issue #25: all test checked and passed. the funcs in the utils file are specifically for this folder don't use elsewhere

SimpleX/regex_simplexlinks.py

@@ -17,61 +17,48 @@ pattern = re.compile('[0-9A-Za-z-_]*')
 # Regular expression pattern for a valid hostname (can be an IP, domain, or onion)
 hostname_pattern = re.compile(r'^(?:[a-zA-Z0-9.-]+|[0-9]{1,3}(?:\.[0-9]{1,3}){3}|[a-zA-Z0-9-]+\.onion)$')
 
-
-
 def IsSimpleXChatroomValid(url: str) -> bool:
-	# Step 1: Check if it starts with http://, https://, or simplex:/
+    """Validate the SimpleX chatroom URL."""
-	if url.startswith(('http://', 'https://', 'simplex:/')):
+    REQUIRED_SUBSTRING = "contact#/?v=2-7&smp=smp%3A%2F"
-		# Step 1.5: If http:// or https://, check for valid clearnet or onion domain
+    
-		if url.startswith(('http://', 'https://')):
+    # Step 1: Check if it starts with http://, https://, or simplex:/
-			parsed_url = urllib.parse.urlparse(url)
+    if url.startswith(('http://', 'https://', 'simplex:/')):
-			print(parsed_url.hostname)
+        # Step 1.5: If http:// or https://, check for valid clearnet or onion domain
-			if not IsUrlValid(parsed_url.hostname):
+        if url.startswith(('http://', 'https://')):
-				return False  # Invalid domain
+            return IsUrlValid(url)
-	elif not url.startswith('simplex:/'):
+    elif not url.startswith('simplex:/'):
-		return False  # Must start with one of the valid protocols
+        return False  # Must start with one of the valid protocols
 
+    # Step 2: Check for the presence of the required substring
+    if REQUIRED_SUBSTRING not in url:
+        return False  # Required substring not found
 
-	# Step 2: Check for the presence of "contact#/?v=2-7&smp=smp%3A%2F"
+    # Step 3: Extract the part after "smp=smp%3A%2F"
-	if "contact#/?v=2-7&smp=smp%3A%2F" not in url:
+    smp_start = url.find("smp=smp%3A%2F")
-		return False  # Required substring not found
+    if smp_start == -1:
+        return False  # Required substring not found
 
+    smp_start += len("smp=smp%3A%2F")
+    smp_end = url.find("&", smp_start)
+    if smp_end == -1:
+        smp_end = len(url)  # Take until the end if no "&" is found
 
-	# Step 3: Extract the part after "smp=smp%3A%2F" and before the next "&" or end of string
+    smp_value = urllib.parse.unquote(url[smp_start:smp_end])  # Decode the URL-encoded string
-	smp_start = url.find("smp=smp%3A%2F")
-	if smp_start == -1:
-		return False  # Required substring not found
 
+    # Step 3.5: Check if the smp_value contains a valid hostname
+    if '@' not in smp_value:
+        return False  # Must contain '@' to separate fingerprint and hostname
 
-	smp_start += len("smp=smp%3A%2F")
+    fingerprint, hostname = smp_value.split('@', 1)
-	smp_end = url.find("&", smp_start)
+    if not IsUrlValid(hostname):
-	if smp_end == -1:
+        return False  # Invalid hostname
-		smp_end = len(url)  # Take until the end if no "&" is found
 
+    # Step 4: Check for the presence of "%2F" in the original URL
+    if "%2F" not in url:
+        return False  # Required substring not found
 
-	smp_value = urllib.parse.unquote(url[smp_start:smp_end])  # Decode the URL-encoded string
+    # If all checks pass, return True
-
+    return True
-
-	# Step 3.5: Check if the smp_value contains a valid hostname
-	if '@' not in smp_value:
-		return False  # Must contain '@' to separate fingerprint and hostname
-
-
-	fingerprint, hostname = smp_value.split('@', 1)
-	if not IsUrlValid(hostname):
-		return False  # Invalid hostname
-
-
-	# Step 4: Check for the presence of "%2F" in the original URL
-	if "%2F" not in url:
-		return False  # Required substring not found
-
-
-	# If all checks pass, return True
-	return True
-
-
-	
 
 
 	#xftp://fingerprint:password@host1,host2
@@ -139,6 +126,6 @@ if __name__ == '__main__':
 	#link = 'https://simplex.chat/contact#/?v=2-7&smp=smp%3A%2F%2FBD4qkVq8lJUgjHt0kUaxeQBYsKaxDejeecxm6-2vOwI%3D%40b6geeakpwskovltbesvy3b6ah3ewxfmnhnshojndmpp7wcv2df7bnead.onion%2FOReK0M4-3C5NeZyQx_yFuTHSknVVS-3h%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEANi5VHx-Q1mIKmgZEg2ls47NGSlntttvcgLLbfKBpym4%253D&data=%7B%22groupLinkId%22%3A%22ndniy85i4DjITgVhB-MXnQ%3D%3D%22%7D'
 	#link = 'simplex:/contact#/?v=2-7&smp=smp%3A%2F%2FBD4qkVq8lJUgjHt0kUaxeQBYsKaxDejeecxm6-2vOwI%3D%40b6geeakpwskovltbesvy3b6ah3ewxfmnhnshojndmpp7wcv2df7bnead.onion%2FOReK0M4-3C5NeZyQx_yFuTHSknVVS-3h%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEANi5VHx-Q1mIKmgZEg2ls47NGSlntttvcgLLbfKBpym4%253D&data=%7B%22groupLinkId%22%3A%22ndniy85i4DjITgVhB-MXnQ%3D%3D%22%7D'
 	#link = 'https://simplex.chat/contact#/?v=2-7&smp=smp%3A%2F%2Fhpq7_4gGJiilmz5Rf-CswuU5kZGkm_zOIooSw6yALRg%3D%40smp5.simplex.im%2F2KNui9H8xxaPTuHAsQzJlfLmz_SOMsFk%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEA8BPETTg3ooyvQ1LiMGeCFbh2MeK9NyubT6NLE8EJzyA%253D%26srv%3Djjbyvoemxysm7qxap7m5d5m35jzv5qq6gnlv7s4rsn7tdwwmuqciwpid.onion&data=%7B%22type%22%3A%22group%22%2C%22groupLinkId%22%3A%22wNDKKQR3EW8Y045FsVofSg%3D%3D%22%7D'
-	link = 'https://simplex.hackliberty.org/contact/#/?v=2-7&smp=smp%3A%2F%2Fhpq7_4gGJiilmz5Rf-CswuU5kZGkm_zOIooSw6yALRg%3D%40smp5.simplex.im%2F2KNui9H8xxaPTuHAsQzJlfLmz_SOMsFk%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEA8BPETTg3ooyvQ1LiMGeCFbh2MeK9NyubT6NLE8EJzyA%253D%26srv%3Djjbyvoemxysm7qxap7m5d5m35jzv5qq6gnlv7s4rsn7tdwwmuqciwpid.onion&data=%7B%22type%22%3A%22group%22%2C%22groupLinkId%22%3A%22wNDKKQR3EW8Y045FsVofSg%3D%3D%22%7D'
+	#link = 'https://simplex.hackliberty.org/contact/#/?v=2-7&smp=smp%3A%2F%2Fhpq7_4gGJiilmz5Rf-CswuU5kZGkm_zOIooSw6yALRg%3D%40smp5.simplex.im%2F2KNui9H8xxaPTuHAsQzJlfLmz_SOMsFk%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEA8BPETTg3ooyvQ1LiMGeCFbh2MeK9NyubT6NLE8EJzyA%253D%26srv%3Djjbyvoemxysm7qxap7m5d5m35jzv5qq6gnlv7s4rsn7tdwwmuqciwpid.onion&data=%7B%22type%22%3A%22group%22%2C%22groupLinkId%22%3A%22wNDKKQR3EW8Y045FsVofSg%3D%3D%22%7D'
 	#link = 'http://b6geeakpwskovltbesvy3b6ah3ewxfmnhnshojndmpp7wcv2df7bnead.onion/contact/#/?v=2-7&smp=smp%3A%2F%2Fhpq7_4gGJiilmz5Rf-CswuU5kZGkm_zOIooSw6yALRg%3D%40smp5.simplex.im%2F2KNui9H8xxaPTuHAsQzJlfLmz_SOMsFk%23%2F%3Fv%3D1-3%26dh%3DMCowBQYDK2VuAyEA8BPETTg3ooyvQ1LiMGeCFbh2MeK9NyubT6NLE8EJzyA%253D%26srv%3Djjbyvoemxysm7qxap7m5d5m35jzv5qq6gnlv7s4rsn7tdwwmuqciwpid.onion&data=%7B%22type%22%3A%22group%22%2C%22groupLinkId%22%3A%22wNDKKQR3EW8Y045FsVofSg%3D%3D%22%7D'
 	print(IsSimpleXChatroomValid(link))

SimpleX/utils.py

@@ -5,7 +5,7 @@ def IsOnionValid(url: str)-> bool:
     Checks if the domain(param) is a valid onion domain and return True else False.
     """
     try:
-        pattern = re.compile("^[A-Za-z0-9.]+(.onion)?$")
+        pattern = re.compile(r"^[A-Za-z0-9:/._%-=#?&@]+(.onion)$")
         url = url.strip().removesuffix('/')
         if url.startswith('http://'):
             domain = url.split('/')[2]
@@ -40,7 +40,7 @@ def IsUrlValid(url:str)->bool:
         """
         Check if url is valid both dark net end clearnet.
         """
-        pattern  = re.compile("^[A-Za-z0-9:/.-]+$")
+        pattern = re.compile(r"^[A-Za-z0-9:/._%-=#?&@]+$")
         url = str(url)
         if len(url) < 4:
                 return False
@@ -51,4 +51,4 @@ def IsUrlValid(url:str)->bool:
                         return False
                 if pattern.fullmatch(url) is None:
                         return False
-                return True
+                return True