urlValues.go

//Copyright (c) 2009 The Go Authors. All rights reserved.

// url package has been modified to be a lightweight url.Values for adding and encoding values, with an added EncodeWithOrder
// function to keep the order of the values added if the order is important, the original package does not support this.

package urlValues

import (
	"sort"
	"strings"
)

type Values map[string][]string
type encoding int

const OrderKey = "_GO_ORDER"

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

func (v Values) Encode() string {
	if v == nil {
		return ""
	}
	var buf strings.Builder
	keys := make([]string, 0, len(v))
	for k := range v {
		keys = append(keys, k)
	}
	sort.Strings(keys)
	for _, k := range keys {
		if k == OrderKey {
			continue
		}
		vs := v[k]
		keyEscaped := QueryEscape(k)
		for _, v := range vs {
			if buf.Len() > 0 {
				buf.WriteByte('&')
			}
			buf.WriteString(keyEscaped)
			buf.WriteByte('=')
			buf.WriteString(QueryEscape(v))
		}
	}
	return buf.String()
}
func (v Values) EncodeWithOrder() string {
	if v == nil {
		return ""
	}
	var buf strings.Builder
	//sort.Strings(keys) sort ruins original order of our strings, so we remove it to keep order
	for _, k := range v[OrderKey] {
		vs := v[k]
		for _, v := range vs {
			if buf.Len() > 0 {
				buf.WriteByte('&')
			}
			buf.WriteString(k)
			buf.WriteByte('=')
			buf.WriteString(v)
		}
	}
	return buf.String()
}

func (v Values) Add(key, value string) {
	v[key] = append(v[key], value)
	v[OrderKey] = append(v[OrderKey], key)
}

func (v Values) Del(key string) {
	delete(v, key)
	oldOrder := v[OrderKey]
	order := make([]string, len(oldOrder)-1)
	for _, k := range oldOrder {
		if key == k {
			continue
		}
		order = append(order, k)
	}
	v[OrderKey] = order
}

func QueryEscape(s string) string {
	return escape(s, encodeQueryComponent)
}

const upperhex = "0123456789ABCDEF"

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
	}

	var buf [64]byte
	var t []byte

	required := len(s) + 2*hexCount
	if required <= len(buf) {
		t = buf[:required]
	} else {
		t = make([]byte, required)
	}

	if hexCount == 0 {
		copy(t, s)
		for i := 0; i < len(s); i++ {
			if s[i] == ' ' {
				t[i] = '+'
			}
		}
		return string(t)
	}

	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] = upperhex[c>>4]
			t[j+2] = upperhex[c&15]
			j += 3
		default:
			t[j] = s[i]
			j++
		}
	}
	return string(t)
}
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 || mode == encodeZone {
		// §3.2.2 Host allows
		//	sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
		// as part of reg-name.
		// We add : because we include :port as part of host.
		// We add [ ] because we include [ipv6]:port as part of host.
		// We add < > because they're the only characters left that
		// we could possibly allow, and Parse will reject them if we
		// escape them (because hosts can't use %-encoding for
		// ASCII bytes).
		switch c {
		case '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '[', ']', '<', '>', '"':
			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 three as well. That leaves only ? to escape.
			return c == '?'

		case encodePathSegment: // §3.3
			// The RFC allows : @ & = + $ but saves / ; , for assigning
			// meaning to individual path segments.
			return c == '/' || c == ';' || c == ',' || 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
		}
	}

	if mode == encodeFragment {
		// RFC 3986 §2.2 allows not escaping sub-delims. A subset of sub-delims are
		// included in reserved from RFC 2396 §2.2. The remaining sub-delims do not
		// need to be escaped. To minimize potential breakage, we apply two restrictions:
		// (1) we always escape sub-delims outside of the fragment, and (2) we always
		// escape single quote to avoid breaking callers that had previously assumed that
		// single quotes would be escaped. See issue #19917.
		switch c {
		case '!', '(', ')', '*':
			return false
		}
	}

	// Everything else must be escaped.
	return true
}