XMLTokener.java 10.3 KB
Newer Older
Lee Jaebin committed
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
package org.json.adf;

/*
Copyright (c) 2002 JSON.org

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

The Software shall be used for Good, not Evil.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/

/**
 * <b>adkのorg.jsonパッケージとの競合を防ぐためにパッケージ名をorg.json.adfにしました。</b>
 * The XMLTokener extends the JSONTokener to provide additional methods
 * for the parsing of XML texts.
 * @author JSON.org
 * @version 2010-12-24
 */
@SuppressWarnings({ "rawtypes", "unchecked" })
public class XMLTokener extends JSONTokener {


   /** The table of entity values. It initially contains Character values for
    * amp, apos, gt, lt, quot.
    */
   public static final java.util.HashMap entity;

   static {
       entity = new java.util.HashMap(8);
       entity.put("amp",  XML.AMP);
       entity.put("apos", XML.APOS);
       entity.put("gt",   XML.GT);
       entity.put("lt",   XML.LT);
       entity.put("quot", XML.QUOT);
   }

    /**
     * Construct an XMLTokener from a string.
     * @param s A source string.
     */
    public XMLTokener(String s) {
        super(s);
    }

    /**
     * Get the text in the CDATA block.
     * @return The string up to the <code>]]&gt;</code>.
     * @throws JSONException If the <code>]]&gt;</code> is not found.
     */
    public String nextCDATA() throws JSONException {
        char         c;
        int          i;
        StringBuffer sb = new StringBuffer();
        for (;;) {
            c = next();
            if (end()) {
                throw syntaxError("Unclosed CDATA");
            }
            sb.append(c);
            i = sb.length() - 3;
            if (i >= 0 && sb.charAt(i) == ']' &&
                          sb.charAt(i + 1) == ']' && sb.charAt(i + 2) == '>') {
                sb.setLength(i);
                return sb.toString();
            }
        }
    }


    /**
     * Get the next XML outer token, trimming whitespace. There are two kinds
     * of tokens: the '<' character which begins a markup tag, and the content
     * text between markup tags.
     *
     * @return  A string, or a '<' Character, or null if there is no more
     * source text.
     * @throws JSONException
     */
    public Object nextContent() throws JSONException {
        char         c;
        StringBuffer sb;
        do {
            c = next();
        } while (Character.isWhitespace(c));
        if (c == 0) {
            return null;
        }
        if (c == '<') {
            return XML.LT;
        }
        sb = new StringBuffer();
        for (;;) {
            if (c == '<' || c == 0) {
                back();
                return sb.toString().trim();
            }
            if (c == '&') {
                sb.append(nextEntity(c));
            } else {
                sb.append(c);
            }
            c = next();
        }
    }


    /**
     * Return the next entity. These entities are translated to Characters:
     *     <code>&amp;  &apos;  &gt;  &lt;  &quot;</code>.
     * @param ampersand An ampersand character.
     * @return  A Character or an entity String if the entity is not recognized.
     * @throws JSONException If missing ';' in XML entity.
     */
    public Object nextEntity(char ampersand) throws JSONException {
        StringBuffer sb = new StringBuffer();
        for (;;) {
            char c = next();
            if (Character.isLetterOrDigit(c) || c == '#') {
                sb.append(Character.toLowerCase(c));
            } else if (c == ';') {
                break;
            } else {
                throw syntaxError("Missing ';' in XML entity: &" + sb);
            }
        }
        String string = sb.toString();
        Object object = entity.get(string);
        return object != null ? object : ampersand + string + ";";
    }


    /**
     * Returns the next XML meta token. This is used for skipping over <!...>
     * and <?...?> structures.
     * @return Syntax characters (<code>< > / = ! ?</code>) are returned as
     *  Character, and strings and names are returned as Boolean. We don't care
     *  what the values actually are.
     * @throws JSONException If a string is not properly closed or if the XML
     *  is badly structured.
     */
    public Object nextMeta() throws JSONException {
        char c;
        char q;
        do {
            c = next();
        } while (Character.isWhitespace(c));
        switch (c) {
        case 0:
            throw syntaxError("Misshaped meta tag");
        case '<':
            return XML.LT;
        case '>':
            return XML.GT;
        case '/':
            return XML.SLASH;
        case '=':
            return XML.EQ;
        case '!':
            return XML.BANG;
        case '?':
            return XML.QUEST;
        case '"':
        case '\'':
            q = c;
            for (;;) {
                c = next();
                if (c == 0) {
                    throw syntaxError("Unterminated string");
                }
                if (c == q) {
                    return Boolean.TRUE;
                }
            }
        default:
            for (;;) {
                c = next();
                if (Character.isWhitespace(c)) {
                    return Boolean.TRUE;
                }
                switch (c) {
                case 0:
                case '<':
                case '>':
                case '/':
                case '=':
                case '!':
                case '?':
                case '"':
                case '\'':
                    back();
                    return Boolean.TRUE;
                }
            }
        }
    }


    /**
     * Get the next XML Token. These tokens are found inside of angle
     * brackets. It may be one of these characters: <code>/ > = ! ?</code> or it
     * may be a string wrapped in single quotes or double quotes, or it may be a
     * name.
     * @return a String or a Character.
     * @throws JSONException If the XML is not well formed.
     */
    public Object nextToken() throws JSONException {
        char c;
        char q;
        StringBuffer sb;
        do {
            c = next();
        } while (Character.isWhitespace(c));
        switch (c) {
        case 0:
            throw syntaxError("Misshaped element");
        case '<':
            throw syntaxError("Misplaced '<'");
        case '>':
            return XML.GT;
        case '/':
            return XML.SLASH;
        case '=':
            return XML.EQ;
        case '!':
            return XML.BANG;
        case '?':
            return XML.QUEST;

// Quoted string

        case '"':
        case '\'':
            q = c;
            sb = new StringBuffer();
            for (;;) {
                c = next();
                if (c == 0) {
                    throw syntaxError("Unterminated string");
                }
                if (c == q) {
                    return sb.toString();
                }
                if (c == '&') {
                    sb.append(nextEntity(c));
                } else {
                    sb.append(c);
                }
            }
        default:

// Name

            sb = new StringBuffer();
            for (;;) {
                sb.append(c);
                c = next();
                if (Character.isWhitespace(c)) {
                    return sb.toString();
                }
                switch (c) {
                case 0:
                	return sb.toString();
                case '>':
                case '/':
                case '=':
                case '!':
                case '?':
                case '[':
                case ']':
                    back();
                    return sb.toString();
                case '<':
                case '"':
                case '\'':
                    throw syntaxError("Bad character in a name");
                }
            }
        }
    }
    
    
    /**
     * Skip characters until past the requested string.
     * If it is not found, we are left at the end of the source with a result of false.
     * @param to A string to skip past.
     * @throws JSONException
     */
    public boolean skipPast(String to) throws JSONException {
    	boolean b;
    	char c;
    	int i;
    	int j;
    	int offset = 0;
    	int length = to.length();
        char[] circle = new char[length];
        
        /*
         * First fill the circle buffer with as many characters as are in the
         * to string. If we reach an early end, bail.
         */
        
    	for (i = 0; i < length; i += 1) {
    		c = next();
    		if (c == 0) {
    			return false;
    		}
    		circle[i] = c;
    	}
    	/*
    	 * We will loop, possibly for all of the remaining characters.
    	 */
    	for (;;) {
    		j = offset;
    		b = true;
    		/*
    		 * Compare the circle buffer with the to string. 
    		 */
    		for (i = 0; i < length; i += 1) {
    			if (circle[j] != to.charAt(i)) {
    				b = false;
    				break;
    			}
    			j += 1;
    			if (j >= length) {
    				j -= length;
    			}
    		}
    		/*
    		 * If we exit the loop with b intact, then victory is ours.
    		 */
    		if (b) {
    			return true;
    		}
    		/*
    		 * Get the next character. If there isn't one, then defeat is ours.
    		 */
    		c = next();
    		if (c == 0) {
    			return false;
    		}
    		/*
    		 * Shove the character in the circle buffer and advance the 
    		 * circle offset. The offset is mod n.
    		 */
    		circle[offset] = c;
    		offset += 1;
    		if (offset >= length) {
    			offset -= length;
    		}
    	}
    }
}