def make_schema_collection_label(
bundle_db: BundleDB,
info: Citation_Information,
collection_lidvid: str,
bundle_lidvid: str,
verify: bool,
mod_date: str,
) -> bytes:
"""
Create the label text for the schema collection having this LIDVID using
the bundle database. If verify is True, verify the label against
its XML and Schematron schemas. Raise an exception if either
fails.
"""
# TODO this is sloppy; is there a better way?
products = bundle_db.get_schema_products()
record_count = len(products)
if record_count <= 0:
raise ValueError(f"{collection_lidvid} has no schema products.")
collection_lid = lidvid_to_lid(collection_lidvid)
collection_vid = lidvid_to_vid(collection_lidvid)
collection: Collection = bundle_db.get_collection(collection_lidvid)
proposal_id = bundle_db.get_bundle(bundle_lidvid).proposal_id
instruments = ",".join(bundle_db.get_instruments_of_the_bundle()).upper()
title: NodeBuilder = make_schema_collection_title(
{
"instrument": instruments,
"proposal_id": str(proposal_id),
}
)
inventory_name = get_collection_inventory_name(bundle_db, collection_lidvid)
try:
label = (
make_label(
{
"collection_lid": collection_lid,
"collection_vid": collection_vid,
"record_count": record_count,
"title": title,
"mod_date": mod_date,
"proposal_id": str(proposal_id),
"Citation_Information": make_citation_information(info),
"inventory_name": inventory_name,
"Context_Area": combine_nodes_into_fragment([]),
"Reference_List": combine_nodes_into_fragment([]),
"collection_type": "Schema",
}
)
.toxml()
.encode()
)
except Exception as e:
raise LabelError(collection_lidvid) from e
return pretty_and_verify(label, verify)
def make_document_collection_inventory(bundle_db: BundleDB,
collection_lidvid: str) -> bytes:
"""
Create the inventory text for the collection having this LIDVID
using the bundle database.
"""
products = bundle_db.get_collection_products(collection_lidvid)
inventory_lines: List[str] = [
f"P,{product.lidvid}\r\n" for product in products
]
# Include handbooks in the document collection csv
inst_list = bundle_db.get_instruments_of_the_bundle()
for inst in inst_list:
data_handbook_lid = f"S,urn:nasa:pds:hst-support:document:{inst}-dhb\r\n"
inst_handbook_lid = f"S,urn:nasa:pds:hst-support:document:{inst}-ihb\r\n"
inventory_lines.append(data_handbook_lid)
inventory_lines.append(inst_handbook_lid)
res: str = "".join(inventory_lines)
return res.encode()
def make_bundle_label(
bundle_db: BundleDB,
bundle_lidvid: str,
info: Citation_Information,
verify: bool,
use_mod_date_for_testing: bool = False,
) -> bytes:
"""
Create the label text for the bundle in the bundle database using
the database connection. If verify is True, verify the label
against its XML and Schematron schemas. Raise an exception if
either fails.
"""
bundle = bundle_db.get_bundle(bundle_lidvid)
proposal_id = bundle.proposal_id
def get_ref_type(collection: Collection) -> str:
ref_type = switch_on_collection_subtype(
collection,
"bundle_has_context_collection",
"bundle_has_document_collection",
"bundle_has_schema_collection",
"bundle_has_other_collection",
)
if ref_type == "bundle_has_other_collection":
collection_type = cast(OtherCollection, collection).prefix
ref_type = f"bundle_has_{collection_type}_collection"
return ref_type
reduced_collections = [
make_bundle_entry_member({
"collection_lidvid": collection.lidvid,
"ref_type": get_ref_type(collection),
}) for collection in bundle_db.get_bundle_collections(bundle.lidvid)
]
# Get the bundle title from part of CitationInformation description
title = (info.title + ", HST Cycle " + str(info.cycle) + " Program " +
str(info.propno) + ", " + info.publication_year + ".")
# Get the list of target identifications nodes for the collection
target_identifications = bundle_db.get_all_target_identification()
target_identification_nodes: List[NodeBuilder] = []
target_identification_nodes = create_target_identification_nodes(
bundle_db, target_identifications, "bundle")
# Get the investigation node for the collection
investigation_area_name = mk_Investigation_Area_name(proposal_id)
investigation_area_lidvid = mk_Investigation_Area_lidvid(proposal_id)
investigation_area_node = investigation_area(investigation_area_name,
investigation_area_lidvid,
"bundle")
# Get min start_time and max stop_time
start_time, stop_time = bundle_db.get_roll_up_time_from_db()
# Make sure start/stop time exists in db.
if start_time is None:
raise ValueError("Start time is not stored in FitsProduct table.")
if stop_time is None:
raise ValueError("Stop time is not stored in FitsProduct table.")
start_stop_times = {
"start_date_time": start_time,
"stop_date_time": stop_time,
}
time_coordinates_node = get_time_coordinates(start_stop_times)
# Dictionary used for primary result summary
primary_result_dict: Dict[str, Any] = {}
# Put dummy value in processing level, wait for update.
primary_result_dict["processing_level"] = "Raw"
instruments_list = bundle_db.get_instruments_of_the_bundle()
instruments = ", ".join(instruments_list).upper()
p_title = (f"{instruments} observations obtained by the HST " +
f"Observing Program {proposal_id}.")
primary_result_dict["description"] = p_title
# Get unique wavelength names for roll-up in bundle
wavelength_range = bundle_db.get_wavelength_range_from_db()
primary_result_dict["wavelength_range"] = wavelength_range
primary_result_summary_node = primary_result_summary(primary_result_dict)
# Get the observing system node for the bundle
observing_system_nodes: List[NodeBuilder] = [
observing_system(instrument) for instrument in instruments_list
]
context_node: List[NodeBuilder] = []
context_node = [
make_bundle_context_node(
time_coordinates_node,
primary_result_summary_node,
investigation_area_node,
observing_system_nodes,
target_identification_nodes,
)
]
if not use_mod_date_for_testing:
# Get the date when the label is created
mod_date = get_current_date()
else:
mod_date = MOD_DATE_FOR_TESTESING
try:
label = (make_label({
"bundle_lid":
lidvid_to_lid(bundle.lidvid),
"bundle_vid":
lidvid_to_vid(bundle.lidvid),
"proposal_id":
str(proposal_id),
"title":
title,
"Citation_Information":
make_citation_information(info, is_for_bundle=True),
"mod_date":
mod_date,
"Bundle_Member_Entries":
combine_nodes_into_fragment(reduced_collections),
"Context_Area":
combine_nodes_into_fragment(context_node),
"Reference_List":
make_document_reference_list(instruments_list, "bundle"),
}).toxml().encode())
except Exception as e:
raise LabelError(bundle.lidvid) from e
if label[:6] != b"<?xml ":
raise ValueError("Bundle label is not XML.")
return pretty_and_verify(label, verify)
def make_other_collection_label(
bundle_db: BundleDB,
info: Citation_Information,
collection_lidvid: str,
bundle_lidvid: str,
verify: bool,
mod_date: str,
) -> bytes:
"""
Create the label text for the document, browse, and data collection having
this LIDVID using the bundle database. If verify is True, verify the label
against its XML and Schematron schemas. Raise an exception if either
fails.
"""
# TODO this is sloppy; is there a better way?
products = bundle_db.get_collection_products(collection_lidvid)
record_count = len(products)
if record_count <= 0:
raise ValueError(f"{collection_lidvid} has no products.")
collection_lid = lidvid_to_lid(collection_lidvid)
collection_vid = lidvid_to_vid(collection_lidvid)
collection: Collection = bundle_db.get_collection(collection_lidvid)
proposal_id = bundle_db.get_bundle(bundle_lidvid).proposal_id
instruments = ",".join(bundle_db.get_instruments_of_the_bundle()).upper()
def make_ctxt_coll_title(_coll: Collection) -> NodeBuilder:
return make_context_collection_title(
{
"instrument": instruments,
"proposal_id": str(proposal_id),
}
)
def make_doc_coll_title(_coll: Collection) -> NodeBuilder:
return make_document_collection_title(
{
"instrument": instruments,
"proposal_id": str(proposal_id),
}
)
def make_sch_coll_title(_coll: Collection) -> NodeBuilder:
return make_schema_collection_title(
{
"instrument": instruments,
"proposal_id": str(proposal_id),
}
)
def make_other_coll_title(coll: Collection) -> NodeBuilder:
other_collection = cast(OtherCollection, coll)
if other_collection.prefix == "browse":
collection_title = (
f"{other_collection.prefix.capitalize()} "
+ f"collection of {other_collection.instrument.upper()} "
+ f"observations obtained from HST Observing Program {proposal_id}."
)
else:
# Get the data/misc collection title from db.
collection_title = str(other_collection.title)
return make_other_collection_title({"collection_title": collection_title})
title: NodeBuilder = switch_on_collection_subtype(
collection,
make_ctxt_coll_title,
make_doc_coll_title,
make_sch_coll_title,
make_other_coll_title,
)(collection)
inventory_name = get_collection_inventory_name(bundle_db, collection_lidvid)
# Properly assign collection type for Document, Browse, or Data collection.
# Context node only exists in Data collection label.
# Reference_List only exists in Data collection label.
context_node: List[NodeBuilder] = []
reference_list_node: List[NodeBuilder] = []
collection_type: str = ""
type_name = type(collection).__name__
if type_name == "DocumentCollection":
collection_type = "Document"
# For document collection, we need to add all handbooks in the csv but
# we won't create the label for it.
inst_list = bundle_db.get_instruments_of_the_bundle()
record_count += 2 * len(inst_list)
elif type_name == "OtherCollection":
collection_type = cast(OtherCollection, collection).prefix.capitalize()
suffix = cast(OtherCollection, collection).suffix
instrument = cast(OtherCollection, collection).instrument
# Roll-up (Context node) only exists in data collection
if collection_type == "Data":
# Get min start_time and max stop_time
start_time, stop_time = bundle_db.get_roll_up_time_from_db(suffix)
# Make sure start/stop time exists in db.
if start_time is None:
raise ValueError("Start time is not stored in FitsProduct table.")
if stop_time is None:
raise ValueError("Stop time is not stored in FitsProduct table.")
start_stop_times = {
"start_date_time": start_time,
"stop_date_time": stop_time,
}
time_coordinates_node = get_time_coordinates(start_stop_times)
# Dictionary used for primary result summary
primary_result_dict: Dict[str, Any] = {}
# Check if it's raw or calibrated image, we will update this later
processing_level = get_processing_level(
suffix=suffix, instrument_id=instrument.upper()
)
primary_result_dict["processing_level"] = processing_level
p_title = bundle_db.get_fits_product_collection_title(collection_lidvid)
primary_result_dict["description"] = p_title
# Get unique wavelength names for roll-up in data collection
wavelength_range = bundle_db.get_wavelength_range_from_db(suffix)
primary_result_dict["wavelength_range"] = wavelength_range
primary_result_summary_node = primary_result_summary(primary_result_dict)
# Get the list of target identifications nodes for the collection
target_identifications = bundle_db.get_all_target_identification()
target_identification_nodes: List[NodeBuilder] = []
target_identification_nodes = create_target_identification_nodes(
bundle_db, target_identifications, "collection"
)
# Get the investigation node for the collection
investigation_area_name = mk_Investigation_Area_name(proposal_id)
investigation_area_lidvid = mk_Investigation_Area_lidvid(proposal_id)
investigation_area_node = investigation_area(
investigation_area_name, investigation_area_lidvid, "collection"
)
# Get the observing system node for the collection
observing_system_node = observing_system(instrument)
context_node = [
make_collection_context_node(
time_coordinates_node,
primary_result_summary_node,
investigation_area_node,
observing_system_node,
target_identification_nodes,
)
]
# document reference list only exists in data collection
reference_list_node = [
make_document_reference_list([instrument], "collection")
]
try:
label = (
make_label(
{
"collection_lid": collection_lid,
"collection_vid": collection_vid,
"record_count": record_count,
"title": title,
"mod_date": mod_date,
"proposal_id": str(proposal_id),
"Citation_Information": make_citation_information(info),
"inventory_name": inventory_name,
"Context_Area": combine_nodes_into_fragment(context_node),
"collection_type": collection_type,
"Reference_List": combine_nodes_into_fragment(reference_list_node),
}
)
.toxml()
.encode()
)
except Exception as e:
raise LabelError(collection_lidvid) from e
return pretty_and_verify(label, verify)