author | joehw |
Sun, 05 Jan 2014 21:00:00 -0800 | |
changeset 22140 | f2634f2bc36c |
parent 12457 | c348e06f0e82 |
child 25264 | 040625ce9b72 |
permissions | -rw-r--r-- |
6 | 1 |
/* |
2 |
* reserved comment block |
|
3 |
* DO NOT REMOVE OR ALTER! |
|
4 |
*/ |
|
5 |
/* |
|
6 |
* The Apache Software License, Version 1.1 |
|
7 |
* |
|
8 |
* |
|
9 |
* Copyright (c) 1999-2002 The Apache Software Foundation. |
|
10 |
* All rights reserved. |
|
11 |
* |
|
12 |
* Redistribution and use in source and binary forms, with or without |
|
13 |
* modification, are permitted provided that the following conditions |
|
14 |
* are met: |
|
15 |
* |
|
16 |
* 1. Redistributions of source code must retain the above copyright |
|
17 |
* notice, this list of conditions and the following disclaimer. |
|
18 |
* |
|
19 |
* 2. Redistributions in binary form must reproduce the above copyright |
|
20 |
* notice, this list of conditions and the following disclaimer in |
|
21 |
* the documentation and/or other materials provided with the |
|
22 |
* distribution. |
|
23 |
* |
|
24 |
* 3. The end-user documentation included with the redistribution, |
|
25 |
* if any, must include the following acknowledgment: |
|
26 |
* "This product includes software developed by the |
|
27 |
* Apache Software Foundation (http://www.apache.org/)." |
|
28 |
* Alternately, this acknowledgment may appear in the software itself, |
|
29 |
* if and wherever such third-party acknowledgments normally appear. |
|
30 |
* |
|
31 |
* 4. The names "Xerces" and "Apache Software Foundation" must |
|
32 |
* not be used to endorse or promote products derived from this |
|
33 |
* software without prior written permission. For written |
|
34 |
* permission, please contact apache@apache.org. |
|
35 |
* |
|
36 |
* 5. Products derived from this software may not be called "Apache", |
|
37 |
* nor may "Apache" appear in their name, without prior written |
|
38 |
* permission of the Apache Software Foundation. |
|
39 |
* |
|
40 |
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED |
|
41 |
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES |
|
42 |
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
|
43 |
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR |
|
44 |
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
|
45 |
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
|
46 |
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF |
|
47 |
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
|
48 |
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, |
|
49 |
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT |
|
50 |
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
|
51 |
* SUCH DAMAGE. |
|
52 |
* ==================================================================== |
|
53 |
* |
|
54 |
* This software consists of voluntary contributions made by many |
|
55 |
* individuals on behalf of the Apache Software Foundation and was |
|
56 |
* originally based on software copyright (c) 1999, International |
|
57 |
* Business Machines, Inc., http://www.apache.org. For more |
|
58 |
* information on the Apache Software Foundation, please see |
|
59 |
* <http://www.apache.org/>. |
|
60 |
*/ |
|
61 |
||
62 |
package com.sun.org.apache.xerces.internal.impl; |
|
63 |
||
64 |
import com.sun.org.apache.xerces.internal.impl.msg.XMLMessageFormatter; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
65 |
import com.sun.org.apache.xerces.internal.util.XML11Char; |
6 | 66 |
import com.sun.org.apache.xerces.internal.util.XMLChar; |
67 |
import com.sun.org.apache.xerces.internal.util.XMLStringBuffer; |
|
68 |
import com.sun.org.apache.xerces.internal.xni.QName; |
|
69 |
import com.sun.org.apache.xerces.internal.xni.XMLString; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
70 |
import java.io.IOException; |
6 | 71 |
|
72 |
/** |
|
73 |
* Implements the entity scanner methods in |
|
74 |
* the context of XML 1.1. |
|
75 |
* |
|
76 |
* @xerces.internal |
|
77 |
* |
|
78 |
* @author Michael Glavassevich, IBM |
|
79 |
* @author Neil Graham, IBM |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
80 |
* @version $Id: XML11EntityScanner.java,v 1.5 2010-11-01 04:39:40 joehw Exp $ |
6 | 81 |
*/ |
82 |
||
83 |
public class XML11EntityScanner |
|
84 |
extends XMLEntityScanner { |
|
85 |
||
86 |
// |
|
87 |
// Constructors |
|
88 |
// |
|
89 |
||
90 |
/** Default constructor. */ |
|
91 |
public XML11EntityScanner() { |
|
92 |
super(); |
|
93 |
} // <init>() |
|
94 |
||
95 |
// |
|
96 |
// XMLEntityScanner methods |
|
97 |
// |
|
98 |
||
99 |
/** |
|
100 |
* Returns the next character on the input. |
|
101 |
* <p> |
|
102 |
* <strong>Note:</strong> The character is <em>not</em> consumed. |
|
103 |
* |
|
104 |
* @throws IOException Thrown if i/o error occurs. |
|
105 |
* @throws EOFException Thrown on end of file. |
|
106 |
*/ |
|
107 |
public int peekChar() throws IOException { |
|
108 |
||
109 |
// load more characters, if needed |
|
110 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
111 |
load(0, true, true); |
6 | 112 |
} |
113 |
||
114 |
// peek at character |
|
115 |
int c = fCurrentEntity.ch[fCurrentEntity.position]; |
|
116 |
||
117 |
// return peeked character |
|
118 |
if (fCurrentEntity.isExternal()) { |
|
119 |
return (c != '\r' && c != 0x85 && c != 0x2028) ? c : '\n'; |
|
120 |
} |
|
121 |
else { |
|
122 |
return c; |
|
123 |
} |
|
124 |
||
125 |
} // peekChar():int |
|
126 |
||
127 |
/** |
|
128 |
* Returns the next character on the input. |
|
129 |
* <p> |
|
130 |
* <strong>Note:</strong> The character is consumed. |
|
131 |
* |
|
132 |
* @throws IOException Thrown if i/o error occurs. |
|
133 |
* @throws EOFException Thrown on end of file. |
|
134 |
*/ |
|
135 |
public int scanChar() throws IOException { |
|
136 |
||
137 |
// load more characters, if needed |
|
138 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
139 |
load(0, true, true); |
6 | 140 |
} |
141 |
||
142 |
// scan character |
|
143 |
int c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
144 |
boolean external = false; |
|
145 |
if (c == '\n' || |
|
146 |
((c == '\r' || c == 0x85 || c == 0x2028) && (external = fCurrentEntity.isExternal()))) { |
|
147 |
fCurrentEntity.lineNumber++; |
|
148 |
fCurrentEntity.columnNumber = 1; |
|
149 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
150 |
fCurrentEntity.ch[0] = (char)c; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
151 |
load(1, false, true); |
6 | 152 |
} |
153 |
if (c == '\r' && external) { |
|
154 |
int cc = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
155 |
if (cc != '\n' && cc != 0x85) { |
|
156 |
fCurrentEntity.position--; |
|
157 |
} |
|
158 |
} |
|
159 |
c = '\n'; |
|
160 |
} |
|
161 |
||
162 |
// return character that was scanned |
|
163 |
fCurrentEntity.columnNumber++; |
|
164 |
return c; |
|
165 |
||
166 |
} // scanChar():int |
|
167 |
||
168 |
/** |
|
169 |
* Returns a string matching the NMTOKEN production appearing immediately |
|
170 |
* on the input as a symbol, or null if NMTOKEN Name string is present. |
|
171 |
* <p> |
|
172 |
* <strong>Note:</strong> The NMTOKEN characters are consumed. |
|
173 |
* <p> |
|
174 |
* <strong>Note:</strong> The string returned must be a symbol. The |
|
175 |
* SymbolTable can be used for this purpose. |
|
176 |
* |
|
177 |
* @throws IOException Thrown if i/o error occurs. |
|
178 |
* @throws EOFException Thrown on end of file. |
|
179 |
* |
|
180 |
* @see com.sun.org.apache.xerces.internal.util.SymbolTable |
|
181 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11Name |
|
182 |
*/ |
|
183 |
public String scanNmtoken() throws IOException { |
|
184 |
// load more characters, if needed |
|
185 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
186 |
load(0, true, true); |
6 | 187 |
} |
188 |
||
189 |
// scan nmtoken |
|
190 |
int offset = fCurrentEntity.position; |
|
191 |
||
192 |
do { |
|
193 |
char ch = fCurrentEntity.ch[fCurrentEntity.position]; |
|
194 |
if (XML11Char.isXML11Name(ch)) { |
|
195 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
196 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
197 |
invokeListeners(length); |
6 | 198 |
if (length == fCurrentEntity.ch.length) { |
199 |
// bad luck we have to resize our buffer |
|
200 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
201 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
202 |
tmp, 0, length); |
|
203 |
fCurrentEntity.ch = tmp; |
|
204 |
} |
|
205 |
else { |
|
206 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
207 |
fCurrentEntity.ch, 0, length); |
|
208 |
} |
|
209 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
210 |
if (load(length, false, false)) { |
6 | 211 |
break; |
212 |
} |
|
213 |
} |
|
214 |
} |
|
215 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
216 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
217 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
218 |
invokeListeners(length); |
6 | 219 |
if (length == fCurrentEntity.ch.length) { |
220 |
// bad luck we have to resize our buffer |
|
221 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
222 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
223 |
tmp, 0, length); |
|
224 |
fCurrentEntity.ch = tmp; |
|
225 |
} |
|
226 |
else { |
|
227 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
228 |
fCurrentEntity.ch, 0, length); |
|
229 |
} |
|
230 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
231 |
if (load(length, false, false)) { |
6 | 232 |
--fCurrentEntity.startPosition; |
233 |
--fCurrentEntity.position; |
|
234 |
break; |
|
235 |
} |
|
236 |
} |
|
237 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
238 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
239 |
!XML11Char.isXML11Name(XMLChar.supplemental(ch, ch2)) ) { |
|
240 |
--fCurrentEntity.position; |
|
241 |
break; |
|
242 |
} |
|
243 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
244 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
245 |
invokeListeners(length); |
6 | 246 |
if (length == fCurrentEntity.ch.length) { |
247 |
// bad luck we have to resize our buffer |
|
248 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
249 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
250 |
tmp, 0, length); |
|
251 |
fCurrentEntity.ch = tmp; |
|
252 |
} |
|
253 |
else { |
|
254 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
255 |
fCurrentEntity.ch, 0, length); |
|
256 |
} |
|
257 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
258 |
if (load(length, false, false)) { |
6 | 259 |
break; |
260 |
} |
|
261 |
} |
|
262 |
} |
|
263 |
else { |
|
264 |
break; |
|
265 |
} |
|
266 |
} |
|
267 |
while (true); |
|
268 |
||
269 |
int length = fCurrentEntity.position - offset; |
|
270 |
fCurrentEntity.columnNumber += length; |
|
271 |
||
272 |
// return nmtoken |
|
273 |
String symbol = null; |
|
274 |
if (length > 0) { |
|
275 |
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length); |
|
276 |
} |
|
277 |
return symbol; |
|
278 |
||
279 |
} // scanNmtoken():String |
|
280 |
||
281 |
/** |
|
282 |
* Returns a string matching the Name production appearing immediately |
|
283 |
* on the input as a symbol, or null if no Name string is present. |
|
284 |
* <p> |
|
285 |
* <strong>Note:</strong> The Name characters are consumed. |
|
286 |
* <p> |
|
287 |
* <strong>Note:</strong> The string returned must be a symbol. The |
|
288 |
* SymbolTable can be used for this purpose. |
|
289 |
* |
|
290 |
* @throws IOException Thrown if i/o error occurs. |
|
291 |
* @throws EOFException Thrown on end of file. |
|
292 |
* |
|
293 |
* @see com.sun.org.apache.xerces.internal.util.SymbolTable |
|
294 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11Name |
|
295 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11NameStart |
|
296 |
*/ |
|
297 |
public String scanName() throws IOException { |
|
298 |
// load more characters, if needed |
|
299 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
300 |
load(0, true, true); |
6 | 301 |
} |
302 |
||
303 |
// scan name |
|
304 |
int offset = fCurrentEntity.position; |
|
305 |
char ch = fCurrentEntity.ch[offset]; |
|
306 |
||
307 |
if (XML11Char.isXML11NameStart(ch)) { |
|
308 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
309 |
fCurrentEntity.ch[0] = ch; |
|
310 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
311 |
if (load(1, false, true)) { |
6 | 312 |
fCurrentEntity.columnNumber++; |
313 |
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1); |
|
314 |
return symbol; |
|
315 |
} |
|
316 |
} |
|
317 |
} |
|
318 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
319 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
320 |
fCurrentEntity.ch[0] = ch; |
|
321 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
322 |
if (load(1, false, true)) { |
6 | 323 |
--fCurrentEntity.position; |
324 |
--fCurrentEntity.startPosition; |
|
325 |
return null; |
|
326 |
} |
|
327 |
} |
|
328 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
329 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
330 |
!XML11Char.isXML11NameStart(XMLChar.supplemental(ch, ch2)) ) { |
|
331 |
--fCurrentEntity.position; |
|
332 |
return null; |
|
333 |
} |
|
334 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
335 |
fCurrentEntity.ch[0] = ch; |
|
336 |
fCurrentEntity.ch[1] = ch2; |
|
337 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
338 |
if (load(2, false, true)) { |
6 | 339 |
fCurrentEntity.columnNumber += 2; |
340 |
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 2); |
|
341 |
return symbol; |
|
342 |
} |
|
343 |
} |
|
344 |
} |
|
345 |
else { |
|
346 |
return null; |
|
347 |
} |
|
348 |
||
349 |
do { |
|
350 |
ch = fCurrentEntity.ch[fCurrentEntity.position]; |
|
351 |
if (XML11Char.isXML11Name(ch)) { |
|
352 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
353 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
354 |
invokeListeners(length); |
6 | 355 |
if (length == fCurrentEntity.ch.length) { |
356 |
// bad luck we have to resize our buffer |
|
357 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
358 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
359 |
tmp, 0, length); |
|
360 |
fCurrentEntity.ch = tmp; |
|
361 |
} |
|
362 |
else { |
|
363 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
364 |
fCurrentEntity.ch, 0, length); |
|
365 |
} |
|
366 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
367 |
if (load(length, false, false)) { |
6 | 368 |
break; |
369 |
} |
|
370 |
} |
|
371 |
} |
|
372 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
373 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
374 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
375 |
invokeListeners(length); |
6 | 376 |
if (length == fCurrentEntity.ch.length) { |
377 |
// bad luck we have to resize our buffer |
|
378 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
379 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
380 |
tmp, 0, length); |
|
381 |
fCurrentEntity.ch = tmp; |
|
382 |
} |
|
383 |
else { |
|
384 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
385 |
fCurrentEntity.ch, 0, length); |
|
386 |
} |
|
387 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
388 |
if (load(length, false, false)) { |
6 | 389 |
--fCurrentEntity.position; |
390 |
--fCurrentEntity.startPosition; |
|
391 |
break; |
|
392 |
} |
|
393 |
} |
|
394 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
395 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
396 |
!XML11Char.isXML11Name(XMLChar.supplemental(ch, ch2)) ) { |
|
397 |
--fCurrentEntity.position; |
|
398 |
break; |
|
399 |
} |
|
400 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
401 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
402 |
invokeListeners(length); |
6 | 403 |
if (length == fCurrentEntity.ch.length) { |
404 |
// bad luck we have to resize our buffer |
|
405 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
406 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
407 |
tmp, 0, length); |
|
408 |
fCurrentEntity.ch = tmp; |
|
409 |
} |
|
410 |
else { |
|
411 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
412 |
fCurrentEntity.ch, 0, length); |
|
413 |
} |
|
414 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
415 |
if (load(length, false, false)) { |
6 | 416 |
break; |
417 |
} |
|
418 |
} |
|
419 |
} |
|
420 |
else { |
|
421 |
break; |
|
422 |
} |
|
423 |
} |
|
424 |
while (true); |
|
425 |
||
426 |
int length = fCurrentEntity.position - offset; |
|
427 |
fCurrentEntity.columnNumber += length; |
|
428 |
||
429 |
// return name |
|
430 |
String symbol = null; |
|
431 |
if (length > 0) { |
|
432 |
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length); |
|
433 |
} |
|
434 |
return symbol; |
|
435 |
||
436 |
} // scanName():String |
|
437 |
||
438 |
/** |
|
439 |
* Returns a string matching the NCName production appearing immediately |
|
440 |
* on the input as a symbol, or null if no NCName string is present. |
|
441 |
* <p> |
|
442 |
* <strong>Note:</strong> The NCName characters are consumed. |
|
443 |
* <p> |
|
444 |
* <strong>Note:</strong> The string returned must be a symbol. The |
|
445 |
* SymbolTable can be used for this purpose. |
|
446 |
* |
|
447 |
* @throws IOException Thrown if i/o error occurs. |
|
448 |
* @throws EOFException Thrown on end of file. |
|
449 |
* |
|
450 |
* @see com.sun.org.apache.xerces.internal.util.SymbolTable |
|
451 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11NCName |
|
452 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11NCNameStart |
|
453 |
*/ |
|
454 |
public String scanNCName() throws IOException { |
|
455 |
||
456 |
// load more characters, if needed |
|
457 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
458 |
load(0, true, true); |
6 | 459 |
} |
460 |
||
461 |
// scan name |
|
462 |
int offset = fCurrentEntity.position; |
|
463 |
char ch = fCurrentEntity.ch[offset]; |
|
464 |
||
465 |
if (XML11Char.isXML11NCNameStart(ch)) { |
|
466 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
467 |
fCurrentEntity.ch[0] = ch; |
|
468 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
469 |
if (load(1, false, true)) { |
6 | 470 |
fCurrentEntity.columnNumber++; |
471 |
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1); |
|
472 |
return symbol; |
|
473 |
} |
|
474 |
} |
|
475 |
} |
|
476 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
477 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
478 |
fCurrentEntity.ch[0] = ch; |
|
479 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
480 |
if (load(1, false, true)) { |
6 | 481 |
--fCurrentEntity.position; |
482 |
--fCurrentEntity.startPosition; |
|
483 |
return null; |
|
484 |
} |
|
485 |
} |
|
486 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
487 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
488 |
!XML11Char.isXML11NCNameStart(XMLChar.supplemental(ch, ch2)) ) { |
|
489 |
--fCurrentEntity.position; |
|
490 |
return null; |
|
491 |
} |
|
492 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
493 |
fCurrentEntity.ch[0] = ch; |
|
494 |
fCurrentEntity.ch[1] = ch2; |
|
495 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
496 |
if (load(2, false, true)) { |
6 | 497 |
fCurrentEntity.columnNumber += 2; |
498 |
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 2); |
|
499 |
return symbol; |
|
500 |
} |
|
501 |
} |
|
502 |
} |
|
503 |
else { |
|
504 |
return null; |
|
505 |
} |
|
506 |
||
507 |
do { |
|
508 |
ch = fCurrentEntity.ch[fCurrentEntity.position]; |
|
509 |
if (XML11Char.isXML11NCName(ch)) { |
|
510 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
511 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
512 |
invokeListeners(length); |
6 | 513 |
if (length == fCurrentEntity.ch.length) { |
514 |
// bad luck we have to resize our buffer |
|
515 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
516 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
517 |
tmp, 0, length); |
|
518 |
fCurrentEntity.ch = tmp; |
|
519 |
} |
|
520 |
else { |
|
521 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
522 |
fCurrentEntity.ch, 0, length); |
|
523 |
} |
|
524 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
525 |
if (load(length, false, false)) { |
6 | 526 |
break; |
527 |
} |
|
528 |
} |
|
529 |
} |
|
530 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
531 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
532 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
533 |
invokeListeners(length); |
6 | 534 |
if (length == fCurrentEntity.ch.length) { |
535 |
// bad luck we have to resize our buffer |
|
536 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
537 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
538 |
tmp, 0, length); |
|
539 |
fCurrentEntity.ch = tmp; |
|
540 |
} |
|
541 |
else { |
|
542 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
543 |
fCurrentEntity.ch, 0, length); |
|
544 |
} |
|
545 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
546 |
if (load(length, false, false)) { |
6 | 547 |
--fCurrentEntity.startPosition; |
548 |
--fCurrentEntity.position; |
|
549 |
break; |
|
550 |
} |
|
551 |
} |
|
552 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
553 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
554 |
!XML11Char.isXML11NCName(XMLChar.supplemental(ch, ch2)) ) { |
|
555 |
--fCurrentEntity.position; |
|
556 |
break; |
|
557 |
} |
|
558 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
559 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
560 |
invokeListeners(length); |
6 | 561 |
if (length == fCurrentEntity.ch.length) { |
562 |
// bad luck we have to resize our buffer |
|
563 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
564 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
565 |
tmp, 0, length); |
|
566 |
fCurrentEntity.ch = tmp; |
|
567 |
} |
|
568 |
else { |
|
569 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
570 |
fCurrentEntity.ch, 0, length); |
|
571 |
} |
|
572 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
573 |
if (load(length, false, false)) { |
6 | 574 |
break; |
575 |
} |
|
576 |
} |
|
577 |
} |
|
578 |
else { |
|
579 |
break; |
|
580 |
} |
|
581 |
} |
|
582 |
while (true); |
|
583 |
||
584 |
int length = fCurrentEntity.position - offset; |
|
585 |
fCurrentEntity.columnNumber += length; |
|
586 |
||
587 |
// return name |
|
588 |
String symbol = null; |
|
589 |
if (length > 0) { |
|
590 |
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length); |
|
591 |
} |
|
592 |
return symbol; |
|
593 |
||
594 |
} // scanNCName():String |
|
595 |
||
596 |
/** |
|
597 |
* Scans a qualified name from the input, setting the fields of the |
|
598 |
* QName structure appropriately. |
|
599 |
* <p> |
|
600 |
* <strong>Note:</strong> The qualified name characters are consumed. |
|
601 |
* <p> |
|
602 |
* <strong>Note:</strong> The strings used to set the values of the |
|
603 |
* QName structure must be symbols. The SymbolTable can be used for |
|
604 |
* this purpose. |
|
605 |
* |
|
606 |
* @param qname The qualified name structure to fill. |
|
607 |
* |
|
608 |
* @return Returns true if a qualified name appeared immediately on |
|
609 |
* the input and was scanned, false otherwise. |
|
610 |
* |
|
611 |
* @throws IOException Thrown if i/o error occurs. |
|
612 |
* @throws EOFException Thrown on end of file. |
|
613 |
* |
|
614 |
* @see com.sun.org.apache.xerces.internal.util.SymbolTable |
|
615 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11Name |
|
616 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11NameStart |
|
617 |
*/ |
|
618 |
public boolean scanQName(QName qname) throws IOException { |
|
619 |
||
620 |
// load more characters, if needed |
|
621 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
622 |
load(0, true, true); |
6 | 623 |
} |
624 |
||
625 |
// scan qualified name |
|
626 |
int offset = fCurrentEntity.position; |
|
627 |
char ch = fCurrentEntity.ch[offset]; |
|
628 |
||
629 |
if (XML11Char.isXML11NCNameStart(ch)) { |
|
630 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
631 |
fCurrentEntity.ch[0] = ch; |
|
632 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
633 |
if (load(1, false, true)) { |
6 | 634 |
fCurrentEntity.columnNumber++; |
635 |
String name = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 1); |
|
636 |
qname.setValues(null, name, name, null); |
|
637 |
return true; |
|
638 |
} |
|
639 |
} |
|
640 |
} |
|
641 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
642 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
643 |
fCurrentEntity.ch[0] = ch; |
|
644 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
645 |
if (load(1, false, true)) { |
6 | 646 |
--fCurrentEntity.startPosition; |
647 |
--fCurrentEntity.position; |
|
648 |
return false; |
|
649 |
} |
|
650 |
} |
|
651 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
652 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
653 |
!XML11Char.isXML11NCNameStart(XMLChar.supplemental(ch, ch2)) ) { |
|
654 |
--fCurrentEntity.position; |
|
655 |
return false; |
|
656 |
} |
|
657 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
658 |
fCurrentEntity.ch[0] = ch; |
|
659 |
fCurrentEntity.ch[1] = ch2; |
|
660 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
661 |
if (load(2, false, true)) { |
6 | 662 |
fCurrentEntity.columnNumber += 2; |
663 |
String name = fSymbolTable.addSymbol(fCurrentEntity.ch, 0, 2); |
|
664 |
qname.setValues(null, name, name, null); |
|
665 |
return true; |
|
666 |
} |
|
667 |
} |
|
668 |
} |
|
669 |
else { |
|
670 |
return false; |
|
671 |
} |
|
672 |
||
673 |
int index = -1; |
|
674 |
boolean sawIncompleteSurrogatePair = false; |
|
675 |
do { |
|
676 |
ch = fCurrentEntity.ch[fCurrentEntity.position]; |
|
677 |
if (XML11Char.isXML11Name(ch)) { |
|
678 |
if (ch == ':') { |
|
679 |
if (index != -1) { |
|
680 |
break; |
|
681 |
} |
|
682 |
index = fCurrentEntity.position; |
|
683 |
} |
|
684 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
685 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
686 |
invokeListeners(length); |
6 | 687 |
if (length == fCurrentEntity.ch.length) { |
688 |
// bad luck we have to resize our buffer |
|
689 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
690 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
691 |
tmp, 0, length); |
|
692 |
fCurrentEntity.ch = tmp; |
|
693 |
} |
|
694 |
else { |
|
695 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
696 |
fCurrentEntity.ch, 0, length); |
|
697 |
} |
|
698 |
if (index != -1) { |
|
699 |
index = index - offset; |
|
700 |
} |
|
701 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
702 |
if (load(length, false, false)) { |
6 | 703 |
break; |
704 |
} |
|
705 |
} |
|
706 |
} |
|
707 |
else if (XML11Char.isXML11NameHighSurrogate(ch)) { |
|
708 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
709 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
710 |
invokeListeners(length); |
6 | 711 |
if (length == fCurrentEntity.ch.length) { |
712 |
// bad luck we have to resize our buffer |
|
713 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
714 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
715 |
tmp, 0, length); |
|
716 |
fCurrentEntity.ch = tmp; |
|
717 |
} |
|
718 |
else { |
|
719 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
720 |
fCurrentEntity.ch, 0, length); |
|
721 |
} |
|
722 |
if (index != -1) { |
|
723 |
index = index - offset; |
|
724 |
} |
|
725 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
726 |
if (load(length, false, false)) { |
6 | 727 |
sawIncompleteSurrogatePair = true; |
728 |
--fCurrentEntity.startPosition; |
|
729 |
--fCurrentEntity.position; |
|
730 |
break; |
|
731 |
} |
|
732 |
} |
|
733 |
char ch2 = fCurrentEntity.ch[fCurrentEntity.position]; |
|
734 |
if ( !XMLChar.isLowSurrogate(ch2) || |
|
735 |
!XML11Char.isXML11Name(XMLChar.supplemental(ch, ch2)) ) { |
|
736 |
sawIncompleteSurrogatePair = true; |
|
737 |
--fCurrentEntity.position; |
|
738 |
break; |
|
739 |
} |
|
740 |
if (++fCurrentEntity.position == fCurrentEntity.count) { |
|
741 |
int length = fCurrentEntity.position - offset; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
742 |
invokeListeners(length); |
6 | 743 |
if (length == fCurrentEntity.ch.length) { |
744 |
// bad luck we have to resize our buffer |
|
745 |
char[] tmp = new char[fCurrentEntity.ch.length << 1]; |
|
746 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
747 |
tmp, 0, length); |
|
748 |
fCurrentEntity.ch = tmp; |
|
749 |
} |
|
750 |
else { |
|
751 |
System.arraycopy(fCurrentEntity.ch, offset, |
|
752 |
fCurrentEntity.ch, 0, length); |
|
753 |
} |
|
754 |
if (index != -1) { |
|
755 |
index = index - offset; |
|
756 |
} |
|
757 |
offset = 0; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
758 |
if (load(length, false, false)) { |
6 | 759 |
break; |
760 |
} |
|
761 |
} |
|
762 |
} |
|
763 |
else { |
|
764 |
break; |
|
765 |
} |
|
766 |
} |
|
767 |
while (true); |
|
768 |
||
769 |
int length = fCurrentEntity.position - offset; |
|
770 |
fCurrentEntity.columnNumber += length; |
|
771 |
||
772 |
if (length > 0) { |
|
773 |
String prefix = null; |
|
774 |
String localpart = null; |
|
775 |
String rawname = fSymbolTable.addSymbol(fCurrentEntity.ch, |
|
776 |
offset, length); |
|
777 |
if (index != -1) { |
|
778 |
int prefixLength = index - offset; |
|
779 |
prefix = fSymbolTable.addSymbol(fCurrentEntity.ch, |
|
780 |
offset, prefixLength); |
|
781 |
int len = length - prefixLength - 1; |
|
782 |
int startLocal = index +1; |
|
783 |
if (!XML11Char.isXML11NCNameStart(fCurrentEntity.ch[startLocal]) && |
|
784 |
(!XML11Char.isXML11NameHighSurrogate(fCurrentEntity.ch[startLocal]) || |
|
785 |
sawIncompleteSurrogatePair)){ |
|
786 |
fErrorReporter.reportError(XMLMessageFormatter.XML_DOMAIN, |
|
787 |
"IllegalQName", |
|
788 |
null, |
|
789 |
XMLErrorReporter.SEVERITY_FATAL_ERROR); |
|
790 |
} |
|
791 |
localpart = fSymbolTable.addSymbol(fCurrentEntity.ch, |
|
792 |
index + 1, len); |
|
793 |
||
794 |
} |
|
795 |
else { |
|
796 |
localpart = rawname; |
|
797 |
} |
|
798 |
qname.setValues(prefix, localpart, rawname, null); |
|
799 |
return true; |
|
800 |
} |
|
801 |
return false; |
|
802 |
||
803 |
} // scanQName(QName):boolean |
|
804 |
||
805 |
/** |
|
806 |
* Scans a range of parsed character data, setting the fields of the |
|
807 |
* XMLString structure, appropriately. |
|
808 |
* <p> |
|
809 |
* <strong>Note:</strong> The characters are consumed. |
|
810 |
* <p> |
|
811 |
* <strong>Note:</strong> This method does not guarantee to return |
|
812 |
* the longest run of parsed character data. This method may return |
|
813 |
* before markup due to reaching the end of the input buffer or any |
|
814 |
* other reason. |
|
815 |
* <p> |
|
816 |
* <strong>Note:</strong> The fields contained in the XMLString |
|
817 |
* structure are not guaranteed to remain valid upon subsequent calls |
|
818 |
* to the entity scanner. Therefore, the caller is responsible for |
|
819 |
* immediately using the returned character data or making a copy of |
|
820 |
* the character data. |
|
821 |
* |
|
822 |
* @param content The content structure to fill. |
|
823 |
* |
|
824 |
* @return Returns the next character on the input, if known. This |
|
825 |
* value may be -1 but this does <em>note</em> designate |
|
826 |
* end of file. |
|
827 |
* |
|
828 |
* @throws IOException Thrown if i/o error occurs. |
|
829 |
* @throws EOFException Thrown on end of file. |
|
830 |
*/ |
|
831 |
public int scanContent(XMLString content) throws IOException { |
|
832 |
||
833 |
// load more characters, if needed |
|
834 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
835 |
load(0, true, true); |
6 | 836 |
} |
837 |
else if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
838 |
fCurrentEntity.ch[0] = fCurrentEntity.ch[fCurrentEntity.count - 1]; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
839 |
load(1, false, true); |
6 | 840 |
fCurrentEntity.position = 0; |
841 |
fCurrentEntity.startPosition = 0; |
|
842 |
} |
|
843 |
||
844 |
// normalize newlines |
|
845 |
int offset = fCurrentEntity.position; |
|
846 |
int c = fCurrentEntity.ch[offset]; |
|
847 |
int newlines = 0; |
|
848 |
boolean external = fCurrentEntity.isExternal(); |
|
849 |
if (c == '\n' || ((c == '\r' || c == 0x85 || c == 0x2028) && external)) { |
|
850 |
do { |
|
851 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
852 |
if ((c == '\r' ) && external) { |
|
853 |
newlines++; |
|
854 |
fCurrentEntity.lineNumber++; |
|
855 |
fCurrentEntity.columnNumber = 1; |
|
856 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
857 |
offset = 0; |
|
858 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
859 |
fCurrentEntity.position = newlines; |
|
860 |
fCurrentEntity.startPosition = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
861 |
if (load(newlines, false, true)) { |
6 | 862 |
break; |
863 |
} |
|
864 |
} |
|
865 |
int cc = fCurrentEntity.ch[fCurrentEntity.position]; |
|
866 |
if (cc == '\n' || cc == 0x85) { |
|
867 |
fCurrentEntity.position++; |
|
868 |
offset++; |
|
869 |
} |
|
870 |
/*** NEWLINE NORMALIZATION ***/ |
|
871 |
else { |
|
872 |
newlines++; |
|
873 |
} |
|
874 |
} |
|
875 |
else if (c == '\n' || ((c == 0x85 || c == 0x2028) && external)) { |
|
876 |
newlines++; |
|
877 |
fCurrentEntity.lineNumber++; |
|
878 |
fCurrentEntity.columnNumber = 1; |
|
879 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
880 |
offset = 0; |
|
881 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
882 |
fCurrentEntity.position = newlines; |
|
883 |
fCurrentEntity.startPosition = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
884 |
if (load(newlines, false, true)) { |
6 | 885 |
break; |
886 |
} |
|
887 |
} |
|
888 |
} |
|
889 |
else { |
|
890 |
fCurrentEntity.position--; |
|
891 |
break; |
|
892 |
} |
|
893 |
} while (fCurrentEntity.position < fCurrentEntity.count - 1); |
|
894 |
for (int i = offset; i < fCurrentEntity.position; i++) { |
|
895 |
fCurrentEntity.ch[i] = '\n'; |
|
896 |
} |
|
897 |
int length = fCurrentEntity.position - offset; |
|
898 |
if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
899 |
content.setValues(fCurrentEntity.ch, offset, length); |
|
900 |
return -1; |
|
901 |
} |
|
902 |
} |
|
903 |
||
904 |
// inner loop, scanning for content |
|
905 |
if (external) { |
|
906 |
while (fCurrentEntity.position < fCurrentEntity.count) { |
|
907 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
908 |
if (!XML11Char.isXML11Content(c) || c == 0x85 || c == 0x2028) { |
|
909 |
fCurrentEntity.position--; |
|
910 |
break; |
|
911 |
} |
|
912 |
} |
|
913 |
} |
|
914 |
else { |
|
915 |
while (fCurrentEntity.position < fCurrentEntity.count) { |
|
916 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
917 |
// In internal entities control characters are allowed to appear unescaped. |
|
918 |
if (!XML11Char.isXML11InternalEntityContent(c)) { |
|
919 |
fCurrentEntity.position--; |
|
920 |
break; |
|
921 |
} |
|
922 |
} |
|
923 |
} |
|
924 |
int length = fCurrentEntity.position - offset; |
|
925 |
fCurrentEntity.columnNumber += length - newlines; |
|
926 |
content.setValues(fCurrentEntity.ch, offset, length); |
|
927 |
||
928 |
// return next character |
|
929 |
if (fCurrentEntity.position != fCurrentEntity.count) { |
|
930 |
c = fCurrentEntity.ch[fCurrentEntity.position]; |
|
931 |
// REVISIT: Does this need to be updated to fix the |
|
932 |
// #x0D ^#x0A newline normalization problem? -Ac |
|
933 |
if ((c == '\r' || c == 0x85 || c == 0x2028) && external) { |
|
934 |
c = '\n'; |
|
935 |
} |
|
936 |
} |
|
937 |
else { |
|
938 |
c = -1; |
|
939 |
} |
|
940 |
return c; |
|
941 |
||
942 |
} // scanContent(XMLString):int |
|
943 |
||
944 |
/** |
|
945 |
* Scans a range of attribute value data, setting the fields of the |
|
946 |
* XMLString structure, appropriately. |
|
947 |
* <p> |
|
948 |
* <strong>Note:</strong> The characters are consumed. |
|
949 |
* <p> |
|
950 |
* <strong>Note:</strong> This method does not guarantee to return |
|
951 |
* the longest run of attribute value data. This method may return |
|
952 |
* before the quote character due to reaching the end of the input |
|
953 |
* buffer or any other reason. |
|
954 |
* <p> |
|
955 |
* <strong>Note:</strong> The fields contained in the XMLString |
|
956 |
* structure are not guaranteed to remain valid upon subsequent calls |
|
957 |
* to the entity scanner. Therefore, the caller is responsible for |
|
958 |
* immediately using the returned character data or making a copy of |
|
959 |
* the character data. |
|
960 |
* |
|
961 |
* @param quote The quote character that signifies the end of the |
|
962 |
* attribute value data. |
|
963 |
* @param content The content structure to fill. |
|
964 |
* |
|
965 |
* @return Returns the next character on the input, if known. This |
|
966 |
* value may be -1 but this does <em>note</em> designate |
|
967 |
* end of file. |
|
968 |
* |
|
969 |
* @throws IOException Thrown if i/o error occurs. |
|
970 |
* @throws EOFException Thrown on end of file. |
|
971 |
*/ |
|
972 |
public int scanLiteral(int quote, XMLString content) |
|
973 |
throws IOException { |
|
974 |
// load more characters, if needed |
|
975 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
976 |
load(0, true, true); |
6 | 977 |
} |
978 |
else if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
979 |
fCurrentEntity.ch[0] = fCurrentEntity.ch[fCurrentEntity.count - 1]; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
980 |
load(1, false, true); |
6 | 981 |
fCurrentEntity.startPosition = 0; |
982 |
fCurrentEntity.position = 0; |
|
983 |
} |
|
984 |
||
985 |
// normalize newlines |
|
986 |
int offset = fCurrentEntity.position; |
|
987 |
int c = fCurrentEntity.ch[offset]; |
|
988 |
int newlines = 0; |
|
989 |
boolean external = fCurrentEntity.isExternal(); |
|
990 |
if (c == '\n' || ((c == '\r' || c == 0x85 || c == 0x2028) && external)) { |
|
991 |
do { |
|
992 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
993 |
if ((c == '\r' ) && external) { |
|
994 |
newlines++; |
|
995 |
fCurrentEntity.lineNumber++; |
|
996 |
fCurrentEntity.columnNumber = 1; |
|
997 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
998 |
offset = 0; |
|
999 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
1000 |
fCurrentEntity.position = newlines; |
|
1001 |
fCurrentEntity.startPosition = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1002 |
if (load(newlines, false, true)) { |
6 | 1003 |
break; |
1004 |
} |
|
1005 |
} |
|
1006 |
int cc = fCurrentEntity.ch[fCurrentEntity.position]; |
|
1007 |
if (cc == '\n' || cc == 0x85) { |
|
1008 |
fCurrentEntity.position++; |
|
1009 |
offset++; |
|
1010 |
} |
|
1011 |
/*** NEWLINE NORMALIZATION ***/ |
|
1012 |
else { |
|
1013 |
newlines++; |
|
1014 |
} |
|
1015 |
} |
|
1016 |
else if (c == '\n' || ((c == 0x85 || c == 0x2028) && external)) { |
|
1017 |
newlines++; |
|
1018 |
fCurrentEntity.lineNumber++; |
|
1019 |
fCurrentEntity.columnNumber = 1; |
|
1020 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1021 |
offset = 0; |
|
1022 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
1023 |
fCurrentEntity.position = newlines; |
|
1024 |
fCurrentEntity.startPosition = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1025 |
if (load(newlines, false, true)) { |
6 | 1026 |
break; |
1027 |
} |
|
1028 |
} |
|
1029 |
} |
|
1030 |
else { |
|
1031 |
fCurrentEntity.position--; |
|
1032 |
break; |
|
1033 |
} |
|
1034 |
} while (fCurrentEntity.position < fCurrentEntity.count - 1); |
|
1035 |
for (int i = offset; i < fCurrentEntity.position; i++) { |
|
1036 |
fCurrentEntity.ch[i] = '\n'; |
|
1037 |
} |
|
1038 |
int length = fCurrentEntity.position - offset; |
|
1039 |
if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
1040 |
content.setValues(fCurrentEntity.ch, offset, length); |
|
1041 |
return -1; |
|
1042 |
} |
|
1043 |
} |
|
1044 |
||
1045 |
// scan literal value |
|
1046 |
if (external) { |
|
1047 |
while (fCurrentEntity.position < fCurrentEntity.count) { |
|
1048 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1049 |
if (c == quote || c == '%' || !XML11Char.isXML11Content(c) |
|
1050 |
|| c == 0x85 || c == 0x2028) { |
|
1051 |
fCurrentEntity.position--; |
|
1052 |
break; |
|
1053 |
} |
|
1054 |
} |
|
1055 |
} |
|
1056 |
else { |
|
1057 |
while (fCurrentEntity.position < fCurrentEntity.count) { |
|
1058 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1059 |
// In internal entities control characters are allowed to appear unescaped. |
|
1060 |
if ((c == quote && !fCurrentEntity.literal) |
|
1061 |
|| c == '%' || !XML11Char.isXML11InternalEntityContent(c)) { |
|
1062 |
fCurrentEntity.position--; |
|
1063 |
break; |
|
1064 |
} |
|
1065 |
} |
|
1066 |
} |
|
1067 |
int length = fCurrentEntity.position - offset; |
|
1068 |
fCurrentEntity.columnNumber += length - newlines; |
|
1069 |
content.setValues(fCurrentEntity.ch, offset, length); |
|
1070 |
||
1071 |
// return next character |
|
1072 |
if (fCurrentEntity.position != fCurrentEntity.count) { |
|
1073 |
c = fCurrentEntity.ch[fCurrentEntity.position]; |
|
1074 |
// NOTE: We don't want to accidentally signal the |
|
1075 |
// end of the literal if we're expanding an |
|
1076 |
// entity appearing in the literal. -Ac |
|
1077 |
if (c == quote && fCurrentEntity.literal) { |
|
1078 |
c = -1; |
|
1079 |
} |
|
1080 |
} |
|
1081 |
else { |
|
1082 |
c = -1; |
|
1083 |
} |
|
1084 |
return c; |
|
1085 |
||
1086 |
} // scanLiteral(int,XMLString):int |
|
1087 |
||
1088 |
/** |
|
1089 |
* Scans a range of character data up to the specicied delimiter, |
|
1090 |
* setting the fields of the XMLString structure, appropriately. |
|
1091 |
* <p> |
|
1092 |
* <strong>Note:</strong> The characters are consumed. |
|
1093 |
* <p> |
|
1094 |
* <strong>Note:</strong> This assumes that the internal buffer is |
|
1095 |
* at least the same size, or bigger, than the length of the delimiter |
|
1096 |
* and that the delimiter contains at least one character. |
|
1097 |
* <p> |
|
1098 |
* <strong>Note:</strong> This method does not guarantee to return |
|
1099 |
* the longest run of character data. This method may return before |
|
1100 |
* the delimiter due to reaching the end of the input buffer or any |
|
1101 |
* other reason. |
|
1102 |
* <p> |
|
1103 |
* <strong>Note:</strong> The fields contained in the XMLString |
|
1104 |
* structure are not guaranteed to remain valid upon subsequent calls |
|
1105 |
* to the entity scanner. Therefore, the caller is responsible for |
|
1106 |
* immediately using the returned character data or making a copy of |
|
1107 |
* the character data. |
|
1108 |
* |
|
1109 |
* @param delimiter The string that signifies the end of the character |
|
1110 |
* data to be scanned. |
|
1111 |
* @param data The data structure to fill. |
|
1112 |
* |
|
1113 |
* @return Returns true if there is more data to scan, false otherwise. |
|
1114 |
* |
|
1115 |
* @throws IOException Thrown if i/o error occurs. |
|
1116 |
* @throws EOFException Thrown on end of file. |
|
1117 |
*/ |
|
1118 |
public boolean scanData(String delimiter, XMLStringBuffer buffer) |
|
1119 |
throws IOException { |
|
1120 |
||
1121 |
boolean done = false; |
|
1122 |
int delimLen = delimiter.length(); |
|
1123 |
char charAt0 = delimiter.charAt(0); |
|
1124 |
boolean external = fCurrentEntity.isExternal(); |
|
1125 |
do { |
|
1126 |
// load more characters, if needed |
|
1127 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1128 |
load(0, true, false); |
6 | 1129 |
} |
1130 |
||
1131 |
boolean bNextEntity = false; |
|
1132 |
||
1133 |
while ((fCurrentEntity.position >= fCurrentEntity.count - delimLen) |
|
1134 |
&& (!bNextEntity)) |
|
1135 |
{ |
|
1136 |
System.arraycopy(fCurrentEntity.ch, |
|
1137 |
fCurrentEntity.position, |
|
1138 |
fCurrentEntity.ch, |
|
1139 |
0, |
|
1140 |
fCurrentEntity.count - fCurrentEntity.position); |
|
1141 |
||
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1142 |
bNextEntity = load(fCurrentEntity.count - fCurrentEntity.position, false, false); |
6 | 1143 |
fCurrentEntity.position = 0; |
1144 |
fCurrentEntity.startPosition = 0; |
|
1145 |
} |
|
1146 |
||
1147 |
if (fCurrentEntity.position >= fCurrentEntity.count - delimLen) { |
|
1148 |
// something must be wrong with the input: e.g., file ends an unterminated comment |
|
1149 |
int length = fCurrentEntity.count - fCurrentEntity.position; |
|
1150 |
buffer.append (fCurrentEntity.ch, fCurrentEntity.position, length); |
|
1151 |
fCurrentEntity.columnNumber += fCurrentEntity.count; |
|
1152 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
1153 |
fCurrentEntity.position = fCurrentEntity.count; |
|
1154 |
fCurrentEntity.startPosition = fCurrentEntity.count; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1155 |
load(0,true, false); |
6 | 1156 |
return false; |
1157 |
} |
|
1158 |
||
1159 |
// normalize newlines |
|
1160 |
int offset = fCurrentEntity.position; |
|
1161 |
int c = fCurrentEntity.ch[offset]; |
|
1162 |
int newlines = 0; |
|
1163 |
if (c == '\n' || ((c == '\r' || c == 0x85 || c == 0x2028) && external)) { |
|
1164 |
do { |
|
1165 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1166 |
if ((c == '\r' ) && external) { |
|
1167 |
newlines++; |
|
1168 |
fCurrentEntity.lineNumber++; |
|
1169 |
fCurrentEntity.columnNumber = 1; |
|
1170 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1171 |
offset = 0; |
|
1172 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
1173 |
fCurrentEntity.position = newlines; |
|
1174 |
fCurrentEntity.startPosition = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1175 |
if (load(newlines, false, true)) { |
6 | 1176 |
break; |
1177 |
} |
|
1178 |
} |
|
1179 |
int cc = fCurrentEntity.ch[fCurrentEntity.position]; |
|
1180 |
if (cc == '\n' || cc == 0x85) { |
|
1181 |
fCurrentEntity.position++; |
|
1182 |
offset++; |
|
1183 |
} |
|
1184 |
/*** NEWLINE NORMALIZATION ***/ |
|
1185 |
else { |
|
1186 |
newlines++; |
|
1187 |
} |
|
1188 |
} |
|
1189 |
else if (c == '\n' || ((c == 0x85 || c == 0x2028) && external)) { |
|
1190 |
newlines++; |
|
1191 |
fCurrentEntity.lineNumber++; |
|
1192 |
fCurrentEntity.columnNumber = 1; |
|
1193 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1194 |
offset = 0; |
|
1195 |
fCurrentEntity.baseCharOffset += (fCurrentEntity.position - fCurrentEntity.startPosition); |
|
1196 |
fCurrentEntity.position = newlines; |
|
1197 |
fCurrentEntity.startPosition = newlines; |
|
1198 |
fCurrentEntity.count = newlines; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1199 |
if (load(newlines, false, true)) { |
6 | 1200 |
break; |
1201 |
} |
|
1202 |
} |
|
1203 |
} |
|
1204 |
else { |
|
1205 |
fCurrentEntity.position--; |
|
1206 |
break; |
|
1207 |
} |
|
1208 |
} while (fCurrentEntity.position < fCurrentEntity.count - 1); |
|
1209 |
for (int i = offset; i < fCurrentEntity.position; i++) { |
|
1210 |
fCurrentEntity.ch[i] = '\n'; |
|
1211 |
} |
|
1212 |
int length = fCurrentEntity.position - offset; |
|
1213 |
if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
1214 |
buffer.append(fCurrentEntity.ch, offset, length); |
|
1215 |
return true; |
|
1216 |
} |
|
1217 |
} |
|
1218 |
||
1219 |
// iterate over buffer looking for delimiter |
|
1220 |
if (external) { |
|
1221 |
OUTER: while (fCurrentEntity.position < fCurrentEntity.count) { |
|
1222 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1223 |
if (c == charAt0) { |
|
1224 |
// looks like we just hit the delimiter |
|
1225 |
int delimOffset = fCurrentEntity.position - 1; |
|
1226 |
for (int i = 1; i < delimLen; i++) { |
|
1227 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1228 |
fCurrentEntity.position -= i; |
|
1229 |
break OUTER; |
|
1230 |
} |
|
1231 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1232 |
if (delimiter.charAt(i) != c) { |
|
1233 |
fCurrentEntity.position--; |
|
1234 |
break; |
|
1235 |
} |
|
1236 |
} |
|
1237 |
if (fCurrentEntity.position == delimOffset + delimLen) { |
|
1238 |
done = true; |
|
1239 |
break; |
|
1240 |
} |
|
1241 |
} |
|
1242 |
else if (c == '\n' || c == '\r' || c == 0x85 || c == 0x2028) { |
|
1243 |
fCurrentEntity.position--; |
|
1244 |
break; |
|
1245 |
} |
|
1246 |
// In external entities control characters cannot appear |
|
1247 |
// as literals so do not skip over them. |
|
1248 |
else if (!XML11Char.isXML11ValidLiteral(c)) { |
|
1249 |
fCurrentEntity.position--; |
|
1250 |
int length = fCurrentEntity.position - offset; |
|
1251 |
fCurrentEntity.columnNumber += length - newlines; |
|
1252 |
buffer.append(fCurrentEntity.ch, offset, length); |
|
1253 |
return true; |
|
1254 |
} |
|
1255 |
} |
|
1256 |
} |
|
1257 |
else { |
|
1258 |
OUTER: while (fCurrentEntity.position < fCurrentEntity.count) { |
|
1259 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1260 |
if (c == charAt0) { |
|
1261 |
// looks like we just hit the delimiter |
|
1262 |
int delimOffset = fCurrentEntity.position - 1; |
|
1263 |
for (int i = 1; i < delimLen; i++) { |
|
1264 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1265 |
fCurrentEntity.position -= i; |
|
1266 |
break OUTER; |
|
1267 |
} |
|
1268 |
c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1269 |
if (delimiter.charAt(i) != c) { |
|
1270 |
fCurrentEntity.position--; |
|
1271 |
break; |
|
1272 |
} |
|
1273 |
} |
|
1274 |
if (fCurrentEntity.position == delimOffset + delimLen) { |
|
1275 |
done = true; |
|
1276 |
break; |
|
1277 |
} |
|
1278 |
} |
|
1279 |
else if (c == '\n') { |
|
1280 |
fCurrentEntity.position--; |
|
1281 |
break; |
|
1282 |
} |
|
1283 |
// Control characters are allowed to appear as literals |
|
1284 |
// in internal entities. |
|
1285 |
else if (!XML11Char.isXML11Valid(c)) { |
|
1286 |
fCurrentEntity.position--; |
|
1287 |
int length = fCurrentEntity.position - offset; |
|
1288 |
fCurrentEntity.columnNumber += length - newlines; |
|
1289 |
buffer.append(fCurrentEntity.ch, offset, length); |
|
1290 |
return true; |
|
1291 |
} |
|
1292 |
} |
|
1293 |
} |
|
1294 |
int length = fCurrentEntity.position - offset; |
|
1295 |
fCurrentEntity.columnNumber += length - newlines; |
|
1296 |
if (done) { |
|
1297 |
length -= delimLen; |
|
1298 |
} |
|
1299 |
buffer.append(fCurrentEntity.ch, offset, length); |
|
1300 |
||
1301 |
// return true if string was skipped |
|
1302 |
} while (!done); |
|
1303 |
return !done; |
|
1304 |
||
1305 |
} // scanData(String,XMLString) |
|
1306 |
||
1307 |
/** |
|
1308 |
* Skips a character appearing immediately on the input. |
|
1309 |
* <p> |
|
1310 |
* <strong>Note:</strong> The character is consumed only if it matches |
|
1311 |
* the specified character. |
|
1312 |
* |
|
1313 |
* @param c The character to skip. |
|
1314 |
* |
|
1315 |
* @return Returns true if the character was skipped. |
|
1316 |
* |
|
1317 |
* @throws IOException Thrown if i/o error occurs. |
|
1318 |
* @throws EOFException Thrown on end of file. |
|
1319 |
*/ |
|
1320 |
public boolean skipChar(int c) throws IOException { |
|
1321 |
||
1322 |
// load more characters, if needed |
|
1323 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1324 |
load(0, true, true); |
6 | 1325 |
} |
1326 |
||
1327 |
// skip character |
|
1328 |
int cc = fCurrentEntity.ch[fCurrentEntity.position]; |
|
1329 |
if (cc == c) { |
|
1330 |
fCurrentEntity.position++; |
|
1331 |
if (c == '\n') { |
|
1332 |
fCurrentEntity.lineNumber++; |
|
1333 |
fCurrentEntity.columnNumber = 1; |
|
1334 |
} |
|
1335 |
else { |
|
1336 |
fCurrentEntity.columnNumber++; |
|
1337 |
} |
|
1338 |
return true; |
|
1339 |
} |
|
1340 |
else if (c == '\n' && ((cc == 0x2028 || cc == 0x85) && fCurrentEntity.isExternal())) { |
|
1341 |
fCurrentEntity.position++; |
|
1342 |
fCurrentEntity.lineNumber++; |
|
1343 |
fCurrentEntity.columnNumber = 1; |
|
1344 |
return true; |
|
1345 |
} |
|
1346 |
else if (c == '\n' && (cc == '\r' ) && fCurrentEntity.isExternal()) { |
|
1347 |
// handle newlines |
|
1348 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
1349 |
fCurrentEntity.ch[0] = (char)cc; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1350 |
load(1, false, true); |
6 | 1351 |
} |
1352 |
int ccc = fCurrentEntity.ch[++fCurrentEntity.position]; |
|
1353 |
if (ccc == '\n' || ccc == 0x85) { |
|
1354 |
fCurrentEntity.position++; |
|
1355 |
} |
|
1356 |
fCurrentEntity.lineNumber++; |
|
1357 |
fCurrentEntity.columnNumber = 1; |
|
1358 |
return true; |
|
1359 |
} |
|
1360 |
||
1361 |
// character was not skipped |
|
1362 |
return false; |
|
1363 |
||
1364 |
} // skipChar(int):boolean |
|
1365 |
||
1366 |
/** |
|
1367 |
* Skips space characters appearing immediately on the input. |
|
1368 |
* <p> |
|
1369 |
* <strong>Note:</strong> The characters are consumed only if they are |
|
1370 |
* space characters. |
|
1371 |
* |
|
1372 |
* @return Returns true if at least one space character was skipped. |
|
1373 |
* |
|
1374 |
* @throws IOException Thrown if i/o error occurs. |
|
1375 |
* @throws EOFException Thrown on end of file. |
|
1376 |
* |
|
1377 |
* @see com.sun.org.apache.xerces.internal.util.XMLChar#isSpace |
|
1378 |
* @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11Space |
|
1379 |
*/ |
|
1380 |
public boolean skipSpaces() throws IOException { |
|
1381 |
||
1382 |
// load more characters, if needed |
|
1383 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1384 |
load(0, true, true); |
6 | 1385 |
} |
1386 |
||
1387 |
||
1388 |
//we are doing this check only in skipSpace() because it is called by |
|
1389 |
//fMiscDispatcher and we want the parser to exit gracefully when document |
|
1390 |
//is well-formed. |
|
1391 |
//it is possible that end of document is reached and |
|
1392 |
//fCurrentEntity becomes null |
|
1393 |
//nothing was read so entity changed 'false' should be returned. |
|
1394 |
if(fCurrentEntity == null){ |
|
1395 |
return false ; |
|
1396 |
} |
|
1397 |
||
1398 |
// skip spaces |
|
1399 |
int c = fCurrentEntity.ch[fCurrentEntity.position]; |
|
1400 |
||
1401 |
// External -- Match: S + 0x85 + 0x2028, and perform end of line normalization |
|
1402 |
if (fCurrentEntity.isExternal()) { |
|
1403 |
if (XML11Char.isXML11Space(c)) { |
|
1404 |
do { |
|
1405 |
boolean entityChanged = false; |
|
1406 |
// handle newlines |
|
1407 |
if (c == '\n' || c == '\r' || c == 0x85 || c == 0x2028) { |
|
1408 |
fCurrentEntity.lineNumber++; |
|
1409 |
fCurrentEntity.columnNumber = 1; |
|
1410 |
if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
1411 |
fCurrentEntity.ch[0] = (char)c; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1412 |
entityChanged = load(1, true, true); |
6 | 1413 |
if (!entityChanged) { |
1414 |
// the load change the position to be 1, |
|
1415 |
// need to restore it when entity not changed |
|
1416 |
fCurrentEntity.startPosition = 0; |
|
1417 |
fCurrentEntity.position = 0; |
|
1418 |
} else if(fCurrentEntity == null){ |
|
1419 |
return true ; |
|
1420 |
} |
|
1421 |
||
1422 |
} |
|
1423 |
if (c == '\r') { |
|
1424 |
// REVISIT: Does this need to be updated to fix the |
|
1425 |
// #x0D ^#x0A newline normalization problem? -Ac |
|
1426 |
int cc = fCurrentEntity.ch[++fCurrentEntity.position]; |
|
1427 |
if (cc != '\n' && cc != 0x85 ) { |
|
1428 |
fCurrentEntity.position--; |
|
1429 |
} |
|
1430 |
} |
|
1431 |
} |
|
1432 |
else { |
|
1433 |
fCurrentEntity.columnNumber++; |
|
1434 |
} |
|
1435 |
// load more characters, if needed |
|
1436 |
if (!entityChanged) |
|
1437 |
fCurrentEntity.position++; |
|
1438 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1439 |
load(0, true, true); |
6 | 1440 |
|
1441 |
if(fCurrentEntity == null){ |
|
1442 |
return true ; |
|
1443 |
} |
|
1444 |
||
1445 |
} |
|
1446 |
} while (XML11Char.isXML11Space(c = fCurrentEntity.ch[fCurrentEntity.position])); |
|
1447 |
return true; |
|
1448 |
} |
|
1449 |
} |
|
1450 |
// Internal -- Match: S (only) |
|
1451 |
else if (XMLChar.isSpace(c)) { |
|
1452 |
do { |
|
1453 |
boolean entityChanged = false; |
|
1454 |
// handle newlines |
|
1455 |
if (c == '\n') { |
|
1456 |
fCurrentEntity.lineNumber++; |
|
1457 |
fCurrentEntity.columnNumber = 1; |
|
1458 |
if (fCurrentEntity.position == fCurrentEntity.count - 1) { |
|
1459 |
fCurrentEntity.ch[0] = (char)c; |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1460 |
entityChanged = load(1, true, true); |
6 | 1461 |
if (!entityChanged) { |
1462 |
// the load change the position to be 1, |
|
1463 |
// need to restore it when entity not changed |
|
1464 |
fCurrentEntity.startPosition = 0; |
|
1465 |
fCurrentEntity.position = 0; |
|
1466 |
} else if(fCurrentEntity == null){ |
|
1467 |
return true ; |
|
1468 |
} |
|
1469 |
} |
|
1470 |
} |
|
1471 |
else { |
|
1472 |
fCurrentEntity.columnNumber++; |
|
1473 |
} |
|
1474 |
// load more characters, if needed |
|
1475 |
if (!entityChanged) |
|
1476 |
fCurrentEntity.position++; |
|
1477 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1478 |
load(0, true, true); |
6 | 1479 |
|
1480 |
if(fCurrentEntity == null){ |
|
1481 |
return true ; |
|
1482 |
} |
|
1483 |
||
1484 |
} |
|
1485 |
} while (XMLChar.isSpace(c = fCurrentEntity.ch[fCurrentEntity.position])); |
|
1486 |
return true; |
|
1487 |
} |
|
1488 |
||
1489 |
// no spaces were found |
|
1490 |
return false; |
|
1491 |
||
1492 |
} // skipSpaces():boolean |
|
1493 |
||
1494 |
/** |
|
1495 |
* Skips the specified string appearing immediately on the input. |
|
1496 |
* <p> |
|
1497 |
* <strong>Note:</strong> The characters are consumed only if they are |
|
1498 |
* space characters. |
|
1499 |
* |
|
1500 |
* @param s The string to skip. |
|
1501 |
* |
|
1502 |
* @return Returns true if the string was skipped. |
|
1503 |
* |
|
1504 |
* @throws IOException Thrown if i/o error occurs. |
|
1505 |
* @throws EOFException Thrown on end of file. |
|
1506 |
*/ |
|
1507 |
public boolean skipString(String s) throws IOException { |
|
1508 |
||
1509 |
// load more characters, if needed |
|
1510 |
if (fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1511 |
load(0, true, true); |
6 | 1512 |
} |
1513 |
||
1514 |
// skip string |
|
1515 |
final int length = s.length(); |
|
1516 |
for (int i = 0; i < length; i++) { |
|
1517 |
char c = fCurrentEntity.ch[fCurrentEntity.position++]; |
|
1518 |
if (c != s.charAt(i)) { |
|
1519 |
fCurrentEntity.position -= i + 1; |
|
1520 |
return false; |
|
1521 |
} |
|
1522 |
if (i < length - 1 && fCurrentEntity.position == fCurrentEntity.count) { |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1523 |
invokeListeners(0); |
6 | 1524 |
System.arraycopy(fCurrentEntity.ch, fCurrentEntity.count - i - 1, fCurrentEntity.ch, 0, i + 1); |
1525 |
// REVISIT: Can a string to be skipped cross an |
|
1526 |
// entity boundary? -Ac |
|
22140
f2634f2bc36c
8027359: XML parser returns incorrect parsing results
joehw
parents:
12457
diff
changeset
|
1527 |
if (load(i + 1, false, false)) { |
6 | 1528 |
fCurrentEntity.startPosition -= i + 1; |
1529 |
fCurrentEntity.position -= i + 1; |
|
1530 |
return false; |
|
1531 |
} |
|
1532 |
} |
|
1533 |
} |
|
1534 |
fCurrentEntity.columnNumber += length; |
|
1535 |
return true; |
|
1536 |
||
1537 |
} // skipString(String):boolean |
|
1538 |
||
1539 |
} // class XML11EntityScanner |