swapnilpaliwal-sd · Oct 3, 2026 · Oct 3, 2026
@@ -1517,7 +1517,8 @@ class Impact:
                     L = self.code(r['file']); text = L[r['line'] - 1] if r['line'] <= len(L) else ''
                     for qn in re.findall(rf'([A-Za-z_$][\w$]*)\s*\.\s*{re.escape(r["name"])}\b', text): quals.append((r['file'], r['line'], r['name'], qn))
         W('ref', refs); W('qualifier', sorted(set(quals)))
-        W('registration', ax_registration.registrations(g.q, g.site_file))
+        regs = ax_registration.registrations(g.q, g.site_file)      # computed once: reg_key_fact below reads it too
+        W('registration', regs)
         trs = []; trf = set()
         # a reference on a module-level type alias's own lines belongs to the alias, not the module (#784)
         import graph_sql
@@ -1599,7 +1600,7 @@ class Impact:
         regk = []                                        # `rd` and not `decl`: `decl` is the dec_literal list above
         for rd, _f, _l, kind, key, _why in (ax_registration.decoration_keys(g.q, g.site_file)
                                             + ax_registration.value_route_registrations(g.q, g.site_file)
-                                            + ax_registration.registrations(g.q, g.site_file) + tregs):
+                                            + regs + tregs):
             if rd in g.sym and key: regk.append((rd, kind, key))
         W('reg_key_fact', sorted(set(regk)))
         # the callables in test files: a test that publishes a handler table's key drives the handler, and is not

@@ -702,6 +702,9 @@ CREATE INDEX IF NOT EXISTS ce_callee ON call_edges(callee_method_id); CREATE IND
 -- lookups by id and by file + line: without them each per-site or per-test query scans the whole table
 CREATE INDEX IF NOT EXISTS symbols_id ON symbols(id); CREATE INDEX IF NOT EXISTS refs_file_line ON refs(file, line);
 CREATE INDEX IF NOT EXISTS literals_file_line ON literals(file, line);
+-- the fields a caller reads: via_base_rows asks per single-target call site, and without the index each ask
+-- scanned the whole table (65,797 rows × 5,162 sites on an 8,619-file repository = 24 s of a 171 s warm → 1.4 s)
+CREATE INDEX IF NOT EXISTS fa_caller ON field_access(caller_id);
 -- who calls a method: one row per (site, target), with the engine's tier. caller_id is symbols.id: a
 -- Java call written in a field initializer has the TYPE as its caller, and that row is kept, not dropped
 CREATE VIEW callers AS

@@ -969,10 +969,16 @@ class G:
         unfoll = [(r['lib'], r['n']) for r in rows if r['from_site']][:cap]
         return named, unfoll
     def site_file(self, raw):
-        """a call site's file as the repo sees it: Java bundles store absolute paths; the index's paths table maps them"""
-        if self.has('paths'):
-            r = self.q("SELECT rel FROM paths WHERE raw = ?", raw)
-            if r: return r[0]['rel']
+        """a call site's file as the repo sees it: Java bundles store absolute paths; the index's paths table maps them.
+        The map is read ONCE PER GRAPH, not once per row: this ran a query per call (one `has`, one lookup), and the
+        facts export calls it for every call edge — 319k edges on an 8,619-file repository made 638k round-trips
+        through sqlite, which was most of the export's time (reg_key_fact 36 s, calls 34 s, registration 31 s,
+        via_base 25 s of a 171 s warm)."""
+        m = getattr(self, '_site_files', None)
+        if m is None:
+            m = self._site_files = {r['raw']: r['rel'] for r in self.q("SELECT raw, rel FROM paths")} if self.has('paths') else {}
+        got = m.get(raw)
+        if got is not None: return got
         return os.path.relpath(raw, self.repo).replace(os.sep, '/') if os.path.isabs(raw) and raw.startswith(self.repo) else raw
 
     # ── facts: exported once per graph, reused while graph.sqlite is unchanged ───────────────────────────────