Files
PgTidy/pkg/format/format_test.go
T
warkanum d4e6102932 feat(format): add PL/pgSQL body formatting and tests
* Implemented formatting for BEGIN...END blocks in PL/pgSQL.
* Added logic to handle indentation and blank lines.
* Introduced tests for broken formatting cases.
2026-06-27 19:10:02 +02:00

151 lines
3.8 KiB
Go

package format
import (
"os"
"path/filepath"
"strings"
"testing"
"github.com/hein/pgtidy/pkg/config"
"github.com/hein/pgtidy/pkg/lexer"
"github.com/hein/pgtidy/pkg/parser"
)
func format(src string) string {
return File(parser.Parse(src), config.Default())
}
func TestFormatHeaderGolden(t *testing.T) {
src := "--select * from dropall('resolvespec_login');\n" +
"create or replace function resolvespec_login(\n" +
"INOUT p_data jsonb, OUT p_success boolean, OUT p_error text)\n" +
"language plpgsql volatile security definer\n" +
"as $$\nbegin end;\n$$;\n"
want := "--select * from dropall('resolvespec_login');\n" +
"CREATE OR REPLACE FUNCTION resolvespec_login(\n" +
" INOUT p_data jsonb\n" +
" ,OUT p_success boolean\n" +
" ,OUT p_error text\n" +
")\n" +
"LANGUAGE plpgsql\n" +
"VOLATILE\n" +
"SECURITY DEFINER\n" +
"AS\n" +
"$$\nbegin end;\n$$;\n"
got := format(src)
if got != want {
t.Errorf("header format mismatch\n--- got ---\n%s\n--- want ---\n%s", got, want)
}
}
func TestIdempotentSmall(t *testing.T) {
src := "create function f(a int,b text) returns void language sql as $$ select 1 $$;"
once := format(src)
twice := format(once)
if once != twice {
t.Errorf("not idempotent\n--- once ---\n%s\n--- twice ---\n%s", once, twice)
}
}
func TestFormatBodyBroken(t *testing.T) {
dir := filepath.Join("..", "..", "testdata", "corpus")
brokenData, err := os.ReadFile(filepath.Join(dir, "test_a_broken.pgsql"))
if err != nil {
t.Skipf("no test_a_broken.pgsql: %v", err)
}
goldenData, err := os.ReadFile(filepath.Join(dir, "test_a.pgsql"))
if err != nil {
t.Skipf("no test_a.pgsql: %v", err)
}
got := format(string(brokenData))
want := string(goldenData)
if got != want {
t.Errorf("format(test_a_broken) != test_a.pgsql\n--- got ---\n%s\n--- want ---\n%s", got, want)
}
twice := format(got)
if twice != got {
t.Errorf("format(test_a_broken) is not idempotent")
}
}
func TestCorpusIdempotentAndSafe(t *testing.T) {
dir := filepath.Join("..", "..", "testdata", "corpus")
entries, err := os.ReadDir(dir)
if err != nil {
t.Skipf("no corpus: %v", err)
}
var seen int
for _, e := range entries {
if e.IsDir() || !strings.HasSuffix(e.Name(), ".pgsql") {
continue
}
seen++
data, err := os.ReadFile(filepath.Join(dir, e.Name()))
if err != nil {
t.Fatal(err)
}
src := string(data)
once := format(src)
twice := format(once)
if once != twice {
t.Errorf("%s: not idempotent", e.Name())
}
if !semanticallyEqual(src, once) {
t.Errorf("%s: formatting changed semantics", e.Name())
}
}
if seen == 0 {
t.Skip("no corpus files")
}
t.Logf("formatted %d corpus files (idempotent + semantically equal)", seen)
}
// semanticallyEqual compares the non-trivia token streams of two sources,
// treating unquoted identifiers/keywords case-insensitively and everything
// else (strings, numbers, operators, punctuation) exactly. Dollar-quoted body
// tokens are compared recursively so body whitespace normalization does not
// trigger a false failure.
func semanticallyEqual(a, b string) bool {
ta := significant(a)
tb := significant(b)
if len(ta) != len(tb) {
return false
}
for i := range ta {
if ta[i].Kind != tb[i].Kind {
return false
}
switch ta[i].Kind {
case lexer.Ident:
if !strings.EqualFold(ta[i].Text, tb[i].Text) {
return false
}
case lexer.DollarString:
_, innerA, _, okA := splitDollarQuote(ta[i].Text)
_, innerB, _, okB := splitDollarQuote(tb[i].Text)
if okA != okB || (okA && !semanticallyEqual(innerA, innerB)) {
return false
}
default:
if ta[i].Text != tb[i].Text {
return false
}
}
}
return true
}
func significant(src string) []lexer.Token {
var out []lexer.Token
for _, t := range lexer.Lex(src) {
if t.Kind == lexer.EOF || t.IsTrivia() {
continue
}
out = append(out, t)
}
return out
}