def get_reader(Reader=None, Inputter=None, Outputter=None, numpy=True, **kwargs):
"""Initialize a table reader allowing for common customizations. Most of the
default behavior for various parameters is determined by the Reader class.
:param Reader: Reader class (default= :class:`BasicReader`)
:param Inputter: Inputter class
:param Outputter: Outputter class
:param numpy: use the NumpyOutputter class else use BaseOutputter (default=True)
:param delimiter: column delimiter string
:param comment: regular expression defining a comment line in table
:param quotechar: one-character string to quote fields containing special characters
:param header_start: line index for the header line not counting comment lines
:param data_start: line index for the start of data not counting comment lines
:param data_end: line index for the end of data (can be negative to count from end)
:param converters: dict of converters
:param data_Splitter: Splitter class to split data columns
:param header_Splitter: Splitter class to split header columns
:param names: list of names corresponding to each data column
:param include_names: list of names to include in output (default=None selects all names)
:param exclude_names: list of names to exlude from output (applied after ``include_names``)
:param fill_values: specification of fill values for bad or missing table values
:param fill_include_names: list of names to include in fill_values (default=None selects all names)
:param fill_exclude_names: list of names to exlude from fill_values (applied after ``fill_include_names``)
"""
# This function is a light wrapper around core._get_reader to provide a public interface
# with a default Reader.
if Reader is None:
Reader = basic.BasicReader
reader = core._get_reader(Reader, Inputter=Inputter, Outputter=Outputter, numpy=numpy, **kwargs)
return reader
def get_reader(Reader=None, Inputter=None, Outputter=None, numpy=True, **kwargs):
"""Initialize a table reader allowing for common customizations. Most of the
default behavior for various parameters is determined by the Reader class.
:param Reader: Reader class (default= :class:`BasicReader`)
:param Inputter: Inputter class
:param Outputter: Outputter class
:param numpy: use the NumpyOutputter class else use BaseOutputter (default=True)
:param delimiter: column delimiter string
:param comment: regular expression defining a comment line in table
:param quotechar: one-character string to quote fields containing special characters
:param header_start: line index for the header line not counting comment lines
:param data_start: line index for the start of data not counting comment lines
:param data_end: line index for the end of data (can be negative to count from end)
:param converters: dict of converters
:param data_Splitter: Splitter class to split data columns
:param header_Splitter: Splitter class to split header columns
:param names: list of names corresponding to each data column
:param include_names: list of names to include in output (default=None selects all names)
:param exclude_names: list of names to exlude from output (applied after ``include_names``)
:param fill_values: specification of fill values for bad or missing table values
:param fill_include_names: list of names to include in fill_values (default=None selects all names)
:param fill_exclude_names: list of names to exlude from fill_values (applied after ``fill_include_names``)
"""
# This function is a light wrapper around core._get_reader to provide a public interface
# with a default Reader.
if Reader is None:
Reader = basic.BasicReader
reader = core._get_reader(Reader, Inputter=Inputter, Outputter=Outputter, numpy=numpy, **kwargs)
return reader
def get_cols(self, lines):
"""Initialize the header Column objects from the table ``lines``.
Based on the previously set Header attributes find or create the column names.
Sets ``self.cols`` with the list of Columns. This list only includes the actual
requested columns after filtering by the include_names and exclude_names
attributes. See ``self.names`` for the full list.
:param lines: list of table lines
:returns: list of table Columns
"""
if self.names is None:
# No column names supplied so first try to get them from NumPy structured array
try:
self.names = lines.dtype.names
except AttributeError:
# Still no col names available so auto-generate them
try:
first_data_vals = next(iter(lines))
except StopIteration:
raise core.InconsistentTableError('No data lines found so cannot autogenerate column names')
n_data_cols = len(first_data_vals)
self.names = [self.auto_format % i for i in range(1, n_data_cols+1)]
names = set(self.names)
if self.include_names is not None:
names.intersection_update(self.include_names)
if self.exclude_names is not None:
names.difference_update(self.exclude_names)
self.cols = [core.Column(name=x, index=i) for i, x in enumerate(self.names)
if x in names]
# ``lines`` could be one of: NumPy recarray, DictLikeNumpy obj, Python
# list of lists. If NumPy recarray then set col.type accordingly. In
# the other two cases convert the data values to strings so the usual
# data converter processing will get the correct type.
if core.has_numpy and isinstance(lines, numpy.ndarray):
for col in self.cols:
type_name = lines[col.name].dtype.name
if 'int' in type_name:
col.type = core.IntType
elif 'float' in type_name:
col.type = core.FloatType
elif 'string' in type_name:
col.type = core.StrType
else:
basic_reader = core._get_reader(Reader=basic.BasicReader,
names=[col.name for col in self.cols], quotechar="'")
data_in = tuple(' '.join(repr(vals[col.index]) for col in self.cols)
for vals in lines)
data_out = basic_reader.read(data_in)
for col, data_col in zip(self.cols, basic_reader.cols):
col.type = data_col.type
def read(self, table):
output = core.BaseReader.read(self, table)
if core.has_numpy:
reader = core._get_reader(Reader=basic.NoHeaderReader, comment=r'(?!#K)',
names = ['temp1','keyword','temp2','value','unit','format'])
headerkeywords = reader.read(self.comment_lines)
for line in headerkeywords:
self.keywords.append(core.Keyword(line['keyword'], line['value'],
units=line['unit'], format=line['format']))
self.table = output
self.cols = self.header.cols
return self.table
def read(self, table):
output = core.BaseReader.read(self, table)
if core.has_numpy:
reader = core._get_reader(
Reader=basic.NoHeaderReader,
comment=r'(?!#K)',
names=['temp1', 'keyword', 'temp2', 'value', 'unit', 'format'])
headerkeywords = reader.read(self.comment_lines)
for line in headerkeywords:
self.keywords.append(
core.Keyword(line['keyword'],
line['value'],
units=line['unit'],
format=line['format']))
self.table = output
self.cols = self.header.cols
return self.table
