Mercurial > repos > nml > csvtk_replace
diff replace.xml @ 0:1d4ee4308d99 draft default tip
"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"
| author | nml |
|---|---|
| date | Tue, 19 May 2020 17:16:05 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/replace.xml Tue May 19 17:16:05 2020 -0400 @@ -0,0 +1,256 @@ +<tool id="csvtk_replace" name="csvtk-replace" version="@VERSION@+@GALAXY_VERSION@"> + <description> data of selected columns by regular expression</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="version_cmd" /> + <command detect_errors="exit_code"><![CDATA[ + +################### +## Start Command ## +################### +csvtk replace --num-cpus "\${GALAXY_SLOTS:-1}" + + ## Add additional flags as specified ## + ####################################### + $ignore_case + $global_param.illegal_rows + $global_param.empty_rows + $global_param.header + $global_param.lazy_quotes + + ## Set Tabular input/output flag if first input is tabular ## + ############################################################# + #if $in_1.is_of_type("tabular"): + -t -T + #end if + + ## Set input files ## + ##################### + '$in_1' + + ## Specify fields to use ## + ########################### + -F -f '${column_text.in_text}' + + ## Specific Commands ## + ####################### + -p '($pattern_string)' + -r '$replacement_string' + + #if $input_kv + -k '$input_kv' + #end if + + #if $fill.how_fill == "key" + -K + #elif $fill.how_fill == "string" + --key-miss-repl '$fill.fill_string' + #end if + + ## To output ## + ############### + > replaced + + ]]></command> + <inputs> + <expand macro="singular_input"/> + <expand macro="fields_input" /> + <param name="pattern_string" type="text" argument="-p" + label="Pattern Regex" + help="Regex to search column for. Input is structured as '(YOUR_INPUT_HERE)' so if your regex was just a period it would look like '(.)' as an input."> + <expand macro="text_sanitizer" /> + </param> + <param name="replacement_string" type="text" argument="-r" + label="Replacement String"> + <help> + <![CDATA[ + String to replace found data. Supports capture variables and special replacement symbols. + + - Capture Variables: $1 represents the text of the first submatch + - {nr} inserts a record number starting from 1 + - {kv} uses corresponding value of the key (captured variable $n) of a key-value file + + If using the special replacement symbols, the capture variable must be specified as ${1}! + ]]> + </help> + <expand macro="text_sanitizer" /> + </param> + <param name="input_kv" type="data" format="tsv,tabular" argument="-k" + optional="true" + label="Key/Value file for replacement string" + help="Only specify a file if using {kv} in replacement string. The file must be tab delimited with one key/value pair per line. + An example can be found in the help section below" + /> + <conditional name="fill"> + <param name="how_fill" type="select" label="Fill columns that don't get any regex matches"> + <option value="no">No</option> + <option value="key">Yes - Fill with Original Value</option> + <option value="string">Yes - Fill with String</option> + </param> + <when value="no" /> + <when value="key" /> + <when value="string" > + <param name="fill_string" type="text" value="NA" argument="--key-miss-repl" label="Fill string"> + <expand macro="text_sanitizer" /> + </param> + </when> + </conditional> + <expand macro="ignore_case" /> + <expand macro="global_parameters" /> + </inputs> + <outputs> + <data format_source="in_1" name="replaced" from_work_dir="replaced" label='${in_1.name} with column ${column_text.in_text} replaced' /> + </outputs> + <tests> + <test> + <param name="in_1" value="replace_input.csv" /> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="pattern_string" value=".+" /> + <param name="replacement_string" value="{nr}-$1" /> + <output name="replaced" value="replace_1.csv" /> + </test> + <test> + <param name="in_1" value="replace_input.csv" /> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="pattern_string" value=".+" /> + <param name="replacement_string" value="{kv}" /> + <param name="input_kv" value="kv.txt" /> + <conditional name="fill"> + <param name="how_fill" value="key" /> + </conditional> + <output name="replaced" value="replace_2.csv" /> + </test> + </tests> + <help><![CDATA[ + +Csvtk - Replace Help +-------------------- + +Info +#### +Csvtk-replace is a tool that uses Regular Expressions (Regex) to match data in the specified column and replace it with the replacement string. +Non-matched columns can be kept or filled with the Regex key or an input string + +The regex input for this tool is structured such that your regular expression **does not** need to start with with quotes or brackets. You can +start your expression with a `^` or just go straight into it + +For example: + +:: + + Using `.+` as an input would be used in the code as '(.+)' + + Using ^(.+)$ as an input would yield an input in the code as '(^(.+)$)' + +.. class:: warningmark + + Single quotes are not allowed in text inputs! + +----- + + +@HELP_INPUT_DATA@ + + +Usage +##### +You can use csvtk replace to any matched regex expressions with your input replacement string. + +The replacement string has some unique properties that you can use too to better replace your data: + +- Replacement supports capture variables, like $1 which represents the text of the first submatch of the Regex + +- \{nr} can be used to assign ascending numbers starting from 1 to each column + +- \{kv} can be used to get the value of the key (captured variable $n) or a key-value file + +A good Regular expressions cheat sheet that you can use to help yourself build regular expressions can be found at: +https://regexr.com/ + +**Replace Examples** + +1. Replacement with {nr} and $1 + +Input file: + ++---------+--------+ +| Name | Animal | ++=========+========+ +| Bud | Dog | ++---------+--------+ +| Mittens | Cat | ++---------+--------+ + +Now if our regex was set to '.*' on column 2 and our replacement string was set to '{nr}-$1', the following output would be observed: + ++---------+--------+ +| Name | Animal | ++=========+========+ +| Bud | 1-Dog | ++---------+--------+ +| Mittens | 2-Cat | ++---------+--------+ + +--------------- + +2. Replacement with {kv} file + +Suppose you set up a key-value TAB separated file that looked as such: + +:: + + Key Value + Dog Big + Cat Small + +And had a similar input file: + ++---------+--------+ +| Name | Animal | ++=========+========+ +| Bud | Dog | ++---------+--------+ +| Mittens | Cat | ++---------+--------+ +| Fuzzy | Gerbil | ++---------+--------+ + +Now if the regex was '.*' on column 2 with the replacement string as '{kv}'. Your output would look as such with 'No' fill specified: + ++---------+--------+ +| Name | Animal | ++=========+========+ +| Bud | Big | ++---------+--------+ +| Mittens | Small | ++---------+--------+ +| Fuzzy | | ++---------+--------+ + +If you wanted to fill the blank cell you could set it to either: + +- String - the string you input (ex. 'NA') would fill up the blank cell. + +- Original value - would change the blank cell to 'Gerbil' + +---- + +If your having trouble with the regular expressions, please play around with a builder, there are many others online +and they are great resources to improve your regex statements or test them before use! + +---- + +@HELP_END_STATEMENT@ + + + ]]></help> + <expand macro="citations" /> +</tool> \ No newline at end of file