2
* Copyright 2010 Google Inc.
4
* Licensed under the Apache License, Version 2.0 (the "License");
5
* you may not use this file except in compliance with the License.
6
* You may obtain a copy of the License at
8
* http://www.apache.org/licenses/LICENSE-2.0
10
* Unless required by applicable law or agreed to in writing, software
11
* distributed under the License is distributed on an "AS IS" BASIS,
12
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
* See the License for the specific language governing permissions and
14
* limitations under the License.
17
// Author: jmaessen@google.com (Jan Maessen)
19
#ifndef PAGESPEED_KERNEL_HTML_HTML_ATTRIBUTE_QUOTE_REMOVAL_H_
20
#define PAGESPEED_KERNEL_HTML_HTML_ATTRIBUTE_QUOTE_REMOVAL_H_
22
#include "pagespeed/kernel/base/basictypes.h"
23
#include "pagespeed/kernel/html/empty_html_filter.h"
25
namespace net_instaweb {
26
// Very simple html filter that removes quotes from attributes that don't need
29
// From http://www.w3.org/TR/REC-html40/intro/sgmltut.html#h-3.2.2:
30
// In certain cases, authors may specify the value of an attribute without any
31
// quotation marks. The attribute value may only contain letters (a-z and A-Z),
32
// digits (0-9), hyphens (ASCII decimal 45), periods (ASCII decimal 46),
33
// underscores (ASCII decimal 95), and colons (ASCII decimal 58).
35
// This is an experiment, to see if quote removal *actually* saves bandwidth.
36
// After compression it may not (or may not save enough). In that case we
37
// should not bother with quote removal.
42
class HtmlAttributeQuoteRemoval : public EmptyHtmlFilter {
44
explicit HtmlAttributeQuoteRemoval(HtmlParse* html_parse);
45
virtual ~HtmlAttributeQuoteRemoval();
46
// Given context in object, does attribute value val require quotes?
47
bool NeedsQuotes(const char *val);
48
virtual void StartElement(HtmlElement* element);
49
// # of quote pairs removed from attributes in *all* documents processed.
50
int total_quotes_removed() const {
51
return total_quotes_removed_;
54
virtual const char* Name() const { return "HtmlAttributeQuoteRemoval"; }
57
int total_quotes_removed_;
58
HtmlParse* html_parse_;
59
bool needs_no_quotes_[256]; // lookup chars for quotability
60
// should be const, but C++ initializer rules are broken.
62
DISALLOW_COPY_AND_ASSIGN(HtmlAttributeQuoteRemoval);
65
} // namespace net_instaweb
67
#endif // PAGESPEED_KERNEL_HTML_HTML_ATTRIBUTE_QUOTE_REMOVAL_H_