# HG changeset patch # User devteam # Date 1354636419 18000 # Node ID 2c08781560de79db7b9a1d163415ffffc345227a Uploaded condense_characters tarball. diff -r 000000000000 -r 2c08781560de condense_characters.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/condense_characters.pl Tue Dec 04 10:53:39 2012 -0500 @@ -0,0 +1,105 @@ +#! /usr/bin/perl -w + +use strict; +use warnings; + +# condenses all consecutive characters of one type +# convert_characters.pl [input] [character] [output] + +die "Check arguments" unless @ARGV == 3; + +my $inputfile = $ARGV[0]; +my $character = $ARGV[1]; +my $outputfile = $ARGV[2]; + + +my $convert_from; +my $convert_to; + + +if ($character eq "s") +{ + $convert_from = '\s'; +} +elsif ($character eq "T") +{ + $convert_from = '\t'; +} +elsif ($character eq "Sp") +{ + $convert_from = " "; +} +elsif ($character eq "Dt") +{ + $convert_from = '\.'; +} +elsif ($character eq "C") +{ + $convert_from = ","; +} +elsif ($character eq "D") +{ + $convert_from = "-"; +} +elsif ($character eq "U") +{ + $convert_from = "_"; +} +elsif ($character eq "P") +{ + $convert_from = '\|'; +} +else +{ + die "Invalid value specified for convert from\n"; +} + + +if ($character eq "T") +{ + $convert_to = "\t"; +} +elsif ($character eq "Sp") +{ + $convert_to = " "; +} +elsif ($character eq "Dt") +{ + $convert_to = "\."; +} +elsif ($character eq "C") +{ + $convert_to = ","; +} +elsif ($character eq "D") +{ + $convert_to = "-"; +} +elsif ($character eq "U") +{ + $convert_to = "_"; +} +elsif ($character eq "P") +{ + $convert_to = "|"; +} +else +{ + die "Invalid value specified for Convert to\n"; +} + +my $fhIn; +open ($fhIn, "< $inputfile") or die "Cannot open source file"; + +my $fhOut; +open ($fhOut, "> $outputfile"); + +while (<$fhIn>) +{ + my $thisLine = $_; + chomp $thisLine; + $thisLine =~ s/${convert_from}+/$convert_to/g; + print $fhOut $thisLine,"\n"; +} +close ($fhIn) or die "Cannot close source file"; +close ($fhOut) or die "Cannot close output file"; diff -r 000000000000 -r 2c08781560de condense_characters.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/condense_characters.xml Tue Dec 04 10:53:39 2012 -0500 @@ -0,0 +1,48 @@ + + consecutive characters + condense_characters.pl $input $character $out_file1 + + + + + + + + + + + + + + + + + + + + + + + + + +**What it does** + +This tool condenses all consecutive characters of a specified type. + +----- + +**Example** + +- Input file:: + + geneX,,,10,,,,,20 + geneY,,5,,,,,12,15,9, + +- Condense all consecutive commas. The above file will be converted into:: + + geneX,10,20 + geneY,5,12,15,9 + + + diff -r 000000000000 -r 2c08781560de test-data/1.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/1.bed Tue Dec 04 10:53:39 2012 -0500 @@ -0,0 +1,65 @@ +chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - +chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + +chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - +chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + +chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - +chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - +chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + +chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - +chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + +chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - +chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + +chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - +chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - +chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + +chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - +chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + +chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + +chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - +chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + +chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - +chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - +chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + +chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - +chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + +chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + +chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - +chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + +chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - +chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + +chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - +chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + +chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - +chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - +chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + +chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - +chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + +chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + +chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - +chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + +chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - +chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + +chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - +chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + +chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - +chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + +chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - +chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + +chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - +chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - +chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + +chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - +chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + +chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + +chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - +chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + +chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - +chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - +chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + +chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - +chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + +chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - +chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + +chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - +chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + +chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - diff -r 000000000000 -r 2c08781560de test-data/eq-condense.dat --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/eq-condense.dat Tue Dec 04 10:53:39 2012 -0500 @@ -0,0 +1,65 @@ +chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - +chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + +chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - +chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + +chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - +chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - +chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + +chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - +chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + +chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - +chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + +chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - +chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - +chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + +chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - +chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + +chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + +chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - +chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + +chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - +chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - +chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + +chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - +chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + +chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + +chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - +chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + +chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - +chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + +chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - +chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + +chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - +chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - +chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + +chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - +chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + +chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + +chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - +chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + +chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - +chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + +chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - +chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + +chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - +chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + +chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - +chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + +chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - +chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - +chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + +chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - +chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + +chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + +chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - +chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + +chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - +chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - +chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + +chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - +chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + +chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - +chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + +chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - +chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + +chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 -