opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #7193 from jmchilton/export_extra_files

Browse Source 
Simplify history import to fix extra files and ObjectStore interactions.
This commit is contained in:
Marius van den Beek
2019-01-14 14:12:52 +01:00
committed by GitHub
parent b0bc39261d 8a55a486e3
commit cdacfca484
1 changed files with 14 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/galaxy/tools/imp_exp/__init__.py
+14 -28
View File
@@ -101,16 +101,6 @@ class JobImportHistoryArchiveWrapper(UsesAnnotations):
provenance_attrs = load(open(provenance_file_name))
datasets_attrs += provenance_attrs
# Get counts of how often each dataset file is used; a file can
# be linked to multiple dataset objects (HDAs).
datasets_usage_counts = {}
for dataset_attrs in datasets_attrs:
temp_dataset_file_name = \
os.path.realpath(os.path.join(archive_dir, dataset_attrs['file_name']))
if (temp_dataset_file_name not in datasets_usage_counts):
datasets_usage_counts[temp_dataset_file_name] = 0
datasets_usage_counts[temp_dataset_file_name] += 1
# Create datasets.
for dataset_attrs in datasets_attrs:
metadata = dataset_attrs['metadata']
@@ -150,26 +140,22 @@ class JobImportHistoryArchiveWrapper(UsesAnnotations):
os.path.realpath(os.path.abspath(os.path.join(archive_dir, dataset_attrs['file_name'])))
if not file_in_dir(temp_dataset_file_name, os.path.join(archive_dir, "datasets")):
raise MalformedContents("Invalid dataset path: %s" % temp_dataset_file_name)
if datasets_usage_counts[temp_dataset_file_name] == 1:
self.app.object_store.update_from_file(hda.dataset, file_name=temp_dataset_file_name, create=True)
self.app.object_store.update_from_file(hda.dataset, file_name=temp_dataset_file_name, create=True)
# Import additional files if present. Histories exported previously might not have this attribute set.
dataset_extra_files_path = dataset_attrs.get('extra_files_path', None)
if dataset_extra_files_path:
try:
file_list = os.listdir(os.path.join(archive_dir, dataset_extra_files_path))
except OSError:
file_list = []
# Import additional files if present. Histories exported previously might not have this attribute set.
dataset_extra_files_path = dataset_attrs.get('extra_files_path', None)
if dataset_extra_files_path:
try:
file_list = os.listdir(os.path.join(archive_dir, dataset_extra_files_path))
except OSError:
file_list = []
if file_list:
for extra_file in file_list:
self.app.object_store.update_from_file(
hda.dataset, extra_dir='dataset_%s_files' % hda.dataset.id,
alt_name=extra_file, file_name=os.path.join(archive_dir, dataset_extra_files_path, extra_file),
create=True)
else:
datasets_usage_counts[temp_dataset_file_name] -= 1
shutil.copyfile(temp_dataset_file_name, hda.file_name)
if file_list:
for extra_file in file_list:
self.app.object_store.update_from_file(
hda.dataset, extra_dir='dataset_%s_files' % hda.dataset.id,
alt_name=extra_file, file_name=os.path.join(archive_dir, dataset_extra_files_path, extra_file),
create=True)
hda.dataset.set_total_size() # update the filesize record in the database
# Set tags, annotations.