MIL-003: Step 2 - New flash cards

Review record RC-025 (Go, autonomous mode, not independent).

Task: MIL-003#1
Task: MIL-003#2
Task: MIL-003#3
Task: MIL-003#4
Task: MIL-003#5

tests/unit/infrastructure/test_csv_word_list.py

@@ -0,0 +1,95 @@
+"""Tests of read_word_list and CsvVocabularyRepository."""
+
+from pathlib import Path
+
+import pytest
+
+from flash_card.domain.entities.card import Card
+from flash_card.domain.errors.vocabulary_errors import (
+    VocabularyFormatError,
+    VocabularyNotFoundError,
+)
+from flash_card.domain.value_objects.language_pair import LanguagePair
+from flash_card.infrastructure.persistence.csv_vocabulary_repository import (
+    CsvVocabularyRepository,
+)
+from flash_card.infrastructure.persistence.csv_word_list import read_word_list
+
+
+def _write(path: Path, content: str) -> Path:
+    path.write_bytes(content.encode("utf-8"))
+    return path
+
+
+def test_read_word_list_returns_pair_and_cards(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", "ms;da\naku;mig\nkau;du\n")
+    pair, cards = read_word_list(path)
+    assert pair == LanguagePair("ms", "da")
+    assert cards == (Card("aku", "mig"), Card("kau", "du"))
+
+
+def test_read_word_list_drops_byte_order_mark(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", "ms;da\r\naku;mig\r\n")
+    pair, cards = read_word_list(path)
+    assert pair == LanguagePair("ms", "da")
+    assert cards == (Card("aku", "mig"),)
+
+
+def test_read_word_list_skips_blank_lines(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", "\nms;da\n\naku;mig\n  \n;\nkau;du\n\n")
+    _pair, cards = read_word_list(path)
+    assert cards == (Card("aku", "mig"), Card("kau", "du"))
+
+
+def test_read_word_list_strips_whitespace(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", " ms ; da \n aku ; mig \n")
+    pair, cards = read_word_list(path)
+    assert pair == LanguagePair("ms", "da")
+    assert cards == (Card("aku", "mig"),)
+
+
+def test_read_word_list_raises_not_found_when_file_is_missing(
+    tmp_path: Path,
+) -> None:
+    with pytest.raises(VocabularyNotFoundError) as info:
+        read_word_list(tmp_path / "missing.csv")
+    assert isinstance(info.value.__cause__, FileNotFoundError)
+
+
+def test_read_word_list_raises_format_error_when_file_is_empty(
+    tmp_path: Path,
+) -> None:
+    path = _write(tmp_path / "w.csv", "\n\n")
+    with pytest.raises(VocabularyFormatError, match="empty"):
+        read_word_list(path)
+
+
+@pytest.mark.parametrize("header", ["ms\n", "ms;da;en\n", "ms;\n"])
+def test_read_word_list_raises_format_error_for_bad_header(
+    tmp_path: Path, header: str
+) -> None:
+    path = _write(tmp_path / "w.csv", header + "aku;mig\n")
+    with pytest.raises(VocabularyFormatError, match="line 1"):
+        read_word_list(path)
+
+
+def test_read_word_list_raises_format_error_with_line_number_for_bad_row(
+    tmp_path: Path,
+) -> None:
+    path = _write(tmp_path / "w.csv", "ms;da\naku;mig\n\nkau;du;extra\n")
+    with pytest.raises(VocabularyFormatError, match="line 4") as info:
+        read_word_list(path)
+    assert str(path) in str(info.value)
+
+
+def test_repository_load_returns_vocabulary(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", "ms;da\naku;mig\n")
+    vocabulary = CsvVocabularyRepository(path).load()
+    assert vocabulary.language_pair == LanguagePair("ms", "da")
+    assert vocabulary.cards == (Card("aku", "mig"),)
+
+
+def test_repository_load_raises_format_error_when_no_card(tmp_path: Path) -> None:
+    path = _write(tmp_path / "w.csv", "ms;da\n")
+    with pytest.raises(VocabularyFormatError):
+        CsvVocabularyRepository(path).load()