// Copyright 2019 chnykn@gmail.com All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package toolfunc

import "strconv"

type encoding int

const (
	encodePath encoding = 1 + iota
	encodeHost
	encodeUserPassword
	encodeQueryComponent
	encodeFragment
)

//---------------------------------------------------------------

//EscapeError ***
type EscapeError string

func (e EscapeError) Error() string {
	return "invalid URL escape " + strconv.Quote(string(e))
}

//---------------------------------------------------------------

func ishex(c byte) bool {
	switch {
	case '0' <= c && c <= '9':
		return true
	case 'a' <= c && c <= 'f':
		return true
	case 'A' <= c && c <= 'F':
		return true
	}
	return false
}

func unhex(c byte) byte {
	switch {
	case '0' <= c && c <= '9':
		return c - '0'
	case 'a' <= c && c <= 'f':
		return c - 'a' + 10
	case 'A' <= c && c <= 'F':
		return c - 'A' + 10
	}
	return 0
}

// Return true if the specified character should be escaped when
// appearing in a URL string, according to RFC 3986.
//
// Please be informed that for now shouldEscape does not check all
// reserved characters correctly. See golang.org/issue/5684.
func shouldEscape(c byte, mode encoding) bool {
	// §2.3 Unreserved characters (alphanum)
	if 'A' <= c && c <= 'Z' || 'a' <= c && c <= 'z' || '0' <= c && c <= '9' {
		return false
	}

	if mode == encodeHost {
		// §3.2.2 Host allows
		//  sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
		// as part of reg-name.
		// We add : because we include :port as part of host.
		// We add [ ] because we include [ipv6]:port as part of host
		switch c {
		case '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '[', ']':
			return false
		}
	}

	switch c {
	case '-', '_', '.', '~': // §2.3 Unreserved characters (mark)
		return false

	case '$', '&', '+', ',', '/', ':', ';', '=', '?', '@': // §2.2 Reserved characters (reserved)
		// Different sections of the URL allow a few of
		// the reserved characters to appear unescaped.
		switch mode {
		case encodePath: // §3.3
			// The RFC allows : @ & = + $ but saves / ; , for assigning
			// meaning to individual path segments. This package
			// only manipulates the path as a whole, so we allow those
			// last two as well. That leaves only ? to escape.
			return c == '?'

		case encodeUserPassword: // §3.2.1
			// The RFC allows ';', ':', '&', '=', '+', '$', and ',' in
			// userinfo, so we must escape only '@', '/', and '?'.
			// The parsing of userinfo treats ':' as special so we must escape
			// that too.
			return c == '@' || c == '/' || c == '?' || c == ':'

		case encodeQueryComponent: // §3.4
			// The RFC reserves (so we must escape) everything.
			return true

		case encodeFragment: // §4.1
			// The RFC text is silent but the grammar allows
			// everything, so escape nothing.
			return false
		}
	}

	// Everything else must be escaped.
	return true
}

func escape(s string, mode encoding) string {
	spaceCount, hexCount := 0, 0
	for i := 0; i < len(s); i++ {
		c := s[i]
		if shouldEscape(c, mode) {
			if c == ' ' && mode == encodeQueryComponent {
				spaceCount++
			} else {
				hexCount++
			}
		}
	}

	if spaceCount == 0 && hexCount == 0 {
		return s
	}

	t := make([]byte, len(s)+2*hexCount)
	j := 0
	for i := 0; i < len(s); i++ {
		switch c := s[i]; {
		case c == ' ' && mode == encodeQueryComponent:
			t[j] = '+'
			j++
		case shouldEscape(c, mode):
			t[j] = '%'
			t[j+1] = "0123456789ABCDEF"[c>>4]
			t[j+2] = "0123456789ABCDEF"[c&15]
			j += 3
		default:
			t[j] = s[i]
			j++
		}
	}
	return string(t)
}

// unescape unescapes a string; the mode specifies
// which section of the URL string is being unescaped.
func unescape(s string, mode encoding) (string, error) {
	// Count %, check that they're well-formed.
	n := 0
	hasPlus := false
	for i := 0; i < len(s); {
		switch s[i] {
		case '%':
			n++
			if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
				s = s[i:]
				if len(s) > 3 {
					s = s[:3]
				}
				return "", EscapeError(s)
			}
			i += 3
		case '+':
			hasPlus = mode == encodeQueryComponent
			i++
		default:
			i++
		}
	}

	if n == 0 && !hasPlus {
		return s, nil
	}

	t := make([]byte, len(s)-2*n)
	j := 0
	for i := 0; i < len(s); {
		switch s[i] {
		case '%':
			t[j] = unhex(s[i+1])<<4 | unhex(s[i+2])
			j++
			i += 3
		case '+':
			if mode == encodeQueryComponent {
				t[j] = ' '
			} else {
				t[j] = '+'
			}
			j++
			i++
		default:
			t[j] = s[i]
			j++
			i++
		}
	}
	return string(t), nil
}

//EncodeURI ***
func EncodeURI(rawString string) string {
	return escape(rawString, encodeFragment)
}

//DecodeURI ***
func DecodeURI(encoded string) (string, error) {
	return unescape(encoded, encodeQueryComponent)
}