MVP сайта

tests/test_importing.py

@@ -0,0 +1,35 @@
+import pytest
+from parser_lab.importing import read_upload, ImportOptions, ImportErrorDetail
+from parser_lab.paths import resolve_pointer,field_summary
+
+def test_csv_preserves_strings_and_quotes():
+    r = read_upload('id;answer\n001;"a\nb"\n002;\n'.encode(), 'a.csv', ImportOptions(delimiter=';'))
+    assert r.records == [{'id': '001', 'answer': 'a\nb'}, {'id': '002', 'answer': ''}]
+
+def test_json_preserves_types_and_nested_selection():
+    r = read_upload(b'{"items":[{"x":null},{"x":false},{"x":0},{"x":""},{}]}', 'a.json', ImportOptions(record_pointer='/items'))
+    assert r.records == [{'x': None}, {'x': False}, {'x': 0}, {'x': ''}, {}]
+    assert resolve_pointer({'a/b': {'~c': 0}}, '/a~1b/~0c') == (True, 0)
+    assert resolve_pointer({}, '/x') == (False, None)
+
+@pytest.mark.parametrize('data,name', [(b'a,a\n1,2','a.csv'), (b'a,b\n1,2,3','a.csv'), (b'{"x":1,"x":2}','a.json'), (b'{"x":NaN}','a.json'), (b'[1,2]','a.json'), (b'[]','a.json')])
+def test_invalid_inputs_rejected(data, name):
+    with pytest.raises(ImportErrorDetail): read_upload(data, name, ImportOptions())
+
+def test_jsonl_reports_line_and_blanks():
+    assert read_upload(b'{"a":1}\n\n{"b":2}', 'a.jsonl', ImportOptions()).warnings
+    with pytest.raises(ImportErrorDetail, match='3'):
+        read_upload(b'{"a":1}\n\nBAD', 'a.jsonl', ImportOptions())
+
+def test_encoding_limits_and_fields():
+    assert read_upload('имя;возраст\nОля;20'.encode('cp1251'), 'a.csv', ImportOptions(encoding='cp1251', delimiter=';')).records[0]['имя'] == 'Оля'
+    assert '/later' in read_upload(b'[{}, {"later":1}]','a.json',ImportOptions()).fields
+    with pytest.raises(ImportErrorDetail): read_upload(b'12345','a.json',ImportOptions(), max_bytes=4)
+    with pytest.raises(ImportErrorDetail): read_upload(b'[{},{}]','a.json',ImportOptions(), max_records=1)
+    with pytest.raises(ImportErrorDetail): read_upload(('[' + '{"x":'*21 + '0' + '}'*21 + ']').encode(),'a.json',ImportOptions())
+
+def test_field_tree_and_missing_counts():
+    summary=field_summary([{'profile':{'age':20},'a/b':0},{'profile':{}},{}])
+    assert summary['/profile/age']['missing']==2
+    assert summary['/profile/age']['parent']=='/profile'
+    assert summary['/a~1b']['label']=='a/b'