C++ UnicodeSet::toUSet方法代码示例

void AlphabeticIndex::addIndexExemplars(const Locale &locale, UErrorCode &status) {
    LocalULocaleDataPointer uld(ulocdata_open(locale.getName(), &status));
    if (U_FAILURE(status)) {
        return;
    }

    UnicodeSet exemplars;
    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_INDEX, &status);
    if (U_SUCCESS(status)) {
        initialLabels_->addAll(exemplars);
        return;
    }
    status = U_ZERO_ERROR;  // Clear out U_MISSING_RESOURCE_ERROR

    // The locale data did not include explicit Index characters.
    // Synthesize a set of them from the locale's standard exemplar characters.
    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_STANDARD, &status);
    if (U_FAILURE(status)) {
        return;
    }

    // question: should we add auxiliary exemplars?
    if (exemplars.containsSome(0x61, 0x7A) /* a-z */ || exemplars.size() == 0) {
        exemplars.add(0x61, 0x7A);
    }
    if (exemplars.containsSome(0xAC00, 0xD7A3)) {  // Hangul syllables
        // cut down to small list
        exemplars.remove(0xAC00, 0xD7A3).
            add(0xAC00).add(0xB098).add(0xB2E4).add(0xB77C).
            add(0xB9C8).add(0xBC14).add(0xC0AC).add(0xC544).
            add(0xC790).add(0xCC28).add(0xCE74).add(0xD0C0).
            add(0xD30C).add(0xD558);
    }
    if (exemplars.containsSome(0x1200, 0x137F)) {  // Ethiopic block
        // cut down to small list
        // make use of the fact that Ethiopic is allocated in 8's, where
        // the base is 0 mod 8.
        UnicodeSet ethiopic(
            UNICODE_STRING_SIMPLE("[[:Block=Ethiopic:]&[:Script=Ethiopic:]]"), status);
        UnicodeSetIterator it(ethiopic);
        while (it.next() && !it.isString()) {
            if ((it.getCodepoint() & 0x7) != 0) {
                exemplars.remove(it.getCodepoint());
            }
        }
    }

    // Upper-case any that aren't already so.
    //   (We only do this for synthesized index characters.)
    UnicodeSetIterator it(exemplars);
    UnicodeString upperC;
    while (it.next()) {
        const UnicodeString &exemplarC = it.getString();
        upperC = exemplarC;
        upperC.toUpper(locale);
        initialLabels_->add(upperC);
    }
}

void LocalPointerTest::TestLocalXyzPointerMoveSwap() {
#if !UCONFIG_NO_NORMALIZATION
    IcuTestErrorCode errorCode(*this, "TestLocalXyzPointerMoveSwap");
    const UNormalizer2 *nfc=unorm2_getNFCInstance(errorCode);
    const UNormalizer2 *nfd=unorm2_getNFDInstance(errorCode);
    if(errorCode.logIfFailureAndReset("unorm2_getNF[CD]Instance()")) {
        return;
    }
    UnicodeSet emptySet;
    UNormalizer2 *p1 = unorm2_openFiltered(nfc, emptySet.toUSet(), errorCode);
    UNormalizer2 *p2 = unorm2_openFiltered(nfd, emptySet.toUSet(), errorCode);
    LocalUNormalizer2Pointer f1(p1);
    LocalUNormalizer2Pointer f2(p2);
    if(errorCode.logIfFailureAndReset("unorm2_openFiltered()")) {
        return;
    }
    if(f1.isNull() || f2.isNull()) {
        errln("LocalUNormalizer2Pointer failure");
        return;
    }
    f1.swap(f2);
    if(f1.getAlias() != p2 || f2.getAlias() != p1) {
        errln("LocalUNormalizer2Pointer.swap() did not swap");
    }
    swap(f1, f2);
    if(f1.getAlias() != p1 || f2.getAlias() != p2) {
        errln("swap(LocalUNormalizer2Pointer) did not swap back");
    }
    LocalUNormalizer2Pointer f3;
    f3.moveFrom(f1);
    if(f3.getAlias() != p1 || f1.isValid()) {
        errln("LocalUNormalizer2Pointer.moveFrom() did not move");
    }
#if U_HAVE_RVALUE_REFERENCES
    infoln("TestLocalXyzPointerMoveSwap() with rvalue references");
    f1 = static_cast<LocalUNormalizer2Pointer &&>(f3);
    if(f1.getAlias() != p1 || f3.isValid()) {
        errln("LocalUNormalizer2Pointer move assignment operator did not move");
    }
    LocalUNormalizer2Pointer f4(static_cast<LocalUNormalizer2Pointer &&>(f2));
    if(f4.getAlias() != p2 || f2.isValid()) {
        errln("LocalUNormalizer2Pointer move constructor did not move");
    }
#else
    infoln("TestLocalXyzPointerMoveSwap() without rvalue references");
#endif
    // Move self assignment leaves the object valid but in an undefined state.
    // Do it to make sure there is no crash,
    // but do not check for any particular resulting value.
    f1.moveFrom(f1);
    f3.moveFrom(f3);
#endif /* !UCONFIG_NO_NORMALIZATION */
}

U_CAPI const USet * U_EXPORT2
u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode) {
    if (U_FAILURE(*pErrorCode)) { return nullptr; }
    if (property < 0 || UCHAR_BINARY_LIMIT <= property) {
        *pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
        return nullptr;
    }
    Mutex m(&cpMutex);
    UnicodeSet *set = sets[property];
    if (set == nullptr) {
        sets[property] = set = makeSet(property, *pErrorCode);
    }
    if (U_FAILURE(*pErrorCode)) { return nullptr; }
    return set->toUSet();
}

UBool AlphabeticIndex::addChineseIndexCharacters(UErrorCode &errorCode) {
    UnicodeSet contractions;
    ucol_getContractionsAndExpansions(collatorPrimaryOnly_->getUCollator(),
                                      contractions.toUSet(), NULL, FALSE, &errorCode);
    if (U_FAILURE(errorCode)) { return FALSE; }
    UnicodeString firstHanBoundary;
    UBool hasPinyin = FALSE;
    UnicodeSetIterator iter(contractions);
    while (iter.next()) {
        const UnicodeString &s = iter.getString();
        if (s.startsWith(BASE, BASE_LENGTH)) {
            initialLabels_->add(s);
            if (firstHanBoundary.isEmpty() ||
                    collatorPrimaryOnly_->compare(s, firstHanBoundary, errorCode) < 0) {
                firstHanBoundary = s;
            }
            UChar c = s.charAt(s.length() - 1);
            if (0x41 <= c && c <= 0x5A) {  // A-Z
                hasPinyin = TRUE;
            }
        }
    }
    if (hasPinyin) {
        initialLabels_->add(0x41, 0x5A);  // A-Z
    }
    if (!firstHanBoundary.isEmpty()) {
        // The hardcoded list of script boundaries includes U+4E00
        // which is tailored to not be the first primary
        // in all Chinese tailorings except "unihan".
        // Replace U+4E00 with the first boundary string from the tailoring.
        // TODO: This becomes obsolete when the root collator gets
        // reliable script-first-primary mappings.
        int32_t hanIndex = binarySearch(
                *firstCharsInScripts_, UnicodeString((UChar)0x4E00), *collatorPrimaryOnly_);
        if (hanIndex >= 0) {
            UnicodeString *fh = new UnicodeString(firstHanBoundary);
            if (fh == NULL) {
                errorCode = U_MEMORY_ALLOCATION_ERROR;
                return FALSE;
            }
            firstCharsInScripts_->setElementAt(fh, hanIndex);
        }
        return TRUE;
    } else {
        return FALSE;
    }
}

// Use LocalXyzPointer types that are not covered elsewhere in the intltest suite.
void LocalPointerTest::TestLocalXyzPointer() {
    IcuTestErrorCode errorCode(*this, "TestLocalXyzPointer");

    static const char *const encoding="ISO-8859-1";
    LocalUConverterSelectorPointer sel(
        ucnvsel_open(&encoding, 1, NULL, UCNV_ROUNDTRIP_SET, errorCode));
    if(errorCode.logIfFailureAndReset("ucnvsel_open()")) {
        return;
    }
    if(sel.isNull()) {
        errln("LocalUConverterSelectorPointer failure");
        return;
    }

#if !UCONFIG_NO_FORMATTING
    LocalUCalendarPointer cal(ucal_open(NULL, 0, "root", UCAL_GREGORIAN, errorCode));
    if(errorCode.logDataIfFailureAndReset("ucal_open()")) {
        return;
    }
    if(cal.isNull()) {
        errln("LocalUCalendarPointer failure");
        return;
    }

    LocalUDateTimePatternGeneratorPointer patgen(udatpg_open("root", errorCode));
    if(errorCode.logDataIfFailureAndReset("udatpg_open()")) {
        return;
    }
    if(patgen.isNull()) {
        errln("LocalUDateTimePatternGeneratorPointer failure");
        return;
    }

    LocalULocaleDisplayNamesPointer ldn(uldn_open("de-CH", ULDN_STANDARD_NAMES, errorCode));
    if(errorCode.logIfFailureAndReset("uldn_open()")) {
        return;
    }
    if(ldn.isNull()) {
        errln("LocalULocaleDisplayNamesPointer failure");
        return;
    }

    UnicodeString hello=UNICODE_STRING_SIMPLE("Hello {0}!");
    LocalUMessageFormatPointer msg(
        umsg_open(hello.getBuffer(), hello.length(), "root", NULL, errorCode));
    if(errorCode.logIfFailureAndReset("umsg_open()")) {
        return;
    }
    if(msg.isNull()) {
        errln("LocalUMessageFormatPointer failure");
        return;
    }
#endif  /* UCONFIG_NO_FORMATTING  */

#if !UCONFIG_NO_NORMALIZATION
    const UNormalizer2 *nfc=unorm2_getNFCInstance(errorCode);
    UnicodeSet emptySet;
    LocalUNormalizer2Pointer fn2(unorm2_openFiltered(nfc, emptySet.toUSet(), errorCode));
    if(errorCode.logIfFailureAndReset("unorm2_openFiltered()")) {
        return;
    }
    if(fn2.isNull()) {
        errln("LocalUNormalizer2Pointer failure");
        return;
    }
#endif /* !UCONFIG_NO_NORMALIZATION */

#if !UCONFIG_NO_IDNA
    LocalUIDNAPointer idna(uidna_openUTS46(0, errorCode));
    if(errorCode.logIfFailureAndReset("uidna_openUTS46()")) {
        return;
    }
    if(idna.isNull()) {
        errln("LocalUIDNAPointer failure");
        return;
    }
#endif  /* !UCONFIG_NO_IDNA */

#if !UCONFIG_NO_REGULAR_EXPRESSIONS
    UnicodeString pattern=UNICODE_STRING_SIMPLE("abc|xy+z");
    LocalURegularExpressionPointer regex(
        uregex_open(pattern.getBuffer(), pattern.length(), 0, NULL, errorCode));
    if(errorCode.logIfFailureAndReset("uregex_open()")) {
        return;
    }
    if(regex.isNull()) {
        errln("LocalURegularExpressionPointer failure");
        return;
    }
#endif /* UCONFIG_NO_REGULAR_EXPRESSIONS */

#if !UCONFIG_NO_TRANSLITERATION
    UnicodeString id=UNICODE_STRING_SIMPLE("Grek-Latn");
    LocalUTransliteratorPointer trans(
        utrans_openU(id.getBuffer(), id.length(), UTRANS_FORWARD, NULL, 0, NULL, errorCode));
    if(errorCode.logIfFailureAndReset("utrans_open()")) {
        return;
    }
    if(trans.isNull()) {
//.........这里部分代码省略.........

void AlphabeticIndex::addIndexExemplars(const Locale &locale, UErrorCode &status) {
    if (U_FAILURE(status)) { return; }
    // Chinese index characters, which are specific to each of the several Chinese tailorings,
    // take precedence over the single locale data exemplar set per language.
    const char *language = locale.getLanguage();
    if (uprv_strcmp(language, "zh") == 0 || uprv_strcmp(language, "ja") == 0 ||
            uprv_strcmp(language, "ko") == 0) {
        // TODO: This should be done regardless of the language, but it's expensive.
        // We should add a Collator function (can be @internal)
        // to enumerate just the contractions that start with a given code point or string.
        if (addChineseIndexCharacters(status) || U_FAILURE(status)) {
            return;
        }
    }

    LocalULocaleDataPointer uld(ulocdata_open(locale.getName(), &status));
    if (U_FAILURE(status)) {
        return;
    }

    UnicodeSet exemplars;
    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_INDEX, &status);
    if (U_SUCCESS(status)) {
        initialLabels_->addAll(exemplars);
        return;
    }
    status = U_ZERO_ERROR;  // Clear out U_MISSING_RESOURCE_ERROR

    // The locale data did not include explicit Index characters.
    // Synthesize a set of them from the locale's standard exemplar characters.
    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_STANDARD, &status);
    if (U_FAILURE(status)) {
        return;
    }

    // question: should we add auxiliary exemplars?
    if (exemplars.containsSome(0x61, 0x7A) /* a-z */ || exemplars.size() == 0) {
        exemplars.add(0x61, 0x7A);
    }
    if (exemplars.containsSome(0xAC00, 0xD7A3)) {  // Hangul syllables
        // cut down to small list
        exemplars.remove(0xAC00, 0xD7A3).
            add(0xAC00).add(0xB098).add(0xB2E4).add(0xB77C).
            add(0xB9C8).add(0xBC14).add(0xC0AC).add(0xC544).
            add(0xC790).add(0xCC28).add(0xCE74).add(0xD0C0).
            add(0xD30C).add(0xD558);
    }
    if (exemplars.containsSome(0x1200, 0x137F)) {  // Ethiopic block
        // cut down to small list
        // make use of the fact that Ethiopic is allocated in 8's, where
        // the base is 0 mod 8.
        UnicodeSet ethiopic(
            UNICODE_STRING_SIMPLE("[[:Block=Ethiopic:]&[:Script=Ethiopic:]]"), status);
        UnicodeSetIterator it(ethiopic);
        while (it.next() && !it.isString()) {
            if ((it.getCodepoint() & 0x7) != 0) {
                exemplars.remove(it.getCodepoint());
            }
        }
    }

    // Upper-case any that aren't already so.
    //   (We only do this for synthesized index characters.)
    UnicodeSetIterator it(exemplars);
    UnicodeString upperC;
    while (it.next()) {
        const UnicodeString &exemplarC = it.getString();
        upperC = exemplarC;
        upperC.toUpper(locale);
        initialLabels_->add(upperC);
    }
}

//
//  First characters in scripts.
//  Create a UVector whose contents are pointers to UnicodeStrings for the First Characters in each script.
//  The vector is sorted according to this index's collation.
//
//  This code is too slow to use, so for now hard code the data.
//    Hard coded implementation is follows.
//
UVector *AlphabeticIndex::firstStringsInScript(Collator *ruleBasedCollator, UErrorCode &status) {

    if (U_FAILURE(status)) {
        return NULL;
    }

    UnicodeString results[USCRIPT_CODE_LIMIT];
    UnicodeString LOWER_A = UNICODE_STRING_SIMPLE("a");

    UnicodeSetIterator siter(*TO_TRY);
    while (siter.next()) {
        const UnicodeString &current = siter.getString();
        Collator::EComparisonResult r = ruleBasedCollator->compare(current, LOWER_A);
        if (r < 0) {  // TODO fix; we only want "real" script characters, not
                      // symbols.
            continue;
        }

        int script = uscript_getScript(current.char32At(0), &status);
        if (results[script].length() == 0) {
            results[script] = current;
        }
        else if (ruleBasedCollator->compare(current, results[script]) < 0) {
            results[script] = current;
        }
    }

    UnicodeSet extras;
    UnicodeSet expansions;
    RuleBasedCollator *rbc = dynamic_cast<RuleBasedCollator *>(ruleBasedCollator);
    const UCollator *uRuleBasedCollator = rbc->getUCollator();
    ucol_getContractionsAndExpansions(uRuleBasedCollator, extras.toUSet(), expansions.toUSet(), true, &status);
    extras.addAll(expansions).removeAll(*TO_TRY);
    if (extras.size() != 0) {
        const Normalizer2 *normalizer = Normalizer2::getNFKCInstance(status);
        UnicodeSetIterator extrasIter(extras);
        while (extrasIter.next()) {
            const UnicodeString &current = extrasIter.next();
            if (!TO_TRY->containsAll(current))
                continue;
            if (!normalizer->isNormalized(current, status) ||
                ruleBasedCollator->compare(current, LOWER_A) < 0) {
                continue;
            }
            int script = uscript_getScript(current.char32At(0), &status);
            if (results[script].length() == 0) {
                results[script] = current;
            } else if (ruleBasedCollator->compare(current, results[script]) < 0) {
                results[script] = current;
            }
        }
    }

    UVector *dest = new UVector(status);
    dest->setDeleter(uprv_deleteUObject);
    for (uint32_t i = 0; i < sizeof(results) / sizeof(results[0]); ++i) {
        if (results[i].length() > 0) {
            dest->addElement(results[i].clone(), status);
        }
    }
    dest->sortWithUComparator(sortCollateComparator, ruleBasedCollator, status);
    return dest;
}

void AlphabeticIndex::getIndexExemplars(UnicodeSet  &dest, const Locale &locale, UErrorCode &status) {
    if (U_FAILURE(status)) {
        return;
    }

    LocalULocaleDataPointer uld(ulocdata_open(locale.getName(), &status));
    UnicodeSet exemplars;
    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_INDEX, &status);
    if (U_SUCCESS(status)) {
        dest.addAll(exemplars);
        return;
    }
    status = U_ZERO_ERROR;  // Clear out U_MISSING_RESOURCE_ERROR

    // Locale data did not include explicit Index characters.
    // Synthesize a set of them from the locale's standard exemplar characters.

    ulocdata_getExemplarSet(uld.getAlias(), exemplars.toUSet(), 0, ULOCDATA_ES_STANDARD, &status);
    if (U_FAILURE(status)) {
        return;
    }

    // Upper-case any that aren't already so.
    //   (We only do this for synthesized index characters.)

    UnicodeSetIterator it(exemplars);
    UnicodeString upperC;
    UnicodeSet  lowersToRemove;
    UnicodeSet  uppersToAdd;
    while (it.next()) {
        const UnicodeString &exemplarC = it.getString();
        upperC = exemplarC;
        upperC.toUpper(locale);
        if (exemplarC != upperC) {
            lowersToRemove.add(exemplarC);
            uppersToAdd.add(upperC);
        }
    }
    exemplars.removeAll(lowersToRemove);
    exemplars.addAll(uppersToAdd);

    // get the exemplars, and handle special cases

    // question: should we add auxiliary exemplars?
    if (exemplars.containsSome(*CORE_LATIN)) {
        exemplars.addAll(*CORE_LATIN);
    }
    if (exemplars.containsSome(*HANGUL)) {
        // cut down to small list
        UnicodeSet BLOCK_HANGUL_SYLLABLES(UNICODE_STRING_SIMPLE("[:block=hangul_syllables:]"), status);
        exemplars.removeAll(BLOCK_HANGUL_SYLLABLES);
        exemplars.addAll(*HANGUL);
    }
    if (exemplars.containsSome(*ETHIOPIC)) {
        // cut down to small list
        // make use of the fact that Ethiopic is allocated in 8's, where
        // the base is 0 mod 8.
        UnicodeSetIterator  it(*ETHIOPIC);
        while (it.next() && !it.isString()) {
            if ((it.getCodepoint() & 0x7) != 0) {
                exemplars.remove(it.getCodepoint());
            }
        }
    }
    dest.addAll(exemplars);
}