lee/graphify
1
0
Fork 0
mirror of https://github.com/safishamsi/graphify.git synced 2026-09-23 14:05:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(dedup): deterministic collision survivor + bare-file definer (#1851 followup)

Browse Source 
Two tweaks on top of @bchan84x's #1852:

1. The definer heuristic decided the survivor pairwise, so when several
   same-file nodes co-defined one ID the surviving label still depended on
   arrival order (the exact 3-node case #1851 reports). Choose the survivor
   by a total order (definer first, then shorter/canonical label, then
   lexically) via a min over _collision_rank, so it is order-independent.
   Direction preserves #1504 (lexically-first source path wins).

2. _defines_id now also recognizes a bare file-level node whose id is
   exactly the slugified path (nid == prefix), not only <path>_<entity>.

Adds an order-independence test over all 6 permutations of definer +
same-file relabel + cross-file reference, and a bare-file-node test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
safishamsi
2026-07-14 13:51:42 +01:00
co-authored by Claude Opus 4.8
parent 70bc9ca7b2
commit fd54f0ef0b
3 changed files with 59 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
graphify/dedup.py
+28 -2
View File
@@ -218,7 +218,30 @@ def _defines_id(node: dict) -> bool:
source_file = node.get("source_file") or ""
if not nid or not source_file:
return False
return any(nid.startswith(f"{prefix}_") for prefix in _id_prefixes(source_file))
# `nid == prefix` covers a bare file-level node whose id is exactly the
# slugified path with no `_entity` suffix (a semantic node for the file
# itself); `startswith(prefix + "_")` covers the usual `<path>_<entity>` id.
return any(nid == prefix or nid.startswith(f"{prefix}_")
for prefix in _id_prefixes(source_file))
def _collision_rank(node: dict) -> tuple:
"""A total order for choosing the survivor of an ID collision, independent of
the order the colliding nodes arrive in.
The winner is the node with the SMALLEST rank. A node whose ``source_file``
defines the ID always outranks a mere reference; among equally-(non-)defining
nodes it prefers the shorter, more canonical label over a longer qualified
variant, then breaks any remaining tie lexically on label and then source_file
(so the lexically-first path wins) — fully deterministic regardless of order.
"""
label = node.get("label") or ""
return (
not _defines_id(node), # definers (False) sort before references (True)
len(label), # shorter, more canonical label first
label, # lexical tiebreak
node.get("source_file") or "", # lexically-first source path wins
)
def _report_id_collision(nid: str, survivor: dict, losers: list[dict]) -> None:
@@ -304,7 +327,10 @@ def deduplicate_entities(
incumbent = seen_ids.get(nid)
if incumbent is None:
seen_ids[nid] = node
elif _defines_id(node) and not _defines_id(incumbent):
elif _collision_rank(node) < _collision_rank(incumbent):
# Smallest-ranked node wins; the min over a total order is independent
# of the order nodes arrive in, so the survivor no longer depends on
# chunk ordering (#1851).
seen_ids[nid] = node
dropped[nid].append(incumbent)
else: