1/*
2 * Copyright (C) 2003, 2006, 2008, 2009, 2010, 2011 Apple Inc. All rights reserved.
3 * Copyright (C) 2008 Holger Hans Peter Freyther
4 * Copyright (C) Research In Motion Limited 2011. All rights reserved.
5 *
6 * This library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Library General Public
8 * License as published by the Free Software Foundation; either
9 * version 2 of the License, or (at your option) any later version.
10 *
11 * This library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14 * Library General Public License for more details.
15 *
16 * You should have received a copy of the GNU Library General Public License
17 * along with this library; see the file COPYING.LIB.  If not, write to
18 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
19 * Boston, MA 02110-1301, USA.
20 *
21 */
22
23#include "config.h"
24#include "platform/text/SurrogatePairAwareTextIterator.h"
25
26#include <unicode/unorm.h>
27
28using namespace WTF;
29using namespace Unicode;
30
31namespace blink {
32
33SurrogatePairAwareTextIterator::SurrogatePairAwareTextIterator(const UChar* characters, int currentCharacter, int lastCharacter, int endCharacter)
34    : m_characters(characters)
35    , m_currentCharacter(currentCharacter)
36    , m_lastCharacter(lastCharacter)
37    , m_endCharacter(endCharacter)
38{
39}
40
41bool SurrogatePairAwareTextIterator::consumeSlowCase(UChar32& character, unsigned& clusterLength)
42{
43    if (character <= 0x30FE) {
44        // Deal with Hiragana and Katakana voiced and semi-voiced syllables.
45        // Normalize into composed form, and then look for glyph with base + combined mark.
46        // Check above for character range to minimize performance impact.
47        if (UChar32 normalized = normalizeVoicingMarks()) {
48            character = normalized;
49            clusterLength = 2;
50        }
51        return true;
52    }
53
54    if (!U16_IS_SURROGATE(character))
55        return true;
56
57    // If we have a surrogate pair, make sure it starts with the high part.
58    if (!U16_IS_SURROGATE_LEAD(character))
59        return false;
60
61    // Do we have a surrogate pair? If so, determine the full Unicode (32 bit) code point before glyph lookup.
62    // Make sure we have another character and it's a low surrogate.
63    if (m_currentCharacter + 1 >= m_endCharacter)
64        return false;
65
66    UChar low = m_characters[1];
67    if (!U16_IS_TRAIL(low))
68        return false;
69
70    character = U16_GET_SUPPLEMENTARY(character, low);
71    clusterLength = 2;
72    return true;
73}
74
75UChar32 SurrogatePairAwareTextIterator::normalizeVoicingMarks()
76{
77    // According to http://www.unicode.org/Public/UNIDATA/UCD.html#Canonical_Combining_Class_Values
78    static const uint8_t hiraganaKatakanaVoicingMarksCombiningClass = 8;
79
80    if (m_currentCharacter + 1 >= m_endCharacter)
81        return 0;
82
83    if (combiningClass(m_characters[1]) == hiraganaKatakanaVoicingMarksCombiningClass) {
84        // Normalize into composed form using 3.2 rules.
85        UChar normalizedCharacters[2] = { 0, 0 };
86        UErrorCode uStatus = U_ZERO_ERROR;
87        int32_t resultLength = unorm_normalize(m_characters, 2, UNORM_NFC, UNORM_UNICODE_3_2, &normalizedCharacters[0], 2, &uStatus);
88        if (resultLength == 1 && !uStatus)
89            return normalizedCharacters[0];
90    }
91
92    return 0;
93}
94
95}
96