| Previous changeset 4:6e8d94597139 (2020-07-15) Next changeset 6:13b6f0007d9e (2021-01-25) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/column_maker commit a993d43d9d1702a6cf584683cf72527a3f999236" |
|
modified:
column_maker.py column_maker.xml |
| b |
| diff -r 6e8d94597139 -r 9cd341095afd column_maker.py --- a/column_maker.py Wed Jul 15 10:38:50 2020 -0400 +++ b/column_maker.py Wed Dec 30 00:50:15 2020 +0000 |
| [ |
| @@ -5,31 +5,48 @@ original file. The tool will skip over invalid lines within the file, informing the user about the number of lines skipped. """ -from __future__ import print_function +import argparse +import json import re -import sys - -assert sys.version_info[:2] >= (2, 4) -inp_file = sys.argv[1] -out_file = sys.argv[2] -expr = sys.argv[3] -round_result = sys.argv[4] +parser = argparse.ArgumentParser() +parser.add_argument('input', type=argparse.FileType('r'), help="input file") +parser.add_argument('output', type=argparse.FileType('wt'), help="output file") +parser.add_argument('cond', nargs='?', type=str, help="expression") +parser.add_argument('round', nargs='?', type=str, choices=['yes', 'no'], + help="round result") +parser.add_argument('columns', nargs='?', type=int, help="number of columns") +parser.add_argument('column_types', nargs='?', type=str, help="comma separated list of column types") +parser.add_argument('avoid_scientific_notation', nargs='?', type=str, choices=['yes', 'no'], + help="avoid scientific notation") +parser.add_argument('--load_json', default=None, type=argparse.FileType('r'), + help="overwrite parsed arguments from json file") +args = parser.parse_args() + +argparse_dict = vars(args) +if args.load_json: + json_dict = json.load(args.load_json) + argparse_dict.update(json_dict) + +fh = argparse_dict['input'] +out = argparse_dict['output'] +expr = argparse_dict['cond'] +round_result = argparse_dict['round'] try: - in_columns = int(sys.argv[5]) + in_columns = int(argparse_dict['columns']) except Exception: exit("Missing or invalid 'columns' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data.") if in_columns < 2: # To be considered tabular, data must fulfill requirements of the sniff.is_column_based() method. exit("Missing or invalid 'columns' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data.") try: - in_column_types = sys.argv[6].split(',') + in_column_types = argparse_dict['column_types'].split(',') except Exception: exit("Missing or invalid 'column_types' metadata value, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data.") if len(in_column_types) != in_columns: exit("The 'columns' metadata setting does not conform to the 'column_types' metadata setting, click the pencil icon in the history item and select the Auto-detect option to correct it. This tool can only be used with tab-delimited data.") -avoid_scientific_notation = sys.argv[7] +avoid_scientific_notation = argparse_dict['avoid_scientific_notation'] # Unescape if input has been escaped mapped_str = { @@ -74,7 +91,6 @@ invalid_line = None lines_kept = 0 total_lines = 0 -out = open(out_file, 'wt') # Read input file, skipping invalid lines, and perform computation that will result in a new column code = ''' @@ -89,7 +105,6 @@ ) from numpy import format_float_positional -fh = open(inp_file) for i, line in enumerate(fh): total_lines += 1 line = line.rstrip('\\r\\n') |
| b |
| diff -r 6e8d94597139 -r 9cd341095afd column_maker.xml --- a/column_maker.xml Wed Jul 15 10:38:50 2020 -0400 +++ b/column_maker.xml Wed Dec 30 00:50:15 2020 +0000 |
| [ |
| b'@@ -1,164 +1,170 @@\n-<tool id="Add_a_column1" name="Compute" version="1.3.1">\r\n- <description>an expression on every row</description>\r\n- <requirements>\r\n- <requirement type="package" version="2.7.13">python</requirement>\r\n- <requirement type="package" version="4.4">sed</requirement>\r\n- <requirement type="package" version="1.14">numpy</requirement>\r\n- </requirements>\r\n- <command detect_errors="aggressive"><![CDATA[\r\n- #if $header_lines_conditional.header_lines_select == "yes":\r\n- (sed -n \'1,1p\' \'$input\' | sed "s|$|%${header_lines_conditional.header_new_column_name}|" | tr "%" "\\t") > header &&\r\n- sed \'1,1d\' \'$input\' > data &&\r\n- #else:\r\n- touch header &&\r\n- ln -s \'$input\' data &&\r\n- #end if\r\n-\r\n- python \'$__tool_directory__/column_maker.py\'\r\n- data column_maker_output\r\n- "$cond"\r\n- $round\r\n- ${input.metadata.columns}\r\n- "${input.metadata.column_types}"\r\n- $avoid_scientific_notation &&\r\n- cat header column_maker_output > \'$out_file1\'\r\n- ]]></command>\r\n- <inputs>\r\n- <param name="cond" type="text" value="c3-c2" label="Add expression"/>\r\n- <param format="tabular" name="input" type="data" label="as a new column to" help="Dataset missing? See TIP below"/>\r\n- <param name="round" type="select" label="Round result?">\r\n- <option value="no">NO</option>\r\n- <option value="yes">YES</option>\r\n- </param>\r\n- <conditional name="header_lines_conditional">\r\n- <param name="header_lines_select" type="select" label="Skip a header line" help="# characters are already considered as comments and kept" >\r\n- <option value="no" >no</option>\r\n- <option value="yes" >yes</option>\r\n- </param>\r\n- <when value="no">\r\n- </when>\r\n- <when value="yes">\r\n- <param name="header_new_column_name" type="text" value="New Column" label="The new column name" />\r\n- </when>\r\n- </conditional>\r\n- <param name="avoid_scientific_notation" type="select" label="Avoid scientific notation" help="If yes, use fully expanded decimal representation when writing new columns (use only if expression produces decimal numbers).">\r\n- <option value="no">no</option>\r\n- <option value="yes">yes</option>\r\n- </param>\r\n- </inputs>\r\n- <outputs>\r\n- <data format_source="input" name="out_file1" metadata_source="input"/>\r\n- </outputs>\r\n- <tests>\r\n- <test>\r\n- <param name="cond" value="c3-c2"/>\r\n- <param name="input" value="1.bed"/>\r\n- <param name="round" value="no"/>\r\n- <output name="out_file1" file="column_maker_out1.interval"/>\r\n- </test>\r\n- <test>\r\n- <param name="cond" value="c4*1"/>\r\n- <param name="input" value="1.interval"/>\r\n- <param name="round" value="no"/>\r\n- <output name="out_file1" file="column_maker_out2.interval"/>\r\n- </test>\r\n- <test>\r\n- <param name="cond" value="c4*1"/>\r\n- <param name="input" value="1.header.tsv"/>\r\n- <param name="round" value="no"/>\r\n- <conditional name="header_lines_conditional">\r\n- <param name="header_lines_select" value="yes" />\r\n- <param name="header_new_column_name" value="value1_again" />\r\n- </conditional>\r\n- <output name="out_file1" file="column_maker_out2.header.tsv"/>\r\n- </test>\r\n- <test>\r\n- <param name="cond" value="c4*1"/>\r\n- <param name="input" value="1.interval"/>\r\n- <param name="round" value="yes"/>\r\n- <output name="out_file1" file="column_maker_out3.interval"/>\r\n- </test>\r\n- <test>\r\n- <param name="cond" value="float(.0000000000001)"/>\r\n- <param n'..b'" name="out_file1" metadata_source="input"/>\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="cond" value="c3-c2"/>\n+ <param name="input" value="1.bed"/>\n+ <param name="round" value="no"/>\n+ <output name="out_file1" file="column_maker_out1.interval"/>\n+ </test>\n+ <test>\n+ <param name="cond" value="c4*1"/>\n+ <param name="input" value="1.interval"/>\n+ <param name="round" value="no"/>\n+ <output name="out_file1" file="column_maker_out2.interval"/>\n+ </test>\n+ <test>\n+ <param name="cond" value="c4*1"/>\n+ <param name="input" value="1.header.tsv"/>\n+ <param name="round" value="no"/>\n+ <conditional name="header_lines_conditional">\n+ <param name="header_lines_select" value="yes" />\n+ <param name="header_new_column_name" value="value1_again" />\n+ </conditional>\n+ <output name="out_file1" file="column_maker_out2.header.tsv"/>\n+ </test>\n+ <test>\n+ <param name="cond" value="c4*1"/>\n+ <param name="input" value="1.interval"/>\n+ <param name="round" value="yes"/>\n+ <output name="out_file1" file="column_maker_out3.interval"/>\n+ </test>\n+ <test>\n+ <param name="cond" value="float(.0000000000001)"/>\n+ <param name="input" value="1.bed"/>\n+ <param name="round" value="no"/>\n+ <output name="out_file1">\n+ <assert_contents>\n+ <has_text text="CCDS10397" />\n+ <has_text text="1e-13" />\n+ </assert_contents>\n+ </output>\n+ </test>\n+ <test>\n+ <param name="cond" value="float(.0000000000001)"/>\n+ <param name="input" value="1.bed"/>\n+ <param name="round" value="no"/>\n+ <param name="avoid_scientific_notation" value="yes"/>\n+ <output name="out_file1">\n+ <assert_contents>\n+ <has_text text="CCDS10397" />\n+ <has_text text=".0000000000001" />\n+ <not_has_text text="1e-13" />\n+ </assert_contents>\n+ </output>\n+ </test>\n+ </tests>\n+ <help>\n+\n+ .. class:: infomark\n+\n+**TIP:** If your data is not TAB delimited, use *Text Manipulation->Convert*\n+\n+-----\n+\n+**What it does**\n+\n+This tool computes an expression for every row of a dataset and appends the result as a new column (field).\n+\n+- Columns are referenced with **c** and a **number**. For example, **c1** refers to the first column of a tab-delimited file\n+\n+- **c3-c2** will add a length column to the dataset if **c2** and **c3** are start and end position\n+\n+-----\n+\n+**Example**\n+\n+If this is your input::\n+\n+ chr1 151077881 151077918 2 200 -\n+ chr1 151081985 151082078 3 500 +\n+\n+computing "c4*c5" will produce::\n+\n+ chr1 151077881 151077918 2 200 - 400.0\n+ chr1 151081985 151082078 3 500 + 1500.0\n+\n+if, at the same time, "Round result?" is set to **YES** results will look like this::\n+\n+ chr1 151077881 151077918 2 200 - 400\n+ chr1 151081985 151082078 3 500 + 1500\n+\n+You can also use this tool to evaluate expressions. For example, computing "c3>=c2" for Input will result in the following::\n+\n+ chr1 151077881 151077918 2 200 - True\n+ chr1 151081985 151082078 3 500 + True\n+\n+or computing "type(c2)==type(\'\') for Input will return::\n+\n+ chr1 151077881 151077918 2 200 - False\n+ chr1 151081985 151082078 3 500 + False\n+\n+\n+The following built-in functions are available::\n+\n+ abs | all | any | bin | bool | chr | ceil | cmp | complex\n+\n+ divmod | exp | float | log | log10 | floor | hex | int | len | long\n+\n+ max | min | oct | ord | pow | range | reversed\n+\n+ round | sorted | sqrt | str | sum | type | unichr | unicode |\n+\n+ </help>\n+ <citations />\n+</tool>\n' |