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
|
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* This file is part of the LibreOffice project.
*
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/.
*
* This file incorporates work covered by the following license notice:
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed
* with this work for additional information regarding copyright
* ownership. The ASF licenses this file to you under the Apache
* License, Version 2.0 (the "License"); you may not use this file
* except in compliance with the License. You may obtain a copy of
* the License at http://www.apache.org/licenses/LICENSE-2.0 .
*/
#pragma once
#include <osl/file.h>
#include <sal/types.h>
#include <com/sun/star/i18n/Boundary.hpp>
namespace i18npool {
#define CACHE_MAX 32 // max cache structure number
#define DEFAULT_SIZE 256 // for boundary size, to avoid alloc and release memory
// cache structure.
struct WordBreakCache {
sal_Unicode *contents; // separated segment contents.
sal_Int32* wordboundary; // word boundaries in segments.
sal_Int32 length; // contents length saved here.
sal_Int32 size; // size of wordboundary
WordBreakCache();
bool equals(const sal_Unicode *str, css::i18n::Boundary const & boundary) const; // checking cached string
};
struct xdictionarydata
{
const sal_uInt8 * existMark;
const sal_Int16 * index1;
const sal_Int32 * index2;
const sal_Int32 * lenArray;
const sal_Unicode* dataArea;
xdictionarydata() :
existMark( nullptr ),
index1( nullptr ),
index2( nullptr ),
lenArray( nullptr ),
dataArea( nullptr )
{
}
};
class xdictionary
{
private:
xdictionarydata data;
void initDictionaryData(const char *lang);
css::i18n::Boundary boundary;
bool japaneseWordBreak;
#ifdef DICT_JA_ZH_IN_DATAFILE
oslFileHandle m_aFileHandle;
sal_uInt64 m_nFileSize;
char* m_pMapping;
#endif
public:
xdictionary(const char *lang);
~xdictionary();
css::i18n::Boundary nextWord( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType);
css::i18n::Boundary previousWord( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType);
css::i18n::Boundary const & getWordBoundary( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType, bool bDirection );
void setJapaneseWordBreak();
private:
WordBreakCache cache[CACHE_MAX];
OUString segmentCachedString;
css::i18n::Boundary segmentCachedBoundary;
bool seekSegment(const OUString& rText, sal_Int32 pos, css::i18n::Boundary& boundary);
WordBreakCache& getCache(const sal_Unicode *text, css::i18n::Boundary const & boundary);
bool exists(const sal_uInt32 u) const;
sal_Int32 getLongestMatch(const sal_Unicode *text, sal_Int32 len) const;
};
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|
