def test_container():
table = (('foo', 'bar'), ('a', 1), ('b', 2), ('c', 2))
actual = etl.wrap(table)[0]
expect = ('foo', 'bar')
eq_(expect, actual)
actual = len(etl.wrap(table))
expect = 4
eq_(expect, actual)
def test_container():
table = (('foo', 'bar'),
('a', 1),
('b', 2),
('c', 2))
actual = etl.wrap(table)[0]
expect = ('foo', 'bar')
eq_(expect, actual)
actual = len(etl.wrap(table))
expect = 4
eq_(expect, actual)
def test_repr_html():
table = (('foo', 'bar'),
('a', 1),
('b', 2),
('c', 2))
expect = u"""<table class='petl'>
<thead>
<tr>
<th>foo</th>
<th>bar</th>
</tr>
</thead>
<tbody>
<tr>
<td>a</td>
<td style='text-align: right'>1</td>
</tr>
<tr>
<td>b</td>
<td style='text-align: right'>2</td>
</tr>
<tr>
<td>c</td>
<td style='text-align: right'>2</td>
</tr>
</tbody>
</table>
"""
actual = etl.wrap(table)._repr_html_()
for l1, l2 in zip(expect.split('\n'), actual.split('\r\n')):
eq_(l1, l2)
def test_repr_html_limit():
table = (('foo', 'bar'), ('a', 1), ('b', 2), ('c', 2))
# lower repr limit
etl.repr_html_limit = 2
expect = u"""<table class='petl'>
<thead>
<tr>
<th>foo</th>
<th>bar</th>
</tr>
</thead>
<tbody>
<tr>
<td>a</td>
<td style='text-align: right'>1</td>
</tr>
<tr>
<td>b</td>
<td style='text-align: right'>2</td>
</tr>
</tbody>
</table>
<p><strong>...</strong></p>
"""
actual = etl.wrap(table)._repr_html_()
for l1, l2 in zip(expect.split('\n'), actual.split('\r\n')):
eq_(l1, l2)
def test_repr_html_limit():
table = (('foo', 'bar'),
('a', 1),
('b', 2),
('c', 2))
# lower repr limit
etl.repr_html_limit = 2
expect = u"""<table class='petl'>
<thead>
<tr>
<th>foo</th>
<th>bar</th>
</tr>
</thead>
<tbody>
<tr>
<td>a</td>
<td style='text-align: right'>1</td>
</tr>
<tr>
<td>b</td>
<td style='text-align: right'>2</td>
</tr>
</tbody>
</table>
<p><strong>...</strong></p>
"""
actual = etl.wrap(table)._repr_html_()
for l1, l2 in zip(expect.split('\n'), actual.split('\r\n')):
print l1, l2
eq_(l1, l2)
def test_repr_html():
table = (('foo', 'bar'), ('a', 1), ('b', 2), ('c', 2))
expect = u"""<table class='petl'>
<thead>
<tr>
<th>foo</th>
<th>bar</th>
</tr>
</thead>
<tbody>
<tr>
<td>a</td>
<td style='text-align: right'>1</td>
</tr>
<tr>
<td>b</td>
<td style='text-align: right'>2</td>
</tr>
<tr>
<td>c</td>
<td style='text-align: right'>2</td>
</tr>
</tbody>
</table>
"""
actual = etl.wrap(table)._repr_html_()
for l1, l2 in zip(expect.split('\n'), actual.split('\r\n')):
print l1, l2
eq_(l1, l2)
def test_basics():
t1 = (('foo', 'bar'), ('A', 1), ('B', 2))
w1 = etl.wrap(t1)
eq_(('foo', 'bar'), w1.header())
eq_(petl.header(w1), w1.header())
ieq((('A', 1), ('B', 2)), w1.data())
ieq(petl.data(w1), w1.data())
w2 = w1.cut('bar', 'foo')
expect2 = (('bar', 'foo'), (1, 'A'), (2, 'B'))
ieq(expect2, w2)
ieq(petl.cut(w1, 'bar', 'foo'), w2)
w3 = w1.cut('bar', 'foo').cut('foo', 'bar')
ieq(t1, w3)
def test_basics():
t1 = (('foo', 'bar'),
('A', 1),
('B', 2))
w1 = etl.wrap(t1)
eq_(('foo', 'bar'), w1.header())
eq_(petl.header(w1), w1.header())
ieq((('A', 1), ('B', 2)), w1.data())
ieq(petl.data(w1), w1.data())
w2 = w1.cut('bar', 'foo')
expect2 = (('bar', 'foo'),
(1, 'A'),
(2, 'B'))
ieq(expect2, w2)
ieq(petl.cut(w1, 'bar', 'foo'), w2)
w3 = w1.cut('bar', 'foo').cut('foo', 'bar')
ieq(t1, w3)
# -*- coding: utf-8 -*- # <nbformat>3.0</nbformat> # <markdowncell> # Notes supporting [issue #256](https://github.com/alimanfoo/petl/issues/256). # <codecell> import petl.interactive as etl # <codecell> t1 = etl.wrap([['foo', 'bar'], [1, 'a'], [2, 'b']]) t1 # <codecell> t2 = etl.wrap([['foo', 'bar'], [1, 'a'], [2, 'c']]) t2 # <codecell> t3 = etl.merge(t1, t2, key='foo') t3 # <markdowncell> # The problem with the above is that you cannot tell from inspecting *t3* alone which conflicting value comes from which source. # # A workaround as suggested by [@pawl](https://github.com/pawl) is to use the [*conflicts()*](http://petl.readthedocs.org/en/latest/#petl.conflicts) function, e.g.:
# -*- coding: utf-8 -*- # <nbformat>3.0</nbformat> # <markdowncell> # Notes supporting [issue #256](https://github.com/alimanfoo/petl/issues/256). # <codecell> import petl.interactive as etl # <codecell> t1 = etl.wrap([["foo", "bar"], [1, "a"], [2, "b"]]) t1 # <codecell> t2 = etl.wrap([["foo", "bar"], [1, "a"], [2, "c"]]) t2 # <codecell> t3 = etl.merge(t1, t2, key="foo") t3 # <markdowncell> # The problem with the above is that you cannot tell from inspecting *t3* alone which conflicting value comes from which source. # # A workaround as suggested by [@pawl](https://github.com/pawl) is to use the [*conflicts()*](http://petl.readthedocs.org/en/latest/#petl.conflicts) function, e.g.:
class CustomTransformer(object):
def __init__(self, source):
self.source = source
def __iter__(self):
it = iter(self.source)
# construct new header
source_fields = it.next()
out_fields = ('category',) + tuple(source_fields)
yield out_fields
# transform data
current_category = None
for row in it:
if len(row) == 1:
current_category = row[0]
else:
yield (current_category,) + tuple(row)
# <codecell>
tbl5 = CustomTransformer(tbl1)
# <codecell>
# just so it formats nicely as HTML in the notebook...
etl.wrap(tbl5)
