Merge pull request #137 from mdevolde/tests

docs: separated tests in files, added doc and typing, moved cli tests from bash to python

Author: mdevolde

.github/workflows/test.yml

@@ -52,12 +52,7 @@ jobs:
 
     - name: Test with pytest
       run: |
-        pytest -vx --dist=loadfile -n auto
-
-    - name: Run additional tests in bash scripts for Ubuntu
-      run: |
-        bash tests/test_local.bash
-        bash tests/test_remote.bash
+        pytest --dist=loadfile -n auto
 
   lint:
     name: Lint with Ruff

Makefile

@@ -11,7 +11,7 @@ check:
 
 test:
 	pytest
-
+	uvx --with defusedxml genbadge coverage --input-file coverage.xml --silent
 doc:
 	source ./.venv/bin/activate && uv run sphinx-apidoc -o docs/source/references language_tool_python
 	source ./.venv/bin/activate && cd ./docs && make html

README.md

@@ -3,6 +3,7 @@
 [![language tool python on pypi](https://badge.fury.io/py/language-tool-python.svg)](https://pypi.org/project/language-tool-python/)
 [![Documentation Status](https://readthedocs.org/projects/language-tool-python/badge/?version=latest)](https://language-tool-python.readthedocs.io/en/latest/)
 [![Test with PyTest](https://github.com/jxmorris12/language_tool_python/workflows/Test%20with%20PyTest/badge.svg)](https://github.com/jxmorris12/language_tool_python/actions)
+[![Coverage Status](./coverage-badge.svg)](https://github.com/jxmorris12/language_tool_python/actions)
 [![Downloads](https://static.pepy.tech/badge/language-tool-python)](https://pepy.tech/project/language-tool-python)
 [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](LICENSE)
 [![Contributions Welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/jxmorris12/language_tool_python/pulls)

coverage-badge.svg

@@ -10,7 +10,7 @@
 from importlib.metadata import PackageNotFoundError, version
 from logging.config import dictConfig
 from pathlib import Path
-from typing import Any, Optional, Set, Union
+from typing import Any, Optional, Sequence, Set, Union
 
 import toml
 
@@ -37,7 +37,7 @@
 dictConfig(log_config)
 
 
-def parse_args() -> argparse.Namespace:
+def parse_args(argv: Optional[Sequence[str]] = None) -> argparse.Namespace:
     """
     Parse command line arguments.
 
@@ -121,7 +121,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--remote-port", help="port of the remote LanguageTool server")
     parser.add_argument("--verbose", action="store_true", help="enable verbose output")
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.enabled_only:
         if args.disable:
@@ -219,14 +219,14 @@ def print_exception(exc: Exception, debug: bool) -> None:
         print(exc, file=sys.stderr)
 
 
-def main() -> int:
+def main(argv: Optional[Sequence[str]] = None) -> int:
     """
     Main function to parse arguments, process files, and check text using LanguageTool.
 
     :return: Exit status code
     :rtype: int
     """
-    args = parse_args()
+    args = parse_args(argv)
 
     if args.verbose:
         logging.getLogger().setLevel(logging.DEBUG)
@@ -237,16 +237,6 @@ def main() -> int:
         if len(args.files) > 1:
             print(filename, file=sys.stderr)
 
-        if filename == "-":
-            filename = sys.stdin.fileno()
-            encoding = args.encoding or (
-                sys.stdin.encoding
-                if sys.stdin.isatty()
-                else locale.getpreferredencoding()
-            )
-        else:
-            encoding = args.encoding or "utf-8"
-
         remote_server = None
         if args.remote_host is not None:
             remote_server = args.remote_host
@@ -257,11 +247,27 @@ def main() -> int:
             mother_tongue=args.mother_tongue,
             remote_server=remote_server,
         ) as lang_tool:
-            try:
-                text = get_text(filename, encoding, ignore=args.ignore_lines)
-            except (UnicodeError, FileNotFoundError) as exception:
-                print_exception(exception, args.verbose)
-                continue
+            if filename == "-":
+                encoding = args.encoding or (
+                    sys.stdin.encoding
+                    if sys.stdin.isatty()
+                    else locale.getpreferredencoding()
+                )
+                raw = sys.stdin.read()
+                if args.ignore_lines:
+                    text = "".join(
+                        "\n" if re.match(args.ignore_lines, line) else line
+                        for line in raw.splitlines(keepends=True)
+                    )
+                else:
+                    text = raw
+            else:
+                encoding = args.encoding or "utf-8"
+                try:
+                    text = get_text(filename, encoding, ignore=args.ignore_lines)
+                except (UnicodeError, FileNotFoundError) as exception:
+                    print_exception(exception, args.verbose)
+                    continue
 
             if not args.spell_check:
                 lang_tool.disable_spellchecking()
@@ -302,4 +308,5 @@ def main() -> int:
     return status
 
 
-sys.exit(main())
+if __name__ == "__main__":
+    raise SystemExit(main())

language_tool_python/__main__.py

@@ -19,6 +19,7 @@ exit /b %errorlevel%
 
 :test
 pytest
+uvx --with defusedxml genbadge coverage --input-file coverage.xml --silent
 exit /b %errorlevel%
 
 :doc

make.bat

@@ -80,7 +80,7 @@ select = ["F", "W", "I", "B", "SIM", "RET", "Q", "N", "S", "BLE"]
 "tests/*.py" = ["S101"]
 
 [tool.mypy]
-files = ["language_tool_python"]
+files = ["language_tool_python", "tests"]
 strict = true
 warn_unused_ignores = true
 warn_redundant_casts = true

pyproject.toml

@@ -1,5 +1,5 @@
 [pytest]
-addopts = -ra --cov=language_tool_python --cov-report=html --cov-report=xml
+addopts = -vra --cov=language_tool_python --cov-report=html --cov-report=xml
 testpaths = tests
 
 [coverage:run]

pytest.ini

@@ -0,0 +1 @@
+"""Tests for language_tool_python package."""

tests/__init__.py

@@ -0,0 +1,26 @@
+"""Tests for the public API functionality."""
+
+from language_tool_python.exceptions import RateLimitError
+
+
+def test_remote_es() -> None:
+    """
+    Test the public API with Spanish language text.
+    This test verifies that the LanguageToolPublicAPI correctly identifies
+    various errors in a Spanish text sample.
+
+    :raises AssertionError: If the detected matches do not match the expected output.
+    """
+    import language_tool_python
+
+    try:
+        with language_tool_python.LanguageToolPublicAPI("es") as tool:
+            es_text = "Escriba un texto aquí. LanguageTool le ayudará a afrentar algunas dificultades propias de la escritura. Se a hecho un esfuerzo para detectar errores tipográficos, ortograficos y incluso gramaticales. También algunos errores de estilo, a grosso modo."
+            matches = tool.check(es_text)
+            assert (
+                str(matches)
+                == """[Match({'rule_id': 'AFRENTAR_DIFICULTADES', 'message': 'Confusión entre «afrontar» y «afrentar».', 'replacements': ['afrontar'], 'offset_in_context': 43, 'context': '...n texto aquí. LanguageTool le ayudará a afrentar algunas dificultades propias de la escr...', 'offset': 49, 'error_length': 8, 'category': 'INCORRECT_EXPRESSIONS', 'rule_issue_type': 'grammar', 'sentence': 'LanguageTool le ayudará a afrentar algunas dificultades propias de la escritura.'}), Match({'rule_id': 'PRON_HABER_PARTICIPIO', 'message': 'El v. ‘haber’ se escribe con hache.', 'replacements': ['ha'], 'offset_in_context': 43, 'context': '...ificultades propias de la escritura. Se a hecho un esfuerzo para detectar errores...', 'offset': 107, 'error_length': 1, 'category': 'MISSPELLING', 'rule_issue_type': 'misspelling', 'sentence': 'Se a hecho un esfuerzo para detectar errores tipográficos, ortograficos y incluso gramaticales.'}), Match({'rule_id': 'MORFOLOGIK_RULE_ES', 'message': 'Se ha encontrado un posible error ortográfico.', 'replacements': ['ortográficos', 'ortográficas', 'ortográfico', 'orográficos', 'ortografiaos', 'ortografíeos'], 'offset_in_context': 43, 'context': '...rzo para detectar errores tipográficos, ortograficos y incluso gramaticales. También algunos...', 'offset': 163, 'error_length': 12, 'category': 'TYPOS', 'rule_issue_type': 'misspelling', 'sentence': 'Se a hecho un esfuerzo para detectar errores tipográficos, ortograficos y incluso gramaticales.'}), Match({'rule_id': 'Y_E_O_U', 'message': 'Cuando precede a palabras que comienzan por ‘i’, la conjunción ‘y’ se transforma en ‘e’.', 'replacements': ['e'], 'offset_in_context': 43, 'context': '...ctar errores tipográficos, ortograficos y incluso gramaticales. También algunos e...', 'offset': 176, 'error_length': 1, 'category': 'GRAMMAR', 'rule_issue_type': 'grammar', 'sentence': 'Se a hecho un esfuerzo para detectar errores tipográficos, ortograficos y incluso gramaticales.'}), Match({'rule_id': 'GROSSO_MODO', 'message': 'Esta expresión latina se usa sin preposición.', 'replacements': ['grosso modo'], 'offset_in_context': 43, 'context': '...les. También algunos errores de estilo, a grosso modo.', 'offset': 235, 'error_length': 13, 'category': 'GRAMMAR', 'rule_issue_type': 'grammar', 'sentence': 'También algunos errores de estilo, a grosso modo.'})]"""
+            )
+    except RateLimitError:
+        print("Rate limit error: skipping test about public API.")
+        return