def test_regexr_split(self):
regexr = RegexrClass()
string = '/article/page_2.html?param=1'
print("String to be split: %s" % string)
split_string = regexr.split(string)
assert isinstance(split_string, list)
print("Results: ")
print(split_string)
if len(split_string) == 12:
test_passed = split_string[0] == "/" \
and split_string[1] == "article" \
and split_string[2] == "/" \
and split_string[3] == "page" \
and split_string[4] == "_" \
and split_string[5] == "2" \
and split_string[6] == "." \
and split_string[7] == "html" \
and split_string[8] == "?" \
and split_string[9] == "param" \
and split_string[10] == "=" \
and split_string[11] == "1"
if test_passed:
self.print_success("OK!")
else:
self.print_failure("Test failed.")
def isUrlTest(self):
rg = RegexrClass()
urls = ["/url", "http://www.url.com", "www.url.com", "#"]
for u in urls:
if rg.is_url(u): self.print_success("Matched %s" % u)
else: self.print_failure("Did not match %s" % u)
def has_http_prefix(url):
regxr = RegexrClass()
matches = regxr.compile("(http:\/\/)").search(url)
if matches:
if matches.group(0) == 'http://':
return True
return False
def _is_url(url, root):
regxr = RegexrClass()
if not root:
if regxr.is_url(url):
return True
return False
else:
if regxr.is_rooturl(url):
return True
return False
def SpecialCharsTest(self):
rg = RegexrClass()
special_chars = ["/", "?", "-"]
_string = "/hey?you-"
self.print_info("Trying to return the special characters in %s" %
_string)
rspchars = rg.special_chars(_string)
if rspchars == special_chars:
self.print_success("returned %s" % special_chars)
self.print_success("OK!")
else:
self.print_failure("returned %s" % rspchars)
self.print_failure("FAILED!")
def __init__(self, rooturl=None, domitems=None): self.regexr = RegexrClass([]) # Explicitly passing an empty list to indicate that this instance will be used as a helper only. self.rooturl = rooturl # This is called the normalization phase # The nesting of the function calls is very important self.domitems = self.clean(self.decode(self.normalize(self.validate(domitems))))
def splitTest(self):
regexr = RegexrClass()
_links = "www.alyaoum24.com/news/sport"
# _links = "/topics/آش-واقع"
print("String to be split: %s" % _links)
split_string = regexr.split(_links)
assert isinstance(split_string, list)
print("Results: ")
print(split_string)
_links = "maing?#asdokasd/okao_sdka"
igndel = ["?", "#"]
print("String to be split: %s with ignored delimieters %s" %
(_links, igndel))
split_string = regexr.split(_links, igndel)
assert isinstance(split_string, list)
print("Results: ")
print(split_string)
def _patternize_test_smart(url_examples, matcheables, unmatcheables):
self.print_seperator()
try:
regexr = RegexrClass(url_examples)
except Exception as e:
self.print_failure("Test failed with %s" % str(e))
raise e
else:
print("The provided urls : %s" % url_examples)
print("The extracted pattern is : %s" % regexr.pattern)
self.print_info("\nThese tests should all succeed!\n")
_match_smart(regexr, matcheables)
self.print_info("\nThese tests should all fail!\n")
_match_smart(regexr, unmatcheables)
self.print_seperator()
def test_remove_double_slash(self):
examples = [
"//alink", "//alink//", "/alink/", "alink//", "///link///link",
"http://link//linkk", "/link/http://link/link"
]
results = [
"/alink", "/alink", "/alink", "alink", "/link/link",
"http://link/linkk", "/link/http://link/link"
]
regexr = RegexrClass()
rresults = list(map(regexr.remove_double_slash, examples))
for i, el in enumerate(results):
self.print_with_color(
"BOLD", "Arg Supplied: %s, Expected: %s, Result: %s" %
(examples[i], el, rresults[i]))
if el == rresults[i]:
self.print_success("OK!")
else:
self.print_failure("FAILED!")
def __init__(self, rooturl=None, domitems=None): self.regexr = RegexrClass() self.rooturl = rooturl self.temp = self.normalize(domitems)
def __init__(self, rooturl=None, domitems=None): self.regexr = RegexrClass() self.rooturl = rooturl self.domitems = self.clean(self.decode(self.normalize(self.validate(domitems)))) self.patternize()