def test_nonbreaking_space_issue_99():
# https://github.com/goodmami/penman/issues/99
assert [tok.type for tok in lexer.lex('1 2')] == ['SYMBOL', 'SYMBOL']
assert [tok.type for tok in lexer.lex('1\t2')] == ['SYMBOL', 'SYMBOL']
assert [tok.type for tok in lexer.lex('1\n2')] == ['SYMBOL', 'SYMBOL']
assert [tok.type for tok in lexer.lex('1\r2')] == ['SYMBOL', 'SYMBOL']
assert [tok.type for tok in lexer.lex('1\u00a02')] == ['SYMBOL']
assert [tok.type for tok in lexer.lex('あ い')] == ['SYMBOL']
def parse(s: str) -> Tree:
"""
Parse PENMAN-notation string *s* into its tree structure.
Args:
s: a string containing a single PENMAN-serialized graph
Returns:
The tree structure described by *s*.
Example:
>>> import penman
>>> penman.parse('(b / bark-01 :ARG0 (d / dog))') # noqa
Tree(('b', [('/', 'bark-01'), (':ARG0', ('d', [('/', 'dog')]))]))
"""
tokens = lex(s, pattern=PENMAN_RE)
return _parse(tokens)
def parse_triples(s: str) -> List[BasicTriple]:
"""
Parse a triple conjunction from *s*.
Example:
>>> import penman
>>> for triple in penman.parse_triples('''
... instance(b, bark) ^
... ARG0(b, d) ^
... instance(d, dog)'''):
... print(triple)
('b', ':instance', 'bark')
('b', ':ARG0', 'd')
('d', ':instance', 'dog')
"""
tokens = lex(s, pattern=TRIPLE_RE)
return _parse_triples(tokens)
def iterparse(lines: Union[Iterable[str], str]) -> Iterator[Tree]:
"""
Yield trees parsed from *lines*.
Args:
lines: a string or open file with PENMAN-serialized graphs
Returns:
The :class:`~penman.tree.Tree` object described in *lines*.
Example:
>>> import penman
>>> for t in penman.iterparse('(a / alpha) (b / beta)'):
... print(repr(t))
...
Tree(('a', [('/', 'alpha')]))
Tree(('b', [('/', 'beta')]))
"""
tokens = lex(lines, pattern=PENMAN_RE)
while tokens and tokens.peek().type in ('COMMENT', 'LPAREN'):
yield _parse(tokens)
def _lex(s):
return [tok.type for tok in lexer.lex(s)]
def _lex(s):
return [tok.type for tok in lexer.lex(s, pattern=lexer.TRIPLE_RE)]
def test_lexing_issue_50():
# https://github.com/goodmami/penman/issues/50
assert [tok.type for tok in lexer.lex('(a :ROLE "a~b"~1)')
] == ['LPAREN', 'SYMBOL', 'ROLE', 'STRING', 'ALIGNMENT', 'RPAREN']
