Mercurial > repos > bgruening > text_processing
annotate awk.xml @ 29:4f7cade041cb draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
author | bgruening |
---|---|
date | Wed, 04 Jun 2025 15:11:51 +0000 |
parents | 08cdbfffce67 |
children |
rev | line source |
---|---|
26
f22a309187a3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents:
24
diff
changeset
|
1 <tool id="tp_awk_tool" name="Text reformatting" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> |
2 | 2 <description>with awk</description> |
4 | 3 <macros> |
4 <import>macros.xml</import> | |
5 </macros> | |
26
f22a309187a3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents:
24
diff
changeset
|
6 <expand macro="creator"/> |
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
|
7 <requirements> |
27
08cdbfffce67
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents:
26
diff
changeset
|
8 <requirement type="package" version="5.3.1">gawk</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
|
9 </requirements> |
4 | 10 <version_command>awk --version | head -n 1</version_command> |
0 | 11 <command> |
4 | 12 <![CDATA[ |
20
1aa30b2c73c9
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4f79443517baf378fbfe1f81be361d97f2938601
bgruening
parents:
18
diff
changeset
|
13 env -i |
24
5fef6d08de83
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 5f5d5802a961a77ceb092cbdef90d93e29717029-dirty"
bgruening
parents:
22
diff
changeset
|
14 \$(which awk) |
4 | 15 --sandbox |
6 | 16 -v FS=' ' |
17 -v OFS=' ' | |
29
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
18 #for $i, $r in enumerate($variables, start=1) |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
19 -v VAR$i='$r.value' |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
20 #end for |
4 | 21 --re-interval |
26
f22a309187a3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents:
24
diff
changeset
|
22 -f '$awk_script' |
f22a309187a3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents:
24
diff
changeset
|
23 '$infile' |
f22a309187a3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents:
24
diff
changeset
|
24 > '$outfile' |
4 | 25 ]]> |
0 | 26 </command> |
13
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
27 <configfiles> |
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
28 <configfile name="awk_script">$code</configfile> |
3c685c4106b3
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents:
12
diff
changeset
|
29 </configfiles> |
0 | 30 <inputs> |
6 | 31 <param name="infile" format="txt" type="data" label="File to process" /> |
32 <param name="code" type="text" area="true" size="5x35" label="AWK Program" help=""> | |
0 | 33 <sanitizer> |
34 <valid initial="string.printable"> | |
35 <remove value="'"/> | |
36 </valid> | |
37 </sanitizer> | |
38 </param> | |
29
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
39 <repeat name="variables" min="0" default="0" title="Variables"> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
40 <param name="value" type="text" label="Value"> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
41 <validator type="regex">[a-zA-Z0-9 .]+</validator> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
42 </param> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
43 </repeat> |
4 | 44 </inputs> |
45 <outputs> | |
6 | 46 <data name="outfile" format_source="infile" metadata_source="infile"/> |
4 | 47 </outputs> |
48 <tests> | |
6 | 49 <test> |
29
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
50 <param name="infile" value="awk1.txt"/> |
6 | 51 <!-- commas are not allowed in a value field. Values with comma will be splitted --> |
52 <param name="code" value='$2>0.5 { print $2*9"\t"$1 }' /> | |
53 <output name="outfile" file="awk_results1.txt" /> | |
54 </test> | |
29
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
55 <test> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
56 <param name="infile" value="awk1.txt"/> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
57 <!-- commas are not allowed in a value field. Values with comma will be splitted --> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
58 <param name="code" value='$2>VAR2 { print VAR1"\t"$2*9"\t"$1 }' /> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
59 <repeat name="variables"> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
60 <param name="value" value="xyz"/> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
61 </repeat> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
62 <repeat name="variables"> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
63 <param name="value" value="0.1"/> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
64 </repeat> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
65 <output name="outfile"> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
66 <assert_contents> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
67 <has_line_matching expression="^xyz.*" n="6"/> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
68 </assert_contents> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
69 </output> |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
70 </test> |
4 | 71 </tests> |
72 <help> | |
73 <![CDATA[ | |
0 | 74 **What it does** |
75 | |
76 This tool runs the unix **awk** command on the selected data file. | |
77 | |
78 .. class:: infomark | |
79 | |
7 | 80 **TIP:** |
1 | 81 |
7 | 82 This tool uses the **extended regular** expression syntax (not the perl syntax). |
1 | 83 **\\d**, **\\w**, **\\s** etc. are **not** supported. |
0 | 84 |
85 | |
86 **Further reading** | |
87 | |
14
7725ab6dab67
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b'e6ee273f75fff61d1e419283fa8088528cf59470\n'
bgruening
parents:
13
diff
changeset
|
88 - Awk by Example (http://www.ibm.com/developerworks/linux/library/l-awk1/index.html) |
0 | 89 - Long AWK tutorial (http://www.grymoire.com/Unix/Awk.html) |
90 | |
91 ----- | |
92 | |
93 **AWK programs** | |
94 | |
95 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). | |
96 | |
97 The basic form of AWK program is:: | |
98 | |
99 pattern { action 1; action 2; action 3; } | |
100 | |
29
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
101 **Variables** |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
102 |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
103 In order to allow parametrization in workflows, the tool allows to specify values for variables that can be used in AWK program. |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
104 that will be named **VAR1**, **VAR2**, ... |
4f7cade041cb
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4dd118c84ed4d6157303e71438c24446ec4b4f31
bgruening
parents:
27
diff
changeset
|
105 |
0 | 106 |
107 **Pattern Examples** | |
108 | |
109 - **$2 == "chr3"** will match lines whose second column is the string 'chr3' | |
110 - **$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. | |
111 - **/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.) | |
112 - **$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.) | |
6 | 113 - **10000 < $4 && $4 < 20000** will match lines whose fourth column value is larger than 10,000 but smaller than 20,000 |
18
1e974b82380d
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 0ba37c1f33eeb1c77b4d9363d681fe522d9f7fe7
bgruening
parents:
15
diff
changeset
|
114 - **BEGIN** will be executed once only, before the first input record is read. |
0 | 115 - If no pattern is specified, all lines match (meaning the **action** part will be executed on all lines). |
116 | |
117 | |
15
74aae7d6cb09
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 3103ebed1a420c7d3415b67ef532ea579edf9faa
bgruening
parents:
14
diff
changeset
|
118 |
0 | 119 **Action Examples** |
120 | |
121 - **{ 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'. | |
122 - **{ print $1, $4, $5 }** will print only the first, fourth and fifth fields of the input line. | |
123 - **{ 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). | |
15
74aae7d6cb09
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 3103ebed1a420c7d3415b67ef532ea579edf9faa
bgruening
parents:
14
diff
changeset
|
124 - **{ FS = "," }** can be used to change the field separator (delimeter) for parsing the input file. |
0 | 125 - If no action part is specified (not even the curly brackets) - the default action is to print the entire line. |
126 | |
127 | |
128 **AWK's Regular Expression Syntax** | |
129 | |
7 | 130 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. |
0 | 131 |
132 - **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for. | |
133 - **^** matches the beginning of a string(but not an internal line). | |
134 - **(** .. **)** groups a particular pattern. | |
135 - **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern. | |
136 | |
137 - **{n}** The preceding item is matched exactly n times. | |
7 | 138 - **{n,}** The preceding item ismatched n or more times. |
139 - **{n,m}** The preceding item is matched at least n times but not more than m times. | |
0 | 140 |
141 - **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**. | |
142 - **.** Matches any single character except a newline. | |
143 - ***** The preceding item will be matched zero or more times. | |
144 - **?** The preceding item is optional and matched at most once. | |
145 - **+** The preceding item will be matched one or more times. | |
146 - **^** has two meaning: | |
7 | 147 - matches the beginning of a line or string. |
0 | 148 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets. |
149 - **$** matches the end of a line or string. | |
7 | 150 - **\|** Separates alternate possibilities. |
0 | 151 |
4 | 152 ]]> |
1 | 153 </help> |
14
7725ab6dab67
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b'e6ee273f75fff61d1e419283fa8088528cf59470\n'
bgruening
parents:
13
diff
changeset
|
154 <expand macro="citations" /> |
0 | 155 </tool> |