def analyze_csv(url, sample=1000):
try:
fileobj = urlopen(url)
row_set = CSVRowSet('data', fileobj, window=sample)
sample = list(row_set.sample)
headers, sample = sample[0], sample[1:]
# values = frequent_values(sample)
types = type_guess(sample[500:], types=LIMITED_TYPES)
mapping = {}
for header, type_ in zip(headers, types):
type_ = repr(type_).lower()
name = slugify(header.value).lower()
meta = {
'label': header.value,
'column': header.value,
'datatype': type_
}
if type_ in ['decimal', 'integer', 'float']:
meta['type'] = 'measure'
meta['datatype'] = 'float'
elif type_.startswith('date'):
meta['type'] = 'date'
meta['datatype'] = 'date'
else:
meta['type'] = 'attribute'
mapping[name] = meta
return {'columns': [h.value for h in headers], 'mapping': mapping}
except Exception as e:
log.exception(e)
return {'error': unicode(e)}
def generate_mapping(fileobj, sample=2000):
row_set = CSVRowSet('data', fileobj, window=sample)
sample = list(row_set.sample)
headers, sample = sample[0], sample[1:]
values = frequent_values(sample)
types = type_guess(sample)
mapping = {}
for header, type_, value in zip(headers, types, values):
type_ = repr(type_).lower()
name = slugify(header.value).lower()
meta = {
'label': header.value,
'column': header.value,
'common_values': value,
'datatype': type_
}
if type_ in ['decimal', 'integer', 'float']:
meta['type'] = 'measure'
meta['datatype'] = 'float'
elif type_ in ['date']:
meta['type'] = 'date'
meta['datatype'] = 'date'
else:
meta['type'] = 'value'
mapping[name] = meta
return mapping
def analyze_csv(url, sample=1000):
try:
fileobj = urlopen(url)
row_set = CSVRowSet('data', fileobj, window=sample)
sample = list(row_set.sample)
headers, sample = sample[0], sample[1:]
#values = frequent_values(sample)
types = type_guess(sample[500:], types=LIMITED_TYPES)
mapping = {}
for header, type_ in zip(headers, types):
type_ = repr(type_).lower()
name = slugify(header.value).lower()
meta = {
'label': header.value,
'column': header.value,
'datatype': type_
}
if type_ in ['decimal', 'integer', 'float']:
meta['type'] = 'measure'
meta['datatype'] = 'float'
elif type_.startswith('date'):
meta['type'] = 'date'
meta['datatype'] = 'date'
else:
meta['type'] = 'attribute'
mapping[name] = meta
return {'columns': [h.value for h in headers],
'mapping': mapping}
except Exception, e:
return {'error': unicode(e)}
def make_name(dataset, label):
from openspending.lib.util import slugify
from itertools import count
name = name_orig = slugify(label)
view = View.by_name(dataset, name)
for i in count():
if view is None:
return name
name = name_orig + str(i)
view = View.by_name(dataset, name)
def make_name(dataset, label):
from openspending.lib.util import slugify
from itertools import count
name = name_orig = slugify(label)
view = View.by_name(dataset, name)
for i in count():
if view is None:
return name
name = name_orig + str(i)
view = View.by_name(dataset, name)
def entity_slug(entity):
'''generate an ascii slug for an entity.
``entity``
A dict-like ``entity`` object
Returns: `str`
'''
slug_source = entity.get('label', '')
if not slug_source:
slug_source = entity.get('name', '')
if not slug_source:
slug_source = str(entity['_id'])
return slugify(slug_source)
def entity_slug(entity):
"""generate an ascii slug for an entity.
``entity``
A dict-like ``entity`` object
Returns: `str`
"""
slug_source = entity.get("label", "")
if not slug_source:
slug_source = entity.get("name", "")
if not slug_source:
slug_source = str(entity["_id"])
return slugify(slug_source)
def entity_slug(entity):
'''generate an ascii slug for an entity.
``entity``
A :class:`openspending.model.Entity` object
Returns: `str`
'''
slug_source = entity.get('label', '')
if not slug_source:
slug_source = entity.get('name', '')
if not slug_source:
slug_source = str(entity['_id'])
return slugify(slug_source)
def entity_slug(entity):
'''generate an ascii slug for an entity.
``entity``
A dict-like ``entity`` object
Returns: `str`
'''
slug_source = entity.get('label', '')
if not slug_source:
slug_source = entity.get('name', '')
if not slug_source:
slug_source = str(entity['_id'])
return slugify(slug_source)
def test_slugify():
h.assert_equal(util.slugify(u'foo'), 'foo')
h.assert_equal(util.slugify(u'fóo'), 'foo')
h.assert_equal(util.slugify(u'fóo&bañ'), 'foo-ban')
def test_slugify():
h.assert_equal(util.slugify(u'foo'), 'foo')
h.assert_equal(util.slugify(u'fóo'), 'foo')
h.assert_equal(util.slugify(u'fóo&bañ'), 'foo-ban')
def test_slugify(self):
assert util.slugify(u'foo') == 'foo'
assert util.slugify(u'fóo') == 'foo'
assert util.slugify(u'fóo&bañ') == 'foo-ban'
