go.net/html: put escaping tests escape_test.go
R=golang-dev, r
CC=golang-dev
https://golang.org/cl/11094043
diff --git a/html/escape_test.go b/html/escape_test.go
new file mode 100644
index 0000000..b405d4b
--- /dev/null
+++ b/html/escape_test.go
@@ -0,0 +1,97 @@
+// Copyright 2013 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"
+
+type unescapeTest struct {
+ // A short description of the test case.
+ desc string
+ // The HTML text.
+ html string
+ // The unescaped text.
+ unescaped string
+}
+
+var unescapeTests = []unescapeTest{
+ // Handle no entities.
+ {
+ "copy",
+ "A\ttext\nstring",
+ "A\ttext\nstring",
+ },
+ // Handle simple named entities.
+ {
+ "simple",
+ "& > <",
+ "& > <",
+ },
+ // Handle hitting the end of the string.
+ {
+ "stringEnd",
+ "& &",
+ "& &",
+ },
+ // Handle entities with two codepoints.
+ {
+ "multiCodepoint",
+ "text ⋛︀ blah",
+ "text \u22db\ufe00 blah",
+ },
+ // Handle decimal numeric entities.
+ {
+ "decimalEntity",
+ "Delta = Δ ",
+ "Delta = Δ ",
+ },
+ // Handle hexadecimal numeric entities.
+ {
+ "hexadecimalEntity",
+ "Lambda = λ = λ ",
+ "Lambda = λ = λ ",
+ },
+ // Handle numeric early termination.
+ {
+ "numericEnds",
+ "&# &#x €43 © = ©f = ©",
+ "&# &#x €43 © = ©f = ©",
+ },
+ // Handle numeric ISO-8859-1 entity replacements.
+ {
+ "numericReplacements",
+ "Footnote‡",
+ "Footnote‡",
+ },
+}
+
+func TestUnescape(t *testing.T) {
+ for _, tt := range unescapeTests {
+ unescaped := UnescapeString(tt.html)
+ if unescaped != tt.unescaped {
+ t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
+ }
+ }
+}
+
+func TestUnescapeEscape(t *testing.T) {
+ ss := []string{
+ ``,
+ `abc def`,
+ `a & b`,
+ `a&b`,
+ `a & b`,
+ `"`,
+ `"`,
+ `"<&>"`,
+ `"<&>"`,
+ `3&5==1 && 0<1, "0<1", a+acute=á`,
+ `The special characters are: <, >, &, ' and "`,
+ }
+ for _, s := range ss {
+ if got := UnescapeString(EscapeString(s)); got != s {
+ t.Errorf("got %q want %q", got, s)
+ }
+ }
+}
diff --git a/html/token_test.go b/html/token_test.go
index 14e2346..fd49ea6 100644
--- a/html/token_test.go
+++ b/html/token_test.go
@@ -468,96 +468,6 @@
}
}
-type unescapeTest struct {
- // A short description of the test case.
- desc string
- // The HTML text.
- html string
- // The unescaped text.
- unescaped string
-}
-
-var unescapeTests = []unescapeTest{
- // Handle no entities.
- {
- "copy",
- "A\ttext\nstring",
- "A\ttext\nstring",
- },
- // Handle simple named entities.
- {
- "simple",
- "& > <",
- "& > <",
- },
- // Handle hitting the end of the string.
- {
- "stringEnd",
- "& &",
- "& &",
- },
- // Handle entities with two codepoints.
- {
- "multiCodepoint",
- "text ⋛︀ blah",
- "text \u22db\ufe00 blah",
- },
- // Handle decimal numeric entities.
- {
- "decimalEntity",
- "Delta = Δ ",
- "Delta = Δ ",
- },
- // Handle hexadecimal numeric entities.
- {
- "hexadecimalEntity",
- "Lambda = λ = λ ",
- "Lambda = λ = λ ",
- },
- // Handle numeric early termination.
- {
- "numericEnds",
- "&# &#x €43 © = ©f = ©",
- "&# &#x €43 © = ©f = ©",
- },
- // Handle numeric ISO-8859-1 entity replacements.
- {
- "numericReplacements",
- "Footnote‡",
- "Footnote‡",
- },
-}
-
-func TestUnescape(t *testing.T) {
- for _, tt := range unescapeTests {
- unescaped := UnescapeString(tt.html)
- if unescaped != tt.unescaped {
- t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
- }
- }
-}
-
-func TestUnescapeEscape(t *testing.T) {
- ss := []string{
- ``,
- `abc def`,
- `a & b`,
- `a&b`,
- `a & b`,
- `"`,
- `"`,
- `"<&>"`,
- `"<&>"`,
- `3&5==1 && 0<1, "0<1", a+acute=á`,
- `The special characters are: <, >, &, ' and "`,
- }
- for _, s := range ss {
- if got := UnescapeString(EscapeString(s)); got != s {
- t.Errorf("got %q want %q", got, s)
- }
- }
-}
-
func TestBufAPI(t *testing.T) {
s := "0<a>1</a>2<b>3<a>4<a>5</a>6</b>7</a>8<a/>9"
z := NewTokenizer(bytes.NewBufferString(s))