feat(cmd): add the encoder mode to the toml-test adapter

Assisted-by: DeepSeek V4.1 Flash

cmd/interpres-decode/main.go

@@ -4,14 +4,16 @@
 // Command interpres-decode is the toml-test harness adapter and a TOML
 // validator. Without flags it reads a TOML document from standard input and
 // writes the toml-test "tagged JSON" representation to standard output. With
-// -validate it checks the named documents, or standard input when none are
-// named, and exits non-zero on the first invalid one:
+// -encode it is the reverse: it reads tagged JSON and writes the TOML document
+// it describes. With -validate it checks the named documents, or standard
+// input when none are named, and exits non-zero on the first invalid one:
 //
 //	interpres-decode -validate config.toml
+//	interpres-decode -encode < case.json
 //
-// Run the official suite against the adapter with:
+// Run the official suite in both directions against the adapter with:
 //
-//	toml-test ./interpres-decode
+//	toml-test test -decoder=./interpres-decode -encoder='./interpres-decode -encode'
 package main
 
 import (
@@ -39,12 +41,17 @@ func Run(args []string, stdin io.Reader, stdout, stderr io.Writer) int {
 	fs := flag.NewFlagSet("interpres-decode", flag.ContinueOnError)
 	fs.SetOutput(stderr)
 	validate := fs.Bool("validate", false, "validate the documents instead of emitting tagged JSON")
+	encode := fs.Bool("encode", false, "read tagged JSON from stdin and write TOML instead")
 	if err := fs.Parse(args); err != nil {
 		if errors.Is(err, flag.ErrHelp) {
 			return 0
 		}
 		return 2
 	}
+	if *validate && *encode {
+		fmt.Fprintln(stderr, "interpres-decode: -validate and -encode cannot be combined")
+		return 2
+	}
 	if *validate {
 		return validatePaths(fs.Args(), stdin, stderr)
 	}
@@ -52,6 +59,9 @@ func Run(args []string, stdin io.Reader, stdout, stderr io.Writer) int {
 		fmt.Fprintln(stderr, "interpres-decode: the adapter mode takes no arguments; name files with -validate")
 		return 2
 	}
+	if *encode {
+		return encodeJSON(stdin, stdout, stderr)
+	}
 	data, err := io.ReadAll(stdin)
 	if err != nil {
 		fmt.Fprintln(stderr, "read stdin:", err)
@@ -109,6 +119,187 @@ func validatePaths(paths []string, stdin io.Reader, stderr io.Writer) int {
 	return 0
 }
 
+// encodeJSON reads a toml-test tagged JSON description from standard input and
+// writes the TOML document it describes to standard output.
+func encodeJSON(stdin io.Reader, stdout, stderr io.Writer) int {
+	data, err := io.ReadAll(stdin)
+	if err != nil {
+		fmt.Fprintln(stderr, "read stdin:", err)
+		return 2
+	}
+	var desc any
+	if err := json.Unmarshal(data, &desc); err != nil {
+		fmt.Fprintln(stderr, "decode JSON:", err)
+		return 2
+	}
+	tree, err := untag(desc)
+	if err != nil {
+		fmt.Fprintln(stderr, err)
+		return 2
+	}
+	doc, ok := tree.(map[string]any)
+	if !ok {
+		fmt.Fprintln(stderr, "interpres-decode: the description must be a JSON object at the top level")
+		return 2
+	}
+	out, err := interpres.Marshal(doc)
+	if err != nil {
+		fmt.Fprintln(stderr, err)
+		return 2
+	}
+	if _, err := stdout.Write(out); err != nil {
+		fmt.Fprintln(stderr, "write stdout:", err)
+		return 2
+	}
+	return 0
+}
+
+// untag converts a toml-test JSON description into the value tree Marshal
+// expects: a JSON object becomes a map[string]any, a JSON array becomes a
+// []any, and an object carrying exactly the keys "type" and "value" becomes
+// the Go value for that TOML type.
+func untag(v any) (any, error) {
+	switch x := v.(type) {
+	case map[string]any:
+		if typ, val, ok := taggedValue(x); ok {
+			return decodeTagged(typ, val)
+		}
+		out := make(map[string]any, len(x))
+		for k, e := range x {
+			u, err := untag(e)
+			if err != nil {
+				return nil, fmt.Errorf("%s: %w", k, err)
+			}
+			out[k] = u
+		}
+		return out, nil
+	case []any:
+		out := make([]any, len(x))
+		for i, e := range x {
+			u, err := untag(e)
+			if err != nil {
+				return nil, fmt.Errorf("[%d]: %w", i, err)
+			}
+			out[i] = u
+		}
+		return asTables(out), nil
+	default:
+		return nil, fmt.Errorf("unsupported JSON value %T", v)
+	}
+}
+
+// asTables returns the elements as a []map[string]any when there is at least
+// one and every element is a table, the shape the encoder renders as an array
+// of tables. The tagged JSON cannot tell an array of tables from a value array
+// of inline tables, and both parse back to the same value, so the header form
+// is chosen because it is the one the encoder otherwise never exercises. An
+// empty array stays a []any, because TOML has no empty array of tables.
+func asTables(items []any) any {
+	if len(items) == 0 {
+		return items
+	}
+	tbls := make([]map[string]any, len(items))
+	for i, e := range items {
+		tbl, ok := e.(map[string]any)
+		if !ok {
+			return items
+		}
+		tbls[i] = tbl
+	}
+	return tbls
+}
+
+// taggedValue reports whether m is a toml-test value object: a JSON object of
+// exactly the two string keys "type" and "value", carrying a type this adapter
+// knows. Any other object is a table.
+func taggedValue(m map[string]any) (typ, val string, ok bool) {
+	if len(m) != 2 {
+		return "", "", false
+	}
+	ts, ok := m["type"].(string)
+	if !ok || !knownType(ts) {
+		return "", "", false
+	}
+	vs, ok := m["value"].(string)
+	if !ok {
+		return "", "", false
+	}
+	return ts, vs, true
+}
+
+func knownType(typ string) bool {
+	switch typ {
+	case "string", "integer", "float", "bool",
+		"datetime", "datetime-local", "date-local", "time-local":
+		return true
+	}
+	return false
+}
+
+// decodeTagged returns the Go value for one tagged JSON value. Every type but
+// string is parsed by the library itself, so the adapter and the library agree
+// on what an integer, a float or a date-time is.
+func decodeTagged(typ, val string) (any, error) {
+	if typ == "string" {
+		return val, nil
+	}
+	v, err := parseAtom(val)
+	if err != nil {
+		return nil, fmt.Errorf("%s %q: %w", typ, val, err)
+	}
+	// A float with no fractional part and no exponent is described by a bare
+	// integer literal, so here the tag decides and not the literal.
+	if n, ok := v.(int64); ok && typ == "float" {
+		return float64(n), nil
+	}
+	if !typeMatches(typ, v) {
+		return nil, fmt.Errorf("%s %q parsed as %T", typ, val, v)
+	}
+	return v, nil
+}
+
+// parseAtom parses one bare TOML value, by handing `v = <val>` to the library's
+// parser and requiring the result to hold exactly that one statement, so a
+// value carrying a newline or a comment cannot smuggle a second one in.
+func parseAtom(val string) (any, error) {
+	tree, err := interpres.Parse([]byte("v = " + val + "\n"))
+	if err != nil {
+		return nil, err
+	}
+	if len(tree) != 1 {
+		return nil, errors.New("not a single bare value")
+	}
+	return tree["v"], nil
+}
+
+// typeMatches reports whether v is the Go value the tagged type names.
+func typeMatches(typ string, v any) bool {
+	switch typ {
+	case "integer":
+		_, ok := v.(int64)
+		return ok
+	case "float":
+		_, ok := v.(float64)
+		return ok
+	case "bool":
+		_, ok := v.(bool)
+		return ok
+	case "datetime":
+		_, ok := v.(time.Time)
+		return ok
+	case "datetime-local":
+		_, ok := v.(interpres.LocalDateTime)
+		return ok
+	case "date-local":
+		_, ok := v.(interpres.LocalDate)
+		return ok
+	case "time-local":
+		_, ok := v.(interpres.LocalTime)
+		return ok
+	}
+	return false
+}
+
 // tag converts an interpres value into its toml-test tagged-JSON form. Tables
 // become JSON objects and arrays become JSON arrays; scalars are wrapped in a
 // {"type", "value"} object. An error is returned for value types the encoder

cmd/interpres-decode/main_test.go

@@ -8,6 +8,7 @@ import (
 	"encoding/json"
 	"errors"
 	"os"
+	"reflect"
 	"strings"
 	"testing"
 	"time"
@@ -283,3 +284,165 @@ func TestUnknownFlagReturnsTwo(t *testing.T) {
 		t.Fatalf("Run returned %d, want 2; stderr = %q", code, stderr.String())
 	}
 }
+
+// --- encoder mode ----------------------------------------------------------
+
+func TestRunEncoderScalars(t *testing.T) {
+	in := `{
+    "s":   {"type": "string", "value": "quote \" and backslash \\"},
+    "nl":  {"type": "string", "value": "line1\nline2"},
+    "i":   {"type": "integer", "value": "-9223372036854775808"},
+    "g":   {"type": "float", "value": "1.5"},
+    "f":   {"type": "float", "value": "inf"},
+    "b":   {"type": "bool", "value": "false"},
+    "dt":  {"type": "datetime", "value": "1979-05-27T07:32:00-07:00"},
+    "ldt": {"type": "datetime-local", "value": "1979-05-27T07:32:00"},
+    "ld":  {"type": "date-local", "value": "1979-05-27"},
+    "lt":  {"type": "time-local", "value": "07:32:00.999"}
+}
+`
+	var stdout, stderr bytes.Buffer
+	code := Run([]string{"-encode"}, strings.NewReader(in), &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("Run returned %d, stderr = %q", code, stderr.String())
+	}
+	want := "b = false\n" +
+		"dt = 1979-05-27T07:32:00-07:00\n" +
+		"f = inf\n" +
+		"g = 1.5\n" +
+		"i = -9223372036854775808\n" +
+		"ld = 1979-05-27\n" +
+		"ldt = 1979-05-27T07:32:00\n" +
+		"lt = 07:32:00.999000000\n" +
+		"nl = \"line1\\nline2\"\n" +
+		"s = \"quote \\\" and backslash \\\\\"\n"
+	if stdout.String() != want {
+		t.Errorf("output mismatch:\ngot:  %q\nwant: %q", stdout.String(), want)
+	}
+}
+
+func TestRunEncoderNested(t *testing.T) {
+	in := `{
+    "tbl": {"x": {"type": "bool", "value": "true"},
+            "sub": {"y": {"type": "integer", "value": "1"}}},
+    "items": [{"n": {"type": "string", "value": "a"}},
+              {"n": {"type": "string", "value": "b"}}],
+    "list": [{"type": "integer", "value": "1"}, {"type": "string", "value": "two"}],
+    "emptyTbl": {},
+    "emptyArr": []
+}
+`
+	var stdout, stderr bytes.Buffer
+	code := Run([]string{"-encode"}, strings.NewReader(in), &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("Run returned %d, stderr = %q", code, stderr.String())
+	}
+	want := "emptyArr = []\n" +
+		"list = [1, \"two\"]\n" +
+		"\n[emptyTbl]\n" +
+		"\n[tbl]\nx = true\n" +
+		"\n[tbl.sub]\ny = 1\n" +
+		"\n[[items]]\nn = \"a\"\n" +
+		"\n[[items]]\nn = \"b\"\n"
+	if stdout.String() != want {
+		t.Errorf("output mismatch:\ngot:  %q\nwant: %q", stdout.String(), want)
+	}
+}
+
+func TestRunEncoderFloatTagDecides(t *testing.T) {
+	// A float with no fraction is described by a bare integer literal, so the
+	// tag decides the type; the output must stay a float.
+	var stdout, stderr bytes.Buffer
+	in := `{"whole": {"type": "float", "value": "1"}, "exp": {"type": "float", "value": "5e+22"}}`
+	code := Run([]string{"-encode"}, strings.NewReader(in), &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("Run returned %d, stderr = %q", code, stderr.String())
+	}
+	if want := "exp = 5e+22\nwhole = 1.0\n"; stdout.String() != want {
+		t.Errorf("output mismatch:\ngot:  %q\nwant: %q", stdout.String(), want)
+	}
+}
+
+func TestRunEncoderRejectsBadInput(t *testing.T) {
+	cases := []struct {
+		name string
+		in   string
+		want string
+	}{
+		{"not-json", "not json", "decode JSON"},
+		{"top-level-array", `[{"type": "integer", "value": "1"}]`, "must be a JSON object"},
+		{"untagged-scalar", `{"x": 1}`, "unsupported JSON value"},
+		{"literal-mismatch", `{"x": {"type": "integer", "value": "1.5"}}`, "parsed as float64"},
+		{"offset-for-local", `{"x": {"type": "datetime-local", "value": "1979-05-27T07:32:00Z"}}`, "parsed as time.Time"},
+		{"bad-literal", `{"x": {"type": "date-local", "value": "nope"}}`, "date-local"},
+		{"smuggled-statement", `{"x": {"type": "integer", "value": "1\nx = 2"}}`, "not a single bare value"},
+	}
+	for _, c := range cases {
+		var stdout, stderr bytes.Buffer
+		code := Run([]string{"-encode"}, strings.NewReader(c.in), &stdout, &stderr)
+		if code != 2 {
+			t.Errorf("%s: Run returned %d, want 2; stderr = %q", c.name, code, stderr.String())
+			continue
+		}
+		if !strings.Contains(stderr.String(), c.want) {
+			t.Errorf("%s: stderr = %q, want it to mention %q", c.name, stderr.String(), c.want)
+		}
+		if stdout.Len() != 0 {
+			t.Errorf("%s: stdout should be empty, got %q", c.name, stdout.String())
+		}
+	}
+}
+
+func TestRunEncoderFlagConflicts(t *testing.T) {
+	var stdout, stderr bytes.Buffer
+	if code := Run([]string{"-encode", "-validate"}, strings.NewReader(""), &stdout, &stderr); code != 2 {
+		t.Errorf("Run returned %d, want 2 for the two modes together", code)
+	}
+	if !strings.Contains(stderr.String(), "cannot be combined") {
+		t.Errorf("stderr = %q, want it to explain the conflict", stderr.String())
+	}
+
+	stdout.Reset()
+	stderr.Reset()
+	if code := Run([]string{"-encode", "file.json"}, strings.NewReader(""), &stdout, &stderr); code != 2 {
+		t.Errorf("Run returned %d, want 2 for an argument", code)
+	}
+}
+
+func TestEncodeAfterDecodeRoundTrip(t *testing.T) {
+	doc := `title = "x"
+flt = 1.5
+whole = 7.0
+big = 9223372036854775807
+when = 1979-05-27T07:32:00-07:00
+day = 1979-05-27
+clock = 07:32:00.999
+list = [1, "two"]
+multi = "a\nb"
+
+[tbl]
+x = true
+
+[[items]]
+n = "a"
+`
+	var tagged, stderr bytes.Buffer
+	if code := Run(nil, strings.NewReader(doc), &tagged, &stderr); code != 0 {
+		t.Fatalf("decode returned %d, stderr = %q", code, stderr.String())
+	}
+	var out bytes.Buffer
+	if code := Run([]string{"-encode"}, bytes.NewReader(tagged.Bytes()), &out, &stderr); code != 0 {
+		t.Fatalf("encode returned %d, stderr = %q", code, stderr.String())
+	}
+	want, err := interpres.Parse([]byte(doc))
+	if err != nil {
+		t.Fatalf("parse of the original: %v", err)
+	}
+	got, err := interpres.Parse(out.Bytes())
+	if err != nil {
+		t.Fatalf("parse of the encoder output (%q): %v", out.String(), err)
+	}
+	if !reflect.DeepEqual(want, got) {
+		t.Errorf("round trip changed the document:\noriginal: %#v\nencoded:  %#v\noutput: %q", want, got, out.String())
+	}
+}