diff options
| author | Terry Truong <terry06890@gmail.com> | 2022-09-11 14:55:42 +1000 |
|---|---|---|
| committer | Terry Truong <terry06890@gmail.com> | 2022-09-11 15:04:14 +1000 |
| commit | 5de5fb93e50fe9006221b30ac4a66f1be0db82e7 (patch) | |
| tree | 2567c25c902dbb40d44419805cebb38171df47fa /backend/tests/enwiki/test_gen_desc_data.py | |
| parent | daccbbd9c73a5292ea9d6746560d7009e5aa666d (diff) | |
Add backend unit tests
- Add unit testing code in backend/tests/
- Change to snake-case for script/file/directory names
- Use os.path.join() instead of '/'
- Refactor script code into function defs and a main-guard
- Make global vars all-caps
Some fixes:
- For getting descriptions, some wiki redirects weren't properly resolved
- Linked images were sub-optimally propagated
- Generation of reduced trees assumed a wiki-id association implied a description
- Tilo.py had potential null dereferences by not always using a reduced node set
- EOL image downloading didn't properly wait for all threads to end when finishing
Diffstat (limited to 'backend/tests/enwiki/test_gen_desc_data.py')
| -rw-r--r-- | backend/tests/enwiki/test_gen_desc_data.py | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/backend/tests/enwiki/test_gen_desc_data.py b/backend/tests/enwiki/test_gen_desc_data.py new file mode 100644 index 0000000..801aa69 --- /dev/null +++ b/backend/tests/enwiki/test_gen_desc_data.py @@ -0,0 +1,37 @@ +import unittest +import os, tempfile + +from tests.common import readTestDbTable +from tol_data.enwiki.gen_desc_data import genData + +TEST_DUMP_FILE = os.path.join(os.path.dirname(__file__), 'sample_enwiki_pages_articles.xml.bz2') + +class TestGenData(unittest.TestCase): + def test_gen(self): + with tempfile.TemporaryDirectory() as tempDir: + # Run + dbFile = os.path.join(tempDir, 'descData.db') + genData(TEST_DUMP_FILE, dbFile) + # Check + self.assertEqual( + readTestDbTable(dbFile, 'SELECT id, title FROM pages'), + { + (10, 'AccessibleComputing'), + (13, 'AfghanistanHistory'), + (25, 'Autism'), + } + ) + self.assertEqual( + readTestDbTable(dbFile, 'SELECT id, target FROM redirects'), + { + (10, 'Computer accessibility'), + (13, 'History of Afghanistan'), + } + ) + descsRows = readTestDbTable(dbFile, 'SELECT id, desc FROM descs') + expectedDescPrefixes = { + 25: 'Kanner autism, or classic autism, is a neurodevelopmental disorder', + } + self.assertEqual({row[0] for row in descsRows}, set(expectedDescPrefixes.keys())) + for id, desc in descsRows: + self.assertTrue(id in expectedDescPrefixes and desc.startswith(expectedDescPrefixes[id])) |
