expand keyword tests

nomen/utils.py

@@ -1,55 +1,15 @@
 import logging
 from asyncio import TimeoutError
-from itertools import chain
 
 import re2 as re
 from disnake.ext.commands import BadArgument
 
 log = logging.getLogger("nomen.utils")
 
-ALPHABET = list("abcdefghijklmnopqrstuvwxyz ")
+ALPHABET = "abcdefghijklmnopqrstuvwxyz"
+SYMBOLS = "!@#$%^&*()[]{}-_=+`~;:'\"/\\"
 
-COMMON_WORDS = [
-    # common words
-    "of",
-    "in",
-    "is",
-    "to",
-    "it",
-    "as",
-    "on",
-    "by",
-    "or",
-    "be",
-    "an",
-    "at",
-    "if",
-    "up",
-    "so",
-    "do",
-    "th",
-    "no",
-    "de",
-    "the",
-    "and",
-    "was",
-    "for",
-    "that",
-    "are",
-    "with",
-    "from",
-    "this",
-    "not",
-    "also",
-    "has",
-    "were",
-    "which",
-    "have",
-    "people",
-    "one",
-    "can",
-    "help",
-    # pronouns
+PRONOUNS = [
     "you",
     "your",
     "yours",
@@ -67,15 +27,92 @@ COMMON_WORDS = [
     "theirs",
     "themself",
     "themselves",
-    "a" * 100,
+    "we",
+    "me",
+    "any",
+    "us",
 ]
 
-TESTS = list(
-    chain(
-        ALPHABET,  # single letters
-        COMMON_WORDS,
-    )
-)
+NUMBERS = [
+    *"0123456789",
+    "10",
+    "zero",
+    "one",
+    "two",
+    "three",
+    "four",
+    "five",
+    "six",
+    "seven",
+    "eight",
+    "nine",
+    "ten",
+]
+
+COMMON_WORDS = [
+    "about",
+    "after",
+    "also",
+    "an",
+    "and",
+    "are",
+    "as",
+    "at",
+    "be",
+    "by",
+    "can",
+    "do",
+    "for",
+    "from",
+    "has",
+    "have",
+    "help",
+    "if",
+    "in",
+    "into",
+    "is",
+    "it",
+    "no",
+    "not",
+    "of",
+    "on",
+    "or",
+    "over",
+    "people",
+    "so",
+    "that",
+    "the",
+    "this",
+    "to",
+    "up",
+    "was",
+    "were",
+    "which",
+    "with",
+]
+
+COMMON_FRAGMENTS = [
+    "de",
+    "th",
+    "un",
+]
+
+WILDCARDS = [
+    "a" * 100,  # letters
+    "0" * 100,  # numbers
+    " " * 100,  # whitespace
+]
+
+TESTS = [
+    *ALPHABET,
+    *NUMBERS,
+    *PRONOUNS,
+    *COMMON_WORDS,
+    *COMMON_FRAGMENTS,
+    *WILDCARDS,
+    " ",  # single space
+    "\n",  # newline
+]
 
 
 regex_cache = {}