[2] | 1 | #!/usr/bin/env python |
---|
| 2 | """ |
---|
| 3 | Concatenate two bed files. The concatenated files are returned in the |
---|
| 4 | same format as the first. If --sameformat is specified, then all |
---|
| 5 | columns will be treated as the same, and all fields will be saved, |
---|
| 6 | although the output will be trimmed to match the primary input. In |
---|
| 7 | addition, if --sameformat is specified, missing fields will be padded |
---|
| 8 | with a period(.). |
---|
| 9 | |
---|
| 10 | usage: %prog in_file_1 in_file_2 out_file |
---|
| 11 | -1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in first file |
---|
| 12 | -2, --cols2=N,N,N,N: Columns for chrom, start, end, strand in second file |
---|
| 13 | -s, --sameformat: All files are precisely the same format. |
---|
| 14 | """ |
---|
| 15 | from galaxy import eggs |
---|
| 16 | import pkg_resources |
---|
| 17 | pkg_resources.require( "bx-python" ) |
---|
| 18 | import sys, traceback, fileinput |
---|
| 19 | from warnings import warn |
---|
| 20 | from bx.intervals import * |
---|
| 21 | from bx.intervals.io import * |
---|
| 22 | from bx.intervals.operations.concat import * |
---|
| 23 | from bx.cookbook import doc_optparse |
---|
| 24 | from galaxy.tools.util.galaxyops import * |
---|
| 25 | |
---|
| 26 | assert sys.version_info[:2] >= ( 2, 4 ) |
---|
| 27 | |
---|
| 28 | def main(): |
---|
| 29 | sameformat=False |
---|
| 30 | upstream_pad = 0 |
---|
| 31 | downstream_pad = 0 |
---|
| 32 | |
---|
| 33 | options, args = doc_optparse.parse( __doc__ ) |
---|
| 34 | try: |
---|
| 35 | chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 ) |
---|
| 36 | chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 ) |
---|
| 37 | if options.sameformat: sameformat = True |
---|
| 38 | in_file_1, in_file_2, out_fname = args |
---|
| 39 | except: |
---|
| 40 | doc_optparse.exception() |
---|
| 41 | |
---|
| 42 | g1 = NiceReaderWrapper( fileinput.FileInput( in_file_1 ), |
---|
| 43 | chrom_col=chr_col_1, |
---|
| 44 | start_col=start_col_1, |
---|
| 45 | end_col=end_col_1, |
---|
| 46 | fix_strand=True ) |
---|
| 47 | |
---|
| 48 | g2 = NiceReaderWrapper( fileinput.FileInput( in_file_2 ), |
---|
| 49 | chrom_col=chr_col_2, |
---|
| 50 | start_col=start_col_2, |
---|
| 51 | end_col=end_col_2, |
---|
| 52 | strand_col=strand_col_2, |
---|
| 53 | fix_strand=True ) |
---|
| 54 | |
---|
| 55 | if strand_col_1 >= 0: |
---|
| 56 | g1.strand_col = strand_col_1 |
---|
| 57 | |
---|
| 58 | out_file = open( out_fname, "w" ) |
---|
| 59 | |
---|
| 60 | try: |
---|
| 61 | for line in concat( [g1, g2], sameformat=sameformat ): |
---|
| 62 | if type( line ) is GenomicInterval: |
---|
| 63 | out_file.write( "%s\n" % "\t".join( line.fields ) ) |
---|
| 64 | else: |
---|
| 65 | out_file.write( "%s\n" % line ) |
---|
| 66 | except ParseError, exc: |
---|
| 67 | out_file.close() |
---|
| 68 | fail( "Invalid file format: %s" % str( exc ) ) |
---|
| 69 | |
---|
| 70 | out_file.close() |
---|
| 71 | |
---|
| 72 | if g1.skipped > 0: |
---|
| 73 | print skipped( g1, filedesc=" of 1st dataset" ) |
---|
| 74 | if g2.skipped > 0: |
---|
| 75 | print skipped( g2, filedesc=" of 2nd dataset" ) |
---|
| 76 | |
---|
| 77 | if __name__ == "__main__": |
---|
| 78 | main() |
---|