chore(build): cleanup code and add new unit test

Author: AlgorithmAlchemy

flake8_no_emoji/checker.py

@@ -67,4 +67,4 @@ def run(self) -> Generator[Tuple[int, int, str, Type["NoEmojiChecker"]], None, N
                         continue
 
                     yield lineno, match.start(), self._error_tmpl, type(self)
-                    break   # stop after 1 match
+                    break  # stop after 1 match

pyproject.toml

@@ -12,7 +12,7 @@ readme = "README.md"
 requires-python = ">=3.8"
 license = { text = "MIT" }
 authors = [
-  { name = "AlgorithmAlchemy" }
+    { name = "AlgorithmAlchemy" }
 ]
 keywords = ["flake8", "plugin", "emoji", "linter", "pre-commit", "unicode", "code style", "static analysis", "code quality", "no-emoji-in-code"]
 classifiers = [
@@ -33,8 +33,8 @@ classifiers = [
 ]
 
 dependencies = [
-  "regex",
-  "emoji>=2.0.0"
+    "regex",
+    "emoji>=2.0.0"
 ]
 
 [project.entry-points."flake8.extension"]

tests/test_checker.py

@@ -7,12 +7,20 @@
 from flake8_no_emoji.checker import NoEmojiChecker
 
 
-def run_checker_on_content(content, ignore_emoji_types=None, only_emoji_types=None):
-    """Write content to temp file, set options, run checker, return results."""
-    fd, path = tempfile.mkstemp(suffix=".py", text=True)
+def run_checker_on_content(content, ignore_emoji_types=None, only_emoji_types=None, filename=None):
+    """
+    Write content to a temp file (if filename not provided), set options, run checker, return results.
+    Allows passing a real file path for special cases like unreadable or binary files.
+    """
+    if filename is None:
+        fd, path = tempfile.mkstemp(suffix=".py", text=True)
+    else:
+        path = filename
+
     try:
-        with os.fdopen(fd, "w", encoding="utf-8") as f:
-            f.write(content)
+        if filename is None:
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                f.write(content)
 
         opts = SimpleNamespace(
             ignore_emoji_types=(ignore_emoji_types or ""),
@@ -24,10 +32,11 @@ def run_checker_on_content(content, ignore_emoji_types=None, only_emoji_types=No
         checker._only_categories = NoEmojiChecker._only_categories
         return list(checker.run())
     finally:
-        try:
-            os.unlink(path)
-        except OSError:
-            pass
+        if filename is None:
+            try:
+                os.unlink(path)
+            except OSError:
+                pass
 
 
 def test_detect_any_emoji_by_default():
@@ -181,3 +190,159 @@ def test_multiple_lines_with_only_emojis():
     content = "😀\n🐶\n⭐\n🛸\n👩‍💻"
     results = run_checker_on_content(content)
     assert len(results) == 5, "Each line with single emoji should be detected"
+
+
+def test_empty_file():
+    results = run_checker_on_content("")
+    assert results == [], "Empty file should produce no results"
+
+
+def test_empty_comment():
+    results = run_checker_on_content("# ")
+    assert results == [], "Empty comment should produce no results"
+
+
+def test_unreadable_file(tmp_path):
+    path = tmp_path / "unreadable.py"
+    path.write_text("x = '😀'")
+    os.chmod(path, 0)  # remove permissions
+    results = run_checker_on_content("", filename=str(path))
+    assert results == [], "Unreadable file should produce no results"
+    os.chmod(path, 0o644)
+
+
+def test_binary_file(tmp_path):
+    path = tmp_path / "binary.bin"
+    path.write_bytes(b"\x00\x01\x02\x03\x04")
+    results = run_checker_on_content("", filename=str(path))
+    assert results == [], "Binary file should produce no results"
+
+
+def test_disable_all_checks():
+    # simulate ignoring all categories
+    results = run_checker_on_content("x = '😀🐶⭐'",
+                                     ignore_emoji_types="PEOPLE,NATURE,FOOD,ACTIVITY,TRAVEL,OBJECTS,SYMBOLS,FLAGS,OTHER")
+    assert results == [], "All emoji checks disabled should produce no results"
+
+
+def test_non_english_with_noqa():
+    content = "# Привет 🌸 # noqa"
+    results = run_checker_on_content(content)
+    assert results == [], "Line with # noqa should skip emoji check"
+
+
+def test_comment_with_multiple_noqa():
+    content = "# 🚀 test # noqa something else # noqa"
+    results = run_checker_on_content(content)
+    assert results == [], "Multiple # noqa should skip check"
+
+
+def test_string_with_noqa():
+    content = "x = '😀' # noqa"
+    results = run_checker_on_content(content)
+    assert results == [], "String with # noqa should skip check"
+
+
+def test_emoji_in_multiline_string():
+    content = '''x = """Line 1
+🚀 Line 2
+Line 3 🐶"""'''
+    results = run_checker_on_content(content)
+    assert len(results) == 2, "Should detect emoji in multiline strings"
+
+
+def test_emoji_in_docstring():
+    content = '''"""
+This is a docstring with emoji 🌸
+"""'''
+    results = run_checker_on_content(content)
+    assert len(results) == 1, "Should detect emoji in docstrings"
+
+
+def test_emoji_in_variable_name():
+    content = "😀 = 5"
+    results = run_checker_on_content(content)
+    assert results, "Should detect emoji in variable names"
+
+
+def test_emoji_in_function_name():
+    content = "def 🐶():\n    pass"
+    results = run_checker_on_content(content)
+    assert results, "Should detect emoji in function names"
+
+
+def test_multiple_noqa_in_code():
+    content = "# noqa 🚀\n😀 # noqa"
+    results = run_checker_on_content(content)
+    assert results == [], "Multiple # noqa should skip all checks"
+
+
+def test_only_category_with_no_matches():
+    results = run_checker_on_content("x = '😀🐶'", only_emoji_types="FLAGS")
+    assert results == [], "No matches for only category should yield no results"
+
+
+def test_ignore_category_with_all_matches():
+    results = run_checker_on_content("x = '😀🐶⭐'", ignore_emoji_types="PEOPLE,NATURE,SYMBOLS")
+    assert results == [], "Ignoring all categories with matches should yield no results"
+
+
+def test_unicode_non_emoji_characters():
+    content = "x = '© ™ ∑ √'"
+    results = run_checker_on_content(content)
+    assert results == [], "Unicode symbols that are not emojis should not be detected"
+
+
+def test_emoji_with_combining_characters():
+    content = "x = '🇺🇸‍👩‍🚀'"
+    results = run_checker_on_content(content)
+    assert results, "Emoji with combining characters should be detected"
+
+
+def test_long_file_with_sparse_emojis(tmp_path):
+    path = tmp_path / "long_file.py"
+    lines = ["print('line {}')\n".format(i) for i in range(1000)]
+    lines[500] = "print('🚀')\n"
+    path.write_text("".join(lines), encoding="utf-8")
+    results = run_checker_on_content("", filename=str(path))
+    assert results, "Long file with sparse emoji should detect at least one"
+
+
+def test_noqa_with_different_cases():
+    content = "# NoQA 🚀\n😀 # NoQa"
+    results = run_checker_on_content(content)
+    assert results == [], "NoQA in different cases should still skip checks"
+
+
+def test_multiple_emojis_with_noqa():
+    content = "x = '😀🐶⭐' # noqa"
+    results = run_checker_on_content(content)
+    assert results == [], "Line with multiple emojis and noqa should skip all checks"
+
+
+def test_comment_only_with_emoji():
+    content = "# 🚀"
+    results = run_checker_on_content(content)
+    assert results, "Emoji in comment should be detected"
+
+
+def test_comment_with_emoji_and_text():
+    content = "# This is 🚀 a comment"
+    results = run_checker_on_content(content)
+    assert results, "Emoji in comment with text should be detected"
+
+
+def test_long_line_with_multiple_emojis():
+    content = "x = '😀🐶⭐🛸👩‍💻🏳️‍🌈' * 100"
+    results = run_checker_on_content(content)
+    assert len(results) == 1, "Only first emoji per line should be reported even for long lines"
+
+
+def test_ignore_case_category_names():
+    results = run_checker_on_content("x = '😀'", ignore_emoji_types="people")
+    assert results == [], "Category ignoring should be case insensitive"
+
+
+def test_only_case_category_names():
+    results = run_checker_on_content("x = '🐶'", only_emoji_types="nature")
+    assert results, "Category only check should be case insensitive"