Marcos
1534a99630
Items were keyed `{repo}#{pr}`, e.g. `netcracker/interview#29`. Both
characters break the UI's item route: the `/` in `owner/repo` splits into
extra path segments, and everything after the `#` is a fragment the browser
never sends. Items were created successfully and then 404'd when opened.
Ids are now `{owner}__{repo}__pr{n}`, which needs no percent-encoding. The
real repo and pr stay intact in `input`, so nothing downstream reads the id
back apart. Session ids elsewhere keep the `{repo}#{pr}` form — those are
never path segments and feedback_scores depends on that shape.
The 28 existing items were unusable and are regenerable from feedback.db;
they were deleted and recreated under the new ids.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
96 lines
3.1 KiB
Python
96 lines
3.1 KiB
Python
"""Tests for the eval bootstrap's dataset-item construction."""
|
|
import os
|
|
import sqlite3
|
|
import sys
|
|
import urllib.parse
|
|
|
|
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "pilot"))
|
|
|
|
import eval_bootstrap as eb # noqa: E402
|
|
|
|
|
|
# --- item_id --------------------------------------------------------------
|
|
|
|
def test_item_id_has_no_path_separator():
|
|
"""A `/` would split the UI's item route into extra path segments."""
|
|
assert "/" not in eb.item_id("netcracker/interview", 29)
|
|
|
|
|
|
def test_item_id_has_no_fragment_marker():
|
|
"""Everything after a `#` is a fragment the browser never sends."""
|
|
assert "#" not in eb.item_id("netcracker/interview", 29)
|
|
|
|
|
|
def test_item_id_survives_a_url_round_trip():
|
|
"""The id must appear verbatim in a path, needing no percent-encoding."""
|
|
ident = eb.item_id("netcracker/interview", 29)
|
|
assert urllib.parse.quote(ident, safe="") == ident
|
|
|
|
|
|
def test_item_id_keeps_repo_and_pr_readable():
|
|
assert eb.item_id("netcracker/interview", 29) == "netcracker__interview__pr29"
|
|
|
|
|
|
def test_item_id_is_unique_per_pr():
|
|
assert eb.item_id("o/r", 1) != eb.item_id("o/r", 2)
|
|
|
|
|
|
def test_item_id_is_unique_per_repo():
|
|
assert eb.item_id("o/one", 1) != eb.item_id("o/two", 1)
|
|
|
|
|
|
def test_item_id_accepts_a_string_pr():
|
|
assert eb.item_id("o/r", "29") == eb.item_id("o/r", 29)
|
|
|
|
|
|
# --- read_review_items ----------------------------------------------------
|
|
|
|
def _db(tmp_path, rows, findings=()):
|
|
path = str(tmp_path / "feedback.db")
|
|
conn = sqlite3.connect(path)
|
|
conn.execute(
|
|
"CREATE TABLE review (repo TEXT, pr INTEGER, posted_at INTEGER, head_sha TEXT)"
|
|
)
|
|
conn.execute(
|
|
"CREATE TABLE inline_finding (repo TEXT, pr INTEGER, path TEXT, line INTEGER,"
|
|
" severity TEXT, problem TEXT, fix TEXT)"
|
|
)
|
|
conn.executemany("INSERT INTO review VALUES (?,?,?,?)", rows)
|
|
conn.executemany("INSERT INTO inline_finding VALUES (?,?,?,?,?,?,?)", findings)
|
|
conn.commit()
|
|
conn.close()
|
|
return path
|
|
|
|
|
|
def test_items_use_url_safe_ids(tmp_path):
|
|
path = _db(tmp_path, [("netcracker/interview", 29, 100, "abc")])
|
|
items = eb.read_review_items(path)
|
|
assert [i["id"] for i in items] == ["netcracker__interview__pr29"]
|
|
|
|
|
|
def test_item_input_keeps_the_real_repo_name(tmp_path):
|
|
"""The id is mangled for the URL; the payload must stay faithful."""
|
|
path = _db(tmp_path, [("netcracker/interview", 29, 100, "abc")])
|
|
item = eb.read_review_items(path)[0]
|
|
assert item["input"]["repo"] == "netcracker/interview"
|
|
assert item["input"]["pr"] == 29
|
|
|
|
|
|
def test_one_item_per_pr_not_per_review(tmp_path):
|
|
path = _db(
|
|
tmp_path,
|
|
[
|
|
("o/r", 1, 100, "a"),
|
|
("o/r", 1, 200, "b"),
|
|
("o/r", 2, 300, "c"),
|
|
],
|
|
)
|
|
items = eb.read_review_items(path)
|
|
assert [i["id"] for i in items] == ["o__r__pr1", "o__r__pr2"]
|
|
assert items[0]["metadata"]["reviews_run"] == 2
|
|
|
|
|
|
def test_items_are_not_flagged_as_human_labelled(tmp_path):
|
|
path = _db(tmp_path, [("o/r", 1, 100, "a")])
|
|
assert eb.read_review_items(path)[0]["metadata"]["labelled_by_human"] is False
|