"""The WJ reference loader's resolve, crosswalk binding and source aliasing. The loader had no tests at all, and three of its defects were the silent kind: they did not raise, they imported fewer rows and finished cheerfully. These cover the logic that can be exercised without a MySQL source, which is exactly the part that was wrong. Not covered here: the stage functions themselves. They need the classic source schema, so they belong in a fixture-backed integration test against a scratch database, not in the unit suite. """ import json import os import pytest from scripts.site_imports.wjf import run as loader from scripts.site_imports.wjf.harness import IdMap, Source, StaleIdMapError class FakeHarness: """Records the paths requested and replays canned list responses.""" def __init__(self, pages): self.pages = pages self.requested = [] def get(self, path): self.requested.append(path) return 200, self.pages.get(path, {'items': []}) class TestResolveExisting: def test_finds_a_row_beyond_the_first_page(self): """The bug: per_page is clamped to 100, so row 101 was invisible. The old code asked for per_page=10000, read one response, and returned None for anything the server did not fit in its first 100 rows. The target already holds more than 100 models and more than 100 applications, so this fired on every resume. """ page1 = {'items': [{'modelnumber': 'M%03d' % i, 'modelnumberid': i} for i in range(100)]} page2 = {'items': [{'modelnumber': 'LATE', 'modelnumberid': 999}]} harness = FakeHarness({ '/api/models?modelnumber=LATE&per_page=100': {'items': []}, '/api/models?per_page=100&page=1': page1, '/api/models?per_page=100&page=2': page2, }) found = loader._resolve_existing( harness, '/api/models', 'modelnumber', 'LATE', 'modelnumberid') assert found == 999 def test_tries_the_exact_filter_first(self): harness = FakeHarness({ '/api/models?modelnumber=WIDGET&per_page=100': {'items': [{'modelnumber': 'WIDGET', 'modelnumberid': 7}]}, }) assert loader._resolve_existing( harness, '/api/models', 'modelnumber', 'WIDGET', 'modelnumberid') == 7 # One request: it must not walk every page when the filter answered. assert len(harness.requested) == 1 def test_values_needing_encoding_do_not_break_the_filter(self): harness = FakeHarness({}) loader._resolve_existing(harness, '/api/vendors', 'vendor', 'Acme & Co/Ltd', 'vendorid') assert 'Acme%20%26%20Co/Ltd' in harness.requested[0] or \ 'Acme%20%26%20Co%2FLtd' in harness.requested[0] def test_matching_ignores_case_and_padding(self): harness = FakeHarness({ '/api/vendors?vendor=acme&per_page=100': {'items': [{'vendor': ' ACME ', 'vendorid': 3}]}, }) assert loader._resolve_existing( harness, '/api/vendors', 'vendor', 'acme', 'vendorid') == 3 def test_missing_row_returns_none_without_spinning(self): harness = FakeHarness({}) assert loader._resolve_existing( harness, '/api/models', 'modelnumber', 'NOPE', 'modelnumberid') is None # Empty first page ends it: the filter attempt plus one page. assert len(harness.requested) == 2 def test_a_short_page_ends_the_walk(self): harness = FakeHarness({ '/api/models?per_page=100&page=1': {'items': [{'modelnumber': 'A', 'modelnumberid': 1}]}, }) assert loader._resolve_existing( harness, '/api/models', 'modelnumber', 'ZZZ', 'modelnumberid') is None assert len(harness.requested) == 2 def test_a_bare_list_response_is_accepted(self): harness = FakeHarness({ '/api/x?name=a&per_page=100': [{'name': 'a', 'id': 5}], }) assert loader._resolve_existing(harness, '/api/x', 'name', 'a', 'id') == 5 def test_an_existing_query_string_keeps_its_separator(self): harness = FakeHarness({}) loader._resolve_existing(harness, '/api/models?category=pc', 'modelnumber', 'M1', 'modelnumberid') assert harness.requested[0].startswith('/api/models?category=pc&modelnumber=') class TestIdMapBinding: def test_a_crosswalk_from_another_database_is_refused(self, tmp_path): """The silent corruption this guard exists for. Keeping idmap.json across a drop-and-rebuild leaves legacy ids pointing at assetids from the OLD database, so warranties and printer assignments attach to whatever asset holds that id now. No error, wrong data. """ path = tmp_path / 'idmap.json' path.write_text(json.dumps({'_target': 'aaaa', 'asset': {'1': 10}})) with pytest.raises(StaleIdMapError) as caught: IdMap(str(path), target='bbbb') assert 'different database' in str(caught.value) def test_the_matching_target_loads(self, tmp_path): path = tmp_path / 'idmap.json' path.write_text(json.dumps({'_target': 'aaaa', 'asset': {'1': 10}})) ids = IdMap(str(path), target='aaaa') assert ids.get('asset', 1) == 10 def test_an_unstamped_crosswalk_is_adopted_not_refused(self, tmp_path): # Written before the guard existed. Refusing would strand a crosswalk # that is probably fine; adopting binds it for every run after. path = tmp_path / 'idmap.json' path.write_text(json.dumps({'asset': {'1': 10}})) ids = IdMap(str(path), target='ccc') assert ids.get('asset', 1) == 10 assert json.loads(path.read_text())['_target'] == 'ccc' def test_the_bookkeeping_key_is_not_counted_as_a_namespace(self, tmp_path): path = tmp_path / 'idmap.json' ids = IdMap(str(path), target='ccc') ids.put('asset', 1, 10) assert ids.count('asset') == 1 assert ids.count('_target') == 0 def test_a_fresh_crosswalk_needs_no_stamp_to_start(self, tmp_path): ids = IdMap(str(tmp_path / 'new.json'), target='ddd') ids.put('asset', 5, 50) assert ids.get('asset', 5) == 50 class TestSourceAliasing: def test_logical_names_default_to_the_scratch_databases(self, monkeypatch): for var in ('SOURCE_DB_MAIN', 'SOURCE_DB_USB', 'SOURCE_DB_EMPLOYEES'): monkeypatch.delenv(var, raising=False) assert Source.resolve('shopdb_src') == 'shopdb_src' assert Source.resolve('cmmc_usb_src') == 'cmmc_usb_src' assert Source.resolve('wjf_employees_src') == 'wjf_employees_src' def test_the_environment_repoints_the_loader(self, monkeypatch): """What unblocks the prodscratch run without editing run.py.""" monkeypatch.setenv('SOURCE_DB_MAIN', 'prodscratch') assert Source.resolve('shopdb_src') == 'prodscratch' def test_an_unknown_name_passes_through(self, monkeypatch): assert Source.resolve('something_else') == 'something_else'