def createReader(readable, **keywords):
"""
A reader fitting the contents of ``readable``. Supported formats are
delimited data (such as CSV), ODS and Excel. When iterating the reader,
it returns a Python array for each row of data.
"""
# TODO: Get rid of circular import.
import _parsers
assert readable is not None
encoding = keywords.get("encoding", DEFAULT_ENCODING)
assert encoding is not None
result = None
icdHeader = readable.read(4)
_log.debug(u"header=%r", icdHeader)
if icdHeader == _ODS_HEADER:
# Consider ICD to be ODS.
readable.seek(0)
result = _parsers.odsReader(readable)
else:
icdHeader += readable.read(4)
readable.seek(0)
if _tools.isEqualBytes(icdHeader, _EXCEL_HEADER):
# Consider ICD to be Excel.
result = _parsers.excelReader(readable)
else:
# Consider ICD to be CSV.
dialect = _parsers.DelimitedDialect()
dialect.lineDelimiter = _parsers.AUTO
dialect.itemDelimiter = _parsers.AUTO
dialect.quoteChar = "\""
dialect.escapeChar = "\""
result = _parsers.delimitedReader(readable, dialect, encoding)
return result
def testIcdCustomersXls(self):
icdCustomersIcdXlsPath = dev_test.getTestIcdPath("customers.xls")
readable = open(icdCustomersIcdXlsPath, "rb")
try:
for row in _parsers.excelReader(readable):
self.assertTrue(row is not None)
self.assertTrue(len(row))
except _parsers.CutplaceXlrdImportError:
_log.warning("ignored ImportError caused by missing xlrd")
finally:
readable.close()
def testIcdCustomersXls(self):
icdCustomersIcdXlsPath = dev_test.getTestIcdPath("customers.xls")
readable = open(icdCustomersIcdXlsPath, "rb")
try:
for row in _parsers.excelReader(readable):
self.assertTrue(row is not None)
self.assertTrue(len(row))
except _parsers.CutplaceXlrdImportError:
_log.warning("ignored ImportError caused by missing xlrd")
finally:
readable.close()
def testCellValue(self):
fieldTypesXlsPath = dev_test.getTestInputPath("fieldtypes.xls")
readable = open(fieldTypesXlsPath, "rb")
try:
titleRowSkipped = False
for row in _parsers.excelReader(readable):
self.assertTrue(row is not None)
self.assertTrue(len(row) == 3, "row=%r" % row)
if titleRowSkipped:
self.assertEqual(row[1], row[2], "row=%r" % row)
else:
titleRowSkipped = True
except _parsers.CutplaceXlrdImportError:
_log.warning("ignored ImportError caused by missing xlrd")
finally:
readable.close()
def testCellValue(self):
fieldTypesXlsPath = dev_test.getTestInputPath("fieldtypes.xls")
readable = open(fieldTypesXlsPath, "rb")
try:
titleRowSkipped = False
for row in _parsers.excelReader(readable):
self.assertTrue(row is not None)
self.assertTrue(len(row) == 3, "row=%r" % row)
if titleRowSkipped:
self.assertEqual(row[1], row[2], "row=%r" % row)
else:
titleRowSkipped = True
except _parsers.CutplaceXlrdImportError:
_log.warning("ignored ImportError caused by missing xlrd")
finally:
readable.close()
