def test_duplicate_key():
text_str = """
\\newacronym{thekey}{OTHER}{Abbreviation of other}
\\newglossaryentry{thekey}{
name={name},
description={the description},
type={symbols}
}
"""
with pytest.raises(KeyError):
parse_tex(text_str=text_str)
def test_parse_gterms():
text_str = """
\\newglossaryentry{otherkey}{
name={other name},
description={the description of other}
}
\\newglossaryentry{thekey}{
name={name},
description={the description},
type={symbols}
}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert acronyms == {}
assert gterms == {
"otherkey": {
"description": "the description of other",
"name": "other name"
},
"thekey": {
"description": "the description",
"name": "name",
"type": "symbols"
},
}
def load_tex(self, text_str=None, path=None, encoding='utf8',
skip_ioerrors=False, ignore_unknown_types=True):
"""load a tex file
Parameters
----------
text_str=None: str or None
string representing the bib file contents
path=None: str or None
path to bibfile
bibdb=None: bibtexparser.bibdatabase.BibDatabase or None
encoding="utf8": str
bib file encoding
skip_ioerrors: bool
if False, an IOError will be raised if
newglossaryterm or newacronym is badly formatted
ignore_unknown_types: bool
if True, strip unknown types, otherwise raise a ValueError
Notes
-----
the texsoup package is required.
if a newglossaryterm has field 'type={symbols}', then
it will be loaded as a symbol
"""
from ipypublish.bib2glossary.parse_tex import parse_tex
gterms, acronyms = parse_tex(
text_str=text_str, path=path, encoding=encoding,
skip_ioerrors=skip_ioerrors
)
entries = {}
for key, fields in gterms.items():
fields["ENTRYTYPE"] = ETYPE_GLOSS
if fields.get("type", None) == "symbols":
fields["ENTRYTYPE"] = ETYPE_SYMBOL
fields.pop("type")
elif "type" in fields:
if not ignore_unknown_types:
raise ValueError("the 'type' is not recognised: "
"{}".format(fields['type']))
fields.pop("type")
fields["ID"] = key
entry = BibGlossEntry(fields)
entries[entry.key] = entry
for key, fields in acronyms.items():
fields["ENTRYTYPE"] = ETYPE_ACRONYM
fields["ID"] = key
entry = BibGlossEntry(fields)
entries[entry.key] = entry
self._entries = entries
return True
def test_ioerror_skip():
text_str = """
\\newacronym{thekey}{Abbreviation of other}
\\newacronym{thekey2}{ABBR}{Abbreviation of other}
"""
gterms, acronyms = parse_tex(text_str=text_str, skip_ioerrors=True)
assert gterms == {}
assert acronyms == {
"thekey2": {
"abbreviation": "ABBR",
"longname": "Abbreviation of other"
}
}
def test_ioerror_skip():
text_str = """
\\newacronym{thekey}{Abbreviation of other}
\\newacronym{thekey2}{ABBR}{Abbreviation of other}
"""
gterms, acronyms = parse_tex(text_str=text_str, skip_ioerrors=True)
assert gterms == {}
assert acronyms == {
"thekey2": {
'abbreviation': 'ABBR',
'longname': 'Abbreviation of other'
}
}
def test_parse_acronyms():
text_str = """
\\newacronym{otherkey}{OTHER}{Abbreviation of other}
\\newacronym{thekey}{ABRV}{Abbreviation}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert gterms == {}
assert acronyms == {
'otherkey': {
'abbreviation': 'OTHER',
'longname': 'Abbreviation of other'},
'thekey': {
'abbreviation': 'ABRV',
'longname': 'Abbreviation'}
}
def test_parse_acronyms():
text_str = """
\\newacronym{otherkey}{OTHER}{Abbreviation of other}
\\newacronym{thekey}{ABRV}{Abbreviation}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert gterms == {}
assert acronyms == {
"otherkey": {
"abbreviation": "OTHER",
"longname": "Abbreviation of other"
},
"thekey": {
"abbreviation": "ABRV",
"longname": "Abbreviation"
},
}
def test_parse_acronyms_with_options():
text_str = """
\\newacronym[description={a description}]{otherkey}{OTHER}{Abbreviation of other}
\\newacronym[plural={ABRVs},longplural={Abbreviations}]{thekey}{ABRV}{Abbreviation}
""" # noqa: E501
gterms, acronyms = parse_tex(text_str=text_str)
assert gterms == {}
assert acronyms == {
'otherkey': {
'abbreviation': 'OTHER',
'longname': 'Abbreviation of other',
'description': 'a description'},
'thekey': {
'abbreviation': 'ABRV',
'longname': 'Abbreviation',
'longplural': 'Abbreviations',
'plural': 'ABRVs'}
}
def test_parse_acronyms_with_options():
text_str = """
\\newacronym[description={a description}]{otherkey}{OTHER}{Abbreviation of other}
\\newacronym[plural={ABRVs},longplural={Abbreviations}]{thekey}{ABRV}{Abbreviation}
""" # noqa: E501
gterms, acronyms = parse_tex(text_str=text_str)
assert gterms == {}
assert acronyms == {
"otherkey": {
"abbreviation": "OTHER",
"longname": "Abbreviation of other",
"description": "a description",
},
"thekey": {
"abbreviation": "ABRV",
"longname": "Abbreviation",
"longplural": "Abbreviations",
"plural": "ABRVs",
},
}
def test_parse_mixed():
text_str = """
\\newacronym{otherkey}{OTHER}{Abbreviation of other}
\\newglossaryentry{thekey}{
name={name},
description={the description},
type={symbols}
}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert acronyms == {
'otherkey': {
'abbreviation': 'OTHER',
'longname': 'Abbreviation of other'}
}
assert gterms == {
'thekey': {
'description': 'the description',
'name': 'name',
'type': 'symbols'}
}
def test_parse_mixed():
text_str = """
\\newacronym{otherkey}{OTHER}{Abbreviation of other}
\\newglossaryentry{thekey}{
name={name},
description={the description},
type={symbols}
}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert acronyms == {
"otherkey": {
"abbreviation": "OTHER",
"longname": "Abbreviation of other"
}
}
assert gterms == {
"thekey": {
"description": "the description",
"name": "name",
"type": "symbols"
}
}
def test_parse_gterms():
text_str = """
\\newglossaryentry{otherkey}{
name={other name},
description={the description of other}
}
\\newglossaryentry{thekey}{
name={name},
description={the description},
type={symbols}
}
"""
gterms, acronyms = parse_tex(text_str=text_str)
assert acronyms == {}
assert gterms == {
'otherkey': {
'description': 'the description of other',
'name': 'other name'},
'thekey': {
'description': 'the description',
'name': 'name',
'type': 'symbols'}
}
def test_gterm_ioerror():
text_str = """
\\newglossaryentry{}
"""
with pytest.raises(IOError):
parse_tex(text_str=text_str)
def test_acronym_ioerror():
text_str = """
\\newacronym{thekey}{Abbreviation of other}
"""
with pytest.raises(IOError):
parse_tex(text_str=text_str)