|
4
|
1 <tool id="tp_find_and_replace" name="Replace" version="@BASE_VERSION@.0">
|
|
2
|
2 <description>parts of text</description>
|
|
4
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
0
|
6 <command interpreter="perl">
|
|
4
|
7 <![CDATA[
|
|
0
|
8 find_and_replace
|
|
4
|
9 #if $searchwhere.searchwhere_select == "column":
|
|
0
|
10 -c $searchwhere.column
|
|
|
11 #end if
|
|
4
|
12 -o $outfile
|
|
0
|
13 $caseinsensitive
|
|
|
14 $wholewords
|
|
|
15 $skip_first_line
|
|
|
16 $is_regex
|
|
4
|
17 '$find_pattern'
|
|
|
18 '$replace_pattern'
|
|
|
19 '$infile'
|
|
|
20 ]]>
|
|
0
|
21 </command>
|
|
|
22 <inputs>
|
|
4
|
23 <param name="infile" format="txt" type="data" label="File to process" />
|
|
|
24 <param name="find_pattern" type="text" size="20" label="Find pattern" help="Use simple text, or a valid regular expression (without backslashes // ) " >
|
|
0
|
25 <sanitizer>
|
|
|
26 <valid initial="string.printable">
|
|
|
27 <remove value="'"/>
|
|
|
28 </valid>
|
|
|
29 </sanitizer>
|
|
|
30 </param>
|
|
4
|
31 <param name="replace_pattern" type="text" size="20" label="Replace with" help="Use simple text, or $& (dollar-ampersand) and $1 $2 $3 to refer to matched text. See examples below." >
|
|
0
|
32 <sanitizer>
|
|
|
33 <valid initial="string.printable">
|
|
|
34 <remove value="'"/>
|
|
|
35 </valid>
|
|
|
36 </sanitizer>
|
|
|
37 </param>
|
|
|
38
|
|
4
|
39 <param name="is_regex" type="boolean" checked="false" truevalue="-r" falsevalue=""
|
|
|
40 label="Find-Pattern is a regular expression" help="see help section for details." />
|
|
0
|
41
|
|
4
|
42 <param name="caseinsensitive" type="boolean" checked="false" truevalue="-i" falsevalue=""
|
|
|
43 label="Case-Insensitive search" help="" />
|
|
0
|
44
|
|
4
|
45 <param name="wholewords" type="boolean" checked="false" truevalue="-w" falsevalue=""
|
|
|
46 label="Find whole-words" help="ignore partial matches (e.g. 'apple' will not match 'snapple')" />
|
|
0
|
47
|
|
4
|
48 <param name="skip_first_line" type="boolean" checked="false" truevalue="-s" falsevalue=""
|
|
|
49 label="Ignore first line" help="Select this option if the first line contains column headers. Text in the line will not be replaced. " />
|
|
0
|
50
|
|
|
51 <conditional name="searchwhere">
|
|
4
|
52 <param name="searchwhere_select" type="select" label="Find and Replace text in">
|
|
0
|
53 <option value="line" selected="true">entire line</option>
|
|
|
54 <option value="column">specific column</option>
|
|
|
55 </param>
|
|
|
56 <when value="line" />
|
|
|
57 <when value="column">
|
|
4
|
58 <param name="column" label="in column" type="data_column" data_ref="infile" accept_default="true" />
|
|
0
|
59 </when>
|
|
|
60 </conditional>
|
|
|
61 </inputs>
|
|
|
62 <outputs>
|
|
4
|
63 <data format="input" name="outfile" metadata_source="infile" />
|
|
0
|
64 </outputs>
|
|
4
|
65 <tests>
|
|
|
66 <test>
|
|
|
67 <param name="infile" value="find_and_replace1.txt" />
|
|
|
68 <param name="find_pattern" value="day" />
|
|
|
69 <param name="replace_pattern" value="great day" />
|
|
|
70 <param name="is_regex" value="False" />
|
|
|
71 <param name="caseinsensitive" value="False" />
|
|
|
72 <param name="wholewords" value="True" />
|
|
|
73 <output name="outfile" file="find_and_replace_results1.txt" />
|
|
|
74 </test>
|
|
|
75 <test>
|
|
|
76 <param name="infile" value="find_and_replace2.txt" />
|
|
|
77 <param name="find_pattern" value="^chr" />
|
|
|
78 <param name="replace_pattern" value="" />
|
|
|
79 <param name="is_regex" value="True" />
|
|
|
80 <param name="caseinsensitive" value="False" />
|
|
|
81 <param name="wholewords" value="False" />
|
|
|
82 <param name="searchwhere_select" value="column" />
|
|
|
83 <param name="column" value="3" />
|
|
|
84 <output name="outfile" file="find_and_replace_results2.txt" />
|
|
|
85 </test>
|
|
|
86 </tests>
|
|
|
87 <help>
|
|
|
88 <![CDATA[
|
|
0
|
89 **What it does**
|
|
|
90
|
|
4
|
91 This tool finds $ replaces text in an input dataset.
|
|
0
|
92
|
|
|
93 .. class:: infomark
|
|
|
94
|
|
|
95 The **pattern to find** can be a simple text string, or a perl **regular expression** string (depending on *pattern is a regex* check-box).
|
|
|
96
|
|
|
97 .. class:: infomark
|
|
|
98
|
|
|
99 When using regular expressions, the **replace pattern** can contain back-references ( e.g. \\1 )
|
|
|
100
|
|
|
101 .. class:: infomark
|
|
|
102
|
|
|
103 This tool uses Perl regular expression syntax.
|
|
|
104
|
|
|
105 -----
|
|
|
106
|
|
|
107 **Examples of *regular-expression* Find Patterns**
|
|
|
108
|
|
|
109 - **HELLO** The word 'HELLO' (case sensitive).
|
|
|
110 - **AG.T** The letters A,G followed by any single character, followed by the letter T.
|
|
|
111 - **A{4,}** Four or more consecutive A's.
|
|
|
112 - **chr2[012]\\t** The words 'chr20' or 'chr21' or 'chr22' followed by a tab character.
|
|
|
113 - **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.
|
|
|
114
|
|
|
115
|
|
|
116 **Examples of Replace Patterns**
|
|
|
117
|
|
|
118 - **WORLD** The word 'WORLD' will be placed whereever the find pattern was found.
|
|
4
|
119 - **FOO-$&-BAR** Each time the find pattern is found, it will be surrounded with 'FOO-' at the begining and '-BAR' at the end. **$&** (dollar-ampersand) represents the matched find pattern.
|
|
0
|
120 - **$1** The text which matched the first parenthesis in the Find Pattern.
|
|
|
121
|
|
|
122
|
|
|
123 -----
|
|
|
124
|
|
|
125 **Example 1**
|
|
|
126
|
|
|
127 **Find Pattern:** HELLO
|
|
|
128 **Replace Pattern:** WORLD
|
|
|
129 **Regular Expression:** no
|
|
|
130 **Replace what:** entire line
|
|
|
131
|
|
4
|
132 Every time the word HELLO is found, it will be replaced with the word WORLD.
|
|
0
|
133
|
|
|
134 -----
|
|
|
135
|
|
|
136 **Example 2**
|
|
|
137
|
|
|
138 **Find Pattern:** ^chr
|
|
|
139 **Replace Pattern:** (empty)
|
|
|
140 **Regular Expression:** yes
|
|
|
141 **Replace what:** column 11
|
|
|
142
|
|
|
143 If column 11 (of every line) begins with ther letters 'chr', they will be removed. Effectively, it'll turn "chr4" into "4" and "chrXHet" into "XHet"
|
|
|
144
|
|
|
145
|
|
|
146 -----
|
|
|
147
|
|
|
148 **Perl's Regular Expression Syntax**
|
|
|
149
|
|
4
|
150 The Find & Replace 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
|
151
|
|
|
152 - **( ) { } [ ] . * ? + \\ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
|
|
|
153 - **^** matches the beginning of a string(but not an internal line).
|
|
|
154 - **(** .. **)** groups a particular pattern.
|
|
|
155 - **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
|
|
|
156
|
|
|
157 - **{n}** The preceding item is matched exactly n times.
|
|
|
158 - **{n,}** The preceding item ismatched n or more times.
|
|
|
159 - **{n,m}** The preceding item is matched at least n times but not more than m times.
|
|
|
160
|
|
|
161 - **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
|
|
|
162 - **.** Matches any single character except a newline.
|
|
|
163 - ***** The preceding item will be matched zero or more times.
|
|
|
164 - **?** The preceding item is optional and matched at most once.
|
|
|
165 - **+** The preceding item will be matched one or more times.
|
|
|
166 - **^** has two meaning:
|
|
|
167 - matches the beginning of a line or string.
|
|
|
168 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
|
|
|
169 - **$** matches the end of a line or string.
|
|
|
170 - **\\|** Separates alternate possibilities.
|
|
|
171 - **\\d** matches a single digit
|
|
|
172 - **\\w** matches a single letter or digit or an underscore.
|
|
|
173 - **\\s** matches a single white-space (space or tabs).
|
|
|
174
|
|
4
|
175 @REFERENCES@
|
|
|
176 ]]>
|
|
|
177 </help>
|
|
0
|
178 </tool>
|
