6
|
1 |
/*
|
|
2 |
* reserved comment block
|
|
3 |
* DO NOT REMOVE OR ALTER!
|
|
4 |
*/
|
|
5 |
/*
|
|
6 |
* Copyright 1999-2005 The Apache Software Foundation.
|
|
7 |
*
|
|
8 |
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
9 |
* you may not use this file except in compliance with the License.
|
|
10 |
* You may obtain a copy of the License at
|
|
11 |
*
|
|
12 |
* http://www.apache.org/licenses/LICENSE-2.0
|
|
13 |
*
|
|
14 |
* Unless required by applicable law or agreed to in writing, software
|
|
15 |
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
16 |
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
17 |
* See the License for the specific language governing permissions and
|
|
18 |
* limitations under the License.
|
|
19 |
*/
|
|
20 |
|
|
21 |
package com.sun.org.apache.xerces.internal.util;
|
|
22 |
|
|
23 |
import java.io.IOException;
|
|
24 |
import java.io.Serializable;
|
17538
|
25 |
import java.util.Objects;
|
6
|
26 |
|
|
27 |
/**********************************************************************
|
|
28 |
* A class to represent a Uniform Resource Identifier (URI). This class
|
|
29 |
* is designed to handle the parsing of URIs and provide access to
|
|
30 |
* the various components (scheme, host, port, userinfo, path, query
|
|
31 |
* string and fragment) that may constitute a URI.
|
|
32 |
* <p>
|
|
33 |
* Parsing of a URI specification is done according to the URI
|
|
34 |
* syntax described in
|
|
35 |
* <a href="http://www.ietf.org/rfc/rfc2396.txt?number=2396">RFC 2396</a>,
|
|
36 |
* and amended by
|
|
37 |
* <a href="http://www.ietf.org/rfc/rfc2732.txt?number=2732">RFC 2732</a>.
|
|
38 |
* <p>
|
|
39 |
* Every absolute URI consists of a scheme, followed by a colon (':'),
|
|
40 |
* followed by a scheme-specific part. For URIs that follow the
|
|
41 |
* "generic URI" syntax, the scheme-specific part begins with two
|
|
42 |
* slashes ("//") and may be followed by an authority segment (comprised
|
|
43 |
* of user information, host, and port), path segment, query segment
|
|
44 |
* and fragment. Note that RFC 2396 no longer specifies the use of the
|
|
45 |
* parameters segment and excludes the "user:password" syntax as part of
|
|
46 |
* the authority segment. If "user:password" appears in a URI, the entire
|
|
47 |
* user/password string is stored as userinfo.
|
|
48 |
* <p>
|
|
49 |
* For URIs that do not follow the "generic URI" syntax (e.g. mailto),
|
|
50 |
* the entire scheme-specific part is treated as the "path" portion
|
|
51 |
* of the URI.
|
|
52 |
* <p>
|
|
53 |
* Note that, unlike the java.net.URL class, this class does not provide
|
|
54 |
* any built-in network access functionality nor does it provide any
|
|
55 |
* scheme-specific functionality (for example, it does not know a
|
|
56 |
* default port for a specific scheme). Rather, it only knows the
|
|
57 |
* grammar and basic set of operations that can be applied to a URI.
|
|
58 |
*
|
|
59 |
*
|
|
60 |
**********************************************************************/
|
|
61 |
public class URI implements Serializable {
|
|
62 |
|
|
63 |
/*******************************************************************
|
|
64 |
* MalformedURIExceptions are thrown in the process of building a URI
|
|
65 |
* or setting fields on a URI when an operation would result in an
|
|
66 |
* invalid URI specification.
|
|
67 |
*
|
|
68 |
********************************************************************/
|
|
69 |
public static class MalformedURIException extends IOException {
|
|
70 |
|
|
71 |
/** Serialization version. */
|
|
72 |
static final long serialVersionUID = -6695054834342951930L;
|
|
73 |
|
|
74 |
/******************************************************************
|
|
75 |
* Constructs a <code>MalformedURIException</code> with no specified
|
|
76 |
* detail message.
|
|
77 |
******************************************************************/
|
|
78 |
public MalformedURIException() {
|
|
79 |
super();
|
|
80 |
}
|
|
81 |
|
|
82 |
/*****************************************************************
|
|
83 |
* Constructs a <code>MalformedURIException</code> with the
|
|
84 |
* specified detail message.
|
|
85 |
*
|
|
86 |
* @param p_msg the detail message.
|
|
87 |
******************************************************************/
|
|
88 |
public MalformedURIException(String p_msg) {
|
|
89 |
super(p_msg);
|
|
90 |
}
|
|
91 |
}
|
|
92 |
|
|
93 |
/** Serialization version. */
|
|
94 |
static final long serialVersionUID = 1601921774685357214L;
|
|
95 |
|
|
96 |
private static final byte [] fgLookupTable = new byte[128];
|
|
97 |
|
|
98 |
/**
|
|
99 |
* Character Classes
|
|
100 |
*/
|
|
101 |
|
|
102 |
/** reserved characters ;/?:@&=+$,[] */
|
|
103 |
//RFC 2732 added '[' and ']' as reserved characters
|
|
104 |
private static final int RESERVED_CHARACTERS = 0x01;
|
|
105 |
|
|
106 |
/** URI punctuation mark characters: -_.!~*'() - these, combined with
|
|
107 |
alphanumerics, constitute the "unreserved" characters */
|
|
108 |
private static final int MARK_CHARACTERS = 0x02;
|
|
109 |
|
|
110 |
/** scheme can be composed of alphanumerics and these characters: +-. */
|
|
111 |
private static final int SCHEME_CHARACTERS = 0x04;
|
|
112 |
|
|
113 |
/** userinfo can be composed of unreserved, escaped and these
|
|
114 |
characters: ;:&=+$, */
|
|
115 |
private static final int USERINFO_CHARACTERS = 0x08;
|
|
116 |
|
|
117 |
/** ASCII letter characters */
|
|
118 |
private static final int ASCII_ALPHA_CHARACTERS = 0x10;
|
|
119 |
|
|
120 |
/** ASCII digit characters */
|
|
121 |
private static final int ASCII_DIGIT_CHARACTERS = 0x20;
|
|
122 |
|
|
123 |
/** ASCII hex characters */
|
|
124 |
private static final int ASCII_HEX_CHARACTERS = 0x40;
|
|
125 |
|
|
126 |
/** Path characters */
|
|
127 |
private static final int PATH_CHARACTERS = 0x80;
|
|
128 |
|
|
129 |
/** Mask for alpha-numeric characters */
|
|
130 |
private static final int MASK_ALPHA_NUMERIC = ASCII_ALPHA_CHARACTERS | ASCII_DIGIT_CHARACTERS;
|
|
131 |
|
|
132 |
/** Mask for unreserved characters */
|
|
133 |
private static final int MASK_UNRESERVED_MASK = MASK_ALPHA_NUMERIC | MARK_CHARACTERS;
|
|
134 |
|
|
135 |
/** Mask for URI allowable characters except for % */
|
|
136 |
private static final int MASK_URI_CHARACTER = MASK_UNRESERVED_MASK | RESERVED_CHARACTERS;
|
|
137 |
|
|
138 |
/** Mask for scheme characters */
|
|
139 |
private static final int MASK_SCHEME_CHARACTER = MASK_ALPHA_NUMERIC | SCHEME_CHARACTERS;
|
|
140 |
|
|
141 |
/** Mask for userinfo characters */
|
|
142 |
private static final int MASK_USERINFO_CHARACTER = MASK_UNRESERVED_MASK | USERINFO_CHARACTERS;
|
|
143 |
|
|
144 |
/** Mask for path characters */
|
|
145 |
private static final int MASK_PATH_CHARACTER = MASK_UNRESERVED_MASK | PATH_CHARACTERS;
|
|
146 |
|
|
147 |
static {
|
|
148 |
// Add ASCII Digits and ASCII Hex Numbers
|
|
149 |
for (int i = '0'; i <= '9'; ++i) {
|
|
150 |
fgLookupTable[i] |= ASCII_DIGIT_CHARACTERS | ASCII_HEX_CHARACTERS;
|
|
151 |
}
|
|
152 |
|
|
153 |
// Add ASCII Letters and ASCII Hex Numbers
|
|
154 |
for (int i = 'A'; i <= 'F'; ++i) {
|
|
155 |
fgLookupTable[i] |= ASCII_ALPHA_CHARACTERS | ASCII_HEX_CHARACTERS;
|
|
156 |
fgLookupTable[i+0x00000020] |= ASCII_ALPHA_CHARACTERS | ASCII_HEX_CHARACTERS;
|
|
157 |
}
|
|
158 |
|
|
159 |
// Add ASCII Letters
|
|
160 |
for (int i = 'G'; i <= 'Z'; ++i) {
|
|
161 |
fgLookupTable[i] |= ASCII_ALPHA_CHARACTERS;
|
|
162 |
fgLookupTable[i+0x00000020] |= ASCII_ALPHA_CHARACTERS;
|
|
163 |
}
|
|
164 |
|
|
165 |
// Add Reserved Characters
|
|
166 |
fgLookupTable[';'] |= RESERVED_CHARACTERS;
|
|
167 |
fgLookupTable['/'] |= RESERVED_CHARACTERS;
|
|
168 |
fgLookupTable['?'] |= RESERVED_CHARACTERS;
|
|
169 |
fgLookupTable[':'] |= RESERVED_CHARACTERS;
|
|
170 |
fgLookupTable['@'] |= RESERVED_CHARACTERS;
|
|
171 |
fgLookupTable['&'] |= RESERVED_CHARACTERS;
|
|
172 |
fgLookupTable['='] |= RESERVED_CHARACTERS;
|
|
173 |
fgLookupTable['+'] |= RESERVED_CHARACTERS;
|
|
174 |
fgLookupTable['$'] |= RESERVED_CHARACTERS;
|
|
175 |
fgLookupTable[','] |= RESERVED_CHARACTERS;
|
|
176 |
fgLookupTable['['] |= RESERVED_CHARACTERS;
|
|
177 |
fgLookupTable[']'] |= RESERVED_CHARACTERS;
|
|
178 |
|
|
179 |
// Add Mark Characters
|
|
180 |
fgLookupTable['-'] |= MARK_CHARACTERS;
|
|
181 |
fgLookupTable['_'] |= MARK_CHARACTERS;
|
|
182 |
fgLookupTable['.'] |= MARK_CHARACTERS;
|
|
183 |
fgLookupTable['!'] |= MARK_CHARACTERS;
|
|
184 |
fgLookupTable['~'] |= MARK_CHARACTERS;
|
|
185 |
fgLookupTable['*'] |= MARK_CHARACTERS;
|
|
186 |
fgLookupTable['\''] |= MARK_CHARACTERS;
|
|
187 |
fgLookupTable['('] |= MARK_CHARACTERS;
|
|
188 |
fgLookupTable[')'] |= MARK_CHARACTERS;
|
|
189 |
|
|
190 |
// Add Scheme Characters
|
|
191 |
fgLookupTable['+'] |= SCHEME_CHARACTERS;
|
|
192 |
fgLookupTable['-'] |= SCHEME_CHARACTERS;
|
|
193 |
fgLookupTable['.'] |= SCHEME_CHARACTERS;
|
|
194 |
|
|
195 |
// Add Userinfo Characters
|
|
196 |
fgLookupTable[';'] |= USERINFO_CHARACTERS;
|
|
197 |
fgLookupTable[':'] |= USERINFO_CHARACTERS;
|
|
198 |
fgLookupTable['&'] |= USERINFO_CHARACTERS;
|
|
199 |
fgLookupTable['='] |= USERINFO_CHARACTERS;
|
|
200 |
fgLookupTable['+'] |= USERINFO_CHARACTERS;
|
|
201 |
fgLookupTable['$'] |= USERINFO_CHARACTERS;
|
|
202 |
fgLookupTable[','] |= USERINFO_CHARACTERS;
|
|
203 |
|
|
204 |
// Add Path Characters
|
|
205 |
fgLookupTable[';'] |= PATH_CHARACTERS;
|
|
206 |
fgLookupTable['/'] |= PATH_CHARACTERS;
|
|
207 |
fgLookupTable[':'] |= PATH_CHARACTERS;
|
|
208 |
fgLookupTable['@'] |= PATH_CHARACTERS;
|
|
209 |
fgLookupTable['&'] |= PATH_CHARACTERS;
|
|
210 |
fgLookupTable['='] |= PATH_CHARACTERS;
|
|
211 |
fgLookupTable['+'] |= PATH_CHARACTERS;
|
|
212 |
fgLookupTable['$'] |= PATH_CHARACTERS;
|
|
213 |
fgLookupTable[','] |= PATH_CHARACTERS;
|
|
214 |
}
|
|
215 |
|
|
216 |
/** Stores the scheme (usually the protocol) for this URI. */
|
|
217 |
private String m_scheme = null;
|
|
218 |
|
|
219 |
/** If specified, stores the userinfo for this URI; otherwise null */
|
|
220 |
private String m_userinfo = null;
|
|
221 |
|
|
222 |
/** If specified, stores the host for this URI; otherwise null */
|
|
223 |
private String m_host = null;
|
|
224 |
|
|
225 |
/** If specified, stores the port for this URI; otherwise -1 */
|
|
226 |
private int m_port = -1;
|
|
227 |
|
|
228 |
/** If specified, stores the registry based authority for this URI; otherwise -1 */
|
|
229 |
private String m_regAuthority = null;
|
|
230 |
|
|
231 |
/** If specified, stores the path for this URI; otherwise null */
|
|
232 |
private String m_path = null;
|
|
233 |
|
|
234 |
/** If specified, stores the query string for this URI; otherwise
|
|
235 |
null. */
|
|
236 |
private String m_queryString = null;
|
|
237 |
|
|
238 |
/** If specified, stores the fragment for this URI; otherwise null */
|
|
239 |
private String m_fragment = null;
|
|
240 |
|
|
241 |
private static boolean DEBUG = false;
|
|
242 |
|
|
243 |
/**
|
|
244 |
* Construct a new and uninitialized URI.
|
|
245 |
*/
|
|
246 |
public URI() {
|
|
247 |
}
|
|
248 |
|
|
249 |
/**
|
|
250 |
* Construct a new URI from another URI. All fields for this URI are
|
|
251 |
* set equal to the fields of the URI passed in.
|
|
252 |
*
|
|
253 |
* @param p_other the URI to copy (cannot be null)
|
|
254 |
*/
|
|
255 |
public URI(URI p_other) {
|
|
256 |
initialize(p_other);
|
|
257 |
}
|
|
258 |
|
|
259 |
/**
|
|
260 |
* Construct a new URI from a URI specification string. If the
|
|
261 |
* specification follows the "generic URI" syntax, (two slashes
|
|
262 |
* following the first colon), the specification will be parsed
|
|
263 |
* accordingly - setting the scheme, userinfo, host,port, path, query
|
|
264 |
* string and fragment fields as necessary. If the specification does
|
|
265 |
* not follow the "generic URI" syntax, the specification is parsed
|
|
266 |
* into a scheme and scheme-specific part (stored as the path) only.
|
|
267 |
*
|
|
268 |
* @param p_uriSpec the URI specification string (cannot be null or
|
|
269 |
* empty)
|
|
270 |
*
|
|
271 |
* @exception MalformedURIException if p_uriSpec violates any syntax
|
|
272 |
* rules
|
|
273 |
*/
|
|
274 |
public URI(String p_uriSpec) throws MalformedURIException {
|
|
275 |
this((URI)null, p_uriSpec);
|
|
276 |
}
|
|
277 |
|
|
278 |
/**
|
|
279 |
* Construct a new URI from a URI specification string. If the
|
|
280 |
* specification follows the "generic URI" syntax, (two slashes
|
|
281 |
* following the first colon), the specification will be parsed
|
|
282 |
* accordingly - setting the scheme, userinfo, host,port, path, query
|
|
283 |
* string and fragment fields as necessary. If the specification does
|
|
284 |
* not follow the "generic URI" syntax, the specification is parsed
|
|
285 |
* into a scheme and scheme-specific part (stored as the path) only.
|
|
286 |
* Construct a relative URI if boolean is assigned to "true"
|
|
287 |
* and p_uriSpec is not valid absolute URI, instead of throwing an exception.
|
|
288 |
*
|
|
289 |
* @param p_uriSpec the URI specification string (cannot be null or
|
|
290 |
* empty)
|
|
291 |
* @param allowNonAbsoluteURI true to permit non-absolute URIs,
|
|
292 |
* false otherwise.
|
|
293 |
*
|
|
294 |
* @exception MalformedURIException if p_uriSpec violates any syntax
|
|
295 |
* rules
|
|
296 |
*/
|
|
297 |
public URI(String p_uriSpec, boolean allowNonAbsoluteURI) throws MalformedURIException {
|
|
298 |
this((URI)null, p_uriSpec, allowNonAbsoluteURI);
|
|
299 |
}
|
|
300 |
|
|
301 |
/**
|
|
302 |
* Construct a new URI from a base URI and a URI specification string.
|
|
303 |
* The URI specification string may be a relative URI.
|
|
304 |
*
|
|
305 |
* @param p_base the base URI (cannot be null if p_uriSpec is null or
|
|
306 |
* empty)
|
|
307 |
* @param p_uriSpec the URI specification string (cannot be null or
|
|
308 |
* empty if p_base is null)
|
|
309 |
*
|
|
310 |
* @exception MalformedURIException if p_uriSpec violates any syntax
|
|
311 |
* rules
|
|
312 |
*/
|
|
313 |
public URI(URI p_base, String p_uriSpec) throws MalformedURIException {
|
|
314 |
initialize(p_base, p_uriSpec);
|
|
315 |
}
|
|
316 |
|
|
317 |
/**
|
|
318 |
* Construct a new URI from a base URI and a URI specification string.
|
|
319 |
* The URI specification string may be a relative URI.
|
|
320 |
* Construct a relative URI if boolean is assigned to "true"
|
|
321 |
* and p_uriSpec is not valid absolute URI and p_base is null
|
|
322 |
* instead of throwing an exception.
|
|
323 |
*
|
|
324 |
* @param p_base the base URI (cannot be null if p_uriSpec is null or
|
|
325 |
* empty)
|
|
326 |
* @param p_uriSpec the URI specification string (cannot be null or
|
|
327 |
* empty if p_base is null)
|
|
328 |
* @param allowNonAbsoluteURI true to permit non-absolute URIs,
|
|
329 |
* false otherwise.
|
|
330 |
*
|
|
331 |
* @exception MalformedURIException if p_uriSpec violates any syntax
|
|
332 |
* rules
|
|
333 |
*/
|
|
334 |
public URI(URI p_base, String p_uriSpec, boolean allowNonAbsoluteURI) throws MalformedURIException {
|
|
335 |
initialize(p_base, p_uriSpec, allowNonAbsoluteURI);
|
|
336 |
}
|
|
337 |
|
|
338 |
/**
|
|
339 |
* Construct a new URI that does not follow the generic URI syntax.
|
|
340 |
* Only the scheme and scheme-specific part (stored as the path) are
|
|
341 |
* initialized.
|
|
342 |
*
|
|
343 |
* @param p_scheme the URI scheme (cannot be null or empty)
|
|
344 |
* @param p_schemeSpecificPart the scheme-specific part (cannot be
|
|
345 |
* null or empty)
|
|
346 |
*
|
|
347 |
* @exception MalformedURIException if p_scheme violates any
|
|
348 |
* syntax rules
|
|
349 |
*/
|
|
350 |
public URI(String p_scheme, String p_schemeSpecificPart)
|
|
351 |
throws MalformedURIException {
|
|
352 |
if (p_scheme == null || p_scheme.trim().length() == 0) {
|
|
353 |
throw new MalformedURIException(
|
|
354 |
"Cannot construct URI with null/empty scheme!");
|
|
355 |
}
|
|
356 |
if (p_schemeSpecificPart == null ||
|
|
357 |
p_schemeSpecificPart.trim().length() == 0) {
|
|
358 |
throw new MalformedURIException(
|
|
359 |
"Cannot construct URI with null/empty scheme-specific part!");
|
|
360 |
}
|
|
361 |
setScheme(p_scheme);
|
|
362 |
setPath(p_schemeSpecificPart);
|
|
363 |
}
|
|
364 |
|
|
365 |
/**
|
|
366 |
* Construct a new URI that follows the generic URI syntax from its
|
|
367 |
* component parts. Each component is validated for syntax and some
|
|
368 |
* basic semantic checks are performed as well. See the individual
|
|
369 |
* setter methods for specifics.
|
|
370 |
*
|
|
371 |
* @param p_scheme the URI scheme (cannot be null or empty)
|
|
372 |
* @param p_host the hostname, IPv4 address or IPv6 reference for the URI
|
|
373 |
* @param p_path the URI path - if the path contains '?' or '#',
|
|
374 |
* then the query string and/or fragment will be
|
|
375 |
* set from the path; however, if the query and
|
|
376 |
* fragment are specified both in the path and as
|
|
377 |
* separate parameters, an exception is thrown
|
|
378 |
* @param p_queryString the URI query string (cannot be specified
|
|
379 |
* if path is null)
|
|
380 |
* @param p_fragment the URI fragment (cannot be specified if path
|
|
381 |
* is null)
|
|
382 |
*
|
|
383 |
* @exception MalformedURIException if any of the parameters violates
|
|
384 |
* syntax rules or semantic rules
|
|
385 |
*/
|
|
386 |
public URI(String p_scheme, String p_host, String p_path,
|
|
387 |
String p_queryString, String p_fragment)
|
|
388 |
throws MalformedURIException {
|
|
389 |
this(p_scheme, null, p_host, -1, p_path, p_queryString, p_fragment);
|
|
390 |
}
|
|
391 |
|
|
392 |
/**
|
|
393 |
* Construct a new URI that follows the generic URI syntax from its
|
|
394 |
* component parts. Each component is validated for syntax and some
|
|
395 |
* basic semantic checks are performed as well. See the individual
|
|
396 |
* setter methods for specifics.
|
|
397 |
*
|
|
398 |
* @param p_scheme the URI scheme (cannot be null or empty)
|
|
399 |
* @param p_userinfo the URI userinfo (cannot be specified if host
|
|
400 |
* is null)
|
|
401 |
* @param p_host the hostname, IPv4 address or IPv6 reference for the URI
|
|
402 |
* @param p_port the URI port (may be -1 for "unspecified"; cannot
|
|
403 |
* be specified if host is null)
|
|
404 |
* @param p_path the URI path - if the path contains '?' or '#',
|
|
405 |
* then the query string and/or fragment will be
|
|
406 |
* set from the path; however, if the query and
|
|
407 |
* fragment are specified both in the path and as
|
|
408 |
* separate parameters, an exception is thrown
|
|
409 |
* @param p_queryString the URI query string (cannot be specified
|
|
410 |
* if path is null)
|
|
411 |
* @param p_fragment the URI fragment (cannot be specified if path
|
|
412 |
* is null)
|
|
413 |
*
|
|
414 |
* @exception MalformedURIException if any of the parameters violates
|
|
415 |
* syntax rules or semantic rules
|
|
416 |
*/
|
|
417 |
public URI(String p_scheme, String p_userinfo,
|
|
418 |
String p_host, int p_port, String p_path,
|
|
419 |
String p_queryString, String p_fragment)
|
|
420 |
throws MalformedURIException {
|
|
421 |
if (p_scheme == null || p_scheme.trim().length() == 0) {
|
|
422 |
throw new MalformedURIException("Scheme is required!");
|
|
423 |
}
|
|
424 |
|
|
425 |
if (p_host == null) {
|
|
426 |
if (p_userinfo != null) {
|
|
427 |
throw new MalformedURIException(
|
|
428 |
"Userinfo may not be specified if host is not specified!");
|
|
429 |
}
|
|
430 |
if (p_port != -1) {
|
|
431 |
throw new MalformedURIException(
|
|
432 |
"Port may not be specified if host is not specified!");
|
|
433 |
}
|
|
434 |
}
|
|
435 |
|
|
436 |
if (p_path != null) {
|
|
437 |
if (p_path.indexOf('?') != -1 && p_queryString != null) {
|
|
438 |
throw new MalformedURIException(
|
|
439 |
"Query string cannot be specified in path and query string!");
|
|
440 |
}
|
|
441 |
|
|
442 |
if (p_path.indexOf('#') != -1 && p_fragment != null) {
|
|
443 |
throw new MalformedURIException(
|
|
444 |
"Fragment cannot be specified in both the path and fragment!");
|
|
445 |
}
|
|
446 |
}
|
|
447 |
|
|
448 |
setScheme(p_scheme);
|
|
449 |
setHost(p_host);
|
|
450 |
setPort(p_port);
|
|
451 |
setUserinfo(p_userinfo);
|
|
452 |
setPath(p_path);
|
|
453 |
setQueryString(p_queryString);
|
|
454 |
setFragment(p_fragment);
|
|
455 |
}
|
|
456 |
|
|
457 |
/**
|
|
458 |
* Initialize all fields of this URI from another URI.
|
|
459 |
*
|
|
460 |
* @param p_other the URI to copy (cannot be null)
|
|
461 |
*/
|
|
462 |
private void initialize(URI p_other) {
|
|
463 |
m_scheme = p_other.getScheme();
|
|
464 |
m_userinfo = p_other.getUserinfo();
|
|
465 |
m_host = p_other.getHost();
|
|
466 |
m_port = p_other.getPort();
|
|
467 |
m_regAuthority = p_other.getRegBasedAuthority();
|
|
468 |
m_path = p_other.getPath();
|
|
469 |
m_queryString = p_other.getQueryString();
|
|
470 |
m_fragment = p_other.getFragment();
|
|
471 |
}
|
|
472 |
|
|
473 |
/**
|
|
474 |
* Initializes this URI from a base URI and a URI specification string.
|
|
475 |
* See RFC 2396 Section 4 and Appendix B for specifications on parsing
|
|
476 |
* the URI and Section 5 for specifications on resolving relative URIs
|
|
477 |
* and relative paths.
|
|
478 |
*
|
|
479 |
* @param p_base the base URI (may be null if p_uriSpec is an absolute
|
|
480 |
* URI)
|
|
481 |
* @param p_uriSpec the URI spec string which may be an absolute or
|
|
482 |
* relative URI (can only be null/empty if p_base
|
|
483 |
* is not null)
|
|
484 |
* @param allowNonAbsoluteURI true to permit non-absolute URIs,
|
|
485 |
* in case of relative URI, false otherwise.
|
|
486 |
*
|
|
487 |
* @exception MalformedURIException if p_base is null and p_uriSpec
|
|
488 |
* is not an absolute URI or if
|
|
489 |
* p_uriSpec violates syntax rules
|
|
490 |
*/
|
|
491 |
private void initialize(URI p_base, String p_uriSpec, boolean allowNonAbsoluteURI)
|
|
492 |
throws MalformedURIException {
|
|
493 |
|
|
494 |
String uriSpec = p_uriSpec;
|
|
495 |
int uriSpecLen = (uriSpec != null) ? uriSpec.length() : 0;
|
|
496 |
|
|
497 |
if (p_base == null && uriSpecLen == 0) {
|
|
498 |
if (allowNonAbsoluteURI) {
|
|
499 |
m_path = "";
|
|
500 |
return;
|
|
501 |
}
|
|
502 |
throw new MalformedURIException("Cannot initialize URI with empty parameters.");
|
|
503 |
}
|
|
504 |
|
|
505 |
// just make a copy of the base if spec is empty
|
|
506 |
if (uriSpecLen == 0) {
|
|
507 |
initialize(p_base);
|
|
508 |
return;
|
|
509 |
}
|
|
510 |
|
|
511 |
int index = 0;
|
|
512 |
|
|
513 |
// Check for scheme, which must be before '/', '?' or '#'.
|
|
514 |
int colonIdx = uriSpec.indexOf(':');
|
|
515 |
if (colonIdx != -1) {
|
|
516 |
final int searchFrom = colonIdx - 1;
|
|
517 |
// search backwards starting from character before ':'.
|
|
518 |
int slashIdx = uriSpec.lastIndexOf('/', searchFrom);
|
|
519 |
int queryIdx = uriSpec.lastIndexOf('?', searchFrom);
|
|
520 |
int fragmentIdx = uriSpec.lastIndexOf('#', searchFrom);
|
|
521 |
|
|
522 |
if (colonIdx == 0 || slashIdx != -1 ||
|
|
523 |
queryIdx != -1 || fragmentIdx != -1) {
|
|
524 |
// A standalone base is a valid URI according to spec
|
|
525 |
if (colonIdx == 0 || (p_base == null && fragmentIdx != 0 && !allowNonAbsoluteURI)) {
|
|
526 |
throw new MalformedURIException("No scheme found in URI.");
|
|
527 |
}
|
|
528 |
}
|
|
529 |
else {
|
|
530 |
initializeScheme(uriSpec);
|
|
531 |
index = m_scheme.length()+1;
|
|
532 |
|
|
533 |
// Neither 'scheme:' or 'scheme:#fragment' are valid URIs.
|
|
534 |
if (colonIdx == uriSpecLen - 1 || uriSpec.charAt(colonIdx+1) == '#') {
|
|
535 |
throw new MalformedURIException("Scheme specific part cannot be empty.");
|
|
536 |
}
|
|
537 |
}
|
|
538 |
}
|
|
539 |
else if (p_base == null && uriSpec.indexOf('#') != 0 && !allowNonAbsoluteURI) {
|
|
540 |
throw new MalformedURIException("No scheme found in URI.");
|
|
541 |
}
|
|
542 |
|
|
543 |
// Two slashes means we may have authority, but definitely means we're either
|
|
544 |
// matching net_path or abs_path. These two productions are ambiguous in that
|
|
545 |
// every net_path (except those containing an IPv6Reference) is an abs_path.
|
|
546 |
// RFC 2396 resolves this ambiguity by applying a greedy left most matching rule.
|
|
547 |
// Try matching net_path first, and if that fails we don't have authority so
|
|
548 |
// then attempt to match abs_path.
|
|
549 |
//
|
|
550 |
// net_path = "//" authority [ abs_path ]
|
|
551 |
// abs_path = "/" path_segments
|
|
552 |
if (((index+1) < uriSpecLen) &&
|
|
553 |
(uriSpec.charAt(index) == '/' && uriSpec.charAt(index+1) == '/')) {
|
|
554 |
index += 2;
|
|
555 |
int startPos = index;
|
|
556 |
|
|
557 |
// Authority will be everything up to path, query or fragment
|
|
558 |
char testChar = '\0';
|
|
559 |
while (index < uriSpecLen) {
|
|
560 |
testChar = uriSpec.charAt(index);
|
|
561 |
if (testChar == '/' || testChar == '?' || testChar == '#') {
|
|
562 |
break;
|
|
563 |
}
|
|
564 |
index++;
|
|
565 |
}
|
|
566 |
|
|
567 |
// Attempt to parse authority. If the section is an empty string
|
|
568 |
// this is a valid server based authority, so set the host to this
|
|
569 |
// value.
|
|
570 |
if (index > startPos) {
|
|
571 |
// If we didn't find authority we need to back up. Attempt to
|
|
572 |
// match against abs_path next.
|
|
573 |
if (!initializeAuthority(uriSpec.substring(startPos, index))) {
|
|
574 |
index = startPos - 2;
|
|
575 |
}
|
|
576 |
}
|
|
577 |
else {
|
|
578 |
m_host = "";
|
|
579 |
}
|
|
580 |
}
|
|
581 |
|
|
582 |
initializePath(uriSpec, index);
|
|
583 |
|
|
584 |
// Resolve relative URI to base URI - see RFC 2396 Section 5.2
|
|
585 |
// In some cases, it might make more sense to throw an exception
|
|
586 |
// (when scheme is specified is the string spec and the base URI
|
|
587 |
// is also specified, for example), but we're just following the
|
|
588 |
// RFC specifications
|
|
589 |
if (p_base != null) {
|
|
590 |
absolutize(p_base);
|
|
591 |
}
|
|
592 |
}
|
|
593 |
|
|
594 |
/**
|
|
595 |
* Initializes this URI from a base URI and a URI specification string.
|
|
596 |
* See RFC 2396 Section 4 and Appendix B for specifications on parsing
|
|
597 |
* the URI and Section 5 for specifications on resolving relative URIs
|
|
598 |
* and relative paths.
|
|
599 |
*
|
|
600 |
* @param p_base the base URI (may be null if p_uriSpec is an absolute
|
|
601 |
* URI)
|
|
602 |
* @param p_uriSpec the URI spec string which may be an absolute or
|
|
603 |
* relative URI (can only be null/empty if p_base
|
|
604 |
* is not null)
|
|
605 |
*
|
|
606 |
* @exception MalformedURIException if p_base is null and p_uriSpec
|
|
607 |
* is not an absolute URI or if
|
|
608 |
* p_uriSpec violates syntax rules
|
|
609 |
*/
|
|
610 |
private void initialize(URI p_base, String p_uriSpec)
|
|
611 |
throws MalformedURIException {
|
|
612 |
|
|
613 |
String uriSpec = p_uriSpec;
|
|
614 |
int uriSpecLen = (uriSpec != null) ? uriSpec.length() : 0;
|
|
615 |
|
|
616 |
if (p_base == null && uriSpecLen == 0) {
|
|
617 |
throw new MalformedURIException(
|
|
618 |
"Cannot initialize URI with empty parameters.");
|
|
619 |
}
|
|
620 |
|
|
621 |
// just make a copy of the base if spec is empty
|
|
622 |
if (uriSpecLen == 0) {
|
|
623 |
initialize(p_base);
|
|
624 |
return;
|
|
625 |
}
|
|
626 |
|
|
627 |
int index = 0;
|
|
628 |
|
|
629 |
// Check for scheme, which must be before '/', '?' or '#'.
|
|
630 |
int colonIdx = uriSpec.indexOf(':');
|
|
631 |
if (colonIdx != -1) {
|
|
632 |
final int searchFrom = colonIdx - 1;
|
|
633 |
// search backwards starting from character before ':'.
|
|
634 |
int slashIdx = uriSpec.lastIndexOf('/', searchFrom);
|
|
635 |
int queryIdx = uriSpec.lastIndexOf('?', searchFrom);
|
|
636 |
int fragmentIdx = uriSpec.lastIndexOf('#', searchFrom);
|
|
637 |
|
|
638 |
if (colonIdx == 0 || slashIdx != -1 ||
|
|
639 |
queryIdx != -1 || fragmentIdx != -1) {
|
|
640 |
// A standalone base is a valid URI according to spec
|
|
641 |
if (colonIdx == 0 || (p_base == null && fragmentIdx != 0)) {
|
|
642 |
throw new MalformedURIException("No scheme found in URI.");
|
|
643 |
}
|
|
644 |
}
|
|
645 |
else {
|
|
646 |
initializeScheme(uriSpec);
|
|
647 |
index = m_scheme.length()+1;
|
|
648 |
|
|
649 |
// Neither 'scheme:' or 'scheme:#fragment' are valid URIs.
|
|
650 |
if (colonIdx == uriSpecLen - 1 || uriSpec.charAt(colonIdx+1) == '#') {
|
|
651 |
throw new MalformedURIException("Scheme specific part cannot be empty.");
|
|
652 |
}
|
|
653 |
}
|
|
654 |
}
|
|
655 |
else if (p_base == null && uriSpec.indexOf('#') != 0) {
|
|
656 |
throw new MalformedURIException("No scheme found in URI.");
|
|
657 |
}
|
|
658 |
|
|
659 |
// Two slashes means we may have authority, but definitely means we're either
|
|
660 |
// matching net_path or abs_path. These two productions are ambiguous in that
|
|
661 |
// every net_path (except those containing an IPv6Reference) is an abs_path.
|
|
662 |
// RFC 2396 resolves this ambiguity by applying a greedy left most matching rule.
|
|
663 |
// Try matching net_path first, and if that fails we don't have authority so
|
|
664 |
// then attempt to match abs_path.
|
|
665 |
//
|
|
666 |
// net_path = "//" authority [ abs_path ]
|
|
667 |
// abs_path = "/" path_segments
|
|
668 |
if (((index+1) < uriSpecLen) &&
|
|
669 |
(uriSpec.charAt(index) == '/' && uriSpec.charAt(index+1) == '/')) {
|
|
670 |
index += 2;
|
|
671 |
int startPos = index;
|
|
672 |
|
|
673 |
// Authority will be everything up to path, query or fragment
|
|
674 |
char testChar = '\0';
|
|
675 |
while (index < uriSpecLen) {
|
|
676 |
testChar = uriSpec.charAt(index);
|
|
677 |
if (testChar == '/' || testChar == '?' || testChar == '#') {
|
|
678 |
break;
|
|
679 |
}
|
|
680 |
index++;
|
|
681 |
}
|
|
682 |
|
|
683 |
// Attempt to parse authority. If the section is an empty string
|
|
684 |
// this is a valid server based authority, so set the host to this
|
|
685 |
// value.
|
|
686 |
if (index > startPos) {
|
|
687 |
// If we didn't find authority we need to back up. Attempt to
|
|
688 |
// match against abs_path next.
|
|
689 |
if (!initializeAuthority(uriSpec.substring(startPos, index))) {
|
|
690 |
index = startPos - 2;
|
|
691 |
}
|
|
692 |
}
|
|
693 |
else {
|
|
694 |
m_host = "";
|
|
695 |
}
|
|
696 |
}
|
|
697 |
|
|
698 |
initializePath(uriSpec, index);
|
|
699 |
|
|
700 |
// Resolve relative URI to base URI - see RFC 2396 Section 5.2
|
|
701 |
// In some cases, it might make more sense to throw an exception
|
|
702 |
// (when scheme is specified is the string spec and the base URI
|
|
703 |
// is also specified, for example), but we're just following the
|
|
704 |
// RFC specifications
|
|
705 |
if (p_base != null) {
|
|
706 |
absolutize(p_base);
|
|
707 |
}
|
|
708 |
}
|
|
709 |
|
|
710 |
/**
|
|
711 |
* Absolutize URI with given base URI.
|
|
712 |
*
|
|
713 |
* @param p_base base URI for absolutization
|
|
714 |
*/
|
|
715 |
public void absolutize(URI p_base) {
|
|
716 |
|
|
717 |
// check to see if this is the current doc - RFC 2396 5.2 #2
|
|
718 |
// note that this is slightly different from the RFC spec in that
|
|
719 |
// we don't include the check for query string being null
|
|
720 |
// - this handles cases where the urispec is just a query
|
|
721 |
// string or a fragment (e.g. "?y" or "#s") -
|
|
722 |
// see <http://www.ics.uci.edu/~fielding/url/test1.html> which
|
|
723 |
// identified this as a bug in the RFC
|
|
724 |
if (m_path.length() == 0 && m_scheme == null &&
|
|
725 |
m_host == null && m_regAuthority == null) {
|
|
726 |
m_scheme = p_base.getScheme();
|
|
727 |
m_userinfo = p_base.getUserinfo();
|
|
728 |
m_host = p_base.getHost();
|
|
729 |
m_port = p_base.getPort();
|
|
730 |
m_regAuthority = p_base.getRegBasedAuthority();
|
|
731 |
m_path = p_base.getPath();
|
|
732 |
|
|
733 |
if (m_queryString == null) {
|
|
734 |
m_queryString = p_base.getQueryString();
|
|
735 |
|
|
736 |
if (m_fragment == null) {
|
|
737 |
m_fragment = p_base.getFragment();
|
|
738 |
}
|
|
739 |
}
|
|
740 |
return;
|
|
741 |
}
|
|
742 |
|
|
743 |
// check for scheme - RFC 2396 5.2 #3
|
|
744 |
// if we found a scheme, it means absolute URI, so we're done
|
|
745 |
if (m_scheme == null) {
|
|
746 |
m_scheme = p_base.getScheme();
|
|
747 |
}
|
|
748 |
else {
|
|
749 |
return;
|
|
750 |
}
|
|
751 |
|
|
752 |
// check for authority - RFC 2396 5.2 #4
|
|
753 |
// if we found a host, then we've got a network path, so we're done
|
|
754 |
if (m_host == null && m_regAuthority == null) {
|
|
755 |
m_userinfo = p_base.getUserinfo();
|
|
756 |
m_host = p_base.getHost();
|
|
757 |
m_port = p_base.getPort();
|
|
758 |
m_regAuthority = p_base.getRegBasedAuthority();
|
|
759 |
}
|
|
760 |
else {
|
|
761 |
return;
|
|
762 |
}
|
|
763 |
|
|
764 |
// check for absolute path - RFC 2396 5.2 #5
|
|
765 |
if (m_path.length() > 0 &&
|
|
766 |
m_path.startsWith("/")) {
|
|
767 |
return;
|
|
768 |
}
|
|
769 |
|
|
770 |
// if we get to this point, we need to resolve relative path
|
|
771 |
// RFC 2396 5.2 #6
|
|
772 |
String path = "";
|
|
773 |
String basePath = p_base.getPath();
|
|
774 |
|
|
775 |
// 6a - get all but the last segment of the base URI path
|
|
776 |
if (basePath != null && basePath.length() > 0) {
|
|
777 |
int lastSlash = basePath.lastIndexOf('/');
|
|
778 |
if (lastSlash != -1) {
|
|
779 |
path = basePath.substring(0, lastSlash+1);
|
|
780 |
}
|
|
781 |
}
|
|
782 |
else if (m_path.length() > 0) {
|
|
783 |
path = "/";
|
|
784 |
}
|
|
785 |
|
|
786 |
// 6b - append the relative URI path
|
|
787 |
path = path.concat(m_path);
|
|
788 |
|
|
789 |
// 6c - remove all "./" where "." is a complete path segment
|
|
790 |
int index = -1;
|
|
791 |
while ((index = path.indexOf("/./")) != -1) {
|
|
792 |
path = path.substring(0, index+1).concat(path.substring(index+3));
|
|
793 |
}
|
|
794 |
|
|
795 |
// 6d - remove "." if path ends with "." as a complete path segment
|
|
796 |
if (path.endsWith("/.")) {
|
|
797 |
path = path.substring(0, path.length()-1);
|
|
798 |
}
|
|
799 |
|
|
800 |
// 6e - remove all "<segment>/../" where "<segment>" is a complete
|
|
801 |
// path segment not equal to ".."
|
|
802 |
index = 1;
|
|
803 |
int segIndex = -1;
|
|
804 |
String tempString = null;
|
|
805 |
|
|
806 |
while ((index = path.indexOf("/../", index)) > 0) {
|
|
807 |
tempString = path.substring(0, path.indexOf("/../"));
|
|
808 |
segIndex = tempString.lastIndexOf('/');
|
|
809 |
if (segIndex != -1) {
|
|
810 |
if (!tempString.substring(segIndex).equals("..")) {
|
|
811 |
path = path.substring(0, segIndex+1).concat(path.substring(index+4));
|
|
812 |
index = segIndex;
|
|
813 |
}
|
|
814 |
else {
|
|
815 |
index += 4;
|
|
816 |
}
|
|
817 |
}
|
|
818 |
else {
|
|
819 |
index += 4;
|
|
820 |
}
|
|
821 |
}
|
|
822 |
|
|
823 |
// 6f - remove ending "<segment>/.." where "<segment>" is a
|
|
824 |
// complete path segment
|
|
825 |
if (path.endsWith("/..")) {
|
|
826 |
tempString = path.substring(0, path.length()-3);
|
|
827 |
segIndex = tempString.lastIndexOf('/');
|
|
828 |
if (segIndex != -1) {
|
|
829 |
path = path.substring(0, segIndex+1);
|
|
830 |
}
|
|
831 |
}
|
|
832 |
m_path = path;
|
|
833 |
}
|
|
834 |
|
|
835 |
/**
|
|
836 |
* Initialize the scheme for this URI from a URI string spec.
|
|
837 |
*
|
|
838 |
* @param p_uriSpec the URI specification (cannot be null)
|
|
839 |
*
|
|
840 |
* @exception MalformedURIException if URI does not have a conformant
|
|
841 |
* scheme
|
|
842 |
*/
|
|
843 |
private void initializeScheme(String p_uriSpec)
|
|
844 |
throws MalformedURIException {
|
|
845 |
int uriSpecLen = p_uriSpec.length();
|
|
846 |
int index = 0;
|
|
847 |
String scheme = null;
|
|
848 |
char testChar = '\0';
|
|
849 |
|
|
850 |
while (index < uriSpecLen) {
|
|
851 |
testChar = p_uriSpec.charAt(index);
|
|
852 |
if (testChar == ':' || testChar == '/' ||
|
|
853 |
testChar == '?' || testChar == '#') {
|
|
854 |
break;
|
|
855 |
}
|
|
856 |
index++;
|
|
857 |
}
|
|
858 |
scheme = p_uriSpec.substring(0, index);
|
|
859 |
|
|
860 |
if (scheme.length() == 0) {
|
|
861 |
throw new MalformedURIException("No scheme found in URI.");
|
|
862 |
}
|
|
863 |
else {
|
|
864 |
setScheme(scheme);
|
|
865 |
}
|
|
866 |
}
|
|
867 |
|
|
868 |
/**
|
|
869 |
* Initialize the authority (either server or registry based)
|
|
870 |
* for this URI from a URI string spec.
|
|
871 |
*
|
|
872 |
* @param p_uriSpec the URI specification (cannot be null)
|
|
873 |
*
|
|
874 |
* @return true if the given string matched server or registry
|
|
875 |
* based authority
|
|
876 |
*/
|
|
877 |
private boolean initializeAuthority(String p_uriSpec) {
|
|
878 |
|
|
879 |
int index = 0;
|
|
880 |
int start = 0;
|
|
881 |
int end = p_uriSpec.length();
|
|
882 |
|
|
883 |
char testChar = '\0';
|
|
884 |
String userinfo = null;
|
|
885 |
|
|
886 |
// userinfo is everything up to @
|
|
887 |
if (p_uriSpec.indexOf('@', start) != -1) {
|
|
888 |
while (index < end) {
|
|
889 |
testChar = p_uriSpec.charAt(index);
|
|
890 |
if (testChar == '@') {
|
|
891 |
break;
|
|
892 |
}
|
|
893 |
index++;
|
|
894 |
}
|
|
895 |
userinfo = p_uriSpec.substring(start, index);
|
|
896 |
index++;
|
|
897 |
}
|
|
898 |
|
|
899 |
// host is everything up to last ':', or up to
|
|
900 |
// and including ']' if followed by ':'.
|
|
901 |
String host = null;
|
|
902 |
start = index;
|
|
903 |
boolean hasPort = false;
|
|
904 |
if (index < end) {
|
|
905 |
if (p_uriSpec.charAt(start) == '[') {
|
|
906 |
int bracketIndex = p_uriSpec.indexOf(']', start);
|
|
907 |
index = (bracketIndex != -1) ? bracketIndex : end;
|
|
908 |
if (index+1 < end && p_uriSpec.charAt(index+1) == ':') {
|
|
909 |
++index;
|
|
910 |
hasPort = true;
|
|
911 |
}
|
|
912 |
else {
|
|
913 |
index = end;
|
|
914 |
}
|
|
915 |
}
|
|
916 |
else {
|
|
917 |
int colonIndex = p_uriSpec.lastIndexOf(':', end);
|
|
918 |
index = (colonIndex > start) ? colonIndex : end;
|
|
919 |
hasPort = (index != end);
|
|
920 |
}
|
|
921 |
}
|
|
922 |
host = p_uriSpec.substring(start, index);
|
|
923 |
int port = -1;
|
|
924 |
if (host.length() > 0) {
|
|
925 |
// port
|
|
926 |
if (hasPort) {
|
|
927 |
index++;
|
|
928 |
start = index;
|
|
929 |
while (index < end) {
|
|
930 |
index++;
|
|
931 |
}
|
|
932 |
String portStr = p_uriSpec.substring(start, index);
|
|
933 |
if (portStr.length() > 0) {
|
|
934 |
// REVISIT: Remove this code.
|
|
935 |
/** for (int i = 0; i < portStr.length(); i++) {
|
|
936 |
if (!isDigit(portStr.charAt(i))) {
|
|
937 |
throw new MalformedURIException(
|
|
938 |
portStr +
|
|
939 |
" is invalid. Port should only contain digits!");
|
|
940 |
}
|
|
941 |
}**/
|
|
942 |
// REVISIT: Remove this code.
|
|
943 |
// Store port value as string instead of integer.
|
|
944 |
try {
|
|
945 |
port = Integer.parseInt(portStr);
|
|
946 |
if (port == -1) --port;
|
|
947 |
}
|
|
948 |
catch (NumberFormatException nfe) {
|
|
949 |
port = -2;
|
|
950 |
}
|
|
951 |
}
|
|
952 |
}
|
|
953 |
}
|
|
954 |
|
|
955 |
if (isValidServerBasedAuthority(host, port, userinfo)) {
|
|
956 |
m_host = host;
|
|
957 |
m_port = port;
|
|
958 |
m_userinfo = userinfo;
|
|
959 |
return true;
|
|
960 |
}
|
|
961 |
// Note: Registry based authority is being removed from a
|
|
962 |
// new spec for URI which would obsolete RFC 2396. If the
|
|
963 |
// spec is added to XML errata, processing of reg_name
|
|
964 |
// needs to be removed. - mrglavas.
|
|
965 |
else if (isValidRegistryBasedAuthority(p_uriSpec)) {
|
|
966 |
m_regAuthority = p_uriSpec;
|
|
967 |
return true;
|
|
968 |
}
|
|
969 |
return false;
|
|
970 |
}
|
|
971 |
|
|
972 |
/**
|
|
973 |
* Determines whether the components host, port, and user info
|
|
974 |
* are valid as a server authority.
|
|
975 |
*
|
|
976 |
* @param host the host component of authority
|
|
977 |
* @param port the port number component of authority
|
|
978 |
* @param userinfo the user info component of authority
|
|
979 |
*
|
|
980 |
* @return true if the given host, port, and userinfo compose
|
|
981 |
* a valid server authority
|
|
982 |
*/
|
|
983 |
private boolean isValidServerBasedAuthority(String host, int port, String userinfo) {
|
|
984 |
|
|
985 |
// Check if the host is well formed.
|
|
986 |
if (!isWellFormedAddress(host)) {
|
|
987 |
return false;
|
|
988 |
}
|
|
989 |
|
|
990 |
// Check that port is well formed if it exists.
|
|
991 |
// REVISIT: There's no restriction on port value ranges, but
|
|
992 |
// perform the same check as in setPort to be consistent. Pass
|
|
993 |
// in a string to this method instead of an integer.
|
|
994 |
if (port < -1 || port > 65535) {
|
|
995 |
return false;
|
|
996 |
}
|
|
997 |
|
|
998 |
// Check that userinfo is well formed if it exists.
|
|
999 |
if (userinfo != null) {
|
|
1000 |
// Userinfo can contain alphanumerics, mark characters, escaped
|
|
1001 |
// and ';',':','&','=','+','$',','
|
|
1002 |
int index = 0;
|
|
1003 |
int end = userinfo.length();
|
|
1004 |
char testChar = '\0';
|
|
1005 |
while (index < end) {
|
|
1006 |
testChar = userinfo.charAt(index);
|
|
1007 |
if (testChar == '%') {
|
|
1008 |
if (index+2 >= end ||
|
|
1009 |
!isHex(userinfo.charAt(index+1)) ||
|
|
1010 |
!isHex(userinfo.charAt(index+2))) {
|
|
1011 |
return false;
|
|
1012 |
}
|
|
1013 |
index += 2;
|
|
1014 |
}
|
|
1015 |
else if (!isUserinfoCharacter(testChar)) {
|
|
1016 |
return false;
|
|
1017 |
}
|
|
1018 |
++index;
|
|
1019 |
}
|
|
1020 |
}
|
|
1021 |
return true;
|
|
1022 |
}
|
|
1023 |
|
|
1024 |
/**
|
|
1025 |
* Determines whether the given string is a registry based authority.
|
|
1026 |
*
|
|
1027 |
* @param authority the authority component of a URI
|
|
1028 |
*
|
|
1029 |
* @return true if the given string is a registry based authority
|
|
1030 |
*/
|
|
1031 |
private boolean isValidRegistryBasedAuthority(String authority) {
|
|
1032 |
int index = 0;
|
|
1033 |
int end = authority.length();
|
|
1034 |
char testChar;
|
|
1035 |
|
|
1036 |
while (index < end) {
|
|
1037 |
testChar = authority.charAt(index);
|
|
1038 |
|
|
1039 |
// check for valid escape sequence
|
|
1040 |
if (testChar == '%') {
|
|
1041 |
if (index+2 >= end ||
|
|
1042 |
!isHex(authority.charAt(index+1)) ||
|
|
1043 |
!isHex(authority.charAt(index+2))) {
|
|
1044 |
return false;
|
|
1045 |
}
|
|
1046 |
index += 2;
|
|
1047 |
}
|
|
1048 |
// can check against path characters because the set
|
|
1049 |
// is the same except for '/' which we've already excluded.
|
|
1050 |
else if (!isPathCharacter(testChar)) {
|
|
1051 |
return false;
|
|
1052 |
}
|
|
1053 |
++index;
|
|
1054 |
}
|
|
1055 |
return true;
|
|
1056 |
}
|
|
1057 |
|
|
1058 |
/**
|
|
1059 |
* Initialize the path for this URI from a URI string spec.
|
|
1060 |
*
|
|
1061 |
* @param p_uriSpec the URI specification (cannot be null)
|
|
1062 |
* @param p_nStartIndex the index to begin scanning from
|
|
1063 |
*
|
|
1064 |
* @exception MalformedURIException if p_uriSpec violates syntax rules
|
|
1065 |
*/
|
|
1066 |
private void initializePath(String p_uriSpec, int p_nStartIndex)
|
|
1067 |
throws MalformedURIException {
|
|
1068 |
if (p_uriSpec == null) {
|
|
1069 |
throw new MalformedURIException(
|
|
1070 |
"Cannot initialize path from null string!");
|
|
1071 |
}
|
|
1072 |
|
|
1073 |
int index = p_nStartIndex;
|
|
1074 |
int start = p_nStartIndex;
|
|
1075 |
int end = p_uriSpec.length();
|
|
1076 |
char testChar = '\0';
|
|
1077 |
|
|
1078 |
// path - everything up to query string or fragment
|
|
1079 |
if (start < end) {
|
|
1080 |
// RFC 2732 only allows '[' and ']' to appear in the opaque part.
|
|
1081 |
if (getScheme() == null || p_uriSpec.charAt(start) == '/') {
|
|
1082 |
|
|
1083 |
// Scan path.
|
|
1084 |
// abs_path = "/" path_segments
|
|
1085 |
// rel_path = rel_segment [ abs_path ]
|
|
1086 |
while (index < end) {
|
|
1087 |
testChar = p_uriSpec.charAt(index);
|
|
1088 |
|
|
1089 |
// check for valid escape sequence
|
|
1090 |
if (testChar == '%') {
|
|
1091 |
if (index+2 >= end ||
|
|
1092 |
!isHex(p_uriSpec.charAt(index+1)) ||
|
|
1093 |
!isHex(p_uriSpec.charAt(index+2))) {
|
|
1094 |
throw new MalformedURIException(
|
|
1095 |
"Path contains invalid escape sequence!");
|
|
1096 |
}
|
|
1097 |
index += 2;
|
|
1098 |
}
|
|
1099 |
// Path segments cannot contain '[' or ']' since pchar
|
|
1100 |
// production was not changed by RFC 2732.
|
|
1101 |
else if (!isPathCharacter(testChar)) {
|
|
1102 |
if (testChar == '?' || testChar == '#') {
|
|
1103 |
break;
|
|
1104 |
}
|
|
1105 |
throw new MalformedURIException(
|
|
1106 |
"Path contains invalid character: " + testChar);
|
|
1107 |
}
|
|
1108 |
++index;
|
|
1109 |
}
|
|
1110 |
}
|
|
1111 |
else {
|
|
1112 |
|
|
1113 |
// Scan opaque part.
|
|
1114 |
// opaque_part = uric_no_slash *uric
|
|
1115 |
while (index < end) {
|
|
1116 |
testChar = p_uriSpec.charAt(index);
|
|
1117 |
|
|
1118 |
if (testChar == '?' || testChar == '#') {
|
|
1119 |
break;
|
|
1120 |
}
|
|
1121 |
|
|
1122 |
// check for valid escape sequence
|
|
1123 |
if (testChar == '%') {
|
|
1124 |
if (index+2 >= end ||
|
|
1125 |
!isHex(p_uriSpec.charAt(index+1)) ||
|
|
1126 |
!isHex(p_uriSpec.charAt(index+2))) {
|
|
1127 |
throw new MalformedURIException(
|
|
1128 |
"Opaque part contains invalid escape sequence!");
|
|
1129 |
}
|
|
1130 |
index += 2;
|
|
1131 |
}
|
|
1132 |
// If the scheme specific part is opaque, it can contain '['
|
|
1133 |
// and ']'. uric_no_slash wasn't modified by RFC 2732, which
|
|
1134 |
// I've interpreted as an error in the spec, since the
|
|
1135 |
// production should be equivalent to (uric - '/'), and uric
|
|
1136 |
// contains '[' and ']'. - mrglavas
|
|
1137 |
else if (!isURICharacter(testChar)) {
|
|
1138 |
throw new MalformedURIException(
|
|
1139 |
"Opaque part contains invalid character: " + testChar);
|
|
1140 |
}
|
|
1141 |
++index;
|
|
1142 |
}
|
|
1143 |
}
|
|
1144 |
}
|
|
1145 |
m_path = p_uriSpec.substring(start, index);
|
|
1146 |
|
|
1147 |
// query - starts with ? and up to fragment or end
|
|
1148 |
if (testChar == '?') {
|
|
1149 |
index++;
|
|
1150 |
start = index;
|
|
1151 |
while (index < end) {
|
|
1152 |
testChar = p_uriSpec.charAt(index);
|
|
1153 |
if (testChar == '#') {
|
|
1154 |
break;
|
|
1155 |
}
|
|
1156 |
if (testChar == '%') {
|
|
1157 |
if (index+2 >= end ||
|
|
1158 |
!isHex(p_uriSpec.charAt(index+1)) ||
|
|
1159 |
!isHex(p_uriSpec.charAt(index+2))) {
|
|
1160 |
throw new MalformedURIException(
|
|
1161 |
"Query string contains invalid escape sequence!");
|
|
1162 |
}
|
|
1163 |
index += 2;
|
|
1164 |
}
|
|
1165 |
else if (!isURICharacter(testChar)) {
|
|
1166 |
throw new MalformedURIException(
|
|
1167 |
"Query string contains invalid character: " + testChar);
|
|
1168 |
}
|
|
1169 |
index++;
|
|
1170 |
}
|
|
1171 |
m_queryString = p_uriSpec.substring(start, index);
|
|
1172 |
}
|
|
1173 |
|
|
1174 |
// fragment - starts with #
|
|
1175 |
if (testChar == '#') {
|
|
1176 |
index++;
|
|
1177 |
start = index;
|
|
1178 |
while (index < end) {
|
|
1179 |
testChar = p_uriSpec.charAt(index);
|
|
1180 |
|
|
1181 |
if (testChar == '%') {
|
|
1182 |
if (index+2 >= end ||
|
|
1183 |
!isHex(p_uriSpec.charAt(index+1)) ||
|
|
1184 |
!isHex(p_uriSpec.charAt(index+2))) {
|
|
1185 |
throw new MalformedURIException(
|
|
1186 |
"Fragment contains invalid escape sequence!");
|
|
1187 |
}
|
|
1188 |
index += 2;
|
|
1189 |
}
|
|
1190 |
else if (!isURICharacter(testChar)) {
|
|
1191 |
throw new MalformedURIException(
|
|
1192 |
"Fragment contains invalid character: "+testChar);
|
|
1193 |
}
|
|
1194 |
index++;
|
|
1195 |
}
|
|
1196 |
m_fragment = p_uriSpec.substring(start, index);
|
|
1197 |
}
|
|
1198 |
}
|
|
1199 |
|
|
1200 |
/**
|
|
1201 |
* Get the scheme for this URI.
|
|
1202 |
*
|
|
1203 |
* @return the scheme for this URI
|
|
1204 |
*/
|
|
1205 |
public String getScheme() {
|
|
1206 |
return m_scheme;
|
|
1207 |
}
|
|
1208 |
|
|
1209 |
/**
|
|
1210 |
* Get the scheme-specific part for this URI (everything following the
|
|
1211 |
* scheme and the first colon). See RFC 2396 Section 5.2 for spec.
|
|
1212 |
*
|
|
1213 |
* @return the scheme-specific part for this URI
|
|
1214 |
*/
|
|
1215 |
public String getSchemeSpecificPart() {
|
17538
|
1216 |
final StringBuilder schemespec = new StringBuilder();
|
6
|
1217 |
|
|
1218 |
if (m_host != null || m_regAuthority != null) {
|
|
1219 |
schemespec.append("//");
|
|
1220 |
|
|
1221 |
// Server based authority.
|
|
1222 |
if (m_host != null) {
|
|
1223 |
|
|
1224 |
if (m_userinfo != null) {
|
|
1225 |
schemespec.append(m_userinfo);
|
|
1226 |
schemespec.append('@');
|
|
1227 |
}
|
|
1228 |
|
|
1229 |
schemespec.append(m_host);
|
|
1230 |
|
|
1231 |
if (m_port != -1) {
|
|
1232 |
schemespec.append(':');
|
|
1233 |
schemespec.append(m_port);
|
|
1234 |
}
|
|
1235 |
}
|
|
1236 |
// Registry based authority.
|
|
1237 |
else {
|
|
1238 |
schemespec.append(m_regAuthority);
|
|
1239 |
}
|
|
1240 |
}
|
|
1241 |
|
|
1242 |
if (m_path != null) {
|
|
1243 |
schemespec.append((m_path));
|
|
1244 |
}
|
|
1245 |
|
|
1246 |
if (m_queryString != null) {
|
|
1247 |
schemespec.append('?');
|
|
1248 |
schemespec.append(m_queryString);
|
|
1249 |
}
|
|
1250 |
|
|
1251 |
if (m_fragment != null) {
|
|
1252 |
schemespec.append('#');
|
|
1253 |
schemespec.append(m_fragment);
|
|
1254 |
}
|
|
1255 |
|
|
1256 |
return schemespec.toString();
|
|
1257 |
}
|
|
1258 |
|
|
1259 |
/**
|
|
1260 |
* Get the userinfo for this URI.
|
|
1261 |
*
|
|
1262 |
* @return the userinfo for this URI (null if not specified).
|
|
1263 |
*/
|
|
1264 |
public String getUserinfo() {
|
|
1265 |
return m_userinfo;
|
|
1266 |
}
|
|
1267 |
|
|
1268 |
/**
|
|
1269 |
* Get the host for this URI.
|
|
1270 |
*
|
|
1271 |
* @return the host for this URI (null if not specified).
|
|
1272 |
*/
|
|
1273 |
public String getHost() {
|
|
1274 |
return m_host;
|
|
1275 |
}
|
|
1276 |
|
|
1277 |
/**
|
|
1278 |
* Get the port for this URI.
|
|
1279 |
*
|
|
1280 |
* @return the port for this URI (-1 if not specified).
|
|
1281 |
*/
|
|
1282 |
public int getPort() {
|
|
1283 |
return m_port;
|
|
1284 |
}
|
|
1285 |
|
|
1286 |
/**
|
|
1287 |
* Get the registry based authority for this URI.
|
|
1288 |
*
|
|
1289 |
* @return the registry based authority (null if not specified).
|
|
1290 |
*/
|
|
1291 |
public String getRegBasedAuthority() {
|
|
1292 |
return m_regAuthority;
|
|
1293 |
}
|
|
1294 |
|
|
1295 |
/**
|
|
1296 |
* Get the authority for this URI.
|
|
1297 |
*
|
|
1298 |
* @return the authority
|
|
1299 |
*/
|
|
1300 |
public String getAuthority() {
|
17538
|
1301 |
final StringBuilder authority = new StringBuilder();
|
6
|
1302 |
if (m_host != null || m_regAuthority != null) {
|
|
1303 |
authority.append("//");
|
|
1304 |
|
|
1305 |
// Server based authority.
|
|
1306 |
if (m_host != null) {
|
|
1307 |
|
|
1308 |
if (m_userinfo != null) {
|
|
1309 |
authority.append(m_userinfo);
|
|
1310 |
authority.append('@');
|
|
1311 |
}
|
|
1312 |
|
|
1313 |
authority.append(m_host);
|
|
1314 |
|
|
1315 |
if (m_port != -1) {
|
|
1316 |
authority.append(':');
|
|
1317 |
authority.append(m_port);
|
|
1318 |
}
|
|
1319 |
}
|
|
1320 |
// Registry based authority.
|
|
1321 |
else {
|
|
1322 |
authority.append(m_regAuthority);
|
|
1323 |
}
|
|
1324 |
}
|
|
1325 |
return authority.toString();
|
|
1326 |
}
|
|
1327 |
|
|
1328 |
/**
|
|
1329 |
* Get the path for this URI (optionally with the query string and
|
|
1330 |
* fragment).
|
|
1331 |
*
|
|
1332 |
* @param p_includeQueryString if true (and query string is not null),
|
|
1333 |
* then a "?" followed by the query string
|
|
1334 |
* will be appended
|
|
1335 |
* @param p_includeFragment if true (and fragment is not null),
|
|
1336 |
* then a "#" followed by the fragment
|
|
1337 |
* will be appended
|
|
1338 |
*
|
|
1339 |
* @return the path for this URI possibly including the query string
|
|
1340 |
* and fragment
|
|
1341 |
*/
|
|
1342 |
public String getPath(boolean p_includeQueryString,
|
|
1343 |
boolean p_includeFragment) {
|
17538
|
1344 |
final StringBuilder pathString = new StringBuilder(m_path);
|
6
|
1345 |
|
|
1346 |
if (p_includeQueryString && m_queryString != null) {
|
|
1347 |
pathString.append('?');
|
|
1348 |
pathString.append(m_queryString);
|
|
1349 |
}
|
|
1350 |
|
|
1351 |
if (p_includeFragment && m_fragment != null) {
|
|
1352 |
pathString.append('#');
|
|
1353 |
pathString.append(m_fragment);
|
|
1354 |
}
|
|
1355 |
return pathString.toString();
|
|
1356 |
}
|
|
1357 |
|
|
1358 |
/**
|
|
1359 |
* Get the path for this URI. Note that the value returned is the path
|
|
1360 |
* only and does not include the query string or fragment.
|
|
1361 |
*
|
|
1362 |
* @return the path for this URI.
|
|
1363 |
*/
|
|
1364 |
public String getPath() {
|
|
1365 |
return m_path;
|
|
1366 |
}
|
|
1367 |
|
|
1368 |
/**
|
|
1369 |
* Get the query string for this URI.
|
|
1370 |
*
|
|
1371 |
* @return the query string for this URI. Null is returned if there
|
|
1372 |
* was no "?" in the URI spec, empty string if there was a
|
|
1373 |
* "?" but no query string following it.
|
|
1374 |
*/
|
|
1375 |
public String getQueryString() {
|
|
1376 |
return m_queryString;
|
|
1377 |
}
|
|
1378 |
|
|
1379 |
/**
|
|
1380 |
* Get the fragment for this URI.
|
|
1381 |
*
|
|
1382 |
* @return the fragment for this URI. Null is returned if there
|
|
1383 |
* was no "#" in the URI spec, empty string if there was a
|
|
1384 |
* "#" but no fragment following it.
|
|
1385 |
*/
|
|
1386 |
public String getFragment() {
|
|
1387 |
return m_fragment;
|
|
1388 |
}
|
|
1389 |
|
|
1390 |
/**
|
|
1391 |
* Set the scheme for this URI. The scheme is converted to lowercase
|
|
1392 |
* before it is set.
|
|
1393 |
*
|
|
1394 |
* @param p_scheme the scheme for this URI (cannot be null)
|
|
1395 |
*
|
|
1396 |
* @exception MalformedURIException if p_scheme is not a conformant
|
|
1397 |
* scheme name
|
|
1398 |
*/
|
|
1399 |
public void setScheme(String p_scheme) throws MalformedURIException {
|
|
1400 |
if (p_scheme == null) {
|
|
1401 |
throw new MalformedURIException(
|
|
1402 |
"Cannot set scheme from null string!");
|
|
1403 |
}
|
|
1404 |
if (!isConformantSchemeName(p_scheme)) {
|
|
1405 |
throw new MalformedURIException("The scheme is not conformant.");
|
|
1406 |
}
|
|
1407 |
|
|
1408 |
m_scheme = p_scheme.toLowerCase();
|
|
1409 |
}
|
|
1410 |
|
|
1411 |
/**
|
|
1412 |
* Set the userinfo for this URI. If a non-null value is passed in and
|
|
1413 |
* the host value is null, then an exception is thrown.
|
|
1414 |
*
|
|
1415 |
* @param p_userinfo the userinfo for this URI
|
|
1416 |
*
|
|
1417 |
* @exception MalformedURIException if p_userinfo contains invalid
|
|
1418 |
* characters
|
|
1419 |
*/
|
|
1420 |
public void setUserinfo(String p_userinfo) throws MalformedURIException {
|
|
1421 |
if (p_userinfo == null) {
|
|
1422 |
m_userinfo = null;
|
|
1423 |
return;
|
|
1424 |
}
|
|
1425 |
else {
|
|
1426 |
if (m_host == null) {
|
|
1427 |
throw new MalformedURIException(
|
|
1428 |
"Userinfo cannot be set when host is null!");
|
|
1429 |
}
|
|
1430 |
|
|
1431 |
// userinfo can contain alphanumerics, mark characters, escaped
|
|
1432 |
// and ';',':','&','=','+','$',','
|
|
1433 |
int index = 0;
|
|
1434 |
int end = p_userinfo.length();
|
|
1435 |
char testChar = '\0';
|
|
1436 |
while (index < end) {
|
|
1437 |
testChar = p_userinfo.charAt(index);
|
|
1438 |
if (testChar == '%') {
|
|
1439 |
if (index+2 >= end ||
|
|
1440 |
!isHex(p_userinfo.charAt(index+1)) ||
|
|
1441 |
!isHex(p_userinfo.charAt(index+2))) {
|
|
1442 |
throw new MalformedURIException(
|
|
1443 |
"Userinfo contains invalid escape sequence!");
|
|
1444 |
}
|
|
1445 |
}
|
|
1446 |
else if (!isUserinfoCharacter(testChar)) {
|
|
1447 |
throw new MalformedURIException(
|
|
1448 |
"Userinfo contains invalid character:"+testChar);
|
|
1449 |
}
|
|
1450 |
index++;
|
|
1451 |
}
|
|
1452 |
}
|
|
1453 |
m_userinfo = p_userinfo;
|
|
1454 |
}
|
|
1455 |
|
|
1456 |
/**
|
|
1457 |
* <p>Set the host for this URI. If null is passed in, the userinfo
|
|
1458 |
* field is also set to null and the port is set to -1.</p>
|
|
1459 |
*
|
|
1460 |
* <p>Note: This method overwrites registry based authority if it
|
|
1461 |
* previously existed in this URI.</p>
|
|
1462 |
*
|
|
1463 |
* @param p_host the host for this URI
|
|
1464 |
*
|
|
1465 |
* @exception MalformedURIException if p_host is not a valid IP
|
|
1466 |
* address or DNS hostname.
|
|
1467 |
*/
|
|
1468 |
public void setHost(String p_host) throws MalformedURIException {
|
|
1469 |
if (p_host == null || p_host.length() == 0) {
|
|
1470 |
if (p_host != null) {
|
|
1471 |
m_regAuthority = null;
|
|
1472 |
}
|
|
1473 |
m_host = p_host;
|
|
1474 |
m_userinfo = null;
|
|
1475 |
m_port = -1;
|
|
1476 |
return;
|
|
1477 |
}
|
|
1478 |
else if (!isWellFormedAddress(p_host)) {
|
|
1479 |
throw new MalformedURIException("Host is not a well formed address!");
|
|
1480 |
}
|
|
1481 |
m_host = p_host;
|
|
1482 |
m_regAuthority = null;
|
|
1483 |
}
|
|
1484 |
|
|
1485 |
/**
|
|
1486 |
* Set the port for this URI. -1 is used to indicate that the port is
|
|
1487 |
* not specified, otherwise valid port numbers are between 0 and 65535.
|
|
1488 |
* If a valid port number is passed in and the host field is null,
|
|
1489 |
* an exception is thrown.
|
|
1490 |
*
|
|
1491 |
* @param p_port the port number for this URI
|
|
1492 |
*
|
|
1493 |
* @exception MalformedURIException if p_port is not -1 and not a
|
|
1494 |
* valid port number
|
|
1495 |
*/
|
|
1496 |
public void setPort(int p_port) throws MalformedURIException {
|
|
1497 |
if (p_port >= 0 && p_port <= 65535) {
|
|
1498 |
if (m_host == null) {
|
|
1499 |
throw new MalformedURIException(
|
|
1500 |
"Port cannot be set when host is null!");
|
|
1501 |
}
|
|
1502 |
}
|
|
1503 |
else if (p_port != -1) {
|
|
1504 |
throw new MalformedURIException("Invalid port number!");
|
|
1505 |
}
|
|
1506 |
m_port = p_port;
|
|
1507 |
}
|
|
1508 |
|
|
1509 |
/**
|
|
1510 |
* <p>Sets the registry based authority for this URI.</p>
|
|
1511 |
*
|
|
1512 |
* <p>Note: This method overwrites server based authority
|
|
1513 |
* if it previously existed in this URI.</p>
|
|
1514 |
*
|
|
1515 |
* @param authority the registry based authority for this URI
|
|
1516 |
*
|
|
1517 |
* @exception MalformedURIException it authority is not a
|
|
1518 |
* well formed registry based authority
|
|
1519 |
*/
|
|
1520 |
public void setRegBasedAuthority(String authority)
|
|
1521 |
throws MalformedURIException {
|
|
1522 |
|
|
1523 |
if (authority == null) {
|
|
1524 |
m_regAuthority = null;
|
|
1525 |
return;
|
|
1526 |
}
|
|
1527 |
// reg_name = 1*( unreserved | escaped | "$" | "," |
|
|
1528 |
// ";" | ":" | "@" | "&" | "=" | "+" )
|
|
1529 |
else if (authority.length() < 1 ||
|
|
1530 |
!isValidRegistryBasedAuthority(authority) ||
|
|
1531 |
authority.indexOf('/') != -1) {
|
|
1532 |
throw new MalformedURIException("Registry based authority is not well formed.");
|
|
1533 |
}
|
|
1534 |
m_regAuthority = authority;
|
|
1535 |
m_host = null;
|
|
1536 |
m_userinfo = null;
|
|
1537 |
m_port = -1;
|
|
1538 |
}
|
|
1539 |
|
|
1540 |
/**
|
|
1541 |
* Set the path for this URI. If the supplied path is null, then the
|
|
1542 |
* query string and fragment are set to null as well. If the supplied
|
|
1543 |
* path includes a query string and/or fragment, these fields will be
|
|
1544 |
* parsed and set as well. Note that, for URIs following the "generic
|
|
1545 |
* URI" syntax, the path specified should start with a slash.
|
|
1546 |
* For URIs that do not follow the generic URI syntax, this method
|
|
1547 |
* sets the scheme-specific part.
|
|
1548 |
*
|
|
1549 |
* @param p_path the path for this URI (may be null)
|
|
1550 |
*
|
|
1551 |
* @exception MalformedURIException if p_path contains invalid
|
|
1552 |
* characters
|
|
1553 |
*/
|
|
1554 |
public void setPath(String p_path) throws MalformedURIException {
|
|
1555 |
if (p_path == null) {
|
|
1556 |
m_path = null;
|
|
1557 |
m_queryString = null;
|
|
1558 |
m_fragment = null;
|
|
1559 |
}
|
|
1560 |
else {
|
|
1561 |
initializePath(p_path, 0);
|
|
1562 |
}
|
|
1563 |
}
|
|
1564 |
|
|
1565 |
/**
|
|
1566 |
* Append to the end of the path of this URI. If the current path does
|
|
1567 |
* not end in a slash and the path to be appended does not begin with
|
|
1568 |
* a slash, a slash will be appended to the current path before the
|
|
1569 |
* new segment is added. Also, if the current path ends in a slash
|
|
1570 |
* and the new segment begins with a slash, the extra slash will be
|
|
1571 |
* removed before the new segment is appended.
|
|
1572 |
*
|
|
1573 |
* @param p_addToPath the new segment to be added to the current path
|
|
1574 |
*
|
|
1575 |
* @exception MalformedURIException if p_addToPath contains syntax
|
|
1576 |
* errors
|
|
1577 |
*/
|
|
1578 |
public void appendPath(String p_addToPath)
|
|
1579 |
throws MalformedURIException {
|
|
1580 |
if (p_addToPath == null || p_addToPath.trim().length() == 0) {
|
|
1581 |
return;
|
|
1582 |
}
|
|
1583 |
|
|
1584 |
if (!isURIString(p_addToPath)) {
|
|
1585 |
throw new MalformedURIException(
|
|
1586 |
"Path contains invalid character!");
|
|
1587 |
}
|
|
1588 |
|
|
1589 |
if (m_path == null || m_path.trim().length() == 0) {
|
|
1590 |
if (p_addToPath.startsWith("/")) {
|
|
1591 |
m_path = p_addToPath;
|
|
1592 |
}
|
|
1593 |
else {
|
|
1594 |
m_path = "/" + p_addToPath;
|
|
1595 |
}
|
|
1596 |
}
|
|
1597 |
else if (m_path.endsWith("/")) {
|
|
1598 |
if (p_addToPath.startsWith("/")) {
|
|
1599 |
m_path = m_path.concat(p_addToPath.substring(1));
|
|
1600 |
}
|
|
1601 |
else {
|
|
1602 |
m_path = m_path.concat(p_addToPath);
|
|
1603 |
}
|
|
1604 |
}
|
|
1605 |
else {
|
|
1606 |
if (p_addToPath.startsWith("/")) {
|
|
1607 |
m_path = m_path.concat(p_addToPath);
|
|
1608 |
}
|
|
1609 |
else {
|
|
1610 |
m_path = m_path.concat("/" + p_addToPath);
|
|
1611 |
}
|
|
1612 |
}
|
|
1613 |
}
|
|
1614 |
|
|
1615 |
/**
|
|
1616 |
* Set the query string for this URI. A non-null value is valid only
|
|
1617 |
* if this is an URI conforming to the generic URI syntax and
|
|
1618 |
* the path value is not null.
|
|
1619 |
*
|
|
1620 |
* @param p_queryString the query string for this URI
|
|
1621 |
*
|
|
1622 |
* @exception MalformedURIException if p_queryString is not null and this
|
|
1623 |
* URI does not conform to the generic
|
|
1624 |
* URI syntax or if the path is null
|
|
1625 |
*/
|
|
1626 |
public void setQueryString(String p_queryString) throws MalformedURIException {
|
|
1627 |
if (p_queryString == null) {
|
|
1628 |
m_queryString = null;
|
|
1629 |
}
|
|
1630 |
else if (!isGenericURI()) {
|
|
1631 |
throw new MalformedURIException(
|
|
1632 |
"Query string can only be set for a generic URI!");
|
|
1633 |
}
|
|
1634 |
else if (getPath() == null) {
|
|
1635 |
throw new MalformedURIException(
|
|
1636 |
"Query string cannot be set when path is null!");
|
|
1637 |
}
|
|
1638 |
else if (!isURIString(p_queryString)) {
|
|
1639 |
throw new MalformedURIException(
|
|
1640 |
"Query string contains invalid character!");
|
|
1641 |
}
|
|
1642 |
else {
|
|
1643 |
m_queryString = p_queryString;
|
|
1644 |
}
|
|
1645 |
}
|
|
1646 |
|
|
1647 |
/**
|
|
1648 |
* Set the fragment for this URI. A non-null value is valid only
|
|
1649 |
* if this is a URI conforming to the generic URI syntax and
|
|
1650 |
* the path value is not null.
|
|
1651 |
*
|
|
1652 |
* @param p_fragment the fragment for this URI
|
|
1653 |
*
|
|
1654 |
* @exception MalformedURIException if p_fragment is not null and this
|
|
1655 |
* URI does not conform to the generic
|
|
1656 |
* URI syntax or if the path is null
|
|
1657 |
*/
|
|
1658 |
public void setFragment(String p_fragment) throws MalformedURIException {
|
|
1659 |
if (p_fragment == null) {
|
|
1660 |
m_fragment = null;
|
|
1661 |
}
|
|
1662 |
else if (!isGenericURI()) {
|
|
1663 |
throw new MalformedURIException(
|
|
1664 |
"Fragment can only be set for a generic URI!");
|
|
1665 |
}
|
|
1666 |
else if (getPath() == null) {
|
|
1667 |
throw new MalformedURIException(
|
|
1668 |
"Fragment cannot be set when path is null!");
|
|
1669 |
}
|
|
1670 |
else if (!isURIString(p_fragment)) {
|
|
1671 |
throw new MalformedURIException(
|
|
1672 |
"Fragment contains invalid character!");
|
|
1673 |
}
|
|
1674 |
else {
|
|
1675 |
m_fragment = p_fragment;
|
|
1676 |
}
|
|
1677 |
}
|
|
1678 |
|
|
1679 |
/**
|
|
1680 |
* Determines if the passed-in Object is equivalent to this URI.
|
|
1681 |
*
|
|
1682 |
* @param p_test the Object to test for equality.
|
|
1683 |
*
|
|
1684 |
* @return true if p_test is a URI with all values equal to this
|
|
1685 |
* URI, false otherwise
|
|
1686 |
*/
|
17538
|
1687 |
@Override
|
6
|
1688 |
public boolean equals(Object p_test) {
|
|
1689 |
if (p_test instanceof URI) {
|
|
1690 |
URI testURI = (URI) p_test;
|
|
1691 |
if (((m_scheme == null && testURI.m_scheme == null) ||
|
|
1692 |
(m_scheme != null && testURI.m_scheme != null &&
|
|
1693 |
m_scheme.equals(testURI.m_scheme))) &&
|
|
1694 |
((m_userinfo == null && testURI.m_userinfo == null) ||
|
|
1695 |
(m_userinfo != null && testURI.m_userinfo != null &&
|
|
1696 |
m_userinfo.equals(testURI.m_userinfo))) &&
|
|
1697 |
((m_host == null && testURI.m_host == null) ||
|
|
1698 |
(m_host != null && testURI.m_host != null &&
|
|
1699 |
m_host.equals(testURI.m_host))) &&
|
|
1700 |
m_port == testURI.m_port &&
|
|
1701 |
((m_path == null && testURI.m_path == null) ||
|
|
1702 |
(m_path != null && testURI.m_path != null &&
|
|
1703 |
m_path.equals(testURI.m_path))) &&
|
|
1704 |
((m_queryString == null && testURI.m_queryString == null) ||
|
|
1705 |
(m_queryString != null && testURI.m_queryString != null &&
|
|
1706 |
m_queryString.equals(testURI.m_queryString))) &&
|
|
1707 |
((m_fragment == null && testURI.m_fragment == null) ||
|
|
1708 |
(m_fragment != null && testURI.m_fragment != null &&
|
|
1709 |
m_fragment.equals(testURI.m_fragment)))) {
|
|
1710 |
return true;
|
|
1711 |
}
|
|
1712 |
}
|
|
1713 |
return false;
|
|
1714 |
}
|
|
1715 |
|
17538
|
1716 |
@Override
|
|
1717 |
public int hashCode() {
|
|
1718 |
int hash = 5;
|
|
1719 |
hash = 47 * hash + Objects.hashCode(this.m_scheme);
|
|
1720 |
hash = 47 * hash + Objects.hashCode(this.m_userinfo);
|
|
1721 |
hash = 47 * hash + Objects.hashCode(this.m_host);
|
|
1722 |
hash = 47 * hash + this.m_port;
|
|
1723 |
hash = 47 * hash + Objects.hashCode(this.m_path);
|
|
1724 |
hash = 47 * hash + Objects.hashCode(this.m_queryString);
|
|
1725 |
hash = 47 * hash + Objects.hashCode(this.m_fragment);
|
|
1726 |
return hash;
|
|
1727 |
}
|
|
1728 |
|
6
|
1729 |
/**
|
|
1730 |
* Get the URI as a string specification. See RFC 2396 Section 5.2.
|
|
1731 |
*
|
|
1732 |
* @return the URI string specification
|
|
1733 |
*/
|
17538
|
1734 |
@Override
|
6
|
1735 |
public String toString() {
|
17538
|
1736 |
final StringBuilder uriSpecString = new StringBuilder();
|
6
|
1737 |
|
|
1738 |
if (m_scheme != null) {
|
|
1739 |
uriSpecString.append(m_scheme);
|
|
1740 |
uriSpecString.append(':');
|
|
1741 |
}
|
|
1742 |
uriSpecString.append(getSchemeSpecificPart());
|
|
1743 |
return uriSpecString.toString();
|
|
1744 |
}
|
|
1745 |
|
|
1746 |
/**
|
|
1747 |
* Get the indicator as to whether this URI uses the "generic URI"
|
|
1748 |
* syntax.
|
|
1749 |
*
|
|
1750 |
* @return true if this URI uses the "generic URI" syntax, false
|
|
1751 |
* otherwise
|
|
1752 |
*/
|
|
1753 |
public boolean isGenericURI() {
|
|
1754 |
// presence of the host (whether valid or empty) means
|
|
1755 |
// double-slashes which means generic uri
|
|
1756 |
return (m_host != null);
|
|
1757 |
}
|
|
1758 |
|
|
1759 |
/**
|
|
1760 |
* Returns whether this URI represents an absolute URI.
|
|
1761 |
*
|
|
1762 |
* @return true if this URI represents an absolute URI, false
|
|
1763 |
* otherwise
|
|
1764 |
*/
|
|
1765 |
public boolean isAbsoluteURI() {
|
|
1766 |
// presence of the scheme means absolute uri
|
|
1767 |
return (m_scheme != null);
|
|
1768 |
}
|
|
1769 |
|
|
1770 |
/**
|
|
1771 |
* Determine whether a scheme conforms to the rules for a scheme name.
|
|
1772 |
* A scheme is conformant if it starts with an alphanumeric, and
|
|
1773 |
* contains only alphanumerics, '+','-' and '.'.
|
|
1774 |
*
|
|
1775 |
* @return true if the scheme is conformant, false otherwise
|
|
1776 |
*/
|
|
1777 |
public static boolean isConformantSchemeName(String p_scheme) {
|
|
1778 |
if (p_scheme == null || p_scheme.trim().length() == 0) {
|
|
1779 |
return false;
|
|
1780 |
}
|
|
1781 |
|
|
1782 |
if (!isAlpha(p_scheme.charAt(0))) {
|
|
1783 |
return false;
|
|
1784 |
}
|
|
1785 |
|
|
1786 |
char testChar;
|
|
1787 |
int schemeLength = p_scheme.length();
|
|
1788 |
for (int i = 1; i < schemeLength; ++i) {
|
|
1789 |
testChar = p_scheme.charAt(i);
|
|
1790 |
if (!isSchemeCharacter(testChar)) {
|
|
1791 |
return false;
|
|
1792 |
}
|
|
1793 |
}
|
|
1794 |
|
|
1795 |
return true;
|
|
1796 |
}
|
|
1797 |
|
|
1798 |
/**
|
|
1799 |
* Determine whether a string is syntactically capable of representing
|
|
1800 |
* a valid IPv4 address, IPv6 reference or the domain name of a network host.
|
|
1801 |
* A valid IPv4 address consists of four decimal digit groups separated by a
|
|
1802 |
* '.'. Each group must consist of one to three digits. See RFC 2732 Section 3,
|
|
1803 |
* and RFC 2373 Section 2.2, for the definition of IPv6 references. A hostname
|
|
1804 |
* consists of domain labels (each of which must begin and end with an alphanumeric
|
|
1805 |
* but may contain '-') separated & by a '.'. See RFC 2396 Section 3.2.2.
|
|
1806 |
*
|
|
1807 |
* @return true if the string is a syntactically valid IPv4 address,
|
|
1808 |
* IPv6 reference or hostname
|
|
1809 |
*/
|
|
1810 |
public static boolean isWellFormedAddress(String address) {
|
|
1811 |
if (address == null) {
|
|
1812 |
return false;
|
|
1813 |
}
|
|
1814 |
|
|
1815 |
int addrLength = address.length();
|
|
1816 |
if (addrLength == 0) {
|
|
1817 |
return false;
|
|
1818 |
}
|
|
1819 |
|
|
1820 |
// Check if the host is a valid IPv6reference.
|
|
1821 |
if (address.startsWith("[")) {
|
|
1822 |
return isWellFormedIPv6Reference(address);
|
|
1823 |
}
|
|
1824 |
|
|
1825 |
// Cannot start with a '.', '-', or end with a '-'.
|
|
1826 |
if (address.startsWith(".") ||
|
|
1827 |
address.startsWith("-") ||
|
|
1828 |
address.endsWith("-")) {
|
|
1829 |
return false;
|
|
1830 |
}
|
|
1831 |
|
|
1832 |
// rightmost domain label starting with digit indicates IP address
|
|
1833 |
// since top level domain label can only start with an alpha
|
|
1834 |
// see RFC 2396 Section 3.2.2
|
|
1835 |
int index = address.lastIndexOf('.');
|
|
1836 |
if (address.endsWith(".")) {
|
|
1837 |
index = address.substring(0, index).lastIndexOf('.');
|
|
1838 |
}
|
|
1839 |
|
|
1840 |
if (index+1 < addrLength && isDigit(address.charAt(index+1))) {
|
|
1841 |
return isWellFormedIPv4Address(address);
|
|
1842 |
}
|
|
1843 |
else {
|
|
1844 |
// hostname = *( domainlabel "." ) toplabel [ "." ]
|
|
1845 |
// domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
|
|
1846 |
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
|
|
1847 |
|
|
1848 |
// RFC 2396 states that hostnames take the form described in
|
|
1849 |
// RFC 1034 (Section 3) and RFC 1123 (Section 2.1). According
|
|
1850 |
// to RFC 1034, hostnames are limited to 255 characters.
|
|
1851 |
if (addrLength > 255) {
|
|
1852 |
return false;
|
|
1853 |
}
|
|
1854 |
|
|
1855 |
// domain labels can contain alphanumerics and '-"
|
|
1856 |
// but must start and end with an alphanumeric
|
|
1857 |
char testChar;
|
|
1858 |
int labelCharCount = 0;
|
|
1859 |
|
|
1860 |
for (int i = 0; i < addrLength; i++) {
|
|
1861 |
testChar = address.charAt(i);
|
|
1862 |
if (testChar == '.') {
|
|
1863 |
if (!isAlphanum(address.charAt(i-1))) {
|
|
1864 |
return false;
|
|
1865 |
}
|
|
1866 |
if (i+1 < addrLength && !isAlphanum(address.charAt(i+1))) {
|
|
1867 |
return false;
|
|
1868 |
}
|
|
1869 |
labelCharCount = 0;
|
|
1870 |
}
|
|
1871 |
else if (!isAlphanum(testChar) && testChar != '-') {
|
|
1872 |
return false;
|
|
1873 |
}
|
|
1874 |
// RFC 1034: Labels must be 63 characters or less.
|
|
1875 |
else if (++labelCharCount > 63) {
|
|
1876 |
return false;
|
|
1877 |
}
|
|
1878 |
}
|
|
1879 |
}
|
|
1880 |
return true;
|
|
1881 |
}
|
|
1882 |
|
|
1883 |
/**
|
|
1884 |
* <p>Determines whether a string is an IPv4 address as defined by
|
|
1885 |
* RFC 2373, and under the further constraint that it must be a 32-bit
|
|
1886 |
* address. Though not expressed in the grammar, in order to satisfy
|
|
1887 |
* the 32-bit address constraint, each segment of the address cannot
|
|
1888 |
* be greater than 255 (8 bits of information).</p>
|
|
1889 |
*
|
|
1890 |
* <p><code>IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT</code></p>
|
|
1891 |
*
|
|
1892 |
* @return true if the string is a syntactically valid IPv4 address
|
|
1893 |
*/
|
|
1894 |
public static boolean isWellFormedIPv4Address(String address) {
|
|
1895 |
|
|
1896 |
int addrLength = address.length();
|
|
1897 |
char testChar;
|
|
1898 |
int numDots = 0;
|
|
1899 |
int numDigits = 0;
|
|
1900 |
|
|
1901 |
// make sure that 1) we see only digits and dot separators, 2) that
|
|
1902 |
// any dot separator is preceded and followed by a digit and
|
|
1903 |
// 3) that we find 3 dots
|
|
1904 |
//
|
|
1905 |
// RFC 2732 amended RFC 2396 by replacing the definition
|
|
1906 |
// of IPv4address with the one defined by RFC 2373. - mrglavas
|
|
1907 |
//
|
|
1908 |
// IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
|
|
1909 |
//
|
|
1910 |
// One to three digits must be in each segment.
|
|
1911 |
for (int i = 0; i < addrLength; i++) {
|
|
1912 |
testChar = address.charAt(i);
|
|
1913 |
if (testChar == '.') {
|
|
1914 |
if ((i > 0 && !isDigit(address.charAt(i-1))) ||
|
|
1915 |
(i+1 < addrLength && !isDigit(address.charAt(i+1)))) {
|
|
1916 |
return false;
|
|
1917 |
}
|
|
1918 |
numDigits = 0;
|
|
1919 |
if (++numDots > 3) {
|
|
1920 |
return false;
|
|
1921 |
}
|
|
1922 |
}
|
|
1923 |
else if (!isDigit(testChar)) {
|
|
1924 |
return false;
|
|
1925 |
}
|
|
1926 |
// Check that that there are no more than three digits
|
|
1927 |
// in this segment.
|
|
1928 |
else if (++numDigits > 3) {
|
|
1929 |
return false;
|
|
1930 |
}
|
|
1931 |
// Check that this segment is not greater than 255.
|
|
1932 |
else if (numDigits == 3) {
|
|
1933 |
char first = address.charAt(i-2);
|
|
1934 |
char second = address.charAt(i-1);
|
|
1935 |
if (!(first < '2' ||
|
|
1936 |
(first == '2' &&
|
|
1937 |
(second < '5' ||
|
|
1938 |
(second == '5' && testChar <= '5'))))) {
|
|
1939 |
return false;
|
|
1940 |
}
|
|
1941 |
}
|
|
1942 |
}
|
|
1943 |
return (numDots == 3);
|
|
1944 |
}
|
|
1945 |
|
|
1946 |
/**
|
|
1947 |
* <p>Determines whether a string is an IPv6 reference as defined
|
|
1948 |
* by RFC 2732, where IPv6address is defined in RFC 2373. The
|
|
1949 |
* IPv6 address is parsed according to Section 2.2 of RFC 2373,
|
|
1950 |
* with the additional constraint that the address be composed of
|
|
1951 |
* 128 bits of information.</p>
|
|
1952 |
*
|
|
1953 |
* <p><code>IPv6reference = "[" IPv6address "]"</code></p>
|
|
1954 |
*
|
|
1955 |
* <p>Note: The BNF expressed in RFC 2373 Appendix B does not
|
|
1956 |
* accurately describe section 2.2, and was in fact removed from
|
|
1957 |
* RFC 3513, the successor of RFC 2373.</p>
|
|
1958 |
*
|
|
1959 |
* @return true if the string is a syntactically valid IPv6 reference
|
|
1960 |
*/
|
|
1961 |
public static boolean isWellFormedIPv6Reference(String address) {
|
|
1962 |
|
|
1963 |
int addrLength = address.length();
|
|
1964 |
int index = 1;
|
|
1965 |
int end = addrLength-1;
|
|
1966 |
|
|
1967 |
// Check if string is a potential match for IPv6reference.
|
|
1968 |
if (!(addrLength > 2 && address.charAt(0) == '['
|
|
1969 |
&& address.charAt(end) == ']')) {
|
|
1970 |
return false;
|
|
1971 |
}
|
|
1972 |
|
|
1973 |
// Counter for the number of 16-bit sections read in the address.
|
|
1974 |
int [] counter = new int[1];
|
|
1975 |
|
|
1976 |
// Scan hex sequence before possible '::' or IPv4 address.
|
|
1977 |
index = scanHexSequence(address, index, end, counter);
|
|
1978 |
if (index == -1) {
|
|
1979 |
return false;
|
|
1980 |
}
|
|
1981 |
// Address must contain 128-bits of information.
|
|
1982 |
else if (index == end) {
|
|
1983 |
return (counter[0] == 8);
|
|
1984 |
}
|
|
1985 |
|
|
1986 |
if (index+1 < end && address.charAt(index) == ':') {
|
|
1987 |
if (address.charAt(index+1) == ':') {
|
|
1988 |
// '::' represents at least one 16-bit group of zeros.
|
|
1989 |
if (++counter[0] > 8) {
|
|
1990 |
return false;
|
|
1991 |
}
|
|
1992 |
index += 2;
|
|
1993 |
// Trailing zeros will fill out the rest of the address.
|
|
1994 |
if (index == end) {
|
|
1995 |
return true;
|
|
1996 |
}
|
|
1997 |
}
|
|
1998 |
// If the second character wasn't ':', in order to be valid,
|
|
1999 |
// the remainder of the string must match IPv4Address,
|
|
2000 |
// and we must have read exactly 6 16-bit groups.
|
|
2001 |
else {
|
|
2002 |
return (counter[0] == 6) &&
|
|
2003 |
isWellFormedIPv4Address(address.substring(index+1, end));
|
|
2004 |
}
|
|
2005 |
}
|
|
2006 |
else {
|
|
2007 |
return false;
|
|
2008 |
}
|
|
2009 |
|
|
2010 |
// 3. Scan hex sequence after '::'.
|
|
2011 |
int prevCount = counter[0];
|
|
2012 |
index = scanHexSequence(address, index, end, counter);
|
|
2013 |
|
|
2014 |
// We've either reached the end of the string, the address ends in
|
|
2015 |
// an IPv4 address, or it is invalid. scanHexSequence has already
|
|
2016 |
// made sure that we have the right number of bits.
|
|
2017 |
return (index == end) ||
|
|
2018 |
(index != -1 && isWellFormedIPv4Address(
|
|
2019 |
address.substring((counter[0] > prevCount) ? index+1 : index, end)));
|
|
2020 |
}
|
|
2021 |
|
|
2022 |
/**
|
|
2023 |
* Helper method for isWellFormedIPv6Reference which scans the
|
|
2024 |
* hex sequences of an IPv6 address. It returns the index of the
|
|
2025 |
* next character to scan in the address, or -1 if the string
|
|
2026 |
* cannot match a valid IPv6 address.
|
|
2027 |
*
|
|
2028 |
* @param address the string to be scanned
|
|
2029 |
* @param index the beginning index (inclusive)
|
|
2030 |
* @param end the ending index (exclusive)
|
|
2031 |
* @param counter a counter for the number of 16-bit sections read
|
|
2032 |
* in the address
|
|
2033 |
*
|
|
2034 |
* @return the index of the next character to scan, or -1 if the
|
|
2035 |
* string cannot match a valid IPv6 address
|
|
2036 |
*/
|
|
2037 |
private static int scanHexSequence (String address, int index, int end, int [] counter) {
|
|
2038 |
|
|
2039 |
char testChar;
|
|
2040 |
int numDigits = 0;
|
|
2041 |
int start = index;
|
|
2042 |
|
|
2043 |
// Trying to match the following productions:
|
|
2044 |
// hexseq = hex4 *( ":" hex4)
|
|
2045 |
// hex4 = 1*4HEXDIG
|
|
2046 |
for (; index < end; ++index) {
|
|
2047 |
testChar = address.charAt(index);
|
|
2048 |
if (testChar == ':') {
|
|
2049 |
// IPv6 addresses are 128-bit, so there can be at most eight sections.
|
|
2050 |
if (numDigits > 0 && ++counter[0] > 8) {
|
|
2051 |
return -1;
|
|
2052 |
}
|
|
2053 |
// This could be '::'.
|
|
2054 |
if (numDigits == 0 || ((index+1 < end) && address.charAt(index+1) == ':')) {
|
|
2055 |
return index;
|
|
2056 |
}
|
|
2057 |
numDigits = 0;
|
|
2058 |
}
|
|
2059 |
// This might be invalid or an IPv4address. If it's potentially an IPv4address,
|
|
2060 |
// backup to just after the last valid character that matches hexseq.
|
|
2061 |
else if (!isHex(testChar)) {
|
|
2062 |
if (testChar == '.' && numDigits < 4 && numDigits > 0 && counter[0] <= 6) {
|
|
2063 |
int back = index - numDigits - 1;
|
|
2064 |
return (back >= start) ? back : (back+1);
|
|
2065 |
}
|
|
2066 |
return -1;
|
|
2067 |
}
|
|
2068 |
// There can be at most 4 hex digits per group.
|
|
2069 |
else if (++numDigits > 4) {
|
|
2070 |
return -1;
|
|
2071 |
}
|
|
2072 |
}
|
|
2073 |
return (numDigits > 0 && ++counter[0] <= 8) ? end : -1;
|
|
2074 |
}
|
|
2075 |
|
|
2076 |
|
|
2077 |
/**
|
|
2078 |
* Determine whether a char is a digit.
|
|
2079 |
*
|
|
2080 |
* @return true if the char is betweeen '0' and '9', false otherwise
|
|
2081 |
*/
|
|
2082 |
private static boolean isDigit(char p_char) {
|
|
2083 |
return p_char >= '0' && p_char <= '9';
|
|
2084 |
}
|
|
2085 |
|
|
2086 |
/**
|
|
2087 |
* Determine whether a character is a hexadecimal character.
|
|
2088 |
*
|
|
2089 |
* @return true if the char is betweeen '0' and '9', 'a' and 'f'
|
|
2090 |
* or 'A' and 'F', false otherwise
|
|
2091 |
*/
|
|
2092 |
private static boolean isHex(char p_char) {
|
|
2093 |
return (p_char <= 'f' && (fgLookupTable[p_char] & ASCII_HEX_CHARACTERS) != 0);
|
|
2094 |
}
|
|
2095 |
|
|
2096 |
/**
|
|
2097 |
* Determine whether a char is an alphabetic character: a-z or A-Z
|
|
2098 |
*
|
|
2099 |
* @return true if the char is alphabetic, false otherwise
|
|
2100 |
*/
|
|
2101 |
private static boolean isAlpha(char p_char) {
|
|
2102 |
return ((p_char >= 'a' && p_char <= 'z') || (p_char >= 'A' && p_char <= 'Z' ));
|
|
2103 |
}
|
|
2104 |
|
|
2105 |
/**
|
|
2106 |
* Determine whether a char is an alphanumeric: 0-9, a-z or A-Z
|
|
2107 |
*
|
|
2108 |
* @return true if the char is alphanumeric, false otherwise
|
|
2109 |
*/
|
|
2110 |
private static boolean isAlphanum(char p_char) {
|
|
2111 |
return (p_char <= 'z' && (fgLookupTable[p_char] & MASK_ALPHA_NUMERIC) != 0);
|
|
2112 |
}
|
|
2113 |
|
|
2114 |
/**
|
|
2115 |
* Determine whether a character is a reserved character:
|
|
2116 |
* ';', '/', '?', ':', '@', '&', '=', '+', '$', ',', '[', or ']'
|
|
2117 |
*
|
|
2118 |
* @return true if the string contains any reserved characters
|
|
2119 |
*/
|
|
2120 |
private static boolean isReservedCharacter(char p_char) {
|
|
2121 |
return (p_char <= ']' && (fgLookupTable[p_char] & RESERVED_CHARACTERS) != 0);
|
|
2122 |
}
|
|
2123 |
|
|
2124 |
/**
|
|
2125 |
* Determine whether a char is an unreserved character.
|
|
2126 |
*
|
|
2127 |
* @return true if the char is unreserved, false otherwise
|
|
2128 |
*/
|
|
2129 |
private static boolean isUnreservedCharacter(char p_char) {
|
|
2130 |
return (p_char <= '~' && (fgLookupTable[p_char] & MASK_UNRESERVED_MASK) != 0);
|
|
2131 |
}
|
|
2132 |
|
|
2133 |
/**
|
|
2134 |
* Determine whether a char is a URI character (reserved or
|
|
2135 |
* unreserved, not including '%' for escaped octets).
|
|
2136 |
*
|
|
2137 |
* @return true if the char is a URI character, false otherwise
|
|
2138 |
*/
|
|
2139 |
private static boolean isURICharacter (char p_char) {
|
|
2140 |
return (p_char <= '~' && (fgLookupTable[p_char] & MASK_URI_CHARACTER) != 0);
|
|
2141 |
}
|
|
2142 |
|
|
2143 |
/**
|
|
2144 |
* Determine whether a char is a scheme character.
|
|
2145 |
*
|
|
2146 |
* @return true if the char is a scheme character, false otherwise
|
|
2147 |
*/
|
|
2148 |
private static boolean isSchemeCharacter (char p_char) {
|
|
2149 |
return (p_char <= 'z' && (fgLookupTable[p_char] & MASK_SCHEME_CHARACTER) != 0);
|
|
2150 |
}
|
|
2151 |
|
|
2152 |
/**
|
|
2153 |
* Determine whether a char is a userinfo character.
|
|
2154 |
*
|
|
2155 |
* @return true if the char is a userinfo character, false otherwise
|
|
2156 |
*/
|
|
2157 |
private static boolean isUserinfoCharacter (char p_char) {
|
|
2158 |
return (p_char <= 'z' && (fgLookupTable[p_char] & MASK_USERINFO_CHARACTER) != 0);
|
|
2159 |
}
|
|
2160 |
|
|
2161 |
/**
|
|
2162 |
* Determine whether a char is a path character.
|
|
2163 |
*
|
|
2164 |
* @return true if the char is a path character, false otherwise
|
|
2165 |
*/
|
|
2166 |
private static boolean isPathCharacter (char p_char) {
|
|
2167 |
return (p_char <= '~' && (fgLookupTable[p_char] & MASK_PATH_CHARACTER) != 0);
|
|
2168 |
}
|
|
2169 |
|
|
2170 |
|
|
2171 |
/**
|
|
2172 |
* Determine whether a given string contains only URI characters (also
|
|
2173 |
* called "uric" in RFC 2396). uric consist of all reserved
|
|
2174 |
* characters, unreserved characters and escaped characters.
|
|
2175 |
*
|
|
2176 |
* @return true if the string is comprised of uric, false otherwise
|
|
2177 |
*/
|
|
2178 |
private static boolean isURIString(String p_uric) {
|
|
2179 |
if (p_uric == null) {
|
|
2180 |
return false;
|
|
2181 |
}
|
|
2182 |
int end = p_uric.length();
|
|
2183 |
char testChar = '\0';
|
|
2184 |
for (int i = 0; i < end; i++) {
|
|
2185 |
testChar = p_uric.charAt(i);
|
|
2186 |
if (testChar == '%') {
|
|
2187 |
if (i+2 >= end ||
|
|
2188 |
!isHex(p_uric.charAt(i+1)) ||
|
|
2189 |
!isHex(p_uric.charAt(i+2))) {
|
|
2190 |
return false;
|
|
2191 |
}
|
|
2192 |
else {
|
|
2193 |
i += 2;
|
|
2194 |
continue;
|
|
2195 |
}
|
|
2196 |
}
|
|
2197 |
if (isURICharacter(testChar)) {
|
|
2198 |
continue;
|
|
2199 |
}
|
|
2200 |
else {
|
|
2201 |
return false;
|
|
2202 |
}
|
|
2203 |
}
|
|
2204 |
return true;
|
|
2205 |
}
|
|
2206 |
}
|