src/html/escape.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 html provides functions for escaping and unescaping HTML text.
package html

import (
	"strings"
	"unicode/utf8"
)

// These replacements permit compatibility with old numeric entities that
// assumed Windows-1252 encoding.
// http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#consume-a-character-reference
var replacementTable = [...]rune{
	'\u20AC', // First entry is what 0x80 should be replaced with.
	'\u0081',
	'\u201A',
	'\u0192',
	'\u201E',
	'\u2026',
	'\u2020',
	'\u2021',
	'\u02C6',
	'\u2030',
	'\u0160',
	'\u2039',
	'\u0152',
	'\u008D',
	'\u017D',
	'\u008F',
	'\u0090',
	'\u2018',
	'\u2019',
	'\u201C',
	'\u201D',
	'\u2022',
	'\u2013',
	'\u2014',
	'\u02DC',
	'\u2122',
	'\u0161',
	'\u203A',
	'\u0153',
	'\u009D',
	'\u017E',
	'\u0178', // Last entry is 0x9F.
	// 0x00->'\uFFFD' is handled programmatically.
	// 0x0D->'\u000D' is a no-op.
}

// unescapeEntity reads an entity like "<" from b[src:] and writes the
// corresponding "<" to b[dst:], returning the incremented dst and src cursors.
// Precondition: b[src] == '&' && dst <= src.
func unescapeEntity(b []byte, dst, src int) (dst1, src1 int) {
	const attribute = false

	// http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#consume-a-character-reference

	// i starts at 1 because we already know that s[0] == '&'.
	i, s := 1, b[src:]

	if len(s) <= 1 {
		b[dst] = b[src]
		return dst + 1, src + 1
	}

	if s[i] == '#' {
		if len(s) <= 3 { // We need to have at least "&#.".
			b[dst] = b[src]
			return dst + 1, src + 1
		}
		i++
		c := s[i]
		hex := false
		if c == 'x' || c == 'X' {
			hex = true
			i++
		}

		x := '\x00'
		for i < len(s) {
			c = s[i]
			i++
			if hex {
				if '0' <= c && c <= '9' {
					x = 16*x + rune(c) - '0'
					continue
				} else if 'a' <= c && c <= 'f' {
					x = 16*x + rune(c) - 'a' + 10
					continue
				} else if 'A' <= c && c <= 'F' {
					x = 16*x + rune(c) - 'A' + 10
					continue
				}
			} else if '0' <= c && c <= '9' {
				x = 10*x + rune(c) - '0'
				continue
			}
			if c != ';' {
				i--
			}
			break
		}

		if i <= 3 { // No characters matched.
			b[dst] = b[src]
			return dst + 1, src + 1
		}

		if 0x80 <= x && x <= 0x9F {
			// Replace characters from Windows-1252 with UTF-8 equivalents.
			x = replacementTable[x-0x80]
		} else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF {
			// Replace invalid characters with the replacement character.
			x = '\uFFFD'
		}

		return dst + utf8.EncodeRune(b[dst:], x), src + i
	}

	// Consume the maximum number of characters possible, with the
	// consumed characters matching one of the named references.

	for i < len(s) {
		c := s[i]
		i++
		// Lower-cased characters are more common in entities, so we check for them first.
		if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
			continue
		}
		if c != ';' {
			i--
		}
		break
	}

	entityName := s[1:i]
	if len(entityName) == 0 {
		// No-op.
	} else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' {
		// No-op.
	} else if x := entity[string(entityName)]; x != 0 {
		return dst + utf8.EncodeRune(b[dst:], x), src + i
	} else if x := entity2[string(entityName)]; x[0] != 0 {
		dst1 := dst + utf8.EncodeRune(b[dst:], x[0])
		return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i
	} else if !attribute {
		maxLen := len(entityName) - 1
		if maxLen > longestEntityWithoutSemicolon {
			maxLen = longestEntityWithoutSemicolon
		}
		for j := maxLen; j > 1; j-- {
			if x := entity[string(entityName[:j])]; x != 0 {
				return dst + utf8.EncodeRune(b[dst:], x), src + j + 1
			}
		}
	}

	dst1, src1 = dst+i, src+i
	copy(b[dst:dst1], b[src:src1])
	return dst1, src1
}

var htmlEscaper = strings.NewReplacer(
	`&`, "&amp;",
	`'`, "&#39;", // "&#39;" is shorter than "&apos;" and apos was not in HTML until HTML5.
	`<`, "&lt;",
	`>`, "&gt;",
	`"`, "&#34;", // "&#34;" is shorter than "&quot;".
)

// EscapeString escapes special characters like "<" to become "&lt;". It
// escapes only five such characters: <, >, &, ' and ".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func EscapeString(s string) string {
	return htmlEscaper.Replace(s)
}

// UnescapeString unescapes entities like "&lt;" to become "<". It unescapes a
// larger range of entities than EscapeString escapes. For example, "&aacute;"
// unescapes to "á", as does "&#225;" and "&#xE1;".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func UnescapeString(s string) string {
	populateMapsOnce.Do(populateMaps)
	i := strings.IndexByte(s, '&')

	if i < 0 {
		return s
	}

	b := []byte(s)
	dst, src := unescapeEntity(b, i, i)
	for len(s[src:]) > 0 {
		if s[src] == '&' {
			i = 0
		} else {
			i = strings.IndexByte(s[src:], '&')
		}
		if i < 0 {
			dst += copy(b[dst:], s[src:])
			break
		}

		if i > 0 {
			copy(b[dst:], s[src:src+i])
		}
		dst, src = unescapeEntity(b, dst+i, src+i)
	}
	return string(b[:dst])
}