Mercurial > repos > bgruening > text_processing
diff find_and_replace.xml @ 0:5314e5d6f040 draft
Imported from capsule None
author | bgruening |
---|---|
date | Thu, 29 Jan 2015 07:53:17 -0500 |
parents | |
children | 37e1eb05b1b4 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/find_and_replace.xml Thu Jan 29 07:53:17 2015 -0500 @@ -0,0 +1,178 @@ +<tool id="tp_find_and_replace" name="Replace" version="@BASE_VERSION@.0"> + <description>parts of text</description> + <macros> + <import>macros.xml</import> + </macros> + <command interpreter="perl"> +<![CDATA[ + find_and_replace + #if $searchwhere.searchwhere_select == "column": + -c $searchwhere.column + #end if + -o $outfile + $caseinsensitive + $wholewords + $skip_first_line + $is_regex + '$find_pattern' + '$replace_pattern' + '$infile' +]]> + </command> + <inputs> + <param name="infile" format="txt" type="data" label="File to process" /> + <param name="find_pattern" type="text" size="20" label="Find pattern" help="Use simple text, or a valid regular expression (without backslashes // ) " > + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + </sanitizer> + </param> + <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." > + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + </sanitizer> + </param> + <param name="is_regex" type="boolean" checked="false" truevalue="-r" falsevalue="" + label="Find-Pattern is a regular expression" help="see help section for details." /> + + <param name="caseinsensitive" type="boolean" checked="false" truevalue="-i" falsevalue="" + label="Case-Insensitive search" help="" /> + + <param name="wholewords" type="boolean" checked="false" truevalue="-w" falsevalue="" + label="Find whole-words" help="ignore partial matches (e.g. 'apple' will not match 'snapple')" /> + + <param name="skip_first_line" type="boolean" checked="false" truevalue="-s" falsevalue="" + label="Ignore first line" help="Select this option if the first line contains column headers. Text in the line will not be replaced. " /> + + <conditional name="searchwhere"> + <param name="searchwhere_select" type="select" label="Find and Replace text in"> + <option value="line" selected="true">entire line</option> + <option value="column">specific column</option> + </param> + <when value="line" /> + <when value="column"> + <param name="column" label="in column" type="data_column" data_ref="infile" accept_default="true" /> + </when> + </conditional> + </inputs> + <outputs> + <data format_source="infile" name="outfile" metadata_source="infile" /> + </outputs> + <tests> + <test> + <param name="infile" value="find_and_replace1.txt" /> + <param name="find_pattern" value="day" /> + <param name="replace_pattern" value="great day" /> + <param name="is_regex" value="False" /> + <param name="caseinsensitive" value="False" /> + <param name="wholewords" value="True" /> + <output name="outfile" file="find_and_replace_results1.txt" /> + </test> + <test> + <param name="infile" value="find_and_replace2.txt" /> + <param name="find_pattern" value="^chr" /> + <param name="replace_pattern" value="" /> + <param name="is_regex" value="True" /> + <param name="caseinsensitive" value="False" /> + <param name="wholewords" value="False" /> + <param name="searchwhere_select" value="column" /> + <param name="column" value="3" /> + <output name="outfile" file="find_and_replace_results2.txt" /> + </test> + </tests> + <help> +<![CDATA[ +**What it does** + +This tool finds $ replaces text in an input dataset. + +.. class:: infomark + +The **pattern to find** can be a simple text string, or a perl **regular expression** string (depending on *pattern is a regex* check-box). + +.. class:: infomark + +When using regular expressions, the **replace pattern** can contain back-references ( e.g. \\1 ) + +.. class:: infomark + +This tool uses Perl regular expression syntax. + +----- + +**Examples of *regular-expression* 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-$&-BAR** Each time the find pattern is found, it will be surrounded with 'FOO-' at the begining and '-BAR' at the end. **$&** (dollar-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 +**Regular Expression:** no +**Replace what:** entire line + +Every time the word HELLO is found, it will be replaced with the word WORLD. + +----- + +**Example 2** + +**Find Pattern:** ^chr +**Replace Pattern:** (empty) +**Regular Expression:** yes +**Replace what:** column 11 + +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" + + +----- + +**Perl's Regular Expression Syntax** + +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. + +- **( ) { } [ ] . * ? + \\ ^ $** are all special characters. **\\** can be used to "escape" a special character, allowing that special character to be searched for. +- **^** matches the beginning of a string(but not an internal line). +- **(** .. **)** groups a particular pattern. +- **{** n or n, or n,m **}** specifies an expected number of repetitions of the preceding pattern. + + - **{n}** The preceding item is matched exactly n times. + - **{n,}** The preceding item ismatched n or more times. + - **{n,m}** The preceding item is matched at least n times but not more than m times. + +- **[** ... **]** creates a character class. Within the brackets, single characters can be placed. A dash (-) may be used to indicate a range such as **a-z**. +- **.** Matches any single character except a newline. +- ***** The preceding item will be matched zero or more times. +- **?** The preceding item is optional and matched at most once. +- **+** The preceding item will be matched one or more times. +- **^** has two meaning: + - matches the beginning of a line or string. + - indicates negation in a character class. For example, [^...] matches every character except the ones inside brackets. +- **$** matches the end of a line or string. +- **\\|** Separates alternate possibilities. +- **\\d** matches a single digit +- **\\w** matches a single letter or digit or an underscore. +- **\\s** matches a single white-space (space or tabs). + +@REFERENCES@ +]]> + </help> +</tool>