PageRenderTime 25ms CodeModel.GetById 19ms app.highlight 2ms RepoModel.GetById 2ms app.codeStats 0ms

XML | 87 lines | 72 code | 14 blank | 1 comment | 0 complexity | 722f2a5926ec78995c52ad8830e570c4 MD5 | raw file
 1<tool id="Filter1" name="Filter" version="1.1.0">
 2  <description>data on any column using simple expressions</description>
 3  <command interpreter="python">
 4 $input $out_file1 "$cond" ${input.metadata.columns} "${input.metadata.column_types}" $header_lines
 5  </command>
 6  <inputs>
 7    <param format="tabular" name="input" type="data" label="Filter" help="Dataset missing? See TIP below."/>
 8    <param name="cond" size="40" type="text" value="c1=='chr22'" label="With following condition" help="Double equal signs, ==, must be used as shown above. To filter for an arbitrary string, use the Select tool.">
 9      <validator type="empty_field" message="Enter a valid filtering condition, see syntax and examples below."/>
10    </param>
11    <param name="header_lines" type="integer" value="0" label="Number of header lines to skip"/>
12  </inputs>
13  <outputs>
14    <data format="input" name="out_file1" metadata_source="input"/>
15  </outputs>
16  <tests>
17    <test>
18      <param name="input" value="1.bed"/>
19      <param name="cond" value="c1=='chr22'"/>
20      <param name="header_lines" value="0"/>
21      <output name="out_file1" file="filter1_test1.bed"/>
22    </test>
23    <test>
24      <param name="input" value="7.bed"/>
25      <param name="cond" value="c1=='chr1' and c3-c2>=2000 and c6=='+'"/>
26      <param name="header_lines" value="0"/>
27      <output name="out_file1" file="filter1_test2.bed"/>
28    </test>
29    <!-- Test filtering of file with a variable number of columns. -->
30    <test>
31      <param name="input" value="filter1_in3.sam"/>
32      <param name="cond" value="c3=='chr1' and c5>5"/>
33      <param name="header_lines" value="0"/>
34      <output name="out_file1" file="filter1_test3.sam"/>
35    </test>
36    <test>
37      <param name="input" value="filter1_inbad.bed"/>
38      <param name="cond" value="c1=='chr22'"/>
39      <param name="header_lines" value="0"/>
40      <output name="out_file1" file="filter1_test4.bed"/>
41    </test>
42    <test>
43      <param name="input" value=""/>
44      <param name="cond" value="c8>500"/>
45      <param name="header_lines" value="1"/>
46      <output name="out_file1" file=""/>
47    </test>
48  </tests>
49  <help>
51.. class:: warningmark
53Double equal signs, ==, must be used as *"equal to"* (e.g., **c1 == 'chr22'**)
55.. class:: infomark
57**TIP:** Attempting to apply a filtering condition may throw exceptions if the data type (e.g., string, integer) in every line of the columns being filtered is not appropriate for the condition (e.g., attempting certain numerical calculations on strings).  If an exception is thrown when applying the condition to a line, that line is skipped as invalid for the filter condition.  The number of invalid skipped lines is documented in the resulting history item as a "Condition/data issue".
59.. class:: infomark
61**TIP:** If your data is not TAB delimited, use *Text Manipulation-&gt;Convert*
67The filter tool allows you to restrict the dataset using simple conditional statements.
69- Columns are referenced with **c** and a **number**. For example, **c1** refers to the first column of a tab-delimited file
70- Make sure that multi-character operators contain no white space ( e.g., **&lt;=** is valid while **&lt; =** is not valid )
71- When using 'equal-to' operator **double equal sign '==' must be used** ( e.g., **c1=='chr1'** )
72- Non-numerical values must be included in single or double quotes ( e.g., **c6=='+'** )
73- Filtering condition can include logical operators, but **make sure operators are all lower case** ( e.g., **(c1!='chrX' and c1!='chrY') or not c6=='+'** )
79- **c1=='chr1'** selects lines in which the first column is chr1
80- **c3-c2&lt;100*c4** selects lines where subtracting column 3 from column 2 is less than the value of column 4 times 100
81- **len(c2.split(',')) &lt; 4** will select lines where the second column has less than four comma separated elements
82- **c2>=1** selects lines in which the value of column 2 is greater than or equal to 1
83- Numbers should not contain commas - **c2&lt;=44,554,350** will not work, but **c2&lt;=44554350** will
84- Some words in the data can be used, but must be single or double quoted ( e.g., **c3=='exon'** )