1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
From: Simon McVittie <smcv@debian.org>
Date: Fri, 22 Jul 2016 09:27:26 +0100
Subject: t: use a pre-HTML5 DOCTYPE to get warnings about unescaped ampersand
HTML5 defines an ampersand followed by whitespace to be unambiguously
an ampersand, matching what browsers have always done in practice.
As a result, tidy-html5 does not warn about them when the doctype
is either HTML5 or missing (lack of a DOCTYPE is treated as HTML5,
on the basis that HTML5 is a closer match for what browsers actually
do than any previous standard). Discussion here:
<https://github.com/htacg/tidy-html5/issues/207>
Adding the DOCTYPE throws off some of the line numbering, which needs
adjusting.
t/ignore-text.t also seems to rely on the missing DOCTYPE provoking a
warning, which is obviously not going to happen now that we've
added one, to be able to verify that case-insensitive ignoring
can work. Add a new error so we can ignore that instead.
Signed-off-by: Simon McVittie <smcv@debian.org>
t/ignore-text.t | 8 +++++---
t/ignore.t | 10 +++++-----
t/levels.t | 10 +++++-----
3 files changed, 15 insertions(+), 13 deletions(-)
diff --git a/t/ignore-text.t b/t/ignore-text.t
index 9695a5a..a95e0e0 100644
@@ -10,8 +10,8 @@ use HTML::Tidy;
my $html = do { local $/; <DATA> };
my @expected_messages = split /\n/, q{
-DATA (24:XX) Warning: unescaped & which should be written as &
-DATA (24:XX) Warning: unescaped & which should be written as &
+DATA (26:XX) Warning: unescaped & which should be written as &
+DATA (26:XX) Warning: unescaped & which should be written as &
};
chomp @expected_messages;
@@ -22,7 +22,7 @@ IGNORE_BOGOTAG: {
isa_ok( $tidy, 'HTML::Tidy' );
$tidy->ignore( text => qr/bogotag/ );
- $tidy->ignore( text => [ qr/UNESCAPED/, qr/doctype/i ] );
+ $tidy->ignore( text => [ qr/UNESCAPED/, qr/case-insensitive/i ] );
# The qr/UNESCAPED/ should not ignore anything because there's no /i
my $rc = $tidy->parse( 'DATA', $html );
ok( $rc, 'Parsed OK' );
@@ -44,6 +44,7 @@ sub munge_returned {
}
}
__DATA__
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html;CHARSET=iso-8859-1">
@@ -67,6 +68,7 @@ DIV.TOC P {
</HEAD>
<BODY BGCOLOR="white">
<BOGOTAG>
+<CASE-INSENSITIVE>
<IMG SRC="/pix/petdance-logo-400x312.gif" HEIGHT=312 WIDTH=400 ALT="Andy & Amy's Pet Supplies & Dance Instruction" ALIGN=RIGHT>
<DIV CLASS="TOC">
<h2>Perl, Programming & Writing</h2>
diff --git a/t/ignore.t b/t/ignore.t
index 3991733..c0a1317 100644
@@ -10,16 +10,15 @@ use HTML::Tidy;
my $html = do { local $/ = undef; <DATA> };
my @expected_warnings = split /\n/, q{
-- (1:1) Warning: missing <!DOCTYPE> declaration
-- (23:1) Warning: discarding unexpected <bogotag>
-- (24:XX) Warning: unescaped & which should be written as &
-- (24:XX) Warning: unescaped & which should be written as &
+- (24:1) Warning: discarding unexpected <bogotag>
+- (25:XX) Warning: unescaped & which should be written as &
+- (25:XX) Warning: unescaped & which should be written as &
};
chomp @expected_warnings;
shift @expected_warnings; # First one's blank
my @expected_errors = split /\n/, q{
-- (23:1) Error: <bogotag> is not recognized!
+- (24:1) Error: <bogotag> is not recognized!
};
chomp @expected_errors;
shift @expected_errors; # First one's blank
@@ -71,6 +70,7 @@ sub munge_returned {
}
}
__DATA__
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html;CHARSET=iso-8859-1">
diff --git a/t/levels.t b/t/levels.t
index 01aeb3b..2ee3162 100644
@@ -13,11 +13,10 @@ my $rc = $tidy->parse( '-', <DATA> );
ok( $rc, 'Parsed OK' );
my @expected = split /\n/, q{
-- (1:1) Warning: missing <!DOCTYPE> declaration
-- (23:1) Error: <bogotag> is not recognized!
-- (23:1) Warning: discarding unexpected <bogotag>
-- (24:XX) Warning: unescaped & which should be written as &
-- (24:XX) Warning: unescaped & which should be written as &
+- (24:1) Error: <bogotag> is not recognized!
+- (24:1) Warning: discarding unexpected <bogotag>
+- (25:XX) Warning: unescaped & which should be written as &
+- (25:XX) Warning: unescaped & which should be written as &
};
chomp @expected;
shift @expected; # First one's blank
@@ -41,6 +40,7 @@ sub munge_returned {
}
__DATA__
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html;CHARSET=iso-8859-1">
|
