1
0
mirror of https://github.com/golang/go synced 2024-11-20 11:34:48 -07:00

html: move the sanity checking of the entity map from runtime

(during init) to test-time (via gotest).

R=gri
CC=golang-dev
https://golang.org/cl/3466044
This commit is contained in:
Nigel Tao 2010-12-08 07:55:03 +11:00
parent ae2495c5b0
commit 688a83128d
2 changed files with 26 additions and 20 deletions

View File

@ -4,10 +4,6 @@
package html package html
import (
"utf8"
)
// entity is a map from HTML entity names to their values. The semicolon matters: // entity is a map from HTML entity names to their values. The semicolon matters:
// http://www.whatwg.org/specs/web-apps/current-work/multipage/named-character-references.html // http://www.whatwg.org/specs/web-apps/current-work/multipage/named-character-references.html
// lists both "amp" and "amp;" as two separate entries. // lists both "amp" and "amp;" as two separate entries.
@ -2252,19 +2248,3 @@ var entity2 = map[string][2]int{
"vsupnE;": {'\u2ACC', '\uFE00'}, "vsupnE;": {'\u2ACC', '\uFE00'},
"vsupne;": {'\u228B', '\uFE00'}, "vsupne;": {'\u228B', '\uFE00'},
} }
func init() {
// 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.
for k, v := range entity {
if 1+len(k) < utf8.RuneLen(v) {
panic("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v))
}
}
for k, v := range entity2 {
if 1+len(k) < utf8.RuneLen(v[0])+utf8.RuneLen(v[1]) {
panic("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v[0]) + string(v[1]))
}
}
}

View File

@ -0,0 +1,26 @@
// 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
import (
"testing"
"utf8"
)
func TestEntityLength(t *testing.T) {
// 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.
for k, v := range entity {
if 1+len(k) < utf8.RuneLen(v) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v))
}
}
for k, v := range entity2 {
if 1+len(k) < utf8.RuneLen(v[0])+utf8.RuneLen(v[1]) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v[0]) + string(v[1]))
}
}
}