def export_entities(export_id):
export = Export.by_id(export_id)
log.info("Export entities [%r]...", export)
export_dir = ensure_path(mkdtemp(prefix="aleph.export."))
collections = {}
try:
filters = [export.meta.get("query", {"match_none": {}})]
file_path = export_dir.joinpath("query-export.zip")
with ZipFile(file_path, mode="w") as zf:
excel_path = export_dir.joinpath(EXCEL_FILE)
exporter = ExcelExporter(excel_path, extra=EXTRA_HEADERS)
for entity in iter_proxies(filters=filters):
collection_id = entity.context.get("collection_id")
if collection_id not in collections:
collections[collection_id] = get_collection(collection_id)
collection = collections[collection_id]
if collection is None:
continue
extra = [entity_url(entity.id), collection.get("label")]
exporter.write(entity, extra=extra)
write_document(export_dir, zf, collection, entity)
if file_path.stat().st_size >= Export.MAX_FILE_SIZE:
log.warn("Export too large: %r", export)
break
exporter.finalize()
zf.write(excel_path, arcname=EXCEL_FILE)
complete_export(export_id, file_path)
except Exception:
log.exception("Failed to process export [%s]", export_id)
export = Export.by_id(export_id)
export.set_status(status=Status.FAILED)
db.session.commit()
finally:
shutil.rmtree(export_dir)
def test_excel_export(self):
entity = model.get_proxy(ENTITY)
exporter = ExcelExporter(self.temp, extra=["source"])
exporter.write(entity, extra=["test"])
exporter.finalize()
workbook = load_workbook(self.temp)
self.assertListEqual(workbook.sheetnames, ["People"])
sheet = workbook["People"]
rows = list(sheet)
props = exporter.exportable_properties(entity.schema)
self.assertListEqual(
[cell.value for cell in rows[0]],
["ID", "source"] + [prop.label for prop in props],
)
self.assertListEqual([cell.value for cell in rows[1][:3]],
["person", "test", "Ralph Tester"])
def test_excel_export(self):
entity = model.get_proxy(ENTITY)
exporter = ExcelExporter(self.temp, extra=['source'])
exporter.write(entity, extra=['test'])
exporter.finalize()
workbook = load_workbook(self.temp)
self.assertListEqual(workbook.sheetnames, ['People'])
sheet = workbook["People"]
rows = list(sheet)
self.assertListEqual(
[cell.value for cell in rows[0]],
['ID', 'source'] +
[prop.label for prop in entity.schema.sorted_properties]
)
self.assertListEqual(
[cell.value for cell in rows[1][:3]],
['person', 'test', 'Ralph Tester']
)
def export_entities(export_id):
export = Export.by_id(export_id)
log.info("Export entities [%r]...", export)
export_dir = ensure_path(mkdtemp(prefix="aleph.export."))
collections = {}
try:
filters = [export.meta.get("query", {"match_none": {}})]
file_path = export_dir.joinpath("export.zip")
with ZipFile(file_path, mode="w") as zf:
excel_name = safe_filename(export.label, extension="xlsx")
excel_path = export_dir.joinpath(excel_name)
exporter = ExcelExporter(excel_path, extra=EXTRA_HEADERS)
for idx, entity in enumerate(iter_proxies(filters=filters)):
collection_id = entity.context.get("collection_id")
if collection_id not in collections:
collections[collection_id] = get_collection(collection_id)
collection = collections[collection_id]
if collection is None:
continue
extra = [entity_url(entity.id), collection.get("label")]
exporter.write(entity, extra=extra)
write_document(export_dir, zf, collection, entity)
if file_path.stat().st_size >= settings.EXPORT_MAX_SIZE:
concern = "total size of the"
zf.writestr("EXPORT_TOO_LARGE.txt", WARNING % concern)
break
if idx >= settings.EXPORT_MAX_RESULTS:
concern = "number of"
zf.writestr("EXPORT_TOO_LARGE.txt", WARNING % concern)
break
exporter.finalize()
zf.write(excel_path, arcname=excel_name)
file_name = "Export: %s" % export.label
file_name = safe_filename(file_name, extension="zip")
complete_export(export_id, file_path, file_name)
except Exception:
log.exception("Failed to process export [%s]", export_id)
export = Export.by_id(export_id)
export.set_status(status=Status.FAILED)
db.session.commit()
finally:
shutil.rmtree(export_dir)