From 6a06b652cce0963e0709dedf1993d0b632b626ee Mon Sep 17 00:00:00 2001
From: akshitj11 <126861164+akshitj11@users.noreply.github.com>
Date: Mon, 24 Aug 2026 14:06:55 +0100
Subject: [PATCH] fix(sql): extract CREATE TABLE inside BEGIN/COMMIT blocks
 (#2953)

DDL wrapped in a transaction parses under a `transaction` node the statement walker never
descended into, so a CREATE TABLE inside BEGIN/COMMIT was never extracted while a top-level
one was. Recurse into transaction blocks; nested statements get the same handling, no
double-emit.
---
 graphify/extractors/sql.py            |  4 ++++
 tests/fixtures/sample_transaction.sql | 11 +++++++++++
 tests/test_multilang.py               | 19 +++++++++++++++++++
 3 files changed, 34 insertions(+)
 create mode 100644 tests/fixtures/sample_transaction.sql

diff --git a/graphify/extractors/sql.py b/graphify/extractors/sql.py
index a5dc18c3..162c73fb 100644
--- a/graphify/extractors/sql.py
+++ b/graphify/extractors/sql.py
@@ -398,6 +398,10 @@ def extract_sql(path: Path, content: str | bytes | None = None) -> dict:
         if stmt.type == "statement":
             for child in stmt.children:
                 walk(child)
+        elif stmt.type == "transaction":
+            # BEGIN; ... COMMIT; wraps DDL in a transaction node whose children
+            # are statement nodes, not direct create_table nodes (#2953).
+            walk(stmt)
         elif stmt.type in ("fb_proc_or_trigger", "set_term", "declare_external_function", "ERROR"):
             walk(stmt)
 
diff --git a/tests/fixtures/sample_transaction.sql b/tests/fixtures/sample_transaction.sql
new file mode 100644
index 00000000..291ff6e9
--- /dev/null
+++ b/tests/fixtures/sample_transaction.sql
@@ -0,0 +1,11 @@
+CREATE TABLE alfa (id integer PRIMARY KEY);
+
+BEGIN;
+
+CREATE TABLE gamma (id integer PRIMARY KEY);
+CREATE TABLE delta (
+  id integer PRIMARY KEY,
+  alfa_id integer REFERENCES alfa(id)
+);
+
+COMMIT;
diff --git a/tests/test_multilang.py b/tests/test_multilang.py
index db7c0d90..7ff96d3f 100644
--- a/tests/test_multilang.py
+++ b/tests/test_multilang.py
@@ -461,6 +461,25 @@ def test_sql_finds_tables():
     assert any("users" in l for l in labels)
     assert any("organizations" in l for l in labels)
 
+
+def test_sql_create_table_inside_transaction_block():
+    """#2953: DDL wrapped in BEGIN; ... COMMIT; must emit table nodes."""
+    r = _extract_sql_or_skip("sample_transaction.sql")
+    labels = [n["label"] for n in r["nodes"]]
+    assert any("alfa" in l for l in labels)
+    assert any("gamma" in l for l in labels)
+    assert any("delta" in l for l in labels)
+    refs = [
+        (e["source"], e["target"])
+        for e in r["edges"]
+        if e["relation"] == "references"
+    ]
+    node_by_id = {n["id"]: n["label"] for n in r["nodes"]}
+    assert any(
+        "delta" in node_by_id.get(s, "") and "alfa" in node_by_id.get(t, "")
+        for s, t in refs
+    )
+
 def test_sql_finds_view():
     r = _extract_sql_or_skip()
     labels = [n["label"] for n in r["nodes"]]