Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
66224d9
convert dict to string type
hyi Feb 6, 2026
ecb3bac
attempt to fix input issues
hyi Feb 7, 2026
3f1b0f9
fixed the ingest data issue
hyi Feb 7, 2026
e2a5bd4
need to handle sources list of dicts for memgraph ingest after all
hyi Feb 9, 2026
75379c0
added node name and id indexes in memgraph cypher dump
hyi Feb 10, 2026
0b5a00a
breaking one single memgraph cypher output into 3 to prevent conflict…
hyi Feb 10, 2026
c27cc09
breaking one single memgraph cypher output into 3 to prevent conflict…
hyi Feb 10, 2026
6b4c18d
standardized memgraph output cypher file names
hyi Feb 10, 2026
92d4e97
further standardization of memgraph cypher output file names
hyi Feb 10, 2026
60d22c0
updated memgraph cypher dump to work through some issues
hyi Feb 11, 2026
de1e64c
updated memgraph data dump code to dump csvs rather than cyphers for …
hyi Feb 14, 2026
bc33fa0
need to pass in output_target when output memgraph edge csv files
hyi Feb 14, 2026
2f87674
reuse already generated edge files for memgraph dump
hyi Feb 14, 2026
7c422f7
fix edge manifest ext name issue
hyi Feb 14, 2026
b65c8ca
revert node csv output back to cypher output
hyi Feb 16, 2026
4cf2f75
need to backtick property names in the node dump cypher file to fix t…
hyi Mar 4, 2026
f85eb29
replace node cypher dump with node csv dump for memgraph ingestion
hyi Mar 6, 2026
e4056a0
fixing split edges files bug, always raising exceptions on fail
EvanDietzMorris Mar 6, 2026
fe7c180
write temp split files to output dir instead of input file dir
EvanDietzMorris Mar 6, 2026
5e6bb72
Merge pull request #376 from RobokopU24/memgraph-split-files
EvanDietzMorris Mar 6, 2026
690a3b7
added property types in headers for memgraph csv dumps
hyi Mar 13, 2026
5e96237
Merge branch 'master' into neo4j-sources-issue
EvanDietzMorris Mar 31, 2026
278e4e1
remove split edge json files after csv conversion
EvanDietzMorris Mar 31, 2026
735766c
return False instead of raising exception to match previous pattern
EvanDietzMorris Mar 31, 2026
1c58adf
clean up weird logger usage and remove temp files after neo4j dump
EvanDietzMorris Mar 31, 2026
6420d46
improving checks for existing memgraph dump files
EvanDietzMorris Mar 31, 2026
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
13 changes: 5 additions & 8 deletions orion/build_manager.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
from orion.kgx_file_merger import KGXFileMerger, DONT_MERGE
from orion.kgx_validation import validate_graph
from orion.neo4j_tools import create_neo4j_dump
from orion.memgraph_tools import create_memgraph_dump
from orion.kgxmodel import GraphSpec, SubGraphSource, DataSource
from orion.normalization import NORMALIZATION_CODE_VERSION, NormalizationScheme
from orion.metadata import Metadata, GraphMetadata, SourceMetadata
Expand Down Expand Up @@ -185,8 +186,7 @@ def build_graph(self, graph_spec: GraphSpec):
graph_id=graph_id,
graph_version=graph_version,
node_property_ignore_list=node_property_ignore_list,
edge_property_ignore_list=edge_property_ignore_list,
logger=self.logger)
edge_property_ignore_list=edge_property_ignore_list)
if dump_success:
graph_metadata.set_dump(dump_type="neo4j_redundant",
dump_url=f'{graph_output_url}graph_{graph_version}_redundant.db.dump')
Expand All @@ -208,8 +208,7 @@ def build_graph(self, graph_spec: GraphSpec):
graph_id=graph_id,
graph_version=graph_version,
node_property_ignore_list=node_property_ignore_list,
edge_property_ignore_list=edge_property_ignore_list,
logger=self.logger)
edge_property_ignore_list=edge_property_ignore_list)
if dump_success:
graph_metadata.set_dump(dump_type="neo4j_collapsed_qualifiers",
dump_url=f'{graph_output_url}graph_{graph_version}'
Expand All @@ -223,8 +222,7 @@ def build_graph(self, graph_spec: GraphSpec):
graph_id=graph_id,
graph_version=graph_version,
node_property_ignore_list=node_property_ignore_list,
edge_property_ignore_list=edge_property_ignore_list,
logger=self.logger)
edge_property_ignore_list=edge_property_ignore_list)
if dump_success:
graph_metadata.set_dump(dump_type="neo4j",
dump_url=f'{graph_output_url}graph_{graph_version}.db.dump')
Expand All @@ -237,8 +235,7 @@ def build_graph(self, graph_spec: GraphSpec):
graph_id=graph_id,
graph_version=graph_version,
node_property_ignore_list=node_property_ignore_list,
edge_property_ignore_list=edge_property_ignore_list,
logger=self.logger)
edge_property_ignore_list=edge_property_ignore_list)
if dump_success:
graph_metadata.set_dump(dump_type="memgraph",
dump_url=f'{graph_output_url}memgraph_{graph_version}.cypher')
Expand Down
9 changes: 2 additions & 7 deletions orion/cli/memgraph_dump.py
Original file line number Diff line number Diff line change
@@ -1,14 +1,9 @@
import argparse
import os
from orion.utils import LoggingUtil
from orion.memgraph_tools import create_memgraph_dump

def main():
logger = LoggingUtil.init_logging("ORION.cli.memgraph_dump",
line_format='medium',
log_file_path=os.environ['ORION_LOGS'])

ap = argparse.ArgumentParser(description='')
ap = argparse.ArgumentParser(description='Create memgraph CSV import files from KGX jsonl files.')
ap.add_argument('nodes_filepath')
ap.add_argument('edges_filepath')
ap.add_argument('output_directory')
Expand All @@ -18,7 +13,7 @@ def main():
e_filepath = args['edges_filepath']
output_directory = args['output_directory']

create_memgraph_dump(n_filepath, e_filepath, output_directory, logger=logger)
create_memgraph_dump(n_filepath, e_filepath, output_directory)


if __name__ == '__main__':
Expand Down
10 changes: 2 additions & 8 deletions orion/cli/neo4j_dump.py
Original file line number Diff line number Diff line change
@@ -1,14 +1,9 @@
import argparse
import os
from orion.utils import LoggingUtil
from orion.neo4j_tools import create_neo4j_dump

def main():
logger = LoggingUtil.init_logging("ORION.cli.neo4j_dump",
line_format='medium',
log_file_path=os.environ['ORION_LOGS'])

ap = argparse.ArgumentParser(description='')
ap = argparse.ArgumentParser(description='Create a neo4j dump from KGX jsonl files.')
ap.add_argument('nodes_filepath')
ap.add_argument('edges_filepath')
ap.add_argument('output_directory')
Expand All @@ -20,8 +15,7 @@ def main():

create_neo4j_dump(nodes_filepath=n_filepath,
edges_filepath=e_filepath,
output_directory=output_directory,
logger=logger)
output_directory=output_directory)


if __name__ == '__main__':
Expand Down
Loading
Loading