def _global_re_handler(match: _re) -> str:
f_name = match.group(1)
if f_name not in _globals:
return match.group(0)
try:
return _globals[f_name]()
except Exception as e:
raise RuntimeError('Error while calling lang function {}(): {}'.format(f_name, e))
def is_href_matching(url_string: str, regex: re) -> bool:
"""
Check if the regex has any match in the url string.
:param url_string: URL as string
:param regex: Regex used to search URL
:return: boolean
"""
if regex.search(url_query_cleaner(url_string)):
return True
return False
def _parse_table_lines(lines: List[str], regex: re) -> List[Dict[str, any]]:
"""Parse the lines using the given regular expression.
If a line can't be parsed it is logged and skipped in the output.
"""
results = []
for line in lines:
match = regex.search(line)
if not match:
_LOGGER.debug("Could not parse line: %s", line)
continue
results.append(match.groupdict())
return results
def is_querystring_matching(url: URL, regex: re) -> bool:
"""
Check if the regex has any match in the URL query parameters.
:param url: URL object
:param regex: Regex used to search query
:return: boolean
"""
for key in url.query:
if regex.search(key):
return True
return False
def parse_files(content_list: list, matcher: re) -> List[str]:
result = []
for item in content_list:
content = item.read_text('utf-8') if isinstance(item,
Path) else item
for line in content.splitlines():
m = matcher.match(line)
if m:
value = m.group(1).strip(' \t\n\r')
# replace multiple consequent space/tabs with a single space
value = re.sub(r'\s+', ' ', value)
result.append(value)
return result
def scan_recent(self, pattern: re, timeout=10):
if not os.path.isfile(self.path):
return False
with open(self.path) as fd:
end = datetime.now() + timedelta(seconds=timeout)
while True:
fd.seek(self._last_pos, os.SEEK_SET)
for line in fd:
if pattern.match(line):
return True
if datetime.now() > end:
raise TimeoutError(
f"pattern not found in error log after {timeout} seconds"
)
time.sleep(.1)
return False
def __set_url(self, url_exists: re): # set the url, title & coords attributes
if url_exists:
try:
prefix = re.sub(r"\?q=", "/place/", self.__mq).replace('+', "\+")
path = re.search(fr'{prefix}.+?/data.+?\\"', self.__resp.text).group()
path = re.sub(r"\\\\u003d", '=', path)
coords = re.search(r"@-?\d\d?\.\d{4,8},-?\d\d?\.\d{4,8}",
url_exists.group()).group()
self.coords = self.coordinates = tuple(coords.strip('@').split(','))
path = re.sub(r"/data", f"/{coords},17z/data", path)
self.url = path[:-11] + "!8m2!3d" + re.sub(r",", "!4d", coords.strip('@'))
title = re.search(r"(?<=https://www.google.com/maps/place/)\w+.*?/@",
self.url).group().strip("/@")
self.title = unquote_plus(title)
except AttributeError:
pass
def is_subdomain_matching(url: URL, regex: re) -> bool:
"""
Check if the url subdomain matches the regex
:param url: URL object
:param regex: regex object
:return: boolean
"""
if not url.host:
return False
split = url.host.split(".")
if len(split) <= 2:
return False
sub_domains = ".".join(split[:-2])
if regex.search(sub_domains):
return True
return False
def expand_corpus(contraction: re) -> str:
contraction_match = contraction.group(0).lower()
expanded_contraction = contraction_map.get(contraction_match)
return expanded_contraction
def displaymatch(match: re):
if match is None:
return None
return '<Match: %r, group=%r?>' % (match.group(), match.groups())