annotate replace_text_in_column.xml @ 18:1e974b82380d draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 0ba37c1f33eeb1c77b4d9363d681fe522d9f7fe7
author bgruening
date Tue, 27 Feb 2018 17:10:53 -0500
parents 7725ab6dab67
children bed2226b90f7
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
18
1e974b82380d planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 0ba37c1f33eeb1c77b4d9363d681fe522d9f7fe7
bgruening
parents: 14
diff changeset
1 <tool id="tp_replace_in_column" name="Replace Text" version="@BASE_VERSION@.2">
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
2 <description>in a specific column</description>
4
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>
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
6 <requirements>
18
1e974b82380d planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 0ba37c1f33eeb1c77b4d9363d681fe522d9f7fe7
bgruening
parents: 14
diff changeset
7 <requirement type="package" version="4.2.0">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
8 </requirements>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
9 <version_command>awk --version | head -n 1</version_command>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
10 <command>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
11 <![CDATA[
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
12 awk
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
13 -v OFS="\t"
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
14 -v FS="\t"
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
15 --re-interval
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
16 --sandbox '{ \$$column = gensub( /$find_pattern/, "$replace_pattern", "g", \$$column ) ; print \$0 ; }'
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
17 "$infile"
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
18 > "$outfile"
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
19 ]]>
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
20 </command>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
21 <inputs>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
22 <param format="tabular" name="infile" type="data" label="File to process" />
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
23 <param name="column" label="in column" type="data_column" data_ref="infile" accept_default="true" />
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
24
10
c78b1767db2b planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 10052765d6b712cf7d38356af4251fcc38a339b6-dirty
bgruening
parents: 7
diff changeset
25 <param name="find_pattern" type="text" label="Find pattern" help="Use simple text, or a valid regular expression (without backslashes // ) " >
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
26 <sanitizer>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
27 <valid initial="string.printable">
7068d1548234 Uploaded
bgruening
parents:
diff changeset
28 <remove value="&apos;"/>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
29 </valid>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
30 </sanitizer>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
31 </param>
10
c78b1767db2b planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 10052765d6b712cf7d38356af4251fcc38a339b6-dirty
bgruening
parents: 7
diff changeset
32 <param name="replace_pattern" type="text" label="Replace with" help="Use simple text, or &amp; (ampersand) and \\1 \\2 \\3 to refer to matched text. See examples below." >
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
33 <sanitizer>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
34 <valid initial="string.printable">
7068d1548234 Uploaded
bgruening
parents:
diff changeset
35 <remove value="&apos;"/>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
36 </valid>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
37 </sanitizer>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
38 </param>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
39 </inputs>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
40 <outputs>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
41 <data name="outfile" format_source="infile" metadata_source="infile" />
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
42 </outputs>
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
43 <tests>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
44 <test>
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
45 <param name="infile" value="replace_text_in_column1.txt" ftype="tabular" />
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
46 <param name="column" value="4" />
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
47 <param name="find_pattern" value=".+_(R.)" />
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
48 <param name="replace_pattern" value="\\1" />
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
49 <output name="outfile" file="replace_text_in_column_results1.txt" />
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
50 </test>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
51 </tests>
7068d1548234 Uploaded
bgruening
parents:
diff changeset
52 <help>
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
53 <![CDATA[
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
54 **What it does**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
55
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
56 This tool performs find & replace operation on a specified column in a given file.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
57
7068d1548234 Uploaded
bgruening
parents:
diff changeset
58 .. class:: infomark
7068d1548234 Uploaded
bgruening
parents:
diff changeset
59
7068d1548234 Uploaded
bgruening
parents:
diff changeset
60 The **pattern to find** uses the **extended regular** expression syntax (same as running 'awk --re-interval').
7068d1548234 Uploaded
bgruening
parents:
diff changeset
61
7068d1548234 Uploaded
bgruening
parents:
diff changeset
62 .. class:: infomark
7068d1548234 Uploaded
bgruening
parents:
diff changeset
63
7068d1548234 Uploaded
bgruening
parents:
diff changeset
64 **TIP:** If you need more complex patterns, use the *awk* tool.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
65
7068d1548234 Uploaded
bgruening
parents:
diff changeset
66 -----
7068d1548234 Uploaded
bgruening
parents:
diff changeset
67
7068d1548234 Uploaded
bgruening
parents:
diff changeset
68
7068d1548234 Uploaded
bgruening
parents:
diff changeset
69 **Examples of Find Patterns**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
70
7068d1548234 Uploaded
bgruening
parents:
diff changeset
71 - **HELLO** The word 'HELLO' (case sensitive).
7068d1548234 Uploaded
bgruening
parents:
diff changeset
72 - **AG.T** The letters A,G followed by any single character, followed by the letter T.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
73 - **A{4,}** Four or more consecutive A's.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
74 - **chr2[012]\\t** The words 'chr20' or 'chr21' or 'chr22' followed by a tab character.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
75 - **hsa-mir-([^ ]+)** The text 'hsa-mir-' followed by one-or-more non-space characters. When using parenthesis, the matched content of the parenthesis can be accessed with **\1** in the **replace** pattern.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
76
7068d1548234 Uploaded
bgruening
parents:
diff changeset
77
7068d1548234 Uploaded
bgruening
parents:
diff changeset
78 **Examples of Replace Patterns**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
79
7068d1548234 Uploaded
bgruening
parents:
diff changeset
80 - **WORLD** The word 'WORLD' will be placed whereever the find pattern was found.
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
81 - **FOO-&-BAR** Each time the find pattern is found, it will be surrounded with 'FOO-' at the begining and '-BAR' at the end. **&** (ampersand) represents the matched find pattern.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
82 - **\\1** The text which matched the first parenthesis in the Find Pattern.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
83
7068d1548234 Uploaded
bgruening
parents:
diff changeset
84
7068d1548234 Uploaded
bgruening
parents:
diff changeset
85 -----
7068d1548234 Uploaded
bgruening
parents:
diff changeset
86
7068d1548234 Uploaded
bgruening
parents:
diff changeset
87 **Example 1**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
88
7068d1548234 Uploaded
bgruening
parents:
diff changeset
89 **Find Pattern:** HELLO
7068d1548234 Uploaded
bgruening
parents:
diff changeset
90 **Replace Pattern:** WORLD
7068d1548234 Uploaded
bgruening
parents:
diff changeset
91
7068d1548234 Uploaded
bgruening
parents:
diff changeset
92 Every time the word HELLO is found, it will be replaced with the word WORLD. This operation affects only the selected column.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
93
7068d1548234 Uploaded
bgruening
parents:
diff changeset
94 -----
7068d1548234 Uploaded
bgruening
parents:
diff changeset
95
7068d1548234 Uploaded
bgruening
parents:
diff changeset
96 **Example 2**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
97
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
98 **Find Pattern:** ^(.{4})
6
8928e6d1e7ba Uploaded
bgruening
parents: 4
diff changeset
99 **Replace Pattern:** &\\t
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
100
7068d1548234 Uploaded
bgruening
parents:
diff changeset
101 Find the first four characters in each line, and replace them with the same text, followed by a tab character. In practice - this will split the first line into two columns. This operation affects only the selected column.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
102
7068d1548234 Uploaded
bgruening
parents:
diff changeset
103
7068d1548234 Uploaded
bgruening
parents:
diff changeset
104 -----
7068d1548234 Uploaded
bgruening
parents:
diff changeset
105
7068d1548234 Uploaded
bgruening
parents:
diff changeset
106 **Extened Regular Expression Syntax**
7068d1548234 Uploaded
bgruening
parents:
diff changeset
107
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
108 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.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
109
7068d1548234 Uploaded
bgruening
parents:
diff changeset
110 - **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
111 - **^** matches the beginning of a string(but not an internal line).
7068d1548234 Uploaded
bgruening
parents:
diff changeset
112 - **(** .. **)** groups a particular pattern.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
113 - **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
114
7068d1548234 Uploaded
bgruening
parents:
diff changeset
115 - **{n}** The preceding item is matched exactly n times.
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
116 - **{n,}** The preceding item ismatched n or more times.
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
117 - **{n,m}** The preceding item is matched at least n times but not more than m times.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
118
7068d1548234 Uploaded
bgruening
parents:
diff changeset
119 - **[** ... **]** 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**.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
120 - **.** Matches any single character except a newline.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
121 - ***** The preceding item will be matched zero or more times.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
122 - **?** The preceding item is optional and matched at most once.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
123 - **+** The preceding item will be matched one or more times.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
124 - **^** has two meaning:
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
125 - matches the beginning of a line or string.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
126 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
127 - **$** matches the end of a line or string.
7
d64eace4f9f3 Uploaded
bgruening
parents: 6
diff changeset
128 - **\|** Separates alternate possibilities.
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
129
7068d1548234 Uploaded
bgruening
parents:
diff changeset
130
7068d1548234 Uploaded
bgruening
parents:
diff changeset
131 **Note**: AWK uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.
7068d1548234 Uploaded
bgruening
parents:
diff changeset
132
4
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
133 @REFERENCES@
56e80527c482 Uploaded
bgruening
parents: 3
diff changeset
134 ]]>
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
135 </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
136 <expand macro="citations" />
3
7068d1548234 Uploaded
bgruening
parents:
diff changeset
137 </tool>