def test_one_or_more(self):
len_eq(OneOrMore(Literal('b')).match('b'), 1) # one
len_eq(OneOrMore(Literal('b')).match('bbb'), 3) # more
len_eq(OneOrMore(Literal('b'), min=3).match('bbb'),
3) # with custom min; success
assert_raises(ParseError,
OneOrMore(Literal('b'), min=3).match,
'bb') # with custom min; failure
len_eq(OneOrMore(Regex('^')).match('bb'), 0) # attempt infinite loop
def test_parse_success(self):
"""Make sure ``parse()`` returns the tree on success.
There's not much more than that to test that we haven't already vetted
above.
"""
expr = OneOrMore(Literal("a", name="lit"), name="more")
text = "aa"
eq_(expr.parse(text), Node("more", text, 0, 2, children=[Node("lit", text, 0, 1), Node("lit", text, 1, 2)]))
def test_one_or_more_one(self):
"""Test the 1 case of ``OneOrMore``; it should return a node with a child."""
expr = OneOrMore(Literal('a', name='lit'), name='one')
text = 'a'
eq_(
expr.match(text),
Node(expr,
text,
0,
1,
children=[Node(expr.members[0], text, 0, 1)]))
def test_parse_success(self):
"""Make sure ``parse()`` returns the tree on success.
There's not much more than that to test that we haven't already vetted
above.
"""
expr = OneOrMore(Literal('a', name='lit'), name='more')
text = 'aa'
self.assertEqual(expr.parse(text), Node(expr, text, 0, 2, children=[
Node(expr.members[0], text, 0, 1),
Node(expr.members[0], text, 1, 2)]))
def test_parse_success(self):
"""Make sure ``parse()`` returns the tree on success.
There's not much more than that to test that we haven't already vetted
above.
"""
expr = OneOrMore(Literal('a', name='lit'), name='more')
text = 'aa'
eq_(expr.parse(text), Node('more', text, 0, 2, children=[
Node('lit', text, 0, 1),
Node('lit', text, 1, 2)]))
def _expressions_from_rules(self, rule_syntax):
"""Return the rules for parsing the grammar definition syntax.
Return a 2-tuple: a dict of rule names pointing to their expressions,
and then the top-level expression for the first rule.
"""
# Hard-code enough of the rules to parse the grammar that describes the
# grammar description language, to bootstrap:
ws = Regex(r'\s+', name='ws')
_ = Regex(r'[ \t]+', name='_')
label = Regex(r'[a-zA-Z_][a-zA-Z_0-9]*', name='label')
quantifier = Regex(r'[*+?]', name='quantifier')
# This pattern supports empty literals. TODO: A problem?
literal = Regex(r'u?r?"[^"\\]*(?:\\.[^"\\]*)*"',
ignore_case=True,
dot_all=True,
name='literal')
regex = Sequence(Literal('~'),
literal,
Regex('[ilmsux]*', ignore_case=True),
name='regex')
atom = OneOf(label, literal, regex, name='atom')
quantified = Sequence(atom, quantifier, name='quantified')
term = OneOf(quantified, atom, name='term')
another_term = Sequence(_, term, name='another_term')
sequence = Sequence(term, OneOrMore(another_term), name='sequence')
or_term = Sequence(_, Literal('/'), another_term, name='or_term')
ored = Sequence(term, OneOrMore(or_term), name='ored')
and_term = Sequence(_, Literal('&'), another_term, name='and_term')
anded = Sequence(term, OneOrMore(and_term), name='anded')
poly_term = OneOf(anded, ored, sequence, name='poly_term')
rhs = OneOf(poly_term, term, name='rhs')
eol = Regex(r'[\r\n$]', name='eol') # TODO: Support $.
rule = Sequence(Optional(ws),
label,
Optional(_),
Literal('='),
Optional(_),
rhs,
Optional(_),
eol,
name='rule')
rules = Sequence(OneOrMore(rule), Optional(ws), name='rules')
# Use those hard-coded rules to parse the (possibly more extensive)
# rule syntax. (For example, unless I start using parentheses in the
# rule language definition itself, I should never have to hard-code
# expressions for those above.)
rule_tree = rules.parse(rule_syntax)
# Turn the parse tree into a map of expressions:
return RuleVisitor().visit(rule_tree)
def _expressions_from_rules(self, rule_syntax, custom_rules):
"""Return the rules for parsing the grammar definition syntax.
Return a 2-tuple: a dict of rule names pointing to their expressions,
and then the top-level expression for the first rule.
"""
# Hard-code enough of the rules to parse the grammar that describes the
# grammar description language, to bootstrap:
comment = Regex(r'#[^\r\n]*', name='comment')
meaninglessness = OneOf(Regex(r'\s+'), comment, name='meaninglessness')
_ = ZeroOrMore(meaninglessness, name='_')
equals = Sequence(Literal('='), _, name='equals')
label = Sequence(Regex(r'[a-zA-Z_][a-zA-Z_0-9]*'), _, name='label')
reference = Sequence(label, Not(equals), name='reference')
quantifier = Sequence(Regex(r'[*+?]'), _, name='quantifier')
# This pattern supports empty literals. TODO: A problem?
spaceless_literal = Regex(r'u?r?"[^"\\]*(?:\\.[^"\\]*)*"',
ignore_case=True,
dot_all=True,
name='spaceless_literal')
literal = Sequence(spaceless_literal, _, name='literal')
regex = Sequence(Literal('~'),
literal,
Regex('[ilmsuxa]*', ignore_case=True),
_,
name='regex')
atom = OneOf(reference, literal, regex, name='atom')
quantified = Sequence(atom, quantifier, name='quantified')
term = OneOf(quantified, atom, name='term')
not_term = Sequence(Literal('!'), term, _, name='not_term')
term.members = (not_term, ) + term.members
sequence = Sequence(term, OneOrMore(term), name='sequence')
or_term = Sequence(Literal('/'), _, term, name='or_term')
ored = Sequence(term, OneOrMore(or_term), name='ored')
expression = OneOf(ored, sequence, term, name='expression')
rule = Sequence(label, equals, expression, name='rule')
rules = Sequence(_, OneOrMore(rule), name='rules')
# Use those hard-coded rules to parse the (more extensive) rule syntax.
# (For example, unless I start using parentheses in the rule language
# definition itself, I should never have to hard-code expressions for
# those above.)
rule_tree = rules.parse(rule_syntax)
# Turn the parse tree into a map of expressions:
return RuleVisitor().visit(rule_tree)
def _expressions_from_rules(self, rule_syntax):
"""Return the rules for parsing the grammar definition syntax.
Return a 2-tuple: a dict of rule names pointing to their expressions,
and then the top-level expression for the first rule.
"""
# Hard-code enough of the rules to parse the grammar that describes the
# grammar description language, to bootstrap:
ws = Regex(r'\s+', name='ws')
comment = Regex(r'#[^\r\n]*', name='comment')
_ = Regex(r'[ \t]+', name='_')
label = Regex(r'[a-zA-Z_][a-zA-Z_0-9]*', name='label')
quantifier = Regex(r'[*+?]', name='quantifier')
# This pattern supports empty literals. TODO: A problem?
literal = Regex(r'u?r?"[^"\\]*(?:\\.[^"\\]*)*"', ignore_case=True, dot_all=True, name='literal')
regex = Sequence(Literal('~'), literal, Regex('[ilmsux]*', ignore_case=True), name='regex')
atom = OneOf(label, literal, regex, name='atom')
quantified = Sequence(atom, quantifier, name='quantified')
term = OneOf(quantified, atom, name='term')
another_term = Sequence(_, term, name='another_term')
sequence = Sequence(term, OneOrMore(another_term), name='sequence')
or_term = Sequence(_, Literal('/'), another_term, name='or_term')
ored = Sequence(term, OneOrMore(or_term), name='ored')
expression = OneOf(ored, sequence, term, name='expression')
eol = Regex(r'[\r\n$]', name='eol') # TODO: Support $.
rule = Sequence(label, Optional(_), Literal('='), Optional(_),
expression, Optional(_), Optional(comment), eol,
name='rule')
rule_or_rubbish = OneOf(rule, ws, comment, name='rule_or_rubbish')
rules = OneOrMore(rule_or_rubbish, name='rules')
# Use those hard-coded rules to parse the (more extensive) rule syntax.
# (For example, unless I start using parentheses in the rule language
# definition itself, I should never have to hard-code expressions for
# those above.)
rule_tree = rules.parse(rule_syntax)
# Turn the parse tree into a map of expressions:
return RuleVisitor().visit(rule_tree)
def test_one_or_more_one(self):
"""Test the 1 case of ``OneOrMore``; it should return a node with a child."""
expr = OneOrMore(Literal('a', name='lit'), name='one')
text = 'a'
eq_(expr.match(text), Node('one', text, 0, 1, children=[
Node('lit', text, 0, 1)]))
def test_parse_failure(self):
"""Make sure ``parse()`` fails when it doesn't recognize all the way to
the end."""
expr = OneOrMore(Literal("a", name="lit"), name="more")
text = "aab"
eq_(expr.parse(text), None)
def test_one_or_more_one(self):
"""Test the 1 case of ``OneOrMore``; it should return a node with a child."""
expr = OneOrMore(Literal("a", name="lit"), name="one")
text = "a"
eq_(expr.match(text), Node("one", text, 0, 1, children=[Node("lit", text, 0, 1)]))
def test_parse_failure(self):
"""Make sure ``parse()`` fails when it doesn't recognize all the way to the end."""
expr = OneOrMore(Literal('a', name='lit'), name='more')
text = 'aab'
eq_(expr.parse(text), None)
def test_one_or_more(self):
len_eq(OneOrMore(Literal('b')).match('b'), 1) # one
len_eq(OneOrMore(Literal('b')).match('bbb'), 3) # more
len_eq(OneOrMore(Literal('b'), min=3).match('bbb'), 3) # with custom min; success
len_eq(OneOrMore(Literal('b'), min=3).match('bb'), None) # with custom min; failure
len_eq(OneOrMore(Regex('^')).match('bb'), 0) # attempt infinite loop
def test_parse_failure(self):
"""Make sure ``parse()`` fails when it doesn't recognize all the way to
the end."""
expr = OneOrMore(Literal('a', name='lit'), name='more')
text = 'aab'
eq_(expr.parse(text), None)
