Skip to content
Snippets Groups Projects
XMLString.hpp 51 KiB
Newer Older
PeiYong Zhang's avatar
PeiYong Zhang committed
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419

    /** Tells if a string has any occurance of another string within itself
      * @param toSearch The string to be searched
      * @param searchList The sub-string to be searched within the string
      * @return Returns the pointer to the location where the sub-string was
      * found, else returns 0
      */
    static const XMLCh* findAny
    (
        const   XMLCh* const    toSearch
        , const XMLCh* const    searchList
    );

    /** Tells if a string has any occurance of another string within itself
      * @param toSearch The string to be searched
      * @param searchList The sub-string to be searched within the string
      * @return Returns the pointer to the location where the sub-string was
      * found, else returns 0
      */
    static XMLCh* findAny
    (
                XMLCh* const    toSearch
        , const XMLCh* const    searchList
    );

    /** Tells if a string has pattern within itself
      * @param toSearch The string to be searched
      * @param pattern The pattern to be searched within the string
      * @return Returns index to the location where the pattern was
      * found, else returns -1
      */
    static int patternMatch
    (
                XMLCh* const    toSearch
        , const XMLCh* const    pattern
    );

    /** Get the length of the string
      * @param src The string whose length is to be determined
      * @return Returns the length of the string
      */
    static unsigned int stringLen(const char* const src);

    /** Get the length of the string
      * @param src The string whose length is to be determined
      * @return Returns the length of the string
      */
    static unsigned int stringLen(const XMLCh* const src);

    /**
      * Checks whether an name is a valid NCName.
      * @param name The string to check its NCName validity
      * @return Returns true if name is NCName valid, otherwise false
      */
    static bool isValidNCName(const XMLCh* const name);

    /**
      * Checks whether an name is a valid Name.
      * @param name The string to check its Name validity
      * @return Returns true if name is Name valid, otherwise false
      */
    static bool isValidName(const XMLCh* const name);

    /**
      * Checks whether an name is a valid EncName.
      * @param name The string to check its EncName validity
      * @return Returns true if name is EncName valid, otherwise false
      */
    static bool isValidEncName(const XMLCh* const name);  

    /**
      * Checks whether an name is a valid QName.
      * @param name The string to check its QName validity
      * @return Returns true if name is QName valid, otherwise false
      */
    static bool isValidQName(const XMLCh* const name);  

    /**
      * Checks whether a character is within [a-zA-Z].
      * @param theChar: the character to check 
      * @return Returns true if within the range, otherwise false
      */

    static bool isAlpha(XMLCh const theChar);

    /**
      * Checks whether a character is within [0-9].
      * @param theChar: the character to check 
      * @return Returns true if within the range, otherwise false
      */
    static bool isDigit(XMLCh const theChar);

    /**
      * Checks whether a character is within [0-9a-zA-Z].
      * @param theChar: the character to check 
      * @return Returns true if within the range, otherwise false
      */
    static bool isAlphaNum(XMLCh const theChar);

    /**
      * Checks whether a character is within [0-9a-fA-F].
      * @param theChar: the character to check 
      * @return Returns true if within the range, otherwise false
      */
    static bool isHex(XMLCh const theChar);

    /**
      * Checks whether a string contains only whitespace.
      * @param toCheck: the string to check 
      * @return Returns true if it is, otherwise false
      */
    static bool isAllWhiteSpace(const XMLCh* const toCheck);

    //@}

    /** @name Conversion functions */
    //@{

    /** Cut leading chars from a string
      *
      * @param toCut The string to cut chars from
      * @param count The count of leading chars to cut
      */
    static void cut
    (
                XMLCh* const    toCutFrom
        , const unsigned int    count
    );

    /** Transcodes a string to native code-page
      *
      * NOTE: The returned buffer is dynamically allocated and is the
      * responsibility of the caller to delete it when not longer needed.
      *
      * @param toTranscode The string to be transcoded
      * @return Returns the transcoded string
      */
    static char* transcode
    (
        const   XMLCh* const    toTranscode
    );

    /** Transcodes a string to native code-page
      *
      * Be aware that when transcoding to an external encoding, that each
      * Unicode char can create multiple output bytes. So you cannot assume
      * a one to one correspondence of input chars to output bytes.
      *
      * @param toTranscode The string tobe transcoded
      * @param toFill The buffer that is filled with the transcoded value.
      *        The size of this buffer should atleast be 'maxChars + 1'.
      * @param maxChars The maximum number of bytes that the output
      *         buffer can hold (not including the null, which is why
      *         toFill should be at least maxChars+1.) If the resulting
      *         output cannot fit into this many bytes, it is an error and
      *         false is returned.
      * @return Returns true if successful, false if there was an error
      */
    static bool transcode
    (
        const   XMLCh* const    toTranscode
        ,       char* const     toFill
        , const unsigned int    maxChars
    );

    /** Transcodes a string to native code-page
      *
      * NOTE: The returned buffer is dynamically allocated and is the
      * responsibility of the caller to delete it when not longer needed.
      *
      * @param toTranscode The string to be transcoded
      * @return Returns the transcoded string
      */
    static XMLCh* transcode
    (
        const   char* const     toTranscode
    );

    /** Transcodes a string to native code-page
      * @param toTranscode The string tobe transcoded
      * @param toFill The buffer that is filled with the transcoded value.
      *        The size of this buffer should atleast be 'maxChars + 1'.
      * @param maxChars The maximum number of characters that the output
      *         buffer can hold (not including the null, which is why
      *         toFill should be at least maxChars+1.) If the resulting
      *         output cannot fit into this many characters, it is an error
      *         and false is returned.
      * @return Returns true if successful, false if there was an error
      */
    static bool transcode
    (
        const   char* const     toTranscode
        ,       XMLCh* const    toFill
        , const unsigned int    maxChars
    );

    /** Trims off extra space characters from the start and end of the string,
      * moving the non-space string content back to the start.
      * @param toTrim The string to be trimmed. On return this contains the
      * trimmed string
      */
    static void trim(char* const toTrim);

    /** Trims off extra space characters from the start and end of the string,
      * moving the non-space string content back to the start.
      * @param toTrim The string to be trimmed. On return this contains
      * the trimmed string
      */
    static void trim(XMLCh* const toTrim);

    /** Break a string into tokens with space as delimiter, and
      * stored in a string vector.  The caller owns the string vector
      * that is returned, and is responsible for deleting it.
      * @param tokenizeStr String to be tokenized
      * @return a vector of all the tokenized string
      */
    static RefVectorOf<XMLCh>* tokenizeString(const XMLCh* const tokenizeSrc);

    /** Find is the string appears in the enum list
      * @param toFind the string to be found
      * @param enumList the list
      * return true if found
      */
    static bool isInList(const XMLCh* const toFind, const XMLCh* const enumList);

    //@}

    /** @name Formatting functions */
    //@{
    /** Creates a UName from a URI and base name. It is in the form
      * {url}name, and is commonly used internally to represent fully
      * qualified names when namespaces are enabled.
      *
      * @param pszURI The URI part of the name
      * @param pszName The base part of the name
      * @return Returns the complete formatted UName
      */
    static XMLCh* makeUName
    (
        const   XMLCh* const    pszURI
        , const XMLCh* const    pszName
    );

    /**
      * Internal function to perform token replacement for strings.
      *
      * @param errText The text (NULL terminated) where the replacement
      *        is to be done. The size of this buffer should be
      *        'maxChars + 1' to account for the final NULL.
      * @param maxChars The size of the output buffer, i.e. the maximum
      *         number of characters that it will hold. If the result is
      *         larger, it will be truncated.
      * @param text1 Replacement text-one
      * @param text2 Replacement text-two
      * @param text3 Replacement text-three
      * @param text4 Replacement text-four
      * @return Returns the count of characters that are outputted
      */
    static unsigned int replaceTokens
    (
                XMLCh* const    errText
        , const unsigned int    maxChars
        , const XMLCh* const    text1
        , const XMLCh* const    text2
        , const XMLCh* const    text3
        , const XMLCh* const    text4
    );

    /** Converts a string to uppercase
      * @param toUpperCase The string which needs to be converted to uppercase.
      *        On return, this buffer also holds the converted uppercase string
      */
    static void upperCase(XMLCh* const toUpperCase);

	/** Converts a string to lowercase
      * @param toLowerCase The string which needs to be converted to lowercase.
      *        On return, this buffer also holds the converted lowercase string
      */
    static void lowerCase(XMLCh* const toLowerCase);

	/** Check if string is WhiteSpace:replace
      * @param toCheck The string which needs to be checked.
      */
    static bool isWSReplaced(const XMLCh* const toCheck);

	/** Check if string is WhiteSpace:collapse
      * @param toCheck The string which needs to be checked.
      */
    static bool isWSCollapsed(const XMLCh* const toCheck);

	/** Replace whitespace
      * @param toCheck The string which needs to be whitespace replaced.
      *        On return , this buffer also holds the converted string
      */
    static void replaceWS(XMLCh* const toConvert);

	/** Collapse whitespace
      * @param toConvert The string which needs to be whitespace collapsed.
      *        On return , this buffer also holds the converted string
      */       
    static void collapseWS(XMLCh* const toConvert);
    //@}


private :

    /** @name Constructors and Destructor */
    //@{
    /** Unimplemented default constructor */
    XMLString();
    /** Unimplemented destructor */
    ~XMLString();
    //@}


    /** @name Initialization */
    //@{
    /** Init/Term methods called from XMLPlatformUtils class */
    static void initString(XMLLCPTranscoder* const defToUse);
    static void termString();
    //@}

	/**
	  * Called by regionMatches/regionIMatches to validate that we
	  * have a valid input
	  */
	static bool validateRegion(const XMLCh* const str1, const int offset1,
						const XMLCh* const str2, const int offset2,
						const unsigned int charsCount);

    friend class XMLPlatformUtils;
};


// ---------------------------------------------------------------------------
//  Inline some methods that are either just passthroughs to other string
//  methods, or which are key for performance.
// ---------------------------------------------------------------------------
inline void XMLString::moveChars(       XMLCh* const    targetStr
                                , const XMLCh* const    srcStr
                                , const unsigned int    count)
{
    XMLCh* outPtr = targetStr;
    const XMLCh* inPtr = srcStr;
    for (unsigned int index = 0; index < count; index++)
        *outPtr++ = *inPtr++;
}

inline unsigned int XMLString::stringLen(const XMLCh* const src)
{
    if (src == 0 || *src == 0)
    {
        return 0;
   }
    else
   {
        const XMLCh* pszTmp = src + 1;

        while (*pszTmp)
            ++pszTmp;

        return (unsigned int)(pszTmp - src);
    }
}

inline bool XMLString::startsWith(  const   XMLCh* const    toTest
                                    , const XMLCh* const    prefix)
{
    return (compareNString(toTest, prefix, stringLen(prefix)) == 0);
}

inline bool XMLString::startsWithI( const   XMLCh* const    toTest
                                    , const XMLCh* const    prefix)
{
    return (compareNIString(toTest, prefix, stringLen(prefix)) == 0);
}

inline bool XMLString::endsWith(const XMLCh* const toTest,
                                const XMLCh* const suffix)
{

    unsigned int suffixLen = XMLString::stringLen(suffix);

    return regionMatches(toTest, XMLString::stringLen(toTest) - suffixLen,
                         suffix, 0, suffixLen);
}

inline XMLCh* XMLString::replicate(const XMLCh* const toRep)
{
    // If a null string, return a null string!
    XMLCh* ret = 0;
    if (toRep)
    {
        const unsigned int len = stringLen(toRep);
        ret = new XMLCh[len + 1];
        XMLCh* outPtr = ret;
        const XMLCh* inPtr = toRep;
        for (unsigned int index = 0; index <= len; index++)
            *outPtr++ = *inPtr++;
    }
    return ret;
}

inline bool XMLString::validateRegion(const XMLCh* const str1,
									  const int offset1,
									  const XMLCh* const str2,
									  const int offset2,
									  const unsigned int charsCount)
{

	if (offset1 < 0 || offset2 < 0 ||
		(offset1 + charsCount) > XMLString::stringLen(str1) ||
		(offset2 + charsCount) > XMLString::stringLen(str2) )
		return false;

	return true;
}

#endif