DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (31ec81b5d7bb)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
/*
 **********************************************************************
 *   Copyright (C) 2005-2012, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 */

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/ucsdet.h"

#include "csdetect.h"
#include "csmatch.h"
#include "uenumimp.h"

#include "cmemory.h"
#include "cstring.h"
#include "umutex.h"
#include "ucln_in.h"
#include "uarrsort.h"
#include "inputext.h"
#include "csrsbcs.h"
#include "csrmbcs.h"
#include "csrutf8.h"
#include "csrucode.h"
#include "csr2022.h"

#define ARRAY_SIZE(array) (sizeof array / sizeof array[0])

#define NEW_ARRAY(type,count) (type *) uprv_malloc((count) * sizeof(type))
#define DELETE_ARRAY(array) uprv_free((void *) (array))

U_CDECL_BEGIN
static icu::CharsetRecognizer **fCSRecognizers = NULL;

static int32_t fCSRecognizers_size = 0;

static UBool U_CALLCONV csdet_cleanup(void)
{
    if (fCSRecognizers != NULL) {
        for(int32_t r = 0; r < fCSRecognizers_size; r += 1) {
            delete fCSRecognizers[r];
            fCSRecognizers[r] = NULL;
        }

        DELETE_ARRAY(fCSRecognizers);
        fCSRecognizers = NULL;
        fCSRecognizers_size = 0;
    }

    return TRUE;
}

static int32_t U_CALLCONV
charsetMatchComparator(const void * /*context*/, const void *left, const void *right)
{
    U_NAMESPACE_USE

    const CharsetMatch **csm_l = (const CharsetMatch **) left;
    const CharsetMatch **csm_r = (const CharsetMatch **) right;

    // NOTE: compare is backwards to sort from highest to lowest.
    return (*csm_r)->getConfidence() - (*csm_l)->getConfidence();
}

U_CDECL_END

U_NAMESPACE_BEGIN

void CharsetDetector::setRecognizers(UErrorCode &status)
{
    UBool needsInit;
    CharsetRecognizer **recognizers;

    if (U_FAILURE(status)) {
        return;
    }

    UMTX_CHECK(NULL, (UBool) (fCSRecognizers == NULL), needsInit);

    if (needsInit) {
        CharsetRecognizer *tempArray[] = {
            new CharsetRecog_UTF8(),

            new CharsetRecog_UTF_16_BE(),
            new CharsetRecog_UTF_16_LE(),
            new CharsetRecog_UTF_32_BE(),
            new CharsetRecog_UTF_32_LE(),

            new CharsetRecog_8859_1(),
            new CharsetRecog_8859_2(),
            new CharsetRecog_8859_5_ru(),
            new CharsetRecog_8859_6_ar(),
            new CharsetRecog_8859_7_el(),
            new CharsetRecog_8859_8_I_he(),
            new CharsetRecog_8859_8_he(),
            new CharsetRecog_windows_1251(),
            new CharsetRecog_windows_1256(),
            new CharsetRecog_KOI8_R(),
            new CharsetRecog_8859_9_tr(),
            new CharsetRecog_sjis(),
            new CharsetRecog_gb_18030(),
            new CharsetRecog_euc_jp(),
            new CharsetRecog_euc_kr(),
            new CharsetRecog_big5(),

            new CharsetRecog_2022JP(),
            new CharsetRecog_2022KR(),
            new CharsetRecog_2022CN(),
            
            new CharsetRecog_IBM424_he_rtl(),
            new CharsetRecog_IBM424_he_ltr(),
            new CharsetRecog_IBM420_ar_rtl(),
            new CharsetRecog_IBM420_ar_ltr()
        };
        int32_t rCount = ARRAY_SIZE(tempArray);
        int32_t r;

        recognizers = NEW_ARRAY(CharsetRecognizer *, rCount);

        if (recognizers == NULL) {
            status = U_MEMORY_ALLOCATION_ERROR;
            return;
        } else {
            for (r = 0; r < rCount; r += 1) {
                recognizers[r] = tempArray[r];

                if (recognizers[r] == NULL) {
                    status = U_MEMORY_ALLOCATION_ERROR;
                    break;
                }
            }
        }

        if (U_SUCCESS(status)) {
            umtx_lock(NULL);
            if (fCSRecognizers == NULL) {
                fCSRecognizers_size = rCount;
                fCSRecognizers = recognizers;
            }
            umtx_unlock(NULL);
        }

        if (fCSRecognizers != recognizers) {
            for (r = 0; r < rCount; r += 1) {
                delete recognizers[r];
                recognizers[r] = NULL;
            }

            DELETE_ARRAY(recognizers);
        }

        recognizers = NULL;
        ucln_i18n_registerCleanup(UCLN_I18N_CSDET, csdet_cleanup);
    }
}

CharsetDetector::CharsetDetector(UErrorCode &status)
  : textIn(new InputText(status)), resultArray(NULL),
    resultCount(0), fStripTags(FALSE), fFreshTextSet(FALSE)
{
    if (U_FAILURE(status)) {
        return;
    }

    setRecognizers(status);

    if (U_FAILURE(status)) {
        return;
    }

    resultArray = (CharsetMatch **)uprv_malloc(sizeof(CharsetMatch *)*fCSRecognizers_size);

    if (resultArray == NULL) {
        status = U_MEMORY_ALLOCATION_ERROR;
        return;
    }

    for(int32_t i = 0; i < fCSRecognizers_size; i += 1) {
        resultArray[i] = new CharsetMatch();

        if (resultArray[i] == NULL) {
            status = U_MEMORY_ALLOCATION_ERROR;
            break;
        }
    }
}

CharsetDetector::~CharsetDetector()
{
    delete textIn;

    for(int32_t i = 0; i < fCSRecognizers_size; i += 1) {
        delete resultArray[i];
    }

    uprv_free(resultArray);
}

void CharsetDetector::setText(const char *in, int32_t len)
{
    textIn->setText(in, len);
    fFreshTextSet = TRUE;
}

UBool CharsetDetector::setStripTagsFlag(UBool flag)
{
    UBool temp = fStripTags;
    fStripTags = flag;
    fFreshTextSet = TRUE;
    return temp;
}

UBool CharsetDetector::getStripTagsFlag() const
{
    return fStripTags;
}

void CharsetDetector::setDeclaredEncoding(const char *encoding, int32_t len) const
{
    textIn->setDeclaredEncoding(encoding,len);
}

int32_t CharsetDetector::getDetectableCount()
{
    UErrorCode status = U_ZERO_ERROR;

    setRecognizers(status);

    return fCSRecognizers_size; 
}

const CharsetMatch *CharsetDetector::detect(UErrorCode &status)
{
    int32_t maxMatchesFound = 0;

    detectAll(maxMatchesFound, status);

    if(maxMatchesFound > 0) {
        return resultArray[0];
    } else {
        return NULL;
    }
}

const CharsetMatch * const *CharsetDetector::detectAll(int32_t &maxMatchesFound, UErrorCode &status)
{
    if(!textIn->isSet()) {
        status = U_MISSING_RESOURCE_ERROR;// TODO:  Need to set proper status code for input text not set

        return NULL;
    } else if (fFreshTextSet) {
        CharsetRecognizer *csr;
        int32_t            i;

        textIn->MungeInput(fStripTags);

        // Iterate over all possible charsets, remember all that
        // give a match quality > 0.
        resultCount = 0;
        for (i = 0; i < fCSRecognizers_size; i += 1) {
            csr = fCSRecognizers[i];
            if (csr->match(textIn, resultArray[resultCount])) {
                resultCount++;
            }
        }

        if (resultCount > 1) {
            uprv_sortArray(resultArray, resultCount, sizeof resultArray[0], charsetMatchComparator, NULL, TRUE, &status);
        }
        fFreshTextSet = FALSE;
    }

    maxMatchesFound = resultCount;

    return resultArray;
}

/*const char *CharsetDetector::getCharsetName(int32_t index, UErrorCode &status) const
{
    if( index > fCSRecognizers_size-1 || index < 0) {
        status = U_INDEX_OUTOFBOUNDS_ERROR;

        return 0;
    } else {
        return fCSRecognizers[index]->getName();
    }
}*/

U_NAMESPACE_END

U_CDECL_BEGIN
typedef struct {
    int32_t currIndex;
} Context;



static void U_CALLCONV
enumClose(UEnumeration *en) {
    if(en->context != NULL) {
        DELETE_ARRAY(en->context);
    }

    DELETE_ARRAY(en);
}

static int32_t U_CALLCONV
enumCount(UEnumeration *, UErrorCode *) {
    return fCSRecognizers_size;
}

static const char* U_CALLCONV
enumNext(UEnumeration *en, int32_t *resultLength, UErrorCode * /*status*/) {
    if(((Context *)en->context)->currIndex >= fCSRecognizers_size) {
        if(resultLength != NULL) {
            *resultLength = 0;
        }
        return NULL;
    }
    const char *currName = fCSRecognizers[((Context *)en->context)->currIndex]->getName();
    if(resultLength != NULL) {
        *resultLength = (int32_t)uprv_strlen(currName);
    }
    ((Context *)en->context)->currIndex++;

    return currName;
}

static void U_CALLCONV
enumReset(UEnumeration *en, UErrorCode *) {
    ((Context *)en->context)->currIndex = 0;
}

static const UEnumeration gCSDetEnumeration = {
    NULL,
    NULL,
    enumClose,
    enumCount,
    uenum_unextDefault,
    enumNext,
    enumReset
};

U_CAPI  UEnumeration * U_EXPORT2
ucsdet_getAllDetectableCharsets(const UCharsetDetector * /*ucsd*/, UErrorCode *status)
{
    U_NAMESPACE_USE

    if(U_FAILURE(*status)) {
        return 0;
    }

    /* Initialize recognized charsets. */
    CharsetDetector::getDetectableCount();

    UEnumeration *en = NEW_ARRAY(UEnumeration, 1);
    memcpy(en, &gCSDetEnumeration, sizeof(UEnumeration));
    en->context = (void*)NEW_ARRAY(Context, 1);
    uprv_memset(en->context, 0, sizeof(Context));
    return en;
}
U_CDECL_END

#endif