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

pkg/pgsql/extensions_test.go

@@ -0,0 +1,165 @@
+package pgsql
+
+import (
+	"reflect"
+	"strings"
+	"testing"
+)
+
+func TestExtensionRegistryConsistency(t *testing.T) {
+	for name, ext := range postgresExtensions {
+		if name != ext.Name {
+			t.Errorf("extension registered as %q has Name %q", name, ext.Name)
+		}
+		if name != strings.ToLower(name) {
+			t.Errorf("extension %q must be registered lowercase", name)
+		}
+		if ext.Description == "" || ext.Category == "" {
+			t.Errorf("extension %q is missing a category or description", name)
+		}
+		for _, dependency := range ext.Requires {
+			if !IsKnownExtension(dependency) {
+				t.Errorf("extension %q requires unregistered extension %q", name, dependency)
+			}
+		}
+	}
+}
+
+// Every extension named by a type in the type registry must itself be registered,
+// otherwise a column type would ask for a CREATE EXTENSION nothing knows how to order.
+func TestTypeExtensionsAreRegistered(t *testing.T) {
+	for typeName, spec := range postgresBaseTypes {
+		if spec.Extension == "" {
+			continue
+		}
+		if !IsKnownExtension(spec.Extension) {
+			t.Errorf("type %q declares unregistered extension %q", typeName, spec.Extension)
+		}
+	}
+}
+
+func TestIndexMethodExtension(t *testing.T) {
+	tests := map[string]string{
+		"hnsw":     "vector",
+		"ivfflat":  "vector",
+		"HNSW":     "vector",
+		"vchordrq": "vchord",
+		"vchordg":  "vchord",
+		"bm25":     "pg_search",
+		"btree":    "",
+		"gin":      "",
+		"":         "",
+	}
+
+	for method, want := range tests {
+		if got := IndexMethodExtension(method); got != want {
+			t.Errorf("IndexMethodExtension(%q) = %q, want %q", method, got, want)
+		}
+	}
+}
+
+func TestOperatorClassExtension(t *testing.T) {
+	tests := map[string]string{
+		"gin_trgm_ops":         "pg_trgm",
+		"gist_trgm_ops":        "pg_trgm",
+		"vector_cosine_ops":    "vector",
+		"halfvec_l2_ops":       "vector",
+		"gist_ltree_ops":       "ltree",
+		"gist_geometry_ops_2d": "postgis",
+		"jsonb_path_ops":       "",
+		"array_ops":            "",
+		"":                     "",
+	}
+
+	for opClass, want := range tests {
+		if got := OperatorClassExtension(opClass); got != want {
+			t.Errorf("OperatorClassExtension(%q) = %q, want %q", opClass, got, want)
+		}
+	}
+}
+
+func TestExtensionsForExpression(t *testing.T) {
+	tests := []struct {
+		name       string
+		expression string
+		want       []string
+	}{
+		{"empty", "", nil},
+		{"no functions", "status = 'active'", nil},
+		{"builtin only", "now()", nil},
+		{"uuid-ossp default", "uuid_generate_v4()", []string{"uuid-ossp"}},
+		{"gen_random_uuid is builtin", "gen_random_uuid()", nil},
+		{"pgcrypto", "crypt(password, gen_salt('bf'))", []string{"pgcrypto"}},
+		{"postgis prefix", "ST_Area(geom) > 0", []string{"postgis"}},
+		{"paradedb prefix", "paradedb.snippet(body)", []string{"pg_search"}},
+		{"jsonschema", "json_matches_schema('{}', payload)", []string{"pg_jsonschema"}},
+		{"whitespace before paren", "unaccent ('crème')", []string{"unaccent"}},
+		{"multiple sorted", "ST_X(geom) = levenshtein(a, b)::float", []string{"fuzzystrmatch", "postgis"}},
+		{"column named like function", "similarity_score > 0.5", nil},
+		{"numeric prefix ignored", "2(3)", nil},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := ExtensionsForExpression(tt.expression); !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("ExtensionsForExpression(%q) = %v, want %v", tt.expression, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestSortExtensions(t *testing.T) {
+	tests := []struct {
+		name  string
+		input []string
+		want  []string
+	}{
+		{"empty", nil, nil},
+		{"alphabetical", []string{"pg_trgm", "citext"}, []string{"citext", "pg_trgm"}},
+		{"deduplicated", []string{"vector", "vector", " VECTOR "}, []string{"vector"}},
+		{"dependency first", []string{"vchord", "vector"}, []string{"vector", "vchord"}},
+		{
+			"postgis dependants",
+			[]string{"postgis_topology", "pgrouting", "postgis"},
+			[]string{"postgis", "pgrouting", "postgis_topology"},
+		},
+		{"dependency not requested", []string{"vchord"}, []string{"vchord"}},
+		{"unknown names kept", []string{"zzz_custom", "citext"}, []string{"citext", "zzz_custom"}},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := SortExtensions(tt.input); !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("SortExtensions(%v) = %v, want %v", tt.input, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestQuoteExtensionName(t *testing.T) {
+	tests := map[string]string{
+		"vector":    "vector",
+		"pg_trgm":   "pg_trgm",
+		"uuid-ossp": `"uuid-ossp"`,
+		"PostGIS":   `"PostGIS"`,
+		"":          "",
+	}
+
+	for name, want := range tests {
+		if got := QuoteExtensionName(name); got != want {
+			t.Errorf("QuoteExtensionName(%q) = %q, want %q", name, got, want)
+		}
+	}
+}
+
+func TestExtensionDependencies(t *testing.T) {
+	if got := ExtensionDependencies("vchord"); !reflect.DeepEqual(got, []string{"vector"}) {
+		t.Errorf("ExtensionDependencies(vchord) = %v, want [vector]", got)
+	}
+	if got := ExtensionDependencies("citext"); got != nil {
+		t.Errorf("ExtensionDependencies(citext) = %v, want nil", got)
+	}
+	if got := ExtensionDependencies("not_an_extension"); got != nil {
+		t.Errorf("ExtensionDependencies(not_an_extension) = %v, want nil", got)
+	}
+}