Dictionaries und Schleifentechniken

PUNCTUATION = ".,!?;:"


def words(text: str) -> list[str]:
    """Split text into lower-case words without surrounding punctuation."""
    return text.split()

from main import words


def test_lower_case():
    """Schreibt jedes Wort klein"""
    got = words("The Cat")
    assert got == ["the", "cat"], f"words('The Cat') lieferte {got!r}, erwartet: ['the', 'cat']"


def test_punctuation():
    """Entfernt Satzzeichen an den Wortenden"""
    got = words("Hello, world! Hello?")
    assert got == ["hello", "world", "hello"], f"erhalten: {got!r}, erwartet: ['hello', 'world', 'hello']"


def test_no_empty_words():
    """Verwirft Teile, die nur aus Satzzeichen bestanden"""
    got = words("wait ... what")
    assert got == ["wait", "what"], f"words('wait ... what') lieferte {got!r}, erwartet: ['wait', 'what']"

PUNCTUATION = ".,!?;:"


def words(text: str) -> list[str]:
    """Split text into lower-case words without surrounding punctuation."""
    cleaned = [word.strip(PUNCTUATION) for word in text.lower().split()]
    return [word for word in cleaned if word]


def count_words(word_list: list[str]) -> dict[str, int]:
    """Return how often each word occurs."""
    counts: dict[str, int] = {}
    # Add 1 to the count of each word; a new word starts at 0.
    return counts

from main import count_words, words


def test_counts():
    """Zählt jedes Wort"""
    got = count_words(["the", "cat", "the"])
    assert got == {"the": 2, "cat": 1}, f"erhalten: {got!r}, erwartet: {{'the': 2, 'cat': 1}}"


def test_first_seen_order():
    """Behält die Wörter in der Reihenfolge ihres ersten Auftretens"""
    got = list(count_words(["b", "a", "b"]))
    assert got == ["b", "a"], f"die Schlüssel sind {got!r}, erwartet: ['b', 'a']"


def test_with_words():
    """Funktioniert mit dem Ergebnis von words()"""
    got = count_words(words("Go, go, GO!"))
    assert got == {"go": 3}, f"erhalten: {got!r}, erwartet: {{'go': 3}}"


def test_empty():
    """Keine Wörter ergeben ein leeres Dict"""
    got = count_words([])
    assert got == {}, f"count_words([]) lieferte {got!r}, erwartet: {{}}"

PUNCTUATION = ".,!?;:"


def words(text: str) -> list[str]:
    """Split text into lower-case words without surrounding punctuation."""
    cleaned = [word.strip(PUNCTUATION) for word in text.lower().split()]
    return [word for word in cleaned if word]


def count_words(word_list: list[str]) -> dict[str, int]:
    """Return how often each word occurs."""
    counts: dict[str, int] = {}
    for word in word_list:
        counts[word] = counts.get(word, 0) + 1
    return counts


def top_words(counts: dict[str, int], n: int) -> list[tuple[str, int]]:
    """Return the n most frequent (word, count) pairs; ties in alphabetical order."""
    return sorted(counts.items())[:n]


text = "The cat saw the dog. The dog saw a bird!"
for place, (word, count) in enumerate(top_words(count_words(words(text)), 3), start=1):
    print(place, word, count)

from main import top_words


def test_most_frequent_first():
    """Setzt das häufigste Wort an den Anfang"""
    got = top_words({"a": 1, "the": 3, "dog": 2}, 2)
    assert got == [("the", 3), ("dog", 2)], f"erhalten: {got!r}, erwartet: [('the', 3), ('dog', 2)]"


def test_ties_alphabetical():
    """Wörter mit gleicher Anzahl stehen alphabetisch"""
    got = top_words({"saw": 2, "dog": 2, "the": 3}, 3)
    assert got == [("the", 3), ("dog", 2), ("saw", 2)], f"erhalten: {got!r}, erwartet: [('the', 3), ('dog', 2), ('saw', 2)]"


def test_n_larger_than_dict():
    """Liefert alle Paare, wenn n größer ist als die Zahl der Wörter"""
    got = top_words({"hi": 1}, 5)
    assert got == [("hi", 1)], f"erhalten: {got!r}, erwartet: [('hi', 1)]"