def test_encoding_with_homogenize(self):
with codecs.open(
'tests/data/encoding.bib', 'r', 'utf-8'
) as bibfile:
bib = BibTexParser(
bibfile.read(), customization=homogenize_latex_encoding
)
res = bib.get_entry_list()
expected = [
{
'keywords': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'abstract': 'This is an abstract. This line should be long enough to test\nmultilines... and with a french {\\\'e}rudit word',
'year': '2013',
'journal': 'El{\\\'e}mentaire',
'ID': 'Cesar_2013',
'pages': '12-23',
'title': '{A}n amazing title: {\\`a}',
'comments': 'A comment',
'author': 'Jean C{\\\'e}sar',
'volume': '12',
'month': 'jan',
}
]
self.assertEqual(res, expected)
def test_article_cust_latex(self):
with codecs.open(
'tests/data/article.bib', 'r', 'utf-8'
) as bibfile:
bib = BibTexParser(
bibfile.read(), customization=customizations_latex
)
res = bib.get_entry_list()
expected = [
{
'abstract': 'This is an abstract. This line should be long enough to test\nmultilines... and with a french {\\\'e}rudit word',
'ENTRYTYPE': 'article',
'pages': '12--23',
'volume': '12',
'ID': 'Cesar2013',
'year': '2013',
'author': ['C{\\\'e}sar, Jean'],
'journal': {'ID': 'NiceJournal', 'name': 'Nice Journal'},
'comments': 'A comment',
'month': 'jan',
'keyword': ['keyword1', 'keyword2'],
'title': '{A}n amazing title',
}
]
self.assertEqual(res, expected)
def test_article_comma_first(self):
with open(
'tests/data/article_comma_first.bib', 'r'
) as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'ENTRYTYPE': 'article',
'journal': 'Nice Journal',
'volume': '12',
'ID': 'Cesar2013',
'year': '2013',
'author': 'Jean Cesar',
'comments': 'A comment',
'keyword': 'keyword1, keyword2',
'title': 'An amazing title',
},
{
'ENTRYTYPE': 'article',
'journal': 'Nice Journal',
'volume': '12',
'ID': 'Baltazar2013',
'year': '2013',
'author': 'Jean Baltazar',
'comments': 'A comment',
'keyword': 'keyword1, keyword2',
'title': 'An amazing title',
},
]
self.assertEqual(res, expected)
def test_nonstandard_ignored(self):
with open('tests/data/wrong.bib', 'r') as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{'author': 'correct', 'ID': 'bar', 'ENTRYTYPE': 'article'}
]
self.assertEqual(res, expected)
def test_article_cust_order(self):
def cust(record):
record = customization.page_double_hyphen(record)
record = customization.homogenize_latex_encoding(record)
record = customization.author(record)
return record
def cust2(record):
record = customization.author(record)
record = customization.page_double_hyphen(record)
record = customization.homogenize_latex_encoding(record)
return record
with open(
'tests/data/multiple_entries.bib', 'r'
) as bibfile:
bib = BibTexParser(bibfile.read(), customization=cust)
res = bib.get_entry_list()
with open(
'tests/data/multiple_entries.bib', 'r'
) as bibfile:
bib2 = BibTexParser(bibfile.read(), customization=cust2)
res2 = bib.get_entry_list()
self.assertEqual(res, res2)
def test_features(self):
with open('tests/data/features.bib', 'r') as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'ENTRYTYPE': 'inproceedings',
'year': '2014',
'title': 'Cool Stuff',
'author': 'John',
'ID': 'mykey',
'booktitle': 'My International Conference',
}
]
self.assertEqual(res, expected)
def test_string_is_not_interpolated(self):
with open(
'tests/data/article_with_strings.bib', 'r'
) as bibfile:
bib = BibTexParser(
bibfile.read(), common_strings=True, interpolate_strings=False
)
res = bib.get_entry_list()[0]
self.assertIsInstance(res['month'], BibDataStringExpression)
self.assertEqual(len(res['month'].expr), 1)
self.assertEqual(res['month'].get_value(), 'January')
self.assertIsInstance(res['author'], BibDataStringExpression)
self.assertEqual(len(res['author'].expr), 3)
self.assertEqual(res['author'].get_value(), 'Jean César')
self.assertIsInstance(res['journal'], BibDataStringExpression)
self.assertEqual(len(res['journal'].expr), 1)
self.assertEqual(res['journal'].get_value(), 'Nice Journal')
def test_article_annotation(self):
with codecs.open(
'tests/data/article_with_annotation.bib',
'r',
'utf-8',
) as bibfile:
bib = BibTexParser(bibfile.read())
res_list = bib.get_entry_list()
res_dict = bib.get_entry_dict()
expected_list = [
{
'keyword': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'abstract': 'This is an abstract. This line should be long enough to test\nmultilines... and with a french érudit word',
'year': '2013',
'journal': 'Nice Journal',
'ID': 'Cesar2013',
'pages': '12-23',
'title': 'An amazing title',
'comments': 'A comment',
'author': 'Jean César',
'author+an': '1=highlight',
'volume': '12',
'month': 'jan',
}
]
expected_dict = {
'Cesar2013': {
'keyword': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'abstract': 'This is an abstract. This line should be long enough to test\nmultilines... and with a french érudit word',
'year': '2013',
'journal': 'Nice Journal',
'ID': 'Cesar2013',
'pages': '12-23',
'title': 'An amazing title',
'comments': 'A comment',
'author': 'Jean César',
'author+an': '1=highlight',
'volume': '12',
'month': 'jan',
}
}
self.assertEqual(res_list, expected_list)
self.assertEqual(res_dict, expected_dict)
def test_book(self):
with open('tests/data/book.bib', 'r') as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'ENTRYTYPE': 'book',
'year': '1987',
'edition': '2',
'publisher': 'Wiley Edition',
'ID': 'Bird1987',
'volume': '1',
'title': 'Dynamics of Polymeric Liquid',
'author': 'Bird, R.B. and Armstrong, R.C. and Hassager, O.',
}
]
self.assertEqual(res, expected)
def test_string_braces(self):
with codecs.open(
'tests/data/string.bib', 'r', 'utf-8'
) as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'author': 'Sang Kil Cha and Maverick Woo and David Brumley',
'ID': 'cha:oakland15',
'year': '2015',
'booktitle': 'Proceedings of the {IEEE} Symposium on Security and Privacy',
'title': '{Program-Adaptive Mutational Fuzzing}',
'ENTRYTYPE': 'inproceedings',
'pages': '725--741',
}
]
self.assertEqual(res, expected)
def test_article_protection_braces(self):
with open(
'tests/data/article_with_protection_braces.bib', 'r'
) as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'ENTRYTYPE': 'article',
'journal': '{Nice Journal}',
'volume': '12',
'pages': '12-23',
'ID': 'Cesar2013',
'year': '2013',
'month': 'jan',
'author': 'Jean César',
'comments': 'A comment',
'keyword': 'keyword1, keyword2',
'title': '{An amazing title}',
'abstract': "This is an abstract. This line should be long enough to test\nmultilines... and with a french érudit word",
}
]
self.assertEqual(res, expected)
def test_traps(self):
with codecs.open(
'tests/data/traps.bib', 'r', 'utf-8'
) as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'keywords': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'abstract': 'This is an abstract. This line should be long enough to test\nmultilines... and with a french érudit word',
'year': '2013',
'journal': 'Nice Journal',
'ID': 'Laide2013',
'pages': '12-23',
'title': '{An} amazing {title}',
'comments': 'A comment',
'author': 'Jean Laid{\\\'e},\nBen Loaeb',
'volume': 'n.s.~2',
'month': 'jan',
}
]
self.assertEqual(res, expected)
def test_string_is_interpolated(self):
with open(
'tests/data/article_with_strings.bib', 'r'
) as bibfile:
bib = BibTexParser(
bibfile.read(), common_strings=True, interpolate_strings=True
)
res = bib.get_entry_list()
expected = [
{
'keyword': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'year': '2013',
'month': 'January',
'journal': 'Nice Journal',
'ID': 'Cesar2013',
'pages': '12-23',
'title': 'An amazing title',
'comments': 'A comment',
'author': 'Jean César',
'volume': '12',
}
]
self.assertEqual(res, expected)
def test_field_name_with_dash_underscore(self):
with open(
'tests/data/article_field_name_with_underscore.bib',
'r',
) as bibfile:
bib = BibTexParser(bibfile.read())
res = bib.get_entry_list()
expected = [
{
'keyword': 'keyword1, keyword2',
'ENTRYTYPE': 'article',
'year': '2013',
'journal': 'Nice Journal',
'ID': 'Cesar2013',
'pages': '12-23',
'title': 'An amazing title',
'comments': 'A comment',
'author': 'Jean César',
'volume': '12',
'strange_field_name': 'val',
'strange-field-name2': 'val2',
}
]
self.assertEqual(res, expected)
def test_book_cust_latex(self):
with open('tests/data/book.bib', 'r') as bibfile:
bib = BibTexParser(
bibfile.read(), customization=customizations_latex
)
res = bib.get_entry_list()
expected = [
{
'ENTRYTYPE': 'book',
'year': '1987',
'edition': '2',
'publisher': 'Wiley Edition',
'ID': 'Bird1987',
'volume': '1',
'title': '{D}ynamics of {P}olymeric {L}iquid',
'author': [
'Bird, R.B.',
'Armstrong, R.C.',
'Hassager, O.',
],
}
]
self.assertEqual(res, expected)
def test_article_start_with_whitespace(self):
with open(
'tests/data/article_start_with_whitespace.bib', 'r'
) as bibfile:
bib = BibTexParser(bibfile.read())
self.assertEqual(len(bib.get_entry_list()), 2)
def test_nonstandard_not_ignored(self):
with open('tests/data/wrong.bib', 'r') as bibfile:
bib = BibTexParser(bibfile.read(), ignore_nonstandard_types=False)
res = bib.get_entry_list()
self.assertEqual(len(res), 2)
