gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Manually reformatted files

Browse Source
This commit is contained in:
Sanketh Kumar
2024-10-25 13:32:25 +05:30
parent 2401e21ef2
commit a157e8e0a2
11 changed files with 175 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
lightrag/utils.py
View File

@@ -185,6 +185,7 @@ def save_data_to_file(data, file_name):
with open(file_name, "w", encoding="utf-8") as f:
json.dump(data, f, ensure_ascii=False, indent=4)
def xml_to_json(xml_file):
try:
tree = ET.parse(xml_file)
@@ -194,31 +195,42 @@ def xml_to_json(xml_file):
print(f"Root element: {root.tag}")
print(f"Root attributes: {root.attrib}")
data = {
"nodes": [],
"edges": []
}
data = {"nodes": [], "edges": []}
# Use namespace
namespace = {'': 'http://graphml.graphdrawing.org/xmlns'}
namespace = {"": "http://graphml.graphdrawing.org/xmlns"}
for node in root.findall('.//node', namespace):
for node in root.findall(".//node", namespace):
node_data = {
"id": node.get('id').strip('"'),
"entity_type": node.find("./data[@key='d0']", namespace).text.strip('"') if node.find("./data[@key='d0']", namespace) is not None else "",
"description": node.find("./data[@key='d1']", namespace).text if node.find("./data[@key='d1']", namespace) is not None else "",
"source_id": node.find("./data[@key='d2']", namespace).text if node.find("./data[@key='d2']", namespace) is not None else ""
"id": node.get("id").strip('"'),
"entity_type": node.find("./data[@key='d0']", namespace).text.strip('"')
if node.find("./data[@key='d0']", namespace) is not None
else "",
"description": node.find("./data[@key='d1']", namespace).text
if node.find("./data[@key='d1']", namespace) is not None
else "",
"source_id": node.find("./data[@key='d2']", namespace).text
if node.find("./data[@key='d2']", namespace) is not None
else "",
}
data["nodes"].append(node_data)
for edge in root.findall('.//edge', namespace):
for edge in root.findall(".//edge", namespace):
edge_data = {
"source": edge.get('source').strip('"'),
"target": edge.get('target').strip('"'),
"weight": float(edge.find("./data[@key='d3']", namespace).text) if edge.find("./data[@key='d3']", namespace) is not None else 0.0,
"description": edge.find("./data[@key='d4']", namespace).text if edge.find("./data[@key='d4']", namespace) is not None else "",
"keywords": edge.find("./data[@key='d5']", namespace).text if edge.find("./data[@key='d5']", namespace) is not None else "",
"source_id": edge.find("./data[@key='d6']", namespace).text if edge.find("./data[@key='d6']", namespace) is not None else ""
"source": edge.get("source").strip('"'),
"target": edge.get("target").strip('"'),
"weight": float(edge.find("./data[@key='d3']", namespace).text)
if edge.find("./data[@key='d3']", namespace) is not None
else 0.0,
"description": edge.find("./data[@key='d4']", namespace).text
if edge.find("./data[@key='d4']", namespace) is not None
else "",
"keywords": edge.find("./data[@key='d5']", namespace).text
if edge.find("./data[@key='d5']", namespace) is not None
else "",
"source_id": edge.find("./data[@key='d6']", namespace).text
if edge.find("./data[@key='d6']", namespace) is not None
else "",
}
data["edges"].append(edge_data)