def test_script_style(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [
Token('<style>TR {white-space: nowrap;}</style>')
])
assert (
output ==
[
Token('<style>', 'html', False),
Token('TR {white-space: nowrap;}', 'style', False),
Token('</style>', 'html', False)
]
)
output = trans.transform(self.vartok, [
Token('<script>console.log("foo");</script>')
])
assert (
output ==
[
Token('<script>', 'html', False),
Token('console.log("foo");', 'script', False),
Token('</script>', 'html', False)
]
)
def test_alt_title_placeholder(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [
Token('<img alt="foo">')])
eq_(output,
[
Token(u'<img alt="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
]
)
output = trans.transform(self.vartok, [
Token('<img title="foo">')])
eq_(output,
[
Token(u'<img title="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
]
)
output = trans.transform(self.vartok, [
Token('<input placeholder="foo">')])
eq_(output,
[
Token(u'<input placeholder="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
]
)
def test_basic(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [Token("")])
assert output == [Token("", "text", True)]
output = trans.transform(self.vartok, [Token("<b>hi</b>")])
assert output == [
Token("<b>", "html", False),
Token("hi", "text", True),
Token("</b>", "html", False),
]
def test_basic(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [Token('')])
assert output == [Token(u'', 'text', True)]
output = trans.transform(self.vartok, [Token('<b>hi</b>')])
assert (output == [
Token(u'<b>', 'html', False),
Token(u'hi', 'text', True),
Token(u'</b>', 'html', False),
])
def test_basic(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [Token('')])
eq_(output, [Token(u'', 'text', True)])
output = trans.transform(self.vartok, [Token('<b>hi</b>')])
eq_(output,
[
Token(u'<b>', 'html', False),
Token(u'hi', 'text', True),
Token(u'</b>', 'html', False),
]
)
def test_script_style(self):
trans = HTMLExtractorTransform()
output = trans.transform(
self.vartok, [Token('<style>TR {white-space: nowrap;}</style>')])
assert (output == [
Token(u'<style>', 'html', False),
Token(u'TR {white-space: nowrap;}', 'style', False),
Token(u'</style>', 'html', False)
])
output = trans.transform(
self.vartok, [Token('<script>console.log("foo");</script>')])
assert (output == [
Token(u'<script>', 'html', False),
Token(u'console.log("foo");', 'script', False),
Token(u'</script>', 'html', False)
])
def test_script_style(self):
trans = HTMLExtractorTransform()
output = trans.transform(
self.vartok, [Token("<style>TR {white-space: nowrap;}</style>")]
)
assert output == [
Token("<style>", "html", False),
Token("TR {white-space: nowrap;}", "style", False),
Token("</style>", "html", False),
]
output = trans.transform(
self.vartok, [Token('<script>console.log("foo");</script>')]
)
assert output == [
Token("<script>", "html", False),
Token('console.log("foo");', "script", False),
Token("</script>", "html", False),
]
def test_alt_title(self):
htmle = HTMLExtractorTransform()
output = htmle.transform(self.vartok, [
Token('<img alt="foo">')])
eq_(output,
[
Token(u'<img alt="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
]
)
output = htmle.transform(self.vartok, [
Token('<img title="foo">')])
eq_(output,
[
Token(u'<img title="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
]
)
def test_alt_title_placeholder(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [Token('<img alt="foo">')])
assert output == [
Token('<img alt="', "html", False),
Token("foo", "text", True),
Token('">', "html", False),
]
output = trans.transform(self.vartok, [Token('<img title="foo">')])
assert output == [
Token('<img title="', "html", False),
Token("foo", "text", True),
Token('">', "html", False),
]
output = trans.transform(self.vartok, [Token('<input placeholder="foo">')])
assert output == [
Token('<input placeholder="', "html", False),
Token("foo", "text", True),
Token('">', "html", False),
]
def test_alt_title_placeholder(self):
trans = HTMLExtractorTransform()
output = trans.transform(self.vartok, [Token('<img alt="foo">')])
assert (output == [
Token(u'<img alt="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
])
output = trans.transform(self.vartok, [Token('<img title="foo">')])
assert (output == [
Token(u'<img title="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
])
output = trans.transform(self.vartok,
[Token('<input placeholder="foo">')])
assert (output == [
Token(u'<input placeholder="', 'html', False),
Token(u'foo', 'text', True),
Token(u'">', 'html', False),
])
def lint(self, vartok, linted_entry):
msgs = []
from dennis.translator import HTMLExtractorTransform, Token
html = HTMLExtractorTransform()
def equiv(left, right):
return left == right
def tokenize(text):
"""Tokenizes the text using the HTMLExtractorTransform
:raises HTMLParseError: If it's invalid HTML.
"""
tokens = [
token for token in html.transform(vartok, [Token(text)])
if token.type == 'html' and not token.s.startswith('&')
]
return sorted(tokens, key=lambda token: token.s)
for trstr in linted_entry.strs:
if not trstr.msgstr_string:
continue
try:
msgid_parts = tokenize(trstr.msgid_strings[0])
except HTMLParseError as exc:
errmsg = (
u'invalid html: msgid has invalid html {0}'.format(exc))
msgs.append(
LintMessage(WARNING, linted_entry.poentry.linenum, 0,
self.num_error, errmsg, linted_entry.poentry))
return msgs
if len(trstr.msgid_strings) > 1:
# If this is a plural, then we check to see if the two
# msgid strings match each other. If not, then we move
# on because I have no idea what to do in this case.
try:
msgid_plural_parts = tokenize(trstr.msgid_strings[1])
except HTMLParseError as exc:
errmsg = (
u'invalid html: msgid_plural has invalid html {0}'.
format(exc))
msgs.append(
LintMessage(WARNING, linted_entry.poentry.linenum, 0,
self.num_error, errmsg,
linted_entry.poentry))
return msgs
zipped_parts = izip_longest(msgid_parts,
msgid_plural_parts,
fillvalue=None)
for left, right in zipped_parts:
if not left or not right or not equiv(left, right):
return []
try:
msgstr_parts = tokenize(trstr.msgstr_string)
except HTMLParseError as exc:
errmsg = (
u'invalid html: msgstr has invalid html {0}'.format(exc))
msgs.append(
LintMessage(WARNING, linted_entry.poentry.linenum, 0,
self.num_error, errmsg, linted_entry.poentry))
return msgs
for left, right in izip_longest(msgid_parts,
msgstr_parts,
fillvalue=None):
if not left or not right or not equiv(left, right):
msgs.append(
LintMessage(
WARNING, linted_entry.poentry.linenum, 0, self.num,
u'different html: "{0}" vs. "{1}"'.format(
left.s if left else u'',
right.s if right else u''),
linted_entry.poentry))
break
return msgs
def _trans(text):
return HTMLExtractorTransform().transform(self.vartok, [Token(text)])
