libgo/go/html/escape_test.go

   1 // Copyright 2013 The Go Authors. All rights reserved.
   2 // Use of this source code is governed by a BSD-style
   3 // license that can be found in the LICENSE file.
   4
   5 package html
   6
   7 import "testing"
   8
   9 type unescapeTest struct {
  10         // A short description of the test case.
  11         desc string
  12         // The HTML text.
  13         html string
  14         // The unescaped text.
  15         unescaped string
  16 }
  17
  18 var unescapeTests = []unescapeTest{
  19         // Handle no entities.
  20         {
  21                 "copy",
  22                 "A\ttext\nstring",
  23                 "A\ttext\nstring",
  24         },
  25         // Handle simple named entities.
  26         {
  27                 "simple",
  28                 "&amp; &gt; &lt;",
  29                 "& > <",
  30         },
  31         // Handle hitting the end of the string.
  32         {
  33                 "stringEnd",
  34                 "&amp &amp",
  35                 "& &",
  36         },
  37         // Handle entities with two codepoints.
  38         {
  39                 "multiCodepoint",
  40                 "text &gesl; blah",
  41                 "text \u22db\ufe00 blah",
  42         },
  43         // Handle decimal numeric entities.
  44         {
  45                 "decimalEntity",
  46                 "Delta = &#916; ",
  47                 "Delta = Δ ",
  48         },
  49         // Handle hexadecimal numeric entities.
  50         {
  51                 "hexadecimalEntity",
  52                 "Lambda = &#x3bb; = &#X3Bb ",
  53                 "Lambda = λ = λ ",
  54         },
  55         // Handle numeric early termination.
  56         {
  57                 "numericEnds",
  58                 "&# &#x &#128;43 &copy = &#169f = &#xa9",
  59                 "&# &#x €43 © = ©f = ©",
  60         },
  61         // Handle numeric ISO-8859-1 entity replacements.
  62         {
  63                 "numericReplacements",
  64                 "Footnote&#x87;",
  65                 "Footnote‡",
  66         },
  67         // Handle single ampersand.
  68         {
  69                 "copySingleAmpersand",
  70                 "&",
  71                 "&",
  72         },
  73         // Handle ampersand followed by non-entity.
  74         {
  75                 "copyAmpersandNonEntity",
  76                 "text &test",
  77                 "text &test",
  78         },
  79         // Handle "&#".
  80         {
  81                 "copyAmpersandHash",
  82                 "text &#",
  83                 "text &#",
  84         },
  85 }
  86
  87 func TestUnescape(t *testing.T) {
  88         for _, tt := range unescapeTests {
  89                 unescaped := UnescapeString(tt.html)
  90                 if unescaped != tt.unescaped {
  91                         t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
  92                 }
  93         }
  94 }
  95
  96 func TestUnescapeEscape(t *testing.T) {
  97         ss := []string{
  98                 ``,
  99                 `abc def`,
 100                 `a & b`,
 101                 `a&amp;b`,
 102                 `a &amp b`,
 103                 `&quot;`,
 104                 `"`,
 105                 `"<&>"`,
 106                 `&quot;&lt;&amp;&gt;&quot;`,
 107                 `3&5==1 && 0<1, "0&lt;1", a+acute=&aacute;`,
 108                 `The special characters are: <, >, &, ' and "`,
 109         }
 110         for _, s := range ss {
 111                 if got := UnescapeString(EscapeString(s)); got != s {
 112                         t.Errorf("got %q want %q", got, s)
 113                 }
 114         }
 115 }