def test_conc_str():
assert str(conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(charclass("d"), one),
mult(charclass("e"), one),
mult(~charclass("fg"), star),
mult(charclass("h"), multiplier(bound(5), bound(5))),
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
)) == "abcde[^fg]*h{5}[a-z]+"
def test_conc_str():
assert str(conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(charclass("d"), one),
mult(charclass("e"), one),
mult(~charclass("fg"), star),
mult(charclass("h"), multiplier(bound(5), bound(5))),
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
)) == "abcde[^fg]*h{5}[a-z]+"
def test_conc_parsing():
assert conc.parse("abcde[^fg]*h{5}[a-z]+") == conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(charclass("d"), one),
mult(charclass("e"), one),
mult(~charclass("fg"), star),
mult(charclass("h"), multiplier(bound(5), bound(5))),
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
)
assert conc.parse("[bc]*[ab]*") == conc(
mult(charclass("bc"), star),
mult(charclass("ab"), star),
)
assert conc.parse("abc...") == conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(dot, one),
mult(dot, one),
mult(dot, one),
)
assert conc.parse("\\d{4}-\\d{2}-\\d{2}") == conc(
mult(charclass("0123456789"), multiplier(bound(4), bound(4))),
mult(charclass("-"), one),
mult(charclass("0123456789"), multiplier(bound(2), bound(2))),
mult(charclass("-"), one),
mult(charclass("0123456789"), multiplier(bound(2), bound(2))),
)
def test_conc_parsing():
assert conc.parse("abcde[^fg]*h{5}[a-z]+") == conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(charclass("d"), one),
mult(charclass("e"), one),
mult(~charclass("fg"), star),
mult(charclass("h"), multiplier(bound(5), bound(5))),
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
)
assert conc.parse("[bc]*[ab]*") == conc(
mult(charclass("bc"), star),
mult(charclass("ab"), star),
)
assert conc.parse("abc...") == conc(
mult(charclass("a"), one),
mult(charclass("b"), one),
mult(charclass("c"), one),
mult(dot, one),
mult(dot, one),
mult(dot, one),
)
assert conc.parse("\\d{4}-\\d{2}-\\d{2}") == conc(
mult(charclass("0123456789"), multiplier(bound(4), bound(4))),
mult(charclass("-"), one),
mult(charclass("0123456789"), multiplier(bound(2), bound(2))),
mult(charclass("-"), one),
mult(charclass("0123456789"), multiplier(bound(2), bound(2))),
)
def test_mult_reduction_easy():
# mult -> mult
# mult -> charclass
assert mult(charclass("a"), one).reduce() == charclass("a")
assert mult(charclass("a"), qm).reduce() == mult(charclass("a"), qm)
assert mult(charclass("a"), zero).reduce() == emptystring
assert mult(nothing, one).reduce() == nothing
assert mult(nothing, qm).reduce() == emptystring
assert mult(nothing, zero).reduce() == emptystring
assert mult(nothing, multiplier(bound(0), bound(5))).reduce() == emptystring
assert mult(pattern(), one).reduce() == nothing
assert mult(pattern(), qm).reduce() == emptystring
assert mult(pattern(), zero).reduce() == emptystring
assert mult(pattern(), multiplier(bound(0), bound(5))).reduce() == emptystring
def test_mult_parsing():
assert mult.parse("[a-g]+") == mult(charclass("abcdefg"), plus)
assert mult.parse("[a-g0-8$%]+") == mult(charclass("abcdefg012345678$%"), plus)
assert mult.parse("[a-g0-8$%\\^]+") == mult(charclass("abcdefg012345678$%^"), plus)
assert mult.match("abcde[^fg]*", 5) == (
mult(~charclass("fg"), star),
11
)
assert mult.match("abcde[^fg]*h{5}[a-z]+", 11) == (
mult(charclass("h"), multiplier(bound(5), bound(5))),
15
)
assert mult.match("abcde[^fg]*h{5}[a-z]+T{1,}", 15) == (
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
21
)
assert mult.match("abcde[^fg]*h{5}[a-z]+T{2,}", 21) == (
mult(charclass("T"), multiplier(bound(2), inf)),
26
)
def test_mult_parsing():
assert mult.parse("[a-g]+") == mult(charclass("abcdefg"), plus)
assert mult.parse("[a-g0-8$%]+") == mult(charclass("abcdefg012345678$%"), plus)
assert mult.parse("[a-g0-8$%\\^]+") == mult(charclass("abcdefg012345678$%^"), plus)
assert mult.match("abcde[^fg]*", 5) == (
mult(~charclass("fg"), star),
11
)
assert mult.match("abcde[^fg]*h{5}[a-z]+", 11) == (
mult(charclass("h"), multiplier(bound(5), bound(5))),
15
)
assert mult.match("abcde[^fg]*h{5}[a-z]+T{1,}", 15) == (
mult(charclass("abcdefghijklmnopqrstuvwxyz"), plus),
21
)
assert mult.match("abcde[^fg]*h{5}[a-z]+T{2,}", 21) == (
mult(charclass("T"), multiplier(bound(2), inf)),
26
)
def test_multiplier_union(): assert zero | zero == zero assert zero | qm == qm assert zero | one == qm assert zero | star == star assert zero | plus == star assert qm | zero == qm assert qm | qm == qm assert qm | one == qm assert qm | star == star assert qm | plus == star assert one | zero == qm assert one | qm == qm assert one | one == one assert one | star == star assert one | plus == plus assert star | zero == star assert star | qm == star assert star | one == star assert star | star == star assert star | plus == star assert plus | zero == star assert plus | qm == star assert plus | one == plus assert plus | star == star assert plus | plus == plus assert not zero.canunion(multiplier(bound(2), inf)) assert not one.canunion(multiplier(bound(3), bound(4))) assert not multiplier(bound(8), inf).canunion(multiplier(bound(3), bound(4))) try: zero | multiplier(bound(7), bound(8)) assert False except AssertionError: assert False except Exception: pass
def test_multiplier_union(): assert zero | zero == zero assert zero | qm == qm assert zero | one == qm assert zero | star == star assert zero | plus == star assert qm | zero == qm assert qm | qm == qm assert qm | one == qm assert qm | star == star assert qm | plus == star assert one | zero == qm assert one | qm == qm assert one | one == one assert one | star == star assert one | plus == plus assert star | zero == star assert star | qm == star assert star | one == star assert star | star == star assert star | plus == star assert plus | zero == star assert plus | qm == star assert plus | one == plus assert plus | star == star assert plus | plus == plus assert not zero.canunion(multiplier(bound(2), inf)) assert not one.canunion(multiplier(bound(3), bound(4))) assert not multiplier(bound(8), inf).canunion(multiplier(bound(3), bound(4))) try: zero | multiplier(bound(7), bound(8)) assert False except AssertionError: assert False except Exception: pass
def test_bound(): assert min(bound(0), inf) == bound(0) assert min(bound(1), inf) == bound(1) assert qm.mandatory == bound(0) assert qm.optional == bound(1)
def test_conc_equality():
assert conc(mult(charclass("a"), one)) == conc(mult(charclass("a"), one))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("b"), one))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("a"), qm))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("a"), multiplier(bound(1), bound(2))))
assert conc(mult(charclass("a"), one)) != emptystring
def test_mult_equality():
assert mult(charclass("a"), one) == mult(charclass("a"), one)
assert mult(charclass("a"), one) != mult(charclass("b"), one)
assert mult(charclass("a"), one) != mult(charclass("a"), qm)
assert mult(charclass("a"), one) != mult(charclass("a"), multiplier(bound(1), bound(2)))
assert mult(charclass("a"), one) != charclass("a")
def test_mult_str():
assert str(bound(2)) == "2"
assert str(inf) == ""
assert str(multiplier(bound(2), inf)) == "{2,}"
a = charclass("a")
assert str(mult(a, one)) == "a"
assert str(mult(a, multiplier(bound(2), bound(2)))) == "a{2}"
assert str(mult(a, multiplier(bound(3), bound(3)))) == "a{3}"
assert str(mult(a, multiplier(bound(4), bound(4)))) == "a{4}"
assert str(mult(a, multiplier(bound(5), bound(5)))) == "a{5}"
assert str(mult(a, qm)) == "a?"
assert str(mult(a, star)) == "a*"
assert str(mult(a, plus)) == "a+"
assert str(mult(a, multiplier(bound(2), bound(5)))) == "a{2,5}"
assert str(mult(a, multiplier(bound(2), inf))) == "a{2,}"
assert str(mult(d, one)) == "\\d"
assert str(mult(d, multiplier(bound(2), bound(2)))) == "\\d{2}"
assert str(mult(d, multiplier(bound(3), bound(3)))) == "\\d{3}"
def test_mult_equality():
assert mult(charclass("a"), one) == mult(charclass("a"), one)
assert mult(charclass("a"), one) != mult(charclass("b"), one)
assert mult(charclass("a"), one) != mult(charclass("a"), qm)
assert mult(charclass("a"), one) != mult(charclass("a"), multiplier(bound(1), bound(2)))
assert mult(charclass("a"), one) != charclass("a")
def test_mult_str():
assert str(bound(2)) == "2"
assert str(inf) == ""
assert str(multiplier(bound(2), inf)) == "{2,}"
a = charclass("a")
assert str(mult(a, one)) == "a"
assert str(mult(a, multiplier(bound(2), bound(2)))) == "a{2}"
assert str(mult(a, multiplier(bound(3), bound(3)))) == "a{3}"
assert str(mult(a, multiplier(bound(4), bound(4)))) == "a{4}"
assert str(mult(a, multiplier(bound(5), bound(5)))) == "a{5}"
assert str(mult(a, qm)) == "a?"
assert str(mult(a, star)) == "a*"
assert str(mult(a, plus)) == "a+"
assert str(mult(a, multiplier(bound(2), bound(5)))) == "a{2,5}"
assert str(mult(a, multiplier(bound(2), inf))) == "a{2,}"
assert str(mult(d, one)) == "\\d"
assert str(mult(d, multiplier(bound(2), bound(2)))) == "\\d{2}"
assert str(mult(d, multiplier(bound(3), bound(3)))) == "\\d{3}"
def test_conc_equality():
assert conc(mult(charclass("a"), one)) == conc(mult(charclass("a"), one))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("b"), one))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("a"), qm))
assert conc(mult(charclass("a"), one)) != conc(mult(charclass("a"), multiplier(bound(1), bound(2))))
assert conc(mult(charclass("a"), one)) != emptystring
def test_bound(): assert min(bound(0), inf) == bound(0) assert min(bound(1), inf) == bound(1) assert qm.mandatory == bound(0) assert qm.optional == bound(1)