def _remove_all_result_files(ctx: click.Context, error: bool) -> None:
"""Remove all report files of the current paper_config."""
result_folders = _find_result_dir_paths_of_projects(
ctx.obj["case_studies"])
for folder in result_folders:
for res_file in folder.iterdir():
report_file = ReportFilename(res_file.name)
if not report_file.is_result_file():
continue
if ctx.obj["experiment"] and not ctx.obj[
"experiment"].file_belongs_to_experiment(res_file.name):
continue
if ctx.obj["report"] and not ctx.obj[
"report"].is_correct_report_type(res_file.name):
continue
commit_hash = report_file.commit_hash
if any(
list(
case_study.has_revision(commit_hash)
for case_study in ctx.obj["case_studies"])):
if error and not (report_file.has_status_compileerror()
or report_file.has_status_failed()):
continue
res_file.unlink()
def __get_result_files_dict(
project_name: str, result_file_type: tp.Type[BaseReport]
) -> tp.Dict[ShortCommitHash, tp.List[Path]]:
"""
Returns a dict that maps the commit_hash to a list of all result files, of
type result_file_type, for that commit.
Args:
project_name: target project
result_file_type: the type of the result file
"""
res_dir = Path(f"{vara_cfg()['result_dir']}/{project_name}/")
result_files: tp.DefaultDict[ShortCommitHash, tp.List[Path]] = defaultdict(
list
) # maps commit hash -> list of res files (success or fail)
if not res_dir.exists():
return result_files
for res_file in res_dir.iterdir():
report_file = ReportFilename(res_file)
if report_file.is_result_file(
) and result_file_type.is_correct_report_type(res_file.name):
commit_hash = report_file.commit_hash
result_files[commit_hash].append(res_file)
return result_files
def test_get_newest_result_files_for_case_study_fail(self) -> None:
"""Check that when we have two files, the newes one get's selected."""
vara_cfg()['paper_config']['current_config'] = "test_revision_lookup"
load_paper_config()
bad_file = ReportFilename(
'CRE-CR-brotli-brotli-21ac39f7c8_'
'34d4d1b5-7212-4244-9adc-b19bff599cf1_success.yaml')
now = datetime.now().timestamp()
file_path = Path(str(
vara_cfg()['result_dir'])) / 'brotli' / bad_file.filename
os.utime(file_path, (now, now))
newest_res_files = MCS.get_newest_result_files_for_case_study(
get_paper_config().get_case_studies('brotli')[0],
Path(vara_cfg()['result_dir'].value), CR)
# remove unnecessary files
filtered_newest_res_files = list(
filter(
lambda res_file: res_file.commit_hash == bad_file.commit_hash,
map(lambda res_file: ReportFilename(res_file),
newest_res_files)))
self.assertFalse(filtered_newest_res_files[0].uuid.endswith('42'))
def test_get_commit(self):
"""Check if the correct commit hash is returned."""
self.assertEqual(
ReportFilename(self.success_filename).commit_hash,
ShortCommitHash("7bb9ef5f8c"))
self.assertEqual(
ReportFilename(self.fail_filename).commit_hash,
ShortCommitHash("7bb9ef5f8c"))
def setUpClass(cls):
"""Setup file and CommitReport."""
cls.correct_UUID = "fdb09c5a-4cee-42d8-bbdc-4afe7a7864be"
cls.raw_filename = ("CRE-CR-foo-bar-7bb9ef5f8c_"
f"{cls.correct_UUID}_"
"success.txt")
cls.report_filename = ReportFilename(cls.raw_filename)
cls.broken_report_filename = ReportFilename("ThisFileIsWrong.foobar")
def test_file_status(self):
"""Check if the correct file status is returned for BaseReport names."""
self.assertTrue(
ReportFilename(self.success_filename).has_status_success())
self.assertFalse(
ReportFilename(self.fail_filename).has_status_success())
self.assertTrue(ReportFilename(self.fail_filename).has_status_failed())
self.assertFalse(
ReportFilename(self.success_filename).has_status_failed())
def test_is_result_file(self):
"""Check if the result file matcher works."""
self.assertTrue(ReportFilename(self.success_filename).is_result_file())
self.assertTrue(ReportFilename(self.fail_filename).is_result_file())
self.assertFalse(
ReportFilename(self.success_filename.replace("_",
"")).is_result_file())
self.assertFalse(
ReportFilename(self.fail_filename.replace("-",
"")).is_result_file())
def __get_tag_for_revision(
revision: ShortCommitHash,
file_list: tp.List[Path],
project_cls: tp.Type[Project],
result_file_type: tp.Type[BaseReport],
tag_blocked: bool = True
) -> FileStatusExtension:
"""
Calculates the file status for a revision.
Args:
revision: the revision to get the status for
file_list: the list of result files for the revision
project_cls: the project class the revision belongs to
result_file_type: the report type to be considered
Returns:
the status for the revision
"""
if tag_blocked and is_revision_blocked(revision, project_cls):
return FileStatusExtension.BLOCKED
newest_res_file = max(file_list, key=lambda x: x.stat().st_mtime)
if result_file_type.is_correct_report_type(newest_res_file.name):
return ReportFilename(str(newest_res_file)).file_status
return FileStatusExtension.MISSING
def get_newest_result_files_for_case_study(
case_study: CaseStudy, result_dir: Path,
report_type: tp.Type[BaseReport]) -> tp.List[Path]:
"""
Return all result files of a specific type that belong to a given case
study. For revision with multiple files, the newest file will be selected.
Args:
case_study: to load
result_dir: to load the results from
report_type: type of report that should be loaded
Returns:
list of result file paths
"""
files_to_store: tp.Dict[ShortCommitHash, Path] = {}
result_dir /= case_study.project_name
if not result_dir.exists():
return []
for opt_res_file in result_dir.iterdir():
report_file = ReportFilename(opt_res_file.name)
if report_type.is_correct_report_type(report_file.filename):
commit_hash = report_file.commit_hash
if case_study.has_revision(commit_hash):
current_file = files_to_store.get(commit_hash, None)
if current_file is None:
files_to_store[commit_hash] = opt_res_file
else:
if (current_file.stat().st_mtime <
opt_res_file.stat().st_mtime):
files_to_store[commit_hash] = opt_res_file
return list(files_to_store.values())
def filter_report_paths_binary(
report_files: tp.List[Path], binary: ProjectBinaryWrapper
) -> tp.List[Path]:
return list(
filter(
lambda x: ReportFilename(x).binary_name == binary.name, report_files
)
)
def test_is_result_file(self) -> None:
"""Check if the result file matcher works."""
self.assertTrue(self.commit_report_success.filename.is_result_file())
self.assertTrue(self.commit_report_fail.filename.is_result_file())
self.assertFalse(
ReportFilename(
self.commit_report_success.filename.filename.replace("_", "")
).is_result_file()
)
self.assertFalse(
ReportFilename(
self.commit_report_success.filename.filename.replace("-", "")
).is_result_file()
)
self.assertFalse(
ReportFilename(
self.commit_report_success.filename.filename.replace(".", "f")
).is_result_file()
)
def cs_filter(file_name: str) -> bool:
"""
Filter files that are not in the case study.
Returns:
``True`` if a case_study is set and the commit_hash of the file
is not part of this case_study, otherwise, ``False``.
"""
if case_study is None:
return False
return not case_study.has_revision(
ReportFilename(file_name).commit_hash)
def _load_dataframe(cls, project_name: str, commit_map: CommitMap,
case_study: tp.Optional[CaseStudy],
**kwargs: tp.Any) -> pd.DataFrame:
def create_dataframe_layout() -> pd.DataFrame:
df_layout = pd.DataFrame(columns=cls.COLUMNS)
df_layout = df_layout.astype(cls.COLUMN_TYPES)
return df_layout
def create_data_frame_for_report(
report_path: Path) -> tp.Tuple[pd.DataFrame, str, str]:
report = load_commit_report(report_path)
cf_head_interactions_raw = report.number_of_head_cf_interactions()
df_head_interactions_raw = report.number_of_head_df_interactions()
return pd.DataFrame(
{
'revision':
report.head_commit.hash,
'time_id':
commit_map.short_time_id(report.head_commit),
'CFInteractions':
report.number_of_cf_interactions(),
'DFInteractions':
report.number_of_df_interactions(),
'HEAD CF Interactions':
cf_head_interactions_raw[0] + cf_head_interactions_raw[1],
'HEAD DF Interactions':
df_head_interactions_raw[0] + df_head_interactions_raw[1]
},
index=[0]), report.head_commit.hash, str(
report_path.stat().st_mtime_ns)
report_files = get_processed_revisions_files(
project_name, CommitReport,
get_case_study_file_name_filter(case_study))
failed_report_files = get_failed_revisions_files(
project_name, CommitReport,
get_case_study_file_name_filter(case_study))
# cls.CACHE_ID is set by superclass
# pylint: disable=E1101
data_frame = build_cached_report_table(
cls.CACHE_ID, project_name, report_files, failed_report_files,
create_dataframe_layout, create_data_frame_for_report,
lambda path: ReportFilename(path).commit_hash.hash,
lambda path: str(path.stat().st_mtime_ns),
lambda a, b: int(a) > int(b))
return data_frame
def build_report_files_tuple(
project_name: str, case_study: tp.Optional[CaseStudy]
) -> tp.Tuple[tp.Dict[ShortCommitHash, Path], tp.Dict[ShortCommitHash, Path]]:
"""
Build the mappings between commit hash to its corresponding report file
path, where the first mapping corresponds to commit hashes and their
successful report files and the second mapping to commit hashes and their
failed report files.
Args:
project_name: the name of the project
case_study: the selected CaseStudy
Returns:
the mappings from commit hash to successful and failed report files as
tuple
"""
report_files: tp.Dict[ShortCommitHash, Path] = {
ReportFilename(report).commit_hash: report
for report in get_processed_revisions_files(
project_name,
BlameReport,
get_case_study_file_name_filter(case_study)
if case_study else lambda x: False,
)
}
failed_report_files: tp.Dict[ShortCommitHash, Path] = {
ReportFilename(report).commit_hash: report
for report in get_failed_revisions_files(
project_name,
BlameReport,
get_case_study_file_name_filter(case_study)
if case_study else lambda x: False,
)
}
return report_files, failed_report_files
def file_belongs_to_experiment(cls, file_name: str) -> bool:
"""
Checks if the file belongs to this experiment.
Args:
file_name: name of the file to check
Returns:
True, if the file belongs to this experiment type
"""
try:
other_short_hand = ReportFilename(file_name).experiment_shorthand
return cls.shorthand() == other_short_hand
except ValueError:
return False
def _remove_old_result_files(ctx: click.Context) -> None:
"""Remove result files of wich a newer version exists."""
result_dir = Path(str(vara_cfg()['result_dir']))
for case_study in ctx.obj['case_studies']:
old_files: tp.List[Path] = []
newer_files: tp.Dict[ShortCommitHash, Path] = {}
result_dir_cs = result_dir / case_study.project_name
if not result_dir_cs.exists():
continue
for opt_res_file in result_dir_cs.iterdir():
report_file = ReportFilename(opt_res_file.name)
if not report_file.is_result_file():
continue
if ctx.obj["experiment"] and not ctx.obj[
"experiment"].file_belongs_to_experiment(
opt_res_file.name):
continue
if ctx.obj["report"] and not ctx.obj[
"report"].is_correct_report_type(opt_res_file.name):
continue
commit_hash = report_file.commit_hash
if case_study.has_revision(commit_hash):
current_file = newer_files.get(commit_hash)
if current_file is None:
newer_files[commit_hash] = opt_res_file
else:
if (current_file.stat().st_mtime_ns <
opt_res_file.stat().st_mtime_ns):
newer_files[commit_hash] = opt_res_file
old_files.append(current_file)
else:
old_files.append(opt_res_file)
for file in old_files:
if file.exists():
file.unlink()
def get_processed_revisions(
project_name: str, result_file_type: tp.Type[BaseReport]
) -> tp.List[ShortCommitHash]:
"""
Calculates a list of revisions of a project that have already been processed
successfully.
Args:
project_name: target project
result_file_type: the type of the result file
Returns:
list of correctly process revisions
"""
return [
ReportFilename(x.name).commit_hash
for x in get_processed_revisions_files(project_name, result_file_type)
]
def _get_requested_report_paths(
project_name: str, szz_report: SZZReport
) -> tp.Dict[ShortCommitHash, Path]:
bugs = szz_report.get_all_raw_bugs()
requested_report_revisions: tp.Set[ShortCommitHash] = set()
for bug in bugs:
requested_report_revisions.add(bug.fixing_commit.to_short_commit_hash())
requested_report_revisions.update(
introducer.to_short_commit_hash()
for introducer in bug.introducing_commits
)
report_map: tp.Dict[ShortCommitHash, Path] = {}
for report_path in get_processed_revisions_files(project_name, BlameReport):
report_revision = ReportFilename(report_path).commit_hash
if report_revision in requested_report_revisions:
report_map[report_revision] = report_path
return report_map
def __get_files_with_status(
project_name: str,
result_file_type: tp.Type[BaseReport],
file_statuses: tp.List[FileStatusExtension],
file_name_filter: tp.Callable[[str], bool] = lambda x: False,
only_newest: bool = True
) -> tp.List[Path]:
"""
Find all file paths to revision files with given file statuses.
Args:
project_name: target project
result_file_type: the type of the result file
file_statuses: a list of statuses the files should have
file_name_filter: optional filter to exclude certain files; returns
true if the file_name should not be checked
only_newest: whether to include all result files, or only the newest;
if ``False``, result files for the same revision are sorted
descending by the file's mtime
Returns:
a list of file paths to matching revision files
"""
processed_revisions_paths = []
result_files = __get_result_files_dict(project_name, result_file_type)
for value in result_files.values():
sorted_res_files = sorted(
value, key=lambda x: Path(x).stat().st_mtime, reverse=True
)
if only_newest:
sorted_res_files = [sorted_res_files[0]]
for result_file in sorted_res_files:
if file_name_filter(result_file.name):
continue
if ReportFilename(result_file.name).file_status in file_statuses:
processed_revisions_paths.append(result_file)
return processed_revisions_paths
def get_failed_revisions(
project_name: str, result_file_type: tp.Type[BaseReport]
) -> tp.List[ShortCommitHash]:
"""
Calculates a list of revisions of a project that have failed.
Args:
project_name: target project
result_file_type: the type of the result file
Returns:
list of failed revisions
"""
failed_revisions = []
result_files = __get_result_files_dict(project_name, result_file_type)
for commit_hash, value in result_files.items():
newest_res_file = max(value, key=lambda x: Path(x).stat().st_mtime)
if ReportFilename(newest_res_file.name).has_status_failed():
failed_revisions.append(commit_hash)
return failed_revisions
def _load_dataframe(cls, project_name: str, commit_map: CommitMap,
case_study: tp.Optional[CaseStudy],
**kwargs: tp.Any) -> pd.DataFrame:
# pylint: disable=unused-argument
def create_dataframe_layout() -> pd.DataFrame:
df_layout = pd.DataFrame(columns=cls.COLUMNS)
df_layout = df_layout.astype(cls.COLUMN_TYPES)
return df_layout
def create_data_frame_for_report(
report_path: Path) -> tp.Tuple[pd.DataFrame, str, str]:
report_file_name_match = re.search(
BlameVerifierReportDatabase.report_file_name_pattern,
str(report_path))
if report_file_name_match:
report_file_name = report_file_name_match.group()
else:
raise RuntimeWarning(
"report file name could not be read from report path")
report: tp.Union[BlameVerifierReportOpt,
BlameVerifierReportNoOptTBAA]
if BlameVerifierReportOpt.is_correct_report_type(report_file_name):
report_opt = load_blame_verifier_report_opt(report_path)
report = report_opt
opt_level = OptLevel.OPT.value
elif BlameVerifierReportNoOptTBAA.is_correct_report_type(
report_file_name):
report_no_opt = load_blame_verifier_report_no_opt_tbaa(
report_path)
report = report_no_opt
opt_level = OptLevel.NO_OPT.value
else:
raise RuntimeWarning("unknown report type")
number_of_total_annotations = report.get_total_annotations()
number_of_successful_annotations = \
report.get_successful_annotations()
number_of_failed_annotations = report.get_failed_annotations()
number_of_undetermined_annotations \
= report.get_undetermined_annotations()
return pd.DataFrame(
{
'revision': report.head_commit.hash,
'time_id': commit_map.short_time_id(report.head_commit),
'opt_level': opt_level,
'total': number_of_total_annotations,
'successful': number_of_successful_annotations,
'failed': number_of_failed_annotations,
'undetermined': number_of_undetermined_annotations
},
index=[0]
# Add prefix of report name to head_commit to differentiate
# between reports with and without optimization
), report.head_commit.hash + report_path.name.split(
"-", 1)[0], str(report_path.stat().st_mtime_ns)
report_files_opt = get_processed_revisions_files(
project_name, BlameVerifierReportOpt,
get_case_study_file_name_filter(case_study))
report_files_no_opt = get_processed_revisions_files(
project_name, BlameVerifierReportNoOptTBAA,
get_case_study_file_name_filter(case_study))
report_files = report_files_opt + report_files_no_opt
failed_report_files_opt = get_failed_revisions_files(
project_name, BlameVerifierReportOpt,
get_case_study_file_name_filter(case_study))
failed_report_files_no_opt = get_failed_revisions_files(
project_name, BlameVerifierReportNoOptTBAA,
get_case_study_file_name_filter(case_study))
failed_report_files = \
failed_report_files_opt + failed_report_files_no_opt
# cls.CACHE_ID is set by superclass
# pylint: disable=E1101
data_frame = build_cached_report_table(
cls.CACHE_ID, project_name, report_files, failed_report_files,
create_dataframe_layout, create_data_frame_for_report, lambda path:
ReportFilename(path).commit_hash.hash + path.name.split("-", 1)[0],
lambda path: str(path.stat().st_mtime_ns),
lambda a, b: int(a) > int(b))
return data_frame
def head_commit(self) -> ShortCommitHash:
"""The current HEAD commit under which this BlameVerifierReportOpt was
created."""
return ReportFilename(Path(self.path)).commit_hash
def result_file_to_list_entry(result_file: Path) -> str:
file_status = ReportFilename(result_file.name).file_status
status = (file_status.get_colored_status().rjust(
longest_file_status_extension + file_status.num_color_characters(),
" "))
return f"[{status}] {result_file.name}"
def match_revision(file_name: str) -> bool:
return ReportFilename(
file_name).commit_hash != revision.to_short_commit_hash()
def _load_dataframe(
cls, project_name: str, commit_map: CommitMap,
case_study: tp.Optional[CaseStudy], **kwargs: tp.Any
) -> pd.DataFrame:
commit_lookup = create_commit_lookup_helper(project_name)
def create_dataframe_layout() -> pd.DataFrame:
df_layout = pd.DataFrame(columns=cls.COLUMNS)
df_layout = df_layout.astype(cls.COLUMN_TYPES)
return df_layout
def create_data_frame_for_report(
report_path: Path
) -> tp.Tuple[pd.DataFrame, str, str]:
report = load_blame_report(report_path)
categorised_degree_occurrences = generate_lib_dependent_degrees(
report
)
def calc_total_amounts() -> int:
total = 0
for _, lib_dict in categorised_degree_occurrences.items():
for _, tuple_list in lib_dict.items():
for degree_amount_tuple in tuple_list:
total += degree_amount_tuple[1]
return total
total_amounts_of_all_libs = calc_total_amounts()
list_of_author_degree_occurrences = generate_author_degree_tuples(
report, commit_lookup
)
author_degrees, author_amounts = _split_tuple_values_in_lists_tuple(
list_of_author_degree_occurrences
)
author_total = sum(author_amounts)
list_of_max_time_deltas = generate_max_time_distribution_tuples(
report, commit_lookup, MAX_TIME_BUCKET_SIZE
)
(max_time_buckets, max_time_amounts
) = _split_tuple_values_in_lists_tuple(list_of_max_time_deltas)
total_max_time_amounts = sum(max_time_amounts)
list_of_avg_time_deltas = generate_avg_time_distribution_tuples(
report, commit_lookup, AVG_TIME_BUCKET_SIZE
)
(avg_time_buckets, avg_time_amounts
) = _split_tuple_values_in_lists_tuple(list_of_avg_time_deltas)
total_avg_time_amounts = sum(avg_time_amounts)
def build_dataframe_row(
degree_type: DegreeType,
degree: int,
amount: int,
total_amount: int,
base_library: tp.Optional[str] = None,
inter_library: tp.Optional[str] = None
) -> tp.Dict[str, tp.Any]:
data_dict: tp.Dict[str, tp.Any] = {
'revision': report.head_commit.hash,
'time_id': commit_map.short_time_id(report.head_commit),
'degree_type': degree_type.value,
'base_lib': base_library,
'inter_lib': inter_library,
'degree': degree,
'amount': amount,
'fraction': np.divide(amount, total_amount)
}
return data_dict
result_data_dicts: tp.List[tp.Dict[str, tp.Any]] = []
# Append interaction rows
for base_lib_name, inter_lib_dict \
in categorised_degree_occurrences.items():
for inter_lib_name, list_of_lib_degree_amount_tuples in \
inter_lib_dict.items():
(inter_degrees,
inter_amounts) = _split_tuple_values_in_lists_tuple(
list_of_lib_degree_amount_tuples
)
for i, _ in enumerate(inter_degrees):
degree = inter_degrees[i]
lib_amount = inter_amounts[i]
interaction_data_dict = build_dataframe_row(
degree_type=DegreeType.INTERACTION,
degree=degree,
amount=lib_amount,
total_amount=total_amounts_of_all_libs,
base_library=base_lib_name,
inter_library=inter_lib_name,
)
result_data_dicts.append(interaction_data_dict)
def append_rows_of_degree_type(
degree_type: DegreeType,
degrees: tp.List[int],
amounts: tp.List[int],
sum_amounts: int,
) -> None:
for k, _ in enumerate(degrees):
data_dict = build_dataframe_row(
degree_type=degree_type,
degree=degrees[k],
amount=amounts[k],
total_amount=sum_amounts
)
result_data_dicts.append(data_dict)
# Append author rows
append_rows_of_degree_type(
degree_type=DegreeType.AUTHOR,
degrees=author_degrees,
amounts=author_amounts,
sum_amounts=author_total
)
# Append max_time rows
append_rows_of_degree_type(
degree_type=DegreeType.MAX_TIME,
degrees=max_time_buckets,
amounts=max_time_amounts,
sum_amounts=total_max_time_amounts
)
# Append avg_time rows
append_rows_of_degree_type(
degree_type=DegreeType.AVG_TIME,
degrees=avg_time_buckets,
amounts=avg_time_amounts,
sum_amounts=total_avg_time_amounts
)
return pd.DataFrame(result_data_dicts
), report.head_commit.hash, str(
report_path.stat().st_mtime_ns
)
report_files = get_processed_revisions_files(
project_name, BlameReport,
get_case_study_file_name_filter(case_study)
)
failed_report_files = get_failed_revisions_files(
project_name, BlameReport,
get_case_study_file_name_filter(case_study)
)
# cls.CACHE_ID is set by superclass
# pylint: disable=E1101
data_frame = build_cached_report_table(
cls.CACHE_ID, project_name, report_files, failed_report_files,
create_dataframe_layout, create_data_frame_for_report,
lambda path: ReportFilename(path).commit_hash.hash,
lambda path: str(path.stat().st_mtime_ns),
lambda a, b: int(a) > int(b)
)
return data_frame
def file_name_filter(file_name: str) -> bool:
file_commit_hash = ReportFilename(file_name).commit_hash
return not file_commit_hash == commit_hash
def _load_dataframe(cls, project_name: str, commit_map: CommitMap,
case_study: tp.Optional[CaseStudy],
**kwargs: tp.Any) -> pd.DataFrame:
def create_dataframe_layout() -> pd.DataFrame:
df_layout = pd.DataFrame(columns=cls.COLUMNS)
df_layout = df_layout.astype(cls.COLUMN_TYPES)
return df_layout
def create_data_frame_for_report(
report_path: Path) -> tp.Tuple[pd.DataFrame, str, str]:
report = load_blame_report(report_path)
base_inter_c_repo_pair_mapping = \
gen_base_to_inter_commit_repo_pair_mapping(report)
def build_dataframe_row(base_hash: FullCommitHash,
base_library: str,
inter_hash: FullCommitHash,
inter_library: str,
amount: int) -> tp.Dict[str, tp.Any]:
data_dict: tp.Dict[str, tp.Any] = {
'revision': report.head_commit.hash,
'time_id': commit_map.short_time_id(report.head_commit),
'base_hash': base_hash.hash,
'base_lib': base_library,
'inter_hash': inter_hash.hash,
'inter_lib': inter_library,
'amount': amount
}
return data_dict
result_data_dicts: tp.List[tp.Dict[str, tp.Any]] = []
for base_pair in base_inter_c_repo_pair_mapping:
inter_pair_amount_dict = base_inter_c_repo_pair_mapping[
base_pair]
for inter_pair in inter_pair_amount_dict:
result_data_dicts.append(
build_dataframe_row(
base_hash=base_pair.commit.commit_hash,
base_library=base_pair.commit.repository_name,
inter_hash=inter_pair.commit.commit_hash,
inter_library=inter_pair.commit.repository_name,
amount=inter_pair_amount_dict[inter_pair]))
return pd.DataFrame(
result_data_dicts), report.head_commit.hash, str(
report_path.stat().st_mtime_ns)
report_files = get_processed_revisions_files(
project_name, BlameReport,
get_case_study_file_name_filter(case_study))
failed_report_files = get_failed_revisions_files(
project_name, BlameReport,
get_case_study_file_name_filter(case_study))
# cls.CACHE_ID is set by superclass
# pylint: disable=E1101
data_frame = build_cached_report_table(
cls.CACHE_ID, project_name, report_files, failed_report_files,
create_dataframe_layout, create_data_frame_for_report,
lambda path: ReportFilename(path).commit_hash.hash,
lambda path: str(path.stat().st_mtime_ns),
lambda a, b: int(a) > int(b))
return data_frame
