Mercurial > repos > artbio > sequence_format_converter
changeset 1:9ce7ccd468aa draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/sequence_format_converter commit dfecfb40f245a3cdb09dd1cfe37be4cb164ad2eb
| author | artbio |
|---|---|
| date | Fri, 16 Feb 2018 04:55:44 -0500 |
| parents | a8aacccd79a3 |
| children | f1d59113125a |
| files | sequence_format_converter.py sequence_format_converter.xml test-data/input.fastqsanger.gz |
| diffstat | 3 files changed, 35 insertions(+), 8 deletions(-) [+] |
line wrap: on
line diff
--- a/sequence_format_converter.py Mon Sep 04 07:13:28 2017 -0400 +++ b/sequence_format_converter.py Fri Feb 16 04:55:44 2018 -0500 @@ -40,7 +40,7 @@ try: for l in range(4): block.append(input.readline()[:-1]) - except: + except IndexError: logging.info("File hasn't at leat four lines !") sys.exit("File hasn't at leat four lines !") input.close() @@ -81,7 +81,7 @@ if line[0] == '>': int(line.split('_')[-1]) return 'fastaw' - except: + except ValueError: return 'fasta' if line1[0] == '@' and line3[0] == '+': nucleotides = set([base for base in line2]) @@ -98,7 +98,7 @@ sys.exit('No valid format detected') try: int(line.split('\t')[-1]) - except: + except ValueError: logging.info("No valid format detected") sys.exit('No valid format detected') for nucleotide in line.split('\t')[0]: @@ -112,22 +112,22 @@ if format == 'fasta': try: self.readfasta(input) - except: + except Exception: logging.info("an error occured while reading fasta") elif format == 'fastaw': try: self.readfastaw(input) - except: + except Exception: logging.info("an error occured while reading fastaw") elif format == 'tabular': try: self.readtabular(input) - except: + except Exception: logging.info("an error occured while reading tabular") elif format == 'fastq': try: self.readfastq(input) - except: + except Exception: logging.info("an error occured while reading fastq") else: logging.info("no valid format detected")
--- a/sequence_format_converter.xml Mon Sep 04 07:13:28 2017 -0400 +++ b/sequence_format_converter.xml Fri Feb 16 04:55:44 2018 -0500 @@ -1,10 +1,19 @@ -<tool id="sequence_format_converter" name="sequence_format_converter" version="2.0.0"> +<tool id="sequence_format_converter" name="sequence_format_converter" version="2.1.0"> <description></description> <command><![CDATA[ + #if $input.is_of_type('fastq.gz'): + gzip -dc $input > '${input}.tmp'; + python '$__tool_directory__'/sequence_format_converter.py + --input '${input}.tmp' + --output '$output' + --format '$output_format'; + rm '${input}.tmp'; + #else: python '$__tool_directory__'/sequence_format_converter.py --input '$input' --output '$output' --format '$output_format' + #end if ]]></command> <inputs> @@ -79,6 +88,24 @@ <param ftype="fasta" name="input" value="input.fastqsanger" /> <output file="fastqTofastaw.sorted.faw" name="output" sort="True" /> </test> + <test> + <!-- convertion fastq.gz to tabular --> + <param name="output_format" value="tabular" /> + <param ftype="fastq.gz" name="input" value="input.fastqsanger.gz" /> + <output file="fastqTotabular.sorted.tab" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastq.gz to fasta --> + <param name="output_format" value="fasta" /> + <param ftype="fastq.gz" name="input" value="input.fastqsanger.gz" /> + <output file="fastqTofasta.sorted.fa" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastq.gz to fastaw --> + <param name="output_format" value="fastaw" /> + <param ftype="fastq.gz" name="input" value="input.fastqsanger.gz" /> + <output file="fastqTofastaw.sorted.faw" name="output" sort="True" /> + </test> </tests>