def test_custom_parser_ok_for_subclasses():
"""
Tests that if you register a custom parser for a subclass of A, it gets correctly used to parse A (in non-strict
mode, which is the default)
:return:
"""
root_parser = RootParser()
class A:
def __init__(self, txt):
self.txt = txt
class B(A):
""" a subclass of A """
pass
def read_B_from_txt(desired_type: Type[dict], file_object: TextIOBase,
logger: Logger, *args, **kwargs) -> str:
# read the entire stream into a string
str_io = StringIO()
shutil.copyfileobj(file_object, str_io)
# only return the first character
return B(str_io.getvalue()[0])
# before registering a parser for B, only generic parsers are able to parse a A
before_capa = root_parser.get_capabilities_for_type(A)['.txt']
assert list(before_capa.keys()) == ['3_generic']
# register a parser for B
root_parser.register_parser(
SingleFileParserFunction(parser_function=read_B_from_txt,
streaming_mode=True,
supported_exts={'.txt'},
supported_types={B}))
# after registering the new parser appears in the list able to parse A
after_capa = root_parser.get_capabilities_for_type(A)['.txt']
assert str(after_capa['2_approx_match'][0]) == '<read_B_from_txt>'
a = root_parser.parse_item(get_path('b64pickle-float-1.0=True'), A)
# check that the custom parser was used, not the generic 'construct from string'
assert len(a.txt) == 1
assert a.txt == 'g'
def test_pass_parser_options(self):
"""
Passes options to the pandas parser
:return:
"""
from pandas import DataFrame
from parsyfiles import RootParser
# create a root parser
parser = RootParser()
# retrieve the parsers of interest
parsers = parser.get_capabilities_for_type(DataFrame,
strict_type_matching=False)
df_csv_parser = parsers['.csv']['1_exact_match'][0]
p_id_csv = df_csv_parser.get_id_for_options()
print('Parser id for csv is : ' + p_id_csv +
', implementing function is ' + repr(df_csv_parser._parser_func))
print('option hints : ' + df_csv_parser.options_hints())
df_xls_parser = parsers['.xls']['1_exact_match'][0]
p_id_xls = df_xls_parser.get_id_for_options()
print('Parser id for csv is : ' + p_id_xls +
', implementing function is ' + repr(df_xls_parser._parser_func))
print('option hints : ' + df_xls_parser.options_hints())
from parsyfiles import create_parser_options, add_parser_options
# configure the DataFrame parsers to automatically parse dates and use the first column as index
opts = create_parser_options()
opts = add_parser_options(opts, 'read_df_or_series_from_csv', {
'parse_dates': True,
'index_col': 0
})
opts = add_parser_options(opts, 'read_dataframe_from_xls',
{'index_col': 0})
dfs = parser.parse_collection(
fix_path('./test_data/demo/ts_collection'),
DataFrame,
options=opts)
print(dfs)