|
| 1 | +"""Tests for parse_distribution_str function in cli.py""" |
| 2 | + |
| 3 | +from unittest.mock import patch |
| 4 | + |
| 5 | +import pytest |
| 6 | + |
| 7 | +from databusclient.cli import parse_distribution_str |
| 8 | +from databusclient.api.deploy import ( |
| 9 | + create_dataset, |
| 10 | + _get_file_info_from_dict, |
| 11 | +) |
| 12 | + |
| 13 | + |
| 14 | +class TestParseDistributionStr: |
| 15 | + """Unit tests for parse_distribution_str function.""" |
| 16 | + |
| 17 | + # ------------------------------------------------------------------------- |
| 18 | + # URL Extraction Tests |
| 19 | + # ------------------------------------------------------------------------- |
| 20 | + |
| 21 | + def test_basic_url_extraction(self): |
| 22 | + """Test that URL is correctly extracted from distribution string.""" |
| 23 | + result = parse_distribution_str("http://example.com/data.json") |
| 24 | + assert result["url"] == "http://example.com/data.json" |
| 25 | + |
| 26 | + def test_url_with_modifiers(self): |
| 27 | + """Test URL extraction when modifiers are present.""" |
| 28 | + result = parse_distribution_str("http://example.com/data.json|lang=en|.json") |
| 29 | + assert result["url"] == "http://example.com/data.json" |
| 30 | + |
| 31 | + # ------------------------------------------------------------------------- |
| 32 | + # Content Variant Parsing Tests |
| 33 | + # ------------------------------------------------------------------------- |
| 34 | + |
| 35 | + def test_single_variant(self): |
| 36 | + """Test parsing a single key=value variant.""" |
| 37 | + result = parse_distribution_str("http://example.com/file|lang=en") |
| 38 | + assert result["variants"] == {"lang": "en"} |
| 39 | + |
| 40 | + def test_multiple_variants(self): |
| 41 | + """Test parsing multiple key=value variants.""" |
| 42 | + result = parse_distribution_str("http://example.com/file|lang=en|type=full|quality=high") |
| 43 | + assert result["variants"] == { |
| 44 | + "lang": "en", |
| 45 | + "type": "full", |
| 46 | + "quality": "high", |
| 47 | + } |
| 48 | + |
| 49 | + def test_variant_with_equals_in_value(self): |
| 50 | + """Test variant where value contains equals sign.""" |
| 51 | + result = parse_distribution_str("http://example.com/file|filter=a=b") |
| 52 | + assert result["variants"] == {"filter": "a=b"} |
| 53 | + |
| 54 | + def test_empty_variants(self): |
| 55 | + """Test that empty variants dict is returned when no variants present.""" |
| 56 | + result = parse_distribution_str("http://example.com/file.json|.json") |
| 57 | + assert result["variants"] == {} |
| 58 | + |
| 59 | + # ------------------------------------------------------------------------- |
| 60 | + # Format Extension Tests |
| 61 | + # ------------------------------------------------------------------------- |
| 62 | + |
| 63 | + def test_json_extension(self): |
| 64 | + """Test .json format extension detection.""" |
| 65 | + result = parse_distribution_str("http://example.com/file|.json") |
| 66 | + assert result["formatExtension"] == "json" |
| 67 | + |
| 68 | + def test_ttl_extension(self): |
| 69 | + """Test .ttl format extension detection.""" |
| 70 | + result = parse_distribution_str("http://example.com/file|.ttl") |
| 71 | + assert result["formatExtension"] == "ttl" |
| 72 | + |
| 73 | + def test_csv_extension(self): |
| 74 | + """Test .csv format extension detection.""" |
| 75 | + result = parse_distribution_str("http://example.com/file|.csv") |
| 76 | + assert result["formatExtension"] == "csv" |
| 77 | + |
| 78 | + def test_xml_extension(self): |
| 79 | + """Test .xml format extension detection.""" |
| 80 | + result = parse_distribution_str("http://example.com/file|.xml") |
| 81 | + assert result["formatExtension"] == "xml" |
| 82 | + |
| 83 | + def test_no_extension(self): |
| 84 | + """Test that formatExtension is None when not provided.""" |
| 85 | + result = parse_distribution_str("http://example.com/file|lang=en") |
| 86 | + assert result["formatExtension"] is None |
| 87 | + |
| 88 | + # ------------------------------------------------------------------------- |
| 89 | + # Compression Detection Tests |
| 90 | + # ------------------------------------------------------------------------- |
| 91 | + |
| 92 | + def test_gz_compression(self): |
| 93 | + """Test .gz compression detection.""" |
| 94 | + result = parse_distribution_str("http://example.com/file|.gz") |
| 95 | + assert result["compression"] == "gz" |
| 96 | + |
| 97 | + def test_zip_compression(self): |
| 98 | + """Test .zip compression detection.""" |
| 99 | + result = parse_distribution_str("http://example.com/file|.zip") |
| 100 | + assert result["compression"] == "zip" |
| 101 | + |
| 102 | + def test_br_compression(self): |
| 103 | + """Test .br (brotli) compression detection.""" |
| 104 | + result = parse_distribution_str("http://example.com/file|.br") |
| 105 | + assert result["compression"] == "br" |
| 106 | + |
| 107 | + def test_tar_compression(self): |
| 108 | + """Test .tar compression detection.""" |
| 109 | + result = parse_distribution_str("http://example.com/file|.tar") |
| 110 | + assert result["compression"] == "tar" |
| 111 | + |
| 112 | + def test_zst_compression(self): |
| 113 | + """Test .zst (zstandard) compression detection.""" |
| 114 | + result = parse_distribution_str("http://example.com/file|.zst") |
| 115 | + assert result["compression"] == "zst" |
| 116 | + |
| 117 | + def test_no_compression(self): |
| 118 | + """Test that compression is None when not provided.""" |
| 119 | + result = parse_distribution_str("http://example.com/file|.json") |
| 120 | + assert result["compression"] is None |
| 121 | + |
| 122 | + # ------------------------------------------------------------------------- |
| 123 | + # Combined Modifiers Tests |
| 124 | + # ------------------------------------------------------------------------- |
| 125 | + |
| 126 | + def test_full_distribution_string(self): |
| 127 | + """Test parsing a complete distribution string with all modifiers.""" |
| 128 | + result = parse_distribution_str( |
| 129 | + "http://mysite.com/data.json|lang=fr|quality=high|.json|.gz" |
| 130 | + ) |
| 131 | + assert result == { |
| 132 | + "url": "http://mysite.com/data.json", |
| 133 | + "variants": {"lang": "fr", "quality": "high"}, |
| 134 | + "formatExtension": "json", |
| 135 | + "compression": "gz", |
| 136 | + } |
| 137 | + |
| 138 | + def test_order_independence(self): |
| 139 | + """Test that order of modifiers doesn't affect parsing.""" |
| 140 | + result = parse_distribution_str( |
| 141 | + "http://example.com/file|.gz|lang=en|.json|type=full" |
| 142 | + ) |
| 143 | + assert result["variants"] == {"lang": "en", "type": "full"} |
| 144 | + assert result["formatExtension"] == "json" |
| 145 | + assert result["compression"] == "gz" |
| 146 | + |
| 147 | + # ------------------------------------------------------------------------- |
| 148 | + # Edge Cases |
| 149 | + # ------------------------------------------------------------------------- |
| 150 | + |
| 151 | + def test_whitespace_handling(self): |
| 152 | + """Test that whitespace is properly stripped.""" |
| 153 | + result = parse_distribution_str("http://example.com/file | lang = en | .json ") |
| 154 | + assert result["url"] == "http://example.com/file" |
| 155 | + assert result["variants"] == {"lang": "en"} |
| 156 | + assert result["formatExtension"] == "json" |
| 157 | + |
| 158 | + def test_standalone_tag_warning(self, capsys): |
| 159 | + """Test that standalone tags (without =) produce a warning.""" |
| 160 | + result = parse_distribution_str("http://example.com/file|unknown_tag") |
| 161 | + captured = capsys.readouterr() |
| 162 | + assert "WARNING" in captured.out |
| 163 | + assert "unknown_tag" in captured.out |
| 164 | + # Standalone tags should not be added to variants |
| 165 | + assert "unknown_tag" not in result["variants"] |
| 166 | + |
| 167 | + def test_url_only(self): |
| 168 | + """Test parsing URL without any modifiers.""" |
| 169 | + result = parse_distribution_str("http://example.com/data.json") |
| 170 | + assert result == { |
| 171 | + "url": "http://example.com/data.json", |
| 172 | + "variants": {}, |
| 173 | + "formatExtension": None, |
| 174 | + "compression": None, |
| 175 | + } |
| 176 | + |
| 177 | + |
| 178 | +class TestIntegrationWithDeployAPI: |
| 179 | + """Integration tests verifying parsed dicts work with api_deploy functions.""" |
| 180 | + |
| 181 | + @patch("databusclient.api.deploy._load_file_stats") |
| 182 | + def test_get_file_info_from_dict_basic(self, mock_load_stats): |
| 183 | + """Test _get_file_info_from_dict with parsed distribution dict.""" |
| 184 | + mock_load_stats.return_value = ("abc123" * 10 + "abcd", 12345) |
| 185 | + |
| 186 | + parsed = parse_distribution_str( |
| 187 | + "http://example.com/data.json|lang=en|type=full|.json|.gz" |
| 188 | + ) |
| 189 | + cvs, ext, comp, sha, size = _get_file_info_from_dict(parsed) |
| 190 | + |
| 191 | + assert cvs == {"lang": "en", "type": "full"} |
| 192 | + assert ext == "json" |
| 193 | + assert comp == "gz" |
| 194 | + assert sha == "abc123" * 10 + "abcd" |
| 195 | + assert size == 12345 |
| 196 | + |
| 197 | + @patch("databusclient.api.deploy._load_file_stats") |
| 198 | + def test_get_file_info_from_dict_defaults(self, mock_load_stats): |
| 199 | + """Test default values when extension/compression not specified.""" |
| 200 | + mock_load_stats.return_value = ("sha256hash", 1000) |
| 201 | + |
| 202 | + parsed = parse_distribution_str("http://example.com/data|lang=en") |
| 203 | + cvs, ext, comp, sha, size = _get_file_info_from_dict(parsed) |
| 204 | + |
| 205 | + # Should use defaults |
| 206 | + assert ext == "file" # default when not specified |
| 207 | + assert comp == "none" # default when not specified |
| 208 | + |
| 209 | + @patch("databusclient.api.deploy._load_file_stats") |
| 210 | + def test_create_dataset_with_dict_distributions(self, mock_load_stats): |
| 211 | + """Test create_dataset accepts parsed dict distributions.""" |
| 212 | + fake_sha = "a" * 64 |
| 213 | + mock_load_stats.return_value = (fake_sha, 5000) |
| 214 | + |
| 215 | + parsed_dist = parse_distribution_str( |
| 216 | + "http://example.com/file.json|lang=en|.json" |
| 217 | + ) |
| 218 | + |
| 219 | + dataset = create_dataset( |
| 220 | + version_id="https://databus.example.org/user/group/artifact/2024.01.01/", |
| 221 | + title="Test Dataset", |
| 222 | + abstract="Test abstract", |
| 223 | + description="Test description", |
| 224 | + license_url="https://example.org/license", |
| 225 | + distributions=[parsed_dist], |
| 226 | + ) |
| 227 | + |
| 228 | + # Verify dataset structure |
| 229 | + assert "@context" in dataset |
| 230 | + assert "@graph" in dataset |
| 231 | + |
| 232 | + # Find distribution in graph |
| 233 | + graphs = dataset["@graph"] |
| 234 | + version_graph = next( |
| 235 | + (g for g in graphs if "@type" in g and "Version" in g.get("@type", [])), |
| 236 | + None, |
| 237 | + ) |
| 238 | + assert version_graph is not None |
| 239 | + assert "distribution" in version_graph |
| 240 | + |
| 241 | + dist = version_graph["distribution"][0] |
| 242 | + assert dist["downloadURL"] == "http://example.com/file.json" |
| 243 | + assert dist["formatExtension"] == "json" |
| 244 | + assert dist["dcv:lang"] == "en" |
| 245 | + |
| 246 | + @patch("databusclient.api.deploy._load_file_stats") |
| 247 | + def test_create_dataset_multiple_distributions(self, mock_load_stats): |
| 248 | + """Test create_dataset with multiple distributions requires variants.""" |
| 249 | + fake_sha = "b" * 64 |
| 250 | + mock_load_stats.return_value = (fake_sha, 3000) |
| 251 | + |
| 252 | + dist1 = parse_distribution_str("http://example.com/en.json|lang=en|.json") |
| 253 | + dist2 = parse_distribution_str("http://example.com/de.json|lang=de|.json") |
| 254 | + |
| 255 | + dataset = create_dataset( |
| 256 | + version_id="https://databus.example.org/user/group/artifact/2024.01.01/", |
| 257 | + title="Test Dataset", |
| 258 | + abstract="Test abstract", |
| 259 | + description="Test description", |
| 260 | + license_url="https://example.org/license", |
| 261 | + distributions=[dist1, dist2], |
| 262 | + ) |
| 263 | + |
| 264 | + # Both distributions should be present |
| 265 | + graphs = dataset["@graph"] |
| 266 | + version_graph = next( |
| 267 | + (g for g in graphs if "@type" in g and "Version" in g.get("@type", [])), |
| 268 | + None, |
| 269 | + ) |
| 270 | + distributions = version_graph["distribution"] |
| 271 | + assert len(distributions) == 2 |
| 272 | + |
| 273 | + # Verify different language variants |
| 274 | + langs = {d["dcv:lang"] for d in distributions} |
| 275 | + assert langs == {"en", "de"} |
0 commit comments