interpres/cmd/interpres-decode/main.go

// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: MIT

// 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
// --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 when one is invalid:
//
//	interpres-decode --validate config.toml
//	interpres-decode --encode < case.json
//
// Run the official suite in both directions against the adapter with:
//
//	toml-test test -decoder=./interpres-decode -encoder='./interpres-decode --encode'
package main

import (
	"encoding/json"
	"errors"
	"flag"
	"fmt"
	"io"
	"io/fs"
	"math"
	"os"
	"path/filepath"
	"runtime/debug"
	"strconv"
	"strings"
	"time"

	"sourcedock.dev/petrbalvin/interpres/v2"
)

func main() {
	os.Exit(Run(os.Args[1:], os.Stdin, os.Stdout, os.Stderr))
}

// Run runs the command line and returns the process exit code: 0 success,
// 1 an invalid document, 2 a usage, reading, writing, encoding, or
// unsupported-value error.
func Run(args []string, stdin io.Reader, stdout, stderr io.Writer) int {
	fs := flag.NewFlagSet("interpres-decode", flag.ContinueOnError)
	// The flag package's own diagnostics and default usage render flags
	// with a single dash, while the command spells every flag in its
	// two-dash long form, the form the manpage documents. Its output is
	// therefore discarded and the usage below is the only one printed.
	fs.SetOutput(io.Discard)
	fs.Usage = func() {}
	version := fs.Bool("version", false, "print the version and exit")
	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")
	plainJSON := fs.Bool("json", false, "with the default mode, print plain indented JSON instead of tagged JSON")
	infer := fs.Bool("struct", false, "infer a Go struct definition from the document on stdin and print it")
	schemaType := fs.String("schema", "", "write a TOML template for the named struct type; the source file follows as the first argument")
	if err := fs.Parse(args); err != nil {
		if errors.Is(err, flag.ErrHelp) {
			usage(stdout)
			return 0
		}
		fmt.Fprintf(stderr, "interpres-decode: %v\n", err)
		usage(stderr)
		return 2
	}
	if *version {
		if _, err := fmt.Fprintf(stdout, "interpres-decode %s\n", versionString()); err != nil {
			fmt.Fprintln(stderr, "interpres-decode: write stdout:", err)
			return 2
		}
		return 0
	}
	modes := 0
	for _, on := range []*bool{validate, encode, infer} {
		if *on {
			modes++
		}
	}
	if *schemaType != "" {
		modes++
	}
	if modes > 1 {
		fmt.Fprintln(stderr, "interpres-decode: --validate, --encode, --struct and --schema cannot be combined")
		return 2
	}
	// --json shapes the decoding output only, so it is rejected with every
	// mode uniformly instead of being silently ignored by some of them.
	if *plainJSON && modes > 0 {
		fmt.Fprintln(stderr, "interpres-decode: --json shapes the decoder output and cannot be combined with --encode, --struct, --validate or --schema")
		return 2
	}
	if *schemaType != "" {
		rest := fs.Args()
		if len(rest) != 1 {
			fmt.Fprintln(stderr, "interpres-decode: --schema needs the type name and exactly one Go source file")
			return 2
		}
		if err := runSchema(*schemaType, rest[0], stdout); err != nil {
			fmt.Fprintf(stderr, "interpres-decode: %v\n", err)
			return 2
		}
		return 0
	}
	if *validate {
		return validatePaths(fs.Args(), stdin, stderr)
	}
	if fs.NArg() > 0 {
		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, "interpres-decode: read stdin:", err)
		return 2
	}
	if *infer {
		if err := inferStruct(data, stdout); err != nil {
			fmt.Fprintf(stderr, "interpres-decode: %v\n", err)
			// A document that fails to parse keeps the adapter's invalid
			// exit; anything else, a failed write among them, is a tool
			// failure.
			if _, ok := errors.AsType[*interpres.SyntaxError](err); ok {
				return 1
			}
			return 2
		}
		return 0
	}
	tree, err := interpres.ParseMap(data)
	if err != nil {
		fmt.Fprintf(stderr, "interpres-decode: %v\n", err)
		return 1
	}
	if *plainJSON {
		enc := json.NewEncoder(stdout)
		enc.SetEscapeHTML(false)
		enc.SetIndent("", "  ")
		if err := enc.Encode(plainJSONValue(tree)); err != nil {
			fmt.Fprintln(stderr, "interpres-decode: encode:", err)
			return 2
		}
		return 0
	}
	tagged, err := tag(tree)
	if err != nil {
		fmt.Fprintf(stderr, "interpres-decode: %v\n", err)
		return 2
	}
	enc := json.NewEncoder(stdout)
	enc.SetEscapeHTML(false)
	if err := enc.Encode(tagged); err != nil {
		fmt.Fprintln(stderr, "interpres-decode: encode:", err)
		return 2
	}
	return 0
}

// usage prints the command line summary, with every flag in its two-dash
// long form: the flag package's default usage printer renders a single dash,
// and the manpage and docs/CLI.md spell the flags the way this text does.
func usage(w io.Writer) {
	fmt.Fprint(w, `Usage: interpres-decode [flags]

Without a mode flag the command reads one TOML document from standard input
and writes the toml-test tagged JSON representation to standard output.

  --encode            read tagged JSON from standard input and write TOML
                      instead
  --help              print this usage
  --json              with the default mode, print plain indented JSON
                      instead of tagged JSON
  --schema TYPE       write a TOML template for the named struct type; the
                      Go source file follows as the first argument
  --struct            infer a Go struct definition from the document on
                      standard input and print it
  --validate          validate the documents instead of emitting tagged JSON
  --version           print the version and exit
`)
}

// versionString names the version the binary was built at: the module
// version the toolchain recorded, which is the tag when the release pipeline
// builds it, and (devel) for an ordinary build from a working tree.
func versionString() string {
	if info, ok := debug.ReadBuildInfo(); ok {
		if v := info.Main.Version; strings.HasPrefix(v, "v") {
			return v
		}
	}
	return "(devel)"
}

// plainJSONValue converts the parsed tree into the values encoding/json
// renders: the date-time wrappers print in their TOML form, which is the
// same text a reader of the document saw.
func plainJSONValue(v any) any {
	switch x := v.(type) {
	case map[string]any:
		for k, val := range x {
			x[k] = plainJSONValue(val)
		}
		return x
	case []any:
		for i, val := range x {
			x[i] = plainJSONValue(val)
		}
		return x
	case []map[string]any:
		out := make([]any, len(x))
		for i, val := range x {
			out[i] = plainJSONValue(val)
		}
		return out
	case time.Time:
		return x.Format(time.RFC3339Nano)
	case interpres.OffsetDateTime:
		return x.String()
	case interpres.LocalDateTime:
		return x.String()
	case interpres.LocalDate:
		return x.String()
	case interpres.LocalTime:
		return x.String()
	}
	return v
}

// validatePaths parses every named file, or standard input when none are
// named, and reports each invalid document on stderr. A named directory is
// walked for .toml files. It returns 0 when all documents parse, 1 when one
// does not, and 2 on a usage or read failure. A summary names the counts.
func validatePaths(paths []string, stdin io.Reader, stderr io.Writer) int {
	if len(paths) == 0 {
		paths = []string{"-"}
	}
	var files []string
	dirs := 0
	for _, p := range paths {
		if p == "-" {
			files = append(files, "-")
			continue
		}
		info, err := os.Stat(p)
		if err != nil {
			fmt.Fprintf(stderr, "interpres-decode: %s: %v\n", p, err)
			return 2
		}
		if !info.IsDir() {
			files = append(files, p)
			continue
		}
		dirs++
		err = filepath.WalkDir(p, func(path string, d fs.DirEntry, err error) error {
			if err != nil {
				return err
			}
			if !d.IsDir() && strings.EqualFold(filepath.Ext(path), ".toml") {
				files = append(files, path)
			}
			return nil
		})
		if err != nil {
			fmt.Fprintf(stderr, "interpres-decode: walk %s: %v\n", p, err)
			return 2
		}
	}
	checked := 0
	invalid := 0
	for _, p := range files {
		name := p
		var data []byte
		var err error
		if p == "-" {
			data, err = io.ReadAll(stdin)
			name = "<stdin>"
		} else {
			data, err = os.ReadFile(p)
		}
		if err != nil {
			fmt.Fprintf(stderr, "interpres-decode: %s: %v\n", name, err)
			return 2
		}
		checked++
		if _, err := interpres.ParseMap(data); err != nil {
			fmt.Fprintf(stderr, "interpres-decode: %s: %v\n", name, err)
			invalid++
		}
	}
	// The single-document run stays quiet on success, the contract the
	// compliance tooling relies on; a directory walk closes with the
	// summary that makes the sweep readable.
	if dirs > 0 {
		fmt.Fprintf(stderr, "checked %d documents, %d invalid\n", checked, invalid)
	}
	if invalid > 0 {
		return 1
	}
	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, "interpres-decode: read stdin:", err)
		return 2
	}
	var desc any
	if err := json.Unmarshal(data, &desc); err != nil {
		fmt.Fprintln(stderr, "interpres-decode: decode JSON:", err)
		return 2
	}
	tree, err := untag(desc)
	if err != nil {
		fmt.Fprintf(stderr, "interpres-decode: %v\n", 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.Fprintf(stderr, "interpres-decode: %v\n", err)
		return 2
	}
	if _, err := stdout.Write(out); err != nil {
		fmt.Fprintln(stderr, "interpres-decode: 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.ParseMap([]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":
		switch v.(type) {
		case time.Time, interpres.OffsetDateTime:
			return true
		}
		return false
	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
// has no tagged representation for.
func tag(v any) (any, error) {
	switch x := v.(type) {
	case map[string]any:
		out := make(map[string]any, len(x))
		for k, val := range x {
			tagged, err := tag(val)
			if err != nil {
				return nil, err
			}
			out[k] = tagged
		}
		return out, nil
	case []any:
		out := make([]any, len(x))
		for i, e := range x {
			tagged, err := tag(e)
			if err != nil {
				return nil, err
			}
			out[i] = tagged
		}
		return out, nil
	case []map[string]any:
		out := make([]any, len(x))
		for i, e := range x {
			tagged, err := tag(e)
			if err != nil {
				return nil, err
			}
			out[i] = tagged
		}
		return out, nil
	case string:
		return tagged("string", x), nil
	case bool:
		return tagged("bool", strconv.FormatBool(x)), nil
	case int64:
		return tagged("integer", strconv.FormatInt(x, 10)), nil
	case float64:
		return tagged("float", formatFloat(x)), nil
	case time.Time:
		return tagged("datetime", x.Format(time.RFC3339Nano)), nil
	case interpres.OffsetDateTime:
		return tagged("datetime", x.Format(time.RFC3339Nano)), nil
	case interpres.LocalDateTime:
		return tagged("datetime-local", x.Format("2006-01-02T15:04:05.999999999")), nil
	case interpres.LocalDate:
		return tagged("date-local", x.Format("2006-01-02")), nil
	case interpres.LocalTime:
		return tagged("time-local", x.Format("15:04:05.999999999")), nil
	default:
		return nil, fmt.Errorf("unsupported value type %T", v)
	}
}

func tagged(typ, value string) map[string]string {
	return map[string]string{"type": typ, "value": value}
}

func formatFloat(f float64) string {
	switch {
	case math.IsInf(f, 1):
		return "inf"
	case math.IsInf(f, -1):
		return "-inf"
	case math.IsNaN(f):
		return "nan"
	default:
		return strconv.FormatFloat(f, 'g', -1, 64)
	}
}