annotate replace_text_in_column.xml @ 13:0a8c6b61f0f4 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/text_processing commit 4f79443517baf378fbfe1f81be361d97f2938601

<tool id="tp_replace_in_column" name="Replace Text" version="@BASE_VERSION@.3">
    <description>in a specific column</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="4.2.0">gawk</requirement>
    </requirements>
    <version_command>awk --version | head -n 1</version_command>
    <command>
<![CDATA[
        awk
            -v OFS="\t"
            -v FS="\t"
            --re-interval
            --sandbox 
            '{ 
            #for $replacement in $replacements:
                \$$replacement.column = gensub( /$replacement.find_pattern/, "$replacement.replace_pattern", "g", \$$replacement.column ) ;
            #end for
            print \$0 ; }'
            "$infile"
        > "$outfile"
]]>
    </command>
    <inputs>
        <param format="tabular" name="infile" type="data" label="File to process" />
        <repeat name="replacements" title="Replacement" min="1">
            <param name="column" label="in column" type="data_column" data_ref="infile" accept_default="true" />

            <param name="find_pattern" type="text" label="Find pattern" help="Use simple text, or a valid regular expression (without backslashes // ) " >
                <sanitizer>
                    <valid initial="string.printable">
                        <remove value="&apos;"/>
                    </valid>
                </sanitizer>
            </param>
            <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." >
                <sanitizer>
                    <valid initial="string.printable">
                        <remove value="&apos;"/>
                    </valid>
                </sanitizer>
            </param>
        </repeat>
    </inputs>
    <outputs>
        <data name="outfile" format_source="infile" metadata_source="infile" />
    </outputs>
    <tests>
        <test>
              <param name="infile" value="replace_text_in_column1.txt" ftype="tabular" />
              <param name="column" value="4" />
              <param name="find_pattern" value=".+_(R.)" />
              <param name="replace_pattern" value="\\1" />
              <output name="outfile" file="replace_text_in_column_results1.txt" />
        </test>
        <test>
              <param name="infile" value="replace_text_in_column1.txt" ftype="tabular" />
              <repeat name="replacements">
                <param name="column" value="1" />
                <param name="find_pattern" value="[a-z]{2}([a-z])" />
                <param name="replace_pattern" value="\\1" />
              </repeat>
              <repeat name="replacements">
                <param name="column" value="4" />
                <param name="find_pattern" value=".+_(R.)" />
                <param name="replace_pattern" value="\\1" />
              </repeat>
              <output name="outfile" file="replace_text_in_column_results2.txt" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

This tool performs find & replace operation on a specified column in a given file.

.. class:: infomark

The **pattern to find** uses the **extended regular** expression syntax (same as running 'awk --re-interval').

.. class:: infomark

**TIP:** If you need more complex patterns, use the *awk* tool.

-----


**Examples of Find Patterns**

- **HELLO**     The word 'HELLO' (case sensitive).
- **AG.T**      The letters A,G followed by any single character, followed by the letter T.
- **A{4,}**     Four or more consecutive A's.
- **chr2[012]\\t**       The words 'chr20' or 'chr21' or 'chr22' followed by a tab character.
- **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.


**Examples of Replace Patterns**

- **WORLD**  The word 'WORLD' will be placed whereever the find pattern was found.
- **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.
- **\\1**   The text which matched the first parenthesis in the Find Pattern.


-----

**Example 1**

**Find Pattern:** HELLO
**Replace Pattern:** WORLD

Every time the word HELLO is found, it will be replaced with the word WORLD. This operation affects only the selected column.

-----

**Example 2**

**Find Pattern:** ^(.{4})
**Replace Pattern:** &\\t

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.


-----

**Extened Regular Expression Syntax**

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.

- **( ) { } [ ] . * ? + \ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for.
- **^** matches the beginning of a string(but not an internal line).
- **(** .. **)** groups a particular pattern.
- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern.

  - **{n}** The preceding item is matched exactly n times.
  - **{n,}** The preceding item ismatched n or more times.
  - **{n,m}** The preceding item is matched at least n times but not more than m times.

- **[** ... **]** 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**.
- **.** Matches any single character except a newline.
- ***** The preceding item will be matched zero or more times.
- **?** The preceding item is optional and matched at most once.
- **+** The preceding item will be matched one or more times.
- **^** has two meaning:
  - matches the beginning of a line or string.
  - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets.
- **$** matches the end of a line or string.
- **\|** Separates alternate possibilities.


**Note**: AWK uses extended regular expression syntax, not Perl syntax. **\\d**, **\\w**, **\\s** etc. are **not** supported.

@REFERENCES@
]]>
    </help>
    <expand macro="citations" />
</tool>