Updated discord invite regex to match leading http/https/www

botcore/utils/regex.py

@@ -3,14 +3,15 @@
 import re
 
 DISCORD_INVITE = re.compile(
+    r"(https?://)?(www\.)?"                      # Optional http(s) and www.
     r"(discord([.,]|dot)gg|"                     # Could be discord.gg/
     r"discord([.,]|dot)com(/|slash)invite|"      # or discord.com/invite/
     r"discordapp([.,]|dot)com(/|slash)invite|"   # or discordapp.com/invite/
     r"discord([.,]|dot)me|"                      # or discord.me
     r"discord([.,]|dot)li|"                      # or discord.li
     r"discord([.,]|dot)io|"                      # or discord.io.
     r"((?<!\w)([.,]|dot))gg"                     # or .gg/
-    r")([/]|slash)"                              # / or 'slash'
+    r")(/|slash)"                                # / or 'slash'
     r"(?P<invite>\S+)",                          # the invite code itself
     flags=re.IGNORECASE
 )
@@ -32,7 +33,7 @@
     r"(?P<code>.*?)"                        # extract all code inside the markup
     r"\s*"                                  # any more whitespace before the end of the code markup
     r"(?P=delim)",                          # match the exact same delimiter from the start again
-    re.DOTALL | re.IGNORECASE               # "." also matches newlines, case insensitive
+    flags=re.DOTALL | re.IGNORECASE         # "." also matches newlines, case insensitive
 )
 """
 Regex for formatted code, using Discord's code blocks.
@@ -44,7 +45,7 @@
     r"^(?:[ \t]*\n)*"                       # any blank (empty or tabs/spaces only) lines before the code
     r"(?P<code>.*?)"                        # extract all the rest as code
     r"\s*$",                                # any trailing whitespace until the end of the string
-    re.DOTALL                               # "." also matches newlines
+    flags=re.DOTALL                         # "." also matches newlines
 )
 """
 Regex for raw code, *not* using Discord's code blocks.

docs/changelog.rst

@@ -3,6 +3,9 @@
 
 Changelog
 =========
+- :release:`8.1.0 <16th August 2022>`
+- :support:`124` Updated :obj:`botcore.utils.regex.DISCORD_INVITE` regex to optionally match leading "http[s]" and "www".
+
 
 - :release:`8.0.0 <27th July 2022>`
 - :breaking:`110` Bump async-rediscache to v1.0.0-rc2

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bot-core"
-version = "8.0.0"
+version = "8.1.0"
 description = "Bot-Core provides the core functionality and utilities for the bots of the Python Discord community."
 authors = ["Python Discord <info@pythondiscord.com>"]
 license = "MIT"

tests/botcore/utils/test_regex.py

@@ -4,8 +4,18 @@
 from botcore.utils.regex import DISCORD_INVITE
 
 
-def use_regex(s: str) -> Optional[str]:
-    """Helper function to run the Regex on a string.
+def match_regex(s: str) -> Optional[str]:
+    """Helper function to run re.match on a string.
+
+    Return the invite capture group, if the string matches the pattern
+        else return None
+    """
+    result = DISCORD_INVITE.match(s)
+    return result if result is None else result.group("invite")
+
+
+def search_regex(s: str) -> Optional[str]:
+    """Helper function to run re.search on a string.
 
     Return the invite capture group, if the string matches the pattern
         else return None
@@ -19,32 +29,37 @@ class UtilsRegexTests(unittest.TestCase):
     def test_discord_invite_positives(self):
         """Test the DISCORD_INVITE regex on a set of strings we would expect to capture."""
 
-        self.assertEqual(use_regex("discord.gg/python"), "python")
-        self.assertEqual(use_regex("https://discord.gg/python"), "python")
-        self.assertEqual(use_regex("discord.com/invite/python"), "python")
-        self.assertEqual(use_regex("discordapp.com/invite/python"), "python")
-        self.assertEqual(use_regex("discord.me/python"), "python")
-        self.assertEqual(use_regex("discord.li/python"), "python")
-        self.assertEqual(use_regex("discord.io/python"), "python")
-        self.assertEqual(use_regex(".gg/python"), "python")
-
-        self.assertEqual(use_regex("discord.gg/python/but/extra"), "python/but/extra")
-        self.assertEqual(use_regex("discord.me/this/isnt/python"), "this/isnt/python")
-        self.assertEqual(use_regex(".gg/a/a/a/a/a/a/a/a/a/a/a"), "a/a/a/a/a/a/a/a/a/a/a")
-        self.assertEqual(use_regex("discordapp.com/invite/python/snakescord"), "python/snakescord")
-        self.assertEqual(use_regex("http://discord.gg/python/%20/notpython"), "python/%20/notpython")
-        self.assertEqual(use_regex("discord.gg/python?=ts/notpython"), "python?=ts/notpython")
-        self.assertEqual(use_regex("https://discord.gg/python#fragment/notpython"), "python#fragment/notpython")
-        self.assertEqual(use_regex("https://discord.gg/python/~/notpython"), "python/~/notpython")
-
-        self.assertEqual(use_regex("https://discord.gg/python with whitespace"), "python")
-        self.assertEqual(use_regex(" https://discord.gg/python "), "python")
+        self.assertEqual(match_regex("discord.gg/python"), "python")
+        self.assertEqual(match_regex("https://discord.gg/python"), "python")
+        self.assertEqual(match_regex("https://www.discord.gg/python"), "python")
+        self.assertEqual(match_regex("discord.com/invite/python"), "python")
+        self.assertEqual(match_regex("www.discord.com/invite/python"), "python")
+        self.assertEqual(match_regex("discordapp.com/invite/python"), "python")
+        self.assertEqual(match_regex("discord.me/python"), "python")
+        self.assertEqual(match_regex("discord.li/python"), "python")
+        self.assertEqual(match_regex("discord.io/python"), "python")
+        self.assertEqual(match_regex(".gg/python"), "python")
+
+        self.assertEqual(match_regex("discord.gg/python/but/extra"), "python/but/extra")
+        self.assertEqual(match_regex("discord.me/this/isnt/python"), "this/isnt/python")
+        self.assertEqual(match_regex(".gg/a/a/a/a/a/a/a/a/a/a/a"), "a/a/a/a/a/a/a/a/a/a/a")
+        self.assertEqual(match_regex("discordapp.com/invite/python/snakescord"), "python/snakescord")
+        self.assertEqual(match_regex("http://discord.gg/python/%20/notpython"), "python/%20/notpython")
+        self.assertEqual(match_regex("discord.gg/python?=ts/notpython"), "python?=ts/notpython")
+        self.assertEqual(match_regex("https://discord.gg/python#fragment/notpython"), "python#fragment/notpython")
+        self.assertEqual(match_regex("https://discord.gg/python/~/notpython"), "python/~/notpython")
+
+        self.assertEqual(search_regex("https://discord.gg/python with whitespace"), "python")
+        self.assertEqual(search_regex(" https://discord.gg/python "), "python")
 
     def test_discord_invite_negatives(self):
         """Test the DISCORD_INVITE regex on a set of strings we would expect to not capture."""
 
-        self.assertEqual(use_regex("another string"), None)
-        self.assertEqual(use_regex("https://pythondiscord.com"), None)
-        self.assertEqual(use_regex("https://discord.com"), None)
-        self.assertEqual(use_regex("https://discord.gg"), None)
-        self.assertEqual(use_regex("https://discord.gg/ python"), None)
+        self.assertEqual(match_regex("another string"), None)
+        self.assertEqual(match_regex("https://pythondiscord.com"), None)
+        self.assertEqual(match_regex("https://discord.com"), None)
+        self.assertEqual(match_regex("https://discord.gg"), None)
+        self.assertEqual(match_regex("https://discord.gg/ python"), None)
+
+        self.assertEqual(search_regex("https://discord.com with whitespace"), None)
+        self.assertEqual(search_regex(" https://discord.com "), None)