Page MenuHomeSoftware Heritage

D5244.id18851.diff
No OneTemporary

D5244.id18851.diff

diff --git a/requirements-swh.txt b/requirements-swh.txt
--- a/requirements-swh.txt
+++ b/requirements-swh.txt
@@ -1,4 +1,4 @@
# Add here internal Software Heritage dependencies, one per line.
swh.core[http] >= 0.3
swh.journal
-swh.model
+swh.model >= 1.0.0
diff --git a/swh/dataset/exporters/edges.py b/swh/dataset/exporters/edges.py
--- a/swh/dataset/exporters/edges.py
+++ b/swh/dataset/exporters/edges.py
@@ -13,7 +13,16 @@
from swh.dataset.exporter import ExporterDispatch
from swh.dataset.utils import ZSTFile, remove_pull_requests
-from swh.model.identifiers import origin_identifier, swhid
+from swh.model.hashutil import hash_to_bytes
+from swh.model.identifiers import ExtendedObjectType, ExtendedSWHID, origin_identifier
+
+
+def swhid(object_type, object_id):
+ return str(
+ ExtendedSWHID(
+ object_type=ExtendedObjectType[object_type.upper()], object_id=object_id
+ )
+ )
class GraphEdgesExporter(ExporterDispatch):
@@ -66,11 +75,11 @@
edge_writer.write("{}\n".format(edge_line))
def process_origin(self, origin):
- origin_id = origin_identifier({"url": origin["url"]})
+ origin_id = hash_to_bytes(origin_identifier({"url": origin["url"]}))
self.write_node(("origin", origin_id))
def process_origin_visit_status(self, visit_status):
- origin_id = origin_identifier({"url": visit_status["origin"]})
+ origin_id = hash_to_bytes(origin_identifier({"url": visit_status["origin"]}))
self.write_edge(("origin", origin_id), ("snapshot", visit_status["snapshot"]))
def process_snapshot(self, snapshot):

File Metadata

Mime Type
text/plain
Expires
Thu, Jul 3, 1:35 PM (6 d, 6 h ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3220284

Event Timeline