| 1 | """Tests for scripts/topic_paths.py — topic-aware data directory resolution.""" |
| 2 | |
| 3 | from __future__ import annotations |
| 4 | |
| 5 | import pytest |
| 6 | |
| 7 | from scripts.topic_paths import ( |
| 8 | DATA_ROOT, |
| 9 | DEFAULT_TOPIC, |
| 10 | analyzed_dir, |
| 11 | cache_dir, |
| 12 | ensure_dirs, |
| 13 | load_topic_id, |
| 14 | metrics_dir, |
| 15 | raw_dir, |
| 16 | snapshots_dir, |
| 17 | ) |
| 18 | |
| 19 | |
| 20 | class TestDefaultTopic: |
| 21 | """When topic is None or 'general', use legacy flat paths.""" |
| 22 | |
| 23 | def test_raw_dir_none(self): |
| 24 | assert raw_dir(None) == DATA_ROOT / "raw" |
| 25 | |
| 26 | def test_raw_dir_general(self): |
| 27 | assert raw_dir("general") == DATA_ROOT / "raw" |
| 28 | |
| 29 | def test_analyzed_dir_default(self): |
| 30 | assert analyzed_dir() == DATA_ROOT / "analyzed" |
| 31 | |
| 32 | def test_metrics_dir_default(self): |
| 33 | assert metrics_dir() == DATA_ROOT / "metrics" |
| 34 | |
| 35 | def test_snapshots_dir_default(self): |
| 36 | assert snapshots_dir() == DATA_ROOT / "snapshots" |
| 37 | |
| 38 | def test_cache_dir_default(self): |
| 39 | assert cache_dir() == DATA_ROOT / "cache" |
| 40 | |
| 41 | |
| 42 | class TestNamespacedTopic: |
| 43 | """When a specific topic is given, paths include the topic subdirectory.""" |
| 44 | |
| 45 | def test_raw_dir_ai_ml(self): |
| 46 | assert raw_dir("ai-ml") == DATA_ROOT / "raw" / "ai-ml" |
| 47 | |
| 48 | def test_analyzed_dir_rust(self): |
| 49 | assert analyzed_dir("rust") == DATA_ROOT / "analyzed" / "rust" |
| 50 | |
| 51 | def test_metrics_dir_topic(self): |
| 52 | assert metrics_dir("web-dev") == DATA_ROOT / "metrics" / "web-dev" |
| 53 | |
| 54 | def test_snapshots_dir_topic(self): |
| 55 | assert snapshots_dir("ai-ml") == DATA_ROOT / "snapshots" / "ai-ml" |
| 56 | |
| 57 | def test_cache_dir_topic(self): |
| 58 | assert cache_dir("rust") == DATA_ROOT / "cache" / "rust" |
| 59 | |
| 60 | def test_case_normalization(self): |
| 61 | assert raw_dir("AI-ML") == DATA_ROOT / "raw" / "ai-ml" |
| 62 | |
| 63 | def test_whitespace_stripped(self): |
| 64 | assert raw_dir(" rust ") == DATA_ROOT / "raw" / "rust" |
| 65 | |
| 66 | |
| 67 | class TestEnsureDirs: |
| 68 | """ensure_dirs creates all required directories.""" |
| 69 | |
| 70 | def test_creates_all_dirs(self, tmp_path, monkeypatch): |
| 71 | monkeypatch.setattr("scripts.topic_paths.DATA_ROOT", tmp_path / "data") |
| 72 | ensure_dirs("ai-ml") |
| 73 | for subdir in ("raw", "analyzed", "metrics", "snapshots", "cache"): |
| 74 | assert (tmp_path / "data" / subdir / "ai-ml").is_dir() |
| 75 | |
| 76 | def test_creates_flat_dirs_for_general(self, tmp_path, monkeypatch): |
| 77 | monkeypatch.setattr("scripts.topic_paths.DATA_ROOT", tmp_path / "data") |
| 78 | ensure_dirs(None) |
| 79 | for subdir in ("raw", "analyzed", "metrics", "snapshots", "cache"): |
| 80 | assert (tmp_path / "data" / subdir).is_dir() |
| 81 | |
| 82 | |
| 83 | class TestLoadTopicId: |
| 84 | """load_topic_id reads the topic.id from YAML config.""" |
| 85 | |
| 86 | def test_reads_valid_config(self, tmp_path): |
| 87 | config = tmp_path / "topic.yml" |
| 88 | config.write_text("topic:\n id: rust\n name: Rust\n") |
| 89 | assert load_topic_id(config) == "rust" |
| 90 | |
| 91 | def test_missing_file_returns_default(self, tmp_path): |
| 92 | assert load_topic_id(tmp_path / "nope.yml") == DEFAULT_TOPIC |
| 93 | |
| 94 | def test_malformed_yaml_returns_default(self, tmp_path): |
| 95 | config = tmp_path / "bad.yml" |
| 96 | config.write_text("{{invalid yaml") |
| 97 | assert load_topic_id(config) == DEFAULT_TOPIC |
| 98 | |
| 99 | def test_missing_topic_key_returns_default(self, tmp_path): |
| 100 | config = tmp_path / "empty.yml" |
| 101 | config.write_text("scoring:\n min_stars: 10\n") |
| 102 | assert load_topic_id(config) == DEFAULT_TOPIC |
| 103 | |
| 104 | |
| 105 | class TestTopicIdValidation: |
| 106 | """_resolve must reject topic IDs that could cause path traversal.""" |
| 107 | |
| 108 | def test_dotdot_raises(self): |
| 109 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 110 | |
| 111 | with pytest.raises(ValueError, match="Invalid topic ID"): |
| 112 | _resolve(DATA_ROOT / "raw", "../../../etc") |
| 113 | |
| 114 | def test_absolute_path_raises(self): |
| 115 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 116 | |
| 117 | with pytest.raises(ValueError, match="Invalid topic ID"): |
| 118 | _resolve(DATA_ROOT / "raw", "/etc/passwd") |
| 119 | |
| 120 | def test_slash_in_id_raises(self): |
| 121 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 122 | |
| 123 | with pytest.raises(ValueError, match="Invalid topic ID"): |
| 124 | _resolve(DATA_ROOT / "raw", "valid/subdir") |
| 125 | |
| 126 | def test_null_byte_raises(self): |
| 127 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 128 | |
| 129 | with pytest.raises(ValueError, match="Invalid topic ID"): |
| 130 | _resolve(DATA_ROOT / "raw", "evil\x00byte") |
| 131 | |
| 132 | def test_leading_hyphen_raises(self): |
| 133 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 134 | |
| 135 | with pytest.raises(ValueError, match="Invalid topic ID"): |
| 136 | _resolve(DATA_ROOT / "raw", "-bad") |
| 137 | |
| 138 | def test_valid_hyphenated_id_passes(self): |
| 139 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 140 | |
| 141 | result = _resolve(DATA_ROOT / "raw", "ai-ml") |
| 142 | assert result == DATA_ROOT / "raw" / "ai-ml" |
| 143 | |
| 144 | def test_valid_underscore_id_passes(self): |
| 145 | from scripts.topic_paths import DATA_ROOT, _resolve |
| 146 | |
| 147 | result = _resolve(DATA_ROOT / "raw", "rust_2026") |
| 148 | assert result == DATA_ROOT / "raw" / "rust_2026" |