1 | """ |
---|
2 | XML format classes |
---|
3 | """ |
---|
4 | import data |
---|
5 | import logging |
---|
6 | from galaxy.datatypes.sniff import * |
---|
7 | |
---|
8 | log = logging.getLogger(__name__) |
---|
9 | |
---|
10 | class BlastXml( data.Text ): |
---|
11 | """NCBI Blast XML Output data""" |
---|
12 | file_ext = "blastxml" |
---|
13 | |
---|
14 | def set_peek( self, dataset, is_multi_byte=False ): |
---|
15 | """Set the peek and blurb text""" |
---|
16 | if not dataset.dataset.purged: |
---|
17 | dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte ) |
---|
18 | dataset.blurb = 'NCBI Blast XML data' |
---|
19 | else: |
---|
20 | dataset.peek = 'file does not exist' |
---|
21 | dataset.blurb = 'file purged from disk' |
---|
22 | def sniff( self, filename ): |
---|
23 | """ |
---|
24 | Determines whether the file is blastxml |
---|
25 | |
---|
26 | >>> fname = get_test_fname( 'megablast_xml_parser_test1.blastxml' ) |
---|
27 | >>> BlastXml().sniff( fname ) |
---|
28 | True |
---|
29 | >>> fname = get_test_fname( 'interval.interval' ) |
---|
30 | >>> BlastXml().sniff( fname ) |
---|
31 | False |
---|
32 | """ |
---|
33 | blastxml_header = [ '<?xml version="1.0"?>', |
---|
34 | '<!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">', |
---|
35 | '<BlastOutput>' ] |
---|
36 | for i, line in enumerate( file( filename ) ): |
---|
37 | if i >= len( blastxml_header ): |
---|
38 | return True |
---|
39 | line = line.rstrip( '\n\r' ) |
---|
40 | if line != blastxml_header[ i ]: |
---|
41 | return False |
---|