Spaces:
Build error
fix(api+graph+pipeline): M-04+M-05+M-08+M-09 -- misc medium fixes
Browse filesM-04: /debug/env endpoint was publicly accessible with no auth gate.
It revealed NEO4J_URI prefix and credential configuration status.
Fix: added same DEBUG_MODE env-var gate as /debug/neo4j.
M-05: Wikidata enrichment used exact name match (=) -- any difference
in spacing, middle name, honorific, or transliteration caused a silent
miss. With Indian names this is extremely common.
Fix: changed to CONTAINS match in both directions for fuzzy matching.
M-08: --parallel flag had action='store_true', default=True making it
always True whether passed or not. The flag had zero effect. Confusing
for operators who expected --parallel to mean something.
Fix: removed --parallel; --sequential now inverts the default.
M-09: startNode(rel).id and endNode(rel).id in Cypher can return null
if a node has no 'id' property. This created edges with null source/target
silently corrupting graph output.
Fix: added isinstance str check to filter null src/tgt before appending.
- api/main.py +4 -0
- api/routes/graph.py +4 -2
- graph/loader.py +1 -1
- processing/pipeline.py +4 -2
|
@@ -210,6 +210,10 @@ async def websocket_feed(websocket: WebSocket):
|
|
| 210 |
|
| 211 |
@app.get("/debug/env")
|
| 212 |
def debug_env():
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
return {
|
| 214 |
"neo4j_uri_set": bool(os.getenv("NEO4J_URI")),
|
| 215 |
"neo4j_user_set": bool(os.getenv("NEO4J_USER")),
|
|
|
|
| 210 |
|
| 211 |
@app.get("/debug/env")
|
| 212 |
def debug_env():
|
| 213 |
+
# M-04 FIX: gate behind DEBUG_MODE same as /debug/neo4j
|
| 214 |
+
if os.getenv("DEBUG_MODE", "").lower() not in ("1", "true", "yes"):
|
| 215 |
+
from fastapi import HTTPException as _HE
|
| 216 |
+
raise _HE(status_code=404, detail="Not found")
|
| 217 |
return {
|
| 218 |
"neo4j_uri_set": bool(os.getenv("NEO4J_URI")),
|
| 219 |
"neo4j_user_set": bool(os.getenv("NEO4J_USER")),
|
|
@@ -84,8 +84,10 @@ def get_connections(
|
|
| 84 |
src = rel_step.get("src", "")
|
| 85 |
tgt = rel_step.get("tgt", "")
|
| 86 |
rtype = rel_step.get("type", "RELATED_TO")
|
| 87 |
-
|
| 88 |
-
|
|
|
|
|
|
|
| 89 |
edge_key = (src, tgt, rtype)
|
| 90 |
if edge_key not in _edge_seen:
|
| 91 |
_edge_seen.add(edge_key)
|
|
|
|
| 84 |
src = rel_step.get("src", "")
|
| 85 |
tgt = rel_step.get("tgt", "")
|
| 86 |
rtype = rel_step.get("type", "RELATED_TO")
|
| 87 |
+
# M-09 FIX: startNode/endNode may return null .id if node
|
| 88 |
+
# was created without an id property -- filter those out
|
| 89 |
+
if src and tgt and isinstance(src, str) and isinstance(tgt, str):
|
| 90 |
+
# skip duplicate edges -- depth>1 paths share edges
|
| 91 |
edge_key = (src, tgt, rtype)
|
| 92 |
if edge_key not in _edge_seen:
|
| 93 |
_edge_seen.add(edge_key)
|
|
@@ -912,7 +912,7 @@ class GraphLoader:
|
|
| 912 |
try:
|
| 913 |
result = self._run("""
|
| 914 |
MATCH (p:Politician)
|
| 915 |
-
WHERE toLower(p.name)
|
| 916 |
OR any(a IN coalesce(p.aliases,[]) WHERE toLower(a) = toLower($name))
|
| 917 |
SET p.wikidata_id = coalesce($wikidata_id, p.wikidata_id),
|
| 918 |
p.birth_year = coalesce($birth_year, p.birth_year),
|
|
|
|
| 912 |
try:
|
| 913 |
result = self._run("""
|
| 914 |
MATCH (p:Politician)
|
| 915 |
+
WHERE toLower(p.name) CONTAINS toLower($name) OR toLower($name) CONTAINS toLower(p.name)
|
| 916 |
OR any(a IN coalesce(p.aliases,[]) WHERE toLower(a) = toLower($name))
|
| 917 |
SET p.wikidata_id = coalesce($wikidata_id, p.wikidata_id),
|
| 918 |
p.birth_year = coalesce($birth_year, p.birth_year),
|
|
@@ -420,8 +420,10 @@ class BharatGraphPipeline:
|
|
| 420 |
if __name__ == "__main__":
|
| 421 |
parser = argparse.ArgumentParser(description="BharatGraph Full Pipeline (20 scrapers)")
|
| 422 |
parser.add_argument("--scrapers", type=str, default=None)
|
| 423 |
-
|
| 424 |
-
|
|
|
|
|
|
|
| 425 |
args = parser.parse_args()
|
| 426 |
scrapers = args.scrapers.split(",") if args.scrapers else None
|
| 427 |
parallel = not args.sequential
|
|
|
|
| 420 |
if __name__ == "__main__":
|
| 421 |
parser = argparse.ArgumentParser(description="BharatGraph Full Pipeline (20 scrapers)")
|
| 422 |
parser.add_argument("--scrapers", type=str, default=None)
|
| 423 |
+
# M-08 FIX: --parallel was action=store_true,default=True making it always True
|
| 424 |
+
# --sequential now sets parallel=False, and --parallel is removed
|
| 425 |
+
parser.add_argument("--sequential", action="store_true", default=False,
|
| 426 |
+
help="Run scrapers sequentially (default: parallel)")
|
| 427 |
args = parser.parse_args()
|
| 428 |
scrapers = args.scrapers.split(",") if args.scrapers else None
|
| 429 |
parallel = not args.sequential
|