1
// Copyright 2013 The Closure Library Authors. All Rights Reserved.
2
//
3
// Licensed under the Apache License, Version 2.0 (the "License");
4
// you may not use this file except in compliance with the License.
5
// You may obtain a copy of the License at
6
//
7
//      http://www.apache.org/licenses/LICENSE-2.0
8
//
9
// Unless required by applicable law or agreed to in writing, software
10
// distributed under the License is distributed on an "AS-IS" BASIS,
11
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12
// See the License for the specific language governing permissions and
13
// limitations under the License.
14

15

16
/**
17
 * @fileoverview HTML processing utilities for HTML in string form.
18
 */
19

20
goog.provide('goog.html.utils');
21

22
goog.require('goog.string');
23

24

25
/**
26
 * Extracts plain text from HTML.
27
 *
28
 * This behaves similarly to extracting textContent from a hypothetical DOM
29
 * element containing the specified HTML.  Block-level elements such as div are
30
 * surrounded with whitespace, but inline elements are not.  Span is treated as
31
 * a block level element because it is often used as a container.  Breaking
32
 * spaces are compressed and trimmed.
33
 *
34
 * @param {string} value The input HTML to have tags removed.
35
 * @return {string} The plain text of value without tags, HTML comments, or
36
 *     other non-text content.  Does NOT return safe HTML!
37
 */
38
goog.html.utils.stripHtmlTags = function(value) {
39
  // TODO(user): Make a version that extracts text attributes such as alt.
40
  return goog.string.unescapeEntities(
41
      goog.string.trim(
42
          value
43
              .replace(
44
                  goog.html.utils.HTML_TAG_REGEX_,
45
                  function(fullMatch, tagName) {
46
                    return goog.html.utils.INLINE_HTML_TAG_REGEX_.test(
47
                               tagName) ?
48
                        '' :
49
                        ' ';
50
                  })
51
              .replace(/[\t\n ]+/g, ' ')));
52
};
53

54

55
/**
56
 * Matches all tags that do not require extra space.
57
 *
58
 * @private @const
59
 */
60
goog.html.utils.INLINE_HTML_TAG_REGEX_ =
61
    /^(?:abbr|acronym|address|b|em|i|small|strong|su[bp]|u)$/i;
62

63

64
/**
65
 * Matches all tags, HTML comments, and DOCTYPEs in tag soup HTML.
66
 * By removing these, and replacing any '<' or '>' characters with
67
 * entities we guarantee that the result can be embedded into
68
 * an attribute without introducing a tag boundary.
69
 *
70
 * @private @const
71
 */
72
goog.html.utils.HTML_TAG_REGEX_ = /<[!\/]?([a-z0-9]+)([\/ ][^>]*)?>/gi;
73

74