Add text analyzer tests

tests/test_core.py

@@ -0,0 +1,190 @@
+"""Tests for text analyzer core."""
+
+from pathlib import Path
+
+import pytest
+
+from text_analyzer.core import (
+    TextStatistics,
+    analyze_file,
+    analyze_text,
+    count_words,
+    extract_words,
+)
+
+
+@pytest.mark.parametrize(
+    ("text", "expected"),
+    [
+        (
+            "Hello hello world",
+            ["hello", "hello", "world"],
+        ),
+        (
+            "One, two! THREE.",
+            ["one", "two", "three"],
+        ),
+        (
+            "Alpha-beta alpha-beta",
+            ["alpha-beta", "alpha-beta"],
+        ),
+    ],
+)
+def test_extract_words(
+    text: str,
+    expected: list[str],
+) -> None:
+    """Test word extraction."""
+    assert extract_words(text) == expected
+
+
+def test_extract_words_min_len() -> None:
+    """Test minimum word length."""
+    text = "a bb ccc dddd"
+
+    assert extract_words(
+        text,
+        min_len=3,
+    ) == ["ccc", "dddd"]
+
+
+def test_count_words() -> None:
+    """Test word frequency counting."""
+    result = count_words(
+        "apple apple banana",
+    )
+
+    assert result["apple"] == 2
+    assert result["banana"] == 1
+
+
+def test_analyze_text() -> None:
+    """Test complete text analysis."""
+    text = "Apple banana apple.\nBanana orange."
+
+    result = analyze_text(
+        text,
+        top=2,
+    )
+
+    assert result == TextStatistics(
+        lines=2,
+        words=5,
+        characters=len(text),
+        top_words=[
+            ("apple", 2),
+            ("banana", 2),
+        ],
+    )
+
+
+def test_empty_text() -> None:
+    """Test empty text."""
+    result = analyze_text("")
+
+    assert result.lines == 0
+    assert result.words == 0
+    assert result.characters == 0
+    assert result.top_words == []
+
+
+def test_empty_file(
+    tmp_path: Path,
+) -> None:
+    """Test empty file."""
+    path = tmp_path / "empty.txt"
+    path.write_text(
+        "",
+        encoding="utf-8",
+    )
+
+    result = analyze_file(path)
+
+    assert result.lines == 0
+    assert result.words == 0
+    assert result.characters == 0
+
+
+def test_missing_file(
+    tmp_path: Path,
+) -> None:
+    """Test missing file."""
+    path = tmp_path / "missing.txt"
+
+    with pytest.raises(FileNotFoundError):
+        analyze_file(path)
+
+
+def test_invalid_encoding(
+    tmp_path: Path,
+) -> None:
+    """Test invalid encoding."""
+    path = tmp_path / "invalid.txt"
+    path.write_bytes(b"\xff")
+
+    with pytest.raises(
+        UnicodeDecodeError,
+    ):
+        analyze_file(
+            path,
+            encoding="utf-8",
+        )
+
+
+@pytest.mark.parametrize(
+    ("top", "expected"),
+    [
+        (
+            0,
+            [],
+        ),
+        (
+            1,
+            [("apple", 3)],
+        ),
+        (
+            2,
+            [
+                ("apple", 3),
+                ("banana", 2),
+            ],
+        ),
+    ],
+)
+def test_top_parameter(
+    top: int,
+    expected: list[tuple[str, int]],
+) -> None:
+    """Test top-N parameter."""
+    text = "apple apple apple banana banana orange"
+
+    result = analyze_text(
+        text,
+        top=top,
+    )
+
+    assert result.top_words == expected
+
+
+def test_invalid_min_len() -> None:
+    """Test invalid min_len."""
+    with pytest.raises(
+        ValueError,
+        match="min_len",
+    ):
+        analyze_text(
+            "hello",
+            min_len=0,
+        )
+
+
+def test_invalid_top() -> None:
+    """Test invalid top."""
+    with pytest.raises(
+        ValueError,
+        match="top",
+    ):
+        analyze_text(
+            "hello",
+            top=-1,
+        )