[188] | 1 | /*
|
---|
| 2 | * The Apache Software License, Version 1.1
|
---|
| 3 | *
|
---|
| 4 | * Copyright (c) 2001-2003 The Apache Software Foundation. All rights
|
---|
| 5 | * reserved.
|
---|
| 6 | *
|
---|
| 7 | * Redistribution and use in source and binary forms, with or without
|
---|
| 8 | * modification, are permitted provided that the following conditions
|
---|
| 9 | * are met:
|
---|
| 10 | *
|
---|
| 11 | * 1. Redistributions of source code must retain the above copyright
|
---|
| 12 | * notice, this list of conditions and the following disclaimer.
|
---|
| 13 | *
|
---|
| 14 | * 2. Redistributions in binary form must reproduce the above copyright
|
---|
| 15 | * notice, this list of conditions and the following disclaimer in
|
---|
| 16 | * the documentation and/or other materials provided with the
|
---|
| 17 | * distribution.
|
---|
| 18 | *
|
---|
| 19 | * 3. The end-user documentation included with the redistribution,
|
---|
| 20 | * if any, must include the following acknowledgment:
|
---|
| 21 | * "This product includes software developed by the
|
---|
| 22 | * Apache Software Foundation (http://www.apache.org/)."
|
---|
| 23 | * Alternately, this acknowledgment may appear in the software itself,
|
---|
| 24 | * if and wherever such third-party acknowledgments normally appear.
|
---|
| 25 | *
|
---|
| 26 | * 4. The names "Xerces" and "Apache Software Foundation" must
|
---|
| 27 | * not be used to endorse or promote products derived from this
|
---|
| 28 | * software without prior written permission. For written
|
---|
| 29 | * permission, please contact apache\@apache.org.
|
---|
| 30 | *
|
---|
| 31 | * 5. Products derived from this software may not be called "Apache",
|
---|
| 32 | * nor may "Apache" appear in their name, without prior written
|
---|
| 33 | * permission of the Apache Software Foundation.
|
---|
| 34 | *
|
---|
| 35 | * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
|
---|
| 36 | * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
---|
| 37 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
---|
| 38 | * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
|
---|
| 39 | * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
---|
| 40 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
---|
| 41 | * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
|
---|
| 42 | * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
---|
| 43 | * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
---|
| 44 | * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
|
---|
| 45 | * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
---|
| 46 | * SUCH DAMAGE.
|
---|
| 47 | * ====================================================================
|
---|
| 48 | *
|
---|
| 49 | * This software consists of voluntary contributions made by many
|
---|
| 50 | * individuals on behalf of the Apache Software Foundation, and was
|
---|
| 51 | * originally based on software copyright (c) 1999, International
|
---|
| 52 | * Business Machines, Inc., http://www.ibm.com . For more information
|
---|
| 53 | * on the Apache Software Foundation, please see
|
---|
| 54 | * <http://www.apache.org/>.
|
---|
| 55 | */
|
---|
| 56 |
|
---|
| 57 | /*
|
---|
| 58 | * $Id: XMLUri.hpp,v 1.16 2004/01/12 22:01:02 cargilld Exp $
|
---|
| 59 | * $Log: XMLUri.hpp,v $
|
---|
| 60 | * Revision 1.16 2004/01/12 22:01:02 cargilld
|
---|
| 61 | * Minor performance change for handling reserved and unreserved characters.
|
---|
| 62 | *
|
---|
| 63 | * Revision 1.15 2003/12/17 00:18:35 cargilld
|
---|
| 64 | * Update to memory management so that the static memory manager (one used to call Initialize) is only for static data.
|
---|
| 65 | *
|
---|
| 66 | * Revision 1.14 2003/12/11 22:21:25 neilg
|
---|
| 67 | * fixes for the URI implementation to take registry names into account; much thanks to Michael Glavassevich
|
---|
| 68 | *
|
---|
| 69 | * Revision 1.13 2003/12/02 17:50:21 neilg
|
---|
| 70 | * additional fix for bug 25118; once again, thanks to Jeroen Whitmond
|
---|
| 71 | *
|
---|
| 72 | * Revision 1.12 2003/10/01 00:20:41 knoaman
|
---|
| 73 | * Add a static method to check whether a given string is a valid URI.
|
---|
| 74 | *
|
---|
| 75 | * Revision 1.11 2003/09/25 22:23:25 peiyongz
|
---|
| 76 | * Implementation of Serialization/Deserialization
|
---|
| 77 | *
|
---|
| 78 | * Revision 1.10 2003/07/25 10:15:16 gareth
|
---|
| 79 | * Patch by Michael Glavassevich
|
---|
| 80 | *
|
---|
| 81 | * The patch fixes Bugzilla #19787, #20006, #20009, #20010 and #20287, and
|
---|
| 82 | * several other issues. A summary of the changes is listed below:
|
---|
| 83 | *
|
---|
| 84 | * 1. Added '[' and ']' to reserved characters as per RFC 2732.
|
---|
| 85 | * 2. '[' and ']' added in RFC 2732, are not allowed in path segments, but
|
---|
| 86 | * may appear in the opaque part.
|
---|
| 87 | * 3. No URI can begin with a ':'.
|
---|
| 88 | * 4. URI has no scheme if ':' occurs in a URI after '?' or '#', it's part of
|
---|
| 89 | * the query string or fragment.
|
---|
| 90 | * 5. Whitespace (even escaped as %20) is not permitted in the authority
|
---|
| 91 | * portion of a URI.
|
---|
| 92 | * 6. IPv4 addresses must match 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "."
|
---|
| 93 | * 1*3DIGIT. Since RFC 2732.
|
---|
| 94 | * 7. IPv4 addresses are 32-bit, therefore no segment may be larger than 255.
|
---|
| 95 | * This isn't expressed by the grammar.
|
---|
| 96 | * 8. Hostnames cannot end with a '-'.
|
---|
| 97 | * 9. Labels in a hostname must be 63 bytes or less [RFC 1034].
|
---|
| 98 | * 10. Hostnames may be no longer than 255 bytes [RFC 1034]. (That
|
---|
| 99 | * restriction was already there. I just moved it inwards.
|
---|
| 100 | * 11. Added support for IPv6 references added in RFC 2732. URIs such as
|
---|
| 101 | * http://[::ffff:1.2.3.4] are valid. The BNF in RFC 2373 isn't correct. IPv6
|
---|
| 102 | * addresses are read according to section 2.2 of RFC 2373.
|
---|
| 103 | *
|
---|
| 104 | * Revision 1.9 2003/05/16 06:01:53 knoaman
|
---|
| 105 | * Partial implementation of the configurable memory manager.
|
---|
| 106 | *
|
---|
| 107 | * Revision 1.8 2003/05/15 19:07:46 knoaman
|
---|
| 108 | * Partial implementation of the configurable memory manager.
|
---|
| 109 | *
|
---|
| 110 | * Revision 1.7 2003/01/06 19:43:18 tng
|
---|
| 111 | * New feature StandardUriConformant to force strict standard uri conformance.
|
---|
| 112 | *
|
---|
| 113 | * Revision 1.6 2002/11/21 15:42:39 gareth
|
---|
| 114 | * Implemented copy constructor and operator =. Patch by Jennifer Schachter.
|
---|
| 115 | *
|
---|
| 116 | * Revision 1.5 2002/11/04 15:22:05 tng
|
---|
| 117 | * C++ Namespace Support.
|
---|
| 118 | *
|
---|
| 119 | * Revision 1.4 2002/09/23 18:41:00 tng
|
---|
| 120 | * DOM L3: Support baseURI. Add fURIText to XMLUri. Added by Gareth Reakes and Thomas Ford.
|
---|
| 121 | *
|
---|
| 122 | * Revision 1.3 2002/08/23 20:45:24 tng
|
---|
| 123 | * .Memory leak fix: XMLUri data not deleted if constructor failed.
|
---|
| 124 | *
|
---|
| 125 | * Revision 1.2 2002/02/20 18:17:02 tng
|
---|
| 126 | * [Bug 5977] Warnings on generating apiDocs.
|
---|
| 127 | *
|
---|
| 128 | * Revision 1.1.1.1 2002/02/01 22:22:17 peiyongz
|
---|
| 129 | * sane_include
|
---|
| 130 | *
|
---|
| 131 | * Revision 1.3 2001/08/29 19:03:03 peiyongz
|
---|
| 132 | * Bugzilla# 2816:on AIX 4.2, xlC 3 r ev.1, Compilation error on inline method
|
---|
| 133 | *
|
---|
| 134 | * Revision 1.2 2001/08/16 14:09:44 peiyongz
|
---|
| 135 | * Removed unused ctors and methods
|
---|
| 136 | *
|
---|
| 137 | * Revision 1.1 2001/08/10 16:23:41 peiyongz
|
---|
| 138 | * XMLUri: creation
|
---|
| 139 | *
|
---|
| 140 | *
|
---|
| 141 | */
|
---|
| 142 |
|
---|
| 143 | #if !defined(XMLURI_HPP)
|
---|
| 144 | #define XMLURI_HPP
|
---|
| 145 |
|
---|
| 146 | #include <xercesc/util/XMemory.hpp>
|
---|
| 147 | #include <xercesc/util/XMLString.hpp>
|
---|
| 148 |
|
---|
| 149 | #include <xercesc/internal/XSerializable.hpp>
|
---|
| 150 |
|
---|
| 151 | XERCES_CPP_NAMESPACE_BEGIN
|
---|
| 152 |
|
---|
| 153 | /*
|
---|
| 154 | * This class is a direct port of Java's URI class, to distinguish
|
---|
| 155 | * itself from the XMLURL, we use the name XMLUri instead of
|
---|
| 156 | * XMLURI.
|
---|
| 157 | *
|
---|
| 158 | * TODO: how to relate XMLUri and XMLURL since URL is part of URI.
|
---|
| 159 | *
|
---|
| 160 | */
|
---|
| 161 |
|
---|
| 162 | class XMLUTIL_EXPORT XMLUri : public XSerializable, public XMemory
|
---|
| 163 | {
|
---|
| 164 | public:
|
---|
| 165 |
|
---|
| 166 | // -----------------------------------------------------------------------
|
---|
| 167 | // Constructors and Destructor
|
---|
| 168 | // -----------------------------------------------------------------------
|
---|
| 169 |
|
---|
| 170 | /**
|
---|
| 171 | * Construct a new URI from a URI specification string.
|
---|
| 172 | *
|
---|
| 173 | * If the specification follows the "generic URI" syntax, (two slashes
|
---|
| 174 | * following the first colon), the specification will be parsed
|
---|
| 175 | * accordingly - setting the
|
---|
| 176 | * scheme,
|
---|
| 177 | * userinfo,
|
---|
| 178 | * host,
|
---|
| 179 | * port,
|
---|
| 180 | * path,
|
---|
| 181 | * querystring and
|
---|
| 182 | * fragment
|
---|
| 183 | * fields as necessary.
|
---|
| 184 | *
|
---|
| 185 | * If the specification does not follow the "generic URI" syntax,
|
---|
| 186 | * the specification is parsed into a
|
---|
| 187 | * scheme and
|
---|
| 188 | * scheme-specific part (stored as the path) only.
|
---|
| 189 | *
|
---|
| 190 | * @param uriSpec the URI specification string (cannot be null or empty)
|
---|
| 191 | *
|
---|
| 192 | * @param manager Pointer to the memory manager to be used to
|
---|
| 193 | * allocate objects.
|
---|
| 194 | *
|
---|
| 195 | * ctor# 2
|
---|
| 196 | *
|
---|
| 197 | */
|
---|
| 198 | XMLUri(const XMLCh* const uriSpec,
|
---|
| 199 | MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager);
|
---|
| 200 |
|
---|
| 201 | /**
|
---|
| 202 | * Construct a new URI from a base URI and a URI specification string.
|
---|
| 203 | * The URI specification string may be a relative URI.
|
---|
| 204 | *
|
---|
| 205 | * @param baseURI the base URI (cannot be null if uriSpec is null or
|
---|
| 206 | * empty)
|
---|
| 207 | *
|
---|
| 208 | * @param uriSpec the URI specification string (cannot be null or
|
---|
| 209 | * empty if base is null)
|
---|
| 210 | *
|
---|
| 211 | * @param manager Pointer to the memory manager to be used to
|
---|
| 212 | * allocate objects.
|
---|
| 213 | *
|
---|
| 214 | * ctor# 7 relative ctor
|
---|
| 215 | *
|
---|
| 216 | */
|
---|
| 217 | XMLUri(const XMLUri* const baseURI
|
---|
| 218 | , const XMLCh* const uriSpec
|
---|
| 219 | , MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager);
|
---|
| 220 |
|
---|
| 221 | /**
|
---|
| 222 | * Copy constructor
|
---|
| 223 | */
|
---|
| 224 | XMLUri(const XMLUri& toCopy);
|
---|
| 225 | XMLUri& operator=(const XMLUri& toAssign);
|
---|
| 226 |
|
---|
| 227 | virtual ~XMLUri();
|
---|
| 228 |
|
---|
| 229 | // -----------------------------------------------------------------------
|
---|
| 230 | // Getter methods
|
---|
| 231 | // -----------------------------------------------------------------------
|
---|
| 232 | /**
|
---|
| 233 | * Get the URI as a string specification. See RFC 2396 Section 5.2.
|
---|
| 234 | *
|
---|
| 235 | * @return the URI string specification
|
---|
| 236 | */
|
---|
| 237 | const XMLCh* getUriText() const;
|
---|
| 238 |
|
---|
| 239 | /**
|
---|
| 240 | * Get the scheme for this URI.
|
---|
| 241 | *
|
---|
| 242 | * @return the scheme for this URI
|
---|
| 243 | */
|
---|
| 244 | const XMLCh* getScheme() const;
|
---|
| 245 |
|
---|
| 246 | /**
|
---|
| 247 | * Get the userinfo for this URI.
|
---|
| 248 | *
|
---|
| 249 | * @return the userinfo for this URI (null if not specified).
|
---|
| 250 | */
|
---|
| 251 | const XMLCh* getUserInfo() const;
|
---|
| 252 |
|
---|
| 253 |
|
---|
| 254 | /**
|
---|
| 255 | * Get the host for this URI.
|
---|
| 256 | *
|
---|
| 257 | * @return the host for this URI (null if not specified).
|
---|
| 258 | */
|
---|
| 259 | const XMLCh* getHost() const;
|
---|
| 260 |
|
---|
| 261 | /**
|
---|
| 262 | * Get the port for this URI.
|
---|
| 263 | *
|
---|
| 264 | * @return the port for this URI (-1 if not specified).
|
---|
| 265 | */
|
---|
| 266 | int getPort() const;
|
---|
| 267 |
|
---|
| 268 | /**
|
---|
| 269 | * Get the registry based authority for this URI.
|
---|
| 270 | *
|
---|
| 271 | * @return the registry based authority (null if not specified).
|
---|
| 272 | */
|
---|
| 273 | const XMLCh* getRegBasedAuthority() const;
|
---|
| 274 |
|
---|
| 275 | /**
|
---|
| 276 | * Get the path for this URI. Note that the value returned is the path
|
---|
| 277 | * only and does not include the query string or fragment.
|
---|
| 278 | *
|
---|
| 279 | * @return the path for this URI.
|
---|
| 280 | */
|
---|
| 281 | const XMLCh* getPath() const;
|
---|
| 282 |
|
---|
| 283 | /**
|
---|
| 284 | * Get the query string for this URI.
|
---|
| 285 | *
|
---|
| 286 | * @return the query string for this URI. Null is returned if there
|
---|
| 287 | * was no "?" in the URI spec, empty string if there was a
|
---|
| 288 | * "?" but no query string following it.
|
---|
| 289 | */
|
---|
| 290 | const XMLCh* getQueryString() const;
|
---|
| 291 |
|
---|
| 292 | /**
|
---|
| 293 | * Get the fragment for this URI.
|
---|
| 294 | *
|
---|
| 295 | * @return the fragment for this URI. Null is returned if there
|
---|
| 296 | * was no "#" in the URI spec, empty string if there was a
|
---|
| 297 | * "#" but no fragment following it.
|
---|
| 298 | */
|
---|
| 299 | const XMLCh* getFragment() const;
|
---|
| 300 |
|
---|
| 301 | // -----------------------------------------------------------------------
|
---|
| 302 | // Setter methods
|
---|
| 303 | // -----------------------------------------------------------------------
|
---|
| 304 |
|
---|
| 305 | /**
|
---|
| 306 | * Set the scheme for this URI. The scheme is converted to lowercase
|
---|
| 307 | * before it is set.
|
---|
| 308 | *
|
---|
| 309 | * @param newScheme the scheme for this URI (cannot be null)
|
---|
| 310 | *
|
---|
| 311 | */
|
---|
| 312 | void setScheme(const XMLCh* const newScheme);
|
---|
| 313 |
|
---|
| 314 | /**
|
---|
| 315 | * Set the userinfo for this URI. If a non-null value is passed in and
|
---|
| 316 | * the host value is null, then an exception is thrown.
|
---|
| 317 | *
|
---|
| 318 | * @param newUserInfo the userinfo for this URI
|
---|
| 319 | *
|
---|
| 320 | */
|
---|
| 321 | void setUserInfo(const XMLCh* const newUserInfo);
|
---|
| 322 |
|
---|
| 323 | /**
|
---|
| 324 | * Set the host for this URI. If null is passed in, the userinfo
|
---|
| 325 | * field is also set to null and the port is set to -1.
|
---|
| 326 | *
|
---|
| 327 | * Note: This method overwrites registry based authority if it
|
---|
| 328 | * previously existed in this URI.
|
---|
| 329 | *
|
---|
| 330 | * @param newHost the host for this URI
|
---|
| 331 | *
|
---|
| 332 | */
|
---|
| 333 | void setHost(const XMLCh* const newHost);
|
---|
| 334 |
|
---|
| 335 | /**
|
---|
| 336 | * Set the port for this URI. -1 is used to indicate that the port is
|
---|
| 337 | * not specified, otherwise valid port numbers are between 0 and 65535.
|
---|
| 338 | * If a valid port number is passed in and the host field is null,
|
---|
| 339 | * an exception is thrown.
|
---|
| 340 | *
|
---|
| 341 | * @param newPort the port number for this URI
|
---|
| 342 | *
|
---|
| 343 | */
|
---|
| 344 | void setPort(int newPort);
|
---|
| 345 |
|
---|
| 346 | /**
|
---|
| 347 | * Sets the registry based authority for this URI.
|
---|
| 348 | *
|
---|
| 349 | * Note: This method overwrites server based authority
|
---|
| 350 | * if it previously existed in this URI.
|
---|
| 351 | *
|
---|
| 352 | * @param newRegAuth the registry based authority for this URI
|
---|
| 353 | */
|
---|
| 354 | void setRegBasedAuthority(const XMLCh* const newRegAuth);
|
---|
| 355 |
|
---|
| 356 | /**
|
---|
| 357 | * Set the path for this URI.
|
---|
| 358 | *
|
---|
| 359 | * If the supplied path is null, then the
|
---|
| 360 | * query string and fragment are set to null as well.
|
---|
| 361 | *
|
---|
| 362 | * If the supplied path includes a query string and/or fragment,
|
---|
| 363 | * these fields will be parsed and set as well.
|
---|
| 364 | *
|
---|
| 365 | * Note:
|
---|
| 366 | *
|
---|
| 367 | * For URIs following the "generic URI" syntax, the path
|
---|
| 368 | * specified should start with a slash.
|
---|
| 369 | *
|
---|
| 370 | * For URIs that do not follow the generic URI syntax, this method
|
---|
| 371 | * sets the scheme-specific part.
|
---|
| 372 | *
|
---|
| 373 | * @param newPath the path for this URI (may be null)
|
---|
| 374 | *
|
---|
| 375 | */
|
---|
| 376 | void setPath(const XMLCh* const newPath);
|
---|
| 377 |
|
---|
| 378 | /**
|
---|
| 379 | * Set the query string for this URI. A non-null value is valid only
|
---|
| 380 | * if this is an URI conforming to the generic URI syntax and
|
---|
| 381 | * the path value is not null.
|
---|
| 382 | *
|
---|
| 383 | * @param newQueryString the query string for this URI
|
---|
| 384 | *
|
---|
| 385 | */
|
---|
| 386 | void setQueryString(const XMLCh* const newQueryString);
|
---|
| 387 |
|
---|
| 388 | /**
|
---|
| 389 | * Set the fragment for this URI. A non-null value is valid only
|
---|
| 390 | * if this is a URI conforming to the generic URI syntax and
|
---|
| 391 | * the path value is not null.
|
---|
| 392 | *
|
---|
| 393 | * @param newFragment the fragment for this URI
|
---|
| 394 | *
|
---|
| 395 | */
|
---|
| 396 | void setFragment(const XMLCh* const newFragment);
|
---|
| 397 |
|
---|
| 398 | // -----------------------------------------------------------------------
|
---|
| 399 | // Miscellaneous methods
|
---|
| 400 | // -----------------------------------------------------------------------
|
---|
| 401 |
|
---|
| 402 | /**
|
---|
| 403 | * Determine whether a given string contains only URI characters (also
|
---|
| 404 | * called "uric" in RFC 2396). uric consist of all reserved
|
---|
| 405 | * characters, unreserved characters and escaped characters.
|
---|
| 406 | *
|
---|
| 407 | * @return true if the string is comprised of uric, false otherwise
|
---|
| 408 | */
|
---|
| 409 | static bool isURIString(const XMLCh* const uric);
|
---|
| 410 |
|
---|
| 411 | /**
|
---|
| 412 | * Determine whether a given string is a valid URI
|
---|
| 413 | */
|
---|
| 414 | static bool isValidURI( const XMLUri* const baseURI
|
---|
| 415 | , const XMLCh* const uriStr);
|
---|
| 416 | /**
|
---|
| 417 | * Determine whether a given string is a valid URI
|
---|
| 418 | */
|
---|
| 419 | static bool isValidURI( bool haveBaseURI
|
---|
| 420 | , const XMLCh* const uriStr);
|
---|
| 421 |
|
---|
| 422 | /***
|
---|
| 423 | * Support for Serialization/De-serialization
|
---|
| 424 | ***/
|
---|
| 425 | DECL_XSERIALIZABLE(XMLUri)
|
---|
| 426 |
|
---|
| 427 | XMLUri(MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager);
|
---|
| 428 |
|
---|
| 429 | private:
|
---|
| 430 |
|
---|
| 431 | static const XMLCh MARK_OR_RESERVED_CHARACTERS[];
|
---|
| 432 | static const XMLCh RESERVED_CHARACTERS[];
|
---|
| 433 | static const XMLCh MARK_CHARACTERS[];
|
---|
| 434 | static const XMLCh SCHEME_CHARACTERS[];
|
---|
| 435 | static const XMLCh USERINFO_CHARACTERS[];
|
---|
| 436 | static const XMLCh REG_NAME_CHARACTERS[];
|
---|
| 437 | static const XMLCh PATH_CHARACTERS[];
|
---|
| 438 |
|
---|
| 439 | //helper method for getUriText
|
---|
| 440 | void buildFullText();
|
---|
| 441 |
|
---|
| 442 | // -----------------------------------------------------------------------
|
---|
| 443 | // Private helper methods
|
---|
| 444 | // -----------------------------------------------------------------------
|
---|
| 445 |
|
---|
| 446 | /**
|
---|
| 447 | * Determine whether a character is a reserved character:
|
---|
| 448 | *
|
---|
| 449 | * @return true if the string contains any reserved characters
|
---|
| 450 | */
|
---|
| 451 | static bool isReservedCharacter(const XMLCh theChar);
|
---|
| 452 |
|
---|
| 453 | /**
|
---|
| 454 | * Determine whether a character is a path character:
|
---|
| 455 | *
|
---|
| 456 | * @return true if the character is path character
|
---|
| 457 | */
|
---|
| 458 | static bool isPathCharacter(const XMLCh theChar);
|
---|
| 459 |
|
---|
| 460 | /**
|
---|
| 461 | * Determine whether a char is an unreserved character.
|
---|
| 462 | *
|
---|
| 463 | * @return true if the char is unreserved, false otherwise
|
---|
| 464 | */
|
---|
| 465 | static bool isUnreservedCharacter(const XMLCh theChar);
|
---|
| 466 |
|
---|
| 467 | /**
|
---|
| 468 | * Determine whether a char is an reserved or unreserved character.
|
---|
| 469 | *
|
---|
| 470 | * @return true if the char is reserved or unreserved, false otherwise
|
---|
| 471 | */
|
---|
| 472 | static bool isReservedOrUnreservedCharacter(const XMLCh theChar);
|
---|
| 473 |
|
---|
| 474 | /**
|
---|
| 475 | * Determine whether a scheme conforms to the rules for a scheme name.
|
---|
| 476 | * A scheme is conformant if it starts with an alphanumeric, and
|
---|
| 477 | * contains only alphanumerics, '+','-' and '.'.
|
---|
| 478 | *
|
---|
| 479 | * @return true if the scheme is conformant, false otherwise
|
---|
| 480 | */
|
---|
| 481 | static bool isConformantSchemeName(const XMLCh* const scheme);
|
---|
| 482 |
|
---|
| 483 | /**
|
---|
| 484 | * Determine whether a userInfo conforms to the rules for a userinfo.
|
---|
| 485 | *
|
---|
| 486 | * @return true if the scheme is conformant, false otherwise
|
---|
| 487 | */
|
---|
| 488 | static void isConformantUserInfo(const XMLCh* const userInfo
|
---|
| 489 | , MemoryManager* const manager);
|
---|
| 490 |
|
---|
| 491 | /**
|
---|
| 492 | * Determines whether the components host, port, and user info
|
---|
| 493 | * are valid as a server authority.
|
---|
| 494 | *
|
---|
| 495 | * @return true if the given host, port, and userinfo compose
|
---|
| 496 | * a valid server authority
|
---|
| 497 | */
|
---|
| 498 | static bool isValidServerBasedAuthority(const XMLCh* const host
|
---|
| 499 | , const int hostLen
|
---|
| 500 | , const int port
|
---|
| 501 | , const XMLCh* const userinfo
|
---|
| 502 | , const int userLen);
|
---|
| 503 |
|
---|
| 504 | /**
|
---|
| 505 | * Determines whether the components host, port, and user info
|
---|
| 506 | * are valid as a server authority.
|
---|
| 507 | *
|
---|
| 508 | * @return true if the given host, port, and userinfo compose
|
---|
| 509 | * a valid server authority
|
---|
| 510 | */
|
---|
| 511 | static bool isValidServerBasedAuthority(const XMLCh* const host
|
---|
| 512 | , const int port
|
---|
| 513 | , const XMLCh* const userinfo
|
---|
| 514 | , MemoryManager* const manager);
|
---|
| 515 |
|
---|
| 516 | /**
|
---|
| 517 | * Determines whether the given string is a registry based authority.
|
---|
| 518 | *
|
---|
| 519 | * @param authority the authority component of a URI
|
---|
| 520 | *
|
---|
| 521 | * @return true if the given string is a registry based authority
|
---|
| 522 | */
|
---|
| 523 | static bool isValidRegistryBasedAuthority(const XMLCh* const authority
|
---|
| 524 | , const int authLen);
|
---|
| 525 |
|
---|
| 526 | /**
|
---|
| 527 | * Determines whether the given string is a registry based authority.
|
---|
| 528 | *
|
---|
| 529 | * @param authority the authority component of a URI
|
---|
| 530 | *
|
---|
| 531 | * @return true if the given string is a registry based authority
|
---|
| 532 | */
|
---|
| 533 | static bool isValidRegistryBasedAuthority(const XMLCh* const authority);
|
---|
| 534 |
|
---|
| 535 | /**
|
---|
| 536 | * Determine whether a string is syntactically capable of representing
|
---|
| 537 | * a valid IPv4 address, IPv6 reference or the domain name of a network host.
|
---|
| 538 | *
|
---|
| 539 | * A valid IPv4 address consists of four decimal digit groups
|
---|
| 540 | * separated by a '.'.
|
---|
| 541 | *
|
---|
| 542 | * See RFC 2732 Section 3, and RFC 2373 Section 2.2, for the
|
---|
| 543 | * definition of IPv6 references.
|
---|
| 544 | *
|
---|
| 545 | * A hostname consists of domain labels (each of which must begin and
|
---|
| 546 | * end with an alphanumeric but may contain '-') separated by a '.'.
|
---|
| 547 | * See RFC 2396 Section 3.2.2.
|
---|
| 548 | *
|
---|
| 549 | * @return true if the string is a syntactically valid IPv4 address
|
---|
| 550 | * or hostname
|
---|
| 551 | */
|
---|
| 552 | static bool isWellFormedAddress(const XMLCh* const addr
|
---|
| 553 | , MemoryManager* const manager);
|
---|
| 554 |
|
---|
| 555 | /**
|
---|
| 556 | * Determines whether a string is an IPv4 address as defined by
|
---|
| 557 | * RFC 2373, and under the further constraint that it must be a 32-bit
|
---|
| 558 | * address. Though not expressed in the grammar, in order to satisfy
|
---|
| 559 | * the 32-bit address constraint, each segment of the address cannot
|
---|
| 560 | * be greater than 255 (8 bits of information).
|
---|
| 561 | *
|
---|
| 562 | * @return true if the string is a syntactically valid IPv4 address
|
---|
| 563 | */
|
---|
| 564 | static bool isWellFormedIPv4Address(const XMLCh* const addr, const int length);
|
---|
| 565 |
|
---|
| 566 | /**
|
---|
| 567 | * Determines whether a string is an IPv6 reference as defined
|
---|
| 568 | * by RFC 2732, where IPv6address is defined in RFC 2373. The
|
---|
| 569 | * IPv6 address is parsed according to Section 2.2 of RFC 2373,
|
---|
| 570 | * with the additional constraint that the address be composed of
|
---|
| 571 | * 128 bits of information.
|
---|
| 572 | *
|
---|
| 573 | * Note: The BNF expressed in RFC 2373 Appendix B does not
|
---|
| 574 | * accurately describe section 2.2, and was in fact removed from
|
---|
| 575 | * RFC 3513, the successor of RFC 2373.
|
---|
| 576 | *
|
---|
| 577 | * @return true if the string is a syntactically valid IPv6 reference
|
---|
| 578 | */
|
---|
| 579 | static bool isWellFormedIPv6Reference(const XMLCh* const addr, const int length);
|
---|
| 580 |
|
---|
| 581 | /**
|
---|
| 582 | * Helper function for isWellFormedIPv6Reference which scans the
|
---|
| 583 | * hex sequences of an IPv6 address. It returns the index of the
|
---|
| 584 | * next character to scan in the address, or -1 if the string
|
---|
| 585 | * cannot match a valid IPv6 address.
|
---|
| 586 | *
|
---|
| 587 | * @param address the string to be scanned
|
---|
| 588 | * @param index the beginning index (inclusive)
|
---|
| 589 | * @param end the ending index (exclusive)
|
---|
| 590 | * @param counter a counter for the number of 16-bit sections read
|
---|
| 591 | * in the address
|
---|
| 592 | *
|
---|
| 593 | * @return the index of the next character to scan, or -1 if the
|
---|
| 594 | * string cannot match a valid IPv6 address
|
---|
| 595 | */
|
---|
| 596 | static int scanHexSequence (const XMLCh* const addr, int index, int end, int& counter);
|
---|
| 597 |
|
---|
| 598 | /**
|
---|
| 599 | * Get the indicator as to whether this URI uses the "generic URI"
|
---|
| 600 | * syntax.
|
---|
| 601 | *
|
---|
| 602 | * @return true if this URI uses the "generic URI" syntax, false
|
---|
| 603 | * otherwise
|
---|
| 604 | */
|
---|
| 605 | bool isGenericURI();
|
---|
| 606 |
|
---|
| 607 | // -----------------------------------------------------------------------
|
---|
| 608 | // Miscellaneous methods
|
---|
| 609 | // -----------------------------------------------------------------------
|
---|
| 610 |
|
---|
| 611 | /**
|
---|
| 612 | * Initialize all fields of this URI from another URI.
|
---|
| 613 | *
|
---|
| 614 | * @param toCopy the URI to copy (cannot be null)
|
---|
| 615 | */
|
---|
| 616 | void initialize(const XMLUri& toCopy);
|
---|
| 617 |
|
---|
| 618 | /**
|
---|
| 619 | * Initializes this URI from a base URI and a URI specification string.
|
---|
| 620 | * See RFC 2396 Section 4 and Appendix B for specifications on parsing
|
---|
| 621 | * the URI and Section 5 for specifications on resolving relative URIs
|
---|
| 622 | * and relative paths.
|
---|
| 623 | *
|
---|
| 624 | * @param baseURI the base URI (may be null if uriSpec is an absolute
|
---|
| 625 | * URI)
|
---|
| 626 | *
|
---|
| 627 | * @param uriSpec the URI spec string which may be an absolute or
|
---|
| 628 | * relative URI (can only be null/empty if base
|
---|
| 629 | * is not null)
|
---|
| 630 | *
|
---|
| 631 | */
|
---|
| 632 | void initialize(const XMLUri* const baseURI
|
---|
| 633 | , const XMLCh* const uriSpec);
|
---|
| 634 |
|
---|
| 635 | /**
|
---|
| 636 | * Initialize the scheme for this URI from a URI string spec.
|
---|
| 637 | *
|
---|
| 638 | * @param uriSpec the URI specification (cannot be null)
|
---|
| 639 | *
|
---|
| 640 | */
|
---|
| 641 | void initializeScheme(const XMLCh* const uriSpec);
|
---|
| 642 |
|
---|
| 643 | /**
|
---|
| 644 | * Initialize the authority (userinfo, host and port) for this
|
---|
| 645 | * URI from a URI string spec.
|
---|
| 646 | *
|
---|
| 647 | * @param uriSpec the URI specification (cannot be null)
|
---|
| 648 | *
|
---|
| 649 | */
|
---|
| 650 | void initializeAuthority(const XMLCh* const uriSpec);
|
---|
| 651 |
|
---|
| 652 | /**
|
---|
| 653 | * Initialize the path for this URI from a URI string spec.
|
---|
| 654 | *
|
---|
| 655 | * @param uriSpec the URI specification (cannot be null)
|
---|
| 656 | *
|
---|
| 657 | */
|
---|
| 658 | void initializePath(const XMLCh* const uriSpec);
|
---|
| 659 |
|
---|
| 660 | /**
|
---|
| 661 | * cleanup the data variables
|
---|
| 662 | *
|
---|
| 663 | */
|
---|
| 664 | void cleanUp();
|
---|
| 665 |
|
---|
| 666 | static bool isConformantSchemeName(const XMLCh* const scheme,
|
---|
| 667 | const int schemeLen);
|
---|
| 668 | static bool processScheme(const XMLCh* const uriStr, int& index);
|
---|
| 669 | static bool processAuthority(const XMLCh* const uriStr, const int authLen);
|
---|
| 670 | static bool isWellFormedAddress(const XMLCh* const addr, const int addrLen);
|
---|
| 671 | static bool processPath(const XMLCh* const pathStr, const int pathStrLen,
|
---|
| 672 | const bool isSchemePresent);
|
---|
| 673 |
|
---|
| 674 | // -----------------------------------------------------------------------
|
---|
| 675 | // Data members
|
---|
| 676 | //
|
---|
| 677 | // for all the data member, we own it,
|
---|
| 678 | // responsible for the creation and/or deletion for
|
---|
| 679 | // the memory allocated.
|
---|
| 680 | //
|
---|
| 681 | // -----------------------------------------------------------------------
|
---|
| 682 | XMLCh* fScheme;
|
---|
| 683 | XMLCh* fUserInfo;
|
---|
| 684 | XMLCh* fHost;
|
---|
| 685 | int fPort;
|
---|
| 686 | XMLCh* fRegAuth;
|
---|
| 687 | XMLCh* fPath;
|
---|
| 688 | XMLCh* fQueryString;
|
---|
| 689 | XMLCh* fFragment;
|
---|
| 690 | XMLCh* fURIText;
|
---|
| 691 | MemoryManager* fMemoryManager;
|
---|
| 692 | };
|
---|
| 693 |
|
---|
| 694 | // ---------------------------------------------------------------------------
|
---|
| 695 | // XMLUri: Getter methods
|
---|
| 696 | // ---------------------------------------------------------------------------
|
---|
| 697 | inline const XMLCh* XMLUri::getScheme() const
|
---|
| 698 | {
|
---|
| 699 | return fScheme;
|
---|
| 700 | }
|
---|
| 701 |
|
---|
| 702 | inline const XMLCh* XMLUri::getUserInfo() const
|
---|
| 703 | {
|
---|
| 704 | return fUserInfo;
|
---|
| 705 | }
|
---|
| 706 |
|
---|
| 707 | inline const XMLCh* XMLUri::getHost() const
|
---|
| 708 | {
|
---|
| 709 | return fHost;
|
---|
| 710 | }
|
---|
| 711 |
|
---|
| 712 | inline int XMLUri::getPort() const
|
---|
| 713 | {
|
---|
| 714 | return fPort;
|
---|
| 715 | }
|
---|
| 716 |
|
---|
| 717 | inline const XMLCh* XMLUri::getRegBasedAuthority() const
|
---|
| 718 | {
|
---|
| 719 | return fRegAuth;
|
---|
| 720 | }
|
---|
| 721 |
|
---|
| 722 | inline const XMLCh* XMLUri::getPath() const
|
---|
| 723 | {
|
---|
| 724 | return fPath;
|
---|
| 725 | }
|
---|
| 726 |
|
---|
| 727 | inline const XMLCh* XMLUri::getQueryString() const
|
---|
| 728 | {
|
---|
| 729 | return fQueryString;
|
---|
| 730 | }
|
---|
| 731 |
|
---|
| 732 | inline const XMLCh* XMLUri::getFragment() const
|
---|
| 733 | {
|
---|
| 734 | return fFragment;
|
---|
| 735 | }
|
---|
| 736 |
|
---|
| 737 | inline const XMLCh* XMLUri::getUriText() const
|
---|
| 738 | {
|
---|
| 739 | //
|
---|
| 740 | // Fault it in if not already. Since this is a const method and we
|
---|
| 741 | // can't use mutable members due the compilers we have to support,
|
---|
| 742 | // we have to cast off the constness.
|
---|
| 743 | //
|
---|
| 744 | if (!fURIText)
|
---|
| 745 | ((XMLUri*)this)->buildFullText();
|
---|
| 746 |
|
---|
| 747 | return fURIText;
|
---|
| 748 | }
|
---|
| 749 |
|
---|
| 750 | // ---------------------------------------------------------------------------
|
---|
| 751 | // XMLUri: Helper methods
|
---|
| 752 | // ---------------------------------------------------------------------------
|
---|
| 753 | inline bool XMLUri::isReservedOrUnreservedCharacter(const XMLCh theChar)
|
---|
| 754 | {
|
---|
| 755 | return (XMLString::isAlphaNum(theChar) ||
|
---|
| 756 | XMLString::indexOf(MARK_OR_RESERVED_CHARACTERS, theChar) != -1);
|
---|
| 757 | }
|
---|
| 758 |
|
---|
| 759 | inline bool XMLUri::isReservedCharacter(const XMLCh theChar)
|
---|
| 760 | {
|
---|
| 761 | return (XMLString::indexOf(RESERVED_CHARACTERS, theChar) != -1);
|
---|
| 762 | }
|
---|
| 763 |
|
---|
| 764 | inline bool XMLUri::isPathCharacter(const XMLCh theChar)
|
---|
| 765 | {
|
---|
| 766 | return (XMLString::indexOf(PATH_CHARACTERS, theChar) != -1);
|
---|
| 767 | }
|
---|
| 768 |
|
---|
| 769 | inline bool XMLUri::isUnreservedCharacter(const XMLCh theChar)
|
---|
| 770 | {
|
---|
| 771 | return (XMLString::isAlphaNum(theChar) ||
|
---|
| 772 | XMLString::indexOf(MARK_CHARACTERS, theChar) != -1);
|
---|
| 773 | }
|
---|
| 774 |
|
---|
| 775 | XERCES_CPP_NAMESPACE_END
|
---|
| 776 |
|
---|
| 777 | #endif
|
---|