feat(pgsql): support vector and PostGIS indexes with extensions

* Add handling for pgvector and PostGIS extensions in migration scripts * Implement operator class and storage parameters for vector indexes * Update tests to validate new index behaviors and extension creation
2026-08-29 20:39:57 +02:00
parent 16af529120
commit ab3c9217df
19 changed files with 2472 additions and 94 deletions
@@ -392,3 +392,101 @@ func BenchmarkReader_ReadDatabase(b *testing.B) {
 		}
 	}
 }
+
+func TestParseIndexDefinition_ExtensionIndexes(t *testing.T) {
+	reader := &Reader{}
+
+	tests := []struct {
+		name        string
+		indexDef    string
+		wantType    string
+		wantColumns []string
+		wantComment string
+	}{
+		{
+			name:        "hnsw vector index with storage parameters",
+			indexDef:    "CREATE INDEX idx_docs_embedding ON public.docs USING hnsw (embedding vector_cosine_ops) WITH (m='16', ef_construction='64')",
+			wantType:    "hnsw",
+			wantColumns: []string{"embedding"},
+			wantComment: "opclass=vector_cosine_ops; with (m=16, ef_construction=64)",
+		},
+		{
+			name:        "ivfflat vector index",
+			indexDef:    "CREATE INDEX idx_docs_embedding ON public.docs USING ivfflat (embedding vector_l2_ops) WITH (lists='100')",
+			wantType:    "ivfflat",
+			wantColumns: []string{"embedding"},
+			wantComment: "opclass=vector_l2_ops; with (lists=100)",
+		},
+		{
+			name:        "gist geometry index with default operator class",
+			indexDef:    "CREATE INDEX idx_places_geom ON public.places USING gist (geom)",
+			wantType:    "gist",
+			wantColumns: []string{"geom"},
+			wantComment: "",
+		},
+		{
+			name:        "gist geometry index with explicit operator class",
+			indexDef:    "CREATE INDEX idx_places_geom ON public.places USING gist (geom gist_geometry_ops_nd)",
+			wantType:    "gist",
+			wantColumns: []string{"geom"},
+			wantComment: "opclass=gist_geometry_ops_nd",
+		},
+		{
+			name:        "btree ordering modifiers are not operator classes",
+			indexDef:    "CREATE INDEX idx_users_created ON public.users USING btree (created_at DESC NULLS LAST)",
+			wantType:    "btree",
+			wantColumns: []string{"created_at"},
+			wantComment: "",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			index, err := reader.parseIndexDefinition("idx", "tbl", "public", tt.indexDef)
+			if err != nil {
+				t.Fatalf("parseIndexDefinition() error = %v", err)
+			}
+
+			if index.Type != tt.wantType {
+				t.Errorf("Type = %q, want %q", index.Type, tt.wantType)
+			}
+			if len(index.Columns) != len(tt.wantColumns) {
+				t.Fatalf("Columns = %v, want %v", index.Columns, tt.wantColumns)
+			}
+			for i, col := range tt.wantColumns {
+				if index.Columns[i] != col {
+					t.Errorf("Columns[%d] = %q, want %q", i, index.Columns[i], col)
+				}
+			}
+			if index.Comment != tt.wantComment {
+				t.Errorf("Comment = %q, want %q", index.Comment, tt.wantComment)
+			}
+		})
+	}
+}
+
+func TestMapDataType_ExtensionTypesPreserveModifiers(t *testing.T) {
+	reader := &Reader{}
+
+	tests := []struct {
+		name          string
+		pgType        string
+		udtName       string
+		formattedType string
+		want          string
+	}{
+		{"postgis geometry", "USER-DEFINED", "geometry", "geometry(Point,4326)", "geometry(Point,4326)"},
+		{"postgis geography", "USER-DEFINED", "geography", "geography(Point,4326)", "geography(Point,4326)"},
+		{"postgis geometry without modifier", "USER-DEFINED", "geometry", "geometry", "geometry"},
+		{"pgvector halfvec", "USER-DEFINED", "halfvec", "halfvec(768)", "halfvec(768)"},
+		{"postgis geometry array", "ARRAY", "_geometry", "geometry(Point,4326)[]", "geometry(Point,4326)[]"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := reader.mapDataType(tt.pgType, tt.udtName, tt.formattedType, false); got != tt.want {
+				t.Errorf("mapDataType() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}