From 060bad105dc2569fc485adb03b985aa2ab5d367e Mon Sep 17 00:00:00 2001
From: Chris Lovering <chris.lovering.95@gmail.com>
Date: Tue, 22 Feb 2022 23:47:09 +0000
Subject: Move new utilities to the util namespace

---
 botcore/utils/regex.py | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 botcore/utils/regex.py

(limited to 'botcore/utils/regex.py')

diff --git a/botcore/utils/regex.py b/botcore/utils/regex.py
new file mode 100644
index 00000000..036a5113
--- /dev/null
+++ b/botcore/utils/regex.py
@@ -0,0 +1,48 @@
+"""Common regular expressions."""
+
+import re
+
+DISCORD_INVITE = re.compile(
+    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"(?P<invite>[a-zA-Z0-9\-]+)",               # the invite code itself
+    flags=re.IGNORECASE
+)
+"""
+Regex for discord server invites.
+
+:meta hide-value:
+"""
+
+FORMATTED_CODE_REGEX = re.compile(
+    r"(?P<delim>(?P<block>```)|``?)"        # code delimiter: 1-3 backticks; (?P=block) only matches if it's a block
+    r"(?(block)(?:(?P<lang>[a-z]+)\n)?)"    # if we're in a block, match optional language (only letters plus newline)
+    r"(?:[ \t]*\n)*"                        # any blank (empty or tabs/spaces only) lines before the code
+    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
+)
+"""
+Regex for formatted code, using Discord's code blocks.
+
+:meta hide-value:
+"""
+
+RAW_CODE_REGEX = re.compile(
+    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
+)
+"""
+Regex for raw code, *not* using Discord's code blocks.
+
+:meta hide-value:
+"""
-- 
cgit v1.2.3