def get_landed_and_filed_since(self, days: int) -> List[int]:
since = datetime.utcnow() - timedelta(days=days)
commits = []
last_commit_by_bug: Dict[int, datetime] = {}
for commit in repository.get_commits():
if not commit["bug_id"]:
continue
push_date = dateutil.parser.parse(commit["pushdate"])
if push_date >= since and (
commit["bug_id"] not in last_commit_by_bug or push_date -
last_commit_by_bug[commit["bug_id"]] < timedelta(days=91)
or not all(repository.is_test(p)
for p in commit["files"])):
commits.append(commit)
last_commit_by_bug[commit["bug_id"]] = push_date
logger.info(f"Retrieving bug IDs since {days} days ago")
timespan_ids = bugzilla.get_ids_between(since,
resolution=["---", "FIXED"])
return list(
set(commit["bug_id"] for commit in commits) | set(timespan_ids))
def get_landed_and_filed_since(self, days: int) -> List[int]:
since = datetime.utcnow() - timedelta(days=days)
commits = [
commit for commit in repository.get_commits()
if dateutil.parser.parse(commit["pushdate"]) >= since
and commit["bug_id"]
]
logger.info(f"Retrieving bug IDs since {days} days ago")
timespan_ids = bugzilla.get_ids_between(since, datetime.utcnow())
bugzilla.download_bugs(timespan_ids)
bug_ids = set(commit["bug_id"] for commit in commits)
bug_ids.update(bug["id"] for bug in bugzilla.get_bugs()
if dateutil.parser.parse(bug["creation_time"]).replace(
tzinfo=None) >= since and bug["resolution"] not in [
"INVALID",
"WONTFIX",
"INACTIVE",
"DUPLICATE",
"INCOMPLETE",
"MOVED",
"WORKSFORME",
])
return list(bug_ids)
def main(args):
similarity_model = (
similarity.download_and_load_similarity_model(args.similaritymodel)
if args.similaritymodel
else None
)
duplicate_model = DuplicateModel.load("duplicatemodel")
try:
with open("duplicate_test_bugs.json", "r") as f:
test_bugs = json.load(f)
except FileNotFoundError:
test_bug_ids = bugzilla.get_ids_between(
datetime.now() - timedelta(days=21), datetime.now()
)
test_bugs = bugzilla.get(test_bug_ids)
test_bugs = [
bug
for bug in test_bugs.values()
if not bug["creator"] in REPORTERS_TO_IGNORE
]
with open("duplicate_test_bugs.json", "w") as f:
json.dump(test_bugs, f)
with open("duplicate_predictions.csv", "w") as csvfile:
spamwriter = csv.writer(csvfile)
spamwriter.writerow(
["bug 1 ID", "bug 1 summary", "bug 2 ID", "bug 2 summary", "prediction"]
)
if similarity_model:
bug_tuples = []
for test_bug in test_bugs:
similar_bug_ids = similarity_model.get_similar_bugs(test_bug)
similar_bugs = bugzilla.get(similar_bug_ids)
bug_tuples += [
(test_bug, similar_bug) for similar_bug in similar_bugs.values()
]
else:
bug_tuples = combinations(test_bugs, 2)
probs = duplicate_model.classify(bug_tuples, probabilities=True)
for bug_tuple, prob in zip(bug_tuples, probs):
if prob[1] > similarity_model.confidence_threshold:
spamwriter.writerow(
[
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug_tuple[0]["id"]}',
bug_tuple[0]["summary"],
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug_tuple[1]["id"]}',
bug_tuple[1]["summary"],
prob[1],
]
)
def generate_sheet(model_name, token, days, threshold):
model_file_name = f"{model_name}model"
assert os.path.exists(
model_file_name
), f"{model_file_name} does not exist. Train the model with trainer.py first."
model_class = get_model_class(model_name)
model = model_class.load(model_file_name)
today = datetime.utcnow()
start_date = today - timedelta(days)
bugzilla.set_token(token)
bug_ids = bugzilla.get_ids_between(start_date, today)
bugs = bugzilla.get(bug_ids)
print(f"Classifying {len(bugs)} bugs...")
rows = [["Bug", f"{model_name}(model)", model_name, "Title"]]
for bug in bugs.values():
p = model.classify(bug, probabilities=True)
probability = p[0]
if len(probability) > 2:
index = np.argmax(probability)
prediction = model.class_names[index]
else:
prediction = "y" if probability[1] >= threshold else "n"
rows.append(
[
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
prediction,
"",
bug["summary"],
]
)
os.makedirs("sheets", exist_ok=True)
with open(
os.path.join(
"sheets",
f'{model_name}-{datetime.utcnow().strftime("%Y-%m-%d")}-labels.csv',
),
"w",
) as f:
writer = csv.writer(f)
writer.writerows(rows)
def fetch_untriaged(args):
from bugbug import bugzilla
# Set bugzilla token and download bugs
bugzilla.set_token(args.token)
bug_ids = bugzilla.get_ids_between(date.today() -
timedelta(days=args.days_back))
bugs = bugzilla.get(bug_ids)
# Get untriaged bugs
untriaged_bugs = []
for bug in bugs.values():
for history in bug["history"]:
for change in history["changes"]:
if (change["field_name"] == "component"
and change["removed"] == "Untriaged"):
untriaged_bugs.append(bug)
with open("bugs-{}.json".format(datetime.now().strftime("%s")), "w") as f:
json.dump(untriaged_bugs, f)
return untriaged_bugs
def generate_sheet(model_name, token):
model_file_name = f"{model_name}model"
assert os.path.exists(
model_file_name
), f"{model_file_name} does not exist. Train the model with trainer.py first."
model_class = get_model_class(model_name)
model = model_class.load(model_file_name)
today = datetime.utcnow()
a_week_ago = today - timedelta(7)
bugzilla.set_token(token)
bug_ids = bugzilla.get_ids_between(a_week_ago, today)
bugs = bugzilla.get(bug_ids)
print(f"Classifying {len(bugs)} bugs...")
rows = [["Bug", f"{model_name}(model)", model_name, "Title"]]
for bug in bugs.values():
p = model.classify(bug, probabilities=True)
rows.append([
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
"y" if p[0][1] >= 0.7 else "n",
"",
bug["summary"],
])
os.makedirs("sheets", exist_ok=True)
with open(
os.path.join(
"sheets",
f'{model_name}-{datetime.utcnow().strftime("%Y-%m-%d")}-labels.csv',
),
"w",
) as f:
writer = csv.writer(f)
writer.writerows(rows)
from datetime import datetime, timedelta
from bugbug import bugzilla
from bugbug.models.duplicate import DuplicateModel
m = DuplicateModel.load("duplicatemodel")
REPORTERS_TO_IGNORE = {"*****@*****.**", "*****@*****.**"}
try:
with open("duplicate_test_bugs.json", "r") as f:
test_bugs = json.load(f)
except FileNotFoundError:
test_bug_ids = bugzilla.get_ids_between(
datetime.now() - timedelta(days=21), datetime.now()
)
test_bugs = bugzilla.get(test_bug_ids)
test_bugs = [
bug for bug in test_bugs.values() if not bug["creator"] in REPORTERS_TO_IGNORE
]
with open("duplicate_test_bugs.json", "w") as f:
json.dump(test_bugs, f)
bug_tuples = list(itertools.combinations(test_bugs, 2))
# Warning: Classifying all the test bugs takes a while
probs = m.classify(bug_tuples, probabilities=True)
with open("duplicate_predictions.csv", "w") as csvfile:
spamwriter = csv.writer(csvfile)
def retrieve_bugs(self, limit=None):
bugzilla.set_token(get_secret("BUGZILLA_TOKEN"))
db.download(bugzilla.BUGS_DB)
# Get IDs of bugs changed since last run.
last_modified = db.last_modified(bugzilla.BUGS_DB)
logger.info(
f"Retrieving IDs of bugs modified since the last run on {last_modified}"
)
changed_ids = bugzilla.get_ids(
{"f1": "delta_ts", "o1": "greaterthaneq", "v1": last_modified.date()}
)
logger.info(f"Retrieved {len(changed_ids)} IDs.")
# Get IDs of bugs between (two years and six months ago) and (six months ago).
six_months_ago = datetime.utcnow() - relativedelta(months=6)
two_years_and_six_months_ago = six_months_ago - relativedelta(years=2)
logger.info(
f"Retrieving bug IDs from {two_years_and_six_months_ago} to {six_months_ago}"
)
timespan_ids = bugzilla.get_ids_between(
two_years_and_six_months_ago, six_months_ago
)
if limit:
timespan_ids = timespan_ids[:limit]
logger.info(f"Retrieved {len(timespan_ids)} IDs.")
# Get IDs of labelled bugs.
labelled_bug_ids = labels.get_all_bug_ids()
if limit:
labelled_bug_ids = labelled_bug_ids[:limit]
logger.info(f"{len(labelled_bug_ids)} labelled bugs to download.")
# Get the commits DB, as we need it to get the bug IDs linked to recent commits.
# XXX: Temporarily avoid downloading the commits DB when a limit is set, to avoid the integration test fail when the commits DB is bumped.
if limit is None:
assert db.download(repository.COMMITS_DB)
# Get IDs of bugs linked to commits (used for some commit-based models, e.g. backout and regressor).
start_date = datetime.now() - relativedelta(years=3)
commit_bug_ids = [
commit["bug_id"]
for commit in repository.get_commits()
if commit["bug_id"]
and dateutil.parser.parse(commit["pushdate"]) >= start_date
]
if limit:
commit_bug_ids = commit_bug_ids[-limit:]
logger.info(f"{len(commit_bug_ids)} bugs linked to commits to download.")
# Get IDs of bugs which are regressions and bugs which caused regressions (useful for the regressor model).
regressed_by_bug_ids = sum(
(bug["regressed_by"] + bug["regressions"] for bug in bugzilla.get_bugs()),
[],
)
if limit:
regressed_by_bug_ids = regressed_by_bug_ids[-limit:]
logger.info(
f"{len(regressed_by_bug_ids)} bugs which caused regressions fixed by commits."
)
all_ids = (
timespan_ids + labelled_bug_ids + commit_bug_ids + regressed_by_bug_ids
)
all_ids_set = set(all_ids)
# We have to redownload bugs that were changed since the last download.
# We can remove from the DB the bugs that are outside of the considered timespan and are not labelled.
bugzilla.delete_bugs(
lambda bug: bug["id"] in changed_ids or bug["id"] not in all_ids_set
)
bugzilla.download_bugs(all_ids)
# Get regressed_by_bug_ids again (the set could have changed after downloading new bugs).
regressed_by_bug_ids = sum(
(bug["regressed_by"] + bug["regressions"] for bug in bugzilla.get_bugs()),
[],
)
logger.info(
f"{len(regressed_by_bug_ids)} bugs which caused regressions fixed by commits."
)
bugzilla.download_bugs(regressed_by_bug_ids)
# Try to re-download inconsistent bugs, up to three times.
inconsistent_bugs = bugzilla.get_bugs(include_invalid=True)
for i in range(3):
# We look for inconsistencies in all bugs first, then, on following passes,
# we only look for inconsistencies in bugs that were found to be inconsistent in the first pass
inconsistent_bugs = bug_snapshot.get_inconsistencies(inconsistent_bugs)
inconsistent_bug_ids = set(bug["id"] for bug in inconsistent_bugs)
if len(inconsistent_bug_ids) == 0:
break
logger.info(
f"Re-downloading {len(inconsistent_bug_ids)} bugs, as they were inconsistent"
)
bugzilla.delete_bugs(lambda bug: bug["id"] in inconsistent_bug_ids)
bugzilla.download_bugs(inconsistent_bug_ids)
zstd_compress("data/bugs.json")
def main(args):
model_file_name = "{}{}model".format(
args.goal, "" if args.classifier == "default" else args.classifier
)
if args.goal == "component":
if args.classifier == "default":
model_class_name = "component"
else:
model_class_name = "component_nn"
else:
model_class_name = args.goal
model_class = get_model_class(model_class_name)
if args.train:
db.download(bugzilla.BUGS_DB)
db.download(repository.COMMITS_DB)
historical_supported_tasks = [
"defect",
"bugtype",
"defectenhancementtask",
"regression",
]
if args.goal in historical_supported_tasks:
model = model_class(args.lemmatization, args.historical)
elif args.goal == "duplicate":
model = model_class(args.training_set_size, args.lemmatization)
else:
model = model_class(args.lemmatization)
model.train()
else:
model = model_class.load(model_file_name)
if args.classify:
for bug in bugzilla.get_bugs():
print(
f'https://bugzilla.mozilla.org/show_bug.cgi?id={ bug["id"] } - { bug["summary"]} '
)
if model.calculate_importance:
probas, importance = model.classify(
bug, probabilities=True, importances=True
)
feature_names = model.get_human_readable_feature_names()
for i, (importance, index, is_positive) in enumerate(
importance["importances"]
):
print(
f'{i + 1}. \'{feature_names[int(index)]}\' ({"+" if (is_positive) else "-"}{importance})'
)
else:
probas = model.classify(bug, probabilities=True, importances=False)
if np.argmax(probas) == 1:
print(f"Positive! {probas}")
else:
print(f"Negative! {probas}")
input()
if args.generate_sheet:
assert (
args.token is not None
), "A Bugzilla token should be set in order to download bugs"
today = datetime.utcnow()
a_week_ago = today - timedelta(7)
bugzilla.set_token(args.token)
bug_ids = bugzilla.get_ids_between(a_week_ago, today)
bugs = bugzilla.get(bug_ids)
print(f"Classifying {len(bugs)} bugs...")
rows = [["Bug", f"{args.goal}(model)", args.goal, "Title"]]
for bug in bugs.values():
p = model.classify(bug, probabilities=True)
rows.append(
[
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
"y" if p[0][1] >= 0.7 else "n",
"",
bug["summary"],
]
)
os.makedirs("sheets", exist_ok=True)
with open(
os.path.join(
"sheets",
f'{args.goal}-{datetime.utcnow().strftime("%Y-%m-%d")}-labels.csv',
),
"w",
) as f:
writer = csv.writer(f)
writer.writerows(rows)
def retrieve_bugs(self):
bugzilla.set_token(get_secret("BUGZILLA_TOKEN"))
db.download_version(bugzilla.BUGS_DB)
if not db.is_old_version(bugzilla.BUGS_DB):
db.download(bugzilla.BUGS_DB)
# Get IDs of bugs changed since last run.
last_modified = db.last_modified(bugzilla.BUGS_DB)
logger.info(
f"Retrieving IDs of bugs modified since the last run on {last_modified}"
)
changed_ids = bugzilla.get_ids({
"f1": "delta_ts",
"o1": "greaterthaneq",
"v1": last_modified.date()
})
logger.info(f"Retrieved {len(changed_ids)} IDs.")
# Get IDs of bugs between (two years and six months ago) and (six months ago).
six_months_ago = datetime.utcnow() - relativedelta(months=6)
two_years_and_six_months_ago = six_months_ago - relativedelta(years=2)
logger.info(
f"Retrieving bug IDs from {two_years_and_six_months_ago} to {six_months_ago}"
)
timespan_ids = bugzilla.get_ids_between(two_years_and_six_months_ago,
six_months_ago)
logger.info(f"Retrieved {len(timespan_ids)} IDs.")
# Get IDs of labelled bugs.
labelled_bug_ids = labels.get_all_bug_ids()
logger.info(f"{len(labelled_bug_ids)} labelled bugs to download.")
all_ids = set(timespan_ids + labelled_bug_ids)
# We have to redownload bugs that were changed since the last download.
# We can remove from the DB the bugs that are outside of the considered timespan and are not labelled.
bugzilla.delete_bugs(
lambda bug: bug["id"] in changed_ids or bug["id"] not in all_ids)
bugzilla.download_bugs(timespan_ids + labelled_bug_ids)
# Try to re-download inconsistent bugs, up to three times.
inconsistent_bugs = bugzilla.get_bugs()
for i in range(3):
# We look for inconsistencies in all bugs first, then, on following passes,
# we only look for inconsistencies in bugs that were found to be inconsistent in the first pass
inconsistent_bugs = bug_snapshot.get_inconsistencies(
inconsistent_bugs)
inconsistent_bug_ids = set(bug["id"] for bug in inconsistent_bugs)
if len(inconsistent_bug_ids) == 0:
break
logger.info(
f"Re-downloading {len(inconsistent_bug_ids)} bugs, as they were inconsistent"
)
bugzilla.delete_bugs(lambda bug: bug["id"] in inconsistent_bug_ids)
bugzilla.download_bugs(inconsistent_bug_ids)
self.compress_file("data/bugs.json")
def retrieve_bugs(self, limit: int = None) -> None:
bugzilla.set_token(get_secret("BUGZILLA_TOKEN"))
db.download(bugzilla.BUGS_DB)
# Get IDs of bugs changed since last run.
last_modified = db.last_modified(bugzilla.BUGS_DB)
logger.info(
f"Retrieving IDs of bugs modified since the last run on {last_modified}"
)
changed_ids = set(
bugzilla.get_ids({
"f1": "delta_ts",
"o1": "greaterthaneq",
"v1": last_modified.date()
}))
logger.info(f"Retrieved {len(changed_ids)} IDs.")
all_components = bugzilla.get_product_component_count(9999)
deleted_component_ids = set(
bug["id"] for bug in bugzilla.get_bugs() if "{}::{}".format(
bug["product"], bug["component"]) not in all_components)
logger.info(
f"{len(deleted_component_ids)} bugs belonging to deleted components"
)
changed_ids |= deleted_component_ids
# Get IDs of bugs between (two years and six months ago) and now.
two_years_and_six_months_ago = datetime.utcnow() - relativedelta(
years=2, months=6)
logger.info(f"Retrieving bug IDs since {two_years_and_six_months_ago}")
timespan_ids = bugzilla.get_ids_between(two_years_and_six_months_ago)
if limit:
timespan_ids = timespan_ids[-limit:]
logger.info(f"Retrieved {len(timespan_ids)} IDs.")
# Get IDs of labelled bugs.
labelled_bug_ids = labels.get_all_bug_ids()
if limit:
labelled_bug_ids = labelled_bug_ids[-limit:]
logger.info(f"{len(labelled_bug_ids)} labelled bugs to download.")
# Get the commits DB, as we need it to get the bug IDs linked to recent commits.
# XXX: Temporarily avoid downloading the commits DB when a limit is set, to avoid the integration test fail when the commits DB is bumped.
if limit is None:
assert db.download(repository.COMMITS_DB)
# Get IDs of bugs linked to commits (used for some commit-based models, e.g. backout and regressor).
start_date = datetime.now() - relativedelta(years=3)
commit_bug_ids = list(
set(commit["bug_id"] for commit in repository.get_commits()
if commit["bug_id"]
and dateutil.parser.parse(commit["pushdate"]) >= start_date))
if limit:
commit_bug_ids = commit_bug_ids[-limit:]
logger.info(
f"{len(commit_bug_ids)} bugs linked to commits to download.")
# Get IDs of bugs which are regressions, bugs which caused regressions (useful for the regressor model),
# and blocked bugs.
regression_related_ids: List[int] = list(
set(
sum(
(bug["regressed_by"] + bug["regressions"] + bug["blocks"]
for bug in bugzilla.get_bugs()),
[],
)))
if limit:
regression_related_ids = regression_related_ids[-limit:]
logger.info(
f"{len(regression_related_ids)} bugs which caused regressions fixed by commits."
)
# Get IDs of bugs linked to intermittent failures.
test_failure_bug_ids = [
item["bug_id"] for item in test_scheduling.get_failure_bugs(
two_years_and_six_months_ago, datetime.utcnow())
]
if limit:
test_failure_bug_ids = test_failure_bug_ids[-limit:]
logger.info(f"{len(test_failure_bug_ids)} bugs about test failures.")
all_ids = (timespan_ids + labelled_bug_ids + commit_bug_ids +
regression_related_ids + test_failure_bug_ids)
all_ids_set = set(all_ids)
# We have to redownload bugs that were changed since the last download.
# We can remove from the DB the bugs that are outside of the considered timespan and are not labelled.
bugzilla.delete_bugs(lambda bug: bug["id"] in changed_ids or bug["id"]
not in all_ids_set)
new_bugs = bugzilla.download_bugs(all_ids)
# Get regression_related_ids again (the set could have changed after downloading new bugs).
for i in range(7):
regression_related_ids = list(
set(
sum(
(bug["regressed_by"] + bug["regressions"] +
bug["blocks"] for bug in new_bugs),
[],
)))
logger.info(
f"{len(regression_related_ids)} bugs which caused regressions fixed by commits."
)
if limit:
regression_related_ids = regression_related_ids[-limit:]
# If we got all bugs we needed, break.
if set(regression_related_ids).issubset(all_ids):
break
new_bugs = bugzilla.download_bugs(regression_related_ids)
# Try to re-download inconsistent bugs, up to twice.
inconsistent_bugs = bugzilla.get_bugs(include_invalid=True)
for i in range(2):
# We look for inconsistencies in all bugs first, then, on following passes,
# we only look for inconsistencies in bugs that were found to be inconsistent in the first pass
inconsistent_bugs = bug_snapshot.get_inconsistencies(
inconsistent_bugs)
inconsistent_bug_ids = set(bug["id"] for bug in inconsistent_bugs)
if len(inconsistent_bug_ids) == 0:
break
logger.info(
f"Re-downloading {len(inconsistent_bug_ids)} bugs, as they were inconsistent"
)
bugzilla.delete_bugs(lambda bug: bug["id"] in inconsistent_bug_ids)
bugzilla.download_bugs(inconsistent_bug_ids)
# TODO: Figure out why.
missing_history_bug_ids = {
bug["id"]
for bug in bugzilla.get_bugs() if "history" not in bug
}
bugzilla.delete_bugs(lambda bug: bug["id"] in missing_history_bug_ids)
logger.info(
f"Deleted {len(missing_history_bug_ids)} bugs as we couldn't retrieve their history"
)
zstd_compress(bugzilla.BUGS_DB)
