diff table_pandas_rename_columns_regex.xml @ 0:505a8e975968 draft default tip

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/tables commit d0ff40eb2b536fec6c973c3a9ea8e7f31cd9a0d6
author recetox
date Wed, 29 Jan 2025 15:35:08 +0000 (3 months ago)
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/table_pandas_rename_columns_regex.xml	Wed Jan 29 15:35:08 2025 +0000
@@ -0,0 +1,82 @@
+<tool id="table_pandas_rename_columns_regex" name="table rename columns via regex" version="@PANDAS_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01" license="MIT">
+    <description>rename columns in a table using regex</description>
+    <macros>
+        <import>macros.xml</import>
+        <token name="@VERSION_SUFFIX@">0</token>
+    </macros>
+
+    <requirements>
+        <expand macro="requirement_pandas_pyarrow"/>
+    </requirements>
+
+    <required_files>
+        <include path="table_pandas_rename_columns_regex.py" />
+        <include path="utils.py" />
+    </required_files>
+
+    <expand macro="creator" />
+
+    <command detect_errors="exit_code"><![CDATA[
+        python3 '$__tool_directory__/table_pandas_rename_columns_regex.py' 
+            --input_dataset '$input_dataset' '$input_dataset.ext'
+            --columns '$columns'
+            --regex_check '$regex_check'
+            --regex_replace '$regex_replace'
+            --output_dataset '$output_dataset' '$output_dataset.ext'
+    ]]></command>
+    
+    <inputs>
+        <param name="input_dataset" type="data" format="csv,tsv,tabular,parquet" label="Input Dataset" help="The input dataset in CSV, TSV, tabular, or Parquet format."/>
+        <param name="columns" type="data_column" data_ref="input_dataset" multiple="true" use_header_names="true" min="1" label="Columns to Rename"  help="Select one or more columns from the dataset to rename. You can select columns by their header names."/>
+        <param name="regex_check" type="text" label="Regex to Check For" help="The regular expression pattern to search for in the column names. This pattern will be used to identify parts of the column names to be replaced.">
+            <expand macro="regex_sanitizer"/>
+        </param>
+        <param name="regex_replace" type="text" label="Regex to Replace With" optional="true" help="The regular expression pattern to replace the matched parts of the column names with. This pattern will be used to rename the columns.">
+            <expand macro="regex_sanitizer"/>
+        </param>
+    </inputs>
+
+    <outputs>
+        <data name="output_dataset" format_source="input_dataset" label="${tool.name} on ${on_string}">
+            <change_format>
+                <when input="input_dataset.ext" value="tsv" format="tabular" />
+            </change_format>
+        </data>
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="input_dataset" value="rename/reference_both_renamed.tabular" ftype="tabular"/>
+            <param name="columns" value="1,2"/>
+            <param name="regex_check" value="retention_"/>
+            <param name="regex_replace" value=""/>
+            <output name="output_dataset" ftype="tabular">
+                <assert_contents>
+					<has_text text="retention" negate="true"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+This tool renames columns in a table using the specified regex patterns.
+
+Inputs
+------
+
+- **Input Dataset**: The input dataset in CSV, TSV, tabular, or Parquet format.
+- **Columns to Rename**: Select one or more columns from the dataset to rename. You can select columns by their header names.
+- **Regex to Check For**: The regular expression pattern to search for in the column names. This pattern will be used to identify parts of the column names to be replaced.
+- **Regex to Replace With**: The regular expression pattern to replace the matched parts of the column names with. This pattern will be used to rename the columns.
+
+Outputs
+-------
+
+- **Output Dataset**: The output dataset with the renamed columns.
+    ]]></help>
+
+    <citations>
+        <citation type="doi">10.5281/zenodo.3509134</citation>
+        <citation type="doi">10.25080/Majora-92bf1922-00a</citation>
+    </citations>
+</tool>
\ No newline at end of file