Bump version to 4.0.0

README.md

@@ -27,9 +27,10 @@ argument, and it treats the input as a single token or ngram.
 
 ### Compiling models
 
-    gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file>
+    gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file> <compiled model file>
 
-This will print the compiled model encoded in binary format to stdout.
+This will write the compiled model encoded in binary format to `<compiled model
+file>`.
 
 If `-c` is specified, words and ngrams used less than `min_count` times will be
 excluded from the compiled model.

gptc/__main__.py

@@ -13,8 +13,13 @@ def main() -> None:
     )
     subparsers = parser.add_subparsers(dest="subparser_name", required=True)
 
-    compile_parser = subparsers.add_parser("compile", help="compile a raw model")
+    compile_parser = subparsers.add_parser(
+        "compile", help="compile a raw model"
+    )
     compile_parser.add_argument("model", help="raw model to compile")
+    compile_parser.add_argument(
+        "out", help="name of file to write compiled model to"
+    )
     compile_parser.add_argument(
         "--max-ngram-length",
         "-n",
@@ -53,11 +58,15 @@ def main() -> None:
         action="store_true",
     )
 
-    check_parser = subparsers.add_parser("check", help="check one word or ngram in model")
+    check_parser = subparsers.add_parser(
+        "check", help="check one word or ngram in model"
+    )
     check_parser.add_argument("model", help="compiled model to use")
     check_parser.add_argument("token", help="token or ngram to check")
 
-    pack_parser = subparsers.add_parser("pack", help="pack a model from a directory")
+    pack_parser = subparsers.add_parser(
+        "pack", help="pack a model from a directory"
+    )
     pack_parser.add_argument("model", help="directory containing model")
 
     args = parser.parse_args()
@@ -66,7 +75,10 @@ def main() -> None:
         with open(args.model, "r") as f:
             model = json.load(f)
 
-        gptc.compile(model, args.max_ngram_length, args.min_count).serialize(sys.stdout.buffer)
+        with open(args.out, "wb+") as f:
+            gptc.compile(
+                model, args.max_ngram_length, args.min_count
+            ).serialize(f)
     elif args.subparser_name == "classify":
         with open(args.model, "rb") as f:
             model = gptc.deserialize(f)
@@ -76,7 +88,6 @@ def main() -> None:
         else:
             text = sys.stdin.read()
 
-
         if args.category:
             classifier = gptc.Classifier(model, args.max_ngram_length)
             print(classifier.classify(text))

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gptc"
-version = "3.1.1"
+version = "4.0.0"
 description = "General-purpose text classifier"
 readme = "README.md"
 authors = [{ name = "Samuel Sloniker", email = "sam@kj7rrv.com"}]