X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fruby%2Fevoruby%2Flib%2Fevo%2Ftool%2Fphylogenies_decorator.rb;h=0459eeebc68c8aacc7e6478e911caaa8f23d74a4;hb=7e37741c149bbf6c27555ab9cf92766155d3f4d3;hp=953f924c068c954511b54cd50f105a3940bba345;hpb=b2da9d4556ac5b90e50d1460040f7387140dd49b;p=jalview.git diff --git a/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb b/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb index 953f924..0459eee 100644 --- a/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb +++ b/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb @@ -15,11 +15,9 @@ require 'lib/evo/util/constants' require 'lib/evo/util/util' require 'lib/evo/util/command_line_arguments' - require 'date' module Evoruby - class PhylogeniesDecorator #DECORATOR_OPTIONS_SEQ_NAMES = '-r=1 -mdn' @@ -30,9 +28,10 @@ module Evoruby #DECORATOR_OPTIONS_DOMAINS = '-r=1' DECORATOR_OPTIONS_DOMAINS = '-p -t' IDS_MAPFILE_SUFFIX = '.nim' - DOMAINS_MAPFILE_SUFFIX = '.dff' - SLEEP_TIME = 0.1 + DOMAINS_MAPFILE_SUFFIX = '_hmmscan_10.dff' + SLEEP_TIME = 0.05 REMOVE_NI = true + IDS_ONLY = true TMP_FILE_1 = '___PD1___' TMP_FILE_2 = '___PD2___' LOG_FILE = '00_phylogenies_decorator.log' @@ -40,29 +39,27 @@ module Evoruby JAVA_HOME = ENV[Constants::JAVA_HOME_ENV_VARIABLE] PRG_NAME = "phylogenies_decorator" - PRG_DATE = "2012.10.11" + PRG_DATE = "2013.11.15" PRG_DESC = "decoration of phylogenies with sequence/species names and domain architectures" PRG_VERSION = "1.02" - COPYRIGHT = "2012 Christian M Zmasek" + COPYRIGHT = "2013 Christian M Zmasek" CONTACT = "phylosoft@gmail.com" WWW = "https://sites.google.com/site/cmzmasek/home/software/forester" - HELP_OPTION_1 = "help" HELP_OPTION_2 = "h" NL = Constants::LINE_DELIMITER - def run Util.print_program_information( PRG_NAME, - PRG_VERSION, - PRG_DESC, - PRG_DATE, - COPYRIGHT, - CONTACT, - WWW, - STDOUT ) + PRG_VERSION, + PRG_DESC, + PRG_DATE, + COPYRIGHT, + CONTACT, + WWW, + STDOUT ) if ( ARGV == nil || ARGV.length > 3 || ARGV.length < 2 ) print_help @@ -92,7 +89,7 @@ module Evoruby end if ( cla.is_option_set?( HELP_OPTION_1 ) || - cla.is_option_set?( HELP_OPTION_2 ) ) + cla.is_option_set?( HELP_OPTION_2 ) ) print_help exit( 0 ) end @@ -101,32 +98,9 @@ module Evoruby Util.fatal_error( PRG_NAME, 'logfile [' + LOG_FILE + '] already exists' ) end - allowed_opts = Array.new - allowed_opts.push( IDS_ONLY_OPTION ) - allowed_opts.push( DOMAINS_ONLY_OPTION ) - - disallowed = cla.validate_allowed_options_as_str( allowed_opts ) - if ( disallowed.length > 0 ) - Util.fatal_error( PRG_NAME, "unknown option(s): " + disallowed ) - end - - ids_only = false - domains_only = false - in_suffix = cla.get_file_name( 0 ) out_suffix = cla.get_file_name( 1 ) - if cla.is_option_set?( IDS_ONLY_OPTION ) - ids_only = true - end - if cla.is_option_set?( DOMAINS_ONLY_OPTION ) - domains_only = true - end - - if ( ids_only && domains_only ) - Util.fatal_error( PRG_NAME, 'attempt to use ids only and domains only at the same time' ) - end - log = String.new now = DateTime.now @@ -159,10 +133,10 @@ module Evoruby files.each { | phylogeny_file | if ( !File.directory?( phylogeny_file ) && - phylogeny_file !~ /^\./ && - phylogeny_file !~ /^00/ && - phylogeny_file !~ /#{out_suffix}$/ && - phylogeny_file =~ /#{in_suffix}$/ ) + phylogeny_file !~ /^\./ && + phylogeny_file !~ /^00/ && + phylogeny_file !~ /#{out_suffix}$/ && + phylogeny_file =~ /#{in_suffix}$/ ) begin Util.check_file_for_readability( phylogeny_file ) rescue ArgumentError @@ -179,7 +153,7 @@ module Evoruby if File.exists?( outfile ) msg = counter.to_s + ': ' + phylogeny_file + ' -> ' + outfile + - ' : already exists, skipping' + ' : already exists, skipping' Util.print_message( PRG_NAME, msg ) log << msg + NL next @@ -189,20 +163,35 @@ module Evoruby log << counter.to_s + ': ' + phylogeny_file + ' -> ' + outfile + NL phylogeny_id = get_id( phylogeny_file ) + if phylogeny_id == nil || phylogeny_id.size < 1 + Util.fatal_error( PRG_NAME, 'could not get id from ' + phylogeny_file.to_s ) + end + puts + Util.print_message( PRG_NAME, "id: " + phylogeny_id ) + log << "id: " + phylogeny_id + NL ids_mapfile_name = nil domains_mapfile_name = nil seqs_file_name = nil ids_mapfile_name = get_file( files, phylogeny_id, IDS_MAPFILE_SUFFIX ) - domains_mapfile_name = get_file( files, phylogeny_id, DOMAINS_MAPFILE_SUFFIX ) - seqs_file_name = get_seq_file( files, phylogeny_id ) + unless IDS_ONLY + domains_mapfile_name = get_file( files, phylogeny_id, DOMAINS_MAPFILE_SUFFIX ) + seqs_file_name = get_seq_file( files, phylogeny_id ) + end - begin - Util.check_file_for_readability( domains_mapfile_name ) - rescue ArgumentError - Util.fatal_error( PRG_NAME, 'failed to read from [#{domains_mapfile_name}]: ' + $! ) + unless IDS_ONLY + begin + Util.check_file_for_readability( domains_mapfile_name ) + rescue ArgumentError + Util.fatal_error( PRG_NAME, 'failed to read from [#{domains_mapfile_name}]: ' + $! ) + end + begin + Util.check_file_for_readability( seqs_file_name ) + rescue ArgumentError + Util.fatal_error( PRG_NAME, 'failed to read from [#{seqs_file_name }]: ' + $! ) + end end begin @@ -211,33 +200,51 @@ module Evoruby Util.fatal_error( PRG_NAME, 'failed to read from [#{ids_mapfile_name}]: ' + $! ) end - begin - Util.check_file_for_readability( seqs_file_name ) - rescue ArgumentError - Util.fatal_error( PRG_NAME, 'failed to read from [#{seqs_file_name }]: ' + $! ) + unless IDS_ONLY + cmd = decorator + + ' -t -p -f=m ' + phylogeny_file + ' ' + + seqs_file_name + ' ' + TMP_FILE_1 + puts cmd + begin + execute_cmd( cmd, log ) + rescue Error + Util.fatal_error( PRG_NAME, 'error: ' + $! ) + end + + cmd = decorator + ' ' + DECORATOR_OPTIONS_DOMAINS + ' ' + + '-f=d ' + TMP_FILE_1 + ' ' + + domains_mapfile_name + ' ' +TMP_FILE_2 + puts cmd + begin + execute_cmd( cmd, log ) + rescue Error + Util.fatal_error( PRG_NAME, 'error: ' + $! ) + end end - cmd = decorator + - ' -p -f=m ' + phylogeny_file + ' ' + - seqs_file_name + ' ' + TMP_FILE_1 - puts cmd - execute_cmd( cmd, log ) - - cmd = decorator + ' ' + DECORATOR_OPTIONS_DOMAINS + ' ' + - '-f=d ' + TMP_FILE_1 + ' ' + - domains_mapfile_name + ' ' +TMP_FILE_2 - puts cmd - execute_cmd( cmd, log ) - - cmd = decorator + ' ' + DECORATOR_OPTIONS_SEQ_NAMES + ' ' + - '-f=n ' + TMP_FILE_2 + ' ' + - ids_mapfile_name + ' ' + outfile - puts cmd - execute_cmd( cmd, log ) - - File.delete( TMP_FILE_1 ) - File.delete( TMP_FILE_2 ) - + if IDS_ONLY + cmd = decorator + ' ' + DECORATOR_OPTIONS_SEQ_NAMES + ' ' + + '-f=n ' + phylogeny_file + ' ' + + ids_mapfile_name + ' ' + outfile + puts cmd + begin + execute_cmd( cmd, log ) + rescue Error + Util.fatal_error( PRG_NAME, 'error: ' + $! ) + end + else + cmd = decorator + ' ' + DECORATOR_OPTIONS_SEQ_NAMES + ' ' + + '-f=n ' + TMP_FILE_2 + ' ' + + ids_mapfile_name + ' ' + outfile + puts cmd + begin + execute_cmd( cmd, log ) + rescue Error + Util.fatal_error( PRG_NAME, 'error: ' + $! ) + end + File.delete( TMP_FILE_1 ) + File.delete( TMP_FILE_2 ) + end end } open( LOG_FILE, 'w' ) do | f | @@ -249,7 +256,7 @@ module Evoruby end # def run def execute_cmd( cmd, log ) - log << 'excuting ' + cmd + NL + log << 'executing ' + cmd + NL IO.popen( cmd , 'r+' ) do | pipe | pipe.close_write log << pipe.read + NL + NL @@ -257,41 +264,36 @@ module Evoruby sleep( SLEEP_TIME ) end - def get_id( phylogeny_file_name ) - phylogeny_file_name =~ /^([^_]+)/ - $1 + if phylogeny_file_name =~ /^(.+?_.+?)_/ + return $1 + elsif phylogeny_file_name =~ /^(.+?)__/ + return $1 + elsif phylogeny_file_name =~ /^(.+?)_/ + return $1 + end + nil end def get_file( files_in_dir, phylogeny_id, suffix_pattern ) matching_files = Array.new - matching_suffix_files = Array.new + files_in_dir.each { | file | if ( !File.directory?( file ) && - file !~ /^\./ && - file !~ /^00/ && - file =~ /^#{phylogeny_id}.*#{suffix_pattern}$/ ) + file !~ /^\./ && + file !~ /^00/ && + file =~ /^#{phylogeny_id}.*#{suffix_pattern}$/ ) matching_files << file end - if ( !File.directory?( file ) && - file !~ /^\./ && - file !~ /^00/ && - file =~ /#{suffix_pattern}$/ ) - matching_suffix_files << file - end } - if matching_files.length < 1 && matching_suffix_files.length == 1 - return matching_suffix_files[ 0 ] - end - - if matching_files.length < 1 && matching_suffix_files.length < 1 + if matching_files.length < 1 Util.fatal_error( PRG_NAME, 'no file matching [' + phylogeny_id + - '_] [' + suffix_pattern + '] present in current directory' ) + '...' + suffix_pattern + '] present in current directory' ) end if matching_files.length > 1 - Util.fatal_error( PRG_NAME, 'more than one file matching [' + phylogeny_id + - '_] [' + suffix_pattern + '] present in current directory' ) + Util.fatal_error( PRG_NAME, 'more than one file matching [' + + phylogeny_id + '...' + suffix_pattern + '] present in current directory' ) end matching_files[ 0 ] end @@ -302,24 +304,24 @@ module Evoruby files_in_dir.each { | file | if ( !File.directory?( file ) && - file !~ /^\./ && - file !~ /^00/ && - file =~ /^#{phylogeny_id}.+\d$/ ) + file !~ /^\./ && + file !~ /^00/ && + ( file =~ /^#{phylogeny_id}__.+\d$/ || file =~ /^#{phylogeny_id}_.*\.fasta$/ ) ) matching_files << file end - } if matching_files.length < 1 - Util.fatal_error( PRG_NAME, 'no seq file matching [' + phylogeny_id + '] present in current directory' ) + Util.fatal_error( PRG_NAME, 'no seq file matching [' + + phylogeny_id + '_] present in current directory' ) end if matching_files.length > 1 - Util.fatal_error( PRG_NAME, 'more than one seq file matching [' + phylogeny_id + '] present in current directory' ) + Util.fatal_error( PRG_NAME, 'more than one seq file matching [' + + phylogeny_id + '_] present in current directory' ) end matching_files[ 0 ] end - def print_help() puts( "Usage:" ) puts()