Use PatternLite instead of defunkt pattern...

It looks like we get a loss in qualiity too

Makefile

@@ -30,7 +30,7 @@ all: develop
 
 #: Word-list data. Customize with lang and eventually WORDLIST_SIZE variables
 wordlist:
-	$(PYTHON) -m nltk.downloader wordnet2022 omw-1.4
+	$(PYTHON) -m nltk.downloader wordnet2022 omw-1.4 popular
 	$(PYTHON) -m spacy download $(SPACY_DOWNLOAD)
 
 #: build everything needed to install

pymathics/natlang/nltk.py

@@ -7,6 +7,8 @@
 from itertools import chain
 
 import nltk
+from pattern.en import lexeme, pluralize
+
 from mathics.builtin.codetables import iso639_3
 from mathics.core.atoms import String
 from mathics.core.builtin import Builtin, MessageException
@@ -304,12 +306,9 @@ def inflected_forms(self, syn, desc):
         try:
             word, pos, _ = desc
             if pos == "Verb":
-                from pattern.en import lexeme
 
                 return [w for w in reversed(lexeme(word)) if w != word]
             elif pos == "Noun":
-                from pattern.en import pluralize
-
                 return [pluralize(word)]
             elif pos == "Adjective":
                 from pattern.en import comparative, superlative

pymathics/natlang/normalization.py

@@ -101,7 +101,7 @@ class TextCases(_SpacyBuiltin):
     ## >> TextCases[Import["ExampleData/EinsteinSzilLetter.txt"], "Person", 3][[2;;3]]
     ##  = {L. Szilard, Joliot}
 
-    >> TextCases["Anne, Peter and Mr Johnes say hello.", "Person", 3][[2;;3]]
+    >> TextCases["Saul, Peter and Mr Johnes say hello.", "Person", 3][[2;;3]]
      = {Peter, Johnes}
 
     """

pymathics/natlang/textual_analysis.py

@@ -217,13 +217,13 @@ class WordSimilarity(_SpacyBuiltin):
     </dl>
 
     >> NumberForm[WordSimilarity["car", "train"], 3]
-     = 0.439
+     = 0.169
 
     >> NumberForm[WordSimilarity["car", "hedgehog"], 3]
-     = 0.195
+     = 0.0173
 
     >> NumberForm[WordSimilarity[{"An ocean full of water.", {2, 2}}, { "A desert full of sand.", {2, 5}}], 3]
-     = {0.505, 0.481}
+     = {0.127, 0.256}
     """
 
     messages = merge_dictionaries(

setup.py

@@ -59,10 +59,11 @@ def read(*rnames):
         "langid",  # replace with a supported newer package, e.g. via spacy
         "llvmlite>=0.36",
         "nltk>=3.8.0",
-        "pattern",
+        "PatternLite",
         "pyenchant>=3.2.0",
         "pycountry>=3.2.0",
         "spacy>=3.4",
+        "textblob",
         "wasabi<1.1.0,>=0.8.2",
     ],
     zip_safe=False,
@@ -76,11 +77,11 @@ def read(*rnames):
         "Intended Audience :: Science/Research",
         "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Programming Language :: Python",
-        "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
         "Programming Language :: Python :: Implementation :: CPython",
         "Programming Language :: Python :: Implementation :: PyPy",
         "Topic :: Scientific/Engineering",

test/consistency-and-style/test_summary_text.py

@@ -6,6 +6,9 @@
 
 import pytest
 
+from types import ModuleType
+from typing import Dict
+
 from mathics.core.load_builtin import name_is_builtin_symbol
 from mathics.core.builtin import Builtin
 from mathics.doc.gather import skip_doc

test/helper.py

@@ -1,7 +1,8 @@
 import time
 from typing import Optional
 
-from mathics.session import MathicsSession, import_and_load_builtins
+from mathics.core.load_builtin import import_and_load_builtins
+from mathics.session import MathicsSession
 
 import_and_load_builtins()