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_dump_index_db.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_dump_index_db.py')
| -rw-r--r-- | backend/tests/enwiki/test_gen_dump_index_db.py | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/backend/tests/enwiki/test_gen_dump_index_db.py b/backend/tests/enwiki/test_gen_dump_index_db.py new file mode 100644 index 0000000..e0715f3 --- /dev/null +++ b/backend/tests/enwiki/test_gen_dump_index_db.py @@ -0,0 +1,39 @@ +import unittest +import tempfile, os + +from tests.common import createTestBz2, readTestDbTable +from tol_data.enwiki.gen_dump_index_db import genData + +def runGenData(indexFileContents: str): + """ Sets up index file to be read by genData(), runs it, reads the output database, and returns offset info. """ + with tempfile.TemporaryDirectory() as tempDir: + # Create temp index file + indexFile = os.path.join(tempDir, 'index.txt.bz2') + createTestBz2(indexFile, indexFileContents) + # Run + dbFile = os.path.join(tempDir, 'data.db') + genData(indexFile, dbFile) + # Read db + return readTestDbTable(dbFile, 'SELECT title, id, offset, next_offset FROM offsets') + +class TestGenData(unittest.TestCase): + def setUp(self): + self.maxDiff = None # Remove output-diff size limit + def test_index_file(self): + indexFileContents = ( + '100:10:apple\n' + '100:11:ant\n' + '300:99:banana ice-cream\n' + '1000:2030:Custard!\n' + ) + offsetsMap = runGenData(indexFileContents) + self.assertEqual(offsetsMap, { + ('apple', 10, 100, 300), + ('ant', 11, 100, 300), + ('banana ice-cream', 99, 300, 1000), + ('Custard!', 2030, 1000, -1), + }) + def test_emp_index(self): + offsetsMap = runGenData('') + self.assertEqual(offsetsMap, set()) + pass |
