Source code

Download source archive ↓

upstream-extended/community/tools/text_processing/text_processing/replace_text_in_column.xml

1<tool id="tp_replace_in_column" name="Replace Text" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2    <description>in a specific column</description>
3    <macros>
4        <import>macros.xml</import>
5    </macros>
6    <expand macro="creator"/>
7    <requirements>
8        <requirement type="package" version="5.4.1">gawk</requirement>
9    </requirements>
10    <version_command>awk --version | head -n 1</version_command>
11    <command>
12<![CDATA[
13        awk
14            -v OFS="\t"
15            -v FS="\t"
16            --re-interval
17            --sandbox 
18            '{ 
19            #for $replacement in $replacements:
20                \$$replacement.column = gensub( /$replacement.find_pattern/, "$replacement.replace_pattern", "g", \$$replacement.column ) ;
21            #end for
22            print \$0 ; }'
23            '$infile'
24        > '$outfile'
25]]>
26    </command>
27    <inputs>
28        <param format="tabular" name="infile" type="data" label="File to process" />
29        <repeat name="replacements" title="Replacement" min="1">
30            <param name="column" label="in column" type="data_column" data_ref="infile" accept_default="true" />
31
32            <param name="find_pattern" type="text" label="Find pattern" help="Use simple text, or a valid regular expression (without backslashes // ) " >
33                <sanitizer>
34                    <valid initial="string.printable">
35                        <remove value="&apos;"/>
36                    </valid>
37                </sanitizer>
38            </param>
39            <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." >
40                <sanitizer>
41                    <valid initial="string.printable">
42                        <remove value="&apos;"/>
43                    </valid>
44                </sanitizer>
45            </param>
46        </repeat>
47    </inputs>
48    <outputs>
49        <data name="outfile" format_source="infile" metadata_source="infile" />
50    </outputs>
51    <tests>
52        <test>
53              <param name="infile" value="replace_text_in_column1.txt" ftype="tabular" />
54              <repeat name="replacements">
55                <param name="column" value="4" />
56                <param name="find_pattern" value=".+_(R.)" />
57                <param name="replace_pattern" value="\\1" />
58              </repeat>
59              <output name="outfile" file="replace_text_in_column_results1.txt" />
60        </test>
61        <test>
62              <param name="infile" value="replace_text_in_column1.txt" ftype="tabular" />
63              <repeat name="replacements">
64                <param name="column" value="1" />
65                <param name="find_pattern" value="[a-z]{2}([a-z])" />
66                <param name="replace_pattern" value="\\1" />
67              </repeat>
68              <repeat name="replacements">
69                <param name="column" value="4" />
70                <param name="find_pattern" value=".+_(R.)" />
71                <param name="replace_pattern" value="\\1" />
72              </repeat>
73              <output name="outfile" file="replace_text_in_column_results2.txt" />
74        </test>
75    </tests>
76    <help>
77<![CDATA[
78**What it does**
79
80This tool performs find & replace operation on a specified column in a given file.
81
82.. class:: infomark
83
84The **pattern to find** uses the **extended regular** expression syntax (same as running 'awk --re-interval').
85
86.. class:: infomark
87
88**TIP:** If you need more complex patterns, use the *awk* tool.
89
90-----
91
92
93**Examples of Find Patterns**
94
95- **HELLO**     The word 'HELLO' (case sensitive).
96- **AG.T**      The letters A,G followed by any single character, followed by the letter T.
97- **A{4,}**     Four or more consecutive A's.
98- **chr2[012]\\t**       The words 'chr20' or 'chr21' or 'chr22' followed by a tab character.
99- **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.
100
101
102**Examples of Replace Patterns**
103
104- **WORLD**  The word 'WORLD' will be placed whereever the find pattern was found.
105- **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.
106- **\\1**   The text which matched the first parenthesis in the Find Pattern.
107
108
109-----
110
111**Example 1**
112
113**Find Pattern:** HELLO
114**Replace Pattern:** WORLD
115
116Every time the word HELLO is found, it will be replaced with the word WORLD. This operation affects only the selected column.
117
118-----
119
120**Example 2**
121
122**Find Pattern:** ^(.{4})
123**Replace Pattern:** &\\t
124
125Find 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.
126
127
128-----
129
130**Extened Regular Expression Syntax**
131
132The 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.
133
134- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
135- **^** matches the beginning of a string(but not an internal line).
136- **(** .. **)** groups a particular pattern.
137- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.
138
139  - **{n}** The preceding item is matched exactly n times.
140  - **{n,}** The preceding item ismatched n or more times.
141  - **{n,m}** The preceding item is matched at least n times but not more than m times.
142
143- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**.
144- **.** Matches any single character except a newline.
145- ***** The preceding item will be matched zero or more times.
146- **?** The preceding item is optional and matched at most once.
147- **+** The preceding item will be matched one or more times.
148- **^** has two meaning:
149  - matches the beginning of a line or string.
150  - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
151- **$** matches the end of a line or string.
152- **\|** Separates alternate possibilities.
153
154
155**Note**: AWK uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.
156
157]]>
158    </help>
159    <expand macro="citations" />
160</tool>