html: lazily populate Unescape tables

Saves ~105KB of heap for callers who don't use html.UnescapeString.
(EscapeString is much more common).

Also saves 70KB of binary size, because now the linker can do dead
code elimination. (because #2559 is still open and global maps always
generate init code)

Fixes #26727
Updates #6853

Change-Id: I18fe9a273097e2c7e0cb7f88205cae1bb60fa89b
Reviewed-on: https://go-review.googlesource.com/127075
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
Reviewed-by: Emmanuel Odeke <emm.odeke@gmail.com>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>

src/html/entity.go

@@ -4,6 +4,8 @@
 
 package html
 
+import "sync"
+
 // All entities that do not end with ';' are 6 or fewer bytes long.
 const longestEntityWithoutSemicolon = 6
 
@@ -13,7 +15,17 @@ const longestEntityWithoutSemicolon = 6
 //
 // Note that the HTML5 list is larger than the HTML4 list at
 // http://www.w3.org/TR/html4/sgml/entities.html
-var entity = map[string]rune{
+var entity map[string]rune
+
+// HTML entities that are two unicode codepoints.
+var entity2 map[string][2]rune
+
+// populateMapsOnce guards calling populateMaps.
+var populateMapsOnce sync.Once
+
+// populateMaps populates entity and entity2.
+func populateMaps() {
+	entity = map[string]rune{
 		"AElig;":                           '\U000000C6',
 		"AMP;":                             '\U00000026',
 		"Aacute;":                          '\U000000C1',
@@ -2152,10 +2164,9 @@ var entity = map[string]rune{
 		"yacute":                           '\U000000FD',
 		"yen":                              '\U000000A5',
 		"yuml":                             '\U000000FF',
-}
+	}
 
-// HTML entities that are two unicode codepoints.
-var entity2 = map[string][2]rune{
+	entity2 = map[string][2]rune{
 		// TODO(nigeltao): Handle replacements that are wider than their names.
 		// "nLt;":                     {'\u226A', '\u20D2'},
 		// "nGt;":                     {'\u226B', '\u20D2'},
@@ -2250,4 +2261,5 @@ var entity2 = map[string][2]rune{
 		"vsubne;":                  {'\u228A', '\uFE00'},
 		"vsupnE;":                  {'\u2ACC', '\uFE00'},
 		"vsupne;":                  {'\u228B', '\uFE00'},
+	}
 }

src/html/entity_test.go

@@ -9,7 +9,15 @@ import (
 	"unicode/utf8"
 )
 
+func init() {
+	UnescapeString("") // force load of entity maps
+}
+
 func TestEntityLength(t *testing.T) {
+	if len(entity) == 0 || len(entity2) == 0 {
+		t.Fatal("maps not loaded")
+	}
+
 	// We verify that the length of UTF-8 encoding of each value is <= 1 + len(key).
 	// The +1 comes from the leading "&". This property implies that the length of
 	// unescaped text is <= the length of escaped text.

src/html/escape.go

@@ -185,6 +185,7 @@ func EscapeString(s string) string {
 // 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 {