def test_teetsv():
t1 = (("foo", "bar"), ("a", 2), ("b", 1), ("c", 3))
f1 = NamedTemporaryFile(delete=False)
f2 = NamedTemporaryFile(delete=False)
(etl.wrap(t1).teetsv(f1.name, encoding="ascii").selectgt("bar", 1).totsv(f2.name, encoding="ascii"))
ieq(t1, etl.fromtsv(f1.name, encoding="ascii").convertnumbers())
ieq(etl.wrap(t1).selectgt("bar", 1), etl.fromtsv(f2.name, encoding="ascii").convertnumbers())
def test_teetsv_unicode():
t1 = ((u"name", u"id"), (u"Արամ Խաչատրյան", 1), (u"Johann Strauß", 2), (u"Вагиф Сәмәдоғлу", 3), (u"章子怡", 4))
f1 = NamedTemporaryFile(delete=False)
f2 = NamedTemporaryFile(delete=False)
(etl.wrap(t1).teetsv(f1.name, encoding="utf-8").selectgt("id", 1).totsv(f2.name, encoding="utf-8"))
ieq(t1, etl.fromtsv(f1.name, encoding="utf-8").convertnumbers())
ieq(etl.wrap(t1).selectgt("id", 1), etl.fromtsv(f2.name, encoding="utf-8").convertnumbers())
def test_ZipSource():
# setup
table = [('foo', 'bar'), ('a', '1'), ('b', '2')]
totsv(table, 'tmp/issue_241.tsv')
z = zipfile.ZipFile('tmp/issue_241.zip', mode='w')
z.write('tmp/issue_241.tsv', 'data.tsv')
z.close()
# test
actual = fromtsv(ZipSource('tmp/issue_241.zip', 'data.tsv'))
ieq(table, actual)
def test_issue_231():
table = [['foo', 'bar'], ['a', '1'], ['b', '2']]
t = cut(table, 'foo')
totsv(t, 'tmp/issue_231.tsv')
u = fromtsv('tmp/issue_231.tsv')
ieq(t, u)
tocsv(t, 'tmp/issue_231.csv')
u = fromcsv('tmp/issue_231.csv')
ieq(t, u)
topickle(t, 'tmp/issue_231.pickle')
u = frompickle('tmp/issue_231.pickle')
ieq(t, u)
def test_fromtsv():
f = NamedTemporaryFile(delete=False)
writer = csv.writer(f, delimiter="\t")
table = (("foo", "bar"), ("a", 1), ("b", 2), ("c", 2))
for row in table:
writer.writerow(row)
f.close()
actual = fromtsv(f.name)
expect = (("foo", "bar"), ("a", "1"), ("b", "2"), ("c", "2"))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def test_zipsource():
# setup
tbl = [('foo', 'bar'), ('a', '1'), ('b', '2')]
fn_tsv = NamedTemporaryFile().name
etl.totsv(tbl, fn_tsv)
fn_zip = NamedTemporaryFile().name
z = zipfile.ZipFile(fn_zip, mode='w')
z.write(fn_tsv, 'data.tsv')
z.close()
# test
actual = etl.fromtsv(ZipSource(fn_zip, 'data.tsv'))
ieq(tbl, actual)
def test_fromtsv():
f = NamedTemporaryFile(delete=False)
writer = csv.writer(f, delimiter='\t')
table = (('foo', 'bar'),
('a', 1),
('b', 2),
('c', 2))
for row in table:
writer.writerow(row)
f.close()
actual = fromtsv(f.name)
expect = (('foo', 'bar'),
('a', '1'),
('b', '2'),
('c', '2'))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def fromgff3(filename, region=None):
"""
Extract feature rows from a GFF3 file, e.g.::
>>> import petl as etl
>>> # activate bio extensions
... import petlx.bio
>>> table1 = etl.fromgff3('fixture/sample.gff')
>>> table1.look(truncate=30)
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
| seqid | source | type | start | end | score | strand | phase | attributes |
+==============+=========+===============+=======+=========+=======+========+=======+================================+
| 'apidb|MAL1' | 'ApiDB' | 'supercontig' | 1 | 643292 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL2' | 'ApiDB' | 'supercontig' | 1 | 947102 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL3' | 'ApiDB' | 'supercontig' | 1 | 1060087 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL4' | 'ApiDB' | 'supercontig' | 1 | 1204112 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL5' | 'ApiDB' | 'supercontig' | 1 | 1343552 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+-------+---------+-------+--------+-------+--------------------------------+
...
A region query string of the form '[seqid]' or '[seqid]:[start]-[end]'
may be given for the `region` argument. If given, requires the GFF3
file to be position sorted, bgzipped and tabix indexed. Requires pysam to be
installed. E.g.::
>>> # extract from a specific genome region via tabix
... table2 = etl.fromgff3('fixture/sample.sorted.gff.gz',
... region='apidb|MAL5:1289593-1289595')
>>> table2.look(truncate=30)
+--------------+---------+---------------+---------+---------+-------+--------+-------+--------------------------------+
| seqid | source | type | start | end | score | strand | phase | attributes |
+==============+=========+===============+=========+=========+=======+========+=======+================================+
| 'apidb|MAL5' | 'ApiDB' | 'supercontig' | 1 | 1343552 | '.' | '+' | '.' | {'localization': 'nuclear', 'o |
+--------------+---------+---------------+---------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL5' | 'ApiDB' | 'exon' | 1289594 | 1291685 | '.' | '+' | '.' | {'size': '2092', 'Parent': 'ap |
+--------------+---------+---------------+---------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL5' | 'ApiDB' | 'gene' | 1289594 | 1291685 | '.' | '+' | '.' | {'ID': 'apidb|MAL5_18S', 'web_ |
+--------------+---------+---------------+---------+---------+-------+--------+-------+--------------------------------+
| 'apidb|MAL5' | 'ApiDB' | 'rRNA' | 1289594 | 1291685 | '.' | '+' | '.' | {'ID': 'apidb|rna_MAL5_18S-1', |
+--------------+---------+---------------+---------+---------+-------+--------+-------+--------------------------------+
"""
if region is None:
# parse file as tab-delimited
table = etl.fromtsv(filename)
else:
# extract via tabix
table = etl.fromtabix(filename, region=region)
return (
table
.pushheader(GFF3_HEADER)
.skipcomments('#')
# ignore any row not 9 values long (e.g., trailing fasta)
.rowlenselect(9)
# parse attributes into a dict
.convert('attributes', gff3_parse_attributes)
# parse coordinates
.convert(('start', 'end'), int)
)
