extras.go

// Copyright 2010 The Go Authors.  All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package edn

import (
	"reflect"
	"strconv"
	"unicode/utf8"
)

// getu4 decodes \uXXXX from the beginning of s, returning the hex value,
// or it returns -1.
func getu4(s []byte) rune {
	if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
		return -1
	}
	r, err := strconv.ParseUint(string(s[2:6]), 16, 64)
	if err != nil {
		return -1
	}
	return rune(r)
}

// indirect walks down v allocating pointers as needed,
// until it gets to a non-pointer.
// if it encounters an Unmarshaler, indirect stops and returns that.
// if decodingNull is true, indirect stops at the last pointer so it can be set to nil.
func (d *Decoder) indirect(v reflect.Value, decodingNull bool) (Unmarshaler, reflect.Value) {
	// If v is a named type and is addressable,
	// start with its address, so that if the type has pointer methods,
	// we find them.
	if v.Kind() != reflect.Ptr && v.Type().Name() != "" && v.CanAddr() {
		v = v.Addr()
	}
	for {
		// Load value from interface, but only if the result will be
		// usefully addressable.
		if v.Kind() == reflect.Interface && !v.IsNil() {
			e := v.Elem()
			if e.Kind() == reflect.Ptr && !e.IsNil() && (!decodingNull || e.Elem().Kind() == reflect.Ptr) {
				v = e
				continue
			}
		}

		if v.Kind() != reflect.Ptr {
			break
		}

		if v.Elem().Kind() != reflect.Ptr && decodingNull && v.CanSet() {
			break
		}
		if v.IsNil() {
			v.Set(reflect.New(v.Type().Elem()))
		}
		if v.Type().NumMethod() > 0 {
			if u, ok := v.Interface().(Unmarshaler); ok {
				return u, reflect.Value{}
			}
		}
		v = v.Elem()
	}
	return nil, v
}

// unquote converts a quoted EDN string literal s into an actual string t.
// The rules are different than for Go, so cannot use strconv.Unquote.
func unquote(s []byte) (t string, ok bool) {
	s, ok = unquoteBytes(s)
	t = string(s)
	return
}

func unquoteBytes(s []byte) (t []byte, ok bool) {
	if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
		return
	}
	s = s[1 : len(s)-1]

	// Check for unusual characters. If there are none,
	// then no unquoting is needed, so return a slice of the
	// original bytes.
	r := 0
	for r < len(s) {
		c := s[r]
		if c == '\\' || c == '"' {
			break
		}
		if c < utf8.RuneSelf {
			r++
			continue
		}
		rr, size := utf8.DecodeRune(s[r:])
		if rr == utf8.RuneError && size == 1 {
			break
		}
		r += size
	}
	if r == len(s) {
		return s, true
	}

	b := make([]byte, len(s)+2*utf8.UTFMax)
	w := copy(b, s[0:r])
	for r < len(s) {
		// Out of room?  Can only happen if s is full of
		// malformed UTF-8 and we're replacing each
		// byte with RuneError.
		if w >= len(b)-2*utf8.UTFMax {
			nb := make([]byte, (len(b)+utf8.UTFMax)*2)
			copy(nb, b[0:w])
			b = nb
		}
		switch c := s[r]; {
		case c == '\\':
			r++
			if r >= len(s) {
				return
			}
			switch s[r] {
			default:
				return
			case '"', '\\', '/', '\'':
				b[w] = s[r]
				r++
				w++
			case 'b':
				b[w] = '\b'
				r++
				w++
			case 'f':
				b[w] = '\f'
				r++
				w++
			case 'n':
				b[w] = '\n'
				r++
				w++
			case 'r':
				b[w] = '\r'
				r++
				w++
			case 't':
				b[w] = '\t'
				r++
				w++
			case 'u':
				r--
				rr := getu4(s[r:])
				if rr < 0 {
					return
				}
				r += 6
				w += utf8.EncodeRune(b[w:], rr)
			}

		// Quote is invalid
		case c == '"':
			return

		// ASCII
		case c < utf8.RuneSelf:
			b[w] = c
			r++
			w++

		// Coerce to well-formed UTF-8.
		default:
			rr, size := utf8.DecodeRune(s[r:])
			r += size
			w += utf8.EncodeRune(b[w:], rr)
		}
	}
	return b[0:w], true
}