Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pass a PathMapper to the function that computes checksums #1829

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion cwltool/command_line_tool.py
Original file line number Diff line number Diff line change
Expand Up @@ -826,6 +826,7 @@ def job(
_checksum = partial(
compute_checksums,
runtimeContext.make_fs_access(runtimeContext.basedir),
cachebuilder,
)
visit_class(
[cachebuilder.files, cachebuilder.bindings],
Expand Down Expand Up @@ -1252,7 +1253,7 @@ def collect_output_ports(
)

if compute_checksum:
adjustFileObjs(ret, partial(compute_checksums, fs_access))
adjustFileObjs(ret, partial(compute_checksums, fs_access, builder))
expected_schema = cast(Schema, self.names.get_name("outputs_record_schema", None))
validate_ex(
expected_schema,
Expand Down
26 changes: 21 additions & 5 deletions cwltool/process.py
Original file line number Diff line number Diff line change
Expand Up @@ -391,7 +391,7 @@ def _check_adjust(a_file: CWLObjectType) -> CWLObjectType:
visit_class(outputObj, ("File", "Directory"), _check_adjust)

if compute_checksum:
visit_class(outputObj, ("File",), functools.partial(compute_checksums, fs_access))
visit_class(outputObj, ("File",), functools.partial(compute_checksums, fs_access, None))
return outputObj


Expand Down Expand Up @@ -1341,14 +1341,30 @@ def scandeps(
return r


def compute_checksums(fs_access: StdFsAccess, fileobj: CWLObjectType) -> None:
def compute_checksums(fs_access: StdFsAccess, builder: Builder, fileobj: CWLObjectType) -> None:
"""
Compute the checksums of a file object.

:param fs_access: Used to compute file stats such as its size.
:param builder: Optional CWL builder that must have a :py:class:`PathMapper` , which
will be used to resolve the actual file location (not its ``stagedir``).
:param fileobj: File object.
:raises ValueError: If a builder is provided but without having a :py:class:`PathMapper`.
"""
if "checksum" not in fileobj:
checksum = hashlib.sha1() # nosec
location = cast(str, fileobj["location"])
with fs_access.open(location, "rb") as f:
location = file_path = cast(str, fileobj["location"])
if builder:
if not builder.pathmapper:
raise ValueError(
"Do not call compute_checksums using a "
"builder that doesn't have a pathmapper."
)
file_path = builder.pathmapper.mapper(location)[0]
with fs_access.open(file_path, "rb") as f:
contents = f.read(1024 * 1024)
while contents != b"":
checksum.update(contents)
contents = f.read(1024 * 1024)
fileobj["checksum"] = "sha1$%s" % checksum.hexdigest()
fileobj["size"] = fs_access.size(location)
fileobj["size"] = fs_access.size(file_path)