def test__singlecharmatch__chunkmatch_2():
cmp = SingleCharMatchPattern('*', None)
# Explicitly check matching the first character
chk = PositionedChunk('*\n', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk is not None
assert sub_chunk == PositionedChunk('*', 13, 20, 'match')
def test__singlecharmatch__chunkmatch_1():
cmp = SingleCharMatchPattern('*', None)
# Check that it only matches once!
chk = PositionedChunk('aefal "fuin^ef" uynl*fa**', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk is not None
assert sub_chunk == PositionedChunk('*', 13 + 20, 20, 'match')
def test__cli__formatters__violations():
# check not just the formatting, but the ordering
v = {
'foo': [
RuleViolation(
PositionedChunk('blah', 1, 25, 'context'),
RuleGhost('A', 'DESC'), []),
RuleViolation(
PositionedChunk('blah', 2, 21, 'context'),
RuleGhost('B', 'DESC'), [])],
'bar': [
RuleViolation(
PositionedChunk('blah', 10, 2, 'context'),
RuleGhost('C', 'DESC'), [])]
}
f = format_violations(v)
k = sorted(['foo', 'bar'])
chk = {
'foo': ["L: 21 | P: 3 | B | DESC", "L: 25 | P: 2 | A | DESC"],
'bar': ["L: 2 | P: 11 | C | DESC"]
}
chk2 = []
for elem in k:
chk2 = chk2 + [format_filename(elem)] + chk[elem]
chk2 = '\n'.join(chk2)
assert escape_ansi(f) == escape_ansi(chk2)
def test__rules__std__L005():
# L005 is about spaces before commas
cs = ChunkString(PositionedChunk('1', 0, 20, 'content'),
PositionedChunk(' ', 0, 21, 'whitespace'),
PositionedChunk(',', 0, 22, 'comma'))
rs = StandardRuleSet()
vs = rs.evaluate_chunkstring(cs)
assert any([v.rule.code == 'L005' for v in vs])
def test__rules__base__chunkrule():
""" Check functionality with a rule which returns a chunk """
# A rule that returns a chunk
test_chunk = PositionedChunk('foo', 1, 20, 'a')
TRuleD = BaseRule.rule('TRuleD', "NA", lambda c, m: test_chunk)
r = TRuleD()
eval_chunk = PositionedChunk('bar', 1, 20, 'a')
# Check that the violation refers to the other chunk
assert r.evaluate(eval_chunk).chunk == test_chunk
def test__matcherbag__chunkmatch_a():
a = CharMatchPattern('a', 'foo')
b = CharMatchPattern('b', 'bar')
m = MatcherBag(a, b)
chk = PositionedChunk('asdfbjkebkjaekljds', 13, 20, None)
matches = m.chunkmatch(chk)
assert len(matches) == 2
assert matches == [
(PositionedChunk('asdfbjkebkja', 13, 20, 'match'), 0, a),
(PositionedChunk('bjkeb', 13 + 4, 20, 'match'), 4, b)]
def test__rules__base__ruleset_chunkstring():
""" An extension of the above test, but applied to a chunkstring """
rs = TRuleSet()
cs = ChunkString(PositionedChunk('foo', 1, 20, 'a'),
PositionedChunk('bar', 1, 21, 'b'))
vs = rs.evaluate_chunkstring(cs)
# We should get two instances of rule A
assert len(vs) == 2
assert vs[0].rule.code == 'TRuleA'
assert vs[0].chunk.chunk == 'foo'
assert vs[1].rule.code == 'TRuleA'
assert vs[1].chunk.chunk == 'bar'
def test__recursive__lex_chunk_buffer():
# This test requires recursion
rl = RecursiveLexer()
# The whitespace on the end of a comment should be it's own chunk
pc_list = [
PositionedChunk('SELECT\n', 0, 1, None),
PositionedChunk('NOTHING\n', 0, 2, None)
]
res, _ = rl.lex_chunk_buffer(pc_list)
assert res.context_list() == [
'content', 'whitespace', 'content', 'whitespace'
]
assert res[1].chunk == '\n'
assert res[3].chunk == '\n'
def test__recursive__basic_1():
rl = RecursiveLexer()
pc = PositionedChunk(' ', 0, 1, None)
res, _ = rl.lex(pc)
assert isinstance(res, ChunkString)
assert len(res) == 1
assert res[0].chunk == ' '
def test__rules__std__L004():
cs = ChunkString(PositionedChunk(' \n', 0, 20, 'whitespace'),
PositionedChunk('\t\n', 0, 21, 'whitespace'))
# Check individually, there's no errors
# First (alone should not raise)
rs = StandardRuleSet()
vs = rs.evaluate(cs[0])
assert not any([v.rule.code == 'L004' for v in vs])
# Second (alone should not raise)
rs = StandardRuleSet()
vs = rs.evaluate(cs[1])
assert not any([v.rule.code == 'L004' for v in vs])
# Combined (which should raise an L004)
rs = StandardRuleSet()
vs = rs.evaluate_chunkstring(cs)
assert any([v.rule.code == 'L004' for v in vs])
def test__cli__formatters__violation():
""" NB Position is 1 + start_pos """
c = PositionedChunk('foobarbar', 10, 20, 'context')
r = RuleGhost('A', 'DESC')
v = RuleViolation(c, r, [])
f = format_violation(v)
assert escape_ansi(f) == "L: 20 | P: 11 | A | DESC"
def test__recursive__multi_whitespace_a():
rl = RecursiveLexer()
pc = PositionedChunk(' SELECT \n', 0, 1, None)
res, _ = rl.lex(pc)
assert isinstance(res, ChunkString)
assert len(res) == 3
assert res[0].context == 'whitespace'
assert res[1].chunk == 'SELECT'
def test__recursive__comment_a():
# This test requires recursion
rl = RecursiveLexer()
# The whitespace on the end of a comment should be it's own chunk
pc = PositionedChunk('SELECT -- Testing Comment\n', 0, 1, None)
res, _ = rl.lex(pc)
assert res.context_list() == [
'content', 'whitespace', 'comment', 'whitespace'
]
assert res[3].chunk == '\n'
def test__recursive__multi_whitespace_b():
# This test requires recursion
rl = RecursiveLexer()
pc = PositionedChunk(' SELECT foo \n', 0, 1, None)
res, _ = rl.lex(pc)
assert isinstance(res, ChunkString)
assert len(res) == 5
assert res[0].context == 'whitespace'
assert res[1].chunk == 'SELECT'
assert res[3].chunk == 'foo'
assert res[3].start_pos == 13
def test__matcherbag__chunkmatch_c():
"""
A more complicated matcher test,
explicitly testing sorting, with ambiguous matchers
"""
a = SingleCharMatchPattern('a', 'bim', priority=2)
b = SingleCharMatchPattern('a', 'bar', priority=2)
c = SingleCharMatchPattern('a', 'foo', priority=3)
m = MatcherBag(a, b, c)
chk = PositionedChunk('asd', 11, 2, None)
matches = m.chunkmatch(chk)
matcher_ordered = [m[2] for m in matches]
assert matcher_ordered == [c, b, a]
def test__matcherbag__chunkmatch_b():
"""
A more complicated matcher test,
explicitly testing sorting
"""
k = CharMatchPattern('k', 'bim')
b = CharMatchPattern('b', 'bar')
a = CharMatchPattern('a', 'foo')
s = SingleCharMatchPattern('s', 'ess')
r = RegexMatchPattern(r'e[a-z][a-df-z]+e[a-z]', 'eee')
m = MatcherBag(k, b, a, r, s)
chk = PositionedChunk('asdfbjkebkjaekljds', 11, 2, None)
matches = m.chunkmatch(chk)
assert matches == [
(PositionedChunk('asdfbjkebkja', 11, 2, 'match'), 0, a),
(PositionedChunk('s', 11 + 1, 2, 'match'), 1, s),
(PositionedChunk('bjkeb', 11 + 4, 2, 'match'), 4, b),
(PositionedChunk('kebk', 11 + 6, 2, 'match'), 6, k),
(PositionedChunk('ebkjaek', 11 + 7, 2, 'match'), 7, r)]
def test__charmatch__chunkmatch_3():
# Check for an no match scenario
cmp = CharMatchPattern('a', None)
chk = PositionedChunk('sdflkg;j;d;sflkgjds', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk is None
def test__rules__std__L001():
rs = StandardRuleSet()
c = PositionedChunk(' \n', 10, 20, 'whitespace')
assert any([v.rule.code == 'L001' for v in rs.evaluate(c)])
def test__charmatch__chunkmatch_1():
cmp = CharMatchPattern('"', None)
chk = PositionedChunk('aefal "fuin^ef" uynl*fa', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk is not None
assert sub_chunk == PositionedChunk('"fuin^ef"', 13 + 6, 20, 'match')
def test__charmatch__chunkmatch_2():
cmp = CharMatchPattern('a', 'foo')
chk = PositionedChunk('asdfbjkebkjaekljds', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk == PositionedChunk('asdfbjkebkja', 13, 20, 'match')
def test__linter__linted_file__apply_corrections_to_fileobj():
chunk = PositionedChunk('foofoofoo', 9, 2, None)
fo = StringIO("12345678\n123456789foofoofoo654fish\n1234567")
LintedFile.apply_corrections_to_fileobj(
fo, [PositionedCorrection(chunk, 'bar')])
assert fo.getvalue() == "12345678\n123456789bar654fish\n1234567"
def test__chunklist__simple_content():
# Raise an exception if we try to create with anything but chunks
cs = ChunkString(PositionedChunk('foobarbar', 1, 20, 'a'),
PositionedChunk('foobarbar', 1, 21, 'b'))
assert list(cs.simple_list()) == [('foobarbar', 'a'), ('foobarbar', 'b')]
def test__chunk__split():
c = PositionedChunk('foobarbar', 10, 20, None)
a, b = c.split_at(3)
assert a == PositionedChunk('foo', 10, 20, None)
assert b == PositionedChunk('barbar', 13, 20, None)
def test__chunk__split_context_error():
c = PositionedChunk('foobarbar', 10, 20, 'context')
with pytest.raises(RuntimeError):
c.split_at(4)
def test__singlecharmatch__none():
cmp = SingleCharMatchPattern('*', None)
chk = PositionedChunk('aefal "fuin^ef" uynlfa', 13, 20, None)
sub_chunk = cmp.chunkmatch(chk)
assert sub_chunk is None
def test__rules__base__violation_tuple():
r = TRuleA()
v = r.evaluate(PositionedChunk('foo', 1, 20, 'a'))
t = v.check_tuple()
assert t == ('TRuleA', 20, 1)
def test__chunk__subchunk():
c = PositionedChunk('foobarbar', 10, 20, None)
r = c.subchunk(3, 6)
assert r == PositionedChunk('bar', 13, 20, None)
