Report the clustering result in a sentence

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-08-17 22:38:32 +08:00
co-authored by Claude Opus 5
parent e4f40e7c0f
commit dcf9e280d0
2 changed files with 5 additions and 6 deletions
@@ -625,8 +625,7 @@ def main(argv: list[str] | None = None) -> int:
write_meta(args.output_dir / META_JSON, meta)
elapsed: str = format_duration(time.monotonic() - started)
print(
f"done: {len(keywords)} keywords pooled from"
f" {len(run1[1])}+{len(run2[1])} records, clustered into"
f" {len(groups)} groups. {elapsed} elapsed.",
f"Done. Clustered {len(keywords)} keywords into"
f" {len(groups)}. {elapsed} elapsed.",
file=sys.stderr)
return 0
+3 -3
View File
@@ -245,7 +245,7 @@ class TestClusterKeywords(unittest.TestCase):
self.__read_source_keywords(),
["a-left", "b-middle", "shared"])
self.assertIn(
"done: 3 keywords pooled from 1+1 records", stderr)
"Done. Clustered 3 keywords into 2.", stderr)
def test_skips_error_records(self) -> None:
"""Test that records carrying an "error" field are
@@ -265,7 +265,7 @@ class TestClusterKeywords(unittest.TestCase):
self.assertEqual(
self.__read_source_keywords(), ["a-left", "b-middle"])
self.assertIn(
"done: 2 keywords pooled from 1+1 records", stderr)
"Done. Clustered 2 keywords into 2.", stderr)
def test_skips_non_json_text_records(self) -> None:
"""Test that a refusal, whose "text" does not parse as
@@ -285,7 +285,7 @@ class TestClusterKeywords(unittest.TestCase):
self.assertEqual(
self.__read_source_keywords(), ["a-left", "b-middle"])
self.assertIn(
"done: 2 keywords pooled from 1+1 records", stderr)
"Done. Clustered 2 keywords into 2.", stderr)
def test_duplicate_key_in_text_rejected(self) -> None:
"""Test that a "text" JSON object with a duplicate key