upstream-extended/community/tools/text_processing/text_processing/replace_text_in_line.xml
1<tool id="tp_replace_in_line" name="Replace Text" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>in entire line</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="creator"/>
7 <requirements>
8 <requirement type="package" version="4.9">sed</requirement>
9 </requirements>
10 <version_command>sed --version | head -n 1</version_command>
11 <command>
12<![CDATA[
13 sed
14 -r
15 --sandbox
16 #for $replacement in $replacements:
17 -e '$replacement.sed_options'
18 -e
19 's/$replacement.find_pattern/$replacement.replace_pattern/g'
20 #end for
21 '$infile'
22 > '$outfile'
23]]>
24
25 </command>
26 <inputs>
27 <param format="txt" name="infile" type="data" label="File to process" />
28 <repeat name="replacements" title="Replacement" min="1">
29 <param name="find_pattern" type="text" label="Find pattern" help="Use simple text, or a valid regular expression">
30 <sanitizer>
31 <valid initial="string.printable">
32 <remove value="'"/>
33 <remove value="/"/>
34 </valid>
35 <mapping initial="none">
36 <add source="'" target="'"'"'" />
37 <add source="/" target="\/"/>
38 </mapping>
39 </sanitizer>
40 </param>
41 <param name="replace_pattern" type="text" label="Replace with:" help="Use simple text, or & (ampersand) and \1, \2, \3, etc. to refer to matched text. See examples below." >
42 <sanitizer>
43 <valid initial="string.printable">
44 <remove value="'"/>
45 <remove value="/"/>
46 </valid>
47 <mapping initial="none">
48 <add source="'" target="'"'"'" />
49 <add source="/" target="\/"/>
50 </mapping>
51 </sanitizer>
52 </param>
53 <param name="sed_options" type="text" optional="true" label="Additional sed commands before replacement" help="Provide additional sed commands before the replacement (e.g., ':a;N;$!ba;')." >
54 <sanitizer>
55 <valid initial="string.printable">
56 <remove value="'"/> <!-- Removes single quotes -->
57 <remove value="/"/> <!-- Removes slashes -->
58 </valid>
59 <mapping initial="none">
60 <add source="'" target="'"'"'" /> <!-- Escapes single quotes -->
61 <add source="/" target="\/"/> <!-- Escapes slashes -->
62 </mapping>
63 </sanitizer>
64 </param>
65 </repeat>
66 </inputs>
67 <outputs>
68 <data name="outfile" format_source="infile" metadata_source="infile"/>
69 </outputs>
70 <tests>
71 <test>
72 <param name="infile" value="replace_text_in_line1.txt" />
73 <repeat name="replacements">
74 <param name="find_pattern" value="CTC." />
75 <param name="replace_pattern" value="FOOBAR" />
76 <param name="sed_options" value="" />
77 </repeat>
78 <output name="outfile" file="replace_text_in_line_results1.txt" />
79 </test>
80 <test>
81 <param name="infile" value="replace_text_in_line1.txt" />
82 <repeat name="replacements">
83 <param name="find_pattern" value="CTC." />
84 <param name="replace_pattern" value="FOOBAR" />
85 <param name="sed_options" value="" />
86 </repeat>
87 <repeat name="replacements">
88 <param name="find_pattern" value="chr" />
89 <param name="replace_pattern" value="domain" />
90 <param name="sed_options" value="" />
91 </repeat>
92 <output name="outfile" file="replace_text_in_line_results2.txt" />
93 </test>
94 <test>
95 <param name="infile" value="replace_text_in_line1.txt" />
96 <repeat name="replacements">
97 <param name="find_pattern" value="\n" />
98 <param name="replace_pattern" value="" />
99 <param name="sed_options" value=":a;N;$!ba" />
100 </repeat>
101 <output name="outfile" file="replace_text_in_line_results3.txt" />
102 </test>
103 </tests>
104 <help>
105<![CDATA[
106**What it does**
107
108This tool performs find & replace operation on a specified file.
109
110.. class:: infomark
111
112The **pattern to find** uses the **extended regular** expression syntax (same as running 'sed -r').
113
114.. class:: infomark
115
116**TIP:** If you need more complex patterns, use the *sed* tool.
117
118-----
119
120**Examples of Find Patterns**
121
122- **HELLO** The word 'HELLO' (case sensitive).
123- **AG.T** The letters A,G followed by any single character, followed by the letter T.
124- **A{4,}** Four or more consecutive A's.
125- **chr2[012]\\t** The words 'chr20' or 'chr21' or 'chr22' followed by a tab character.
126- **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.
127
128
129**Examples of Replace Patterns**
130
131- **WORLD** The word 'WORLD' will be placed whereever the find pattern was found.
132- **FOO-&-BAR** Each time the find pattern is found, it will be surrounded with 'FOO-' at the beginning and '-BAR' at the end. **&** (ampersand) represents the matched find pattern.
133- **\\1** The text which matched the first parenthesis in the Find Pattern.
134
135
136-----
137
138**Example 1**
139
140**Find Pattern:** HELLO
141**Replace Pattern:** WORLD
142
143Every time the word HELLO is found, it will be replaced with the word WORLD.
144
145
146-----
147
148**Example 2**
149
150**Find Pattern:** ^(.{4})
151**Replace Pattern:** &\\t
152
153Find 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.
154
155
156-----
157
158**Extended Regular Expression Syntax**
159
160The 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.
161
162- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
163- **^** matches the beginning of a string(but not an internal line).
164- **(** .. **)** groups a particular pattern.
165- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
166
167 - **{n}** The preceding item is matched exactly n times.
168 - **{n,}** The preceding item ismatched n or more times.
169 - **{n,m}** The preceding item is matched at least n times but not more than m times.
170
171- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
172- **.** Matches any single character except a newline.
173- ***** The preceding item will be matched zero or more times.
174- **?** The preceding item is optional and matched at most once.
175- **+** The preceding item will be matched one or more times.
176- **^** has two meaning:
177 - matches the beginning of a line or string.
178 - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
179- **$** matches the end of a line or string.
180- **\|** Separates alternate possibilities.
181
182
183**Note**: SED uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported. However, you can use SED FAQ to perform commands using special characters.
184 More complex options can look like `sed -e '$!N;s/foo/bar/;'`. Here, `$!N;` is an optional part which you only need to set in very special cases. The `foo` part is the search string, and the `bar` part is the replacement string.
185 Please read the SED FAQ here: https://www.pement.org/sed/sedfaq3.html#s3.2
186
187]]>
188 </help>
189 <expand macro="citations" />
190</tool>