1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/commits/ce6691088fd5/ Changeset: ce6691088fd5 User: jmchilton Date: 2014-11-02 21:00:05+00:00 Summary: Merged in nsoranzo/galaxy-central (pull request #543) Enhancements to "Convert delimiters" and "velvetg" tools. Affected #: 4 files diff -r ddf23ee6275837e3ca25ca5c51c43ec68a7432d8 -r ce6691088fd59ff13d2566e224551ccccd7ad569 tools/filters/convert_characters.py --- a/tools/filters/convert_characters.py +++ b/tools/filters/convert_characters.py @@ -1,30 +1,18 @@ #!/usr/bin/env python #By, Guruprasad Ananda. +import optparse import re -import sys - -def stop_err(msg): - sys.stderr.write(msg) - sys.exit() - - -def main(): - if len(sys.argv) != 4: - stop_err("usage: convert_characters infile from_char outfile") - - try: - fin = open(sys.argv[1], 'r') - except: - stop_err("Input file cannot be opened for reading.") - - from_char = sys.argv[2] - - try: - fout = open(sys.argv[3], 'w') - except: - stop_err("Output file cannot be opened for writing.") +def __main__(): + parser = optparse.OptionParser() + parser.add_option('--strip', action='store_true', + help='strip leading and trailing whitespaces') + parser.add_option('--condense', action='store_true', + help='condense consecutive delimiters') + (options, args) = parser.parse_args() + if len(args) != 3: + parser.error("usage: convert_characters.py infile from_char outfile") char_dict = { 'T': '\t', @@ -38,20 +26,26 @@ 'Sc': ';' } # regexp to match 1 or more occurences. - from_ch = char_dict[from_char] + '+' + from_char = args[1] + from_ch = char_dict[from_char] + if options.condense: + from_ch += '+' + skipped = 0 + with open(args[0], 'rU') as fin: + with open(args[2], 'w') as fout: + for line in fin: + if options.strip: + line = line.strip() + else: + line = line.rstrip('\n') + try: + fout.write("%s\n" % (re.sub(from_ch, '\t', line))) + except: + skipped += 1 - for line in fin: - line = line.strip() - try: - fout.write("%s\n" % (re.sub(from_ch, '\t', line))) - except: - skipped += 1 - - fin.close() - fout.close() if skipped: print "Skipped %d lines as invalid." % skipped if __name__ == "__main__": - main() + __main__() diff -r ddf23ee6275837e3ca25ca5c51c43ec68a7432d8 -r ce6691088fd59ff13d2566e224551ccccd7ad569 tools/filters/convert_characters.xml --- a/tools/filters/convert_characters.xml +++ b/tools/filters/convert_characters.xml @@ -1,59 +1,77 @@ -<tool id="Convert characters1" name="Convert"> - <description>delimiters to TAB</description> - <command interpreter="python">convert_characters.py $input $convert_from $out_file1</command> - <inputs> - <param name="convert_from" type="select" label="Convert all"> - <option value="s">Whitespaces</option> - <option value="T">Tabs</option> - <!--<option value="Sp">Spaces</option>--> - <option value="Dt">Dots</option> - <option value="C">Commas</option> - <option value="D">Dashes</option> - <option value="U">Underscores</option> - <option value="P">Pipes</option> - <option value="Co">Colons</option> - <option value="Sc">Semicolons</option> - </param> - <param format="txt" name="input" type="data" label="in Dataset"/> - </inputs> - <outputs> - <data format="tabular" name="out_file1" /> - </outputs> - <tests> - <test> - <param name="convert_from" value="s"/> - <param name="input" value="1.bed"/> - <output name="out_file1" file="eq-convert.dat"/> - </test> - <test> - <param name="convert_from" value="s"/> - <param name="input" value="a.txt"/> - <output name="out_file1" file="a.tab"/> - </test> - </tests> - <help> - -**What it does** - -Converts all delimiters of a specified type into TABs. Consecutive characters are condensed. For example, if columns are separated by 5 spaces they will converted into 1 tab. - ------ - -**Example** - -- Input file:: - - chrX||151283558|151283724|NM_000808_exon_8_0_chrX_151283559_r|0|- - chrX|151370273|151370486|NM_000808_exon_9_0_chrX_151370274_r|0|- - chrX|151559494|151559583|NM_018558_exon_1_0_chrX_151559495_f|0|+ - chrX|151564643|151564711|NM_018558_exon_2_0_chrX_151564644_f||||0|+ - -- Converting all pipe delimiters of the above file to TABs will get:: - - chrX 151283558 151283724 NM_000808_exon_8_0_chrX_151283559_r 0 - - chrX 151370273 151370486 NM_000808_exon_9_0_chrX_151370274_r 0 - - chrX 151559494 151559583 NM_018558_exon_1_0_chrX_151559495_f 0 + - chrX 151564643 151564711 NM_018558_exon_2_0_chrX_151564644_f 0 + - -</help> -</tool> +<tool id="Convert characters1" name="Convert"> + <description>delimiters to TAB</description> + <command interpreter="python"> +convert_characters.py +#if $strip + --strip +#end if +#if $condense + --condense +#end if +$input $convert_from $out_file1 + </command> + <inputs> + <param name="convert_from" type="select" label="Convert all"> + <option value="s">Whitespaces</option> + <option value="T">Tabs</option> + <!--<option value="Sp">Spaces</option>--> + <option value="Dt">Dots</option> + <option value="C">Commas</option> + <option value="D">Dashes</option> + <option value="U">Underscores</option> + <option value="P">Pipes</option> + <option value="Co">Colons</option> + <option value="Sc">Semicolons</option> + </param> + <param format="txt" name="input" type="data" label="in Dataset"/> + <param name="strip" type="boolean" checked="true" label="Strip leading and trailing whitespaces" /> + <param name="condense" type="boolean" checked="true" label="Condense consecutive delimiters in one TAB" /> + </inputs> + <outputs> + <data format="tabular" name="out_file1" /> + </outputs> + <stdio> + <exit_code range="1:" level="fatal" /> + </stdio> + <tests> + <test> + <param name="convert_from" value="s"/> + <param name="input" value="1.bed"/> + <param name="strip" value="true" /> + <param name="condense" value="true" /> + <output name="out_file1" file="eq-convert.dat"/> + </test> + <test> + <param name="convert_from" value="s"/> + <param name="input" value="a.txt"/> + <param name="strip" value="true" /> + <param name="condense" value="true" /> + <output name="out_file1" file="a.tab"/> + </test> + </tests> + <help> + +**What it does** + +Converts all delimiters of a specified type into TABs. Consecutive delimiters can be condensed in a single TAB. + +----- + +**Example** + +- Input file:: + + chrX||151283558|151283724|NM_000808_exon_8_0_chrX_151283559_r|0|- + chrX|151370273|151370486|NM_000808_exon_9_0_chrX_151370274_r|0|- + chrX|151559494|151559583|NM_018558_exon_1_0_chrX_151559495_f|0|+ + chrX|151564643|151564711|NM_018558_exon_2_0_chrX_151564644_f||||0|+ + +- Converting all pipe delimiters of the above file to TABs and condensing delimiters will get:: + + chrX 151283558 151283724 NM_000808_exon_8_0_chrX_151283559_r 0 - + chrX 151370273 151370486 NM_000808_exon_9_0_chrX_151370274_r 0 - + chrX 151559494 151559583 NM_018558_exon_1_0_chrX_151559495_f 0 + + chrX 151564643 151564711 NM_018558_exon_2_0_chrX_151564644_f 0 + + + </help> +</tool> diff -r ddf23ee6275837e3ca25ca5c51c43ec68a7432d8 -r ce6691088fd59ff13d2566e224551ccccd7ad569 tools/sr_assembly/velvetg.xml --- a/tools/sr_assembly/velvetg.xml +++ b/tools/sr_assembly/velvetg.xml @@ -4,7 +4,6 @@ <command interpreter="python"> velvetg_wrapper.py '$input.extra_files_path' - '$contigs' '$stats' '$LastGraph' '$velvet_asm' '$unused_reads_fasta' #if $generate_amos.afg == "yes": -amos_file $generate_amos.afg #end if @@ -96,7 +95,7 @@ <when value="yes"/></conditional> - <param name="read_trkg" type="boolean" checked="false" truevalue="-read_trkg yes" falsevalue="-read_trkg no" label="track short read positions" help=" tracking of short read positions in assembly"/> + <param name="read_trkg" type="boolean" checked="false" truevalue="-read_trkg yes" falsevalue="-read_trkg no" label="Tracking of short read positions in assembly" help="Generates Graph2 dataset" /><conditional name="coverage"><param name="cutoff" type="select" label="Coverage cutoff" help=""> @@ -169,20 +168,20 @@ </conditional></inputs><outputs> - <!-- - <data format="velvet_graph" name="LastGraph" /> - --> - <data format="txt" name="LastGraph" label="${tool.name} on ${on_string}: LastGraph"> + <data format="txt" name="Graph2" label="${tool.name} on ${on_string}: Graph2" from_work_dir="Graph2"> + <filter>read_trkg is True</filter> + </data> + <data format="txt" name="LastGraph" label="${tool.name} on ${on_string}: LastGraph" from_work_dir="LastGraph"><filter>last_graph['generate_graph'] == "yes"</filter></data> - <data format="afg" name="velvet_asm" label="${tool.name} on ${on_string}: AMOS.afg"> + <data format="afg" name="velvet_asm" label="${tool.name} on ${on_string}: AMOS.afg" from_work_dir="velvet_asm.afg"><filter>generate_amos['afg'] == "yes"</filter></data> - <data format="fasta" name="unused_reads_fasta" label="${tool.name} on ${on_string}: Unused Reads"> + <data format="fasta" name="unused_reads_fasta" label="${tool.name} on ${on_string}: Unused Reads" from_work_dir="UnusedReads.fa"><filter>unused_reads['generate_unused'] == "yes"</filter></data> - <data format="tabular" name="stats" label="${tool.name} on ${on_string}: Stats"/> - <data format="fasta" name="contigs" label="${tool.name} on ${on_string}: Contigs"/> + <data format="tabular" name="stats" label="${tool.name} on ${on_string}: Stats" from_work_dir="stats.txt" /> + <data format="fasta" name="contigs" label="${tool.name} on ${on_string}: Contigs" from_work_dir="contigs.fa" /></outputs><requirements><requirement type="package">velvet</requirement> diff -r ddf23ee6275837e3ca25ca5c51c43ec68a7432d8 -r ce6691088fd59ff13d2566e224551ccccd7ad569 tools/sr_assembly/velvetg_wrapper.py --- a/tools/sr_assembly/velvetg_wrapper.py +++ b/tools/sr_assembly/velvetg_wrapper.py @@ -4,14 +4,9 @@ Classes encapsulating decypher tool. James E Johnson - University of Minnesota """ -import pkg_resources; -import logging, os, string, sys, tempfile, glob, shutil, types, urllib -import shlex, subprocess -from optparse import OptionParser, OptionGroup -from stat import * - - -log = logging.getLogger( __name__ ) +import os +import sys +import subprocess assert sys.version_info[:2] >= ( 2, 4 ) @@ -19,20 +14,15 @@ sys.stderr.write( "%s\n" % msg ) sys.exit() + def __main__(): #Parse Command Line - s = 'velvetg_wrapper.py: argv = %s\n' % (sys.argv) - # print >> sys.stderr, s # so will appear as blurb for file - argcnt = len(sys.argv) working_dir = sys.argv[1] - contigs = sys.argv[2] - stats = sys.argv[3] - LastGraph = sys.argv[4] - afgFile = sys.argv[5] - unusedReadsFile = sys.argv[6] - inputs = string.join(sys.argv[7:],' ') - cmdline = 'velvetg %s %s > /dev/null' % (working_dir, inputs) - # print >> sys.stderr, cmdline # so will appear as blurb for file + inputs = ' '.join(sys.argv[2:]) + for _ in ('Roadmaps', 'Sequences'): + os.symlink(os.path.join(working_dir, _), _) + cmdline = 'velvetg . %s' % (inputs) + print "Command to be executed: %s" % cmdline try: proc = subprocess.Popen( args=cmdline, shell=True, stderr=subprocess.PIPE ) returncode = proc.wait() @@ -50,41 +40,7 @@ raise Exception, stderr except Exception, e: stop_err( 'Error running velvetg ' + str( e ) ) - out = open(contigs,'w') - contigs_path = os.path.join(working_dir,'contigs.fa') - for line in open( contigs_path ): - out.write( "%s" % (line) ) - out.close() - out = open(stats,'w') - stats_path = os.path.join(working_dir,'stats.txt') - for line in open( stats_path ): - out.write( "%s" % (line) ) - out.close() - if LastGraph != 'None': - out = open(LastGraph,'w') - LastGraph_path = os.path.join(working_dir,'LastGraph') - for line in open( LastGraph_path ): - out.write( "%s" % (line) ) - out.close() - if afgFile != 'None': - out = open(afgFile,'w') - afgFile_path = os.path.join(working_dir,'velvet_asm.afg') - try: - for line in open( afgFile_path ): - out.write( "%s" % (line) ) - except: - logging.warn( 'error reading %s' %(afgFile_path)) - pass - out.close() - if unusedReadsFile != 'None': - out = open(unusedReadsFile,'w') - unusedReadsFile_path = os.path.join(working_dir,'UnusedReads.fa') - try: - for line in open( unusedReadsFile_path ): - out.write( "%s" % (line) ) - except: - logging.info( 'error reading %s' %(unusedReadsFile_path)) - pass - out.close() -if __name__ == "__main__": __main__() + +if __name__ == "__main__": + __main__() Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.