Esempio n. 1
0
def test_extract_with_tsv_snippets(tmpdir: py._path.local.LocalPath,
                                   base_data: typing.Dict[str, str]) -> None:
    xml_data = """
<HouseFile>
    <ProgramInformation>
        <Client>
            <StreetAddress>
                <PostalCode>H0H 0H0</PostalCode>
            </StreetAddress>
        </Client>
    </ProgramInformation>
    <Program>
        <Results>
            <Tsv>
                <ERSRating value='257' />
            </Tsv>
        </Results>
    </Program>
</HouseFile>
    """
    base_data['RAW_XML'] = xml_data

    input_file = tmpdir.join('input.csv')
    with open(input_file, 'w') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=list(base_data.keys()))
        writer.writeheader()
        writer.writerow(base_data)

    output = next(extractor.extract_data(str(input_file)))
    assert output
    assert output['ersRating'] == '257'
    assert output['forwardSortationArea'] == 'H0H'
Esempio n. 2
0
def energuide_zip_fixture(tmpdir: py._path.local.LocalPath,
                          energuide_fixture: str) -> str:
    outfile = os.path.join(tmpdir, 'scrubbed_random_sample_xml.zip')

    data = extractor.extract_data(energuide_fixture)
    extractor.write_data(data, outfile)
    return outfile
Esempio n. 3
0
def test_extract_with_snippets(tmpdir: py._path.local.LocalPath,
                               base_data: typing.Dict[str, str]) -> None:
    xml_data = """
<HouseFile><House><Components><Ceiling>
    <Label>Attic</Label>
    <Construction>
        <Type>
            <English>Attic/gable</English>
            <French>Combles/pignon</French>
        </Type>
        <CeilingType idref="Code 3" rValue="2.9463" nominalInsulation="2.864">2401191000</CeilingType>
    </Construction>
</Ceiling></Components></House></HouseFile>
    """

    base_data['RAW_XML'] = xml_data

    input_file = tmpdir.join('input.csv')
    with open(input_file, 'w') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=list(base_data.keys()))
        writer.writeheader()
        writer.writerow(base_data)

    output = next(extractor.extract_data(str(input_file)))
    assert output
    assert output['ceilings']
    assert output['upgrades'] == []
Esempio n. 4
0
def test_empty_to_none(
        tmpdir: py._path.local.LocalPath,
        nullable_data: typing.Dict[str, typing.Optional[str]]) -> None:
    filepath = os.path.join(tmpdir, 'sample.csv')
    _write_csv(filepath, nullable_data)
    output = extractor.extract_data(filepath)
    row = next(output)
    assert row
    assert row['MODIFICATIONDATE'] is None
Esempio n. 5
0
def extract(infile: str, outfile: str, progress: bool) -> None:
    LOGGER.info(f'Extracting data from {infile} into {outfile}')
    if os.path.exists(outfile):
        LOGGER.warning(f'Warning: file {outfile} exists. Overwriting.')
    extracted = extractor.extract_data(infile, show_progress=progress)
    records_written, records_failed = extractor.write_data(extracted, outfile)
    LOGGER.info(
        f'Finished extracting data into {outfile}. '
        f'Successfully written: {records_written}. Failed: {records_failed}')
Esempio n. 6
0
def energuide_zip_fixture(tmpdir: py._path.local.LocalPath, energuide_fixture: str) -> str:
    outfile = f'{tmpdir}/randomized_energuide_data.zip'

    data = extractor.extract_data(energuide_fixture)
    extractor.write_data(data, outfile)
    return outfile
Esempio n. 7
0
def test_extract_missing(missing_filepath: str) -> None:
    output = extractor.extract_data(missing_filepath)
    result = [x for x in output]
    assert result == [None]
Esempio n. 8
0
def test_purge_unknown(extra_filepath: str) -> None:
    output = next(extractor.extract_data(extra_filepath))
    assert output
    item = dict(output)
    assert 'other_1' not in item
Esempio n. 9
0
def test_extract_valid(valid_filepath: str) -> None:
    output = next(extractor.extract_data(valid_filepath))
    assert output
    item = dict(output)
    assert 'EVAL_ID' in item