summaryrefslogtreecommitdiff
path: root/i18npool/source/collator/collator_unicode.cxx
blob: c705ee9ca23918a6fbc6fe2f916f2be15d54c686 (plain)
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
/* -*- 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 .
 */


// generated list of languages
#include "lrl_include.hxx"

#include <rtl/ustrbuf.hxx>
#include <collator_unicode.hxx>
#include <localedata.hxx>
#include <com/sun/star/i18n/CollatorOptions.hpp>

using namespace ::com::sun::star;
using namespace ::com::sun::star::lang;
using namespace ::com::sun::star::uno;
using namespace ::rtl;

namespace com { namespace sun { namespace star { namespace i18n {

Collator_Unicode::Collator_Unicode()
{
    implementationName = "com.sun.star.i18n.Collator_Unicode";
    collator = NULL;
    uca_base = NULL;
#ifndef DISABLE_DYNLOADING
    hModule = NULL;
#endif
}

Collator_Unicode::~Collator_Unicode()
{
    if (collator) delete collator;
    if (uca_base) delete uca_base;
#ifndef DISABLE_DYNLOADING
    if (hModule) osl_unloadModule(hModule);
#endif
}

#ifdef DISABLE_DYNLOADING

extern "C" {

// For DISABLE_DYNLOADING the generated functions have names that
// start with get_collator_data_ to avoid clashing with a few
// functions in the generated libindex_data that are called just
// get_zh_pinyin for instance.

const sal_uInt8* get_collator_data_ca_charset();
const sal_uInt8* get_collator_data_dz_charset();
const sal_uInt8* get_collator_data_hu_charset();
const sal_uInt8* get_collator_data_ja_charset();
const sal_uInt8* get_collator_data_ja_phonetic_alphanumeric_first();
const sal_uInt8* get_collator_data_ja_phonetic_alphanumeric_last();
const sal_uInt8* get_collator_data_ko_charset();
const sal_uInt8* get_collator_data_ku_alphanumeric();
const sal_uInt8* get_collator_data_ln_charset();
const sal_uInt8* get_collator_data_my_dictionary();
const sal_uInt8* get_collator_data_ne_charset();
const sal_uInt8* get_collator_data_zh_TW_charset();
const sal_uInt8* get_collator_data_zh_TW_radical();
const sal_uInt8* get_collator_data_zh_TW_stroke();
const sal_uInt8* get_collator_data_zh_charset();
const sal_uInt8* get_collator_data_zh_pinyin();
const sal_uInt8* get_collator_data_zh_radical();
const sal_uInt8* get_collator_data_zh_stroke();
const sal_uInt8* get_collator_data_zh_zhuyin();

}

#endif

sal_Int32 SAL_CALL
Collator_Unicode::compareSubstring( const OUString& str1, sal_Int32 off1, sal_Int32 len1,
    const OUString& str2, sal_Int32 off2, sal_Int32 len2) throw(RuntimeException)
{
    return collator->compare(reinterpret_cast<const UChar *>(str1.getStr()) + off1, len1, reinterpret_cast<const UChar *>(str2.getStr()) + off2, len2); // UChar != sal_Unicode in MinGW
}

sal_Int32 SAL_CALL
Collator_Unicode::compareString( const OUString& str1, const OUString& str2) throw(RuntimeException)
{
    return collator->compare(reinterpret_cast<const UChar *>(str1.getStr()), reinterpret_cast<const UChar *>(str2.getStr()));   // UChar != sal_Unicode in MinGW
}

#ifndef DISABLE_DYNLOADING

extern "C" { static void SAL_CALL thisModule() {} }

#endif

sal_Int32 SAL_CALL
Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::Locale& rLocale, sal_Int32 options)
    throw(RuntimeException)
{
    if (!collator) {
        UErrorCode status = U_ZERO_ERROR;
        OUString rule = LocaleData().getCollatorRuleByAlgorithm(rLocale, rAlgorithm);
        if (!rule.isEmpty()) {
            collator = new RuleBasedCollator(reinterpret_cast<const UChar *>(rule.getStr()), status);   // UChar != sal_Unicode in MinGW
            if (! U_SUCCESS(status)) throw RuntimeException();
        }
        if (!collator && OUString::createFromAscii(LOCAL_RULE_LANGS).indexOf(rLocale.Language) >= 0) {
            const sal_uInt8* (*func)() = NULL;

#ifndef DISABLE_DYNLOADING
            OUStringBuffer aBuf;
#ifdef SAL_DLLPREFIX
            aBuf.appendAscii(SAL_DLLPREFIX);
#endif
            aBuf.appendAscii( "collator_data" ).appendAscii( SAL_DLLEXTENSION );
            hModule = osl_loadModuleRelative( &thisModule, aBuf.makeStringAndClear().pData, SAL_LOADMODULE_DEFAULT );
            if (hModule) {
                aBuf.appendAscii("get_").append(rLocale.Language).appendAscii("_");
                if ( rLocale.Language == "zh" ) {
                    OUString func_base = aBuf.makeStringAndClear();
                    if (OUString("TW HK MO").indexOf(rLocale.Country) >= 0)
                        func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule,
                                    (func_base + OUString("TW_") + rAlgorithm).pData);
                    if (!func)
                        func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule, (func_base + rAlgorithm).pData);
                } else {
                    if ( rLocale.Language == "ja" ) {
                        // replace algrithm name to implementation name.
                        if (rAlgorithm.equalsAsciiL(RTL_CONSTASCII_STRINGPARAM("phonetic (alphanumeric first)")) )
                            aBuf.appendAscii("phonetic_alphanumeric_first");
                        else if (rAlgorithm.equalsAsciiL(RTL_CONSTASCII_STRINGPARAM("phonetic (alphanumeric last)")))
                            aBuf.appendAscii("phonetic_alphanumeric_last");
                        else
                            aBuf.append(rAlgorithm);
                    } else {
                        aBuf.append(rAlgorithm);
                    }
                    func=(const sal_uInt8* (*)()) osl_getFunctionSymbol(hModule, aBuf.makeStringAndClear().pData);
                }
            }
#else
            if ( rLocale.Language == "ca" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_ca_charset;
            } else if ( rLocale.Language == "dz" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_dz_charset;
            } else if ( rLocale.Language == "hu" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_hu_charset;
            } else if ( rLocale.Language == "ja" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_hu_charset;
                else if ( rAlgorithm == "phonetic (alphanumeric first)" )
                    func = get_collator_data_ja_phonetic_alphanumeric_first;
                else if ( rAlgorithm == "phonetic (alphanumeric last)" )
                    func = get_collator_data_ja_phonetic_alphanumeric_last;
            } else if ( rLocale.Language == "ko" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_ko_charset;
            } else if ( rLocale.Language == "ku" ) {
                if ( rAlgorithm == "alphanumeric" )
                    func = get_collator_data_ku_alphanumeric;
            } else if ( rLocale.Language == "ln" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_ln_charset;
            } else if ( rLocale.Language == "my" ) {
                if ( rAlgorithm == "dictionary" )
                    func = get_collator_data_my_dictionary;
            } else if ( rLocale.Language == "ne" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_ne_charset;
            } else if ( rLocale.Language == "zh" && (rLocale.Country == "TW" || rLocale.Country == "HK" || rLocale.Country == "MO") ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_zh_TW_charset;
                else if ( rAlgorithm == "radical" )
                    func = get_collator_data_zh_TW_radical;
                else if ( rAlgorithm == "stroke" )
                    func = get_collator_data_zh_TW_stroke;
            } else if ( rLocale.Language == "zh" ) {
                if ( rAlgorithm == "charset" )
                    func = get_collator_data_zh_charset;
                else if ( rAlgorithm == "pinyin" )
                    func = get_collator_data_zh_pinyin;
                else if ( rAlgorithm == "radical" )
                    func = get_collator_data_zh_radical;
                else if ( rAlgorithm == "stroke" )
                    func = get_collator_data_zh_stroke;
                else if ( rAlgorithm == "zhuyin" )
                    func = get_collator_data_zh_zhuyin;
            }
#endif
            if (func) {
                const sal_uInt8* ruleImage=func();
                uca_base = new RuleBasedCollator(static_cast<UChar*>(NULL), status);
                if (! U_SUCCESS(status)) throw RuntimeException();
                collator = new RuleBasedCollator(reinterpret_cast<const uint8_t*>(ruleImage), -1, uca_base, status);
                if (! U_SUCCESS(status)) throw RuntimeException();
            }
        }
        if (!collator) {
            /** ICU collators are loaded using a locale only.
                ICU uses Variant as collation algorithm name (like de__PHONEBOOK
                locale), note the empty territory (Country) designator in this special
                case here. The icu::Locale contructor changes the algorithm name to
                uppercase itself, so we don't have to bother with that.
            */
            icu::Locale icuLocale(
                   OUStringToOString(rLocale.Language, RTL_TEXTENCODING_ASCII_US).getStr(),
                   OUStringToOString(rLocale.Country, RTL_TEXTENCODING_ASCII_US).getStr(),
                   OUStringToOString(rAlgorithm, RTL_TEXTENCODING_ASCII_US).getStr());
            // load ICU collator
            collator = (RuleBasedCollator*) icu::Collator::createInstance(icuLocale, status);
            if (! U_SUCCESS(status)) throw RuntimeException();
        }
    }

    if (options & CollatorOptions::CollatorOptions_IGNORE_CASE_ACCENT)
        collator->setStrength(Collator::PRIMARY);
    else if (options & CollatorOptions::CollatorOptions_IGNORE_CASE)
        collator->setStrength(Collator::SECONDARY);
    else
        collator->setStrength(Collator::TERTIARY);

    return(0);
}


OUString SAL_CALL
Collator_Unicode::getImplementationName() throw( RuntimeException )
{
    return OUString::createFromAscii(implementationName);
}

sal_Bool SAL_CALL
Collator_Unicode::supportsService(const rtl::OUString& rServiceName) throw( RuntimeException )
{
    return !rServiceName.compareToAscii(implementationName);
}

Sequence< OUString > SAL_CALL
Collator_Unicode::getSupportedServiceNames() throw( RuntimeException )
{
    Sequence< OUString > aRet(1);
    aRet[0] = OUString::createFromAscii(implementationName);
    return aRet;
}

} } } }

/* vim:set shiftwidth=4 softtabstop=4 expandtab: */