Skip to content

fix: support schema-valid line ranges in evaluator - #89

Open
quan020406 wants to merge 1 commit into
Tencent:mainfrom
quan020406:fix-evaluator-line-ranges
Open

fix: support schema-valid line ranges in evaluator#89
quan020406 wants to merge 1 commit into
Tencent:mainfrom
quan020406:fix-evaluator-line-ranges

Conversation

@quan020406

Copy link
Copy Markdown

Summary

  • Support integer and start-end line values in the evaluator.
  • Match findings against normalized closed line intervals.
  • Preserve existing integer matching and tolerance behavior.
  • Add regression tests for range matching and tolerance boundaries.
  • Update English and Chinese evaluation documentation.

Root cause

examples/evaluate.py converted all line values with int(...). Schema-valid values such as "112-119" were therefore treated as unmatched.

Validation

  • 6 tests passed.
  • Dataset loading: 184 reports / 408 entries.
  • Example evaluation: 3/184 advisory recall and 3/408 entry recall.
  • git diff --check passed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant