C++ UnicodeString::unescape方法代码示例

void SSearchTest::sharpSTest()
{
    UErrorCode status = U_ZERO_ERROR;
    UCollator *coll = NULL;
    UnicodeString lp  = "fuss";
    UnicodeString sp = "fu\\u00DF";
    UnicodeString targets[]  = {"fu\\u00DF", "fu\\u00DFball", "1fu\\u00DFball", "12fu\\u00DFball", "123fu\\u00DFball", "1234fu\\u00DFball",
                                "ffu\\u00DF", "fufu\\u00DF", "fusfu\\u00DF",
                                "fuss", "ffuss", "fufuss", "fusfuss", "1fuss", "12fuss", "123fuss", "1234fuss", "fu\\u00DF", "1fu\\u00DF", "12fu\\u00DF", "123fu\\u00DF", "1234fu\\u00DF"};
    int32_t start = -1, end = -1;

    coll = ucol_openFromShortString("LEN_S1", FALSE, NULL, &status);
    TEST_ASSERT_SUCCESS(status);

    UnicodeString lpUnescaped = lp.unescape();
    UnicodeString spUnescaped = sp.unescape();

    LocalUStringSearchPointer ussLong(usearch_openFromCollator(lpUnescaped.getBuffer(), lpUnescaped.length(),
                                                           lpUnescaped.getBuffer(), lpUnescaped.length(),   // actual test data will be set later
                                                           coll,
                                                           NULL,     // the break iterator
                                                           &status));

    LocalUStringSearchPointer ussShort(usearch_openFromCollator(spUnescaped.getBuffer(), spUnescaped.length(),
                                                           spUnescaped.getBuffer(), spUnescaped.length(),   // actual test data will be set later
                                                           coll,
                                                           NULL,     // the break iterator
                                                           &status));
    TEST_ASSERT_SUCCESS(status);

    for (uint32_t t = 0; t < (sizeof(targets)/sizeof(targets[0])); t += 1) {
        UBool bFound;
        UnicodeString target = targets[t].unescape();

        start = end = -1;
        usearch_setText(ussLong.getAlias(), target.getBuffer(), target.length(), &status);
        bFound = usearch_search(ussLong.getAlias(), 0, &start, &end, &status);
        TEST_ASSERT_SUCCESS(status);
        if (bFound) {
            logln("Test %d: found long pattern at [%d, %d].", t, start, end);
        } else {
            dataerrln("Test %d: did not find long pattern.", t);
        }

        usearch_setText(ussShort.getAlias(), target.getBuffer(), target.length(), &status);
        bFound = usearch_search(ussShort.getAlias(), 0, &start, &end, &status);
        TEST_ASSERT_SUCCESS(status);
        if (bFound) {
            logln("Test %d: found long pattern at [%d, %d].", t, start, end);
        } else {
            dataerrln("Test %d: did not find long pattern.", t);
        }
    }

    ucol_close(coll);
}

//.........这里部分代码省略.........
        //
        // Get the alternate_handling flag. Default is UCOL_NON_IGNORABLE.
        //
        UColAttributeValue alternateHandling = UCOL_NON_IGNORABLE;
        const UnicodeString *alt = testCase->getAttribute("alternate_handling");
        TEST_ASSERT (alt == NULL || *alt == "SHIFTED" || *alt == "NON_IGNORABLE");
        if (alt != NULL && *alt == "SHIFTED") {
            alternateHandling = UCOL_SHIFTED;
        }

        const UnicodeString defLocale("en");
        char  clocale[100];
        const UnicodeString *locale   = testCase->getAttribute("locale");
        if (locale == NULL || locale->length()==0) {
            locale = &defLocale;
        };
        locale->extract(0, locale->length(), clocale, sizeof(clocale), NULL);


        UnicodeString  text;
        UnicodeString  target;
        UnicodeString  pattern;
        int32_t        expectedMatchStart = -1;
        int32_t        expectedMatchLimit = -1;
        const UXMLElement  *n;
        int32_t                nodeCount = 0;

        n = testCase->getChildElement("pattern");
        TEST_ASSERT(n != NULL);
        if (n==NULL) {
            continue;
        }
        text = n->getText(FALSE);
        text = text.unescape();
        pattern.append(text);
        nodeCount++;

        n = testCase->getChildElement("pre");
        if (n!=NULL) {
            text = n->getText(FALSE);
            text = text.unescape();
            target.append(text);
            nodeCount++;
        }

        n = testCase->getChildElement("m");
        if (n!=NULL) {
            expectedMatchStart = target.length();
            text = n->getText(FALSE);
            text = text.unescape();
            target.append(text);
            expectedMatchLimit = target.length();
            nodeCount++;
        }

        n = testCase->getChildElement("post");
        if (n!=NULL) {
            text = n->getText(FALSE);
            text = text.unescape();
            target.append(text);
            nodeCount++;
        }

        //  Check that there weren't extra things in the XML
        TEST_ASSERT(nodeCount == testCase->countChildren());

//.........这里部分代码省略.........
      "\\ube44\\uc601\\ub9ac", "\\uc870\\uc9c1\\uc73c\\ub85c\\uc11c", "\\ud604\\ub300",
      "\\uc18c\\ud504\\ud2b8\\uc6e8\\uc5b4", "\\uc81c\\ud488\\uacfc",
      "\\ud45c\\uc900\\uc5d0\\uc11c", "\\ud14d\\uc2a4\\ud2b8\\uc758", "\\ud45c\\ud604\\uc744",
      "\\uc9c0\\uc815\\ud558\\ub294", "\\uc720\\ub2c8\\ucf54\\ub4dc", "\\ud45c\\uc900\\uc758",
      "\\uc0ac\\uc6a9\\uc744", "\\uac1c\\ubc1c\\ud558\\uace0", "\\ud655\\uc7a5\\ud558\\uba70",
      "\\uc7a5\\ub824\\ud558\\uae30", "\\uc704\\ud574",
      "\\uc138\\uc6cc\\uc84c\\uc2b5\\ub2c8\\ub2e4.", "\\ucf58\\uc18c\\uc2dc\\uc5c4",
      "\\uba64\\ubc84\\uc27d\\uc740", "\\ucef4\\ud4e8\\ud130\\uc640", "\\uc815\\ubcf4",
      "\\ucc98\\ub9ac", "\\uc0b0\\uc5c5\\uc5d0", "\\uc885\\uc0ac\\ud558\\uace0", "\\uc788\\ub294",
      "\\uad11\\ubc94\\uc704\\ud55c", "\\ud68c\\uc0ac", "\\ubc0f", "\\uc870\\uc9c1\\uc758",
      "\\ubc94\\uc704\\ub97c",
      "\\ub098\\ud0c0\\ub0c5\\ub2c8\\ub2e4.", "\\ucf58\\uc18c\\uc2dc\\uc5c4\\uc758",
      "\\uc7ac\\uc815\\uc740", "\\uc804\\uc801\\uc73c\\ub85c", "\\ud68c\\ube44\\uc5d0",
      "\\uc758\\ud574", "\\ucda9\\ub2f9\\ub429\\ub2c8\\ub2e4.", "\\uc720\\ub2c8\\ucf54\\ub4dc",
      "\\ucee8\\uc18c\\uc2dc\\uc5c4\\uc5d0\\uc11c\\uc758", "\\uba64\\ubc84\\uc27d\\uc740",
      "\\uc804", "\\uc138\\uacc4", "\\uc5b4\\ub290", "\\uacf3\\uc5d0\\uc11c\\ub098",
      "\\uc720\\ub2c8\\ucf54\\ub4dc", "\\ud45c\\uc900\\uc744", "\\uc9c0\\uc6d0\\ud558\\uace0",
      "\\uadf8", "\\ud655\\uc7a5\\uacfc", "\\uad6c\\ud604\\uc744",
      "\\uc9c0\\uc6d0\\ud558\\uace0\\uc790\\ud558\\ub294", "\\uc870\\uc9c1\\uacfc",
      "\\uac1c\\uc778\\uc5d0\\uac8c", "\\uac1c\\ubc29\\ub418\\uc5b4",
      "\\uc788\\uc2b5\\ub2c8\\ub2e4.",

      "\\ub354", "\\uc790\\uc138\\ud55c", "\\ub0b4\\uc6a9\\uc740", "\\uc6a9\\uc5b4\\uc9d1,",
      "\\uc608\\uc81c", "\\uc720\\ub2c8\\ucf54\\ub4dc", "\\uc0ac\\uc6a9", "\\uac00\\ub2a5",
      "\\uc81c\\ud488,", "\\uae30\\uc220", "\\uc815\\ubcf4", "\\ubc0f", "\\uae30\\ud0c0",
      "\\uc720\\uc6a9\\ud55c", "\\uc815\\ubcf4\\ub97c",
      "\\ucc38\\uc870\\ud558\\uc2ed\\uc2dc\\uc624."
    };

    enum { WHAT_IS_UNICODE_length = sizeof(WHAT_IS_UNICODE) / sizeof(WHAT_IS_UNICODE[0]) };

    UParseError parseError;
    UErrorCode status = U_ZERO_ERROR;
    Transliterator* latinJamo = Transliterator::createInstance("Latin-Jamo", UTRANS_FORWARD, parseError, status);
    Transliterator* jamoHangul = Transliterator::createInstance("NFC(NFD)", UTRANS_FORWARD, parseError, status);
    if (latinJamo == 0 || jamoHangul == 0 || U_FAILURE(status)) {
        delete latinJamo;
        delete jamoHangul;
        dataerrln("FAIL: createInstance returned NULL - %s", u_errorName(status));
        return;
    }
    Transliterator* jamoLatin = latinJamo->createInverse(status);
    Transliterator* hangulJamo = jamoHangul->createInverse(status);
    if (jamoLatin == 0 || hangulJamo == 0) {
        errln("FAIL: createInverse returned NULL");
        delete latinJamo;
        delete jamoLatin;
        delete jamoHangul;
        delete hangulJamo;
        return;
    }

    Transliterator* tarray[4] =
        { hangulJamo, jamoLatin, latinJamo, jamoHangul };
    CompoundTransliterator rt(tarray, 4);
    
    UnicodeString buf;
    int32_t total = 0;
    int32_t errors = 0;
    int32_t i;
    for (i=0; i < WHAT_IS_UNICODE_length; ++i) {
        ++total;
        UnicodeString hangul = UnicodeString(WHAT_IS_UNICODE[i], -1, US_INV);
        hangul = hangul.unescape(); // Parse backslash-u escapes
        UnicodeString hangulX = hangul;
        rt.transliterate(hangulX);
        if (hangul != hangulX) {
            ++errors;
            UnicodeString jamo = hangul; hangulJamo->transliterate(jamo);
            UnicodeString latin = jamo; jamoLatin->transliterate(latin);
            UnicodeString jamo2 = latin; latinJamo->transliterate(jamo2);
            UnicodeString hangul2 = jamo2; jamoHangul->transliterate(hangul2);
            
            buf.remove(0);
            buf.append("FAIL: ");
            if (hangul2 != hangulX) {
                buf.append((UnicodeString)"(Weird: " + hangulX + " != " + hangul2 + ")");
            }
            // The Hangul-Jamo conversion is not usually the
            // bug here, so we hide it from display.
            // Uncomment lines to see the Hangul.
            buf.append(//hangul + " => " +
                       jamoToName(jamo) + " => " +
                       latin + " => " + jamoToName(jamo2)
                       //+ " => " + hangul2
                       );
            errln(prettify(buf));
        }
    }
    if (errors != 0) {
        errln((UnicodeString)"Test word failures: " + errors + " out of " + total);
    } else {
        logln((UnicodeString)"All " + total + " test words passed");
    }

    delete latinJamo;
    delete jamoLatin;
    delete jamoHangul;
    delete hangulJamo;
}