def test_indent_splitter(self):
"""indent_splitter should split lines at correct locations"""
#if lines have same indent, should not group together
lines = ['abc xxx', 'def yyy']
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0]], [lines[1]]])
#if second line is indented, should group with first
lines = ['abc xxx', ' def yyy']
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0], lines[1]]])
#if both lines indented but second is more, should group with first
lines = [' abc xxx', ' def yyy']
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0], lines[1]]])
#if both lines indented equally, should not group
lines = [' abc xxx', ' def yyy']
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]], [lines[1]]])
#for more complex situation, should produce correct grouping
lines = [
' xyz', #0 -
' xxx', #1 -
' yyy', #2
' uuu', #3
' iii', #4
' qaz', #5 -
' wsx', #6 -
' az', #7
' sx', #8
' gb', #9
' bg', #10
' aaa', #11 -
]
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]], lines[1:5], [lines[5]], lines[6:11], [lines[11]]])
#real example from genbank file
lines = \
"""LOCUS NT_016354 92123751 bp DNA linear CON 29-AUG-2006
DEFINITION H**o sapiens chromosome 4 genomic contig, reference assembly.
ACCESSION NT_016354 NT_006109 NT_006204 NT_006245 NT_006302 NT_006371
NT_006397 NT_016393 NT_016589 NT_016599 NT_016606 NT_022752
NT_022753 NT_022755 NT_022760 NT_022774 NT_022797 NT_022803
NT_022846 NT_022960 NT_025694 NT_028147 NT_029273 NT_030643
NT_030646 NT_030662 NT_031780 NT_031781 NT_031791 NT_034703
NT_034705 NT_037628 NT_037629 NT_079512
VERSION NT_016354.18 GI:88977422
KEYWORDS .
SOURCE H**o sapiens (human)
ORGANISM H**o sapiens
Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
Mammalia; Eutheria; Euarchontoglires; Primates; Haplorrhini;
Catarrhini; Hominidae; H**o.
?
REFERENCE 2 (bases 1 to 92123751)
AUTHORS International Human Genome Sequencing Consortium.
TITLE Finishing the euchromatic sequence of the human genome""".split('\n')
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]],[lines[1]],lines[2:8],[lines[8]],[lines[9]],lines[10:15],\
[lines[15]], lines[16:]])
def test_indent_splitter(self):
"""indent_splitter should split lines at correct locations"""
#if lines have same indent, should not group together
lines = [
'abc xxx',
'def yyy'
]
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0]], [lines[1]]])
#if second line is indented, should group with first
lines = [
'abc xxx',
' def yyy'
]
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0], lines[1]]])
#if both lines indented but second is more, should group with first
lines = [
' abc xxx',
' def yyy'
]
self.assertEqual(list(indent_splitter(lines)),\
[[lines[0], lines[1]]])
#if both lines indented equally, should not group
lines = [
' abc xxx',
' def yyy'
]
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]], [lines[1]]])
#for more complex situation, should produce correct grouping
lines = [
' xyz', #0 -
' xxx', #1 -
' yyy', #2
' uuu', #3
' iii', #4
' qaz', #5 -
' wsx', #6 -
' az', #7
' sx', #8
' gb',#9
' bg', #10
' aaa', #11 -
]
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]], lines[1:5], [lines[5]], lines[6:11], [lines[11]]])
#real example from genbank file
lines = \
"""LOCUS NT_016354 92123751 bp DNA linear CON 29-AUG-2006
DEFINITION H**o sapiens chromosome 4 genomic contig, reference assembly.
ACCESSION NT_016354 NT_006109 NT_006204 NT_006245 NT_006302 NT_006371
NT_006397 NT_016393 NT_016589 NT_016599 NT_016606 NT_022752
NT_022753 NT_022755 NT_022760 NT_022774 NT_022797 NT_022803
NT_022846 NT_022960 NT_025694 NT_028147 NT_029273 NT_030643
NT_030646 NT_030662 NT_031780 NT_031781 NT_031791 NT_034703
NT_034705 NT_037628 NT_037629 NT_079512
VERSION NT_016354.18 GI:88977422
KEYWORDS .
SOURCE H**o sapiens (human)
ORGANISM H**o sapiens
Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
Mammalia; Eutheria; Euarchontoglires; Primates; Haplorrhini;
Catarrhini; Hominidae; H**o.
?
REFERENCE 2 (bases 1 to 92123751)
AUTHORS International Human Genome Sequencing Consortium.
TITLE Finishing the euchromatic sequence of the human genome""".split('\n')
self.assertEqual(list(indent_splitter(lines)), \
[[lines[0]],[lines[1]],lines[2:8],[lines[8]],[lines[9]],lines[10:15],\
[lines[15]], lines[16:]])
l3_a = Location(10)
l3_b = Location(12)
l3 = Location([l3_a, l3_b])
ll = LocationList([l, l2, l3])
s = ll.extract('ACGTGCAGTCAGTAGCAT')
# 123456789012345678
self.assertEqual(s, 'G' + 'TGC' + 'CAG')
#check a case where it wraps around
l5_a = Location(16)
l5_b = Location(4)
l5 = Location([l5_a, l5_b])
ll = LocationList([l5])
s = ll.extract('ACGTGCAGTCAGTAGCAT')
self.assertEqual(s, 'CATACGT')
if __name__ == '__main__':
from sys import argv
if len(argv) > 2 and argv[1] == 'x':
filename = argv[2]
lines = open(filename)
for i in indent_splitter(lines):
print '******'
print i[0]
for j in indent_splitter(i[1:]):
print '?????'
for line in j:
print line
else:
main()
l3_a = Location(10)
l3_b = Location(12)
l3 = Location([l3_a, l3_b])
ll = LocationList([l, l2, l3])
s = ll.extract('ACGTGCAGTCAGTAGCAT')
# 123456789012345678
self.assertEqual(s, 'G'+'TGC'+'CAG')
#check a case where it wraps around
l5_a = Location(16)
l5_b = Location(4)
l5 = Location([l5_a,l5_b])
ll = LocationList([l5])
s = ll.extract('ACGTGCAGTCAGTAGCAT')
self.assertEqual(s, 'CATACGT')
if __name__ == '__main__':
from sys import argv
if len(argv) > 2 and argv[1] == 'x':
filename = argv[2]
lines = open(filename)
for i in indent_splitter(lines):
print '******'
print i[0]
for j in indent_splitter(i[1:]):
print '?????'
for line in j:
print line
else:
main()
