Files
akyldash/backend/test_search_topic_taxonomy.py

103 lines
4.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import json
import sqlite3
import tempfile
import unittest
from contextlib import closing
from pathlib import Path
from tools.build_search_topic_taxonomy import build, group_for
class SearchTopicTaxonomyTest(unittest.TestCase):
def test_ambiguous_roots_are_left_for_manual_review(self):
self.assertEqual(group_for("Иностранные инвестиции"), "review_required")
def test_preserves_source_tree_counts_and_marks_unclassified_roots(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / "documents/1").mkdir(parents=True)
(root / "documents/2").mkdir(parents=True)
with closing(sqlite3.connect(root / "manifest.sqlite3")) as db:
db.execute("CREATE TABLE documents (code TEXT, state TEXT)")
db.executemany("INSERT INTO documents VALUES (?, 'success')", [("1",), ("2",)])
db.commit()
classifier = {
"Code": None,
"Name": {"Rus": "ЗАКОНОДАТЕЛЬСТВО О ТРУДЕ", "Kyr": None},
"GeneralClassifiers": [{
"Code": "child-1",
"Name": {"Rus": "Рабочее время", "Kyr": "Иш убактысы"},
"GeneralClassifiers": [],
}],
}
unknown = {
"Code": None,
"Name": {"Rus": "НЕИЗВЕСТНАЯ РУБРИКА", "Kyr": None},
"GeneralClassifiers": [],
}
(root / "documents/1/document.json").write_text(
json.dumps({"general_classifiers": [classifier]}, ensure_ascii=False),
encoding="utf-8",
)
(root / "documents/2/document.json").write_text(
json.dumps({"general_classifiers": [classifier, unknown]}, ensure_ascii=False),
encoding="utf-8",
)
catalog = build(root)
groups = {group["code"]: group for group in catalog["groups"]}
labor_root = groups["labor_social"]["children"][0]
self.assertEqual((catalog["source_document_count"], catalog["source_node_count"], catalog["source_root_count"]), (2, 3, 2))
self.assertEqual(labor_root["document_count"], 2)
self.assertEqual(labor_root["children"][0]["document_count"], 2)
self.assertEqual(groups["review_required"]["children"][0]["grouping_status"], "manual_review")
self.assertEqual(catalog["nodes_missing_kyrgyz_label"], 2)
def test_rebuild_fails_instead_of_omitting_successful_manifest_document(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / "documents/1").mkdir(parents=True)
with closing(sqlite3.connect(root / "manifest.sqlite3")) as db:
db.execute("CREATE TABLE documents (code TEXT, state TEXT)")
db.execute("INSERT INTO documents VALUES ('1', 'success')")
db.commit()
with self.assertRaisesRegex(RuntimeError, "normalized document 1"):
build(root)
def test_rebuild_rejects_normalized_document_without_classifier_list(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
document = root / "documents/1"
document.mkdir(parents=True)
with closing(sqlite3.connect(root / "manifest.sqlite3")) as db:
db.execute("CREATE TABLE documents (code TEXT, state TEXT)")
db.execute("INSERT INTO documents VALUES ('1', 'success')")
db.commit()
(document / "document.json").write_text("{}", encoding="utf-8")
with self.assertRaisesRegex(RuntimeError, "general_classifiers list"):
build(root)
def test_rebuild_rejects_invalid_nested_classifier_branch(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
document = root / "documents/1"
document.mkdir(parents=True)
with closing(sqlite3.connect(root / "manifest.sqlite3")) as db:
db.execute("CREATE TABLE documents (code TEXT, state TEXT)")
db.execute("INSERT INTO documents VALUES ('1', 'success')")
db.commit()
(document / "document.json").write_text(
json.dumps({"general_classifiers": [{"Name": {"Rus": "Корень"}, "GeneralClassifiers": "bad"}]}),
encoding="utf-8",
)
with self.assertRaisesRegex(RuntimeError, "non-list GeneralClassifiers branch"):
build(root)
if __name__ == "__main__":
unittest.main()