annotate sed.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
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
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: 18
diff changeset
1 <tool id="tp_sed_tool" name="Text transformation" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
2 <description>with sed</description>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
3 <macros>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
4 <import>macros.xml</import>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
5 </macros>
26
f22a309187a3 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents: 18
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>
26
f22a309187a3 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit c2b1677d1c94433f777c2dc28ac8eec0a99cc6a7
bgruening
parents: 18
diff changeset
8 <requirement type="package" version="4.8">sed</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
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
10 <version_command>sed --version | head -n 1</version_command>
1
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
11 <command>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
12 <![CDATA[
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
13 sed
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
14 --sandbox
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
15 -r
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
16 #if $adv_opts.adv_opts_selector == 'advanced':
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
17 $adv_opts.silent
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
18 #end if
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
19 -f '$sed_script'
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
20 '$infile'
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
21 > '$output'
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
22 ]]>
1
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
23 </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
24 <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
25 <configfile name="sed_script">
3c685c4106b3 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
bgruening
parents: 12
diff changeset
26 $code
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 </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
28 </configfiles>
1
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
29 <inputs>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
30 <param format="txt" name="infile" type="data" label="File to process" />
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
31 <param name="code" type="text" area="true" size="5x35" label="SED Program" help="">
1
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
32 <sanitizer>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
33 <valid initial="string.printable">
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
34 <remove value="&apos;"/>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
35 </valid>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
36 </sanitizer>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
37 </param>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
38 <conditional name="adv_opts">
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
39 <param name="adv_opts_selector" type="select" label="Advanced Options">
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
40 <option value="basic" selected="True">Hide Advanced Options</option>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
41 <option value="advanced">Show Advanced Options</option>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
42 </param>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
43 <when value="basic" />
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
44 <when value="advanced">
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
45 <param name="silent" type="select" label="Operation mode" help="Same as 'sed -n', leave at 'normal' unless you know what you're doing." >
1
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
46 <option value="">normal</option>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
47 <option value="-n">silent</option>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
48 </param>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
49 </when>
a4ad586d1403 Uploaded
bgruening
parents: 0
diff changeset
50 </conditional>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
51 </inputs>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
52 <outputs>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
53 <data name="output" format_source="infile" metadata_source="infile" />
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
54 </outputs>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
55 <tests>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
56 <test>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
57 <param name="infile" value="sed1.txt" />
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
58 <param name="code" value="1d ; s/foo/bar/" />
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
59 <conditional name="adv_opts">
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
60 <param name="adv_opts_selector" value="advanced" />
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
61 <param name="silent" value="" />
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
62 </conditional>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
63 <output name="output" file="sed_results1.txt" />
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
64 </test>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
65 <test>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
66 <param name="infile" value="sed1.txt" />
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
67 <param name="code" value="/foo/ { s/foo/baz/g ; p }" />
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
68 <conditional name="adv_opts">
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
69 <param name="adv_opts_selector" value="advanced" />
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
70 <param name="silent" value="-n" />
08cdbfffce67 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 2dc2df988bd2dde9f8d7f629b594186dbd4fdc2b
bgruening
parents: 26
diff changeset
71 </conditional>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
72 <output name="output" file="sed_results2.txt" />
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
73 </test>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
74 </tests>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
75 <help>
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
76 <![CDATA[
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
77 **What it does**
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
78
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
79 This tool runs the unix **sed** command on the selected data file.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
80
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
81 .. class:: infomark
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
82
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
83 **TIP:** This tool uses the **extended regular** expression syntax (same as running 'sed -r').
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
84
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
85
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
86
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
87 **Further reading**
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
88
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
89 - Short sed tutorial (http://www.linuxhowtos.org/System/sed_tutorial.htm)
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
90 - Long sed tutorial (http://www.grymoire.com/Unix/Sed.html)
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
91 - sed faq with good examples (http://sed.sourceforge.net/sedfaq.html)
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
92 - sed cheat-sheet (http://www.catonmat.net/download/sed.stream.editor.cheat.sheet.pdf)
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
93
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
94 -----
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
95
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
96 **Sed commands**
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
97
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
98 The most useful sed command is **s** (substitute).
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
99
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
100 **Examples**
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
101
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
102 - **s/hsa//** will remove the first instance of 'hsa' in every line.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
103 - **s/hsa//g** will remove all instances (beacuse of the **g**) of 'hsa' in every line.
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
104 - **s/A{4,}/--&--/g** will find sequences of 4 or more consecutive A's, and once found, will surround them with two dashes from each side. The **&** marker is a place holder for 'whatever matched the regular expression'.
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
105 - **s/hsa-mir-([^ ]+)/short name: \\1 full name: &/** will find strings such as 'hsa-mir-43a' (the regular expression is 'hsa-mir-' followed by non-space characters) and will replace it will string such as 'short name: 43a full name: hsa-mir-43a'. The **\\1** marker is a place holder for 'whatever matched the first parenthesis' (similar to perl's **$1**) .
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
106
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
107
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
108 **sed's Regular Expression Syntax**
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
109
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
110 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
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
111
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
112 - **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
113 - **^** matches the beginning of a string(but not an internal line).
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
114 - **(** .. **)** groups a particular pattern.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
115 - **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
116
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
117 - **{n}** The preceding item is matched exactly n times.
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
118 - **{n,}** The preceding item ismatched n or more times.
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
119 - **{n,m}** The preceding item is matched at least n times but not more than m times.
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
120
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
121 - **[** ... **]** 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**.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
122 - **.** Matches any single character except a newline.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
123 - ***** The preceding item will be matched zero or more times.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
124 - **?** The preceding item is optional and matched at most once.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
125 - **+** The preceding item will be matched one or more times.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
126 - **^** has two meaning:
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
127 - matches the beginning of a line or string.
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
128 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
129 - **$** matches the end of a line or string.
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
130 - **\|** Separates alternate possibilities.
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
131
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
132
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
133 **Note**: SED uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
134
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
135 ]]>
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
136 </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
137 <expand macro="citations" />
0
ec66f9d90ef0 initial uploaded
bgruening
parents:
diff changeset
138 </tool>