def parsePrimitiveCategory(chunks, primitives, families, var):
"""
Parse a primitive category
If the primitive is the special category 'var', replace it with the
correct `CCGVar`.
"""
if chunks[0] == "var":
if chunks[1] is None:
if var is None:
var = CCGVar()
return (var, var)
catstr = chunks[0]
if catstr in families:
(cat, cvar) = families[catstr]
if var is None:
var = cvar
else:
cat = cat.substitute([(cvar, var)])
return (cat, var)
if catstr in primitives:
subscrs = parseSubscripts(chunks[1])
return (PrimitiveCategory(catstr, subscrs), var)
raise AssertionError('String \'' + catstr +
'\' is neither a family nor primitive category.')
def fromstring(lex_str, include_semantics=False):
"""
Convert string representation into a lexicon for CCGs.
"""
CCGVar.reset_id()
primitives = []
families = {}
entries = defaultdict(list)
for line in lex_str.splitlines():
# Strip comments and leading/trailing whitespace.
line = COMMENTS_RE.match(line).groups()[0].strip()
if line == "":
continue
if line.startswith(':-'):
# A line of primitive categories.
# The first one is the target category
# ie, :- S, N, NP, VP
primitives = primitives + [
prim.strip() for prim in line[2:].strip().split(',')
]
else:
# Either a family definition, or a word definition
(ident, sep, rhs) = LEX_RE.match(line).groups()
(catstr, semantics_str) = RHS_RE.match(rhs).groups()
(cat, var) = augParseCategory(catstr, primitives, families)
if sep == '::':
# Family definition
# ie, Det :: NP/N
families[ident] = (cat, var)
else:
semantics = None
if include_semantics is True:
if semantics_str is None:
raise AssertionError(
line
+ " must contain semantics because include_semantics is set to True"
)
else:
semantics = Expression.fromstring(
SEMANTICS_RE.match(semantics_str).groups()[0]
)
# Word definition
# ie, which => (N\N)/(S/NP)
entries[ident].append(Token(ident, cat, semantics))
return CCGLexicon(primitives[0], primitives, families, entries)