$file]['forward'] + >> '$forward' && + printf "# ${file}_reverse\n" >> '$reverse' && + $concat_command + $global_condition.inputs[$file]['reverse'] + >> '$reverse' && + #end for + sleep 1 + #end if + #else if $global_condition.paired_cat_type == "by_pair": + mkdir concatenated && + #if $dataset_names == "No": + #for $file in $global_condition.inputs.keys() + $concat_command + $global_condition.inputs[$file]['forward'] + > concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + $concat_command + $global_condition.inputs[$file]['reverse'] + >> concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + #end for + sleep 1 + #else: + #for $file in $global_condition.inputs.keys() + printf "# ${file}_forward\n" > concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + $concat_command + $global_condition.inputs[$file]['forward'] + >> concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + printf "# ${file}_reverse\n" >> concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + $concat_command + $global_condition.inputs[$file]['reverse'] + >> concatenated/'${file}.${global_condition.inputs[$file]['reverse'].ext}.listed' && + #end for + sleep 1 + #end if + #else if $global_condition.paired_cat_type == "all": + #if $dataset_names == "No": + #for $file in $global_condition.inputs.keys() + $concat_command + $global_condition.inputs[$file]['forward'] + >> $out_file1 && + $concat_command + $global_condition.inputs[$file]['reverse'] + >> $out_file1 && + #end for + sleep 1 + #else: + #for $file in $global_condition.inputs.keys() + printf "# ${file}_forward\n" > $out_file1 && + $concat_command + $global_condition.inputs[$file]['forward'] + >> $out_file1 && + printf "# ${file}_reverse\n" >> $out_file1 && + $concat_command + $global_condition.inputs[$file]['reverse'] + >> $out_file1 && + #end for + sleep 1 + #end if + #end if #end if ]]> </command> <inputs> - <param name="headers" type="select" label="include dataset names"> - <option value="No" selected="true">No</option> - <option value="Yes">Yes</option> - </param> - <param name="input" type="data" label="Concatenate Dataset" multiple="True"/> + <conditional name="global_condition"> + <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"> + <option value="singles">Single datasets</option> + <option value="paired_collection">Paired collection</option> + </param> + <when value="singles"> + <param name="inputs" type="data" label="Concatenate Datasets" multiple="True" help="All inputed datasets will be concatenated tail-to-head."/> + </when> + <when value="paired_collection"> + <param name="inputs" type="data_collection" collection_type="list:paired" label="Input paired collections to concatenate"/> + <param name="paired_cat_type" type="select" label="What type of concatenation do you wish to perform?"> + <option value="by_strand">Concatenate all datsets of same strand (outputs a single pair of datasets)</option> + <option value="by_pair">Concatenate pairs of datasets (outputs an unpaired collection of datasets)</option> + <option value="all">Concatenate all datasets into a single file regardless of strand (outputs a single file)</option> + </param> + </when> + </conditional> + <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."/> + <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."/> </inputs> <outputs> - <data name="out_file1" format_source="input" metadata_source="input"/> + <data name="out_file1" format_source="inputs" metadata_source="inputs" label="Concatenated datasets"> + <filter>global_condition['input_type'] == 'singles' or (global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'all')</filter> + </data> + <collection name="paired_output" type="paired" label="Concatenation by strtand"> + <data name="forward" /> + <data name="reverse" /> + <filter>global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'by_strand'</filter> + </collection> + <collection name="list_output" type="list" label="Concatenation by pairs"> + <discover_datasets pattern="(?P<name>.*)\.(?P<ext>[^\._]+\.?[^\._])\.listed" visible="false" directory="concatenated"/> + <filter>global_condition['input_type'] == 'paired_collection' and global_condition['paired_cat_type'] == 'by_pair'</filter> + </collection> </outputs> <tests> - <test> - <param name="headers" value="No" /> - <param name="input" value="1.bed,2.bed"/> + <!-- Single files concatenation --> + <test> <!-- Test 2 single files concatenation with no other option --> + <param name="input_type" value="singles" /> + <param name="inputs" value="1.bed,2.bed"/> + <param name="dataset_names" value="No" /> + <param name="headers" value="0" /> <output name="out_file1" file="cat_wrapper_out1.bed"/> </test> - <test> - <param name="headers" value="Yes" /> - <param name="input" value="1.bed,2.bed"/> + <test> <!-- Test 2 single files concatenation with dataset names activated --> + <param name="input_type" value="singles" /> + <param name="inputs" value="1.bed,2.bed"/> + <param name="dataset_names" value="Yes" /> + <param name="headers" value="0" /> <output name="out_file1" file="cat_wrapper_out2.bed"/> </test> - + <test> <!-- Test 2 single files concatenation skipping 1 line --> + <param name="input_type" value="singles" /> + <param name="inputs" value="1.bed,2.bed"/> + <param name="dataset_names" value="No" /> + <param name="headers" value="1" /> + <output name="out_file1" file="cat_wrapper_out3.bed"/> + </test> + <test> <!-- Test gz handling with no options --> + <param name="input_type" value="singles" /> + <param name="inputs" value="1_f.fastq.gz,1_r.fastq.gz"/> + <param name="dataset_names" value="No" /> + <param name="headers" value="0" /> + <output name="out_file1" file="1.fastq.gz" decompress="True"/> + </test> + <test> <!-- Test gz handling with options --> + <param name="input_type" value="singles" /> + <param name="inputs" value="1_f.fastq.gz,1_r.fastq.gz"/> + <param name="dataset_names" value="Yes" /> + <param name="headers" value="4" /> + <output name="out_file1" file="1_options.fastq.gz" decompress="True"/> + </test> + <!-- Test paired options --> + <test> <!-- Test paired collection concatenation by_pair with no other option --> + <param name="input_type" value="paired_collection" /> + <param name="paired_cat_type" value="by_pair"/> + <param name="inputs"> + <collection type="list:paired"> + <element name="2"> + <collection type="paired"> + <element name="forward" value="2_f.fastq"/> + <element name="reverse" value="2_r.fastq"/> + </collection> + </element> + <element name="3"> + <collection type="paired"> + <element name="forward" value="3_f.fastq"/> + <element name="reverse" value="3_r.fastq"/> + </collection> + </element> + <element name="4"> + <collection type="paired"> + <element name="forward" value="4_f.fastq"/> + <element name="reverse" value="4_r.fastq"/> + </collection> + </element> + </collection> + </param> + <param name="dataset_names" value="No" /> + <param name="headers" value="0" /> + <output_collection name="list_output" type="list" > + <element name="2" file="2.fastq"/> + <element name="3" file="3.fastq"/> + <element name="4" file="4.fastq"/> + </output_collection> + </test> + <test> <!-- Test paired collection concatenation by_strand with no other option --> + <param name="input_type" value="paired_collection" /> + <param name="paired_cat_type" value="by_strand"/> + <param name="inputs"> + <collection type="list:paired"> + <element name="2"> + <collection type="paired"> + <element name="forward" value="2_f.fastq"/> + <element name="reverse" value="2_r.fastq"/> + </collection> + </element> + <element name="3"> + <collection type="paired"> + <element name="forward" value="3_f.fastq"/> + <element name="reverse" value="3_r.fastq"/> + </collection> + </element> + <element name="4"> + <collection type="paired"> + <element name="forward" value="4_f.fastq"/> + <element name="reverse" value="4_r.fastq"/> + </collection> + </element> + </collection> + </param> + <param name="dataset_names" value="No" /> + <param name="headers" value="0" /> + <output_collection name="paired_output" type="paired" > + <element name="forward" file="f.fastq"/> + <element name="reverse" file="r.fastq"/> + </output_collection> + </test> </tests> <help> @@ -45,15 +248,23 @@ **WARNING:** This tool does not check if the datasets being concatenated are in the same format. +**WARNING:** The paired collection operations do not handle gziped files. + ----- **What it does** -Concatenates datasets +Concatenates datasets and paired collections with multiple options: + + - It's possible select either a concatenation by strand, by pair or a whole collection concatenation, when the input is a paired collection. + + - Skipping lines before concatenation to avoid headers + + - Add the name of the concatenated files as separator ----- -**Example** +**Single datasets concatenation example** Concatenating Dataset:: @@ -83,6 +294,98 @@ ----- +**Paired collection concatenation example** + +1rst pair:: + + forward - reverse + +2nd pair:: + + forward - reverse + +Concatenation by strand:: + + concatenates: + + 1rst forward + 2nd forward + 1rst reverse + 2nd reverse + + outputs: + + 1 pair + +Concatenation by pair:: + + concatenates: + + 1rst forward + 1rst reverse + 2nd forward + 2nd reverse + + outputs: + + 2 datasets + +Concatenate all:: + + concatenates: + + 1rst forward + 1rst reverse + 2nd forward + 2nd reverse + + outputs: + + 1 dataset + +----- + +**When selecting "Include dataset names" when concatenating files**: + +1rst file name="first_tabular":: + + chrX 151087187 151087355 A 0 - + chrX 151572400 151572481 B 0 + + +2nd file name="second_tabular":: + + chr1 151242630 151242955 X 0 + + chr1 151271715 151271999 Y 0 + + chr1 151278832 151279227 Z 0 - + +output:: + + # first_tabular + chrX 151087187 151087355 A 0 - + chrX 151572400 151572481 B 0 + + # second_tabular + chr1 151242630 151242955 X 0 + + chr1 151271715 151271999 Y 0 + + chr1 151278832 151279227 Z 0 - + +----- + +**Skiping lines** + +1rst file:: + + chrX 151087187 151087355 A 0 - + chrX 151572400 151572481 B 0 + + +2nd file:: + + chr1 151242630 151242955 X 0 + + chr1 151271715 151271999 Y 0 + + chr1 151278832 151279227 Z 0 - + +skipping 1 line + +output:: + + chrX 151572400 151572481 B 0 + + chr1 151271715 151271999 Y 0 + + chr1 151278832 151279227 Z 0 - + +----- + Adapted from galaxy's catWrapper.xml to allow multiple input files. </help>