annotate awk.xml @ 0:224be21ac8c7

commit
author pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
date Sun, 19 Oct 2014 15:04:49 +0900
parents
children 69fbeac761c2
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
1 <!--
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
2 This tool is based on 'cshl_awk_tool' from Hannon Lab CSHL
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
3 http://hannonlab.cshl.edu/galaxy_unix_tools/
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
4 Thanks. Pitagora
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
5 -->
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
6 <tool id="awk" name="awk">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
7 <description></description>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
8 <command interpreter="sh">awk_wrapper.sh $input $output '$file_data' '$FS' '$OFS'</command>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
9 <inputs>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
10 <param format="txt" name="input" type="data" label="File to process" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
11 <param name="FS" type="select" label="Input field-separator">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
12 <option value=",">comma (,)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
13 <option value=":">colons (:) </option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
14 <option value=" ">single space</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
15 <option value=".">dot (.)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
16 <option value="-">dash (-)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
17 <option value="|">pipe (|)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
18 <option value="_">underscore (_)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
19 <option selected="True" value="tab">tab</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
20 </param>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
21 <param name="OFS" type="select" label="Output field-separator">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
22 <option value=",">comma (,)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
23 <option value=":">colons (:)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
24 <option value=" ">space ( )</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
25 <option value="-">dash (-)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
26 <option value=".">dot (.)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
27 <option value="|">pipe (|)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
28 <option value="_">underscore (_)</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
29 <option selected="True" value="tab">tab</option>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
30 </param>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
31 <param name="file_data" type="text" area="true" size="5x60" label="AWK Program" help="">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
32 <sanitizer>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
33 <valid initial="string.printable">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
34 <remove value="&apos;"/>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
35 </valid>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
36 <mapping initial="none">
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
37 <add source="&apos;" target="__sq__"/>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
38 </mapping>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
39 </sanitizer>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
40 </param>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
41 </inputs>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
42 <tests>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
43 <test>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
44 <param name="input" value="unix_awk_input1.txt" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
45 <output name="output" file="unix_awk_output1.txt" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
46 <param name="FS" value="tab" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
47 <param name="OFS" value="tab" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
48 <param name="file_data" value="$2>0.5 { print $2*9, $1 }" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
49 </test>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
50 </tests>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
51 <outputs>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
52 <data format="input" name="output" metadata_source="input" />
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
53 </outputs>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
54 <help>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
55
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
56 **What it does**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
57
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
58 This tool runs the unix **awk** command on the selected data file.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
59
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
60 .. class:: infomark
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
61
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
62 **TIP:** This tool uses the **extended regular** expression syntax (not the perl syntax).
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
63
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
64
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
65 **Further reading**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
66
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
67 - Awk by Example (http://www.ibm.com/developerworks/linux/library/l-awk1.html)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
68 - Long AWK tutorial (http://www.grymoire.com/Unix/Awk.html)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
69 - Learn AWK in 1 hour (http://www.selectorweb.com/awk.html)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
70 - awk cheat-sheet (http://cbi.med.harvard.edu/people/peshkin/sb302/awk_cheatsheets.pdf)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
71 - Collection of useful awk one-liners (http://student.northpark.edu/pemente/awk/awk1line.txt)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
72
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
73 -----
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
74
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
75 **AWK programs**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
76
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
77 Most AWK programs consist of **patterns** (i.e. rules that match lines of text) and **actions** (i.e. commands to execute when a pattern matches a line).
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
78
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
79 The basic form of AWK program is::
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
80
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
81 pattern { action 1; action 2; action 3; }
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
82
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
83
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
84
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
85
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
86
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
87 **Pattern Examples**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
88
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
89 - **$2 == "chr3"** will match lines whose second column is the string 'chr3'
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
90 - **$5-$4>23** will match lines that after subtracting the value of the fourth column from the value of the fifth column, gives value alrger than 23.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
91 - **/AG..AG/** will match lines that contain the regular expression **AG..AG** (meaning the characeters AG followed by any two characeters followed by AG). (This is the way to specify regular expressions on the entire line, similar to GREP.)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
92 - **$7 ~ /A{4}U/** will match lines whose seventh column contains 4 consecutive A's followed by a U. (This is the way to specify regular expressions on a specific field.)
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
93 - **10000 &lt; $4 &amp;&amp; $4 &lt; 20000** will match lines whose fourth column value is larger than 10,000 but smaller than 20,000
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
94 - If no pattern is specified, all lines match (meaning the **action** part will be executed on all lines).
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
95
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
96
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
97
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
98 **Action Examples**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
99
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
100 - **{ print }** or **{ print $0 }** will print the entire input line (the line that matched in **pattern**). **$0** is a special marker meaning 'the entire line'.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
101 - **{ print $1, $4, $5 }** will print only the first, fourth and fifth fields of the input line.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
102 - **{ print $4, $5-$4 }** will print the fourth column and the difference between the fifth and fourth column. (If the fourth column was start-position in the input file, and the fifth column was end-position - the output file will contain the start-position, and the length).
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
103 - If no action part is specified (not even the curly brackets) - the default action is to print the entire line.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
104
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
105
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
106
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
107
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
108
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
109
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
110
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
111
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
112
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
113 **AWK's Regular Expression Syntax**
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
114
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
115 The select tool searches the data for lines containing or not containing a match to the given pattern. A Regular Expression is a pattern descibing a certain amount of text.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
116
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
117 - **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
118 - **^** matches the beginning of a string(but not an internal line).
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
119 - **(** .. **)** groups a particular pattern.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
120 - **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
121
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
122 - **{n}** The preceding item is matched exactly n times.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
123 - **{n,}** The preceding item ismatched n or more times.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
124 - **{n,m}** The preceding item is matched at least n times but not more than m times.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
125
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
126 - **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
127 - **.** Matches any single character except a newline.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
128 - ***** The preceding item will be matched zero or more times.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
129 - **?** The preceding item is optional and matched at most once.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
130 - **+** The preceding item will be matched one or more times.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
131 - **^** has two meaning:
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
132 - matches the beginning of a line or string.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
133 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
134 - **$** matches the end of a line or string.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
135 - **\|** Separates alternate possibilities.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
136
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
137
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
138 **Note**: AWK uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
139
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
140 </help>
pitagora <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
141 </tool>