def test_dumps():
assert penman.dumps([]) == ''
assert penman.dumps([penman.Graph([('a', 'instance', None)])]) == '(a)'
assert penman.dumps([
penman.Graph([('a', 'instance', None)]),
penman.Graph([('b', 'instance', None)]),
]) == '(a)\n\n(b)'
def test_dumps():
assert penman.dumps([]) == ''
assert penman.dumps([penman.Graph([('a', 'instance', None)])]) == '(a)'
assert penman.dumps([
penman.Graph([('a', 'instance', None)]),
penman.Graph([('b', 'instance', None)]),
]) == '(a)\n\n(b)'
def dumps(ds, properties=False, lnk=True, indent=False):
"""
Serialize DMRS objects to a PENMAN string.
Args:
ds: iterator of :class:`~delphin.mrs.dmrs.DMRS` objects to
serialize
properties: if `True`, encode variable properties
lnk: if `False`, suppress surface alignments and strings
indent: if `True`, adaptively indent; if `False` or `None`,
don't indent; if a non-negative integer N, indent N spaces
per level
Returns:
a PENMAN-serialization of the DMRS objects
"""
if indent is True:
indent = -1
elif indent is False:
indent = None
to_graph = penman.Graph
graphs = [
to_graph(to_triples(d, properties=properties, lnk=lnk)) for d in ds
]
try:
return penman.dumps(graphs, indent=indent)
except penman.PenmanError as exc:
raise PyDelphinException('could not decode with Penman') from exc
def test_dumps_triples():
assert penman.dumps([penman.Graph([('a', 'instance', None)])],
triples=True) == 'instance(a, None)'
assert penman.dumps([penman.Graph([('a', 'instance', 'aaa')])],
triples=True) == 'instance(a, aaa)'
assert penman.dumps(
[penman.Graph([('a', 'instance', None), ('a', 'ARG', 'b')])],
triples=True) == 'instance(a, None) ^\nARG(a, b)'
class TestCodec(penman.PENMANCodec):
TYPE_REL = 'test'
TOP_VAR = 'TOP'
TOP_REL = 'top'
assert penman.dumps([penman.Graph([('a', 'ARG', 'b')])],
triples=True,
cls=TestCodec) == 'top(TOP, a) ^\nARG(a, b)'
def test_dumps_triples():
assert penman.dumps(
[penman.Graph([('a', 'instance', None)])], triples=True
) == 'instance(a, None)'
assert penman.dumps(
[penman.Graph([('a', 'instance', 'aaa')])], triples=True
) == 'instance(a, aaa)'
assert penman.dumps(
[penman.Graph([('a', 'instance', None), ('a', 'ARG', 'b')])],
triples=True
) == 'instance(a, None) ^\nARG(a, b)'
gs = penman.dumps(
[penman.Graph([(1, 'instance', 'alpha')])],
triples=True
) == 'instance(1, alpha)'
gs = penman.dumps(
[penman.Graph([(1.1, 'instance', 'alpha')])],
triples=True
) == 'instance(1.1, alpha)'
gs = penman.dumps(
[penman.Graph([('"a string"', 'instance', 'alpha')])],
triples=True
) == 'instance("a string", alpha)'
class TestCodec(penman.PENMANCodec):
TYPE_REL = 'test'
TOP_VAR = 'TOP'
TOP_REL = 'top'
assert penman.dumps(
[penman.Graph([('a', 'ARG', 'b')])],
triples=True, cls=TestCodec
) == 'top(TOP, a) ^\nARG(a, b)'
def main(args):
with open(args.input, encoding='utf-8') as f, \
open(args.extra, encoding='utf-8') as e, \
open(args.output, mode='w', encoding='utf-8') as out:
amr_pair: List[Tuple[Graph, Graph]]
amr_pair = []
for sent_num, (cur_amr1,
cur_amr2) in enumerate(generate_amr_lines(f, e),
start=1):
amr_pair.append((pp.decode(cur_amr1), pp.decode(cur_amr2)))
amrs = []
for idx, (amr, extra) in enumerate(amr_pair):
amr.metadata.update(extra.metadata)
amrs.append(amr)
out.write(pp.dumps(amrs))
def dumps(xs, model=None, properties=False, indent=True, **kwargs):
"""
Serialize Xmrs (or subclass) objects to PENMAN notation
Args:
xs: iterator of :class:`~delphin.mrs.xmrs.Xmrs` objects to
serialize
model: Xmrs subclass used to get triples
properties: if `True`, encode variable properties
indent: if `True`, adaptively indent; if `False` or `None`,
don't indent; if a non-negative integer N, indent N spaces
per level
Returns:
the PENMAN serialization of *xs*
"""
xs = list(xs)
if not xs:
return ''
given_class = xs[0].__class__ # assume they are all the same
if model is None:
model = xs[0].__class__
if not hasattr(model, 'to_triples'):
raise TypeError('{} class does not implement to_triples()'.format(
model.__name__))
# convert MRS to DMRS if necessary; EDS cannot convert
if given_class.__name__ in ('Mrs', 'Xmrs'):
xs = [model.from_xmrs(x, **kwargs) for x in xs]
elif given_class.__name__ == 'Eds' and model.__name__ != 'Eds':
raise ValueError('Cannot convert EDS to non-EDS')
codec = XMRSCodec()
graphs = [
codec.triples_to_graph(model.to_triples(x, properties=properties))
for x in xs
]
if 'pretty_print' in kwargs:
indent = kwargs['pretty_print']
return penman.dumps(graphs, cls=XMRSCodec, indent=indent)
def dumps(xs, model=None, properties=False, indent=True, **kwargs):
"""
Serialize [Xmrs] (or subclass) objects to PENMAN notation
Args:
xs: an iterator of [Xmrs] objects to serialize
model: the Xmrs subclass used to get triples
properties: if True, encode variable properties
indent: if True, adaptively indent; if False or None, don't
indent; if a non-negative integer N, indent N spaces per level
pretty_print: (deprecated) if set, it overrides indent
Returns:
the PENMAN serialization of *xs*
"""
xs = list(xs)
if not xs:
return ''
if model is None:
model = xs[0].__class__
if not hasattr(model, 'to_triples'):
raise TypeError(
'{} class does not implement to_triples()'.format(model.__name__)
)
codec = XMRSCodec()
graphs = [
codec.triples_to_graph(
model.to_triples(model.from_xmrs(x), properties=properties)
)
for x in xs
]
if 'pretty_print' in kwargs:
indent = kwargs['pretty_print']
return penman.dumps(graphs, cls=XMRSCodec, indent=indent)
