1 /*
2 * Copyright (C) 2010 Google Inc. All rights reserved.
3 *
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions
6 * are met:
7 * 1. Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * 2. Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 *
13 * THIS SOFTWARE IS PROVIDED BY APPLE COMPUTER, INC. ``AS IS'' AND ANY
14 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
16 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE COMPUTER, INC. OR
17 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
18 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
19 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
20 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
21 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
22 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
23 */
24
25 #include "third_party/blink/renderer/core/html/parser/text_document_parser.h"
26
27 #include "third_party/blink/renderer/core/html/parser/html_tree_builder.h"
28 #include "third_party/blink/renderer/core/html/parser/parser_synchronization_policy.h"
29 #include "third_party/blink/renderer/core/html_names.h"
30
31 namespace blink {
32
TextDocumentParser(HTMLDocument & document,ParserSynchronizationPolicy sync_policy)33 TextDocumentParser::TextDocumentParser(HTMLDocument& document,
34 ParserSynchronizationPolicy sync_policy)
35 : HTMLDocumentParser(document, sync_policy),
36 have_inserted_fake_pre_element_(false) {}
37
38 TextDocumentParser::~TextDocumentParser() = default;
39
AppendBytes(const char * data,size_t length)40 void TextDocumentParser::AppendBytes(const char* data, size_t length) {
41 if (!length || IsStopped())
42 return;
43
44 if (!have_inserted_fake_pre_element_)
45 InsertFakePreElement();
46 HTMLDocumentParser::AppendBytes(data, length);
47 }
48
InsertFakePreElement()49 void TextDocumentParser::InsertFakePreElement() {
50 // In principle, we should create a specialized tree builder for
51 // TextDocuments, but instead we re-use the existing HTMLTreeBuilder. We
52 // create a fake token and give it to the tree builder rather than sending
53 // fake bytes through the front-end of the parser to avoid distrubing the
54 // line/column number calculations.
55 Vector<Attribute> attributes;
56 attributes.push_back(Attribute(
57 html_names::kStyleAttr, "word-wrap: break-word; white-space: pre-wrap;"));
58 AtomicHTMLToken fake_pre(HTMLToken::kStartTag,
59 html_names::kPreTag.LocalName(), attributes);
60 TreeBuilder()->ConstructTree(&fake_pre);
61
62 // The document could have been detached by an extension while the
63 // tree was being constructed.
64 if (IsStopped())
65 return;
66
67 // Normally we would skip the first \n after a <pre> element, but we don't
68 // want to skip the first \n for text documents!
69 TreeBuilder()->SetShouldSkipLeadingNewline(false);
70
71 // Although Text Documents expose a "pre" element in their DOM, they
72 // act like a <plaintext> tag, so we have to force plaintext mode.
73 ForcePlaintextForTextDocument();
74
75 have_inserted_fake_pre_element_ = true;
76 }
77
78 } // namespace blink
79