From 59b6a8265f51961e38c1c50a949385f25d2eab17 Mon Sep 17 00:00:00 2001
From: pyr0ball <pyroballpcs@gmail.com>
Date: Mon, 30 Mar 2026 22:46:53 -0700
Subject: [PATCH] feat: data pipeline -- FlavorGraph molecule index builder

---
 scripts/pipeline/build_flavorgraph_index.py   | 79 +++++++++++++++++++
 .../pipeline/test_build_flavorgraph_index.py  | 18 +++++
 2 files changed, 97 insertions(+)
 create mode 100644 scripts/pipeline/build_flavorgraph_index.py
 create mode 100644 tests/pipeline/test_build_flavorgraph_index.py

diff --git a/scripts/pipeline/build_flavorgraph_index.py b/scripts/pipeline/build_flavorgraph_index.py
new file mode 100644
index 0000000..d831f85
--- /dev/null
+++ b/scripts/pipeline/build_flavorgraph_index.py
@@ -0,0 +1,79 @@
+"""
+Import FlavorGraph compound->ingredient map into flavor_molecules table.
+
+FlavorGraph GitHub: https://github.com/lamypark/FlavorGraph
+Download: git clone https://github.com/lamypark/FlavorGraph /tmp/flavorgraph
+
+Usage:
+    conda run -n job-seeker python scripts/pipeline/build_flavorgraph_index.py \
+        --db /path/to/kiwi.db \
+        --graph-json /tmp/flavorgraph/data/graph.json
+"""
+from __future__ import annotations
+import argparse
+import json
+import sqlite3
+from collections import defaultdict
+from pathlib import Path
+
+
+def parse_ingredient_nodes(graph: dict) -> dict[str, list[str]]:
+    """Return {ingredient_name: [compound_id, ...]} from a FlavorGraph JSON."""
+    ingredient_compounds: dict[str, list[str]] = defaultdict(list)
+    ingredient_ids: dict[str, str] = {}   # node_id -> ingredient_name
+
+    for node in graph.get("nodes", []):
+        if node.get("type") == "ingredient":
+            ingredient_ids[node["id"]] = node["name"].lower()
+
+    for link in graph.get("links", []):
+        src, tgt = link.get("source", ""), link.get("target", "")
+        if src in ingredient_ids:
+            ingredient_compounds[ingredient_ids[src]].append(tgt)
+        if tgt in ingredient_ids:
+            ingredient_compounds[ingredient_ids[tgt]].append(src)
+
+    return dict(ingredient_compounds)
+
+
+def build(db_path: Path, graph_json_path: Path) -> None:
+    graph = json.loads(graph_json_path.read_text())
+    ingredient_map = parse_ingredient_nodes(graph)
+
+    compound_ingredients: dict[str, list[str]] = defaultdict(list)
+    compound_names: dict[str, str] = {}
+
+    for node in graph.get("nodes", []):
+        if node.get("type") == "compound":
+            compound_names[node["id"]] = node["name"]
+
+    for ingredient, compounds in ingredient_map.items():
+        for cid in compounds:
+            compound_ingredients[cid].append(ingredient)
+
+    conn = sqlite3.connect(db_path)
+
+    for ingredient, compounds in ingredient_map.items():
+        conn.execute("""
+            UPDATE ingredient_profiles
+            SET flavor_molecule_ids = ?
+            WHERE name = ?
+        """, (json.dumps(compounds), ingredient))
+
+    for cid, ingredients in compound_ingredients.items():
+        conn.execute("""
+            INSERT OR IGNORE INTO flavor_molecules (compound_id, compound_name, ingredient_names)
+            VALUES (?, ?, ?)
+        """, (cid, compound_names.get(cid, cid), json.dumps(ingredients)))
+
+    conn.commit()
+    conn.close()
+    print(f"Indexed {len(ingredient_map)} ingredients, {len(compound_ingredients)} compounds")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--db",         required=True, type=Path)
+    parser.add_argument("--graph-json", required=True, type=Path)
+    args = parser.parse_args()
+    build(args.db, args.graph_json)
diff --git a/tests/pipeline/test_build_flavorgraph_index.py b/tests/pipeline/test_build_flavorgraph_index.py
new file mode 100644
index 0000000..febf381
--- /dev/null
+++ b/tests/pipeline/test_build_flavorgraph_index.py
@@ -0,0 +1,18 @@
+def test_parse_flavorgraph_node():
+    from scripts.pipeline.build_flavorgraph_index import parse_ingredient_nodes
+    sample = {
+        "nodes": [
+            {"id": "I_beef", "type": "ingredient", "name": "beef"},
+            {"id": "C_pyrazine", "type": "compound", "name": "pyrazine"},
+            {"id": "I_mushroom", "type": "ingredient", "name": "mushroom"},
+        ],
+        "links": [
+            {"source": "I_beef",    "target": "C_pyrazine"},
+            {"source": "I_mushroom","target": "C_pyrazine"},
+        ]
+    }
+    result = parse_ingredient_nodes(sample)
+    assert "beef" in result
+    assert "C_pyrazine" in result["beef"]
+    assert "mushroom" in result
+    assert "C_pyrazine" in result["mushroom"]