diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-28 13:15:26 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-28 13:15:26 +0000 |
commit | 82539ad8d59729fb45b0bb0edda8f2bddb719eb1 (patch) | |
tree | 58f0b58e6f44f0e04d4a6373132cf426fa835fa7 /src/html/entity_test.go | |
parent | Initial commit. (diff) | |
download | golang-1.17-82539ad8d59729fb45b0bb0edda8f2bddb719eb1.tar.xz golang-1.17-82539ad8d59729fb45b0bb0edda8f2bddb719eb1.zip |
Adding upstream version 1.17.13.upstream/1.17.13upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/html/entity_test.go')
-rw-r--r-- | src/html/entity_test.go | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/src/html/entity_test.go b/src/html/entity_test.go new file mode 100644 index 0000000..6688ed2 --- /dev/null +++ b/src/html/entity_test.go @@ -0,0 +1,37 @@ +// 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" + "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. + 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)) + } + if len(k) > longestEntityWithoutSemicolon && k[len(k)-1] != ';' { + t.Errorf("entity name %s is %d characters, but longestEntityWithoutSemicolon=%d", k, len(k), longestEntityWithoutSemicolon) + } + } + 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])) + } + } +} |