diff options
Diffstat (limited to 'python/tests/import_matched.py')
-rw-r--r-- | python/tests/import_matched.py | 28 |
1 files changed, 21 insertions, 7 deletions
diff --git a/python/tests/import_matched.py b/python/tests/import_matched.py index 080674ac..8f694456 100644 --- a/python/tests/import_matched.py +++ b/python/tests/import_matched.py @@ -1,7 +1,7 @@ import json import pytest -from fatcat_tools.importers import MatchedImporter +from fatcat_tools.importers import MatchedImporter, JsonLinePusher from fixtures import api @@ -10,26 +10,40 @@ def matched_importer(api): yield MatchedImporter(api) # TODO: use API to check that entities actually created... -def test_matched_importer_batch(matched_importer): +def test_matched_importer(matched_importer): with open('tests/files/example_matched.json', 'r') as f: - matched_importer.process_batch(f) + JsonLinePusher(matched_importer, f).run() def test_matched_importer(matched_importer): + last_index = matched_importer.api.get_changelog(limit=1)[0].index with open('tests/files/example_matched.json', 'r') as f: - matched_importer.process_source(f) + matched_importer.bezerk_mode = True + counts = JsonLinePusher(matched_importer, f).run() + assert counts['insert'] == 2 + assert counts['exists'] == 0 + assert counts['skip'] == 11 # fetch most recent editgroup - changes = matched_importer.api.get_changelog(limit=1) - eg = changes[0].editgroup + change = matched_importer.api.get_changelog_entry(index=last_index+1) + eg = change.editgroup assert eg.description assert "file-to-release" in eg.description.lower() assert eg.extra['git_rev'] assert "fatcat_tools.MatchedImporter" in eg.extra['agent'] + # re-insert; should skip + with open('tests/files/example_matched.json', 'r') as f: + matched_importer.reset() + matched_importer.bezerk_mode = False + counts = JsonLinePusher(matched_importer, f).run() + assert counts['insert'] == 0 + assert counts['exists'] == 2 + assert counts['skip'] == 11 + def test_matched_dict_parse(matched_importer): with open('tests/files/example_matched.json', 'r') as f: raw = json.loads(f.readline()) - f = matched_importer.parse_matched_dict(raw) + f = matched_importer.parse_record(raw) assert f.sha1 == "00242a192acc258bdfdb151943419437f440c313" assert f.md5 == "f4de91152c7ab9fdc2a128f962faebff" assert f.mimetype == "application/pdf" |