| 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ******************************************************************************** |
| 5 | * Copyright (C) 2005-2016, International Business Machines |
| 6 | * Corporation and others. All Rights Reserved. |
| 7 | ******************************************************************************** |
| 8 | */ |
| 9 | |
| 10 | #include "unicode/utypes.h" |
| 11 | |
| 12 | #if !UCONFIG_NO_CONVERSION |
| 13 | #include "unicode/ucsdet.h" |
| 14 | #include "csdetect.h" |
| 15 | #include "csmatch.h" |
| 16 | #include "csrsbcs.h" |
| 17 | #include "csrmbcs.h" |
| 18 | #include "csrutf8.h" |
| 19 | #include "csrucode.h" |
| 20 | #include "csr2022.h" |
| 21 | |
| 22 | #include "cmemory.h" |
| 23 | |
| 24 | U_NAMESPACE_USE |
| 25 | |
| 26 | #define NEW_ARRAY(type,count) (type *) uprv_malloc((count) * sizeof(type)) |
| 27 | #define DELETE_ARRAY(array) uprv_free((void *) (array)) |
| 28 | |
| 29 | U_CDECL_BEGIN |
| 30 | |
| 31 | U_CAPI UCharsetDetector * U_EXPORT2 |
| 32 | ucsdet_open(UErrorCode *status) |
| 33 | { |
| 34 | if(U_FAILURE(*status)) { |
| 35 | return 0; |
| 36 | } |
| 37 | |
| 38 | CharsetDetector* csd = new CharsetDetector(*status); |
| 39 | |
| 40 | if (U_FAILURE(*status)) { |
| 41 | delete csd; |
| 42 | csd = NULL; |
| 43 | } |
| 44 | |
| 45 | return (UCharsetDetector *) csd; |
| 46 | } |
| 47 | |
| 48 | U_CAPI void U_EXPORT2 |
| 49 | ucsdet_close(UCharsetDetector *ucsd) |
| 50 | { |
| 51 | CharsetDetector *csd = (CharsetDetector *) ucsd; |
| 52 | delete csd; |
| 53 | } |
| 54 | |
| 55 | U_CAPI void U_EXPORT2 |
| 56 | ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status) |
| 57 | { |
| 58 | if(U_FAILURE(*status)) { |
| 59 | return; |
| 60 | } |
| 61 | |
| 62 | ((CharsetDetector *) ucsd)->setText(textIn, len); |
| 63 | } |
| 64 | |
| 65 | U_CAPI const char * U_EXPORT2 |
| 66 | ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status) |
| 67 | { |
| 68 | if(U_FAILURE(*status)) { |
| 69 | return NULL; |
| 70 | } |
| 71 | |
| 72 | return ((CharsetMatch *) ucsm)->getName(); |
| 73 | } |
| 74 | |
| 75 | U_CAPI int32_t U_EXPORT2 |
| 76 | ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status) |
| 77 | { |
| 78 | if(U_FAILURE(*status)) { |
| 79 | return 0; |
| 80 | } |
| 81 | |
| 82 | return ((CharsetMatch *) ucsm)->getConfidence(); |
| 83 | } |
| 84 | |
| 85 | U_CAPI const char * U_EXPORT2 |
| 86 | ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status) |
| 87 | { |
| 88 | if(U_FAILURE(*status)) { |
| 89 | return NULL; |
| 90 | } |
| 91 | |
| 92 | return ((CharsetMatch *) ucsm)->getLanguage(); |
| 93 | } |
| 94 | |
| 95 | U_CAPI const UCharsetMatch * U_EXPORT2 |
| 96 | ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status) |
| 97 | { |
| 98 | if(U_FAILURE(*status)) { |
| 99 | return NULL; |
| 100 | } |
| 101 | |
| 102 | return (const UCharsetMatch *) ((CharsetDetector *) ucsd)->detect(*status); |
| 103 | } |
| 104 | |
| 105 | U_CAPI void U_EXPORT2 |
| 106 | ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status) |
| 107 | { |
| 108 | if(U_FAILURE(*status)) { |
| 109 | return; |
| 110 | } |
| 111 | |
| 112 | ((CharsetDetector *) ucsd)->setDeclaredEncoding(encoding,length); |
| 113 | } |
| 114 | |
| 115 | U_CAPI const UCharsetMatch** |
| 116 | ucsdet_detectAll(UCharsetDetector *ucsd, |
| 117 | int32_t *maxMatchesFound, UErrorCode *status) |
| 118 | { |
| 119 | if(U_FAILURE(*status)) { |
| 120 | return NULL; |
| 121 | } |
| 122 | |
| 123 | CharsetDetector *csd = (CharsetDetector *) ucsd; |
| 124 | |
| 125 | return (const UCharsetMatch**)csd->detectAll(*maxMatchesFound,*status); |
| 126 | } |
| 127 | |
| 128 | // U_CAPI const char * U_EXPORT2 |
| 129 | // ucsdet_getDetectableCharsetName(const UCharsetDetector *csd, int32_t index, UErrorCode *status) |
| 130 | // { |
| 131 | // if(U_FAILURE(*status)) { |
| 132 | // return 0; |
| 133 | // } |
| 134 | // return csd->getCharsetName(index,*status); |
| 135 | // } |
| 136 | |
| 137 | // U_CAPI int32_t U_EXPORT2 |
| 138 | // ucsdet_getDetectableCharsetsCount(const UCharsetDetector *csd, UErrorCode *status) |
| 139 | // { |
| 140 | // if(U_FAILURE(*status)) { |
| 141 | // return -1; |
| 142 | // } |
| 143 | // return UCharsetDetector::getDetectableCount(); |
| 144 | // } |
| 145 | |
| 146 | U_CAPI UBool U_EXPORT2 |
| 147 | ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd) |
| 148 | { |
| 149 | // todo: could use an error return... |
| 150 | if (ucsd == NULL) { |
| 151 | return FALSE; |
| 152 | } |
| 153 | |
| 154 | return ((CharsetDetector *) ucsd)->getStripTagsFlag(); |
| 155 | } |
| 156 | |
| 157 | U_CAPI UBool U_EXPORT2 |
| 158 | ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter) |
| 159 | { |
| 160 | // todo: could use an error return... |
| 161 | if (ucsd == NULL) { |
| 162 | return FALSE; |
| 163 | } |
| 164 | |
| 165 | CharsetDetector *csd = (CharsetDetector *) ucsd; |
| 166 | UBool prev = csd->getStripTagsFlag(); |
| 167 | |
| 168 | csd->setStripTagsFlag(filter); |
| 169 | |
| 170 | return prev; |
| 171 | } |
| 172 | |
| 173 | U_CAPI int32_t U_EXPORT2 |
| 174 | ucsdet_getUChars(const UCharsetMatch *ucsm, |
| 175 | UChar *buf, int32_t cap, UErrorCode *status) |
| 176 | { |
| 177 | if(U_FAILURE(*status)) { |
| 178 | return 0; |
| 179 | } |
| 180 | |
| 181 | return ((CharsetMatch *) ucsm)->getUChars(buf, cap, status); |
| 182 | } |
| 183 | |
| 184 | U_CAPI void U_EXPORT2 |
| 185 | ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status) |
| 186 | { |
| 187 | ((CharsetDetector *)ucsd)->setDetectableCharset(encoding, enabled, *status); |
| 188 | } |
| 189 | |
| 190 | U_CAPI UEnumeration * U_EXPORT2 |
| 191 | ucsdet_getAllDetectableCharsets(const UCharsetDetector * /*ucsd*/, UErrorCode *status) |
| 192 | { |
| 193 | return CharsetDetector::getAllDetectableCharsets(*status); |
| 194 | } |
| 195 | |
| 196 | U_DRAFT UEnumeration * U_EXPORT2 |
| 197 | ucsdet_getDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status) |
| 198 | { |
| 199 | return ((CharsetDetector *)ucsd)->getDetectableCharsets(*status); |
| 200 | } |
| 201 | |
| 202 | U_CDECL_END |
| 203 | |
| 204 | |
| 205 | #endif |
| 206 | |