def test_multiline_fields_split(self):
f = StringIO(preamble_s + "PT abc\nSO J.Whatever\nAF Here\n be\n"
" dragons\nER\nEF")
r = PlainTextReader(f)
expected = {"PT": "abc", "SO": "J.Whatever", "AF": "Here; be; dragons"}
assert_dict_equal(next(r), expected)
f.seek(0)
r = PlainTextReader(f, subdelimiter="##")
expected["AF"] = "Here##be##dragons"
assert_dict_equal(next(r), expected)
def test_multiline_fields_nosplit(self):
f = StringIO(preamble_s + "PT abc\nSC Here; there\n be dragons; Yes"
"\nER\nEF")
r = PlainTextReader(f)
expected = {"PT": "abc", "SC": "Here; there be dragons; Yes"}
assert_dict_equal(next(r), expected)
def test_multiple_records(self):
f = StringIO(preamble_s + "PT abc\nAU xyz\nER\n\nPT abc2\n AU xyz2\n"
"AB abstract\nER\nEF")
r = PlainTextReader(f)
results = list(r)
expected = [{"PT": "abc", "AU": "xyz"},
{"PT": "abc2", "AU": "xyz2", "AB": "abstract"}]
assert_equal(len(results), len(expected))
for result, exp in zip(results, expected):
assert_dict_equal(result, exp)
def test_ignore_empty_lines(self):
f = StringIO(preamble_s + "PT abc\n\nAU xyz\nER\nEF")
r = PlainTextReader(f)
expected = {"PT": "abc", "AU": "xyz"}
assert_dict_equal(next(r), expected)
def test_forgotten_EF(self):
f = StringIO(preamble_s + "PT abc\nAU xuz\nER\n\nPT abc2\nER")
r = PlainTextReader(f)
list(r)
def test_wrong_version(self):
f = StringIO("FN Thomson Reuters Web of Science\nVR 1.1")
PlainTextReader(f)
def test_wrong_format(self):
f = StringIO("XY Bla\nVR 1.0")
PlainTextReader(f)
def test_wos_plaintext(self):
# utf-8-sig = UTF-8 with BOM
with open("data/wos_plaintext.txt", "rt", encoding="utf-8-sig") as fh:
r = PlainTextReader(fh)
for record in r:
pass