def convert(line):
s = OrderedDict([
('==', 'Equal'),
('!=', 'NotEqual'),
('!~=', 'NotAlmostEqual'),
('~=', 'AlmostEqual'),
(lambda line: bool(line.count('>') > 1), partial(_convert, '>', 'Greater')),
(lambda line: bool(line.count('<') > 1), partial(_convert, '<', 'Less')),
('>=', 'GreaterEqual'),
('<=', 'LessEqual'),
('>', 'Greater'),
('<', 'Less'),
('raises', lambda line: ['with self.assertRaises(' + line.split('raises')[1].strip() + '):', ' ' + line.split('raises')[0].strip()]),
(' is not instanceof ', 'NotIsInstance'),
(' is instanceof ', 'IsInstance'),
('for ', lambda line: line),
(' not in ', 'NotIn'),
(' in ', 'In'),
(' is not None', 'IsNotNone'),
(' is None', 'IsNone'),
(' is not ', 'IsNot'),
(' is ', 'Is'),
])
def to_lambda(i):
def to_code(k, v, line):
l, op, r = line.rpartition(k)
params = ', '.join(map(strip, (l, r))).rstrip().rstrip(',')
return 'self.assert' + v + '(' + params + ')'
k, v = i
new_v = v if callable(v) else partial(to_code, k, v)
del s[k]
if callable(k):
s[k] = new_v
else:
s[lambda line: k in line] = new_v
map(to_lambda, s.items())
matches = filter(lambda k: k(line), s.keys())
return s[matches[0]](line) if len(matches) else line
class Introspector(object):
def __init__(self, **kwargs):
self.cols = OrderedDict()
self.col_order = OrderedDict()
if 'reader_settings' in kwargs:
self.reader_settings = kwargs['reader_settings']
else:
self.reader_settings = {}
def from_stream(self, stream, limit=None):
for row_count, row in enumerate(OrderedDictReader(stream, **self.reader_settings)):
if limit is None or row_count < limit:
self.introspect_row(row)
else:
break
return self
def introspect_row(self, row):
for (order, (key, val)) in enumerate(row.items()):
self.set_col(key, val, order)
def ordered_cols(self):
'''Create a dictionary that brings together cols and col_order.'''
return dict([(key, (self.cols[key], self.col_order[key])) for key in self.cols.keys()])
def set_col(self, key, value, order):
if key in self.cols:
cast = self.cols[key]
else:
cast = None
# If we haven't done an initial cast, start at most restrictive and move down.
if cast == None:
if self.passes_int(value):
cast = "INT"
elif self.passes_float(value):
cast = "FLOAT"
elif self.passes_char(value):
cast = "CHAR"
else:
cast = "TEXT"
# If we've already cast this column, see if the cast can remain.
elif cast == "INT":
if self.passes_int(value):
cast = "INT"
elif self.passes_float(value):
cast = "FLOAT"
elif self.passes_char(value):
cast = "CHAR"
else:
cast = "TEXT"
elif cast == "FLOAT":
if self.passes_float(value):
cast = "FLOAT"
elif self.passes_char(value):
cast = "CHAR"
else:
cast = "TEXT"
elif cast == "CHAR":
if not self.passes_char(value):
cast = "TEXT"
else:
cast = "TEXT"
self.cols[key] = cast
self.col_order[key] = order
def passes_char(self, value):
if isinstance(value, basestring):
if len(value) <= 100:
return True
return False
def passes_int(self, value, null=True):
if re.match('\d{1,3},?\d{,3}?', value):
value = value.replace(",", "")
if null and value is None:
return True
try:
return str(int(value)) == str(value)
except ValueError:
return False
def passes_float(self, value, null=True):
if re.match('\d{1,3},?\d{,3}?', value):
value = value.replace(",", "")
if null and value is None:
return True
try:
float(value)
return True
except ValueError:
return False
