details: http://www.bx.psu.edu/hg/galaxy/rev/ce15d5e5b6ad changeset: 2743:ce15d5e5b6ad user: Kelly Vincent <kpvincent@bx.psu.edu> date: Mon Sep 21 17:02:26 2009 -0400 description: Modified sort to allow sorting by multiple columns 5 file(s) affected in this change: test-data/sort_in1.bed test-data/sort_out1.bed test-data/sort_out2.bed tools/filters/sorter.py tools/filters/sorter.xml diffs (304 lines): diff -r 46852d01ff16 -r ce15d5e5b6ad test-data/sort_in1.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/sort_in1.bed Mon Sep 21 17:02:26 2009 -0400 @@ -0,0 +1,29 @@ +chr6 108298214 108386086 NM_007214 0 - 108299600 108385906 0 21 1530,105,99,102,159,174,60,83,148,155,93,133,95,109,51,59,62,113,115,100,304, 0,2490,6246,10831,12670,23164,23520,27331,31052,32526,34311,36130,36365,38609,41028,42398,43048,51479,54500,59097,87568, +chr6 108593954 108616704 NM_003269 0 + 108594662 108615360 0 9 733,146,88,236,147,97,150,106,1507, 0,5400,8778,10445,12037,14265,14749,15488,21243, +chr6 108639410 108689143 NM_152827 0 - 108640045 108688818 0 3 741,125,487, 0,2984,49246, +chr6 108722790 108950942 NM_145315 0 + 108722976 108950321 0 13 325,224,52,102,131,100,59,83,71,101,141,114,750, 0,28931,52094,60760,61796,71339,107102,152319,181970,182297,215317,224802,227402, +chr7 113320332 113924911 AK131266 0 + 113862563 113893433 0 20 285,91,178,90,58,75,138,51,201,178,214,105,88,84,77,102,122,70,164,1124, 0,201692,340175,448290,451999,484480,542213,543265,543478,545201,556083,558358,565876,567599,573029,573245,575738,577123,577946,603455, +chr7 116511232 116557294 NM_003391 0 - 116512159 116556994 0 5 1157,265,278,227,383, 0,20384,37843,43339,45679, +chr7 116713967 116902666 NM_000492 0 + 116714099 116901113 0 27 185,111,109,216,90,164,126,247,93,183,192,95,87,724,129,38,251,80,151,228,101,249,156,90,173,106,1754, 0,24290,29071,50936,54313,55285,56585,60137,62053,68678,79501,107776,110390,111971,114967,122863,123569,126711,130556,131618,134650,147559,162475,172879,184725,185496,186945, +chr7 116944658 117107512 AF377960 0 - 116945541 116979926 0 23 1129,102,133,64,186,206,179,188,153,100,87,80,96,276,118,255,151,100,204,1654,225,108,173, 0,7364,8850,10413,13893,14398,17435,24259,24615,35177,35359,45901,47221,49781,56405,66857,69787,72208,73597,80474,100111,150555,162681, +chr2 118288484 118306183 NM_006773 0 + 118288583 118304530 0 14 184,285,144,136,101,200,115,140,162,153,114,57,178,1796, 0,2765,4970,6482,6971,7183,7468,9890,10261,10768,11590,14270,14610,15903, +chr2 118389378 118390700 BC005078 0 - 118390395 118390500 0 1 1322, 0, +chr8 118880786 119193239 NM_000127 0 - 118881131 119192466 0 11 531,172,161,90,96,119,133,120,108,94,1735, 0,5355,7850,13505,19068,20309,23098,30863,36077,37741,310718, +chrX 122719582 122773357 NM_001167 0 + 122745047 122766566 0 7 96,909,100,79,43,201,6985, 0,25433,28421,31040,32533,40295,46790, +chr9 128763240 128783870 NM_174933 0 + 128764156 128783586 0 12 261,118,74,159,76,48,56,63,129,117,127,370, 0,522,875,5630,12374,12603,15040,15175,18961,19191,20037,20260, +chr9 128787362 128789566 NM_014908 0 - 128787519 128789136 0 1 2204, 0, +chr9 128789530 128848928 NM_015354 0 + 128789552 128848511 0 44 54,55,74,85,81,45,93,120,212,115,201,90,66,120,127,153,127,88,77,115,121,67,129,140,107,207,170,70,68,196,78,86,146,182,201,93,159,138,75,228,132,74,130,594, 0,1491,5075,8652,9254,10312,11104,11317,20808,21702,23060,25462,31564,32908,33566,34851,35204,35595,35776,37202,38860,39111,39891,40349,42422,45499,45827,46675,47158,47621,50453,50840,51474,51926,53831,54186,55119,55619,57449,57605,57947,58352,58541,58804, +chr9 128849867 128870133 NM_020145 0 - 128850516 128869987 0 11 757,241,101,90,24,63,93,134,129,142,209, 0,1071,1736,2085,2635,4201,6376,6736,13056,14247,20057, +chr5 131170738 131357870 AF099740 0 - 131311206 131357817 0 31 112,124,120,81,65,40,120,129,61,88,94,79,72,102,144,117,89,73,96,135,135,78,74,52,33,179,100,102,65,115,248, 0,11593,44117,47607,104668,109739,114675,126366,135488,137518,138009,140437,152389,153373,155388,159269,160793,162981,164403,165577,166119,167611,169501,178260,179675,180901,181658,182260,182953,183706,186884, +chr5 131424245 131426795 NM_000588 0 + 131424298 131426383 0 5 215,42,90,42,535, 0,313,1658,1872,2015, +chr5 131556201 131590458 NM_004199 0 - 131556601 131582218 0 15 471,97,69,66,54,100,71,177,194,240,138,152,97,100,170, 0,2316,2802,5596,6269,11138,11472,15098,16528,17674,21306,24587,25142,25935,34087, +chr5 131621285 131637046 NM_003687 0 + 131621326 131635821 0 7 134,152,82,179,164,118,1430, 0,4915,8770,13221,13609,14097,14331, +chr1 147962006 147975713 NM_005997 0 - 147962192 147975670 0 6 574,145,177,115,153,160, 0,1543,7859,9048,9340,13547, +chr1 147984101 148035079 BC007833 0 + 147984545 148033414 0 14 529,32,81,131,118,153,300,206,84,49,85,130,46,1668, 0,25695,28767,33118,33695,33998,35644,38005,39629,40577,41402,43885,48367,49310, +chr1 148077485 148111797 NM_002651 0 - 148078400 148111728 0 12 1097,121,133,266,124,105,110,228,228,45,937,77, 0,2081,2472,6871,9907,10257,11604,14199,15637,18274,23636,34235, +chr1 148185113 148187485 NM_002796 0 + 148185136 148187378 0 7 163,207,147,82,117,89,120, 0,416,877,1199,1674,1977,2252, +chrX 152648233 152662158 NM_000425 0 - 152648964 152662138 0 28 963,12,73,135,156,120,174,123,202,116,223,71,198,111,125,157,167,112,144,132,185,112,171,123,203,106,11,100, 0,1436,1545,1951,2390,2653,2889,3156,3367,3772,4717,5122,5424,5868,6066,6370,6629,6909,7588,7871,8124,8456,8858,9125,10220,10660,11296,13825, +chrX 152691216 152693487 NM_000054 0 + 152691446 152693029 0 3 255,885,664, 0,616,1607, +chrX 152693677 152712545 NM_001666 0 - 152694029 152712503 0 22 586,100,93,184,74,234,106,135,78,61,103,28,85,192,102,222,129,183,63,163,205,109, 0,1693,2066,2364,2635,2794,3129,3323,3545,3752,5323,5647,5841,6032,6401,11455,11778,13249,13719,13987,14227,18759, +chr2 220108603 220116964 NM_001927 0 + 220108689 220116217 0 9 664,61,96,162,126,221,44,83,789, 0,1718,1874,2118,2451,2963,5400,7286,7572, +chr2 220229182 220233943 NM_024536 0 - 220229609 220233765 0 4 1687,180,574,492, 0,1990,2660,4269, diff -r 46852d01ff16 -r ce15d5e5b6ad test-data/sort_out1.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/sort_out1.bed Mon Sep 21 17:02:26 2009 -0400 @@ -0,0 +1,29 @@ +chr6 108298214 108386086 NM_007214 0 - 108299600 108385906 0 21 1530,105,99,102,159,174,60,83,148,155,93,133,95,109,51,59,62,113,115,100,304, 0,2490,6246,10831,12670,23164,23520,27331,31052,32526,34311,36130,36365,38609,41028,42398,43048,51479,54500,59097,87568, +chr6 108593954 108616704 NM_003269 0 + 108594662 108615360 0 9 733,146,88,236,147,97,150,106,1507, 0,5400,8778,10445,12037,14265,14749,15488,21243, +chr6 108639410 108689143 NM_152827 0 - 108640045 108688818 0 3 741,125,487, 0,2984,49246, +chr6 108722790 108950942 NM_145315 0 + 108722976 108950321 0 13 325,224,52,102,131,100,59,83,71,101,141,114,750, 0,28931,52094,60760,61796,71339,107102,152319,181970,182297,215317,224802,227402, +chr7 113320332 113924911 AK131266 0 + 113862563 113893433 0 20 285,91,178,90,58,75,138,51,201,178,214,105,88,84,77,102,122,70,164,1124, 0,201692,340175,448290,451999,484480,542213,543265,543478,545201,556083,558358,565876,567599,573029,573245,575738,577123,577946,603455, +chr7 116511232 116557294 NM_003391 0 - 116512159 116556994 0 5 1157,265,278,227,383, 0,20384,37843,43339,45679, +chr7 116713967 116902666 NM_000492 0 + 116714099 116901113 0 27 185,111,109,216,90,164,126,247,93,183,192,95,87,724,129,38,251,80,151,228,101,249,156,90,173,106,1754, 0,24290,29071,50936,54313,55285,56585,60137,62053,68678,79501,107776,110390,111971,114967,122863,123569,126711,130556,131618,134650,147559,162475,172879,184725,185496,186945, +chr7 116944658 117107512 AF377960 0 - 116945541 116979926 0 23 1129,102,133,64,186,206,179,188,153,100,87,80,96,276,118,255,151,100,204,1654,225,108,173, 0,7364,8850,10413,13893,14398,17435,24259,24615,35177,35359,45901,47221,49781,56405,66857,69787,72208,73597,80474,100111,150555,162681, +chr2 118288484 118306183 NM_006773 0 + 118288583 118304530 0 14 184,285,144,136,101,200,115,140,162,153,114,57,178,1796, 0,2765,4970,6482,6971,7183,7468,9890,10261,10768,11590,14270,14610,15903, +chr2 118389378 118390700 BC005078 0 - 118390395 118390500 0 1 1322, 0, +chr8 118880786 119193239 NM_000127 0 - 118881131 119192466 0 11 531,172,161,90,96,119,133,120,108,94,1735, 0,5355,7850,13505,19068,20309,23098,30863,36077,37741,310718, +chrX 122719582 122773357 NM_001167 0 + 122745047 122766566 0 7 96,909,100,79,43,201,6985, 0,25433,28421,31040,32533,40295,46790, +chr9 128763240 128783870 NM_174933 0 + 128764156 128783586 0 12 261,118,74,159,76,48,56,63,129,117,127,370, 0,522,875,5630,12374,12603,15040,15175,18961,19191,20037,20260, +chr9 128787362 128789566 NM_014908 0 - 128787519 128789136 0 1 2204, 0, +chr9 128789530 128848928 NM_015354 0 + 128789552 128848511 0 44 54,55,74,85,81,45,93,120,212,115,201,90,66,120,127,153,127,88,77,115,121,67,129,140,107,207,170,70,68,196,78,86,146,182,201,93,159,138,75,228,132,74,130,594, 0,1491,5075,8652,9254,10312,11104,11317,20808,21702,23060,25462,31564,32908,33566,34851,35204,35595,35776,37202,38860,39111,39891,40349,42422,45499,45827,46675,47158,47621,50453,50840,51474,51926,53831,54186,55119,55619,57449,57605,57947,58352,58541,58804, +chr9 128849867 128870133 NM_020145 0 - 128850516 128869987 0 11 757,241,101,90,24,63,93,134,129,142,209, 0,1071,1736,2085,2635,4201,6376,6736,13056,14247,20057, +chr5 131170738 131357870 AF099740 0 - 131311206 131357817 0 31 112,124,120,81,65,40,120,129,61,88,94,79,72,102,144,117,89,73,96,135,135,78,74,52,33,179,100,102,65,115,248, 0,11593,44117,47607,104668,109739,114675,126366,135488,137518,138009,140437,152389,153373,155388,159269,160793,162981,164403,165577,166119,167611,169501,178260,179675,180901,181658,182260,182953,183706,186884, +chr5 131424245 131426795 NM_000588 0 + 131424298 131426383 0 5 215,42,90,42,535, 0,313,1658,1872,2015, +chr5 131556201 131590458 NM_004199 0 - 131556601 131582218 0 15 471,97,69,66,54,100,71,177,194,240,138,152,97,100,170, 0,2316,2802,5596,6269,11138,11472,15098,16528,17674,21306,24587,25142,25935,34087, +chr5 131621285 131637046 NM_003687 0 + 131621326 131635821 0 7 134,152,82,179,164,118,1430, 0,4915,8770,13221,13609,14097,14331, +chr1 147962006 147975713 NM_005997 0 - 147962192 147975670 0 6 574,145,177,115,153,160, 0,1543,7859,9048,9340,13547, +chr1 147984101 148035079 BC007833 0 + 147984545 148033414 0 14 529,32,81,131,118,153,300,206,84,49,85,130,46,1668, 0,25695,28767,33118,33695,33998,35644,38005,39629,40577,41402,43885,48367,49310, +chr1 148077485 148111797 NM_002651 0 - 148078400 148111728 0 12 1097,121,133,266,124,105,110,228,228,45,937,77, 0,2081,2472,6871,9907,10257,11604,14199,15637,18274,23636,34235, +chr1 148185113 148187485 NM_002796 0 + 148185136 148187378 0 7 163,207,147,82,117,89,120, 0,416,877,1199,1674,1977,2252, +chrX 152648233 152662158 NM_000425 0 - 152648964 152662138 0 28 963,12,73,135,156,120,174,123,202,116,223,71,198,111,125,157,167,112,144,132,185,112,171,123,203,106,11,100, 0,1436,1545,1951,2390,2653,2889,3156,3367,3772,4717,5122,5424,5868,6066,6370,6629,6909,7588,7871,8124,8456,8858,9125,10220,10660,11296,13825, +chrX 152691216 152693487 NM_000054 0 + 152691446 152693029 0 3 255,885,664, 0,616,1607, +chrX 152693677 152712545 NM_001666 0 - 152694029 152712503 0 22 586,100,93,184,74,234,106,135,78,61,103,28,85,192,102,222,129,183,63,163,205,109, 0,1693,2066,2364,2635,2794,3129,3323,3545,3752,5323,5647,5841,6032,6401,11455,11778,13249,13719,13987,14227,18759, +chr2 220108603 220116964 NM_001927 0 + 220108689 220116217 0 9 664,61,96,162,126,221,44,83,789, 0,1718,1874,2118,2451,2963,5400,7286,7572, +chr2 220229182 220233943 NM_024536 0 - 220229609 220233765 0 4 1687,180,574,492, 0,1990,2660,4269, diff -r 46852d01ff16 -r ce15d5e5b6ad test-data/sort_out2.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/sort_out2.bed Mon Sep 21 17:02:26 2009 -0400 @@ -0,0 +1,29 @@ +chr6 108298214 108386086 NM_007214 0 - 108299600 108385906 0 21 1530,105,99,102,159,174,60,83,148,155,93,133,95,109,51,59,62,113,115,100,304, 0,2490,6246,10831,12670,23164,23520,27331,31052,32526,34311,36130,36365,38609,41028,42398,43048,51479,54500,59097,87568, +chr6 108593954 108616704 NM_003269 0 + 108594662 108615360 0 9 733,146,88,236,147,97,150,106,1507, 0,5400,8778,10445,12037,14265,14749,15488,21243, +chr6 108639410 108689143 NM_152827 0 - 108640045 108688818 0 3 741,125,487, 0,2984,49246, +chr6 108722790 108950942 NM_145315 0 + 108722976 108950321 0 13 325,224,52,102,131,100,59,83,71,101,141,114,750, 0,28931,52094,60760,61796,71339,107102,152319,181970,182297,215317,224802,227402, +chr7 113320332 113924911 AK131266 0 + 113862563 113893433 0 20 285,91,178,90,58,75,138,51,201,178,214,105,88,84,77,102,122,70,164,1124, 0,201692,340175,448290,451999,484480,542213,543265,543478,545201,556083,558358,565876,567599,573029,573245,575738,577123,577946,603455, +chr7 116511232 116557294 NM_003391 0 - 116512159 116556994 0 5 1157,265,278,227,383, 0,20384,37843,43339,45679, +chr7 116713967 116902666 NM_000492 0 + 116714099 116901113 0 27 185,111,109,216,90,164,126,247,93,183,192,95,87,724,129,38,251,80,151,228,101,249,156,90,173,106,1754, 0,24290,29071,50936,54313,55285,56585,60137,62053,68678,79501,107776,110390,111971,114967,122863,123569,126711,130556,131618,134650,147559,162475,172879,184725,185496,186945, +chr7 116944658 117107512 AF377960 0 - 116945541 116979926 0 23 1129,102,133,64,186,206,179,188,153,100,87,80,96,276,118,255,151,100,204,1654,225,108,173, 0,7364,8850,10413,13893,14398,17435,24259,24615,35177,35359,45901,47221,49781,56405,66857,69787,72208,73597,80474,100111,150555,162681, +chr2 118288484 118306183 NM_006773 0 + 118288583 118304530 0 14 184,285,144,136,101,200,115,140,162,153,114,57,178,1796, 0,2765,4970,6482,6971,7183,7468,9890,10261,10768,11590,14270,14610,15903, +chr2 118389378 118390700 BC005078 0 - 118390395 118390500 0 1 1322, 0, +chr8 118880786 119193239 NM_000127 0 - 118881131 119192466 0 11 531,172,161,90,96,119,133,120,108,94,1735, 0,5355,7850,13505,19068,20309,23098,30863,36077,37741,310718, +chrX 122719582 122773357 NM_001167 0 + 122745047 122766566 0 7 96,909,100,79,43,201,6985, 0,25433,28421,31040,32533,40295,46790, +chr9 128763240 128783870 NM_174933 0 + 128764156 128783586 0 12 261,118,74,159,76,48,56,63,129,117,127,370, 0,522,875,5630,12374,12603,15040,15175,18961,19191,20037,20260, +chr9 128787362 128789566 NM_014908 0 - 128787519 128789136 0 1 2204, 0, +chr9 128789530 128848928 NM_015354 0 + 128789552 128848511 0 44 54,55,74,85,81,45,93,120,212,115,201,90,66,120,127,153,127,88,77,115,121,67,129,140,107,207,170,70,68,196,78,86,146,182,201,93,159,138,75,228,132,74,130,594, 0,1491,5075,8652,9254,10312,11104,11317,20808,21702,23060,25462,31564,32908,33566,34851,35204,35595,35776,37202,38860,39111,39891,40349,42422,45499,45827,46675,47158,47621,50453,50840,51474,51926,53831,54186,55119,55619,57449,57605,57947,58352,58541,58804, +chr9 128849867 128870133 NM_020145 0 - 128850516 128869987 0 11 757,241,101,90,24,63,93,134,129,142,209, 0,1071,1736,2085,2635,4201,6376,6736,13056,14247,20057, +chr5 131170738 131357870 AF099740 0 - 131311206 131357817 0 31 112,124,120,81,65,40,120,129,61,88,94,79,72,102,144,117,89,73,96,135,135,78,74,52,33,179,100,102,65,115,248, 0,11593,44117,47607,104668,109739,114675,126366,135488,137518,138009,140437,152389,153373,155388,159269,160793,162981,164403,165577,166119,167611,169501,178260,179675,180901,181658,182260,182953,183706,186884, +chr5 131424245 131426795 NM_000588 0 + 131424298 131426383 0 5 215,42,90,42,535, 0,313,1658,1872,2015, +chr5 131556201 131590458 NM_004199 0 - 131556601 131582218 0 15 471,97,69,66,54,100,71,177,194,240,138,152,97,100,170, 0,2316,2802,5596,6269,11138,11472,15098,16528,17674,21306,24587,25142,25935,34087, +chr5 131621285 131637046 NM_003687 0 + 131621326 131635821 0 7 134,152,82,179,164,118,1430, 0,4915,8770,13221,13609,14097,14331, +chr1 147962006 147975713 NM_005997 0 - 147962192 147975670 0 6 574,145,177,115,153,160, 0,1543,7859,9048,9340,13547, +chr1 147984101 148035079 BC007833 0 + 147984545 148033414 0 14 529,32,81,131,118,153,300,206,84,49,85,130,46,1668, 0,25695,28767,33118,33695,33998,35644,38005,39629,40577,41402,43885,48367,49310, +chr1 148077485 148111797 NM_002651 0 - 148078400 148111728 0 12 1097,121,133,266,124,105,110,228,228,45,937,77, 0,2081,2472,6871,9907,10257,11604,14199,15637,18274,23636,34235, +chr1 148185113 148187485 NM_002796 0 + 148185136 148187378 0 7 163,207,147,82,117,89,120, 0,416,877,1199,1674,1977,2252, +chrX 152648233 152662158 NM_000425 0 - 152648964 152662138 0 28 963,12,73,135,156,120,174,123,202,116,223,71,198,111,125,157,167,112,144,132,185,112,171,123,203,106,11,100, 0,1436,1545,1951,2390,2653,2889,3156,3367,3772,4717,5122,5424,5868,6066,6370,6629,6909,7588,7871,8124,8456,8858,9125,10220,10660,11296,13825, +chrX 152691216 152693487 NM_000054 0 + 152691446 152693029 0 3 255,885,664, 0,616,1607, +chrX 152693677 152712545 NM_001666 0 - 152694029 152712503 0 22 586,100,93,184,74,234,106,135,78,61,103,28,85,192,102,222,129,183,63,163,205,109, 0,1693,2066,2364,2635,2794,3129,3323,3545,3752,5323,5647,5841,6032,6401,11455,11778,13249,13719,13987,14227,18759, +chr2 220108603 220116964 NM_001927 0 + 220108689 220116217 0 9 664,61,96,162,126,221,44,83,789, 0,1718,1874,2118,2451,2963,5400,7286,7572, +chr2 220229182 220233943 NM_024536 0 - 220229609 220233765 0 4 1687,180,574,492, 0,1990,2660,4269, diff -r 46852d01ff16 -r ce15d5e5b6ad tools/filters/sorter.py --- a/tools/filters/sorter.py Mon Sep 21 15:43:38 2009 -0400 +++ b/tools/filters/sorter.py Mon Sep 21 17:02:26 2009 -0400 @@ -1,113 +1,32 @@ -# Filename: sorter.py -# Author: Ian N. Schenck -# Version: 8/22/2005 -# # This script sorts a file based on the inputs: # -cols - column to sort on -# -order - ASC or DESC-ing order +# -order - ASC- or DESCending order # -i - input filename # -o - output filename -import string -import sys -import re -import commands -from os import environ +import os, re, string, sys -def getopts(argv): - opts = {} - while argv: - if argv[0][0] == '-': - opts[argv[0]] = argv[1] - argv = argv[2:] - else: - argv = argv[1:] - return opts +def stop_err( msg ): + sys.stderr.write( "%s\n" % msg ) + sys.exit() def main(): - args = sys.argv[1:] + try: + inputfile = sys.argv[1] + outputfile = '-o %s' % sys.argv[2] + order = ('', '-r')[sys.argv[3] == 'DESC'] + sort_type = ('','-n')[sys.argv[4] == 'num'] + columns = sys.argv[5:] + cols = [ '-k%s,%s'%(n, n) for n in columns ] + except Exception, ex: + stop_err('Error parsing input parameters\n' + str(ex)) + # Launch sort. + cmd = "sort -f -t $'\t' %s %s %s %s %s" % (sort_type, ' '.join(cols), order, outputfile, inputfile) try: - opts = getopts(args) - except IndexError: - print "Usage:" - print " -o Output filename" - print " -i Input filename" - print " -cols Column to sort (base 1)" - print " -order ASC or DESC" - print " -style num or alpha" - return 0 - - outputfile = opts.get("-o") - if outputfile == None: - print "No output file specified." - return -1 - - inputfile = opts.get("-i") - if inputfile == None: - print "No input file specified." - return -2 - - column = opts.get("-cols") - if column == None or column == 'None': - print "Sort column not specified." - return -3 - - order = opts.get("-order") - if order == None: - print "Sort order not specified." - return -4 - - style = opts.get("-style") - if style == None: - style = "num" - - # At this point, all command line options have been collected. - # Verify arguments are valid. - - fileRegEx = re.compile("^[A-Za-z0-9./\-_]+$") - numberRegEx = re.compile("^[0-9]+$") - sortRegEx = re.compile("^(ASC|DESC)$") - if not fileRegEx.match(outputfile): - print "Illegal output filename." - return -5 - if not fileRegEx.match(inputfile): - print "Illegal input filename." - return -6 - if not numberRegEx.match(column): - print "Column number not an integer." - return -7 - if not sortRegEx.match(order): - print "Sort order must be ASCending or DESCending." - return -8 - - # Check sort column against max columns in input file. - - column = string.atoi(column) - if column > len( open(inputfile).readline().split('\t') ): - print "Column "+str(column)+" does not exist." - return -9 - - # Everything is kosher. - - if order == "DESC": - order = " -r" - else: - order = "" - - if style == "num": - style = " -n " - else: - style = " " - - # Launch sort. - - environ['LC_ALL'] = 'POSIX' - commandline = "sort -f"+style+"-k "+str(column)+" -t $'\t' -o "+outputfile+" "+inputfile+order - - errorcode, stdout = commands.getstatusoutput(commandline) - - return errorcode + os.system(cmd) + except Exception, ex: + stop_err('Error running sort command\n' + str(ex)) if __name__ == "__main__": main() diff -r 46852d01ff16 -r ce15d5e5b6ad tools/filters/sorter.xml --- a/tools/filters/sorter.xml Mon Sep 21 15:43:38 2009 -0400 +++ b/tools/filters/sorter.xml Mon Sep 21 17:02:26 2009 -0400 @@ -1,14 +1,27 @@ <tool id="sort1" name="Sort" version="1.0.1"> <description>data in ascending or descending order</description> - <command interpreter="python">sorter.py -i $input -o $out_file1 -cols $column -order $order -style $style</command> + <command interpreter="python"> + sorter.py + $input + $out_file1 + $order + $style + $firstcol + #for $col in $column_set: + ${col.column} + #end for + </command> <inputs> <param format="tabular" name="input" type="data" label="Sort Query" /> - <param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" /> + <param name="firstcol" label="on column" type="data_column" data_ref="input" accept_default="true" /> + <repeat name="column_set" title="Column selection"> + <param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" /> + </repeat> <param name="order" type="select" label="in"> <option value="DESC">Descending order</option> <option value="ASC">Ascending order</option> </param> - <param name="style" type="select" label="Flavor"> + <param name="style" type="select" label="with flavor"> <option value="num">Numerical sort</option> <option value="alpha">Alphabetical sort</option> </param> @@ -18,18 +31,20 @@ </outputs> <tests> <test> - <param name="input" value="1.bed"/> - <param name="column" value="1"/> + <param name="input" value="sort_in1.bed"/> + <param name="firstcol" value="1"/> + <param name="column" value="3" /> <param name="order" value="ASC"/> <param name="style" value="num"/> - <output name="out_file1" file="sort1_num.bed"/> + <output name="out_file1" file="sort_out1.bed"/> </test> <test> - <param name="input" value="7.bed"/> + <param name="input" value="sort_in1.bed"/> + <param name="firstcol" value="3" /> <param name="column" value="1"/> <param name="order" value="ASC"/> <param name="style" value="alpha"/> - <output name="out_file1" file="sort1_alpha.bed"/> + <output name="out_file1" file="sort_out2.bed"/> </test> </tests> <help> @@ -42,7 +57,7 @@ **Syntax** -This tool sorts the dataset on any column in either ascending or descending order. +This tool sorts the dataset on any number of columns in either ascending or descending order (all columns will be ascending or descending). * Numerical sort orders numbers by their magnitude, ignores all characters besides numbers, and evaluates a string of numbers to the value they signify. * Alphabetical sort is a phonebook type sort based on the conventional order of letters in an alphabet. Each nth letter is compared with the nth letter of other words in the list, starting at the first letter of each word and advancing to the second, third, fourth, and so on, until the order is established. Therefore, in an alphabetical sort, 2 comes after 100 (1 < 2).