def test_skip(self):
obj = XLSXObject(data_path("data.xlsx"), FieldList("number", "name"),
skip_rows=2)
self.assertEqual(["number", "name"], obj.fields.names())
rows = list(obj.rows())
self.assertEqual(2, len(obj))
self.assertEqual(2, len(rows))
self.assertSequenceEqual([3.0, "Cecil"], rows[0])
def __init__(self,
resource=None,
fields=None,
sheet=0,
encoding=None,
skip_rows=0,
has_header=True):
"""Creates a XLSX spreadsheet data source stream.
Attributes:
* resource: file name, URL or file-like object
* sheet: sheet index number (as int) or sheet name
* has_header: flag determining whether first line contains header or
not. ``True`` by default.
"""
if isinstance(resource, openpyxl.Workbook):
self.workbook = resource
else:
self.workbook = _load_workbook(resource)
if isinstance(sheet, int):
self.sheet = self.workbook.worksheets[sheet]
elif isinstance(sheet, str):
self.sheet = self.workbook[sheet]
else:
raise ArgumentError('sheet has to be a string or an integer')
if has_header:
self.first_row = skip_rows + 1
else:
self.first_row = skip_rows
if fields:
self.fields = fields
else:
rows = enumerate(self.sheet.rows)
first_row = next(dropwhile(lambda x: x[0] < self.first_row,
rows))[1]
if has_header:
header_row = next(self.sheet.rows)
names = [str(c.value) for c in header_row]
else:
names = ['col%d' % i for i in range(len(first_row))]
self.fields = FieldList()
for name, cell in zip(names, first_row):
if cell.is_date:
storage_type = 'date'
else:
storage_type = CELL_TYPES.get(cell.data_type, 'unknown')
field = Field(name, storage_type=storage_type)
self.fields.append(field)
def test_no_header(self):
with self.assertRaises(ArgumentError):
obj = CSVSource(data_path("fruits-sk.csv"), read_header=False)
fields = FieldList("id", "fruit", "type")
obj = CSVSource(data_path("fruits-sk.csv"),
read_header=False,
fields=fields)
self.assertEqual(["id", "fruit", "type"], obj.fields.names())
rows = list(obj.rows())
self.assertEqual(17, len(rows))
self.assertEqual(["id", "fruit", "type"], rows[0])
obj.release()
