Skip to content

[25.0] Skip sam metadata if we have too many references #20820

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.

Sign up for GitHub

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

Merged
merged 2 commits into from
Oct 1, 2025
Merged

[25.0] Skip sam metadata if we have too many references #20820

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7f3410d
Skip sam metadata if we have too many references
mvdbeek Aug 26, 2025
118bf71
Add metadata_incomplete element
mvdbeek Oct 1, 2025
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
43 changes: 30 additions & 13 deletions lib/galaxy/datatypes/binary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -552,22 +552,29 @@ class _BamOrSam:
Helper class to set the metadata common to sam and bam files
"""

max_references = 100000

def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
try:
bam_file = pysam.AlignmentFile(dataset.get_file_name(), mode="rb")
# TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
dataset.metadata.reference_names = list(bam_file.references)
dataset.metadata.reference_lengths = list(bam_file.lengths)
dataset.metadata.bam_header = dict(bam_file.header.items()) # type: ignore [attr-defined]
dataset.metadata.read_groups = [
read_group["ID"] for read_group in dataset.metadata.bam_header.get("RG", []) if "ID" in read_group
]
dataset.metadata.sort_order = dataset.metadata.bam_header.get("HD", {}).get("SO", None)
dataset.metadata.bam_version = dataset.metadata.bam_header.get("HD", {}).get("VN", None)
with pysam.AlignmentFile(dataset.get_file_name(), mode="rb", check_sq=False) as bam_file:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm going to approve because your time is valuable and I think you have more important things to work on but I do feel like adding a metadata element to indicate these lists are truncated would be the ideal thing to do in this case so the meaning of these fields is consistent across bam files.

# TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
if bam_file.nreferences <= self.max_references:
dataset.metadata.reference_names = list(bam_file.references)
dataset.metadata.reference_lengths = list(bam_file.lengths)
dataset.metadata.bam_header = dict(bam_file.header.items()) # type: ignore [attr-defined]
dataset.metadata.read_groups = [
read_group["ID"]
for read_group in dataset.metadata.bam_header.get("RG", [])
if "ID" in read_group
]
else:
dataset.metadata.metadata_incomplete = True
dataset.metadata.sort_order = bam_file.header.get("HD", {}).get("SO", None) # type: ignore [attr-defined]
dataset.metadata.bam_version = bam_file.header.get("HD", {}).get("VN", None) # type: ignore [attr-defined]
except Exception:
# Per Dan, don't log here because doing so will cause datasets that
# fail metadata to end in the error state
pass
dataset.metadata.metadata_incomplete = True


class BamNative(CompressedArchive, _BamOrSam):
Expand Down Expand Up @@ -656,6 +663,16 @@ class BamNative(CompressedArchive, _BamOrSam):
optional=True,
no_value={},
)
MetadataElement(
name="metadata_incomplete",
default=False,
desc="Indicates if metadata is incomplete",
param=MetadataParameter,
readonly=True,
visible=False,
optional=True,
no_value=False,
)

def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
_BamOrSam().set_meta(dataset, overwrite=overwrite, **kwd)
Expand Down Expand Up @@ -1054,7 +1071,7 @@ def dataset_content_needs_grooming(self, file_name: str) -> bool:
"""
# The best way to ensure that BAM files are coordinate-sorted and indexable
# is to actually index them.
with pysam.AlignmentFile(filename=file_name) as f:
with pysam.AlignmentFile(filename=file_name, check_sq=False) as f:
# The only sure thing we know here is that the sort order can't be coordinate
return f.header.get("HD", {}).get("SO") == "coordinate" # type: ignore[attr-defined]

Expand All @@ -1074,7 +1091,7 @@ def dataset_content_needs_grooming(self, file_name: str) -> bool:
"""
# The best way to ensure that BAM files are coordinate-sorted and indexable
# is to actually index them.
with pysam.AlignmentFile(filename=file_name) as f:
with pysam.AlignmentFile(filename=file_name, check_sq=False) as f:
return f.header.get("HD", {}).get("SO") != "queryname" # type: ignore[attr-defined]


Expand Down
Loading