1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/i18n/ucsdet.cpp Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,205 @@
1.4 +/*
1.5 + ********************************************************************************
1.6 + * Copyright (C) 2005-2013, International Business Machines
1.7 + * Corporation and others. All Rights Reserved.
1.8 + ********************************************************************************
1.9 + */
1.10 +
1.11 +#include "unicode/utypes.h"
1.12 +
1.13 +#if !UCONFIG_NO_CONVERSION
1.14 +#include "unicode/ucsdet.h"
1.15 +#include "csdetect.h"
1.16 +#include "csmatch.h"
1.17 +#include "csrsbcs.h"
1.18 +#include "csrmbcs.h"
1.19 +#include "csrutf8.h"
1.20 +#include "csrucode.h"
1.21 +#include "csr2022.h"
1.22 +
1.23 +#include "cmemory.h"
1.24 +
1.25 +U_NAMESPACE_USE
1.26 +
1.27 +#define ARRAY_SIZE(array) (sizeof array / sizeof array[0])
1.28 +
1.29 +#define NEW_ARRAY(type,count) (type *) uprv_malloc((count) * sizeof(type))
1.30 +#define DELETE_ARRAY(array) uprv_free((void *) (array))
1.31 +
1.32 +U_CDECL_BEGIN
1.33 +
1.34 +U_CAPI UCharsetDetector * U_EXPORT2
1.35 +ucsdet_open(UErrorCode *status)
1.36 +{
1.37 + if(U_FAILURE(*status)) {
1.38 + return 0;
1.39 + }
1.40 +
1.41 + CharsetDetector* csd = new CharsetDetector(*status);
1.42 +
1.43 + if (U_FAILURE(*status)) {
1.44 + delete csd;
1.45 + csd = NULL;
1.46 + }
1.47 +
1.48 + return (UCharsetDetector *) csd;
1.49 +}
1.50 +
1.51 +U_CAPI void U_EXPORT2
1.52 +ucsdet_close(UCharsetDetector *ucsd)
1.53 +{
1.54 + CharsetDetector *csd = (CharsetDetector *) ucsd;
1.55 + delete csd;
1.56 +}
1.57 +
1.58 +U_CAPI void U_EXPORT2
1.59 +ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status)
1.60 +{
1.61 + if(U_FAILURE(*status)) {
1.62 + return;
1.63 + }
1.64 +
1.65 + ((CharsetDetector *) ucsd)->setText(textIn, len);
1.66 +}
1.67 +
1.68 +U_CAPI const char * U_EXPORT2
1.69 +ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status)
1.70 +{
1.71 + if(U_FAILURE(*status)) {
1.72 + return NULL;
1.73 + }
1.74 +
1.75 + return ((CharsetMatch *) ucsm)->getName();
1.76 +}
1.77 +
1.78 +U_CAPI int32_t U_EXPORT2
1.79 +ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status)
1.80 +{
1.81 + if(U_FAILURE(*status)) {
1.82 + return 0;
1.83 + }
1.84 +
1.85 + return ((CharsetMatch *) ucsm)->getConfidence();
1.86 +}
1.87 +
1.88 +U_CAPI const char * U_EXPORT2
1.89 +ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status)
1.90 +{
1.91 + if(U_FAILURE(*status)) {
1.92 + return NULL;
1.93 + }
1.94 +
1.95 + return ((CharsetMatch *) ucsm)->getLanguage();
1.96 +}
1.97 +
1.98 +U_CAPI const UCharsetMatch * U_EXPORT2
1.99 +ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status)
1.100 +{
1.101 + if(U_FAILURE(*status)) {
1.102 + return NULL;
1.103 + }
1.104 +
1.105 + return (const UCharsetMatch *) ((CharsetDetector *) ucsd)->detect(*status);
1.106 +}
1.107 +
1.108 +U_CAPI void U_EXPORT2
1.109 +ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status)
1.110 +{
1.111 + if(U_FAILURE(*status)) {
1.112 + return;
1.113 + }
1.114 +
1.115 + ((CharsetDetector *) ucsd)->setDeclaredEncoding(encoding,length);
1.116 +}
1.117 +
1.118 +U_CAPI const UCharsetMatch**
1.119 +ucsdet_detectAll(UCharsetDetector *ucsd,
1.120 + int32_t *maxMatchesFound, UErrorCode *status)
1.121 +{
1.122 + if(U_FAILURE(*status)) {
1.123 + return NULL;
1.124 + }
1.125 +
1.126 + CharsetDetector *csd = (CharsetDetector *) ucsd;
1.127 +
1.128 + return (const UCharsetMatch**)csd->detectAll(*maxMatchesFound,*status);
1.129 +}
1.130 +
1.131 +// U_CAPI const char * U_EXPORT2
1.132 +// ucsdet_getDetectableCharsetName(const UCharsetDetector *csd, int32_t index, UErrorCode *status)
1.133 +// {
1.134 +// if(U_FAILURE(*status)) {
1.135 +// return 0;
1.136 +// }
1.137 +// return csd->getCharsetName(index,*status);
1.138 +// }
1.139 +
1.140 +// U_CAPI int32_t U_EXPORT2
1.141 +// ucsdet_getDetectableCharsetsCount(const UCharsetDetector *csd, UErrorCode *status)
1.142 +// {
1.143 +// if(U_FAILURE(*status)) {
1.144 +// return -1;
1.145 +// }
1.146 +// return UCharsetDetector::getDetectableCount();
1.147 +// }
1.148 +
1.149 +U_CAPI UBool U_EXPORT2
1.150 +ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd)
1.151 +{
1.152 + // todo: could use an error return...
1.153 + if (ucsd == NULL) {
1.154 + return FALSE;
1.155 + }
1.156 +
1.157 + return ((CharsetDetector *) ucsd)->getStripTagsFlag();
1.158 +}
1.159 +
1.160 +U_CAPI UBool U_EXPORT2
1.161 +ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter)
1.162 +{
1.163 + // todo: could use an error return...
1.164 + if (ucsd == NULL) {
1.165 + return FALSE;
1.166 + }
1.167 +
1.168 + CharsetDetector *csd = (CharsetDetector *) ucsd;
1.169 + UBool prev = csd->getStripTagsFlag();
1.170 +
1.171 + csd->setStripTagsFlag(filter);
1.172 +
1.173 + return prev;
1.174 +}
1.175 +
1.176 +U_CAPI int32_t U_EXPORT2
1.177 +ucsdet_getUChars(const UCharsetMatch *ucsm,
1.178 + UChar *buf, int32_t cap, UErrorCode *status)
1.179 +{
1.180 + if(U_FAILURE(*status)) {
1.181 + return 0;
1.182 + }
1.183 +
1.184 + return ((CharsetMatch *) ucsm)->getUChars(buf, cap, status);
1.185 +}
1.186 +
1.187 +U_CAPI void U_EXPORT2
1.188 +ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status)
1.189 +{
1.190 + ((CharsetDetector *)ucsd)->setDetectableCharset(encoding, enabled, *status);
1.191 +}
1.192 +
1.193 +U_CAPI UEnumeration * U_EXPORT2
1.194 +ucsdet_getAllDetectableCharsets(const UCharsetDetector * /*ucsd*/, UErrorCode *status)
1.195 +{
1.196 + return CharsetDetector::getAllDetectableCharsets(*status);
1.197 +}
1.198 +
1.199 +U_DRAFT UEnumeration * U_EXPORT2
1.200 +ucsdet_getDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status)
1.201 +{
1.202 + return ((CharsetDetector *)ucsd)->getDetectableCharsets(*status);
1.203 +}
1.204 +
1.205 +U_CDECL_END
1.206 +
1.207 +
1.208 +#endif
