mirror of
https://github.com/python/cpython.git
synced 2024-11-26 19:34:19 +08:00
00ee7baf49
which unfortunately means the errors from the bytes type change somewhat: bytes([300]) still raises a ValueError, but bytes([10**100]) now raises a TypeError (either that, or bytes(1.0) also raises a ValueError -- PyNumber_AsSsize_t() can only raise one type of exception.) Merged revisions 51188-51433 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r51189 | kurt.kaiser | 2006-08-10 19:11:09 +0200 (Thu, 10 Aug 2006) | 4 lines Retrieval of previous shell command was not always preserving indentation since 1.2a1) Patch 1528468 Tal Einat. ........ r51190 | guido.van.rossum | 2006-08-10 19:41:07 +0200 (Thu, 10 Aug 2006) | 3 lines Chris McDonough's patch to defend against certain DoS attacks on FieldStorage. SF bug #1112549. ........ r51191 | guido.van.rossum | 2006-08-10 19:42:50 +0200 (Thu, 10 Aug 2006) | 2 lines News item for SF bug 1112549. ........ r51192 | guido.van.rossum | 2006-08-10 20:09:25 +0200 (Thu, 10 Aug 2006) | 2 lines Fix title -- it's rc1, not beta3. ........ r51194 | martin.v.loewis | 2006-08-10 21:04:00 +0200 (Thu, 10 Aug 2006) | 3 lines Update dangling references to the 3.2 database to mention that this is UCD 4.1 now. ........ r51195 | tim.peters | 2006-08-11 00:45:34 +0200 (Fri, 11 Aug 2006) | 6 lines Followup to bug #1069160. PyThreadState_SetAsyncExc(): internal correctness changes wrt refcount safety and deadlock avoidance. Also added a basic test case (relying on ctypes) and repaired the docs. ........ r51196 | tim.peters | 2006-08-11 00:48:45 +0200 (Fri, 11 Aug 2006) | 2 lines Whitespace normalization. ........ r51197 | tim.peters | 2006-08-11 01:22:13 +0200 (Fri, 11 Aug 2006) | 5 lines Whitespace normalization broke test_cgi, because a line of quoted test data relied on preserving a single trailing blank. Changed the string from raw to regular, and forced in the trailing blank via an explicit \x20 escape. ........ r51198 | tim.peters | 2006-08-11 02:49:01 +0200 (Fri, 11 Aug 2006) | 10 lines test_PyThreadState_SetAsyncExc(): This is failing on some 64-bit boxes. I have no idea what the ctypes docs mean by "integers", and blind-guessing here that it intended to mean the signed C "int" type, in which case perhaps I can repair this by feeding the thread id argument to type ctypes.c_long(). Also made the worker thread daemonic, so it doesn't hang Python shutdown if the test continues to fail. ........ r51199 | tim.peters | 2006-08-11 05:49:10 +0200 (Fri, 11 Aug 2006) | 6 lines force_test_exit(): This has been completely ineffective at stopping test_signal from hanging forever on the Tru64 buildbot. That could be because there's no such thing as signal.SIGALARM. Changed to the idiotic (but standard) signal.SIGALRM instead, and added some more debug output. ........ r51202 | neal.norwitz | 2006-08-11 08:09:41 +0200 (Fri, 11 Aug 2006) | 6 lines Fix the failures on cygwin (2006-08-10 fixed the actual locking issue). The first hunk changes the colon to an ! like other Windows variants. We need to always wait on the child so the lock gets released and no other tests fail. This is the try/finally in the second hunk. ........ r51205 | georg.brandl | 2006-08-11 09:15:38 +0200 (Fri, 11 Aug 2006) | 3 lines Add Chris McDonough (latest cgi.py patch) ........ r51206 | georg.brandl | 2006-08-11 09:26:10 +0200 (Fri, 11 Aug 2006) | 3 lines logging's atexit hook now runs even if the rest of the module has already been cleaned up. ........ r51212 | thomas.wouters | 2006-08-11 17:02:39 +0200 (Fri, 11 Aug 2006) | 4 lines Add ignore of *.pyc and *.pyo to Lib/xml/etree/. ........ r51215 | thomas.heller | 2006-08-11 21:55:35 +0200 (Fri, 11 Aug 2006) | 7 lines When a ctypes C callback function is called, zero out the result storage before converting the result to C data. See the comment in the code for details. Provide a better context for errors when the conversion of a callback function's result cannot be converted. ........ r51218 | neal.norwitz | 2006-08-12 03:43:40 +0200 (Sat, 12 Aug 2006) | 6 lines Klocwork made another run and found a bunch more problems. This is the first batch of fixes that should be easy to verify based on context. This fixes problem numbers: 220 (ast), 323-324 (symtable), 321-322 (structseq), 215 (array), 210 (hotshot), 182 (codecs), 209 (etree). ........ r51219 | neal.norwitz | 2006-08-12 03:45:47 +0200 (Sat, 12 Aug 2006) | 9 lines Even though _Py_Mangle() isn't truly public anyone can call it and there was no verification that privateobj was a PyString. If it wasn't a string, this could have allowed a NULL pointer to creep in below and crash. I wonder if this should be PyString_CheckExact? Must identifiers be strings or can they be subclasses? Klocwork #275 ........ r51220 | neal.norwitz | 2006-08-12 03:46:42 +0200 (Sat, 12 Aug 2006) | 5 lines It's highly unlikely, though possible for PyEval_Get*() to return NULLs. So be safe and do an XINCREF. Klocwork # 221-222. ........ r51221 | neal.norwitz | 2006-08-12 03:47:59 +0200 (Sat, 12 Aug 2006) | 7 lines This code is actually not used unless WITHOUT_COMPLEX is defined. However, there was no error checking that PyFloat_FromDouble returned a valid pointer. I believe this change is correct as it seemed to follow other code in the area. Klocwork # 292. ........ r51222 | neal.norwitz | 2006-08-12 03:49:12 +0200 (Sat, 12 Aug 2006) | 5 lines Handle NULL nodes while parsing. I'm not entirely sure this is correct. There might be something else that needs to be done to setup the error. Klocwork #295. ........ r51223 | neal.norwitz | 2006-08-12 03:50:38 +0200 (Sat, 12 Aug 2006) | 6 lines If _stat_float_times is false, we will try to INCREF ival which could be NULL. Return early in that case. The caller checks for PyErr_Occurred so this should be ok. Klocwork #297 ........ r51224 | neal.norwitz | 2006-08-12 03:51:12 +0200 (Sat, 12 Aug 2006) | 3 lines Move the assert which checks for a NULL pointer first. Klocwork #274. ........ r51225 | neal.norwitz | 2006-08-12 03:53:28 +0200 (Sat, 12 Aug 2006) | 5 lines Try to handle a malloc failure. I'm not entirely sure this is correct. There might be something else we need to do to handle the exception. Klocwork # 212-213 ........ r51226 | neal.norwitz | 2006-08-12 03:57:47 +0200 (Sat, 12 Aug 2006) | 6 lines I'm not sure why this code allocates this string for the error message. I think it would be better to always use snprintf and have the format limit the size of the name appropriately (like %.200s). Klocwork #340 ........ r51227 | neal.norwitz | 2006-08-12 04:06:34 +0200 (Sat, 12 Aug 2006) | 3 lines Check returned pointer is valid. Klocwork #233 ........ r51228 | neal.norwitz | 2006-08-12 04:12:30 +0200 (Sat, 12 Aug 2006) | 1 line Whoops, how did that get in there. :-) Revert all the parts of 51227 that were not supposed to go it. Only Modules/_ctypes/cfields.c was supposed to be changed ........ r51229 | neal.norwitz | 2006-08-12 04:33:36 +0200 (Sat, 12 Aug 2006) | 4 lines Don't deref v if it's NULL. Klocwork #214 ........ r51230 | neal.norwitz | 2006-08-12 05:16:54 +0200 (Sat, 12 Aug 2006) | 5 lines Check return of PyMem_MALLOC (garbage) is non-NULL. Check seq in both portions of if/else. Klocwork #289-290. ........ r51231 | neal.norwitz | 2006-08-12 05:17:41 +0200 (Sat, 12 Aug 2006) | 4 lines PyModule_GetDict() can fail, produce fatal errors if this happens on startup. Klocwork #298-299. ........ r51232 | neal.norwitz | 2006-08-12 05:18:50 +0200 (Sat, 12 Aug 2006) | 5 lines Verify verdat which is returned from malloc is not NULL. Ensure we don't pass NULL to free. Klocwork #306 (at least the first part, checking malloc) ........ r51233 | tim.peters | 2006-08-12 06:42:47 +0200 (Sat, 12 Aug 2006) | 35 lines test_signal: Signal handling on the Tru64 buildbot appears to be utterly insane. Plug some theoretical insecurities in the test script: - Verify that the SIGALRM handler was actually installed. - Don't call alarm() before the handler is installed. - Move everything that can fail inside the try/finally, so the test cleans up after itself more often. - Try sending all the expected signals in force_test_exit(), not just SIGALRM. Since that was fixed to actually send SIGALRM (instead of invisibly dying with an AttributeError), we've seen that sending SIGALRM alone does not stop this from hanging. - Move the "kill the child" business into the finally clause, so the child doesn't survive test failure to send SIGALRM to other tests later (there are also baffling SIGALRM-related failures in test_socket). - Cancel the alarm in the finally clause -- if the test dies early, we again don't want SIGALRM showing up to confuse a later test. Alas, this still relies on timing luck wrt the spawned script that sends the test signals, but it's hard to see how waiting for seconds can so often be so unlucky. test_threadedsignals: curiously, this test never fails on Tru64, but doesn't normally signal SIGALRM. Anyway, fixed an obvious (but probably inconsequential) logic error. ........ r51234 | tim.peters | 2006-08-12 07:17:41 +0200 (Sat, 12 Aug 2006) | 8 lines Ah, fudge. One of the prints here actually "shouldn't be" protected by "if verbose:", which caused the test to fail on all non-Windows boxes. Note that I deliberately didn't convert this to unittest yet, because I expect it would be even harder to debug this on Tru64 after conversion. ........ r51235 | georg.brandl | 2006-08-12 10:32:02 +0200 (Sat, 12 Aug 2006) | 3 lines Repair logging test spew caused by rev. 51206. ........ r51236 | neal.norwitz | 2006-08-12 19:03:09 +0200 (Sat, 12 Aug 2006) | 8 lines Patch #1538606, Patch to fix __index__() clipping. I modified this patch some by fixing style, some error checking, and adding XXX comments. This patch requires review and some changes are to be expected. I'm checking in now to get the greatest possible review and establish a baseline for moving forward. I don't want this to hold up release if possible. ........ r51238 | neal.norwitz | 2006-08-12 20:44:06 +0200 (Sat, 12 Aug 2006) | 10 lines Fix a couple of bugs exposed by the new __index__ code. The 64-bit buildbots were failing due to inappropriate clipping of numbers larger than 2**31 with new-style classes. (typeobject.c) In reviewing the code for classic classes, there were 2 problems. Any negative value return could be returned. Always return -1 if there was an error. Also make the checks similar with the new-style classes. I believe this is correct for 32 and 64 bit boxes, including Windows64. Add a test of classic classes too. ........ r51240 | neal.norwitz | 2006-08-13 02:20:49 +0200 (Sun, 13 Aug 2006) | 1 line SF bug #1539336, distutils example code missing ........ r51245 | neal.norwitz | 2006-08-13 20:10:10 +0200 (Sun, 13 Aug 2006) | 6 lines Move/copy assert for tstate != NULL before first use. Verify that PyEval_Get{Globals,Locals} returned valid pointers. Klocwork 231-232 ........ r51246 | neal.norwitz | 2006-08-13 20:10:28 +0200 (Sun, 13 Aug 2006) | 5 lines Handle a whole lot of failures from PyString_FromInternedString(). Should fix most of Klocwork 234-272. ........ r51247 | neal.norwitz | 2006-08-13 20:10:47 +0200 (Sun, 13 Aug 2006) | 8 lines cpathname could be NULL if it was longer than MAXPATHLEN. Don't try to write the .pyc to NULL. Check results of PyList_GetItem() and PyModule_GetDict() are not NULL. Klocwork 282, 283, 285 ........ r51248 | neal.norwitz | 2006-08-13 20:11:08 +0200 (Sun, 13 Aug 2006) | 6 lines Fix segfault when doing string formatting on subclasses of long if __oct__, __hex__ don't return a string. Klocwork 308 ........ r51250 | neal.norwitz | 2006-08-13 20:11:27 +0200 (Sun, 13 Aug 2006) | 5 lines Check return result of PyModule_GetDict(). Fix a bunch of refleaks in the init of the module. This would only be found when running python -v. ........ r51251 | neal.norwitz | 2006-08-13 20:11:43 +0200 (Sun, 13 Aug 2006) | 5 lines Handle malloc and fopen failures more gracefully. Klocwork 180-181 ........ r51252 | neal.norwitz | 2006-08-13 20:12:03 +0200 (Sun, 13 Aug 2006) | 7 lines It's very unlikely, though possible that source is not a string. Verify that PyString_AsString() returns a valid pointer. (The problem can arise when zlib.decompress doesn't return a string.) Klocwork 346 ........ r51253 | neal.norwitz | 2006-08-13 20:12:26 +0200 (Sun, 13 Aug 2006) | 5 lines Handle failures from lookup. Klocwork 341-342 ........ r51254 | neal.norwitz | 2006-08-13 20:12:45 +0200 (Sun, 13 Aug 2006) | 6 lines Handle failure from PyModule_GetDict() (Klocwork 208). Fix a bunch of refleaks in the init of the module. This would only be found when running python -v. ........ r51255 | neal.norwitz | 2006-08-13 20:13:02 +0200 (Sun, 13 Aug 2006) | 4 lines Really address the issue of where to place the assert for leftblock. (Followup of Klocwork 274) ........ r51256 | neal.norwitz | 2006-08-13 20:13:36 +0200 (Sun, 13 Aug 2006) | 4 lines Handle malloc failure. Klocwork 281 ........ r51258 | neal.norwitz | 2006-08-13 20:40:39 +0200 (Sun, 13 Aug 2006) | 4 lines Handle alloca failures. Klocwork 225-228 ........ r51259 | neal.norwitz | 2006-08-13 20:41:15 +0200 (Sun, 13 Aug 2006) | 1 line Get rid of compiler warning ........ r51261 | neal.norwitz | 2006-08-14 02:51:15 +0200 (Mon, 14 Aug 2006) | 1 line Ignore pgen.exe and kill_python.exe for cygwin ........ r51262 | neal.norwitz | 2006-08-14 02:59:03 +0200 (Mon, 14 Aug 2006) | 4 lines Can't return NULL from a void function. If there is a memory error, about the best we can do is call PyErr_WriteUnraisable and go on. We won't be able to do the call below either, so verify delstr is valid. ........ r51263 | neal.norwitz | 2006-08-14 03:49:54 +0200 (Mon, 14 Aug 2006) | 1 line Update purify doc some. ........ r51264 | thomas.heller | 2006-08-14 09:13:05 +0200 (Mon, 14 Aug 2006) | 2 lines Remove unused, buggy test function. Fixes klockwork issue #207. ........ r51265 | thomas.heller | 2006-08-14 09:14:09 +0200 (Mon, 14 Aug 2006) | 2 lines Check for NULL return value from new_CArgObject(). Fixes klockwork issues #183, #184, #185. ........ r51266 | thomas.heller | 2006-08-14 09:50:14 +0200 (Mon, 14 Aug 2006) | 2 lines Check for NULL return value of GenericCData_new(). Fixes klockwork issues #188, #189. ........ r51274 | thomas.heller | 2006-08-14 12:02:24 +0200 (Mon, 14 Aug 2006) | 2 lines Revert the change that tries to zero out a closure's result storage area because the size if unknown in source/callproc.c. ........ r51276 | marc-andre.lemburg | 2006-08-14 12:55:19 +0200 (Mon, 14 Aug 2006) | 11 lines Slightly revised version of patch #1538956: Replace UnicodeDecodeErrors raised during == and != compares of Unicode and other objects with a new UnicodeWarning. All other comparisons continue to raise exceptions. Exceptions other than UnicodeDecodeErrors are also left untouched. ........ r51277 | thomas.heller | 2006-08-14 13:17:48 +0200 (Mon, 14 Aug 2006) | 13 lines Apply the patch #1532975 plus ideas from the patch #1533481. ctypes instances no longer have the internal and undocumented '_as_parameter_' attribute which was used to adapt them to foreign function calls; this mechanism is replaced by a function pointer in the type's stgdict. In the 'from_param' class methods, try the _as_parameter_ attribute if other conversions are not possible. This makes the documented _as_parameter_ mechanism work as intended. Change the ctypes version number to 1.0.1. ........ r51278 | marc-andre.lemburg | 2006-08-14 13:44:34 +0200 (Mon, 14 Aug 2006) | 3 lines Readd NEWS items that were accidentally removed by r51276. ........ r51279 | georg.brandl | 2006-08-14 14:36:06 +0200 (Mon, 14 Aug 2006) | 3 lines Improve markup in PyUnicode_RichCompare. ........ r51280 | marc-andre.lemburg | 2006-08-14 14:57:27 +0200 (Mon, 14 Aug 2006) | 3 lines Correct an accidentally removed previous patch. ........ r51281 | thomas.heller | 2006-08-14 18:17:41 +0200 (Mon, 14 Aug 2006) | 3 lines Patch #1536908: Add support for AMD64 / OpenBSD. Remove the -no-stack-protector compiler flag for OpenBSD as it has been reported to be unneeded. ........ r51282 | thomas.heller | 2006-08-14 18:20:04 +0200 (Mon, 14 Aug 2006) | 1 line News item for rev 51281. ........ r51283 | georg.brandl | 2006-08-14 22:25:39 +0200 (Mon, 14 Aug 2006) | 3 lines Fix refleak introduced in rev. 51248. ........ r51284 | georg.brandl | 2006-08-14 23:34:08 +0200 (Mon, 14 Aug 2006) | 5 lines Make tabnanny recognize IndentationErrors raised by tokenize. Add a test to test_inspect to make sure indented source is recognized correctly. (fixes #1224621) ........ r51285 | georg.brandl | 2006-08-14 23:42:55 +0200 (Mon, 14 Aug 2006) | 3 lines Patch #1535500: fix segfault in BZ2File.writelines and make sure it raises the correct exceptions. ........ r51287 | georg.brandl | 2006-08-14 23:45:32 +0200 (Mon, 14 Aug 2006) | 3 lines Add an additional test: BZ2File write methods should raise IOError when file is read-only. ........ r51289 | georg.brandl | 2006-08-14 23:55:28 +0200 (Mon, 14 Aug 2006) | 3 lines Patch #1536071: trace.py should now find the full module name of a file correctly even on Windows. ........ r51290 | georg.brandl | 2006-08-15 00:01:24 +0200 (Tue, 15 Aug 2006) | 3 lines Cookie.py shouldn't "bogusly" use string._idmap. ........ r51291 | georg.brandl | 2006-08-15 00:10:24 +0200 (Tue, 15 Aug 2006) | 3 lines Patch #1511317: don't crash on invalid hostname info ........ r51292 | tim.peters | 2006-08-15 02:25:04 +0200 (Tue, 15 Aug 2006) | 2 lines Whitespace normalization. ........ r51293 | neal.norwitz | 2006-08-15 06:14:57 +0200 (Tue, 15 Aug 2006) | 3 lines Georg fixed one of my bugs, so I'll repay him with 2 NEWS entries. Now we're even. :-) ........ r51295 | neal.norwitz | 2006-08-15 06:58:28 +0200 (Tue, 15 Aug 2006) | 8 lines Fix the test for SocketServer so it should pass on cygwin and not fail sporadically on other platforms. This is really a band-aid that doesn't fix the underlying issue in SocketServer. It's not clear if it's worth it to fix SocketServer, however, I opened a bug to track it: http://python.org/sf/1540386 ........ r51296 | neal.norwitz | 2006-08-15 06:59:30 +0200 (Tue, 15 Aug 2006) | 3 lines Update the docstring to use a version a little newer than 1999. This was taken from a Debian patch. Should we update the version for each release? ........ r51298 | neal.norwitz | 2006-08-15 08:29:03 +0200 (Tue, 15 Aug 2006) | 2 lines Subclasses of int/long are allowed to define an __index__. ........ r51300 | thomas.heller | 2006-08-15 15:07:21 +0200 (Tue, 15 Aug 2006) | 1 line Check for NULL return value from new_CArgObject calls. ........ r51303 | kurt.kaiser | 2006-08-16 05:15:26 +0200 (Wed, 16 Aug 2006) | 2 lines The 'with' statement is now a Code Context block opener ........ r51304 | anthony.baxter | 2006-08-16 05:42:26 +0200 (Wed, 16 Aug 2006) | 1 line preparing for 2.5c1 ........ r51305 | anthony.baxter | 2006-08-16 05:58:37 +0200 (Wed, 16 Aug 2006) | 1 line preparing for 2.5c1 - no, really this time ........ r51306 | kurt.kaiser | 2006-08-16 07:01:42 +0200 (Wed, 16 Aug 2006) | 9 lines Patch #1540892: site.py Quitter() class attempts to close sys.stdin before raising SystemExit, allowing IDLE to honor quit() and exit(). M Lib/site.py M Lib/idlelib/PyShell.py M Lib/idlelib/CREDITS.txt M Lib/idlelib/NEWS.txt M Misc/NEWS ........ r51307 | ka-ping.yee | 2006-08-16 09:02:50 +0200 (Wed, 16 Aug 2006) | 6 lines Update code and tests to support the 'bytes_le' attribute (for little-endian byte order on Windows), and to work around clocks with low resolution yielding duplicate UUIDs. Anthony Baxter has approved this change. ........ r51308 | kurt.kaiser | 2006-08-16 09:04:17 +0200 (Wed, 16 Aug 2006) | 2 lines Get quit() and exit() to work cleanly when not using subprocess. ........ r51309 | marc-andre.lemburg | 2006-08-16 10:13:26 +0200 (Wed, 16 Aug 2006) | 2 lines Revert to having static version numbers again. ........ r51310 | martin.v.loewis | 2006-08-16 14:55:10 +0200 (Wed, 16 Aug 2006) | 2 lines Build _hashlib on Windows. Build OpenSSL with masm assembler code. Fixes #1535502. ........ r51311 | thomas.heller | 2006-08-16 15:03:11 +0200 (Wed, 16 Aug 2006) | 6 lines Add commented assert statements to check that the result of PyObject_stgdict() and PyType_stgdict() calls are non-NULL before dereferencing the result. Hopefully this fixes what klocwork is complaining about. Fix a few other nits as well. ........ r51312 | anthony.baxter | 2006-08-16 15:08:25 +0200 (Wed, 16 Aug 2006) | 1 line news entry for 51307 ........ r51313 | andrew.kuchling | 2006-08-16 15:22:20 +0200 (Wed, 16 Aug 2006) | 1 line Add UnicodeWarning ........ r51314 | andrew.kuchling | 2006-08-16 15:41:52 +0200 (Wed, 16 Aug 2006) | 1 line Bump document version to 1.0; remove pystone paragraph ........ r51315 | andrew.kuchling | 2006-08-16 15:51:32 +0200 (Wed, 16 Aug 2006) | 1 line Link to docs; remove an XXX comment ........ r51316 | martin.v.loewis | 2006-08-16 15:58:51 +0200 (Wed, 16 Aug 2006) | 1 line Make cl build step compile-only (/c). Remove libs from source list. ........ r51317 | thomas.heller | 2006-08-16 16:07:44 +0200 (Wed, 16 Aug 2006) | 5 lines The __repr__ method of a NULL py_object does no longer raise an exception. Remove a stray '?' character from the exception text when the value is retrieved of such an object. Includes tests. ........ r51318 | andrew.kuchling | 2006-08-16 16:18:23 +0200 (Wed, 16 Aug 2006) | 1 line Update bug/patch counts ........ r51319 | andrew.kuchling | 2006-08-16 16:21:14 +0200 (Wed, 16 Aug 2006) | 1 line Wording/typo fixes ........ r51320 | thomas.heller | 2006-08-16 17:10:12 +0200 (Wed, 16 Aug 2006) | 9 lines Remove the special casing of Py_None when converting the return value of the Python part of a callback function to C. If it cannot be converted, call PyErr_WriteUnraisable with the exception we got. Before, arbitrary data has been passed to the calling C code in this case. (I'm not really sure the NEWS entry is understandable, but I cannot find better words) ........ r51321 | marc-andre.lemburg | 2006-08-16 18:11:01 +0200 (Wed, 16 Aug 2006) | 2 lines Add NEWS item mentioning the reverted distutils version number patch. ........ r51322 | fredrik.lundh | 2006-08-16 18:47:07 +0200 (Wed, 16 Aug 2006) | 5 lines SF#1534630 ignore data that arrives before the opening start tag ........ r51324 | andrew.kuchling | 2006-08-16 19:11:18 +0200 (Wed, 16 Aug 2006) | 1 line Grammar fix ........ r51328 | thomas.heller | 2006-08-16 20:02:11 +0200 (Wed, 16 Aug 2006) | 12 lines Tutorial: Clarify somewhat how parameters are passed to functions (especially explain what integer means). Correct the table - Python integers and longs can both be used. Further clarification to the table comparing ctypes types, Python types, and C types. Reference: Replace integer by C ``int`` where it makes sense. ........ r51329 | kurt.kaiser | 2006-08-16 23:45:59 +0200 (Wed, 16 Aug 2006) | 8 lines File menu hotkeys: there were three 'p' assignments. Reassign the 'Save Copy As' and 'Print' hotkeys to 'y' and 't'. Change the Shell menu hotkey from 's' to 'l'. M Bindings.py M PyShell.py M NEWS.txt ........ r51330 | neil.schemenauer | 2006-08-17 01:38:05 +0200 (Thu, 17 Aug 2006) | 3 lines Fix a bug in the ``compiler`` package that caused invalid code to be generated for generator expressions. ........ r51342 | martin.v.loewis | 2006-08-17 21:19:32 +0200 (Thu, 17 Aug 2006) | 3 lines Merge 51340 and 51341 from 2.5 branch: Leave tk build directory to restore original path. Invoke debug mk1mf.pl after running Configure. ........ r51354 | martin.v.loewis | 2006-08-18 05:47:18 +0200 (Fri, 18 Aug 2006) | 3 lines Bug #1541863: uuid.uuid1 failed to generate unique identifiers on systems with low clock resolution. ........ r51355 | neal.norwitz | 2006-08-18 05:57:54 +0200 (Fri, 18 Aug 2006) | 1 line Add template for 2.6 on HEAD ........ r51356 | neal.norwitz | 2006-08-18 06:01:38 +0200 (Fri, 18 Aug 2006) | 1 line More post-release wibble ........ r51357 | neal.norwitz | 2006-08-18 06:58:33 +0200 (Fri, 18 Aug 2006) | 1 line Try to get Windows bots working again ........ r51358 | neal.norwitz | 2006-08-18 07:10:00 +0200 (Fri, 18 Aug 2006) | 1 line Try to get Windows bots working again. Take 2 ........ r51359 | neal.norwitz | 2006-08-18 07:39:20 +0200 (Fri, 18 Aug 2006) | 1 line Try to get Unix bots install working again. ........ r51360 | neal.norwitz | 2006-08-18 07:41:46 +0200 (Fri, 18 Aug 2006) | 1 line Set version to 2.6a0, seems more consistent. ........ r51362 | neal.norwitz | 2006-08-18 08:14:52 +0200 (Fri, 18 Aug 2006) | 1 line More version wibble ........ r51364 | georg.brandl | 2006-08-18 09:27:59 +0200 (Fri, 18 Aug 2006) | 4 lines Bug #1541682: Fix example in the "Refcount details" API docs. Additionally, remove a faulty example showing PySequence_SetItem applied to a newly created list object and add notes that this isn't a good idea. ........ r51366 | anthony.baxter | 2006-08-18 09:29:02 +0200 (Fri, 18 Aug 2006) | 3 lines Updating IDLE's version number to match Python's (as per python-dev discussion). ........ r51367 | anthony.baxter | 2006-08-18 09:30:07 +0200 (Fri, 18 Aug 2006) | 1 line RPM specfile updates ........ r51368 | georg.brandl | 2006-08-18 09:35:47 +0200 (Fri, 18 Aug 2006) | 2 lines Typo in tp_clear docs. ........ r51378 | andrew.kuchling | 2006-08-18 15:57:13 +0200 (Fri, 18 Aug 2006) | 1 line Minor edits ........ r51379 | thomas.heller | 2006-08-18 16:38:46 +0200 (Fri, 18 Aug 2006) | 6 lines Add asserts to check for 'impossible' NULL values, with comments. In one place where I'n not 1000% sure about the non-NULL, raise a RuntimeError for safety. This should fix the klocwork issues that Neal sent me. If so, it should be applied to the release25-maint branch also. ........ r51400 | neal.norwitz | 2006-08-19 06:22:33 +0200 (Sat, 19 Aug 2006) | 5 lines Move initialization of interned strings to before allocating the object so we don't leak op. (Fixes an earlier patch to this code) Klockwork #350 ........ r51401 | neal.norwitz | 2006-08-19 06:23:04 +0200 (Sat, 19 Aug 2006) | 4 lines Move assert to after NULL check, otherwise we deref NULL in the assert. Klocwork #307 ........ r51402 | neal.norwitz | 2006-08-19 06:25:29 +0200 (Sat, 19 Aug 2006) | 2 lines SF #1542693: Remove semi-colon at end of PyImport_ImportModuleEx macro ........ r51403 | neal.norwitz | 2006-08-19 06:28:55 +0200 (Sat, 19 Aug 2006) | 6 lines Move initialization to after the asserts for non-NULL values. Klocwork 286-287. (I'm not backporting this, but if someone wants to, feel free.) ........ r51404 | neal.norwitz | 2006-08-19 06:52:03 +0200 (Sat, 19 Aug 2006) | 6 lines Handle PyString_FromInternedString() failing (unlikely, but possible). Klocwork #325 (I'm not backporting this, but if someone wants to, feel free.) ........ r51416 | georg.brandl | 2006-08-20 15:15:39 +0200 (Sun, 20 Aug 2006) | 2 lines Patch #1542948: fix urllib2 header casing issue. With new test. ........ r51428 | jeremy.hylton | 2006-08-21 18:19:37 +0200 (Mon, 21 Aug 2006) | 3 lines Move peephole optimizer to separate file. ........ r51429 | jeremy.hylton | 2006-08-21 18:20:29 +0200 (Mon, 21 Aug 2006) | 2 lines Move peephole optimizer to separate file. (Forgot .h in previous checkin.) ........ r51432 | neal.norwitz | 2006-08-21 19:59:46 +0200 (Mon, 21 Aug 2006) | 5 lines Fix bug #1543303, tarfile adds padding that breaks gunzip. Patch # 1543897. Will backport to 2.5 ........ r51433 | neal.norwitz | 2006-08-21 20:01:30 +0200 (Mon, 21 Aug 2006) | 2 lines Add assert to make Klocwork happy (#276) ........
6269 lines
188 KiB
C
6269 lines
188 KiB
C
/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
|
|
See the file COPYING for copying permission.
|
|
*/
|
|
|
|
#define XML_BUILDING_EXPAT 1
|
|
|
|
#ifdef COMPILED_FROM_DSP
|
|
#include "winconfig.h"
|
|
#elif defined(MACOS_CLASSIC)
|
|
#include "macconfig.h"
|
|
#elif defined(__amigaos4__)
|
|
#include "amigaconfig.h"
|
|
#elif defined(HAVE_EXPAT_CONFIG_H)
|
|
#include <expat_config.h>
|
|
#endif /* ndef COMPILED_FROM_DSP */
|
|
|
|
#include <stddef.h>
|
|
#include <string.h> /* memset(), memcpy() */
|
|
#include <assert.h>
|
|
|
|
#include "expat.h"
|
|
|
|
#ifdef XML_UNICODE
|
|
#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX
|
|
#define XmlConvert XmlUtf16Convert
|
|
#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding
|
|
#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS
|
|
#define XmlEncode XmlUtf16Encode
|
|
#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1))
|
|
typedef unsigned short ICHAR;
|
|
#else
|
|
#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX
|
|
#define XmlConvert XmlUtf8Convert
|
|
#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding
|
|
#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS
|
|
#define XmlEncode XmlUtf8Encode
|
|
#define MUST_CONVERT(enc, s) (!(enc)->isUtf8)
|
|
typedef char ICHAR;
|
|
#endif
|
|
|
|
|
|
#ifndef XML_NS
|
|
|
|
#define XmlInitEncodingNS XmlInitEncoding
|
|
#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding
|
|
#undef XmlGetInternalEncodingNS
|
|
#define XmlGetInternalEncodingNS XmlGetInternalEncoding
|
|
#define XmlParseXmlDeclNS XmlParseXmlDecl
|
|
|
|
#endif
|
|
|
|
#ifdef XML_UNICODE
|
|
|
|
#ifdef XML_UNICODE_WCHAR_T
|
|
#define XML_T(x) (const wchar_t)x
|
|
#define XML_L(x) L ## x
|
|
#else
|
|
#define XML_T(x) (const unsigned short)x
|
|
#define XML_L(x) x
|
|
#endif
|
|
|
|
#else
|
|
|
|
#define XML_T(x) x
|
|
#define XML_L(x) x
|
|
|
|
#endif
|
|
|
|
/* Round up n to be a multiple of sz, where sz is a power of 2. */
|
|
#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))
|
|
|
|
/* Handle the case where memmove() doesn't exist. */
|
|
#ifndef HAVE_MEMMOVE
|
|
#ifdef HAVE_BCOPY
|
|
#define memmove(d,s,l) bcopy((s),(d),(l))
|
|
#else
|
|
#error memmove does not exist on this platform, nor is a substitute available
|
|
#endif /* HAVE_BCOPY */
|
|
#endif /* HAVE_MEMMOVE */
|
|
|
|
#include "internal.h"
|
|
#include "xmltok.h"
|
|
#include "xmlrole.h"
|
|
|
|
typedef const XML_Char *KEY;
|
|
|
|
typedef struct {
|
|
KEY name;
|
|
} NAMED;
|
|
|
|
typedef struct {
|
|
NAMED **v;
|
|
unsigned char power;
|
|
size_t size;
|
|
size_t used;
|
|
const XML_Memory_Handling_Suite *mem;
|
|
} HASH_TABLE;
|
|
|
|
/* Basic character hash algorithm, taken from Python's string hash:
|
|
h = h * 1000003 ^ character, the constant being a prime number.
|
|
|
|
*/
|
|
#ifdef XML_UNICODE
|
|
#define CHAR_HASH(h, c) \
|
|
(((h) * 0xF4243) ^ (unsigned short)(c))
|
|
#else
|
|
#define CHAR_HASH(h, c) \
|
|
(((h) * 0xF4243) ^ (unsigned char)(c))
|
|
#endif
|
|
|
|
/* For probing (after a collision) we need a step size relative prime
|
|
to the hash table size, which is a power of 2. We use double-hashing,
|
|
since we can calculate a second hash value cheaply by taking those bits
|
|
of the first hash value that were discarded (masked out) when the table
|
|
index was calculated: index = hash & mask, where mask = table->size - 1.
|
|
We limit the maximum step size to table->size / 4 (mask >> 2) and make
|
|
it odd, since odd numbers are always relative prime to a power of 2.
|
|
*/
|
|
#define SECOND_HASH(hash, mask, power) \
|
|
((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2))
|
|
#define PROBE_STEP(hash, mask, power) \
|
|
((unsigned char)((SECOND_HASH(hash, mask, power)) | 1))
|
|
|
|
typedef struct {
|
|
NAMED **p;
|
|
NAMED **end;
|
|
} HASH_TABLE_ITER;
|
|
|
|
#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */
|
|
#define INIT_DATA_BUF_SIZE 1024
|
|
#define INIT_ATTS_SIZE 16
|
|
#define INIT_ATTS_VERSION 0xFFFFFFFF
|
|
#define INIT_BLOCK_SIZE 1024
|
|
#define INIT_BUFFER_SIZE 1024
|
|
|
|
#define EXPAND_SPARE 24
|
|
|
|
typedef struct binding {
|
|
struct prefix *prefix;
|
|
struct binding *nextTagBinding;
|
|
struct binding *prevPrefixBinding;
|
|
const struct attribute_id *attId;
|
|
XML_Char *uri;
|
|
int uriLen;
|
|
int uriAlloc;
|
|
} BINDING;
|
|
|
|
typedef struct prefix {
|
|
const XML_Char *name;
|
|
BINDING *binding;
|
|
} PREFIX;
|
|
|
|
typedef struct {
|
|
const XML_Char *str;
|
|
const XML_Char *localPart;
|
|
const XML_Char *prefix;
|
|
int strLen;
|
|
int uriLen;
|
|
int prefixLen;
|
|
} TAG_NAME;
|
|
|
|
/* TAG represents an open element.
|
|
The name of the element is stored in both the document and API
|
|
encodings. The memory buffer 'buf' is a separately-allocated
|
|
memory area which stores the name. During the XML_Parse()/
|
|
XMLParseBuffer() when the element is open, the memory for the 'raw'
|
|
version of the name (in the document encoding) is shared with the
|
|
document buffer. If the element is open across calls to
|
|
XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to
|
|
contain the 'raw' name as well.
|
|
|
|
A parser re-uses these structures, maintaining a list of allocated
|
|
TAG objects in a free list.
|
|
*/
|
|
typedef struct tag {
|
|
struct tag *parent; /* parent of this element */
|
|
const char *rawName; /* tagName in the original encoding */
|
|
int rawNameLength;
|
|
TAG_NAME name; /* tagName in the API encoding */
|
|
char *buf; /* buffer for name components */
|
|
char *bufEnd; /* end of the buffer */
|
|
BINDING *bindings;
|
|
} TAG;
|
|
|
|
typedef struct {
|
|
const XML_Char *name;
|
|
const XML_Char *textPtr;
|
|
int textLen; /* length in XML_Chars */
|
|
int processed; /* # of processed bytes - when suspended */
|
|
const XML_Char *systemId;
|
|
const XML_Char *base;
|
|
const XML_Char *publicId;
|
|
const XML_Char *notation;
|
|
XML_Bool open;
|
|
XML_Bool is_param;
|
|
XML_Bool is_internal; /* true if declared in internal subset outside PE */
|
|
} ENTITY;
|
|
|
|
typedef struct {
|
|
enum XML_Content_Type type;
|
|
enum XML_Content_Quant quant;
|
|
const XML_Char * name;
|
|
int firstchild;
|
|
int lastchild;
|
|
int childcnt;
|
|
int nextsib;
|
|
} CONTENT_SCAFFOLD;
|
|
|
|
#define INIT_SCAFFOLD_ELEMENTS 32
|
|
|
|
typedef struct block {
|
|
struct block *next;
|
|
int size;
|
|
XML_Char s[1];
|
|
} BLOCK;
|
|
|
|
typedef struct {
|
|
BLOCK *blocks;
|
|
BLOCK *freeBlocks;
|
|
const XML_Char *end;
|
|
XML_Char *ptr;
|
|
XML_Char *start;
|
|
const XML_Memory_Handling_Suite *mem;
|
|
} STRING_POOL;
|
|
|
|
/* The XML_Char before the name is used to determine whether
|
|
an attribute has been specified. */
|
|
typedef struct attribute_id {
|
|
XML_Char *name;
|
|
PREFIX *prefix;
|
|
XML_Bool maybeTokenized;
|
|
XML_Bool xmlns;
|
|
} ATTRIBUTE_ID;
|
|
|
|
typedef struct {
|
|
const ATTRIBUTE_ID *id;
|
|
XML_Bool isCdata;
|
|
const XML_Char *value;
|
|
} DEFAULT_ATTRIBUTE;
|
|
|
|
typedef struct {
|
|
unsigned long version;
|
|
unsigned long hash;
|
|
const XML_Char *uriName;
|
|
} NS_ATT;
|
|
|
|
typedef struct {
|
|
const XML_Char *name;
|
|
PREFIX *prefix;
|
|
const ATTRIBUTE_ID *idAtt;
|
|
int nDefaultAtts;
|
|
int allocDefaultAtts;
|
|
DEFAULT_ATTRIBUTE *defaultAtts;
|
|
} ELEMENT_TYPE;
|
|
|
|
typedef struct {
|
|
HASH_TABLE generalEntities;
|
|
HASH_TABLE elementTypes;
|
|
HASH_TABLE attributeIds;
|
|
HASH_TABLE prefixes;
|
|
STRING_POOL pool;
|
|
STRING_POOL entityValuePool;
|
|
/* false once a parameter entity reference has been skipped */
|
|
XML_Bool keepProcessing;
|
|
/* true once an internal or external PE reference has been encountered;
|
|
this includes the reference to an external subset */
|
|
XML_Bool hasParamEntityRefs;
|
|
XML_Bool standalone;
|
|
#ifdef XML_DTD
|
|
/* indicates if external PE has been read */
|
|
XML_Bool paramEntityRead;
|
|
HASH_TABLE paramEntities;
|
|
#endif /* XML_DTD */
|
|
PREFIX defaultPrefix;
|
|
/* === scaffolding for building content model === */
|
|
XML_Bool in_eldecl;
|
|
CONTENT_SCAFFOLD *scaffold;
|
|
unsigned contentStringLen;
|
|
unsigned scaffSize;
|
|
unsigned scaffCount;
|
|
int scaffLevel;
|
|
int *scaffIndex;
|
|
} DTD;
|
|
|
|
typedef struct open_internal_entity {
|
|
const char *internalEventPtr;
|
|
const char *internalEventEndPtr;
|
|
struct open_internal_entity *next;
|
|
ENTITY *entity;
|
|
int startTagLevel;
|
|
XML_Bool betweenDecl; /* WFC: PE Between Declarations */
|
|
} OPEN_INTERNAL_ENTITY;
|
|
|
|
typedef enum XML_Error PTRCALL Processor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr);
|
|
|
|
static Processor prologProcessor;
|
|
static Processor prologInitProcessor;
|
|
static Processor contentProcessor;
|
|
static Processor cdataSectionProcessor;
|
|
#ifdef XML_DTD
|
|
static Processor ignoreSectionProcessor;
|
|
static Processor externalParEntProcessor;
|
|
static Processor externalParEntInitProcessor;
|
|
static Processor entityValueProcessor;
|
|
static Processor entityValueInitProcessor;
|
|
#endif /* XML_DTD */
|
|
static Processor epilogProcessor;
|
|
static Processor errorProcessor;
|
|
static Processor externalEntityInitProcessor;
|
|
static Processor externalEntityInitProcessor2;
|
|
static Processor externalEntityInitProcessor3;
|
|
static Processor externalEntityContentProcessor;
|
|
static Processor internalEntityProcessor;
|
|
|
|
static enum XML_Error
|
|
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName);
|
|
static enum XML_Error
|
|
processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
|
|
const char *s, const char *next);
|
|
static enum XML_Error
|
|
initializeEncoding(XML_Parser parser);
|
|
static enum XML_Error
|
|
doProlog(XML_Parser parser, const ENCODING *enc, const char *s,
|
|
const char *end, int tok, const char *next, const char **nextPtr,
|
|
XML_Bool haveMore);
|
|
static enum XML_Error
|
|
processInternalEntity(XML_Parser parser, ENTITY *entity,
|
|
XML_Bool betweenDecl);
|
|
static enum XML_Error
|
|
doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc,
|
|
const char *start, const char *end, const char **endPtr,
|
|
XML_Bool haveMore);
|
|
static enum XML_Error
|
|
doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr,
|
|
const char *end, const char **nextPtr, XML_Bool haveMore);
|
|
#ifdef XML_DTD
|
|
static enum XML_Error
|
|
doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr,
|
|
const char *end, const char **nextPtr, XML_Bool haveMore);
|
|
#endif /* XML_DTD */
|
|
|
|
static enum XML_Error
|
|
storeAtts(XML_Parser parser, const ENCODING *, const char *s,
|
|
TAG_NAME *tagNamePtr, BINDING **bindingsPtr);
|
|
static enum XML_Error
|
|
addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
|
|
const XML_Char *uri, BINDING **bindingsPtr);
|
|
static int
|
|
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata,
|
|
XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser);
|
|
static enum XML_Error
|
|
storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,
|
|
const char *, const char *, STRING_POOL *);
|
|
static enum XML_Error
|
|
appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,
|
|
const char *, const char *, STRING_POOL *);
|
|
static ATTRIBUTE_ID *
|
|
getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start,
|
|
const char *end);
|
|
static int
|
|
setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *);
|
|
static enum XML_Error
|
|
storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start,
|
|
const char *end);
|
|
static int
|
|
reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,
|
|
const char *start, const char *end);
|
|
static int
|
|
reportComment(XML_Parser parser, const ENCODING *enc, const char *start,
|
|
const char *end);
|
|
static void
|
|
reportDefault(XML_Parser parser, const ENCODING *enc, const char *start,
|
|
const char *end);
|
|
|
|
static const XML_Char * getContext(XML_Parser parser);
|
|
static XML_Bool
|
|
setContext(XML_Parser parser, const XML_Char *context);
|
|
|
|
static void FASTCALL normalizePublicId(XML_Char *s);
|
|
|
|
static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms);
|
|
/* do not call if parentParser != NULL */
|
|
static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms);
|
|
static void
|
|
dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms);
|
|
static int
|
|
dtdCopy(DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms);
|
|
static int
|
|
copyEntityTable(HASH_TABLE *, STRING_POOL *, const HASH_TABLE *);
|
|
|
|
static NAMED *
|
|
lookup(HASH_TABLE *table, KEY name, size_t createSize);
|
|
static void FASTCALL
|
|
hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms);
|
|
static void FASTCALL hashTableClear(HASH_TABLE *);
|
|
static void FASTCALL hashTableDestroy(HASH_TABLE *);
|
|
static void FASTCALL
|
|
hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *);
|
|
static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *);
|
|
|
|
static void FASTCALL
|
|
poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms);
|
|
static void FASTCALL poolClear(STRING_POOL *);
|
|
static void FASTCALL poolDestroy(STRING_POOL *);
|
|
static XML_Char *
|
|
poolAppend(STRING_POOL *pool, const ENCODING *enc,
|
|
const char *ptr, const char *end);
|
|
static XML_Char *
|
|
poolStoreString(STRING_POOL *pool, const ENCODING *enc,
|
|
const char *ptr, const char *end);
|
|
static XML_Bool FASTCALL poolGrow(STRING_POOL *pool);
|
|
static const XML_Char * FASTCALL
|
|
poolCopyString(STRING_POOL *pool, const XML_Char *s);
|
|
static const XML_Char *
|
|
poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n);
|
|
static const XML_Char * FASTCALL
|
|
poolAppendString(STRING_POOL *pool, const XML_Char *s);
|
|
|
|
static int FASTCALL nextScaffoldPart(XML_Parser parser);
|
|
static XML_Content * build_model(XML_Parser parser);
|
|
static ELEMENT_TYPE *
|
|
getElementType(XML_Parser parser, const ENCODING *enc,
|
|
const char *ptr, const char *end);
|
|
|
|
static XML_Parser
|
|
parserCreate(const XML_Char *encodingName,
|
|
const XML_Memory_Handling_Suite *memsuite,
|
|
const XML_Char *nameSep,
|
|
DTD *dtd);
|
|
static void
|
|
parserInit(XML_Parser parser, const XML_Char *encodingName);
|
|
|
|
#define poolStart(pool) ((pool)->start)
|
|
#define poolEnd(pool) ((pool)->ptr)
|
|
#define poolLength(pool) ((pool)->ptr - (pool)->start)
|
|
#define poolChop(pool) ((void)--(pool->ptr))
|
|
#define poolLastChar(pool) (((pool)->ptr)[-1])
|
|
#define poolDiscard(pool) ((pool)->ptr = (pool)->start)
|
|
#define poolFinish(pool) ((pool)->start = (pool)->ptr)
|
|
#define poolAppendChar(pool, c) \
|
|
(((pool)->ptr == (pool)->end && !poolGrow(pool)) \
|
|
? 0 \
|
|
: ((*((pool)->ptr)++ = c), 1))
|
|
|
|
struct XML_ParserStruct {
|
|
/* The first member must be userData so that the XML_GetUserData
|
|
macro works. */
|
|
void *m_userData;
|
|
void *m_handlerArg;
|
|
char *m_buffer;
|
|
const XML_Memory_Handling_Suite m_mem;
|
|
/* first character to be parsed */
|
|
const char *m_bufferPtr;
|
|
/* past last character to be parsed */
|
|
char *m_bufferEnd;
|
|
/* allocated end of buffer */
|
|
const char *m_bufferLim;
|
|
XML_Index m_parseEndByteIndex;
|
|
const char *m_parseEndPtr;
|
|
XML_Char *m_dataBuf;
|
|
XML_Char *m_dataBufEnd;
|
|
XML_StartElementHandler m_startElementHandler;
|
|
XML_EndElementHandler m_endElementHandler;
|
|
XML_CharacterDataHandler m_characterDataHandler;
|
|
XML_ProcessingInstructionHandler m_processingInstructionHandler;
|
|
XML_CommentHandler m_commentHandler;
|
|
XML_StartCdataSectionHandler m_startCdataSectionHandler;
|
|
XML_EndCdataSectionHandler m_endCdataSectionHandler;
|
|
XML_DefaultHandler m_defaultHandler;
|
|
XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler;
|
|
XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler;
|
|
XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler;
|
|
XML_NotationDeclHandler m_notationDeclHandler;
|
|
XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler;
|
|
XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler;
|
|
XML_NotStandaloneHandler m_notStandaloneHandler;
|
|
XML_ExternalEntityRefHandler m_externalEntityRefHandler;
|
|
XML_Parser m_externalEntityRefHandlerArg;
|
|
XML_SkippedEntityHandler m_skippedEntityHandler;
|
|
XML_UnknownEncodingHandler m_unknownEncodingHandler;
|
|
XML_ElementDeclHandler m_elementDeclHandler;
|
|
XML_AttlistDeclHandler m_attlistDeclHandler;
|
|
XML_EntityDeclHandler m_entityDeclHandler;
|
|
XML_XmlDeclHandler m_xmlDeclHandler;
|
|
const ENCODING *m_encoding;
|
|
INIT_ENCODING m_initEncoding;
|
|
const ENCODING *m_internalEncoding;
|
|
const XML_Char *m_protocolEncodingName;
|
|
XML_Bool m_ns;
|
|
XML_Bool m_ns_triplets;
|
|
void *m_unknownEncodingMem;
|
|
void *m_unknownEncodingData;
|
|
void *m_unknownEncodingHandlerData;
|
|
void (XMLCALL *m_unknownEncodingRelease)(void *);
|
|
PROLOG_STATE m_prologState;
|
|
Processor *m_processor;
|
|
enum XML_Error m_errorCode;
|
|
const char *m_eventPtr;
|
|
const char *m_eventEndPtr;
|
|
const char *m_positionPtr;
|
|
OPEN_INTERNAL_ENTITY *m_openInternalEntities;
|
|
OPEN_INTERNAL_ENTITY *m_freeInternalEntities;
|
|
XML_Bool m_defaultExpandInternalEntities;
|
|
int m_tagLevel;
|
|
ENTITY *m_declEntity;
|
|
const XML_Char *m_doctypeName;
|
|
const XML_Char *m_doctypeSysid;
|
|
const XML_Char *m_doctypePubid;
|
|
const XML_Char *m_declAttributeType;
|
|
const XML_Char *m_declNotationName;
|
|
const XML_Char *m_declNotationPublicId;
|
|
ELEMENT_TYPE *m_declElementType;
|
|
ATTRIBUTE_ID *m_declAttributeId;
|
|
XML_Bool m_declAttributeIsCdata;
|
|
XML_Bool m_declAttributeIsId;
|
|
DTD *m_dtd;
|
|
const XML_Char *m_curBase;
|
|
TAG *m_tagStack;
|
|
TAG *m_freeTagList;
|
|
BINDING *m_inheritedBindings;
|
|
BINDING *m_freeBindingList;
|
|
int m_attsSize;
|
|
int m_nSpecifiedAtts;
|
|
int m_idAttIndex;
|
|
ATTRIBUTE *m_atts;
|
|
NS_ATT *m_nsAtts;
|
|
unsigned long m_nsAttsVersion;
|
|
unsigned char m_nsAttsPower;
|
|
POSITION m_position;
|
|
STRING_POOL m_tempPool;
|
|
STRING_POOL m_temp2Pool;
|
|
char *m_groupConnector;
|
|
unsigned int m_groupSize;
|
|
XML_Char m_namespaceSeparator;
|
|
XML_Parser m_parentParser;
|
|
XML_ParsingStatus m_parsingStatus;
|
|
#ifdef XML_DTD
|
|
XML_Bool m_isParamEntity;
|
|
XML_Bool m_useForeignDTD;
|
|
enum XML_ParamEntityParsing m_paramEntityParsing;
|
|
#endif
|
|
};
|
|
|
|
#define MALLOC(s) (parser->m_mem.malloc_fcn((s)))
|
|
#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s)))
|
|
#define FREE(p) (parser->m_mem.free_fcn((p)))
|
|
|
|
#define userData (parser->m_userData)
|
|
#define handlerArg (parser->m_handlerArg)
|
|
#define startElementHandler (parser->m_startElementHandler)
|
|
#define endElementHandler (parser->m_endElementHandler)
|
|
#define characterDataHandler (parser->m_characterDataHandler)
|
|
#define processingInstructionHandler \
|
|
(parser->m_processingInstructionHandler)
|
|
#define commentHandler (parser->m_commentHandler)
|
|
#define startCdataSectionHandler \
|
|
(parser->m_startCdataSectionHandler)
|
|
#define endCdataSectionHandler (parser->m_endCdataSectionHandler)
|
|
#define defaultHandler (parser->m_defaultHandler)
|
|
#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler)
|
|
#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler)
|
|
#define unparsedEntityDeclHandler \
|
|
(parser->m_unparsedEntityDeclHandler)
|
|
#define notationDeclHandler (parser->m_notationDeclHandler)
|
|
#define startNamespaceDeclHandler \
|
|
(parser->m_startNamespaceDeclHandler)
|
|
#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler)
|
|
#define notStandaloneHandler (parser->m_notStandaloneHandler)
|
|
#define externalEntityRefHandler \
|
|
(parser->m_externalEntityRefHandler)
|
|
#define externalEntityRefHandlerArg \
|
|
(parser->m_externalEntityRefHandlerArg)
|
|
#define internalEntityRefHandler \
|
|
(parser->m_internalEntityRefHandler)
|
|
#define skippedEntityHandler (parser->m_skippedEntityHandler)
|
|
#define unknownEncodingHandler (parser->m_unknownEncodingHandler)
|
|
#define elementDeclHandler (parser->m_elementDeclHandler)
|
|
#define attlistDeclHandler (parser->m_attlistDeclHandler)
|
|
#define entityDeclHandler (parser->m_entityDeclHandler)
|
|
#define xmlDeclHandler (parser->m_xmlDeclHandler)
|
|
#define encoding (parser->m_encoding)
|
|
#define initEncoding (parser->m_initEncoding)
|
|
#define internalEncoding (parser->m_internalEncoding)
|
|
#define unknownEncodingMem (parser->m_unknownEncodingMem)
|
|
#define unknownEncodingData (parser->m_unknownEncodingData)
|
|
#define unknownEncodingHandlerData \
|
|
(parser->m_unknownEncodingHandlerData)
|
|
#define unknownEncodingRelease (parser->m_unknownEncodingRelease)
|
|
#define protocolEncodingName (parser->m_protocolEncodingName)
|
|
#define ns (parser->m_ns)
|
|
#define ns_triplets (parser->m_ns_triplets)
|
|
#define prologState (parser->m_prologState)
|
|
#define processor (parser->m_processor)
|
|
#define errorCode (parser->m_errorCode)
|
|
#define eventPtr (parser->m_eventPtr)
|
|
#define eventEndPtr (parser->m_eventEndPtr)
|
|
#define positionPtr (parser->m_positionPtr)
|
|
#define position (parser->m_position)
|
|
#define openInternalEntities (parser->m_openInternalEntities)
|
|
#define freeInternalEntities (parser->m_freeInternalEntities)
|
|
#define defaultExpandInternalEntities \
|
|
(parser->m_defaultExpandInternalEntities)
|
|
#define tagLevel (parser->m_tagLevel)
|
|
#define buffer (parser->m_buffer)
|
|
#define bufferPtr (parser->m_bufferPtr)
|
|
#define bufferEnd (parser->m_bufferEnd)
|
|
#define parseEndByteIndex (parser->m_parseEndByteIndex)
|
|
#define parseEndPtr (parser->m_parseEndPtr)
|
|
#define bufferLim (parser->m_bufferLim)
|
|
#define dataBuf (parser->m_dataBuf)
|
|
#define dataBufEnd (parser->m_dataBufEnd)
|
|
#define _dtd (parser->m_dtd)
|
|
#define curBase (parser->m_curBase)
|
|
#define declEntity (parser->m_declEntity)
|
|
#define doctypeName (parser->m_doctypeName)
|
|
#define doctypeSysid (parser->m_doctypeSysid)
|
|
#define doctypePubid (parser->m_doctypePubid)
|
|
#define declAttributeType (parser->m_declAttributeType)
|
|
#define declNotationName (parser->m_declNotationName)
|
|
#define declNotationPublicId (parser->m_declNotationPublicId)
|
|
#define declElementType (parser->m_declElementType)
|
|
#define declAttributeId (parser->m_declAttributeId)
|
|
#define declAttributeIsCdata (parser->m_declAttributeIsCdata)
|
|
#define declAttributeIsId (parser->m_declAttributeIsId)
|
|
#define freeTagList (parser->m_freeTagList)
|
|
#define freeBindingList (parser->m_freeBindingList)
|
|
#define inheritedBindings (parser->m_inheritedBindings)
|
|
#define tagStack (parser->m_tagStack)
|
|
#define atts (parser->m_atts)
|
|
#define attsSize (parser->m_attsSize)
|
|
#define nSpecifiedAtts (parser->m_nSpecifiedAtts)
|
|
#define idAttIndex (parser->m_idAttIndex)
|
|
#define nsAtts (parser->m_nsAtts)
|
|
#define nsAttsVersion (parser->m_nsAttsVersion)
|
|
#define nsAttsPower (parser->m_nsAttsPower)
|
|
#define tempPool (parser->m_tempPool)
|
|
#define temp2Pool (parser->m_temp2Pool)
|
|
#define groupConnector (parser->m_groupConnector)
|
|
#define groupSize (parser->m_groupSize)
|
|
#define namespaceSeparator (parser->m_namespaceSeparator)
|
|
#define parentParser (parser->m_parentParser)
|
|
#define ps_parsing (parser->m_parsingStatus.parsing)
|
|
#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer)
|
|
#ifdef XML_DTD
|
|
#define isParamEntity (parser->m_isParamEntity)
|
|
#define useForeignDTD (parser->m_useForeignDTD)
|
|
#define paramEntityParsing (parser->m_paramEntityParsing)
|
|
#endif /* XML_DTD */
|
|
|
|
XML_Parser XMLCALL
|
|
XML_ParserCreate(const XML_Char *encodingName)
|
|
{
|
|
return XML_ParserCreate_MM(encodingName, NULL, NULL);
|
|
}
|
|
|
|
XML_Parser XMLCALL
|
|
XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep)
|
|
{
|
|
XML_Char tmp[2];
|
|
*tmp = nsSep;
|
|
return XML_ParserCreate_MM(encodingName, NULL, tmp);
|
|
}
|
|
|
|
static const XML_Char implicitContext[] = {
|
|
'x', 'm', 'l', '=', 'h', 't', 't', 'p', ':', '/', '/',
|
|
'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/',
|
|
'X', 'M', 'L', '/', '1', '9', '9', '8', '/',
|
|
'n', 'a', 'm', 'e', 's', 'p', 'a', 'c', 'e', '\0'
|
|
};
|
|
|
|
XML_Parser XMLCALL
|
|
XML_ParserCreate_MM(const XML_Char *encodingName,
|
|
const XML_Memory_Handling_Suite *memsuite,
|
|
const XML_Char *nameSep)
|
|
{
|
|
XML_Parser parser = parserCreate(encodingName, memsuite, nameSep, NULL);
|
|
if (parser != NULL && ns) {
|
|
/* implicit context only set for root parser, since child
|
|
parsers (i.e. external entity parsers) will inherit it
|
|
*/
|
|
if (!setContext(parser, implicitContext)) {
|
|
XML_ParserFree(parser);
|
|
return NULL;
|
|
}
|
|
}
|
|
return parser;
|
|
}
|
|
|
|
static XML_Parser
|
|
parserCreate(const XML_Char *encodingName,
|
|
const XML_Memory_Handling_Suite *memsuite,
|
|
const XML_Char *nameSep,
|
|
DTD *dtd)
|
|
{
|
|
XML_Parser parser;
|
|
|
|
if (memsuite) {
|
|
XML_Memory_Handling_Suite *mtemp;
|
|
parser = (XML_Parser)
|
|
memsuite->malloc_fcn(sizeof(struct XML_ParserStruct));
|
|
if (parser != NULL) {
|
|
mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem);
|
|
mtemp->malloc_fcn = memsuite->malloc_fcn;
|
|
mtemp->realloc_fcn = memsuite->realloc_fcn;
|
|
mtemp->free_fcn = memsuite->free_fcn;
|
|
}
|
|
}
|
|
else {
|
|
XML_Memory_Handling_Suite *mtemp;
|
|
parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct));
|
|
if (parser != NULL) {
|
|
mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem);
|
|
mtemp->malloc_fcn = malloc;
|
|
mtemp->realloc_fcn = realloc;
|
|
mtemp->free_fcn = free;
|
|
}
|
|
}
|
|
|
|
if (!parser)
|
|
return parser;
|
|
|
|
buffer = NULL;
|
|
bufferLim = NULL;
|
|
|
|
attsSize = INIT_ATTS_SIZE;
|
|
atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE));
|
|
if (atts == NULL) {
|
|
FREE(parser);
|
|
return NULL;
|
|
}
|
|
dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char));
|
|
if (dataBuf == NULL) {
|
|
FREE(atts);
|
|
FREE(parser);
|
|
return NULL;
|
|
}
|
|
dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;
|
|
|
|
if (dtd)
|
|
_dtd = dtd;
|
|
else {
|
|
_dtd = dtdCreate(&parser->m_mem);
|
|
if (_dtd == NULL) {
|
|
FREE(dataBuf);
|
|
FREE(atts);
|
|
FREE(parser);
|
|
return NULL;
|
|
}
|
|
}
|
|
|
|
freeBindingList = NULL;
|
|
freeTagList = NULL;
|
|
freeInternalEntities = NULL;
|
|
|
|
groupSize = 0;
|
|
groupConnector = NULL;
|
|
|
|
unknownEncodingHandler = NULL;
|
|
unknownEncodingHandlerData = NULL;
|
|
|
|
namespaceSeparator = '!';
|
|
ns = XML_FALSE;
|
|
ns_triplets = XML_FALSE;
|
|
|
|
nsAtts = NULL;
|
|
nsAttsVersion = 0;
|
|
nsAttsPower = 0;
|
|
|
|
poolInit(&tempPool, &(parser->m_mem));
|
|
poolInit(&temp2Pool, &(parser->m_mem));
|
|
parserInit(parser, encodingName);
|
|
|
|
if (encodingName && !protocolEncodingName) {
|
|
XML_ParserFree(parser);
|
|
return NULL;
|
|
}
|
|
|
|
if (nameSep) {
|
|
ns = XML_TRUE;
|
|
internalEncoding = XmlGetInternalEncodingNS();
|
|
namespaceSeparator = *nameSep;
|
|
}
|
|
else {
|
|
internalEncoding = XmlGetInternalEncoding();
|
|
}
|
|
|
|
return parser;
|
|
}
|
|
|
|
static void
|
|
parserInit(XML_Parser parser, const XML_Char *encodingName)
|
|
{
|
|
processor = prologInitProcessor;
|
|
XmlPrologStateInit(&prologState);
|
|
protocolEncodingName = (encodingName != NULL
|
|
? poolCopyString(&tempPool, encodingName)
|
|
: NULL);
|
|
curBase = NULL;
|
|
XmlInitEncoding(&initEncoding, &encoding, 0);
|
|
userData = NULL;
|
|
handlerArg = NULL;
|
|
startElementHandler = NULL;
|
|
endElementHandler = NULL;
|
|
characterDataHandler = NULL;
|
|
processingInstructionHandler = NULL;
|
|
commentHandler = NULL;
|
|
startCdataSectionHandler = NULL;
|
|
endCdataSectionHandler = NULL;
|
|
defaultHandler = NULL;
|
|
startDoctypeDeclHandler = NULL;
|
|
endDoctypeDeclHandler = NULL;
|
|
unparsedEntityDeclHandler = NULL;
|
|
notationDeclHandler = NULL;
|
|
startNamespaceDeclHandler = NULL;
|
|
endNamespaceDeclHandler = NULL;
|
|
notStandaloneHandler = NULL;
|
|
externalEntityRefHandler = NULL;
|
|
externalEntityRefHandlerArg = parser;
|
|
skippedEntityHandler = NULL;
|
|
elementDeclHandler = NULL;
|
|
attlistDeclHandler = NULL;
|
|
entityDeclHandler = NULL;
|
|
xmlDeclHandler = NULL;
|
|
bufferPtr = buffer;
|
|
bufferEnd = buffer;
|
|
parseEndByteIndex = 0;
|
|
parseEndPtr = NULL;
|
|
declElementType = NULL;
|
|
declAttributeId = NULL;
|
|
declEntity = NULL;
|
|
doctypeName = NULL;
|
|
doctypeSysid = NULL;
|
|
doctypePubid = NULL;
|
|
declAttributeType = NULL;
|
|
declNotationName = NULL;
|
|
declNotationPublicId = NULL;
|
|
declAttributeIsCdata = XML_FALSE;
|
|
declAttributeIsId = XML_FALSE;
|
|
memset(&position, 0, sizeof(POSITION));
|
|
errorCode = XML_ERROR_NONE;
|
|
eventPtr = NULL;
|
|
eventEndPtr = NULL;
|
|
positionPtr = NULL;
|
|
openInternalEntities = NULL;
|
|
defaultExpandInternalEntities = XML_TRUE;
|
|
tagLevel = 0;
|
|
tagStack = NULL;
|
|
inheritedBindings = NULL;
|
|
nSpecifiedAtts = 0;
|
|
unknownEncodingMem = NULL;
|
|
unknownEncodingRelease = NULL;
|
|
unknownEncodingData = NULL;
|
|
parentParser = NULL;
|
|
ps_parsing = XML_INITIALIZED;
|
|
#ifdef XML_DTD
|
|
isParamEntity = XML_FALSE;
|
|
useForeignDTD = XML_FALSE;
|
|
paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
|
|
#endif
|
|
}
|
|
|
|
/* moves list of bindings to freeBindingList */
|
|
static void FASTCALL
|
|
moveToFreeBindingList(XML_Parser parser, BINDING *bindings)
|
|
{
|
|
while (bindings) {
|
|
BINDING *b = bindings;
|
|
bindings = bindings->nextTagBinding;
|
|
b->nextTagBinding = freeBindingList;
|
|
freeBindingList = b;
|
|
}
|
|
}
|
|
|
|
XML_Bool XMLCALL
|
|
XML_ParserReset(XML_Parser parser, const XML_Char *encodingName)
|
|
{
|
|
TAG *tStk;
|
|
OPEN_INTERNAL_ENTITY *openEntityList;
|
|
if (parentParser)
|
|
return XML_FALSE;
|
|
/* move tagStack to freeTagList */
|
|
tStk = tagStack;
|
|
while (tStk) {
|
|
TAG *tag = tStk;
|
|
tStk = tStk->parent;
|
|
tag->parent = freeTagList;
|
|
moveToFreeBindingList(parser, tag->bindings);
|
|
tag->bindings = NULL;
|
|
freeTagList = tag;
|
|
}
|
|
/* move openInternalEntities to freeInternalEntities */
|
|
openEntityList = openInternalEntities;
|
|
while (openEntityList) {
|
|
OPEN_INTERNAL_ENTITY *openEntity = openEntityList;
|
|
openEntityList = openEntity->next;
|
|
openEntity->next = freeInternalEntities;
|
|
freeInternalEntities = openEntity;
|
|
}
|
|
moveToFreeBindingList(parser, inheritedBindings);
|
|
FREE(unknownEncodingMem);
|
|
if (unknownEncodingRelease)
|
|
unknownEncodingRelease(unknownEncodingData);
|
|
poolClear(&tempPool);
|
|
poolClear(&temp2Pool);
|
|
parserInit(parser, encodingName);
|
|
dtdReset(_dtd, &parser->m_mem);
|
|
return setContext(parser, implicitContext);
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)
|
|
{
|
|
/* Block after XML_Parse()/XML_ParseBuffer() has been called.
|
|
XXX There's no way for the caller to determine which of the
|
|
XXX possible error cases caused the XML_STATUS_ERROR return.
|
|
*/
|
|
if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
|
|
return XML_STATUS_ERROR;
|
|
if (encodingName == NULL)
|
|
protocolEncodingName = NULL;
|
|
else {
|
|
protocolEncodingName = poolCopyString(&tempPool, encodingName);
|
|
if (!protocolEncodingName)
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
return XML_STATUS_OK;
|
|
}
|
|
|
|
XML_Parser XMLCALL
|
|
XML_ExternalEntityParserCreate(XML_Parser oldParser,
|
|
const XML_Char *context,
|
|
const XML_Char *encodingName)
|
|
{
|
|
XML_Parser parser = oldParser;
|
|
DTD *newDtd = NULL;
|
|
DTD *oldDtd = _dtd;
|
|
XML_StartElementHandler oldStartElementHandler = startElementHandler;
|
|
XML_EndElementHandler oldEndElementHandler = endElementHandler;
|
|
XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler;
|
|
XML_ProcessingInstructionHandler oldProcessingInstructionHandler
|
|
= processingInstructionHandler;
|
|
XML_CommentHandler oldCommentHandler = commentHandler;
|
|
XML_StartCdataSectionHandler oldStartCdataSectionHandler
|
|
= startCdataSectionHandler;
|
|
XML_EndCdataSectionHandler oldEndCdataSectionHandler
|
|
= endCdataSectionHandler;
|
|
XML_DefaultHandler oldDefaultHandler = defaultHandler;
|
|
XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler
|
|
= unparsedEntityDeclHandler;
|
|
XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler;
|
|
XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler
|
|
= startNamespaceDeclHandler;
|
|
XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler
|
|
= endNamespaceDeclHandler;
|
|
XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;
|
|
XML_ExternalEntityRefHandler oldExternalEntityRefHandler
|
|
= externalEntityRefHandler;
|
|
XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler;
|
|
XML_UnknownEncodingHandler oldUnknownEncodingHandler
|
|
= unknownEncodingHandler;
|
|
XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler;
|
|
XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler;
|
|
XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler;
|
|
XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler;
|
|
ELEMENT_TYPE * oldDeclElementType = declElementType;
|
|
|
|
void *oldUserData = userData;
|
|
void *oldHandlerArg = handlerArg;
|
|
XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities;
|
|
XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;
|
|
#ifdef XML_DTD
|
|
enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing;
|
|
int oldInEntityValue = prologState.inEntityValue;
|
|
#endif
|
|
XML_Bool oldns_triplets = ns_triplets;
|
|
|
|
#ifdef XML_DTD
|
|
if (!context)
|
|
newDtd = oldDtd;
|
|
#endif /* XML_DTD */
|
|
|
|
/* Note that the magical uses of the pre-processor to make field
|
|
access look more like C++ require that `parser' be overwritten
|
|
here. This makes this function more painful to follow than it
|
|
would be otherwise.
|
|
*/
|
|
if (ns) {
|
|
XML_Char tmp[2];
|
|
*tmp = namespaceSeparator;
|
|
parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);
|
|
}
|
|
else {
|
|
parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd);
|
|
}
|
|
|
|
if (!parser)
|
|
return NULL;
|
|
|
|
startElementHandler = oldStartElementHandler;
|
|
endElementHandler = oldEndElementHandler;
|
|
characterDataHandler = oldCharacterDataHandler;
|
|
processingInstructionHandler = oldProcessingInstructionHandler;
|
|
commentHandler = oldCommentHandler;
|
|
startCdataSectionHandler = oldStartCdataSectionHandler;
|
|
endCdataSectionHandler = oldEndCdataSectionHandler;
|
|
defaultHandler = oldDefaultHandler;
|
|
unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler;
|
|
notationDeclHandler = oldNotationDeclHandler;
|
|
startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
|
|
endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
|
|
notStandaloneHandler = oldNotStandaloneHandler;
|
|
externalEntityRefHandler = oldExternalEntityRefHandler;
|
|
skippedEntityHandler = oldSkippedEntityHandler;
|
|
unknownEncodingHandler = oldUnknownEncodingHandler;
|
|
elementDeclHandler = oldElementDeclHandler;
|
|
attlistDeclHandler = oldAttlistDeclHandler;
|
|
entityDeclHandler = oldEntityDeclHandler;
|
|
xmlDeclHandler = oldXmlDeclHandler;
|
|
declElementType = oldDeclElementType;
|
|
userData = oldUserData;
|
|
if (oldUserData == oldHandlerArg)
|
|
handlerArg = userData;
|
|
else
|
|
handlerArg = parser;
|
|
if (oldExternalEntityRefHandlerArg != oldParser)
|
|
externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
|
|
defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
|
|
ns_triplets = oldns_triplets;
|
|
parentParser = oldParser;
|
|
#ifdef XML_DTD
|
|
paramEntityParsing = oldParamEntityParsing;
|
|
prologState.inEntityValue = oldInEntityValue;
|
|
if (context) {
|
|
#endif /* XML_DTD */
|
|
if (!dtdCopy(_dtd, oldDtd, &parser->m_mem)
|
|
|| !setContext(parser, context)) {
|
|
XML_ParserFree(parser);
|
|
return NULL;
|
|
}
|
|
processor = externalEntityInitProcessor;
|
|
#ifdef XML_DTD
|
|
}
|
|
else {
|
|
/* The DTD instance referenced by _dtd is shared between the document's
|
|
root parser and external PE parsers, therefore one does not need to
|
|
call setContext. In addition, one also *must* not call setContext,
|
|
because this would overwrite existing prefix->binding pointers in
|
|
_dtd with ones that get destroyed with the external PE parser.
|
|
This would leave those prefixes with dangling pointers.
|
|
*/
|
|
isParamEntity = XML_TRUE;
|
|
XmlPrologStateInitExternalEntity(&prologState);
|
|
processor = externalParEntInitProcessor;
|
|
}
|
|
#endif /* XML_DTD */
|
|
return parser;
|
|
}
|
|
|
|
static void FASTCALL
|
|
destroyBindings(BINDING *bindings, XML_Parser parser)
|
|
{
|
|
for (;;) {
|
|
BINDING *b = bindings;
|
|
if (!b)
|
|
break;
|
|
bindings = b->nextTagBinding;
|
|
FREE(b->uri);
|
|
FREE(b);
|
|
}
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_ParserFree(XML_Parser parser)
|
|
{
|
|
TAG *tagList;
|
|
OPEN_INTERNAL_ENTITY *entityList;
|
|
if (parser == NULL)
|
|
return;
|
|
/* free tagStack and freeTagList */
|
|
tagList = tagStack;
|
|
for (;;) {
|
|
TAG *p;
|
|
if (tagList == NULL) {
|
|
if (freeTagList == NULL)
|
|
break;
|
|
tagList = freeTagList;
|
|
freeTagList = NULL;
|
|
}
|
|
p = tagList;
|
|
tagList = tagList->parent;
|
|
FREE(p->buf);
|
|
destroyBindings(p->bindings, parser);
|
|
FREE(p);
|
|
}
|
|
/* free openInternalEntities and freeInternalEntities */
|
|
entityList = openInternalEntities;
|
|
for (;;) {
|
|
OPEN_INTERNAL_ENTITY *openEntity;
|
|
if (entityList == NULL) {
|
|
if (freeInternalEntities == NULL)
|
|
break;
|
|
entityList = freeInternalEntities;
|
|
freeInternalEntities = NULL;
|
|
}
|
|
openEntity = entityList;
|
|
entityList = entityList->next;
|
|
FREE(openEntity);
|
|
}
|
|
|
|
destroyBindings(freeBindingList, parser);
|
|
destroyBindings(inheritedBindings, parser);
|
|
poolDestroy(&tempPool);
|
|
poolDestroy(&temp2Pool);
|
|
#ifdef XML_DTD
|
|
/* external parameter entity parsers share the DTD structure
|
|
parser->m_dtd with the root parser, so we must not destroy it
|
|
*/
|
|
if (!isParamEntity && _dtd)
|
|
#else
|
|
if (_dtd)
|
|
#endif /* XML_DTD */
|
|
dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem);
|
|
FREE((void *)atts);
|
|
FREE(groupConnector);
|
|
FREE(buffer);
|
|
FREE(dataBuf);
|
|
FREE(nsAtts);
|
|
FREE(unknownEncodingMem);
|
|
if (unknownEncodingRelease)
|
|
unknownEncodingRelease(unknownEncodingData);
|
|
FREE(parser);
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_UseParserAsHandlerArg(XML_Parser parser)
|
|
{
|
|
handlerArg = parser;
|
|
}
|
|
|
|
enum XML_Error XMLCALL
|
|
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD)
|
|
{
|
|
#ifdef XML_DTD
|
|
/* block after XML_Parse()/XML_ParseBuffer() has been called */
|
|
if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
|
|
return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING;
|
|
useForeignDTD = useDTD;
|
|
return XML_ERROR_NONE;
|
|
#else
|
|
return XML_ERROR_FEATURE_REQUIRES_XML_DTD;
|
|
#endif
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetReturnNSTriplet(XML_Parser parser, int do_nst)
|
|
{
|
|
/* block after XML_Parse()/XML_ParseBuffer() has been called */
|
|
if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
|
|
return;
|
|
ns_triplets = do_nst ? XML_TRUE : XML_FALSE;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetUserData(XML_Parser parser, void *p)
|
|
{
|
|
if (handlerArg == userData)
|
|
handlerArg = userData = p;
|
|
else
|
|
userData = p;
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_SetBase(XML_Parser parser, const XML_Char *p)
|
|
{
|
|
if (p) {
|
|
p = poolCopyString(&_dtd->pool, p);
|
|
if (!p)
|
|
return XML_STATUS_ERROR;
|
|
curBase = p;
|
|
}
|
|
else
|
|
curBase = NULL;
|
|
return XML_STATUS_OK;
|
|
}
|
|
|
|
const XML_Char * XMLCALL
|
|
XML_GetBase(XML_Parser parser)
|
|
{
|
|
return curBase;
|
|
}
|
|
|
|
int XMLCALL
|
|
XML_GetSpecifiedAttributeCount(XML_Parser parser)
|
|
{
|
|
return nSpecifiedAtts;
|
|
}
|
|
|
|
int XMLCALL
|
|
XML_GetIdAttributeIndex(XML_Parser parser)
|
|
{
|
|
return idAttIndex;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetElementHandler(XML_Parser parser,
|
|
XML_StartElementHandler start,
|
|
XML_EndElementHandler end)
|
|
{
|
|
startElementHandler = start;
|
|
endElementHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetStartElementHandler(XML_Parser parser,
|
|
XML_StartElementHandler start) {
|
|
startElementHandler = start;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetEndElementHandler(XML_Parser parser,
|
|
XML_EndElementHandler end) {
|
|
endElementHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetCharacterDataHandler(XML_Parser parser,
|
|
XML_CharacterDataHandler handler)
|
|
{
|
|
characterDataHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetProcessingInstructionHandler(XML_Parser parser,
|
|
XML_ProcessingInstructionHandler handler)
|
|
{
|
|
processingInstructionHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetCommentHandler(XML_Parser parser,
|
|
XML_CommentHandler handler)
|
|
{
|
|
commentHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetCdataSectionHandler(XML_Parser parser,
|
|
XML_StartCdataSectionHandler start,
|
|
XML_EndCdataSectionHandler end)
|
|
{
|
|
startCdataSectionHandler = start;
|
|
endCdataSectionHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetStartCdataSectionHandler(XML_Parser parser,
|
|
XML_StartCdataSectionHandler start) {
|
|
startCdataSectionHandler = start;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetEndCdataSectionHandler(XML_Parser parser,
|
|
XML_EndCdataSectionHandler end) {
|
|
endCdataSectionHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetDefaultHandler(XML_Parser parser,
|
|
XML_DefaultHandler handler)
|
|
{
|
|
defaultHandler = handler;
|
|
defaultExpandInternalEntities = XML_FALSE;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetDefaultHandlerExpand(XML_Parser parser,
|
|
XML_DefaultHandler handler)
|
|
{
|
|
defaultHandler = handler;
|
|
defaultExpandInternalEntities = XML_TRUE;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetDoctypeDeclHandler(XML_Parser parser,
|
|
XML_StartDoctypeDeclHandler start,
|
|
XML_EndDoctypeDeclHandler end)
|
|
{
|
|
startDoctypeDeclHandler = start;
|
|
endDoctypeDeclHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetStartDoctypeDeclHandler(XML_Parser parser,
|
|
XML_StartDoctypeDeclHandler start) {
|
|
startDoctypeDeclHandler = start;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetEndDoctypeDeclHandler(XML_Parser parser,
|
|
XML_EndDoctypeDeclHandler end) {
|
|
endDoctypeDeclHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
|
|
XML_UnparsedEntityDeclHandler handler)
|
|
{
|
|
unparsedEntityDeclHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetNotationDeclHandler(XML_Parser parser,
|
|
XML_NotationDeclHandler handler)
|
|
{
|
|
notationDeclHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetNamespaceDeclHandler(XML_Parser parser,
|
|
XML_StartNamespaceDeclHandler start,
|
|
XML_EndNamespaceDeclHandler end)
|
|
{
|
|
startNamespaceDeclHandler = start;
|
|
endNamespaceDeclHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetStartNamespaceDeclHandler(XML_Parser parser,
|
|
XML_StartNamespaceDeclHandler start) {
|
|
startNamespaceDeclHandler = start;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetEndNamespaceDeclHandler(XML_Parser parser,
|
|
XML_EndNamespaceDeclHandler end) {
|
|
endNamespaceDeclHandler = end;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetNotStandaloneHandler(XML_Parser parser,
|
|
XML_NotStandaloneHandler handler)
|
|
{
|
|
notStandaloneHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetExternalEntityRefHandler(XML_Parser parser,
|
|
XML_ExternalEntityRefHandler handler)
|
|
{
|
|
externalEntityRefHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg)
|
|
{
|
|
if (arg)
|
|
externalEntityRefHandlerArg = (XML_Parser)arg;
|
|
else
|
|
externalEntityRefHandlerArg = parser;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetSkippedEntityHandler(XML_Parser parser,
|
|
XML_SkippedEntityHandler handler)
|
|
{
|
|
skippedEntityHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetUnknownEncodingHandler(XML_Parser parser,
|
|
XML_UnknownEncodingHandler handler,
|
|
void *data)
|
|
{
|
|
unknownEncodingHandler = handler;
|
|
unknownEncodingHandlerData = data;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetElementDeclHandler(XML_Parser parser,
|
|
XML_ElementDeclHandler eldecl)
|
|
{
|
|
elementDeclHandler = eldecl;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetAttlistDeclHandler(XML_Parser parser,
|
|
XML_AttlistDeclHandler attdecl)
|
|
{
|
|
attlistDeclHandler = attdecl;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetEntityDeclHandler(XML_Parser parser,
|
|
XML_EntityDeclHandler handler)
|
|
{
|
|
entityDeclHandler = handler;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_SetXmlDeclHandler(XML_Parser parser,
|
|
XML_XmlDeclHandler handler) {
|
|
xmlDeclHandler = handler;
|
|
}
|
|
|
|
int XMLCALL
|
|
XML_SetParamEntityParsing(XML_Parser parser,
|
|
enum XML_ParamEntityParsing peParsing)
|
|
{
|
|
/* block after XML_Parse()/XML_ParseBuffer() has been called */
|
|
if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
|
|
return 0;
|
|
#ifdef XML_DTD
|
|
paramEntityParsing = peParsing;
|
|
return 1;
|
|
#else
|
|
return peParsing == XML_PARAM_ENTITY_PARSING_NEVER;
|
|
#endif
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
|
|
{
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
errorCode = XML_ERROR_SUSPENDED;
|
|
return XML_STATUS_ERROR;
|
|
case XML_FINISHED:
|
|
errorCode = XML_ERROR_FINISHED;
|
|
return XML_STATUS_ERROR;
|
|
default:
|
|
ps_parsing = XML_PARSING;
|
|
}
|
|
|
|
if (len == 0) {
|
|
ps_finalBuffer = (XML_Bool)isFinal;
|
|
if (!isFinal)
|
|
return XML_STATUS_OK;
|
|
positionPtr = bufferPtr;
|
|
parseEndPtr = bufferEnd;
|
|
|
|
/* If data are left over from last buffer, and we now know that these
|
|
data are the final chunk of input, then we have to check them again
|
|
to detect errors based on that fact.
|
|
*/
|
|
errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
|
|
|
|
if (errorCode == XML_ERROR_NONE) {
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
|
|
positionPtr = bufferPtr;
|
|
return XML_STATUS_SUSPENDED;
|
|
case XML_INITIALIZED:
|
|
case XML_PARSING:
|
|
ps_parsing = XML_FINISHED;
|
|
/* fall through */
|
|
default:
|
|
return XML_STATUS_OK;
|
|
}
|
|
}
|
|
eventEndPtr = eventPtr;
|
|
processor = errorProcessor;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
#ifndef XML_CONTEXT_BYTES
|
|
else if (bufferPtr == bufferEnd) {
|
|
const char *end;
|
|
int nLeftOver;
|
|
enum XML_Error result;
|
|
parseEndByteIndex += len;
|
|
positionPtr = s;
|
|
ps_finalBuffer = (XML_Bool)isFinal;
|
|
|
|
errorCode = processor(parser, s, parseEndPtr = s + len, &end);
|
|
|
|
if (errorCode != XML_ERROR_NONE) {
|
|
eventEndPtr = eventPtr;
|
|
processor = errorProcessor;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
else {
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
result = XML_STATUS_SUSPENDED;
|
|
break;
|
|
case XML_INITIALIZED:
|
|
case XML_PARSING:
|
|
result = XML_STATUS_OK;
|
|
if (isFinal) {
|
|
ps_parsing = XML_FINISHED;
|
|
return result;
|
|
}
|
|
}
|
|
}
|
|
|
|
XmlUpdatePosition(encoding, positionPtr, end, &position);
|
|
nLeftOver = s + len - end;
|
|
if (nLeftOver) {
|
|
if (buffer == NULL || nLeftOver > bufferLim - buffer) {
|
|
/* FIXME avoid integer overflow */
|
|
char *temp;
|
|
temp = (buffer == NULL
|
|
? (char *)MALLOC(len * 2)
|
|
: (char *)REALLOC(buffer, len * 2));
|
|
if (temp == NULL) {
|
|
errorCode = XML_ERROR_NO_MEMORY;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
buffer = temp;
|
|
if (!buffer) {
|
|
errorCode = XML_ERROR_NO_MEMORY;
|
|
eventPtr = eventEndPtr = NULL;
|
|
processor = errorProcessor;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
bufferLim = buffer + len * 2;
|
|
}
|
|
memcpy(buffer, end, nLeftOver);
|
|
}
|
|
bufferPtr = buffer;
|
|
bufferEnd = buffer + nLeftOver;
|
|
positionPtr = bufferPtr;
|
|
parseEndPtr = bufferEnd;
|
|
eventPtr = bufferPtr;
|
|
eventEndPtr = bufferPtr;
|
|
return result;
|
|
}
|
|
#endif /* not defined XML_CONTEXT_BYTES */
|
|
else {
|
|
void *buff = XML_GetBuffer(parser, len);
|
|
if (buff == NULL)
|
|
return XML_STATUS_ERROR;
|
|
else {
|
|
memcpy(buff, s, len);
|
|
return XML_ParseBuffer(parser, len, isFinal);
|
|
}
|
|
}
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_ParseBuffer(XML_Parser parser, int len, int isFinal)
|
|
{
|
|
const char *start;
|
|
enum XML_Status result = XML_STATUS_OK;
|
|
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
errorCode = XML_ERROR_SUSPENDED;
|
|
return XML_STATUS_ERROR;
|
|
case XML_FINISHED:
|
|
errorCode = XML_ERROR_FINISHED;
|
|
return XML_STATUS_ERROR;
|
|
default:
|
|
ps_parsing = XML_PARSING;
|
|
}
|
|
|
|
start = bufferPtr;
|
|
positionPtr = start;
|
|
bufferEnd += len;
|
|
parseEndPtr = bufferEnd;
|
|
parseEndByteIndex += len;
|
|
ps_finalBuffer = (XML_Bool)isFinal;
|
|
|
|
errorCode = processor(parser, start, parseEndPtr, &bufferPtr);
|
|
|
|
if (errorCode != XML_ERROR_NONE) {
|
|
eventEndPtr = eventPtr;
|
|
processor = errorProcessor;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
else {
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
result = XML_STATUS_SUSPENDED;
|
|
break;
|
|
case XML_INITIALIZED:
|
|
case XML_PARSING:
|
|
if (isFinal) {
|
|
ps_parsing = XML_FINISHED;
|
|
return result;
|
|
}
|
|
default: ; /* should not happen */
|
|
}
|
|
}
|
|
|
|
XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
|
|
positionPtr = bufferPtr;
|
|
return result;
|
|
}
|
|
|
|
void * XMLCALL
|
|
XML_GetBuffer(XML_Parser parser, int len)
|
|
{
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
errorCode = XML_ERROR_SUSPENDED;
|
|
return NULL;
|
|
case XML_FINISHED:
|
|
errorCode = XML_ERROR_FINISHED;
|
|
return NULL;
|
|
default: ;
|
|
}
|
|
|
|
if (len > bufferLim - bufferEnd) {
|
|
/* FIXME avoid integer overflow */
|
|
int neededSize = len + (int)(bufferEnd - bufferPtr);
|
|
#ifdef XML_CONTEXT_BYTES
|
|
int keep = (int)(bufferPtr - buffer);
|
|
|
|
if (keep > XML_CONTEXT_BYTES)
|
|
keep = XML_CONTEXT_BYTES;
|
|
neededSize += keep;
|
|
#endif /* defined XML_CONTEXT_BYTES */
|
|
if (neededSize <= bufferLim - buffer) {
|
|
#ifdef XML_CONTEXT_BYTES
|
|
if (keep < bufferPtr - buffer) {
|
|
int offset = (int)(bufferPtr - buffer) - keep;
|
|
memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep);
|
|
bufferEnd -= offset;
|
|
bufferPtr -= offset;
|
|
}
|
|
#else
|
|
memmove(buffer, bufferPtr, bufferEnd - bufferPtr);
|
|
bufferEnd = buffer + (bufferEnd - bufferPtr);
|
|
bufferPtr = buffer;
|
|
#endif /* not defined XML_CONTEXT_BYTES */
|
|
}
|
|
else {
|
|
char *newBuf;
|
|
int bufferSize = (int)(bufferLim - bufferPtr);
|
|
if (bufferSize == 0)
|
|
bufferSize = INIT_BUFFER_SIZE;
|
|
do {
|
|
bufferSize *= 2;
|
|
} while (bufferSize < neededSize);
|
|
newBuf = (char *)MALLOC(bufferSize);
|
|
if (newBuf == 0) {
|
|
errorCode = XML_ERROR_NO_MEMORY;
|
|
return NULL;
|
|
}
|
|
bufferLim = newBuf + bufferSize;
|
|
#ifdef XML_CONTEXT_BYTES
|
|
if (bufferPtr) {
|
|
int keep = (int)(bufferPtr - buffer);
|
|
if (keep > XML_CONTEXT_BYTES)
|
|
keep = XML_CONTEXT_BYTES;
|
|
memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep);
|
|
FREE(buffer);
|
|
buffer = newBuf;
|
|
bufferEnd = buffer + (bufferEnd - bufferPtr) + keep;
|
|
bufferPtr = buffer + keep;
|
|
}
|
|
else {
|
|
bufferEnd = newBuf + (bufferEnd - bufferPtr);
|
|
bufferPtr = buffer = newBuf;
|
|
}
|
|
#else
|
|
if (bufferPtr) {
|
|
memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr);
|
|
FREE(buffer);
|
|
}
|
|
bufferEnd = newBuf + (bufferEnd - bufferPtr);
|
|
bufferPtr = buffer = newBuf;
|
|
#endif /* not defined XML_CONTEXT_BYTES */
|
|
}
|
|
}
|
|
return bufferEnd;
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_StopParser(XML_Parser parser, XML_Bool resumable)
|
|
{
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
if (resumable) {
|
|
errorCode = XML_ERROR_SUSPENDED;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
ps_parsing = XML_FINISHED;
|
|
break;
|
|
case XML_FINISHED:
|
|
errorCode = XML_ERROR_FINISHED;
|
|
return XML_STATUS_ERROR;
|
|
default:
|
|
if (resumable) {
|
|
#ifdef XML_DTD
|
|
if (isParamEntity) {
|
|
errorCode = XML_ERROR_SUSPEND_PE;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
#endif
|
|
ps_parsing = XML_SUSPENDED;
|
|
}
|
|
else
|
|
ps_parsing = XML_FINISHED;
|
|
}
|
|
return XML_STATUS_OK;
|
|
}
|
|
|
|
enum XML_Status XMLCALL
|
|
XML_ResumeParser(XML_Parser parser)
|
|
{
|
|
enum XML_Status result = XML_STATUS_OK;
|
|
|
|
if (ps_parsing != XML_SUSPENDED) {
|
|
errorCode = XML_ERROR_NOT_SUSPENDED;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
ps_parsing = XML_PARSING;
|
|
|
|
errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
|
|
|
|
if (errorCode != XML_ERROR_NONE) {
|
|
eventEndPtr = eventPtr;
|
|
processor = errorProcessor;
|
|
return XML_STATUS_ERROR;
|
|
}
|
|
else {
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
result = XML_STATUS_SUSPENDED;
|
|
break;
|
|
case XML_INITIALIZED:
|
|
case XML_PARSING:
|
|
if (ps_finalBuffer) {
|
|
ps_parsing = XML_FINISHED;
|
|
return result;
|
|
}
|
|
default: ;
|
|
}
|
|
}
|
|
|
|
XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
|
|
positionPtr = bufferPtr;
|
|
return result;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status)
|
|
{
|
|
assert(status != NULL);
|
|
*status = parser->m_parsingStatus;
|
|
}
|
|
|
|
enum XML_Error XMLCALL
|
|
XML_GetErrorCode(XML_Parser parser)
|
|
{
|
|
return errorCode;
|
|
}
|
|
|
|
XML_Index XMLCALL
|
|
XML_GetCurrentByteIndex(XML_Parser parser)
|
|
{
|
|
if (eventPtr)
|
|
return parseEndByteIndex - (parseEndPtr - eventPtr);
|
|
return -1;
|
|
}
|
|
|
|
int XMLCALL
|
|
XML_GetCurrentByteCount(XML_Parser parser)
|
|
{
|
|
if (eventEndPtr && eventPtr)
|
|
return (int)(eventEndPtr - eventPtr);
|
|
return 0;
|
|
}
|
|
|
|
const char * XMLCALL
|
|
XML_GetInputContext(XML_Parser parser, int *offset, int *size)
|
|
{
|
|
#ifdef XML_CONTEXT_BYTES
|
|
if (eventPtr && buffer) {
|
|
*offset = (int)(eventPtr - buffer);
|
|
*size = (int)(bufferEnd - buffer);
|
|
return buffer;
|
|
}
|
|
#endif /* defined XML_CONTEXT_BYTES */
|
|
return (char *) 0;
|
|
}
|
|
|
|
XML_Size XMLCALL
|
|
XML_GetCurrentLineNumber(XML_Parser parser)
|
|
{
|
|
if (eventPtr && eventPtr >= positionPtr) {
|
|
XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
|
|
positionPtr = eventPtr;
|
|
}
|
|
return position.lineNumber + 1;
|
|
}
|
|
|
|
XML_Size XMLCALL
|
|
XML_GetCurrentColumnNumber(XML_Parser parser)
|
|
{
|
|
if (eventPtr && eventPtr >= positionPtr) {
|
|
XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
|
|
positionPtr = eventPtr;
|
|
}
|
|
return position.columnNumber;
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_FreeContentModel(XML_Parser parser, XML_Content *model)
|
|
{
|
|
FREE(model);
|
|
}
|
|
|
|
void * XMLCALL
|
|
XML_MemMalloc(XML_Parser parser, size_t size)
|
|
{
|
|
return MALLOC(size);
|
|
}
|
|
|
|
void * XMLCALL
|
|
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size)
|
|
{
|
|
return REALLOC(ptr, size);
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_MemFree(XML_Parser parser, void *ptr)
|
|
{
|
|
FREE(ptr);
|
|
}
|
|
|
|
void XMLCALL
|
|
XML_DefaultCurrent(XML_Parser parser)
|
|
{
|
|
if (defaultHandler) {
|
|
if (openInternalEntities)
|
|
reportDefault(parser,
|
|
internalEncoding,
|
|
openInternalEntities->internalEventPtr,
|
|
openInternalEntities->internalEventEndPtr);
|
|
else
|
|
reportDefault(parser, encoding, eventPtr, eventEndPtr);
|
|
}
|
|
}
|
|
|
|
const XML_LChar * XMLCALL
|
|
XML_ErrorString(enum XML_Error code)
|
|
{
|
|
static const XML_LChar* const message[] = {
|
|
0,
|
|
XML_L("out of memory"),
|
|
XML_L("syntax error"),
|
|
XML_L("no element found"),
|
|
XML_L("not well-formed (invalid token)"),
|
|
XML_L("unclosed token"),
|
|
XML_L("partial character"),
|
|
XML_L("mismatched tag"),
|
|
XML_L("duplicate attribute"),
|
|
XML_L("junk after document element"),
|
|
XML_L("illegal parameter entity reference"),
|
|
XML_L("undefined entity"),
|
|
XML_L("recursive entity reference"),
|
|
XML_L("asynchronous entity"),
|
|
XML_L("reference to invalid character number"),
|
|
XML_L("reference to binary entity"),
|
|
XML_L("reference to external entity in attribute"),
|
|
XML_L("XML or text declaration not at start of entity"),
|
|
XML_L("unknown encoding"),
|
|
XML_L("encoding specified in XML declaration is incorrect"),
|
|
XML_L("unclosed CDATA section"),
|
|
XML_L("error in processing external entity reference"),
|
|
XML_L("document is not standalone"),
|
|
XML_L("unexpected parser state - please send a bug report"),
|
|
XML_L("entity declared in parameter entity"),
|
|
XML_L("requested feature requires XML_DTD support in Expat"),
|
|
XML_L("cannot change setting once parsing has begun"),
|
|
XML_L("unbound prefix"),
|
|
XML_L("must not undeclare prefix"),
|
|
XML_L("incomplete markup in parameter entity"),
|
|
XML_L("XML declaration not well-formed"),
|
|
XML_L("text declaration not well-formed"),
|
|
XML_L("illegal character(s) in public id"),
|
|
XML_L("parser suspended"),
|
|
XML_L("parser not suspended"),
|
|
XML_L("parsing aborted"),
|
|
XML_L("parsing finished"),
|
|
XML_L("cannot suspend in external parameter entity"),
|
|
XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"),
|
|
XML_L("reserved prefix (xmlns) must not be declared or undeclared"),
|
|
XML_L("prefix must not be bound to one of the reserved namespace names")
|
|
};
|
|
if (code > 0 && code < sizeof(message)/sizeof(message[0]))
|
|
return message[code];
|
|
return NULL;
|
|
}
|
|
|
|
const XML_LChar * XMLCALL
|
|
XML_ExpatVersion(void) {
|
|
|
|
/* V1 is used to string-ize the version number. However, it would
|
|
string-ize the actual version macro *names* unless we get them
|
|
substituted before being passed to V1. CPP is defined to expand
|
|
a macro, then rescan for more expansions. Thus, we use V2 to expand
|
|
the version macros, then CPP will expand the resulting V1() macro
|
|
with the correct numerals. */
|
|
/* ### I'm assuming cpp is portable in this respect... */
|
|
|
|
#define V1(a,b,c) XML_L(#a)XML_L(".")XML_L(#b)XML_L(".")XML_L(#c)
|
|
#define V2(a,b,c) XML_L("expat_")V1(a,b,c)
|
|
|
|
return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION);
|
|
|
|
#undef V1
|
|
#undef V2
|
|
}
|
|
|
|
XML_Expat_Version XMLCALL
|
|
XML_ExpatVersionInfo(void)
|
|
{
|
|
XML_Expat_Version version;
|
|
|
|
version.major = XML_MAJOR_VERSION;
|
|
version.minor = XML_MINOR_VERSION;
|
|
version.micro = XML_MICRO_VERSION;
|
|
|
|
return version;
|
|
}
|
|
|
|
const XML_Feature * XMLCALL
|
|
XML_GetFeatureList(void)
|
|
{
|
|
static const XML_Feature features[] = {
|
|
{XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"),
|
|
sizeof(XML_Char)},
|
|
{XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"),
|
|
sizeof(XML_LChar)},
|
|
#ifdef XML_UNICODE
|
|
{XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0},
|
|
#endif
|
|
#ifdef XML_UNICODE_WCHAR_T
|
|
{XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0},
|
|
#endif
|
|
#ifdef XML_DTD
|
|
{XML_FEATURE_DTD, XML_L("XML_DTD"), 0},
|
|
#endif
|
|
#ifdef XML_CONTEXT_BYTES
|
|
{XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"),
|
|
XML_CONTEXT_BYTES},
|
|
#endif
|
|
#ifdef XML_MIN_SIZE
|
|
{XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0},
|
|
#endif
|
|
#ifdef XML_NS
|
|
{XML_FEATURE_NS, XML_L("XML_NS"), 0},
|
|
#endif
|
|
{XML_FEATURE_END, NULL, 0}
|
|
};
|
|
|
|
return features;
|
|
}
|
|
|
|
/* Initially tag->rawName always points into the parse buffer;
|
|
for those TAG instances opened while the current parse buffer was
|
|
processed, and not yet closed, we need to store tag->rawName in a more
|
|
permanent location, since the parse buffer is about to be discarded.
|
|
*/
|
|
static XML_Bool
|
|
storeRawNames(XML_Parser parser)
|
|
{
|
|
TAG *tag = tagStack;
|
|
while (tag) {
|
|
int bufSize;
|
|
int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1);
|
|
char *rawNameBuf = tag->buf + nameLen;
|
|
/* Stop if already stored. Since tagStack is a stack, we can stop
|
|
at the first entry that has already been copied; everything
|
|
below it in the stack is already been accounted for in a
|
|
previous call to this function.
|
|
*/
|
|
if (tag->rawName == rawNameBuf)
|
|
break;
|
|
/* For re-use purposes we need to ensure that the
|
|
size of tag->buf is a multiple of sizeof(XML_Char).
|
|
*/
|
|
bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char));
|
|
if (bufSize > tag->bufEnd - tag->buf) {
|
|
char *temp = (char *)REALLOC(tag->buf, bufSize);
|
|
if (temp == NULL)
|
|
return XML_FALSE;
|
|
/* if tag->name.str points to tag->buf (only when namespace
|
|
processing is off) then we have to update it
|
|
*/
|
|
if (tag->name.str == (XML_Char *)tag->buf)
|
|
tag->name.str = (XML_Char *)temp;
|
|
/* if tag->name.localPart is set (when namespace processing is on)
|
|
then update it as well, since it will always point into tag->buf
|
|
*/
|
|
if (tag->name.localPart)
|
|
tag->name.localPart = (XML_Char *)temp + (tag->name.localPart -
|
|
(XML_Char *)tag->buf);
|
|
tag->buf = temp;
|
|
tag->bufEnd = temp + bufSize;
|
|
rawNameBuf = temp + nameLen;
|
|
}
|
|
memcpy(rawNameBuf, tag->rawName, tag->rawNameLength);
|
|
tag->rawName = rawNameBuf;
|
|
tag = tag->parent;
|
|
}
|
|
return XML_TRUE;
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
contentProcessor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
enum XML_Error result = doContent(parser, 0, encoding, start, end,
|
|
endPtr, (XML_Bool)!ps_finalBuffer);
|
|
if (result == XML_ERROR_NONE) {
|
|
if (!storeRawNames(parser))
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalEntityInitProcessor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
enum XML_Error result = initializeEncoding(parser);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
processor = externalEntityInitProcessor2;
|
|
return externalEntityInitProcessor2(parser, start, end, endPtr);
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalEntityInitProcessor2(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
const char *next = start; /* XmlContentTok doesn't always set the last arg */
|
|
int tok = XmlContentTok(encoding, start, end, &next);
|
|
switch (tok) {
|
|
case XML_TOK_BOM:
|
|
/* If we are at the end of the buffer, this would cause the next stage,
|
|
i.e. externalEntityInitProcessor3, to pass control directly to
|
|
doContent (by detecting XML_TOK_NONE) without processing any xml text
|
|
declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent.
|
|
*/
|
|
if (next == end && !ps_finalBuffer) {
|
|
*endPtr = next;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
start = next;
|
|
break;
|
|
case XML_TOK_PARTIAL:
|
|
if (!ps_finalBuffer) {
|
|
*endPtr = start;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
eventPtr = start;
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (!ps_finalBuffer) {
|
|
*endPtr = start;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
eventPtr = start;
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
}
|
|
processor = externalEntityInitProcessor3;
|
|
return externalEntityInitProcessor3(parser, start, end, endPtr);
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalEntityInitProcessor3(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
int tok;
|
|
const char *next = start; /* XmlContentTok doesn't always set the last arg */
|
|
eventPtr = start;
|
|
tok = XmlContentTok(encoding, start, end, &next);
|
|
eventEndPtr = next;
|
|
|
|
switch (tok) {
|
|
case XML_TOK_XML_DECL:
|
|
{
|
|
enum XML_Error result;
|
|
result = processXmlDecl(parser, 1, start, next);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*endPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default:
|
|
start = next;
|
|
}
|
|
}
|
|
break;
|
|
case XML_TOK_PARTIAL:
|
|
if (!ps_finalBuffer) {
|
|
*endPtr = start;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (!ps_finalBuffer) {
|
|
*endPtr = start;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
}
|
|
processor = externalEntityContentProcessor;
|
|
tagLevel = 1;
|
|
return externalEntityContentProcessor(parser, start, end, endPtr);
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalEntityContentProcessor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
enum XML_Error result = doContent(parser, 1, encoding, start, end,
|
|
endPtr, (XML_Bool)!ps_finalBuffer);
|
|
if (result == XML_ERROR_NONE) {
|
|
if (!storeRawNames(parser))
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
static enum XML_Error
|
|
doContent(XML_Parser parser,
|
|
int startTagLevel,
|
|
const ENCODING *enc,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr,
|
|
XML_Bool haveMore)
|
|
{
|
|
/* save one level of indirection */
|
|
DTD * const dtd = _dtd;
|
|
|
|
const char **eventPP;
|
|
const char **eventEndPP;
|
|
if (enc == encoding) {
|
|
eventPP = &eventPtr;
|
|
eventEndPP = &eventEndPtr;
|
|
}
|
|
else {
|
|
eventPP = &(openInternalEntities->internalEventPtr);
|
|
eventEndPP = &(openInternalEntities->internalEventEndPtr);
|
|
}
|
|
*eventPP = s;
|
|
|
|
for (;;) {
|
|
const char *next = s; /* XmlContentTok doesn't always set the last arg */
|
|
int tok = XmlContentTok(enc, s, end, &next);
|
|
*eventEndPP = next;
|
|
switch (tok) {
|
|
case XML_TOK_TRAILING_CR:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
*eventEndPP = end;
|
|
if (characterDataHandler) {
|
|
XML_Char c = 0xA;
|
|
characterDataHandler(handlerArg, &c, 1);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, end);
|
|
/* We are at the end of the final buffer, should we check for
|
|
XML_SUSPENDED, XML_FINISHED?
|
|
*/
|
|
if (startTagLevel == 0)
|
|
return XML_ERROR_NO_ELEMENTS;
|
|
if (tagLevel != startTagLevel)
|
|
return XML_ERROR_ASYNC_ENTITY;
|
|
*nextPtr = end;
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_NONE:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
if (startTagLevel > 0) {
|
|
if (tagLevel != startTagLevel)
|
|
return XML_ERROR_ASYNC_ENTITY;
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_NO_ELEMENTS;
|
|
case XML_TOK_INVALID:
|
|
*eventPP = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_ENTITY_REF:
|
|
{
|
|
const XML_Char *name;
|
|
ENTITY *entity;
|
|
XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (ch) {
|
|
if (characterDataHandler)
|
|
characterDataHandler(handlerArg, &ch, 1);
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
}
|
|
name = poolStoreString(&dtd->pool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
entity = (ENTITY *)lookup(&dtd->generalEntities, name, 0);
|
|
poolDiscard(&dtd->pool);
|
|
/* First, determine if a check for an existing declaration is needed;
|
|
if yes, check that the entity exists, and that it is internal,
|
|
otherwise call the skipped entity or default handler.
|
|
*/
|
|
if (!dtd->hasParamEntityRefs || dtd->standalone) {
|
|
if (!entity)
|
|
return XML_ERROR_UNDEFINED_ENTITY;
|
|
else if (!entity->is_internal)
|
|
return XML_ERROR_ENTITY_DECLARED_IN_PE;
|
|
}
|
|
else if (!entity) {
|
|
if (skippedEntityHandler)
|
|
skippedEntityHandler(handlerArg, name, 0);
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
}
|
|
if (entity->open)
|
|
return XML_ERROR_RECURSIVE_ENTITY_REF;
|
|
if (entity->notation)
|
|
return XML_ERROR_BINARY_ENTITY_REF;
|
|
if (entity->textPtr) {
|
|
enum XML_Error result;
|
|
if (!defaultExpandInternalEntities) {
|
|
if (skippedEntityHandler)
|
|
skippedEntityHandler(handlerArg, entity->name, 0);
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
}
|
|
result = processInternalEntity(parser, entity, XML_FALSE);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
}
|
|
else if (externalEntityRefHandler) {
|
|
const XML_Char *context;
|
|
entity->open = XML_TRUE;
|
|
context = getContext(parser);
|
|
entity->open = XML_FALSE;
|
|
if (!context)
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
|
|
context,
|
|
entity->base,
|
|
entity->systemId,
|
|
entity->publicId))
|
|
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
|
|
poolDiscard(&tempPool);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
}
|
|
case XML_TOK_START_TAG_NO_ATTS:
|
|
/* fall through */
|
|
case XML_TOK_START_TAG_WITH_ATTS:
|
|
{
|
|
TAG *tag;
|
|
enum XML_Error result;
|
|
XML_Char *toPtr;
|
|
if (freeTagList) {
|
|
tag = freeTagList;
|
|
freeTagList = freeTagList->parent;
|
|
}
|
|
else {
|
|
tag = (TAG *)MALLOC(sizeof(TAG));
|
|
if (!tag)
|
|
return XML_ERROR_NO_MEMORY;
|
|
tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE);
|
|
if (!tag->buf) {
|
|
FREE(tag);
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
|
|
}
|
|
tag->bindings = NULL;
|
|
tag->parent = tagStack;
|
|
tagStack = tag;
|
|
tag->name.localPart = NULL;
|
|
tag->name.prefix = NULL;
|
|
tag->rawName = s + enc->minBytesPerChar;
|
|
tag->rawNameLength = XmlNameLength(enc, tag->rawName);
|
|
++tagLevel;
|
|
{
|
|
const char *rawNameEnd = tag->rawName + tag->rawNameLength;
|
|
const char *fromPtr = tag->rawName;
|
|
toPtr = (XML_Char *)tag->buf;
|
|
for (;;) {
|
|
int bufSize;
|
|
int convLen;
|
|
XmlConvert(enc,
|
|
&fromPtr, rawNameEnd,
|
|
(ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
|
|
convLen = (int)(toPtr - (XML_Char *)tag->buf);
|
|
if (fromPtr == rawNameEnd) {
|
|
tag->name.strLen = convLen;
|
|
break;
|
|
}
|
|
bufSize = (int)(tag->bufEnd - tag->buf) << 1;
|
|
{
|
|
char *temp = (char *)REALLOC(tag->buf, bufSize);
|
|
if (temp == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
tag->buf = temp;
|
|
tag->bufEnd = temp + bufSize;
|
|
toPtr = (XML_Char *)temp + convLen;
|
|
}
|
|
}
|
|
}
|
|
tag->name.str = (XML_Char *)tag->buf;
|
|
*toPtr = XML_T('\0');
|
|
result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
|
|
if (result)
|
|
return result;
|
|
if (startElementHandler)
|
|
startElementHandler(handlerArg, tag->name.str,
|
|
(const XML_Char **)atts);
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
poolClear(&tempPool);
|
|
break;
|
|
}
|
|
case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
|
|
/* fall through */
|
|
case XML_TOK_EMPTY_ELEMENT_WITH_ATTS:
|
|
{
|
|
const char *rawName = s + enc->minBytesPerChar;
|
|
enum XML_Error result;
|
|
BINDING *bindings = NULL;
|
|
XML_Bool noElmHandlers = XML_TRUE;
|
|
TAG_NAME name;
|
|
name.str = poolStoreString(&tempPool, enc, rawName,
|
|
rawName + XmlNameLength(enc, rawName));
|
|
if (!name.str)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&tempPool);
|
|
result = storeAtts(parser, enc, s, &name, &bindings);
|
|
if (result)
|
|
return result;
|
|
poolFinish(&tempPool);
|
|
if (startElementHandler) {
|
|
startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
|
|
noElmHandlers = XML_FALSE;
|
|
}
|
|
if (endElementHandler) {
|
|
if (startElementHandler)
|
|
*eventPP = *eventEndPP;
|
|
endElementHandler(handlerArg, name.str);
|
|
noElmHandlers = XML_FALSE;
|
|
}
|
|
if (noElmHandlers && defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
poolClear(&tempPool);
|
|
while (bindings) {
|
|
BINDING *b = bindings;
|
|
if (endNamespaceDeclHandler)
|
|
endNamespaceDeclHandler(handlerArg, b->prefix->name);
|
|
bindings = bindings->nextTagBinding;
|
|
b->nextTagBinding = freeBindingList;
|
|
freeBindingList = b;
|
|
b->prefix->binding = b->prevPrefixBinding;
|
|
}
|
|
}
|
|
if (tagLevel == 0)
|
|
return epilogProcessor(parser, next, end, nextPtr);
|
|
break;
|
|
case XML_TOK_END_TAG:
|
|
if (tagLevel == startTagLevel)
|
|
return XML_ERROR_ASYNC_ENTITY;
|
|
else {
|
|
int len;
|
|
const char *rawName;
|
|
TAG *tag = tagStack;
|
|
tagStack = tag->parent;
|
|
tag->parent = freeTagList;
|
|
freeTagList = tag;
|
|
rawName = s + enc->minBytesPerChar*2;
|
|
len = XmlNameLength(enc, rawName);
|
|
if (len != tag->rawNameLength
|
|
|| memcmp(tag->rawName, rawName, len) != 0) {
|
|
*eventPP = rawName;
|
|
return XML_ERROR_TAG_MISMATCH;
|
|
}
|
|
--tagLevel;
|
|
if (endElementHandler) {
|
|
const XML_Char *localPart;
|
|
const XML_Char *prefix;
|
|
XML_Char *uri;
|
|
localPart = tag->name.localPart;
|
|
if (ns && localPart) {
|
|
/* localPart and prefix may have been overwritten in
|
|
tag->name.str, since this points to the binding->uri
|
|
buffer which gets re-used; so we have to add them again
|
|
*/
|
|
uri = (XML_Char *)tag->name.str + tag->name.uriLen;
|
|
/* don't need to check for space - already done in storeAtts() */
|
|
while (*localPart) *uri++ = *localPart++;
|
|
prefix = (XML_Char *)tag->name.prefix;
|
|
if (ns_triplets && prefix) {
|
|
*uri++ = namespaceSeparator;
|
|
while (*prefix) *uri++ = *prefix++;
|
|
}
|
|
*uri = XML_T('\0');
|
|
}
|
|
endElementHandler(handlerArg, tag->name.str);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
while (tag->bindings) {
|
|
BINDING *b = tag->bindings;
|
|
if (endNamespaceDeclHandler)
|
|
endNamespaceDeclHandler(handlerArg, b->prefix->name);
|
|
tag->bindings = tag->bindings->nextTagBinding;
|
|
b->nextTagBinding = freeBindingList;
|
|
freeBindingList = b;
|
|
b->prefix->binding = b->prevPrefixBinding;
|
|
}
|
|
if (tagLevel == 0)
|
|
return epilogProcessor(parser, next, end, nextPtr);
|
|
}
|
|
break;
|
|
case XML_TOK_CHAR_REF:
|
|
{
|
|
int n = XmlCharRefNumber(enc, s);
|
|
if (n < 0)
|
|
return XML_ERROR_BAD_CHAR_REF;
|
|
if (characterDataHandler) {
|
|
XML_Char buf[XML_ENCODE_MAX];
|
|
characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
}
|
|
break;
|
|
case XML_TOK_XML_DECL:
|
|
return XML_ERROR_MISPLACED_XML_PI;
|
|
case XML_TOK_DATA_NEWLINE:
|
|
if (characterDataHandler) {
|
|
XML_Char c = 0xA;
|
|
characterDataHandler(handlerArg, &c, 1);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
case XML_TOK_CDATA_SECT_OPEN:
|
|
{
|
|
enum XML_Error result;
|
|
if (startCdataSectionHandler)
|
|
startCdataSectionHandler(handlerArg);
|
|
#if 0
|
|
/* Suppose you doing a transformation on a document that involves
|
|
changing only the character data. You set up a defaultHandler
|
|
and a characterDataHandler. The defaultHandler simply copies
|
|
characters through. The characterDataHandler does the
|
|
transformation and writes the characters out escaping them as
|
|
necessary. This case will fail to work if we leave out the
|
|
following two lines (because & and < inside CDATA sections will
|
|
be incorrectly escaped).
|
|
|
|
However, now we have a start/endCdataSectionHandler, so it seems
|
|
easier to let the user deal with this.
|
|
*/
|
|
else if (characterDataHandler)
|
|
characterDataHandler(handlerArg, dataBuf, 0);
|
|
#endif
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
else if (!next) {
|
|
processor = cdataSectionProcessor;
|
|
return result;
|
|
}
|
|
}
|
|
break;
|
|
case XML_TOK_TRAILING_RSQB:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
if (characterDataHandler) {
|
|
if (MUST_CONVERT(enc, s)) {
|
|
ICHAR *dataPtr = (ICHAR *)dataBuf;
|
|
XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
|
|
characterDataHandler(handlerArg, dataBuf,
|
|
(int)(dataPtr - (ICHAR *)dataBuf));
|
|
}
|
|
else
|
|
characterDataHandler(handlerArg,
|
|
(XML_Char *)s,
|
|
(int)((XML_Char *)end - (XML_Char *)s));
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, end);
|
|
/* We are at the end of the final buffer, should we check for
|
|
XML_SUSPENDED, XML_FINISHED?
|
|
*/
|
|
if (startTagLevel == 0) {
|
|
*eventPP = end;
|
|
return XML_ERROR_NO_ELEMENTS;
|
|
}
|
|
if (tagLevel != startTagLevel) {
|
|
*eventPP = end;
|
|
return XML_ERROR_ASYNC_ENTITY;
|
|
}
|
|
*nextPtr = end;
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_DATA_CHARS:
|
|
if (characterDataHandler) {
|
|
if (MUST_CONVERT(enc, s)) {
|
|
for (;;) {
|
|
ICHAR *dataPtr = (ICHAR *)dataBuf;
|
|
XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
|
|
*eventEndPP = s;
|
|
characterDataHandler(handlerArg, dataBuf,
|
|
(int)(dataPtr - (ICHAR *)dataBuf));
|
|
if (s == next)
|
|
break;
|
|
*eventPP = s;
|
|
}
|
|
}
|
|
else
|
|
characterDataHandler(handlerArg,
|
|
(XML_Char *)s,
|
|
(int)((XML_Char *)next - (XML_Char *)s));
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
case XML_TOK_PI:
|
|
if (!reportProcessingInstruction(parser, enc, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
case XML_TOK_COMMENT:
|
|
if (!reportComment(parser, enc, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
default:
|
|
if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
}
|
|
*eventPP = s = next;
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default: ;
|
|
}
|
|
}
|
|
/* not reached */
|
|
}
|
|
|
|
/* Precondition: all arguments must be non-NULL;
|
|
Purpose:
|
|
- normalize attributes
|
|
- check attributes for well-formedness
|
|
- generate namespace aware attribute names (URI, prefix)
|
|
- build list of attributes for startElementHandler
|
|
- default attributes
|
|
- process namespace declarations (check and report them)
|
|
- generate namespace aware element name (URI, prefix)
|
|
*/
|
|
static enum XML_Error
|
|
storeAtts(XML_Parser parser, const ENCODING *enc,
|
|
const char *attStr, TAG_NAME *tagNamePtr,
|
|
BINDING **bindingsPtr)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
ELEMENT_TYPE *elementType;
|
|
int nDefaultAtts;
|
|
const XML_Char **appAtts; /* the attribute list for the application */
|
|
int attIndex = 0;
|
|
int prefixLen;
|
|
int i;
|
|
int n;
|
|
XML_Char *uri;
|
|
int nPrefixes = 0;
|
|
BINDING *binding;
|
|
const XML_Char *localPart;
|
|
|
|
/* lookup the element type name */
|
|
elementType = (ELEMENT_TYPE *)lookup(&dtd->elementTypes, tagNamePtr->str,0);
|
|
if (!elementType) {
|
|
const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
elementType = (ELEMENT_TYPE *)lookup(&dtd->elementTypes, name,
|
|
sizeof(ELEMENT_TYPE));
|
|
if (!elementType)
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (ns && !setElementTypePrefix(parser, elementType))
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
nDefaultAtts = elementType->nDefaultAtts;
|
|
|
|
/* get the attributes from the tokenizer */
|
|
n = XmlGetAttributes(enc, attStr, attsSize, atts);
|
|
if (n + nDefaultAtts > attsSize) {
|
|
int oldAttsSize = attsSize;
|
|
ATTRIBUTE *temp;
|
|
attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
|
|
temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE));
|
|
if (temp == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
atts = temp;
|
|
if (n > oldAttsSize)
|
|
XmlGetAttributes(enc, attStr, n, atts);
|
|
}
|
|
|
|
appAtts = (const XML_Char **)atts;
|
|
for (i = 0; i < n; i++) {
|
|
/* add the name and value to the attribute list */
|
|
ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name,
|
|
atts[i].name
|
|
+ XmlNameLength(enc, atts[i].name));
|
|
if (!attId)
|
|
return XML_ERROR_NO_MEMORY;
|
|
/* Detect duplicate attributes by their QNames. This does not work when
|
|
namespace processing is turned on and different prefixes for the same
|
|
namespace are used. For this case we have a check further down.
|
|
*/
|
|
if ((attId->name)[-1]) {
|
|
if (enc == encoding)
|
|
eventPtr = atts[i].name;
|
|
return XML_ERROR_DUPLICATE_ATTRIBUTE;
|
|
}
|
|
(attId->name)[-1] = 1;
|
|
appAtts[attIndex++] = attId->name;
|
|
if (!atts[i].normalized) {
|
|
enum XML_Error result;
|
|
XML_Bool isCdata = XML_TRUE;
|
|
|
|
/* figure out whether declared as other than CDATA */
|
|
if (attId->maybeTokenized) {
|
|
int j;
|
|
for (j = 0; j < nDefaultAtts; j++) {
|
|
if (attId == elementType->defaultAtts[j].id) {
|
|
isCdata = elementType->defaultAtts[j].isCdata;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* normalize the attribute value */
|
|
result = storeAttributeValue(parser, enc, isCdata,
|
|
atts[i].valuePtr, atts[i].valueEnd,
|
|
&tempPool);
|
|
if (result)
|
|
return result;
|
|
appAtts[attIndex] = poolStart(&tempPool);
|
|
poolFinish(&tempPool);
|
|
}
|
|
else {
|
|
/* the value did not need normalizing */
|
|
appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr,
|
|
atts[i].valueEnd);
|
|
if (appAtts[attIndex] == 0)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&tempPool);
|
|
}
|
|
/* handle prefixed attribute names */
|
|
if (attId->prefix) {
|
|
if (attId->xmlns) {
|
|
/* deal with namespace declarations here */
|
|
enum XML_Error result = addBinding(parser, attId->prefix, attId,
|
|
appAtts[attIndex], bindingsPtr);
|
|
if (result)
|
|
return result;
|
|
--attIndex;
|
|
}
|
|
else {
|
|
/* deal with other prefixed names later */
|
|
attIndex++;
|
|
nPrefixes++;
|
|
(attId->name)[-1] = 2;
|
|
}
|
|
}
|
|
else
|
|
attIndex++;
|
|
}
|
|
|
|
/* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */
|
|
nSpecifiedAtts = attIndex;
|
|
if (elementType->idAtt && (elementType->idAtt->name)[-1]) {
|
|
for (i = 0; i < attIndex; i += 2)
|
|
if (appAtts[i] == elementType->idAtt->name) {
|
|
idAttIndex = i;
|
|
break;
|
|
}
|
|
}
|
|
else
|
|
idAttIndex = -1;
|
|
|
|
/* do attribute defaulting */
|
|
for (i = 0; i < nDefaultAtts; i++) {
|
|
const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i;
|
|
if (!(da->id->name)[-1] && da->value) {
|
|
if (da->id->prefix) {
|
|
if (da->id->xmlns) {
|
|
enum XML_Error result = addBinding(parser, da->id->prefix, da->id,
|
|
da->value, bindingsPtr);
|
|
if (result)
|
|
return result;
|
|
}
|
|
else {
|
|
(da->id->name)[-1] = 2;
|
|
nPrefixes++;
|
|
appAtts[attIndex++] = da->id->name;
|
|
appAtts[attIndex++] = da->value;
|
|
}
|
|
}
|
|
else {
|
|
(da->id->name)[-1] = 1;
|
|
appAtts[attIndex++] = da->id->name;
|
|
appAtts[attIndex++] = da->value;
|
|
}
|
|
}
|
|
}
|
|
appAtts[attIndex] = 0;
|
|
|
|
/* expand prefixed attribute names, check for duplicates,
|
|
and clear flags that say whether attributes were specified */
|
|
i = 0;
|
|
if (nPrefixes) {
|
|
int j; /* hash table index */
|
|
unsigned long version = nsAttsVersion;
|
|
int nsAttsSize = (int)1 << nsAttsPower;
|
|
/* size of hash table must be at least 2 * (# of prefixed attributes) */
|
|
if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */
|
|
NS_ATT *temp;
|
|
/* hash table size must also be a power of 2 and >= 8 */
|
|
while (nPrefixes >> nsAttsPower++);
|
|
if (nsAttsPower < 3)
|
|
nsAttsPower = 3;
|
|
nsAttsSize = (int)1 << nsAttsPower;
|
|
temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT));
|
|
if (!temp)
|
|
return XML_ERROR_NO_MEMORY;
|
|
nsAtts = temp;
|
|
version = 0; /* force re-initialization of nsAtts hash table */
|
|
}
|
|
/* using a version flag saves us from initializing nsAtts every time */
|
|
if (!version) { /* initialize version flags when version wraps around */
|
|
version = INIT_ATTS_VERSION;
|
|
for (j = nsAttsSize; j != 0; )
|
|
nsAtts[--j].version = version;
|
|
}
|
|
nsAttsVersion = --version;
|
|
|
|
/* expand prefixed names and check for duplicates */
|
|
for (; i < attIndex; i += 2) {
|
|
const XML_Char *s = appAtts[i];
|
|
if (s[-1] == 2) { /* prefixed */
|
|
ATTRIBUTE_ID *id;
|
|
const BINDING *b;
|
|
unsigned long uriHash = 0;
|
|
((XML_Char *)s)[-1] = 0; /* clear flag */
|
|
id = (ATTRIBUTE_ID *)lookup(&dtd->attributeIds, s, 0);
|
|
if (!id)
|
|
return XML_ERROR_NO_MEMORY;
|
|
b = id->prefix->binding;
|
|
if (!b)
|
|
return XML_ERROR_UNBOUND_PREFIX;
|
|
|
|
/* as we expand the name we also calculate its hash value */
|
|
for (j = 0; j < b->uriLen; j++) {
|
|
const XML_Char c = b->uri[j];
|
|
if (!poolAppendChar(&tempPool, c))
|
|
return XML_ERROR_NO_MEMORY;
|
|
uriHash = CHAR_HASH(uriHash, c);
|
|
}
|
|
while (*s++ != XML_T(':'))
|
|
;
|
|
do { /* copies null terminator */
|
|
const XML_Char c = *s;
|
|
if (!poolAppendChar(&tempPool, *s))
|
|
return XML_ERROR_NO_MEMORY;
|
|
uriHash = CHAR_HASH(uriHash, c);
|
|
} while (*s++);
|
|
|
|
{ /* Check hash table for duplicate of expanded name (uriName).
|
|
Derived from code in lookup(HASH_TABLE *table, ...).
|
|
*/
|
|
unsigned char step = 0;
|
|
unsigned long mask = nsAttsSize - 1;
|
|
j = uriHash & mask; /* index into hash table */
|
|
while (nsAtts[j].version == version) {
|
|
/* for speed we compare stored hash values first */
|
|
if (uriHash == nsAtts[j].hash) {
|
|
const XML_Char *s1 = poolStart(&tempPool);
|
|
const XML_Char *s2 = nsAtts[j].uriName;
|
|
/* s1 is null terminated, but not s2 */
|
|
for (; *s1 == *s2 && *s1 != 0; s1++, s2++);
|
|
if (*s1 == 0)
|
|
return XML_ERROR_DUPLICATE_ATTRIBUTE;
|
|
}
|
|
if (!step)
|
|
step = PROBE_STEP(uriHash, mask, nsAttsPower);
|
|
j < step ? (j += nsAttsSize - step) : (j -= step);
|
|
}
|
|
}
|
|
|
|
if (ns_triplets) { /* append namespace separator and prefix */
|
|
tempPool.ptr[-1] = namespaceSeparator;
|
|
s = b->prefix->name;
|
|
do {
|
|
if (!poolAppendChar(&tempPool, *s))
|
|
return XML_ERROR_NO_MEMORY;
|
|
} while (*s++);
|
|
}
|
|
|
|
/* store expanded name in attribute list */
|
|
s = poolStart(&tempPool);
|
|
poolFinish(&tempPool);
|
|
appAtts[i] = s;
|
|
|
|
/* fill empty slot with new version, uriName and hash value */
|
|
nsAtts[j].version = version;
|
|
nsAtts[j].hash = uriHash;
|
|
nsAtts[j].uriName = s;
|
|
|
|
if (!--nPrefixes) {
|
|
i += 2;
|
|
break;
|
|
}
|
|
}
|
|
else /* not prefixed */
|
|
((XML_Char *)s)[-1] = 0; /* clear flag */
|
|
}
|
|
}
|
|
/* clear flags for the remaining attributes */
|
|
for (; i < attIndex; i += 2)
|
|
((XML_Char *)(appAtts[i]))[-1] = 0;
|
|
for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding)
|
|
binding->attId->name[-1] = 0;
|
|
|
|
if (!ns)
|
|
return XML_ERROR_NONE;
|
|
|
|
/* expand the element type name */
|
|
if (elementType->prefix) {
|
|
binding = elementType->prefix->binding;
|
|
if (!binding)
|
|
return XML_ERROR_UNBOUND_PREFIX;
|
|
localPart = tagNamePtr->str;
|
|
while (*localPart++ != XML_T(':'))
|
|
;
|
|
}
|
|
else if (dtd->defaultPrefix.binding) {
|
|
binding = dtd->defaultPrefix.binding;
|
|
localPart = tagNamePtr->str;
|
|
}
|
|
else
|
|
return XML_ERROR_NONE;
|
|
prefixLen = 0;
|
|
if (ns_triplets && binding->prefix->name) {
|
|
for (; binding->prefix->name[prefixLen++];)
|
|
; /* prefixLen includes null terminator */
|
|
}
|
|
tagNamePtr->localPart = localPart;
|
|
tagNamePtr->uriLen = binding->uriLen;
|
|
tagNamePtr->prefix = binding->prefix->name;
|
|
tagNamePtr->prefixLen = prefixLen;
|
|
for (i = 0; localPart[i++];)
|
|
; /* i includes null terminator */
|
|
n = i + binding->uriLen + prefixLen;
|
|
if (n > binding->uriAlloc) {
|
|
TAG *p;
|
|
uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char));
|
|
if (!uri)
|
|
return XML_ERROR_NO_MEMORY;
|
|
binding->uriAlloc = n + EXPAND_SPARE;
|
|
memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char));
|
|
for (p = tagStack; p; p = p->parent)
|
|
if (p->name.str == binding->uri)
|
|
p->name.str = uri;
|
|
FREE(binding->uri);
|
|
binding->uri = uri;
|
|
}
|
|
/* if namespaceSeparator != '\0' then uri includes it already */
|
|
uri = binding->uri + binding->uriLen;
|
|
memcpy(uri, localPart, i * sizeof(XML_Char));
|
|
/* we always have a namespace separator between localPart and prefix */
|
|
if (prefixLen) {
|
|
uri += i - 1;
|
|
*uri = namespaceSeparator; /* replace null terminator */
|
|
memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char));
|
|
}
|
|
tagNamePtr->str = binding->uri;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
|
|
/* addBinding() overwrites the value of prefix->binding without checking.
|
|
Therefore one must keep track of the old value outside of addBinding().
|
|
*/
|
|
static enum XML_Error
|
|
addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
|
|
const XML_Char *uri, BINDING **bindingsPtr)
|
|
{
|
|
static const XML_Char xmlNamespace[] = {
|
|
'h', 't', 't', 'p', ':', '/', '/',
|
|
'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/',
|
|
'X', 'M', 'L', '/', '1', '9', '9', '8', '/',
|
|
'n', 'a', 'm', 'e', 's', 'p', 'a', 'c', 'e', '\0'
|
|
};
|
|
static const int xmlLen =
|
|
(int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1;
|
|
static const XML_Char xmlnsNamespace[] = {
|
|
'h', 't', 't', 'p', ':', '/', '/',
|
|
'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/',
|
|
'2', '0', '0', '0', '/', 'x', 'm', 'l', 'n', 's', '/', '\0'
|
|
};
|
|
static const int xmlnsLen =
|
|
(int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1;
|
|
|
|
XML_Bool mustBeXML = XML_FALSE;
|
|
XML_Bool isXML = XML_TRUE;
|
|
XML_Bool isXMLNS = XML_TRUE;
|
|
|
|
BINDING *b;
|
|
int len;
|
|
|
|
/* empty URI is only valid for default namespace per XML NS 1.0 (not 1.1) */
|
|
if (*uri == XML_T('\0') && prefix->name)
|
|
return XML_ERROR_UNDECLARING_PREFIX;
|
|
|
|
if (prefix->name
|
|
&& prefix->name[0] == XML_T('x')
|
|
&& prefix->name[1] == XML_T('m')
|
|
&& prefix->name[2] == XML_T('l')) {
|
|
|
|
/* Not allowed to bind xmlns */
|
|
if (prefix->name[3] == XML_T('n')
|
|
&& prefix->name[4] == XML_T('s')
|
|
&& prefix->name[5] == XML_T('\0'))
|
|
return XML_ERROR_RESERVED_PREFIX_XMLNS;
|
|
|
|
if (prefix->name[3] == XML_T('\0'))
|
|
mustBeXML = XML_TRUE;
|
|
}
|
|
|
|
for (len = 0; uri[len]; len++) {
|
|
if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len]))
|
|
isXML = XML_FALSE;
|
|
|
|
if (!mustBeXML && isXMLNS
|
|
&& (len > xmlnsLen || uri[len] != xmlnsNamespace[len]))
|
|
isXMLNS = XML_FALSE;
|
|
}
|
|
isXML = isXML && len == xmlLen;
|
|
isXMLNS = isXMLNS && len == xmlnsLen;
|
|
|
|
if (mustBeXML != isXML)
|
|
return mustBeXML ? XML_ERROR_RESERVED_PREFIX_XML
|
|
: XML_ERROR_RESERVED_NAMESPACE_URI;
|
|
|
|
if (isXMLNS)
|
|
return XML_ERROR_RESERVED_NAMESPACE_URI;
|
|
|
|
if (namespaceSeparator)
|
|
len++;
|
|
if (freeBindingList) {
|
|
b = freeBindingList;
|
|
if (len > b->uriAlloc) {
|
|
XML_Char *temp = (XML_Char *)REALLOC(b->uri,
|
|
sizeof(XML_Char) * (len + EXPAND_SPARE));
|
|
if (temp == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
b->uri = temp;
|
|
b->uriAlloc = len + EXPAND_SPARE;
|
|
}
|
|
freeBindingList = b->nextTagBinding;
|
|
}
|
|
else {
|
|
b = (BINDING *)MALLOC(sizeof(BINDING));
|
|
if (!b)
|
|
return XML_ERROR_NO_MEMORY;
|
|
b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE));
|
|
if (!b->uri) {
|
|
FREE(b);
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
b->uriAlloc = len + EXPAND_SPARE;
|
|
}
|
|
b->uriLen = len;
|
|
memcpy(b->uri, uri, len * sizeof(XML_Char));
|
|
if (namespaceSeparator)
|
|
b->uri[len - 1] = namespaceSeparator;
|
|
b->prefix = prefix;
|
|
b->attId = attId;
|
|
b->prevPrefixBinding = prefix->binding;
|
|
/* NULL binding when default namespace undeclared */
|
|
if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix)
|
|
prefix->binding = NULL;
|
|
else
|
|
prefix->binding = b;
|
|
b->nextTagBinding = *bindingsPtr;
|
|
*bindingsPtr = b;
|
|
/* if attId == NULL then we are not starting a namespace scope */
|
|
if (attId && startNamespaceDeclHandler)
|
|
startNamespaceDeclHandler(handlerArg, prefix->name,
|
|
prefix->binding ? uri : 0);
|
|
return XML_ERROR_NONE;
|
|
}
|
|
|
|
/* The idea here is to avoid using stack for each CDATA section when
|
|
the whole file is parsed with one call.
|
|
*/
|
|
static enum XML_Error PTRCALL
|
|
cdataSectionProcessor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
enum XML_Error result = doCdataSection(parser, encoding, &start, end,
|
|
endPtr, (XML_Bool)!ps_finalBuffer);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
if (start) {
|
|
if (parentParser) { /* we are parsing an external entity */
|
|
processor = externalEntityContentProcessor;
|
|
return externalEntityContentProcessor(parser, start, end, endPtr);
|
|
}
|
|
else {
|
|
processor = contentProcessor;
|
|
return contentProcessor(parser, start, end, endPtr);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
/* startPtr gets set to non-null if the section is closed, and to null if
|
|
the section is not yet closed.
|
|
*/
|
|
static enum XML_Error
|
|
doCdataSection(XML_Parser parser,
|
|
const ENCODING *enc,
|
|
const char **startPtr,
|
|
const char *end,
|
|
const char **nextPtr,
|
|
XML_Bool haveMore)
|
|
{
|
|
const char *s = *startPtr;
|
|
const char **eventPP;
|
|
const char **eventEndPP;
|
|
if (enc == encoding) {
|
|
eventPP = &eventPtr;
|
|
*eventPP = s;
|
|
eventEndPP = &eventEndPtr;
|
|
}
|
|
else {
|
|
eventPP = &(openInternalEntities->internalEventPtr);
|
|
eventEndPP = &(openInternalEntities->internalEventEndPtr);
|
|
}
|
|
*eventPP = s;
|
|
*startPtr = NULL;
|
|
|
|
for (;;) {
|
|
const char *next;
|
|
int tok = XmlCdataSectionTok(enc, s, end, &next);
|
|
*eventEndPP = next;
|
|
switch (tok) {
|
|
case XML_TOK_CDATA_SECT_CLOSE:
|
|
if (endCdataSectionHandler)
|
|
endCdataSectionHandler(handlerArg);
|
|
#if 0
|
|
/* see comment under XML_TOK_CDATA_SECT_OPEN */
|
|
else if (characterDataHandler)
|
|
characterDataHandler(handlerArg, dataBuf, 0);
|
|
#endif
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
*startPtr = next;
|
|
*nextPtr = next;
|
|
if (ps_parsing == XML_FINISHED)
|
|
return XML_ERROR_ABORTED;
|
|
else
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_DATA_NEWLINE:
|
|
if (characterDataHandler) {
|
|
XML_Char c = 0xA;
|
|
characterDataHandler(handlerArg, &c, 1);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
case XML_TOK_DATA_CHARS:
|
|
if (characterDataHandler) {
|
|
if (MUST_CONVERT(enc, s)) {
|
|
for (;;) {
|
|
ICHAR *dataPtr = (ICHAR *)dataBuf;
|
|
XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
|
|
*eventEndPP = next;
|
|
characterDataHandler(handlerArg, dataBuf,
|
|
(int)(dataPtr - (ICHAR *)dataBuf));
|
|
if (s == next)
|
|
break;
|
|
*eventPP = s;
|
|
}
|
|
}
|
|
else
|
|
characterDataHandler(handlerArg,
|
|
(XML_Char *)s,
|
|
(int)((XML_Char *)next - (XML_Char *)s));
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
break;
|
|
case XML_TOK_INVALID:
|
|
*eventPP = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_PARTIAL:
|
|
case XML_TOK_NONE:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_UNCLOSED_CDATA_SECTION;
|
|
default:
|
|
*eventPP = next;
|
|
return XML_ERROR_UNEXPECTED_STATE;
|
|
}
|
|
|
|
*eventPP = s = next;
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default: ;
|
|
}
|
|
}
|
|
/* not reached */
|
|
}
|
|
|
|
#ifdef XML_DTD
|
|
|
|
/* The idea here is to avoid using stack for each IGNORE section when
|
|
the whole file is parsed with one call.
|
|
*/
|
|
static enum XML_Error PTRCALL
|
|
ignoreSectionProcessor(XML_Parser parser,
|
|
const char *start,
|
|
const char *end,
|
|
const char **endPtr)
|
|
{
|
|
enum XML_Error result = doIgnoreSection(parser, encoding, &start, end,
|
|
endPtr, (XML_Bool)!ps_finalBuffer);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
if (start) {
|
|
processor = prologProcessor;
|
|
return prologProcessor(parser, start, end, endPtr);
|
|
}
|
|
return result;
|
|
}
|
|
|
|
/* startPtr gets set to non-null is the section is closed, and to null
|
|
if the section is not yet closed.
|
|
*/
|
|
static enum XML_Error
|
|
doIgnoreSection(XML_Parser parser,
|
|
const ENCODING *enc,
|
|
const char **startPtr,
|
|
const char *end,
|
|
const char **nextPtr,
|
|
XML_Bool haveMore)
|
|
{
|
|
const char *next;
|
|
int tok;
|
|
const char *s = *startPtr;
|
|
const char **eventPP;
|
|
const char **eventEndPP;
|
|
if (enc == encoding) {
|
|
eventPP = &eventPtr;
|
|
*eventPP = s;
|
|
eventEndPP = &eventEndPtr;
|
|
}
|
|
else {
|
|
eventPP = &(openInternalEntities->internalEventPtr);
|
|
eventEndPP = &(openInternalEntities->internalEventEndPtr);
|
|
}
|
|
*eventPP = s;
|
|
*startPtr = NULL;
|
|
tok = XmlIgnoreSectionTok(enc, s, end, &next);
|
|
*eventEndPP = next;
|
|
switch (tok) {
|
|
case XML_TOK_IGNORE_SECT:
|
|
if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
*startPtr = next;
|
|
*nextPtr = next;
|
|
if (ps_parsing == XML_FINISHED)
|
|
return XML_ERROR_ABORTED;
|
|
else
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_INVALID:
|
|
*eventPP = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_PARTIAL:
|
|
case XML_TOK_NONE:
|
|
if (haveMore) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */
|
|
default:
|
|
*eventPP = next;
|
|
return XML_ERROR_UNEXPECTED_STATE;
|
|
}
|
|
/* not reached */
|
|
}
|
|
|
|
#endif /* XML_DTD */
|
|
|
|
static enum XML_Error
|
|
initializeEncoding(XML_Parser parser)
|
|
{
|
|
const char *s;
|
|
#ifdef XML_UNICODE
|
|
char encodingBuf[128];
|
|
if (!protocolEncodingName)
|
|
s = NULL;
|
|
else {
|
|
int i;
|
|
for (i = 0; protocolEncodingName[i]; i++) {
|
|
if (i == sizeof(encodingBuf) - 1
|
|
|| (protocolEncodingName[i] & ~0x7f) != 0) {
|
|
encodingBuf[0] = '\0';
|
|
break;
|
|
}
|
|
encodingBuf[i] = (char)protocolEncodingName[i];
|
|
}
|
|
encodingBuf[i] = '\0';
|
|
s = encodingBuf;
|
|
}
|
|
#else
|
|
s = protocolEncodingName;
|
|
#endif
|
|
if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s))
|
|
return XML_ERROR_NONE;
|
|
return handleUnknownEncoding(parser, protocolEncodingName);
|
|
}
|
|
|
|
static enum XML_Error
|
|
processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
|
|
const char *s, const char *next)
|
|
{
|
|
const char *encodingName = NULL;
|
|
const XML_Char *storedEncName = NULL;
|
|
const ENCODING *newEncoding = NULL;
|
|
const char *version = NULL;
|
|
const char *versionend;
|
|
const XML_Char *storedversion = NULL;
|
|
int standalone = -1;
|
|
if (!(ns
|
|
? XmlParseXmlDeclNS
|
|
: XmlParseXmlDecl)(isGeneralTextEntity,
|
|
encoding,
|
|
s,
|
|
next,
|
|
&eventPtr,
|
|
&version,
|
|
&versionend,
|
|
&encodingName,
|
|
&newEncoding,
|
|
&standalone)) {
|
|
if (isGeneralTextEntity)
|
|
return XML_ERROR_TEXT_DECL;
|
|
else
|
|
return XML_ERROR_XML_DECL;
|
|
}
|
|
if (!isGeneralTextEntity && standalone == 1) {
|
|
_dtd->standalone = XML_TRUE;
|
|
#ifdef XML_DTD
|
|
if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
|
|
paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
|
|
#endif /* XML_DTD */
|
|
}
|
|
if (xmlDeclHandler) {
|
|
if (encodingName != NULL) {
|
|
storedEncName = poolStoreString(&temp2Pool,
|
|
encoding,
|
|
encodingName,
|
|
encodingName
|
|
+ XmlNameLength(encoding, encodingName));
|
|
if (!storedEncName)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&temp2Pool);
|
|
}
|
|
if (version) {
|
|
storedversion = poolStoreString(&temp2Pool,
|
|
encoding,
|
|
version,
|
|
versionend - encoding->minBytesPerChar);
|
|
if (!storedversion)
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone);
|
|
}
|
|
else if (defaultHandler)
|
|
reportDefault(parser, encoding, s, next);
|
|
if (protocolEncodingName == NULL) {
|
|
if (newEncoding) {
|
|
if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) {
|
|
eventPtr = encodingName;
|
|
return XML_ERROR_INCORRECT_ENCODING;
|
|
}
|
|
encoding = newEncoding;
|
|
}
|
|
else if (encodingName) {
|
|
enum XML_Error result;
|
|
if (!storedEncName) {
|
|
storedEncName = poolStoreString(
|
|
&temp2Pool, encoding, encodingName,
|
|
encodingName + XmlNameLength(encoding, encodingName));
|
|
if (!storedEncName)
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
result = handleUnknownEncoding(parser, storedEncName);
|
|
poolClear(&temp2Pool);
|
|
if (result == XML_ERROR_UNKNOWN_ENCODING)
|
|
eventPtr = encodingName;
|
|
return result;
|
|
}
|
|
}
|
|
|
|
if (storedEncName || storedversion)
|
|
poolClear(&temp2Pool);
|
|
|
|
return XML_ERROR_NONE;
|
|
}
|
|
|
|
static enum XML_Error
|
|
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
|
|
{
|
|
if (unknownEncodingHandler) {
|
|
XML_Encoding info;
|
|
int i;
|
|
for (i = 0; i < 256; i++)
|
|
info.map[i] = -1;
|
|
info.convert = NULL;
|
|
info.data = NULL;
|
|
info.release = NULL;
|
|
if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName,
|
|
&info)) {
|
|
ENCODING *enc;
|
|
unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding());
|
|
if (!unknownEncodingMem) {
|
|
if (info.release)
|
|
info.release(info.data);
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
enc = (ns
|
|
? XmlInitUnknownEncodingNS
|
|
: XmlInitUnknownEncoding)(unknownEncodingMem,
|
|
info.map,
|
|
info.convert,
|
|
info.data);
|
|
if (enc) {
|
|
unknownEncodingData = info.data;
|
|
unknownEncodingRelease = info.release;
|
|
encoding = enc;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
}
|
|
if (info.release != NULL)
|
|
info.release(info.data);
|
|
}
|
|
return XML_ERROR_UNKNOWN_ENCODING;
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
prologInitProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
enum XML_Error result = initializeEncoding(parser);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
processor = prologProcessor;
|
|
return prologProcessor(parser, s, end, nextPtr);
|
|
}
|
|
|
|
#ifdef XML_DTD
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalParEntInitProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
enum XML_Error result = initializeEncoding(parser);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
|
|
/* we know now that XML_Parse(Buffer) has been called,
|
|
so we consider the external parameter entity read */
|
|
_dtd->paramEntityRead = XML_TRUE;
|
|
|
|
if (prologState.inEntityValue) {
|
|
processor = entityValueInitProcessor;
|
|
return entityValueInitProcessor(parser, s, end, nextPtr);
|
|
}
|
|
else {
|
|
processor = externalParEntProcessor;
|
|
return externalParEntProcessor(parser, s, end, nextPtr);
|
|
}
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
entityValueInitProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
int tok;
|
|
const char *start = s;
|
|
const char *next = start;
|
|
eventPtr = start;
|
|
|
|
for (;;) {
|
|
tok = XmlPrologTok(encoding, start, end, &next);
|
|
eventEndPtr = next;
|
|
if (tok <= 0) {
|
|
if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
switch (tok) {
|
|
case XML_TOK_INVALID:
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_NONE: /* start == end */
|
|
default:
|
|
break;
|
|
}
|
|
/* found end of entity value - can store it now */
|
|
return storeEntityValue(parser, encoding, s, end);
|
|
}
|
|
else if (tok == XML_TOK_XML_DECL) {
|
|
enum XML_Error result;
|
|
result = processXmlDecl(parser, 0, start, next);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default:
|
|
*nextPtr = next;
|
|
}
|
|
/* stop scanning for text declaration - we found one */
|
|
processor = entityValueProcessor;
|
|
return entityValueProcessor(parser, next, end, nextPtr);
|
|
}
|
|
/* If we are at the end of the buffer, this would cause XmlPrologTok to
|
|
return XML_TOK_NONE on the next call, which would then cause the
|
|
function to exit with *nextPtr set to s - that is what we want for other
|
|
tokens, but not for the BOM - we would rather like to skip it;
|
|
then, when this routine is entered the next time, XmlPrologTok will
|
|
return XML_TOK_INVALID, since the BOM is still in the buffer
|
|
*/
|
|
else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) {
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
start = next;
|
|
eventPtr = start;
|
|
}
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
externalParEntProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
const char *next = s;
|
|
int tok;
|
|
|
|
tok = XmlPrologTok(encoding, s, end, &next);
|
|
if (tok <= 0) {
|
|
if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
switch (tok) {
|
|
case XML_TOK_INVALID:
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_NONE: /* start == end */
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
/* This would cause the next stage, i.e. doProlog to be passed XML_TOK_BOM.
|
|
However, when parsing an external subset, doProlog will not accept a BOM
|
|
as valid, and report a syntax error, so we have to skip the BOM
|
|
*/
|
|
else if (tok == XML_TOK_BOM) {
|
|
s = next;
|
|
tok = XmlPrologTok(encoding, s, end, &next);
|
|
}
|
|
|
|
processor = prologProcessor;
|
|
return doProlog(parser, encoding, s, end, tok, next,
|
|
nextPtr, (XML_Bool)!ps_finalBuffer);
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
entityValueProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
const char *start = s;
|
|
const char *next = s;
|
|
const ENCODING *enc = encoding;
|
|
int tok;
|
|
|
|
for (;;) {
|
|
tok = XmlPrologTok(enc, start, end, &next);
|
|
if (tok <= 0) {
|
|
if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
switch (tok) {
|
|
case XML_TOK_INVALID:
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_NONE: /* start == end */
|
|
default:
|
|
break;
|
|
}
|
|
/* found end of entity value - can store it now */
|
|
return storeEntityValue(parser, enc, s, end);
|
|
}
|
|
start = next;
|
|
}
|
|
}
|
|
|
|
#endif /* XML_DTD */
|
|
|
|
static enum XML_Error PTRCALL
|
|
prologProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
const char *next = s;
|
|
int tok = XmlPrologTok(encoding, s, end, &next);
|
|
return doProlog(parser, encoding, s, end, tok, next,
|
|
nextPtr, (XML_Bool)!ps_finalBuffer);
|
|
}
|
|
|
|
static enum XML_Error
|
|
doProlog(XML_Parser parser,
|
|
const ENCODING *enc,
|
|
const char *s,
|
|
const char *end,
|
|
int tok,
|
|
const char *next,
|
|
const char **nextPtr,
|
|
XML_Bool haveMore)
|
|
{
|
|
#ifdef XML_DTD
|
|
static const XML_Char externalSubsetName[] = { '#' , '\0' };
|
|
#endif /* XML_DTD */
|
|
static const XML_Char atypeCDATA[] = { 'C', 'D', 'A', 'T', 'A', '\0' };
|
|
static const XML_Char atypeID[] = { 'I', 'D', '\0' };
|
|
static const XML_Char atypeIDREF[] = { 'I', 'D', 'R', 'E', 'F', '\0' };
|
|
static const XML_Char atypeIDREFS[] = { 'I', 'D', 'R', 'E', 'F', 'S', '\0' };
|
|
static const XML_Char atypeENTITY[] = { 'E', 'N', 'T', 'I', 'T', 'Y', '\0' };
|
|
static const XML_Char atypeENTITIES[] =
|
|
{ 'E', 'N', 'T', 'I', 'T', 'I', 'E', 'S', '\0' };
|
|
static const XML_Char atypeNMTOKEN[] = {
|
|
'N', 'M', 'T', 'O', 'K', 'E', 'N', '\0' };
|
|
static const XML_Char atypeNMTOKENS[] = {
|
|
'N', 'M', 'T', 'O', 'K', 'E', 'N', 'S', '\0' };
|
|
static const XML_Char notationPrefix[] = {
|
|
'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N', '(', '\0' };
|
|
static const XML_Char enumValueSep[] = { '|', '\0' };
|
|
static const XML_Char enumValueStart[] = { '(', '\0' };
|
|
|
|
/* save one level of indirection */
|
|
DTD * const dtd = _dtd;
|
|
|
|
const char **eventPP;
|
|
const char **eventEndPP;
|
|
enum XML_Content_Quant quant;
|
|
|
|
if (enc == encoding) {
|
|
eventPP = &eventPtr;
|
|
eventEndPP = &eventEndPtr;
|
|
}
|
|
else {
|
|
eventPP = &(openInternalEntities->internalEventPtr);
|
|
eventEndPP = &(openInternalEntities->internalEventEndPtr);
|
|
}
|
|
|
|
for (;;) {
|
|
int role;
|
|
XML_Bool handleDefault = XML_TRUE;
|
|
*eventPP = s;
|
|
*eventEndPP = next;
|
|
if (tok <= 0) {
|
|
if (haveMore && tok != XML_TOK_INVALID) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
switch (tok) {
|
|
case XML_TOK_INVALID:
|
|
*eventPP = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
case XML_TOK_NONE:
|
|
#ifdef XML_DTD
|
|
/* for internal PE NOT referenced between declarations */
|
|
if (enc != encoding && !openInternalEntities->betweenDecl) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
/* WFC: PE Between Declarations - must check that PE contains
|
|
complete markup, not only for external PEs, but also for
|
|
internal PEs if the reference occurs between declarations.
|
|
*/
|
|
if (isParamEntity || enc != encoding) {
|
|
if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc)
|
|
== XML_ROLE_ERROR)
|
|
return XML_ERROR_INCOMPLETE_PE;
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
#endif /* XML_DTD */
|
|
return XML_ERROR_NO_ELEMENTS;
|
|
default:
|
|
tok = -tok;
|
|
next = end;
|
|
break;
|
|
}
|
|
}
|
|
role = XmlTokenRole(&prologState, tok, s, next, enc);
|
|
switch (role) {
|
|
case XML_ROLE_XML_DECL:
|
|
{
|
|
enum XML_Error result = processXmlDecl(parser, 0, s, next);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
enc = encoding;
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_DOCTYPE_NAME:
|
|
if (startDoctypeDeclHandler) {
|
|
doctypeName = poolStoreString(&tempPool, enc, s, next);
|
|
if (!doctypeName)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&tempPool);
|
|
doctypePubid = NULL;
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
doctypeSysid = NULL; /* always initialize to NULL */
|
|
break;
|
|
case XML_ROLE_DOCTYPE_INTERNAL_SUBSET:
|
|
if (startDoctypeDeclHandler) {
|
|
startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid,
|
|
doctypePubid, 1);
|
|
doctypeName = NULL;
|
|
poolClear(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
#ifdef XML_DTD
|
|
case XML_ROLE_TEXT_DECL:
|
|
{
|
|
enum XML_Error result = processXmlDecl(parser, 1, s, next);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
enc = encoding;
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
#endif /* XML_DTD */
|
|
case XML_ROLE_DOCTYPE_PUBLIC_ID:
|
|
#ifdef XML_DTD
|
|
useForeignDTD = XML_FALSE;
|
|
declEntity = (ENTITY *)lookup(&dtd->paramEntities,
|
|
externalSubsetName,
|
|
sizeof(ENTITY));
|
|
if (!declEntity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
#endif /* XML_DTD */
|
|
dtd->hasParamEntityRefs = XML_TRUE;
|
|
if (startDoctypeDeclHandler) {
|
|
if (!XmlIsPublicId(enc, s, next, eventPP))
|
|
return XML_ERROR_PUBLICID;
|
|
doctypePubid = poolStoreString(&tempPool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!doctypePubid)
|
|
return XML_ERROR_NO_MEMORY;
|
|
normalizePublicId((XML_Char *)doctypePubid);
|
|
poolFinish(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
goto alreadyChecked;
|
|
}
|
|
/* fall through */
|
|
case XML_ROLE_ENTITY_PUBLIC_ID:
|
|
if (!XmlIsPublicId(enc, s, next, eventPP))
|
|
return XML_ERROR_PUBLICID;
|
|
alreadyChecked:
|
|
if (dtd->keepProcessing && declEntity) {
|
|
XML_Char *tem = poolStoreString(&dtd->pool,
|
|
enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!tem)
|
|
return XML_ERROR_NO_MEMORY;
|
|
normalizePublicId(tem);
|
|
declEntity->publicId = tem;
|
|
poolFinish(&dtd->pool);
|
|
if (entityDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_DOCTYPE_CLOSE:
|
|
if (doctypeName) {
|
|
startDoctypeDeclHandler(handlerArg, doctypeName,
|
|
doctypeSysid, doctypePubid, 0);
|
|
poolClear(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
/* doctypeSysid will be non-NULL in the case of a previous
|
|
XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler
|
|
was not set, indicating an external subset
|
|
*/
|
|
#ifdef XML_DTD
|
|
if (doctypeSysid || useForeignDTD) {
|
|
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
|
|
dtd->hasParamEntityRefs = XML_TRUE;
|
|
if (paramEntityParsing && externalEntityRefHandler) {
|
|
ENTITY *entity = (ENTITY *)lookup(&dtd->paramEntities,
|
|
externalSubsetName,
|
|
sizeof(ENTITY));
|
|
if (!entity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (useForeignDTD)
|
|
entity->base = curBase;
|
|
dtd->paramEntityRead = XML_FALSE;
|
|
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
|
|
0,
|
|
entity->base,
|
|
entity->systemId,
|
|
entity->publicId))
|
|
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
|
|
if (dtd->paramEntityRead) {
|
|
if (!dtd->standalone &&
|
|
notStandaloneHandler &&
|
|
!notStandaloneHandler(handlerArg))
|
|
return XML_ERROR_NOT_STANDALONE;
|
|
}
|
|
/* if we didn't read the foreign DTD then this means that there
|
|
is no external subset and we must reset dtd->hasParamEntityRefs
|
|
*/
|
|
else if (!doctypeSysid)
|
|
dtd->hasParamEntityRefs = hadParamEntityRefs;
|
|
/* end of DTD - no need to update dtd->keepProcessing */
|
|
}
|
|
useForeignDTD = XML_FALSE;
|
|
}
|
|
#endif /* XML_DTD */
|
|
if (endDoctypeDeclHandler) {
|
|
endDoctypeDeclHandler(handlerArg);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_INSTANCE_START:
|
|
#ifdef XML_DTD
|
|
/* if there is no DOCTYPE declaration then now is the
|
|
last chance to read the foreign DTD
|
|
*/
|
|
if (useForeignDTD) {
|
|
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
|
|
dtd->hasParamEntityRefs = XML_TRUE;
|
|
if (paramEntityParsing && externalEntityRefHandler) {
|
|
ENTITY *entity = (ENTITY *)lookup(&dtd->paramEntities,
|
|
externalSubsetName,
|
|
sizeof(ENTITY));
|
|
if (!entity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
entity->base = curBase;
|
|
dtd->paramEntityRead = XML_FALSE;
|
|
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
|
|
0,
|
|
entity->base,
|
|
entity->systemId,
|
|
entity->publicId))
|
|
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
|
|
if (dtd->paramEntityRead) {
|
|
if (!dtd->standalone &&
|
|
notStandaloneHandler &&
|
|
!notStandaloneHandler(handlerArg))
|
|
return XML_ERROR_NOT_STANDALONE;
|
|
}
|
|
/* if we didn't read the foreign DTD then this means that there
|
|
is no external subset and we must reset dtd->hasParamEntityRefs
|
|
*/
|
|
else
|
|
dtd->hasParamEntityRefs = hadParamEntityRefs;
|
|
/* end of DTD - no need to update dtd->keepProcessing */
|
|
}
|
|
}
|
|
#endif /* XML_DTD */
|
|
processor = contentProcessor;
|
|
return contentProcessor(parser, s, end, nextPtr);
|
|
case XML_ROLE_ATTLIST_ELEMENT_NAME:
|
|
declElementType = getElementType(parser, enc, s, next);
|
|
if (!declElementType)
|
|
return XML_ERROR_NO_MEMORY;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_NAME:
|
|
declAttributeId = getAttributeId(parser, enc, s, next);
|
|
if (!declAttributeId)
|
|
return XML_ERROR_NO_MEMORY;
|
|
declAttributeIsCdata = XML_FALSE;
|
|
declAttributeType = NULL;
|
|
declAttributeIsId = XML_FALSE;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_CDATA:
|
|
declAttributeIsCdata = XML_TRUE;
|
|
declAttributeType = atypeCDATA;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_ID:
|
|
declAttributeIsId = XML_TRUE;
|
|
declAttributeType = atypeID;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_IDREF:
|
|
declAttributeType = atypeIDREF;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_IDREFS:
|
|
declAttributeType = atypeIDREFS;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_ENTITY:
|
|
declAttributeType = atypeENTITY;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES:
|
|
declAttributeType = atypeENTITIES;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN:
|
|
declAttributeType = atypeNMTOKEN;
|
|
goto checkAttListDeclHandler;
|
|
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS:
|
|
declAttributeType = atypeNMTOKENS;
|
|
checkAttListDeclHandler:
|
|
if (dtd->keepProcessing && attlistDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_ATTRIBUTE_ENUM_VALUE:
|
|
case XML_ROLE_ATTRIBUTE_NOTATION_VALUE:
|
|
if (dtd->keepProcessing && attlistDeclHandler) {
|
|
const XML_Char *prefix;
|
|
if (declAttributeType) {
|
|
prefix = enumValueSep;
|
|
}
|
|
else {
|
|
prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE
|
|
? notationPrefix
|
|
: enumValueStart);
|
|
}
|
|
if (!poolAppendString(&tempPool, prefix))
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (!poolAppend(&tempPool, enc, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
declAttributeType = tempPool.start;
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE:
|
|
case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE:
|
|
if (dtd->keepProcessing) {
|
|
if (!defineAttribute(declElementType, declAttributeId,
|
|
declAttributeIsCdata, declAttributeIsId,
|
|
0, parser))
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (attlistDeclHandler && declAttributeType) {
|
|
if (*declAttributeType == XML_T('(')
|
|
|| (*declAttributeType == XML_T('N')
|
|
&& declAttributeType[1] == XML_T('O'))) {
|
|
/* Enumerated or Notation type */
|
|
if (!poolAppendChar(&tempPool, XML_T(')'))
|
|
|| !poolAppendChar(&tempPool, XML_T('\0')))
|
|
return XML_ERROR_NO_MEMORY;
|
|
declAttributeType = tempPool.start;
|
|
poolFinish(&tempPool);
|
|
}
|
|
*eventEndPP = s;
|
|
attlistDeclHandler(handlerArg, declElementType->name,
|
|
declAttributeId->name, declAttributeType,
|
|
0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE);
|
|
poolClear(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
break;
|
|
case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE:
|
|
case XML_ROLE_FIXED_ATTRIBUTE_VALUE:
|
|
if (dtd->keepProcessing) {
|
|
const XML_Char *attVal;
|
|
enum XML_Error result =
|
|
storeAttributeValue(parser, enc, declAttributeIsCdata,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar,
|
|
&dtd->pool);
|
|
if (result)
|
|
return result;
|
|
attVal = poolStart(&dtd->pool);
|
|
poolFinish(&dtd->pool);
|
|
/* ID attributes aren't allowed to have a default */
|
|
if (!defineAttribute(declElementType, declAttributeId,
|
|
declAttributeIsCdata, XML_FALSE, attVal, parser))
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (attlistDeclHandler && declAttributeType) {
|
|
if (*declAttributeType == XML_T('(')
|
|
|| (*declAttributeType == XML_T('N')
|
|
&& declAttributeType[1] == XML_T('O'))) {
|
|
/* Enumerated or Notation type */
|
|
if (!poolAppendChar(&tempPool, XML_T(')'))
|
|
|| !poolAppendChar(&tempPool, XML_T('\0')))
|
|
return XML_ERROR_NO_MEMORY;
|
|
declAttributeType = tempPool.start;
|
|
poolFinish(&tempPool);
|
|
}
|
|
*eventEndPP = s;
|
|
attlistDeclHandler(handlerArg, declElementType->name,
|
|
declAttributeId->name, declAttributeType,
|
|
attVal,
|
|
role == XML_ROLE_FIXED_ATTRIBUTE_VALUE);
|
|
poolClear(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
break;
|
|
case XML_ROLE_ENTITY_VALUE:
|
|
if (dtd->keepProcessing) {
|
|
enum XML_Error result = storeEntityValue(parser, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (declEntity) {
|
|
declEntity->textPtr = poolStart(&dtd->entityValuePool);
|
|
declEntity->textLen = (int)(poolLength(&dtd->entityValuePool));
|
|
poolFinish(&dtd->entityValuePool);
|
|
if (entityDeclHandler) {
|
|
*eventEndPP = s;
|
|
entityDeclHandler(handlerArg,
|
|
declEntity->name,
|
|
declEntity->is_param,
|
|
declEntity->textPtr,
|
|
declEntity->textLen,
|
|
curBase, 0, 0, 0);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
else
|
|
poolDiscard(&dtd->entityValuePool);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
}
|
|
break;
|
|
case XML_ROLE_DOCTYPE_SYSTEM_ID:
|
|
#ifdef XML_DTD
|
|
useForeignDTD = XML_FALSE;
|
|
#endif /* XML_DTD */
|
|
dtd->hasParamEntityRefs = XML_TRUE;
|
|
if (startDoctypeDeclHandler) {
|
|
doctypeSysid = poolStoreString(&tempPool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (doctypeSysid == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
#ifdef XML_DTD
|
|
else
|
|
/* use externalSubsetName to make doctypeSysid non-NULL
|
|
for the case where no startDoctypeDeclHandler is set */
|
|
doctypeSysid = externalSubsetName;
|
|
#endif /* XML_DTD */
|
|
if (!dtd->standalone
|
|
#ifdef XML_DTD
|
|
&& !paramEntityParsing
|
|
#endif /* XML_DTD */
|
|
&& notStandaloneHandler
|
|
&& !notStandaloneHandler(handlerArg))
|
|
return XML_ERROR_NOT_STANDALONE;
|
|
#ifndef XML_DTD
|
|
break;
|
|
#else /* XML_DTD */
|
|
if (!declEntity) {
|
|
declEntity = (ENTITY *)lookup(&dtd->paramEntities,
|
|
externalSubsetName,
|
|
sizeof(ENTITY));
|
|
if (!declEntity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
declEntity->publicId = NULL;
|
|
}
|
|
/* fall through */
|
|
#endif /* XML_DTD */
|
|
case XML_ROLE_ENTITY_SYSTEM_ID:
|
|
if (dtd->keepProcessing && declEntity) {
|
|
declEntity->systemId = poolStoreString(&dtd->pool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!declEntity->systemId)
|
|
return XML_ERROR_NO_MEMORY;
|
|
declEntity->base = curBase;
|
|
poolFinish(&dtd->pool);
|
|
if (entityDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_ENTITY_COMPLETE:
|
|
if (dtd->keepProcessing && declEntity && entityDeclHandler) {
|
|
*eventEndPP = s;
|
|
entityDeclHandler(handlerArg,
|
|
declEntity->name,
|
|
declEntity->is_param,
|
|
0,0,
|
|
declEntity->base,
|
|
declEntity->systemId,
|
|
declEntity->publicId,
|
|
0);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_ENTITY_NOTATION_NAME:
|
|
if (dtd->keepProcessing && declEntity) {
|
|
declEntity->notation = poolStoreString(&dtd->pool, enc, s, next);
|
|
if (!declEntity->notation)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&dtd->pool);
|
|
if (unparsedEntityDeclHandler) {
|
|
*eventEndPP = s;
|
|
unparsedEntityDeclHandler(handlerArg,
|
|
declEntity->name,
|
|
declEntity->base,
|
|
declEntity->systemId,
|
|
declEntity->publicId,
|
|
declEntity->notation);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
else if (entityDeclHandler) {
|
|
*eventEndPP = s;
|
|
entityDeclHandler(handlerArg,
|
|
declEntity->name,
|
|
0,0,0,
|
|
declEntity->base,
|
|
declEntity->systemId,
|
|
declEntity->publicId,
|
|
declEntity->notation);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
break;
|
|
case XML_ROLE_GENERAL_ENTITY_NAME:
|
|
{
|
|
if (XmlPredefinedEntityName(enc, s, next)) {
|
|
declEntity = NULL;
|
|
break;
|
|
}
|
|
if (dtd->keepProcessing) {
|
|
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
declEntity = (ENTITY *)lookup(&dtd->generalEntities, name,
|
|
sizeof(ENTITY));
|
|
if (!declEntity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (declEntity->name != name) {
|
|
poolDiscard(&dtd->pool);
|
|
declEntity = NULL;
|
|
}
|
|
else {
|
|
poolFinish(&dtd->pool);
|
|
declEntity->publicId = NULL;
|
|
declEntity->is_param = XML_FALSE;
|
|
/* if we have a parent parser or are reading an internal parameter
|
|
entity, then the entity declaration is not considered "internal"
|
|
*/
|
|
declEntity->is_internal = !(parentParser || openInternalEntities);
|
|
if (entityDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
else {
|
|
poolDiscard(&dtd->pool);
|
|
declEntity = NULL;
|
|
}
|
|
}
|
|
break;
|
|
case XML_ROLE_PARAM_ENTITY_NAME:
|
|
#ifdef XML_DTD
|
|
if (dtd->keepProcessing) {
|
|
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
declEntity = (ENTITY *)lookup(&dtd->paramEntities,
|
|
name, sizeof(ENTITY));
|
|
if (!declEntity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
if (declEntity->name != name) {
|
|
poolDiscard(&dtd->pool);
|
|
declEntity = NULL;
|
|
}
|
|
else {
|
|
poolFinish(&dtd->pool);
|
|
declEntity->publicId = NULL;
|
|
declEntity->is_param = XML_TRUE;
|
|
/* if we have a parent parser or are reading an internal parameter
|
|
entity, then the entity declaration is not considered "internal"
|
|
*/
|
|
declEntity->is_internal = !(parentParser || openInternalEntities);
|
|
if (entityDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
}
|
|
else {
|
|
poolDiscard(&dtd->pool);
|
|
declEntity = NULL;
|
|
}
|
|
#else /* not XML_DTD */
|
|
declEntity = NULL;
|
|
#endif /* XML_DTD */
|
|
break;
|
|
case XML_ROLE_NOTATION_NAME:
|
|
declNotationPublicId = NULL;
|
|
declNotationName = NULL;
|
|
if (notationDeclHandler) {
|
|
declNotationName = poolStoreString(&tempPool, enc, s, next);
|
|
if (!declNotationName)
|
|
return XML_ERROR_NO_MEMORY;
|
|
poolFinish(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_NOTATION_PUBLIC_ID:
|
|
if (!XmlIsPublicId(enc, s, next, eventPP))
|
|
return XML_ERROR_PUBLICID;
|
|
if (declNotationName) { /* means notationDeclHandler != NULL */
|
|
XML_Char *tem = poolStoreString(&tempPool,
|
|
enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!tem)
|
|
return XML_ERROR_NO_MEMORY;
|
|
normalizePublicId(tem);
|
|
declNotationPublicId = tem;
|
|
poolFinish(&tempPool);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_NOTATION_SYSTEM_ID:
|
|
if (declNotationName && notationDeclHandler) {
|
|
const XML_Char *systemId
|
|
= poolStoreString(&tempPool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!systemId)
|
|
return XML_ERROR_NO_MEMORY;
|
|
*eventEndPP = s;
|
|
notationDeclHandler(handlerArg,
|
|
declNotationName,
|
|
curBase,
|
|
systemId,
|
|
declNotationPublicId);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
poolClear(&tempPool);
|
|
break;
|
|
case XML_ROLE_NOTATION_NO_SYSTEM_ID:
|
|
if (declNotationPublicId && notationDeclHandler) {
|
|
*eventEndPP = s;
|
|
notationDeclHandler(handlerArg,
|
|
declNotationName,
|
|
curBase,
|
|
0,
|
|
declNotationPublicId);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
poolClear(&tempPool);
|
|
break;
|
|
case XML_ROLE_ERROR:
|
|
switch (tok) {
|
|
case XML_TOK_PARAM_ENTITY_REF:
|
|
/* PE references in internal subset are
|
|
not allowed within declarations. */
|
|
return XML_ERROR_PARAM_ENTITY_REF;
|
|
case XML_TOK_XML_DECL:
|
|
return XML_ERROR_MISPLACED_XML_PI;
|
|
default:
|
|
return XML_ERROR_SYNTAX;
|
|
}
|
|
#ifdef XML_DTD
|
|
case XML_ROLE_IGNORE_SECT:
|
|
{
|
|
enum XML_Error result;
|
|
if (defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
handleDefault = XML_FALSE;
|
|
result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
else if (!next) {
|
|
processor = ignoreSectionProcessor;
|
|
return result;
|
|
}
|
|
}
|
|
break;
|
|
#endif /* XML_DTD */
|
|
case XML_ROLE_GROUP_OPEN:
|
|
if (prologState.level >= groupSize) {
|
|
if (groupSize) {
|
|
char *temp = (char *)REALLOC(groupConnector, groupSize *= 2);
|
|
if (temp == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
groupConnector = temp;
|
|
if (dtd->scaffIndex) {
|
|
int *temp = (int *)REALLOC(dtd->scaffIndex,
|
|
groupSize * sizeof(int));
|
|
if (temp == NULL)
|
|
return XML_ERROR_NO_MEMORY;
|
|
dtd->scaffIndex = temp;
|
|
}
|
|
}
|
|
else {
|
|
groupConnector = (char *)MALLOC(groupSize = 32);
|
|
if (!groupConnector)
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
}
|
|
groupConnector[prologState.level] = 0;
|
|
if (dtd->in_eldecl) {
|
|
int myindex = nextScaffoldPart(parser);
|
|
if (myindex < 0)
|
|
return XML_ERROR_NO_MEMORY;
|
|
dtd->scaffIndex[dtd->scaffLevel] = myindex;
|
|
dtd->scaffLevel++;
|
|
dtd->scaffold[myindex].type = XML_CTYPE_SEQ;
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
case XML_ROLE_GROUP_SEQUENCE:
|
|
if (groupConnector[prologState.level] == '|')
|
|
return XML_ERROR_SYNTAX;
|
|
groupConnector[prologState.level] = ',';
|
|
if (dtd->in_eldecl && elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_GROUP_CHOICE:
|
|
if (groupConnector[prologState.level] == ',')
|
|
return XML_ERROR_SYNTAX;
|
|
if (dtd->in_eldecl
|
|
&& !groupConnector[prologState.level]
|
|
&& (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
|
|
!= XML_CTYPE_MIXED)
|
|
) {
|
|
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
|
|
= XML_CTYPE_CHOICE;
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
groupConnector[prologState.level] = '|';
|
|
break;
|
|
case XML_ROLE_PARAM_ENTITY_REF:
|
|
#ifdef XML_DTD
|
|
case XML_ROLE_INNER_PARAM_ENTITY_REF:
|
|
dtd->hasParamEntityRefs = XML_TRUE;
|
|
if (!paramEntityParsing)
|
|
dtd->keepProcessing = dtd->standalone;
|
|
else {
|
|
const XML_Char *name;
|
|
ENTITY *entity;
|
|
name = poolStoreString(&dtd->pool, enc,
|
|
s + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
entity = (ENTITY *)lookup(&dtd->paramEntities, name, 0);
|
|
poolDiscard(&dtd->pool);
|
|
/* first, determine if a check for an existing declaration is needed;
|
|
if yes, check that the entity exists, and that it is internal,
|
|
otherwise call the skipped entity handler
|
|
*/
|
|
if (prologState.documentEntity &&
|
|
(dtd->standalone
|
|
? !openInternalEntities
|
|
: !dtd->hasParamEntityRefs)) {
|
|
if (!entity)
|
|
return XML_ERROR_UNDEFINED_ENTITY;
|
|
else if (!entity->is_internal)
|
|
return XML_ERROR_ENTITY_DECLARED_IN_PE;
|
|
}
|
|
else if (!entity) {
|
|
dtd->keepProcessing = dtd->standalone;
|
|
/* cannot report skipped entities in declarations */
|
|
if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) {
|
|
skippedEntityHandler(handlerArg, name, 1);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
}
|
|
if (entity->open)
|
|
return XML_ERROR_RECURSIVE_ENTITY_REF;
|
|
if (entity->textPtr) {
|
|
enum XML_Error result;
|
|
XML_Bool betweenDecl =
|
|
(role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE);
|
|
result = processInternalEntity(parser, entity, betweenDecl);
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
}
|
|
if (externalEntityRefHandler) {
|
|
dtd->paramEntityRead = XML_FALSE;
|
|
entity->open = XML_TRUE;
|
|
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
|
|
0,
|
|
entity->base,
|
|
entity->systemId,
|
|
entity->publicId)) {
|
|
entity->open = XML_FALSE;
|
|
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
|
|
}
|
|
entity->open = XML_FALSE;
|
|
handleDefault = XML_FALSE;
|
|
if (!dtd->paramEntityRead) {
|
|
dtd->keepProcessing = dtd->standalone;
|
|
break;
|
|
}
|
|
}
|
|
else {
|
|
dtd->keepProcessing = dtd->standalone;
|
|
break;
|
|
}
|
|
}
|
|
#endif /* XML_DTD */
|
|
if (!dtd->standalone &&
|
|
notStandaloneHandler &&
|
|
!notStandaloneHandler(handlerArg))
|
|
return XML_ERROR_NOT_STANDALONE;
|
|
break;
|
|
|
|
/* Element declaration stuff */
|
|
|
|
case XML_ROLE_ELEMENT_NAME:
|
|
if (elementDeclHandler) {
|
|
declElementType = getElementType(parser, enc, s, next);
|
|
if (!declElementType)
|
|
return XML_ERROR_NO_MEMORY;
|
|
dtd->scaffLevel = 0;
|
|
dtd->scaffCount = 0;
|
|
dtd->in_eldecl = XML_TRUE;
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
|
|
case XML_ROLE_CONTENT_ANY:
|
|
case XML_ROLE_CONTENT_EMPTY:
|
|
if (dtd->in_eldecl) {
|
|
if (elementDeclHandler) {
|
|
XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content));
|
|
if (!content)
|
|
return XML_ERROR_NO_MEMORY;
|
|
content->quant = XML_CQUANT_NONE;
|
|
content->name = NULL;
|
|
content->numchildren = 0;
|
|
content->children = NULL;
|
|
content->type = ((role == XML_ROLE_CONTENT_ANY) ?
|
|
XML_CTYPE_ANY :
|
|
XML_CTYPE_EMPTY);
|
|
*eventEndPP = s;
|
|
elementDeclHandler(handlerArg, declElementType->name, content);
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
dtd->in_eldecl = XML_FALSE;
|
|
}
|
|
break;
|
|
|
|
case XML_ROLE_CONTENT_PCDATA:
|
|
if (dtd->in_eldecl) {
|
|
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
|
|
= XML_CTYPE_MIXED;
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
|
|
case XML_ROLE_CONTENT_ELEMENT:
|
|
quant = XML_CQUANT_NONE;
|
|
goto elementContent;
|
|
case XML_ROLE_CONTENT_ELEMENT_OPT:
|
|
quant = XML_CQUANT_OPT;
|
|
goto elementContent;
|
|
case XML_ROLE_CONTENT_ELEMENT_REP:
|
|
quant = XML_CQUANT_REP;
|
|
goto elementContent;
|
|
case XML_ROLE_CONTENT_ELEMENT_PLUS:
|
|
quant = XML_CQUANT_PLUS;
|
|
elementContent:
|
|
if (dtd->in_eldecl) {
|
|
ELEMENT_TYPE *el;
|
|
const XML_Char *name;
|
|
int nameLen;
|
|
const char *nxt = (quant == XML_CQUANT_NONE
|
|
? next
|
|
: next - enc->minBytesPerChar);
|
|
int myindex = nextScaffoldPart(parser);
|
|
if (myindex < 0)
|
|
return XML_ERROR_NO_MEMORY;
|
|
dtd->scaffold[myindex].type = XML_CTYPE_NAME;
|
|
dtd->scaffold[myindex].quant = quant;
|
|
el = getElementType(parser, enc, s, nxt);
|
|
if (!el)
|
|
return XML_ERROR_NO_MEMORY;
|
|
name = el->name;
|
|
dtd->scaffold[myindex].name = name;
|
|
nameLen = 0;
|
|
for (; name[nameLen++]; );
|
|
dtd->contentStringLen += nameLen;
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
}
|
|
break;
|
|
|
|
case XML_ROLE_GROUP_CLOSE:
|
|
quant = XML_CQUANT_NONE;
|
|
goto closeGroup;
|
|
case XML_ROLE_GROUP_CLOSE_OPT:
|
|
quant = XML_CQUANT_OPT;
|
|
goto closeGroup;
|
|
case XML_ROLE_GROUP_CLOSE_REP:
|
|
quant = XML_CQUANT_REP;
|
|
goto closeGroup;
|
|
case XML_ROLE_GROUP_CLOSE_PLUS:
|
|
quant = XML_CQUANT_PLUS;
|
|
closeGroup:
|
|
if (dtd->in_eldecl) {
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
dtd->scaffLevel--;
|
|
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant;
|
|
if (dtd->scaffLevel == 0) {
|
|
if (!handleDefault) {
|
|
XML_Content *model = build_model(parser);
|
|
if (!model)
|
|
return XML_ERROR_NO_MEMORY;
|
|
*eventEndPP = s;
|
|
elementDeclHandler(handlerArg, declElementType->name, model);
|
|
}
|
|
dtd->in_eldecl = XML_FALSE;
|
|
dtd->contentStringLen = 0;
|
|
}
|
|
}
|
|
break;
|
|
/* End element declaration stuff */
|
|
|
|
case XML_ROLE_PI:
|
|
if (!reportProcessingInstruction(parser, enc, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_COMMENT:
|
|
if (!reportComment(parser, enc, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_NONE:
|
|
switch (tok) {
|
|
case XML_TOK_BOM:
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
}
|
|
break;
|
|
case XML_ROLE_DOCTYPE_NONE:
|
|
if (startDoctypeDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_ENTITY_NONE:
|
|
if (dtd->keepProcessing && entityDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_NOTATION_NONE:
|
|
if (notationDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_ATTLIST_NONE:
|
|
if (dtd->keepProcessing && attlistDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
case XML_ROLE_ELEMENT_NONE:
|
|
if (elementDeclHandler)
|
|
handleDefault = XML_FALSE;
|
|
break;
|
|
} /* end of big switch */
|
|
|
|
if (handleDefault && defaultHandler)
|
|
reportDefault(parser, enc, s, next);
|
|
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default:
|
|
s = next;
|
|
tok = XmlPrologTok(enc, s, end, &next);
|
|
}
|
|
}
|
|
/* not reached */
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
epilogProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
processor = epilogProcessor;
|
|
eventPtr = s;
|
|
for (;;) {
|
|
const char *next = NULL;
|
|
int tok = XmlPrologTok(encoding, s, end, &next);
|
|
eventEndPtr = next;
|
|
switch (tok) {
|
|
/* report partial linebreak - it might be the last token */
|
|
case -XML_TOK_PROLOG_S:
|
|
if (defaultHandler) {
|
|
reportDefault(parser, encoding, s, next);
|
|
if (ps_parsing == XML_FINISHED)
|
|
return XML_ERROR_ABORTED;
|
|
}
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_NONE:
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_PROLOG_S:
|
|
if (defaultHandler)
|
|
reportDefault(parser, encoding, s, next);
|
|
break;
|
|
case XML_TOK_PI:
|
|
if (!reportProcessingInstruction(parser, encoding, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
case XML_TOK_COMMENT:
|
|
if (!reportComment(parser, encoding, s, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
case XML_TOK_INVALID:
|
|
eventPtr = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
if (!ps_finalBuffer) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_UNCLOSED_TOKEN;
|
|
case XML_TOK_PARTIAL_CHAR:
|
|
if (!ps_finalBuffer) {
|
|
*nextPtr = s;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
return XML_ERROR_PARTIAL_CHAR;
|
|
default:
|
|
return XML_ERROR_JUNK_AFTER_DOC_ELEMENT;
|
|
}
|
|
eventPtr = s = next;
|
|
switch (ps_parsing) {
|
|
case XML_SUSPENDED:
|
|
*nextPtr = next;
|
|
return XML_ERROR_NONE;
|
|
case XML_FINISHED:
|
|
return XML_ERROR_ABORTED;
|
|
default: ;
|
|
}
|
|
}
|
|
}
|
|
|
|
static enum XML_Error
|
|
processInternalEntity(XML_Parser parser, ENTITY *entity,
|
|
XML_Bool betweenDecl)
|
|
{
|
|
const char *textStart, *textEnd;
|
|
const char *next;
|
|
enum XML_Error result;
|
|
OPEN_INTERNAL_ENTITY *openEntity;
|
|
|
|
if (freeInternalEntities) {
|
|
openEntity = freeInternalEntities;
|
|
freeInternalEntities = openEntity->next;
|
|
}
|
|
else {
|
|
openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY));
|
|
if (!openEntity)
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
entity->open = XML_TRUE;
|
|
entity->processed = 0;
|
|
openEntity->next = openInternalEntities;
|
|
openInternalEntities = openEntity;
|
|
openEntity->entity = entity;
|
|
openEntity->startTagLevel = tagLevel;
|
|
openEntity->betweenDecl = betweenDecl;
|
|
openEntity->internalEventPtr = NULL;
|
|
openEntity->internalEventEndPtr = NULL;
|
|
textStart = (char *)entity->textPtr;
|
|
textEnd = (char *)(entity->textPtr + entity->textLen);
|
|
|
|
#ifdef XML_DTD
|
|
if (entity->is_param) {
|
|
int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
|
|
result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
|
|
next, &next, XML_FALSE);
|
|
}
|
|
else
|
|
#endif /* XML_DTD */
|
|
result = doContent(parser, tagLevel, internalEncoding, textStart,
|
|
textEnd, &next, XML_FALSE);
|
|
|
|
if (result == XML_ERROR_NONE) {
|
|
if (textEnd != next && ps_parsing == XML_SUSPENDED) {
|
|
entity->processed = (int)(next - textStart);
|
|
processor = internalEntityProcessor;
|
|
}
|
|
else {
|
|
entity->open = XML_FALSE;
|
|
openInternalEntities = openEntity->next;
|
|
/* put openEntity back in list of free instances */
|
|
openEntity->next = freeInternalEntities;
|
|
freeInternalEntities = openEntity;
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
internalEntityProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
ENTITY *entity;
|
|
const char *textStart, *textEnd;
|
|
const char *next;
|
|
enum XML_Error result;
|
|
OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities;
|
|
if (!openEntity)
|
|
return XML_ERROR_UNEXPECTED_STATE;
|
|
|
|
entity = openEntity->entity;
|
|
textStart = ((char *)entity->textPtr) + entity->processed;
|
|
textEnd = (char *)(entity->textPtr + entity->textLen);
|
|
|
|
#ifdef XML_DTD
|
|
if (entity->is_param) {
|
|
int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
|
|
result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
|
|
next, &next, XML_FALSE);
|
|
}
|
|
else
|
|
#endif /* XML_DTD */
|
|
result = doContent(parser, openEntity->startTagLevel, internalEncoding,
|
|
textStart, textEnd, &next, XML_FALSE);
|
|
|
|
if (result != XML_ERROR_NONE)
|
|
return result;
|
|
else if (textEnd != next && ps_parsing == XML_SUSPENDED) {
|
|
entity->processed = (int)(next - (char *)entity->textPtr);
|
|
return result;
|
|
}
|
|
else {
|
|
entity->open = XML_FALSE;
|
|
openInternalEntities = openEntity->next;
|
|
/* put openEntity back in list of free instances */
|
|
openEntity->next = freeInternalEntities;
|
|
freeInternalEntities = openEntity;
|
|
}
|
|
|
|
#ifdef XML_DTD
|
|
if (entity->is_param) {
|
|
int tok;
|
|
processor = prologProcessor;
|
|
tok = XmlPrologTok(encoding, s, end, &next);
|
|
return doProlog(parser, encoding, s, end, tok, next, nextPtr,
|
|
(XML_Bool)!ps_finalBuffer);
|
|
}
|
|
else
|
|
#endif /* XML_DTD */
|
|
{
|
|
processor = contentProcessor;
|
|
/* see externalEntityContentProcessor vs contentProcessor */
|
|
return doContent(parser, parentParser ? 1 : 0, encoding, s, end,
|
|
nextPtr, (XML_Bool)!ps_finalBuffer);
|
|
}
|
|
}
|
|
|
|
static enum XML_Error PTRCALL
|
|
errorProcessor(XML_Parser parser,
|
|
const char *s,
|
|
const char *end,
|
|
const char **nextPtr)
|
|
{
|
|
return errorCode;
|
|
}
|
|
|
|
static enum XML_Error
|
|
storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
|
|
const char *ptr, const char *end,
|
|
STRING_POOL *pool)
|
|
{
|
|
enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr,
|
|
end, pool);
|
|
if (result)
|
|
return result;
|
|
if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20)
|
|
poolChop(pool);
|
|
if (!poolAppendChar(pool, XML_T('\0')))
|
|
return XML_ERROR_NO_MEMORY;
|
|
return XML_ERROR_NONE;
|
|
}
|
|
|
|
static enum XML_Error
|
|
appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
|
|
const char *ptr, const char *end,
|
|
STRING_POOL *pool)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
for (;;) {
|
|
const char *next;
|
|
int tok = XmlAttributeValueTok(enc, ptr, end, &next);
|
|
switch (tok) {
|
|
case XML_TOK_NONE:
|
|
return XML_ERROR_NONE;
|
|
case XML_TOK_INVALID:
|
|
if (enc == encoding)
|
|
eventPtr = next;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_PARTIAL:
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_INVALID_TOKEN;
|
|
case XML_TOK_CHAR_REF:
|
|
{
|
|
XML_Char buf[XML_ENCODE_MAX];
|
|
int i;
|
|
int n = XmlCharRefNumber(enc, ptr);
|
|
if (n < 0) {
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_BAD_CHAR_REF;
|
|
}
|
|
if (!isCdata
|
|
&& n == 0x20 /* space */
|
|
&& (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
|
|
break;
|
|
n = XmlEncode(n, (ICHAR *)buf);
|
|
if (!n) {
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_BAD_CHAR_REF;
|
|
}
|
|
for (i = 0; i < n; i++) {
|
|
if (!poolAppendChar(pool, buf[i]))
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
}
|
|
break;
|
|
case XML_TOK_DATA_CHARS:
|
|
if (!poolAppend(pool, enc, ptr, next))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
case XML_TOK_TRAILING_CR:
|
|
next = ptr + enc->minBytesPerChar;
|
|
/* fall through */
|
|
case XML_TOK_ATTRIBUTE_VALUE_S:
|
|
case XML_TOK_DATA_NEWLINE:
|
|
if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
|
|
break;
|
|
if (!poolAppendChar(pool, 0x20))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
case XML_TOK_ENTITY_REF:
|
|
{
|
|
const XML_Char *name;
|
|
ENTITY *entity;
|
|
char checkEntityDecl;
|
|
XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc,
|
|
ptr + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (ch) {
|
|
if (!poolAppendChar(pool, ch))
|
|
return XML_ERROR_NO_MEMORY;
|
|
break;
|
|
}
|
|
name = poolStoreString(&temp2Pool, enc,
|
|
ptr + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!name)
|
|
return XML_ERROR_NO_MEMORY;
|
|
entity = (ENTITY *)lookup(&dtd->generalEntities, name, 0);
|
|
poolDiscard(&temp2Pool);
|
|
/* First, determine if a check for an existing declaration is needed;
|
|
if yes, check that the entity exists, and that it is internal.
|
|
*/
|
|
if (pool == &dtd->pool) /* are we called from prolog? */
|
|
checkEntityDecl =
|
|
#ifdef XML_DTD
|
|
prologState.documentEntity &&
|
|
#endif /* XML_DTD */
|
|
(dtd->standalone
|
|
? !openInternalEntities
|
|
: !dtd->hasParamEntityRefs);
|
|
else /* if (pool == &tempPool): we are called from content */
|
|
checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone;
|
|
if (checkEntityDecl) {
|
|
if (!entity)
|
|
return XML_ERROR_UNDEFINED_ENTITY;
|
|
else if (!entity->is_internal)
|
|
return XML_ERROR_ENTITY_DECLARED_IN_PE;
|
|
}
|
|
else if (!entity) {
|
|
/* Cannot report skipped entity here - see comments on
|
|
skippedEntityHandler.
|
|
if (skippedEntityHandler)
|
|
skippedEntityHandler(handlerArg, name, 0);
|
|
*/
|
|
/* Cannot call the default handler because this would be
|
|
out of sync with the call to the startElementHandler.
|
|
if ((pool == &tempPool) && defaultHandler)
|
|
reportDefault(parser, enc, ptr, next);
|
|
*/
|
|
break;
|
|
}
|
|
if (entity->open) {
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_RECURSIVE_ENTITY_REF;
|
|
}
|
|
if (entity->notation) {
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_BINARY_ENTITY_REF;
|
|
}
|
|
if (!entity->textPtr) {
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF;
|
|
}
|
|
else {
|
|
enum XML_Error result;
|
|
const XML_Char *textEnd = entity->textPtr + entity->textLen;
|
|
entity->open = XML_TRUE;
|
|
result = appendAttributeValue(parser, internalEncoding, isCdata,
|
|
(char *)entity->textPtr,
|
|
(char *)textEnd, pool);
|
|
entity->open = XML_FALSE;
|
|
if (result)
|
|
return result;
|
|
}
|
|
}
|
|
break;
|
|
default:
|
|
if (enc == encoding)
|
|
eventPtr = ptr;
|
|
return XML_ERROR_UNEXPECTED_STATE;
|
|
}
|
|
ptr = next;
|
|
}
|
|
/* not reached */
|
|
}
|
|
|
|
static enum XML_Error
|
|
storeEntityValue(XML_Parser parser,
|
|
const ENCODING *enc,
|
|
const char *entityTextPtr,
|
|
const char *entityTextEnd)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
STRING_POOL *pool = &(dtd->entityValuePool);
|
|
enum XML_Error result = XML_ERROR_NONE;
|
|
#ifdef XML_DTD
|
|
int oldInEntityValue = prologState.inEntityValue;
|
|
prologState.inEntityValue = 1;
|
|
#endif /* XML_DTD */
|
|
/* never return Null for the value argument in EntityDeclHandler,
|
|
since this would indicate an external entity; therefore we
|
|
have to make sure that entityValuePool.start is not null */
|
|
if (!pool->blocks) {
|
|
if (!poolGrow(pool))
|
|
return XML_ERROR_NO_MEMORY;
|
|
}
|
|
|
|
for (;;) {
|
|
const char *next;
|
|
int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next);
|
|
switch (tok) {
|
|
case XML_TOK_PARAM_ENTITY_REF:
|
|
#ifdef XML_DTD
|
|
if (isParamEntity || enc != encoding) {
|
|
const XML_Char *name;
|
|
ENTITY *entity;
|
|
name = poolStoreString(&tempPool, enc,
|
|
entityTextPtr + enc->minBytesPerChar,
|
|
next - enc->minBytesPerChar);
|
|
if (!name) {
|
|
result = XML_ERROR_NO_MEMORY;
|
|
goto endEntityValue;
|
|
}
|
|
entity = (ENTITY *)lookup(&dtd->paramEntities, name, 0);
|
|
poolDiscard(&tempPool);
|
|
if (!entity) {
|
|
/* not a well-formedness error - see XML 1.0: WFC Entity Declared */
|
|
/* cannot report skipped entity here - see comments on
|
|
skippedEntityHandler
|
|
if (skippedEntityHandler)
|
|
skippedEntityHandler(handlerArg, name, 0);
|
|
*/
|
|
dtd->keepProcessing = dtd->standalone;
|
|
goto endEntityValue;
|
|
}
|
|
if (entity->open) {
|
|
if (enc == encoding)
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_RECURSIVE_ENTITY_REF;
|
|
goto endEntityValue;
|
|
}
|
|
if (entity->systemId) {
|
|
if (externalEntityRefHandler) {
|
|
dtd->paramEntityRead = XML_FALSE;
|
|
entity->open = XML_TRUE;
|
|
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
|
|
0,
|
|
entity->base,
|
|
entity->systemId,
|
|
entity->publicId)) {
|
|
entity->open = XML_FALSE;
|
|
result = XML_ERROR_EXTERNAL_ENTITY_HANDLING;
|
|
goto endEntityValue;
|
|
}
|
|
entity->open = XML_FALSE;
|
|
if (!dtd->paramEntityRead)
|
|
dtd->keepProcessing = dtd->standalone;
|
|
}
|
|
else
|
|
dtd->keepProcessing = dtd->standalone;
|
|
}
|
|
else {
|
|
entity->open = XML_TRUE;
|
|
result = storeEntityValue(parser,
|
|
internalEncoding,
|
|
(char *)entity->textPtr,
|
|
(char *)(entity->textPtr
|
|
+ entity->textLen));
|
|
entity->open = XML_FALSE;
|
|
if (result)
|
|
goto endEntityValue;
|
|
}
|
|
break;
|
|
}
|
|
#endif /* XML_DTD */
|
|
/* In the internal subset, PE references are not legal
|
|
within markup declarations, e.g entity values in this case. */
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_PARAM_ENTITY_REF;
|
|
goto endEntityValue;
|
|
case XML_TOK_NONE:
|
|
result = XML_ERROR_NONE;
|
|
goto endEntityValue;
|
|
case XML_TOK_ENTITY_REF:
|
|
case XML_TOK_DATA_CHARS:
|
|
if (!poolAppend(pool, enc, entityTextPtr, next)) {
|
|
result = XML_ERROR_NO_MEMORY;
|
|
goto endEntityValue;
|
|
}
|
|
break;
|
|
case XML_TOK_TRAILING_CR:
|
|
next = entityTextPtr + enc->minBytesPerChar;
|
|
/* fall through */
|
|
case XML_TOK_DATA_NEWLINE:
|
|
if (pool->end == pool->ptr && !poolGrow(pool)) {
|
|
result = XML_ERROR_NO_MEMORY;
|
|
goto endEntityValue;
|
|
}
|
|
*(pool->ptr)++ = 0xA;
|
|
break;
|
|
case XML_TOK_CHAR_REF:
|
|
{
|
|
XML_Char buf[XML_ENCODE_MAX];
|
|
int i;
|
|
int n = XmlCharRefNumber(enc, entityTextPtr);
|
|
if (n < 0) {
|
|
if (enc == encoding)
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_BAD_CHAR_REF;
|
|
goto endEntityValue;
|
|
}
|
|
n = XmlEncode(n, (ICHAR *)buf);
|
|
if (!n) {
|
|
if (enc == encoding)
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_BAD_CHAR_REF;
|
|
goto endEntityValue;
|
|
}
|
|
for (i = 0; i < n; i++) {
|
|
if (pool->end == pool->ptr && !poolGrow(pool)) {
|
|
result = XML_ERROR_NO_MEMORY;
|
|
goto endEntityValue;
|
|
}
|
|
*(pool->ptr)++ = buf[i];
|
|
}
|
|
}
|
|
break;
|
|
case XML_TOK_PARTIAL:
|
|
if (enc == encoding)
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_INVALID_TOKEN;
|
|
goto endEntityValue;
|
|
case XML_TOK_INVALID:
|
|
if (enc == encoding)
|
|
eventPtr = next;
|
|
result = XML_ERROR_INVALID_TOKEN;
|
|
goto endEntityValue;
|
|
default:
|
|
if (enc == encoding)
|
|
eventPtr = entityTextPtr;
|
|
result = XML_ERROR_UNEXPECTED_STATE;
|
|
goto endEntityValue;
|
|
}
|
|
entityTextPtr = next;
|
|
}
|
|
endEntityValue:
|
|
#ifdef XML_DTD
|
|
prologState.inEntityValue = oldInEntityValue;
|
|
#endif /* XML_DTD */
|
|
return result;
|
|
}
|
|
|
|
static void FASTCALL
|
|
normalizeLines(XML_Char *s)
|
|
{
|
|
XML_Char *p;
|
|
for (;; s++) {
|
|
if (*s == XML_T('\0'))
|
|
return;
|
|
if (*s == 0xD)
|
|
break;
|
|
}
|
|
p = s;
|
|
do {
|
|
if (*s == 0xD) {
|
|
*p++ = 0xA;
|
|
if (*++s == 0xA)
|
|
s++;
|
|
}
|
|
else
|
|
*p++ = *s++;
|
|
} while (*s);
|
|
*p = XML_T('\0');
|
|
}
|
|
|
|
static int
|
|
reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,
|
|
const char *start, const char *end)
|
|
{
|
|
const XML_Char *target;
|
|
XML_Char *data;
|
|
const char *tem;
|
|
if (!processingInstructionHandler) {
|
|
if (defaultHandler)
|
|
reportDefault(parser, enc, start, end);
|
|
return 1;
|
|
}
|
|
start += enc->minBytesPerChar * 2;
|
|
tem = start + XmlNameLength(enc, start);
|
|
target = poolStoreString(&tempPool, enc, start, tem);
|
|
if (!target)
|
|
return 0;
|
|
poolFinish(&tempPool);
|
|
data = poolStoreString(&tempPool, enc,
|
|
XmlSkipS(enc, tem),
|
|
end - enc->minBytesPerChar*2);
|
|
if (!data)
|
|
return 0;
|
|
normalizeLines(data);
|
|
processingInstructionHandler(handlerArg, target, data);
|
|
poolClear(&tempPool);
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
reportComment(XML_Parser parser, const ENCODING *enc,
|
|
const char *start, const char *end)
|
|
{
|
|
XML_Char *data;
|
|
if (!commentHandler) {
|
|
if (defaultHandler)
|
|
reportDefault(parser, enc, start, end);
|
|
return 1;
|
|
}
|
|
data = poolStoreString(&tempPool,
|
|
enc,
|
|
start + enc->minBytesPerChar * 4,
|
|
end - enc->minBytesPerChar * 3);
|
|
if (!data)
|
|
return 0;
|
|
normalizeLines(data);
|
|
commentHandler(handlerArg, data);
|
|
poolClear(&tempPool);
|
|
return 1;
|
|
}
|
|
|
|
static void
|
|
reportDefault(XML_Parser parser, const ENCODING *enc,
|
|
const char *s, const char *end)
|
|
{
|
|
if (MUST_CONVERT(enc, s)) {
|
|
const char **eventPP;
|
|
const char **eventEndPP;
|
|
if (enc == encoding) {
|
|
eventPP = &eventPtr;
|
|
eventEndPP = &eventEndPtr;
|
|
}
|
|
else {
|
|
eventPP = &(openInternalEntities->internalEventPtr);
|
|
eventEndPP = &(openInternalEntities->internalEventEndPtr);
|
|
}
|
|
do {
|
|
ICHAR *dataPtr = (ICHAR *)dataBuf;
|
|
XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
|
|
*eventEndPP = s;
|
|
defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf));
|
|
*eventPP = s;
|
|
} while (s != end);
|
|
}
|
|
else
|
|
defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s));
|
|
}
|
|
|
|
|
|
static int
|
|
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
|
|
XML_Bool isId, const XML_Char *value, XML_Parser parser)
|
|
{
|
|
DEFAULT_ATTRIBUTE *att;
|
|
if (value || isId) {
|
|
/* The handling of default attributes gets messed up if we have
|
|
a default which duplicates a non-default. */
|
|
int i;
|
|
for (i = 0; i < type->nDefaultAtts; i++)
|
|
if (attId == type->defaultAtts[i].id)
|
|
return 1;
|
|
if (isId && !type->idAtt && !attId->xmlns)
|
|
type->idAtt = attId;
|
|
}
|
|
if (type->nDefaultAtts == type->allocDefaultAtts) {
|
|
if (type->allocDefaultAtts == 0) {
|
|
type->allocDefaultAtts = 8;
|
|
type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts
|
|
* sizeof(DEFAULT_ATTRIBUTE));
|
|
if (!type->defaultAtts)
|
|
return 0;
|
|
}
|
|
else {
|
|
DEFAULT_ATTRIBUTE *temp;
|
|
int count = type->allocDefaultAtts * 2;
|
|
temp = (DEFAULT_ATTRIBUTE *)
|
|
REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE)));
|
|
if (temp == NULL)
|
|
return 0;
|
|
type->allocDefaultAtts = count;
|
|
type->defaultAtts = temp;
|
|
}
|
|
}
|
|
att = type->defaultAtts + type->nDefaultAtts;
|
|
att->id = attId;
|
|
att->value = value;
|
|
att->isCdata = isCdata;
|
|
if (!isCdata)
|
|
attId->maybeTokenized = XML_TRUE;
|
|
type->nDefaultAtts += 1;
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
const XML_Char *name;
|
|
for (name = elementType->name; *name; name++) {
|
|
if (*name == XML_T(':')) {
|
|
PREFIX *prefix;
|
|
const XML_Char *s;
|
|
for (s = elementType->name; s != name; s++) {
|
|
if (!poolAppendChar(&dtd->pool, *s))
|
|
return 0;
|
|
}
|
|
if (!poolAppendChar(&dtd->pool, XML_T('\0')))
|
|
return 0;
|
|
prefix = (PREFIX *)lookup(&dtd->prefixes, poolStart(&dtd->pool),
|
|
sizeof(PREFIX));
|
|
if (!prefix)
|
|
return 0;
|
|
if (prefix->name == poolStart(&dtd->pool))
|
|
poolFinish(&dtd->pool);
|
|
else
|
|
poolDiscard(&dtd->pool);
|
|
elementType->prefix = prefix;
|
|
|
|
}
|
|
}
|
|
return 1;
|
|
}
|
|
|
|
static ATTRIBUTE_ID *
|
|
getAttributeId(XML_Parser parser, const ENCODING *enc,
|
|
const char *start, const char *end)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
ATTRIBUTE_ID *id;
|
|
const XML_Char *name;
|
|
if (!poolAppendChar(&dtd->pool, XML_T('\0')))
|
|
return NULL;
|
|
name = poolStoreString(&dtd->pool, enc, start, end);
|
|
if (!name)
|
|
return NULL;
|
|
/* skip quotation mark - its storage will be re-used (like in name[-1]) */
|
|
++name;
|
|
id = (ATTRIBUTE_ID *)lookup(&dtd->attributeIds, name, sizeof(ATTRIBUTE_ID));
|
|
if (!id)
|
|
return NULL;
|
|
if (id->name != name)
|
|
poolDiscard(&dtd->pool);
|
|
else {
|
|
poolFinish(&dtd->pool);
|
|
if (!ns)
|
|
;
|
|
else if (name[0] == XML_T('x')
|
|
&& name[1] == XML_T('m')
|
|
&& name[2] == XML_T('l')
|
|
&& name[3] == XML_T('n')
|
|
&& name[4] == XML_T('s')
|
|
&& (name[5] == XML_T('\0') || name[5] == XML_T(':'))) {
|
|
if (name[5] == XML_T('\0'))
|
|
id->prefix = &dtd->defaultPrefix;
|
|
else
|
|
id->prefix = (PREFIX *)lookup(&dtd->prefixes, name + 6, sizeof(PREFIX));
|
|
id->xmlns = XML_TRUE;
|
|
}
|
|
else {
|
|
int i;
|
|
for (i = 0; name[i]; i++) {
|
|
/* attributes without prefix are *not* in the default namespace */
|
|
if (name[i] == XML_T(':')) {
|
|
int j;
|
|
for (j = 0; j < i; j++) {
|
|
if (!poolAppendChar(&dtd->pool, name[j]))
|
|
return NULL;
|
|
}
|
|
if (!poolAppendChar(&dtd->pool, XML_T('\0')))
|
|
return NULL;
|
|
id->prefix = (PREFIX *)lookup(&dtd->prefixes, poolStart(&dtd->pool),
|
|
sizeof(PREFIX));
|
|
if (!id->prefix)
|
|
return NULL;
|
|
if (id->prefix->name == poolStart(&dtd->pool))
|
|
poolFinish(&dtd->pool);
|
|
else
|
|
poolDiscard(&dtd->pool);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return id;
|
|
}
|
|
|
|
#define CONTEXT_SEP XML_T('\f')
|
|
|
|
static const XML_Char *
|
|
getContext(XML_Parser parser)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
HASH_TABLE_ITER iter;
|
|
XML_Bool needSep = XML_FALSE;
|
|
|
|
if (dtd->defaultPrefix.binding) {
|
|
int i;
|
|
int len;
|
|
if (!poolAppendChar(&tempPool, XML_T('=')))
|
|
return NULL;
|
|
len = dtd->defaultPrefix.binding->uriLen;
|
|
if (namespaceSeparator)
|
|
len--;
|
|
for (i = 0; i < len; i++)
|
|
if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i]))
|
|
return NULL;
|
|
needSep = XML_TRUE;
|
|
}
|
|
|
|
hashTableIterInit(&iter, &(dtd->prefixes));
|
|
for (;;) {
|
|
int i;
|
|
int len;
|
|
const XML_Char *s;
|
|
PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter);
|
|
if (!prefix)
|
|
break;
|
|
if (!prefix->binding)
|
|
continue;
|
|
if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
|
|
return NULL;
|
|
for (s = prefix->name; *s; s++)
|
|
if (!poolAppendChar(&tempPool, *s))
|
|
return NULL;
|
|
if (!poolAppendChar(&tempPool, XML_T('=')))
|
|
return NULL;
|
|
len = prefix->binding->uriLen;
|
|
if (namespaceSeparator)
|
|
len--;
|
|
for (i = 0; i < len; i++)
|
|
if (!poolAppendChar(&tempPool, prefix->binding->uri[i]))
|
|
return NULL;
|
|
needSep = XML_TRUE;
|
|
}
|
|
|
|
|
|
hashTableIterInit(&iter, &(dtd->generalEntities));
|
|
for (;;) {
|
|
const XML_Char *s;
|
|
ENTITY *e = (ENTITY *)hashTableIterNext(&iter);
|
|
if (!e)
|
|
break;
|
|
if (!e->open)
|
|
continue;
|
|
if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
|
|
return NULL;
|
|
for (s = e->name; *s; s++)
|
|
if (!poolAppendChar(&tempPool, *s))
|
|
return 0;
|
|
needSep = XML_TRUE;
|
|
}
|
|
|
|
if (!poolAppendChar(&tempPool, XML_T('\0')))
|
|
return NULL;
|
|
return tempPool.start;
|
|
}
|
|
|
|
static XML_Bool
|
|
setContext(XML_Parser parser, const XML_Char *context)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
const XML_Char *s = context;
|
|
|
|
while (*context != XML_T('\0')) {
|
|
if (*s == CONTEXT_SEP || *s == XML_T('\0')) {
|
|
ENTITY *e;
|
|
if (!poolAppendChar(&tempPool, XML_T('\0')))
|
|
return XML_FALSE;
|
|
e = (ENTITY *)lookup(&dtd->generalEntities, poolStart(&tempPool), 0);
|
|
if (e)
|
|
e->open = XML_TRUE;
|
|
if (*s != XML_T('\0'))
|
|
s++;
|
|
context = s;
|
|
poolDiscard(&tempPool);
|
|
}
|
|
else if (*s == XML_T('=')) {
|
|
PREFIX *prefix;
|
|
if (poolLength(&tempPool) == 0)
|
|
prefix = &dtd->defaultPrefix;
|
|
else {
|
|
if (!poolAppendChar(&tempPool, XML_T('\0')))
|
|
return XML_FALSE;
|
|
prefix = (PREFIX *)lookup(&dtd->prefixes, poolStart(&tempPool),
|
|
sizeof(PREFIX));
|
|
if (!prefix)
|
|
return XML_FALSE;
|
|
if (prefix->name == poolStart(&tempPool)) {
|
|
prefix->name = poolCopyString(&dtd->pool, prefix->name);
|
|
if (!prefix->name)
|
|
return XML_FALSE;
|
|
}
|
|
poolDiscard(&tempPool);
|
|
}
|
|
for (context = s + 1;
|
|
*context != CONTEXT_SEP && *context != XML_T('\0');
|
|
context++)
|
|
if (!poolAppendChar(&tempPool, *context))
|
|
return XML_FALSE;
|
|
if (!poolAppendChar(&tempPool, XML_T('\0')))
|
|
return XML_FALSE;
|
|
if (addBinding(parser, prefix, NULL, poolStart(&tempPool),
|
|
&inheritedBindings) != XML_ERROR_NONE)
|
|
return XML_FALSE;
|
|
poolDiscard(&tempPool);
|
|
if (*context != XML_T('\0'))
|
|
++context;
|
|
s = context;
|
|
}
|
|
else {
|
|
if (!poolAppendChar(&tempPool, *s))
|
|
return XML_FALSE;
|
|
s++;
|
|
}
|
|
}
|
|
return XML_TRUE;
|
|
}
|
|
|
|
static void FASTCALL
|
|
normalizePublicId(XML_Char *publicId)
|
|
{
|
|
XML_Char *p = publicId;
|
|
XML_Char *s;
|
|
for (s = publicId; *s; s++) {
|
|
switch (*s) {
|
|
case 0x20:
|
|
case 0xD:
|
|
case 0xA:
|
|
if (p != publicId && p[-1] != 0x20)
|
|
*p++ = 0x20;
|
|
break;
|
|
default:
|
|
*p++ = *s;
|
|
}
|
|
}
|
|
if (p != publicId && p[-1] == 0x20)
|
|
--p;
|
|
*p = XML_T('\0');
|
|
}
|
|
|
|
static DTD *
|
|
dtdCreate(const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD));
|
|
if (p == NULL)
|
|
return p;
|
|
poolInit(&(p->pool), ms);
|
|
poolInit(&(p->entityValuePool), ms);
|
|
hashTableInit(&(p->generalEntities), ms);
|
|
hashTableInit(&(p->elementTypes), ms);
|
|
hashTableInit(&(p->attributeIds), ms);
|
|
hashTableInit(&(p->prefixes), ms);
|
|
#ifdef XML_DTD
|
|
p->paramEntityRead = XML_FALSE;
|
|
hashTableInit(&(p->paramEntities), ms);
|
|
#endif /* XML_DTD */
|
|
p->defaultPrefix.name = NULL;
|
|
p->defaultPrefix.binding = NULL;
|
|
|
|
p->in_eldecl = XML_FALSE;
|
|
p->scaffIndex = NULL;
|
|
p->scaffold = NULL;
|
|
p->scaffLevel = 0;
|
|
p->scaffSize = 0;
|
|
p->scaffCount = 0;
|
|
p->contentStringLen = 0;
|
|
|
|
p->keepProcessing = XML_TRUE;
|
|
p->hasParamEntityRefs = XML_FALSE;
|
|
p->standalone = XML_FALSE;
|
|
return p;
|
|
}
|
|
|
|
static void
|
|
dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
HASH_TABLE_ITER iter;
|
|
hashTableIterInit(&iter, &(p->elementTypes));
|
|
for (;;) {
|
|
ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter);
|
|
if (!e)
|
|
break;
|
|
if (e->allocDefaultAtts != 0)
|
|
ms->free_fcn(e->defaultAtts);
|
|
}
|
|
hashTableClear(&(p->generalEntities));
|
|
#ifdef XML_DTD
|
|
p->paramEntityRead = XML_FALSE;
|
|
hashTableClear(&(p->paramEntities));
|
|
#endif /* XML_DTD */
|
|
hashTableClear(&(p->elementTypes));
|
|
hashTableClear(&(p->attributeIds));
|
|
hashTableClear(&(p->prefixes));
|
|
poolClear(&(p->pool));
|
|
poolClear(&(p->entityValuePool));
|
|
p->defaultPrefix.name = NULL;
|
|
p->defaultPrefix.binding = NULL;
|
|
|
|
p->in_eldecl = XML_FALSE;
|
|
|
|
ms->free_fcn(p->scaffIndex);
|
|
p->scaffIndex = NULL;
|
|
ms->free_fcn(p->scaffold);
|
|
p->scaffold = NULL;
|
|
|
|
p->scaffLevel = 0;
|
|
p->scaffSize = 0;
|
|
p->scaffCount = 0;
|
|
p->contentStringLen = 0;
|
|
|
|
p->keepProcessing = XML_TRUE;
|
|
p->hasParamEntityRefs = XML_FALSE;
|
|
p->standalone = XML_FALSE;
|
|
}
|
|
|
|
static void
|
|
dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
HASH_TABLE_ITER iter;
|
|
hashTableIterInit(&iter, &(p->elementTypes));
|
|
for (;;) {
|
|
ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter);
|
|
if (!e)
|
|
break;
|
|
if (e->allocDefaultAtts != 0)
|
|
ms->free_fcn(e->defaultAtts);
|
|
}
|
|
hashTableDestroy(&(p->generalEntities));
|
|
#ifdef XML_DTD
|
|
hashTableDestroy(&(p->paramEntities));
|
|
#endif /* XML_DTD */
|
|
hashTableDestroy(&(p->elementTypes));
|
|
hashTableDestroy(&(p->attributeIds));
|
|
hashTableDestroy(&(p->prefixes));
|
|
poolDestroy(&(p->pool));
|
|
poolDestroy(&(p->entityValuePool));
|
|
if (isDocEntity) {
|
|
ms->free_fcn(p->scaffIndex);
|
|
ms->free_fcn(p->scaffold);
|
|
}
|
|
ms->free_fcn(p);
|
|
}
|
|
|
|
/* Do a deep copy of the DTD. Return 0 for out of memory, non-zero otherwise.
|
|
The new DTD has already been initialized.
|
|
*/
|
|
static int
|
|
dtdCopy(DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
HASH_TABLE_ITER iter;
|
|
|
|
/* Copy the prefix table. */
|
|
|
|
hashTableIterInit(&iter, &(oldDtd->prefixes));
|
|
for (;;) {
|
|
const XML_Char *name;
|
|
const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter);
|
|
if (!oldP)
|
|
break;
|
|
name = poolCopyString(&(newDtd->pool), oldP->name);
|
|
if (!name)
|
|
return 0;
|
|
if (!lookup(&(newDtd->prefixes), name, sizeof(PREFIX)))
|
|
return 0;
|
|
}
|
|
|
|
hashTableIterInit(&iter, &(oldDtd->attributeIds));
|
|
|
|
/* Copy the attribute id table. */
|
|
|
|
for (;;) {
|
|
ATTRIBUTE_ID *newA;
|
|
const XML_Char *name;
|
|
const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter);
|
|
|
|
if (!oldA)
|
|
break;
|
|
/* Remember to allocate the scratch byte before the name. */
|
|
if (!poolAppendChar(&(newDtd->pool), XML_T('\0')))
|
|
return 0;
|
|
name = poolCopyString(&(newDtd->pool), oldA->name);
|
|
if (!name)
|
|
return 0;
|
|
++name;
|
|
newA = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), name,
|
|
sizeof(ATTRIBUTE_ID));
|
|
if (!newA)
|
|
return 0;
|
|
newA->maybeTokenized = oldA->maybeTokenized;
|
|
if (oldA->prefix) {
|
|
newA->xmlns = oldA->xmlns;
|
|
if (oldA->prefix == &oldDtd->defaultPrefix)
|
|
newA->prefix = &newDtd->defaultPrefix;
|
|
else
|
|
newA->prefix = (PREFIX *)lookup(&(newDtd->prefixes),
|
|
oldA->prefix->name, 0);
|
|
}
|
|
}
|
|
|
|
/* Copy the element type table. */
|
|
|
|
hashTableIterInit(&iter, &(oldDtd->elementTypes));
|
|
|
|
for (;;) {
|
|
int i;
|
|
ELEMENT_TYPE *newE;
|
|
const XML_Char *name;
|
|
const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter);
|
|
if (!oldE)
|
|
break;
|
|
name = poolCopyString(&(newDtd->pool), oldE->name);
|
|
if (!name)
|
|
return 0;
|
|
newE = (ELEMENT_TYPE *)lookup(&(newDtd->elementTypes), name,
|
|
sizeof(ELEMENT_TYPE));
|
|
if (!newE)
|
|
return 0;
|
|
if (oldE->nDefaultAtts) {
|
|
newE->defaultAtts = (DEFAULT_ATTRIBUTE *)
|
|
ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE));
|
|
if (!newE->defaultAtts) {
|
|
ms->free_fcn(newE);
|
|
return 0;
|
|
}
|
|
}
|
|
if (oldE->idAtt)
|
|
newE->idAtt = (ATTRIBUTE_ID *)
|
|
lookup(&(newDtd->attributeIds), oldE->idAtt->name, 0);
|
|
newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts;
|
|
if (oldE->prefix)
|
|
newE->prefix = (PREFIX *)lookup(&(newDtd->prefixes),
|
|
oldE->prefix->name, 0);
|
|
for (i = 0; i < newE->nDefaultAtts; i++) {
|
|
newE->defaultAtts[i].id = (ATTRIBUTE_ID *)
|
|
lookup(&(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0);
|
|
newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata;
|
|
if (oldE->defaultAtts[i].value) {
|
|
newE->defaultAtts[i].value
|
|
= poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value);
|
|
if (!newE->defaultAtts[i].value)
|
|
return 0;
|
|
}
|
|
else
|
|
newE->defaultAtts[i].value = NULL;
|
|
}
|
|
}
|
|
|
|
/* Copy the entity tables. */
|
|
if (!copyEntityTable(&(newDtd->generalEntities),
|
|
&(newDtd->pool),
|
|
&(oldDtd->generalEntities)))
|
|
return 0;
|
|
|
|
#ifdef XML_DTD
|
|
if (!copyEntityTable(&(newDtd->paramEntities),
|
|
&(newDtd->pool),
|
|
&(oldDtd->paramEntities)))
|
|
return 0;
|
|
newDtd->paramEntityRead = oldDtd->paramEntityRead;
|
|
#endif /* XML_DTD */
|
|
|
|
newDtd->keepProcessing = oldDtd->keepProcessing;
|
|
newDtd->hasParamEntityRefs = oldDtd->hasParamEntityRefs;
|
|
newDtd->standalone = oldDtd->standalone;
|
|
|
|
/* Don't want deep copying for scaffolding */
|
|
newDtd->in_eldecl = oldDtd->in_eldecl;
|
|
newDtd->scaffold = oldDtd->scaffold;
|
|
newDtd->contentStringLen = oldDtd->contentStringLen;
|
|
newDtd->scaffSize = oldDtd->scaffSize;
|
|
newDtd->scaffLevel = oldDtd->scaffLevel;
|
|
newDtd->scaffIndex = oldDtd->scaffIndex;
|
|
|
|
return 1;
|
|
} /* End dtdCopy */
|
|
|
|
static int
|
|
copyEntityTable(HASH_TABLE *newTable,
|
|
STRING_POOL *newPool,
|
|
const HASH_TABLE *oldTable)
|
|
{
|
|
HASH_TABLE_ITER iter;
|
|
const XML_Char *cachedOldBase = NULL;
|
|
const XML_Char *cachedNewBase = NULL;
|
|
|
|
hashTableIterInit(&iter, oldTable);
|
|
|
|
for (;;) {
|
|
ENTITY *newE;
|
|
const XML_Char *name;
|
|
const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter);
|
|
if (!oldE)
|
|
break;
|
|
name = poolCopyString(newPool, oldE->name);
|
|
if (!name)
|
|
return 0;
|
|
newE = (ENTITY *)lookup(newTable, name, sizeof(ENTITY));
|
|
if (!newE)
|
|
return 0;
|
|
if (oldE->systemId) {
|
|
const XML_Char *tem = poolCopyString(newPool, oldE->systemId);
|
|
if (!tem)
|
|
return 0;
|
|
newE->systemId = tem;
|
|
if (oldE->base) {
|
|
if (oldE->base == cachedOldBase)
|
|
newE->base = cachedNewBase;
|
|
else {
|
|
cachedOldBase = oldE->base;
|
|
tem = poolCopyString(newPool, cachedOldBase);
|
|
if (!tem)
|
|
return 0;
|
|
cachedNewBase = newE->base = tem;
|
|
}
|
|
}
|
|
if (oldE->publicId) {
|
|
tem = poolCopyString(newPool, oldE->publicId);
|
|
if (!tem)
|
|
return 0;
|
|
newE->publicId = tem;
|
|
}
|
|
}
|
|
else {
|
|
const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr,
|
|
oldE->textLen);
|
|
if (!tem)
|
|
return 0;
|
|
newE->textPtr = tem;
|
|
newE->textLen = oldE->textLen;
|
|
}
|
|
if (oldE->notation) {
|
|
const XML_Char *tem = poolCopyString(newPool, oldE->notation);
|
|
if (!tem)
|
|
return 0;
|
|
newE->notation = tem;
|
|
}
|
|
newE->is_param = oldE->is_param;
|
|
newE->is_internal = oldE->is_internal;
|
|
}
|
|
return 1;
|
|
}
|
|
|
|
#define INIT_POWER 6
|
|
|
|
static XML_Bool FASTCALL
|
|
keyeq(KEY s1, KEY s2)
|
|
{
|
|
for (; *s1 == *s2; s1++, s2++)
|
|
if (*s1 == 0)
|
|
return XML_TRUE;
|
|
return XML_FALSE;
|
|
}
|
|
|
|
static unsigned long FASTCALL
|
|
hash(KEY s)
|
|
{
|
|
unsigned long h = 0;
|
|
while (*s)
|
|
h = CHAR_HASH(h, *s++);
|
|
return h;
|
|
}
|
|
|
|
static NAMED *
|
|
lookup(HASH_TABLE *table, KEY name, size_t createSize)
|
|
{
|
|
size_t i;
|
|
if (table->size == 0) {
|
|
size_t tsize;
|
|
if (!createSize)
|
|
return NULL;
|
|
table->power = INIT_POWER;
|
|
/* table->size is a power of 2 */
|
|
table->size = (size_t)1 << INIT_POWER;
|
|
tsize = table->size * sizeof(NAMED *);
|
|
table->v = (NAMED **)table->mem->malloc_fcn(tsize);
|
|
if (!table->v) {
|
|
table->size = 0;
|
|
return NULL;
|
|
}
|
|
memset(table->v, 0, tsize);
|
|
i = hash(name) & ((unsigned long)table->size - 1);
|
|
}
|
|
else {
|
|
unsigned long h = hash(name);
|
|
unsigned long mask = (unsigned long)table->size - 1;
|
|
unsigned char step = 0;
|
|
i = h & mask;
|
|
while (table->v[i]) {
|
|
if (keyeq(name, table->v[i]->name))
|
|
return table->v[i];
|
|
if (!step)
|
|
step = PROBE_STEP(h, mask, table->power);
|
|
i < step ? (i += table->size - step) : (i -= step);
|
|
}
|
|
if (!createSize)
|
|
return NULL;
|
|
|
|
/* check for overflow (table is half full) */
|
|
if (table->used >> (table->power - 1)) {
|
|
unsigned char newPower = table->power + 1;
|
|
size_t newSize = (size_t)1 << newPower;
|
|
unsigned long newMask = (unsigned long)newSize - 1;
|
|
size_t tsize = newSize * sizeof(NAMED *);
|
|
NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize);
|
|
if (!newV)
|
|
return NULL;
|
|
memset(newV, 0, tsize);
|
|
for (i = 0; i < table->size; i++)
|
|
if (table->v[i]) {
|
|
unsigned long newHash = hash(table->v[i]->name);
|
|
size_t j = newHash & newMask;
|
|
step = 0;
|
|
while (newV[j]) {
|
|
if (!step)
|
|
step = PROBE_STEP(newHash, newMask, newPower);
|
|
j < step ? (j += newSize - step) : (j -= step);
|
|
}
|
|
newV[j] = table->v[i];
|
|
}
|
|
table->mem->free_fcn(table->v);
|
|
table->v = newV;
|
|
table->power = newPower;
|
|
table->size = newSize;
|
|
i = h & newMask;
|
|
step = 0;
|
|
while (table->v[i]) {
|
|
if (!step)
|
|
step = PROBE_STEP(h, newMask, newPower);
|
|
i < step ? (i += newSize - step) : (i -= step);
|
|
}
|
|
}
|
|
}
|
|
table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize);
|
|
if (!table->v[i])
|
|
return NULL;
|
|
memset(table->v[i], 0, createSize);
|
|
table->v[i]->name = name;
|
|
(table->used)++;
|
|
return table->v[i];
|
|
}
|
|
|
|
static void FASTCALL
|
|
hashTableClear(HASH_TABLE *table)
|
|
{
|
|
size_t i;
|
|
for (i = 0; i < table->size; i++) {
|
|
table->mem->free_fcn(table->v[i]);
|
|
table->v[i] = NULL;
|
|
}
|
|
table->used = 0;
|
|
}
|
|
|
|
static void FASTCALL
|
|
hashTableDestroy(HASH_TABLE *table)
|
|
{
|
|
size_t i;
|
|
for (i = 0; i < table->size; i++)
|
|
table->mem->free_fcn(table->v[i]);
|
|
table->mem->free_fcn(table->v);
|
|
}
|
|
|
|
static void FASTCALL
|
|
hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
p->power = 0;
|
|
p->size = 0;
|
|
p->used = 0;
|
|
p->v = NULL;
|
|
p->mem = ms;
|
|
}
|
|
|
|
static void FASTCALL
|
|
hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table)
|
|
{
|
|
iter->p = table->v;
|
|
iter->end = iter->p + table->size;
|
|
}
|
|
|
|
static NAMED * FASTCALL
|
|
hashTableIterNext(HASH_TABLE_ITER *iter)
|
|
{
|
|
while (iter->p != iter->end) {
|
|
NAMED *tem = *(iter->p)++;
|
|
if (tem)
|
|
return tem;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static void FASTCALL
|
|
poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms)
|
|
{
|
|
pool->blocks = NULL;
|
|
pool->freeBlocks = NULL;
|
|
pool->start = NULL;
|
|
pool->ptr = NULL;
|
|
pool->end = NULL;
|
|
pool->mem = ms;
|
|
}
|
|
|
|
static void FASTCALL
|
|
poolClear(STRING_POOL *pool)
|
|
{
|
|
if (!pool->freeBlocks)
|
|
pool->freeBlocks = pool->blocks;
|
|
else {
|
|
BLOCK *p = pool->blocks;
|
|
while (p) {
|
|
BLOCK *tem = p->next;
|
|
p->next = pool->freeBlocks;
|
|
pool->freeBlocks = p;
|
|
p = tem;
|
|
}
|
|
}
|
|
pool->blocks = NULL;
|
|
pool->start = NULL;
|
|
pool->ptr = NULL;
|
|
pool->end = NULL;
|
|
}
|
|
|
|
static void FASTCALL
|
|
poolDestroy(STRING_POOL *pool)
|
|
{
|
|
BLOCK *p = pool->blocks;
|
|
while (p) {
|
|
BLOCK *tem = p->next;
|
|
pool->mem->free_fcn(p);
|
|
p = tem;
|
|
}
|
|
p = pool->freeBlocks;
|
|
while (p) {
|
|
BLOCK *tem = p->next;
|
|
pool->mem->free_fcn(p);
|
|
p = tem;
|
|
}
|
|
}
|
|
|
|
static XML_Char *
|
|
poolAppend(STRING_POOL *pool, const ENCODING *enc,
|
|
const char *ptr, const char *end)
|
|
{
|
|
if (!pool->ptr && !poolGrow(pool))
|
|
return NULL;
|
|
for (;;) {
|
|
XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end);
|
|
if (ptr == end)
|
|
break;
|
|
if (!poolGrow(pool))
|
|
return NULL;
|
|
}
|
|
return pool->start;
|
|
}
|
|
|
|
static const XML_Char * FASTCALL
|
|
poolCopyString(STRING_POOL *pool, const XML_Char *s)
|
|
{
|
|
do {
|
|
if (!poolAppendChar(pool, *s))
|
|
return NULL;
|
|
} while (*s++);
|
|
s = pool->start;
|
|
poolFinish(pool);
|
|
return s;
|
|
}
|
|
|
|
static const XML_Char *
|
|
poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n)
|
|
{
|
|
if (!pool->ptr && !poolGrow(pool))
|
|
return NULL;
|
|
for (; n > 0; --n, s++) {
|
|
if (!poolAppendChar(pool, *s))
|
|
return NULL;
|
|
}
|
|
s = pool->start;
|
|
poolFinish(pool);
|
|
return s;
|
|
}
|
|
|
|
static const XML_Char * FASTCALL
|
|
poolAppendString(STRING_POOL *pool, const XML_Char *s)
|
|
{
|
|
while (*s) {
|
|
if (!poolAppendChar(pool, *s))
|
|
return NULL;
|
|
s++;
|
|
}
|
|
return pool->start;
|
|
}
|
|
|
|
static XML_Char *
|
|
poolStoreString(STRING_POOL *pool, const ENCODING *enc,
|
|
const char *ptr, const char *end)
|
|
{
|
|
if (!poolAppend(pool, enc, ptr, end))
|
|
return NULL;
|
|
if (pool->ptr == pool->end && !poolGrow(pool))
|
|
return NULL;
|
|
*(pool->ptr)++ = 0;
|
|
return pool->start;
|
|
}
|
|
|
|
static XML_Bool FASTCALL
|
|
poolGrow(STRING_POOL *pool)
|
|
{
|
|
if (pool->freeBlocks) {
|
|
if (pool->start == 0) {
|
|
pool->blocks = pool->freeBlocks;
|
|
pool->freeBlocks = pool->freeBlocks->next;
|
|
pool->blocks->next = NULL;
|
|
pool->start = pool->blocks->s;
|
|
pool->end = pool->start + pool->blocks->size;
|
|
pool->ptr = pool->start;
|
|
return XML_TRUE;
|
|
}
|
|
if (pool->end - pool->start < pool->freeBlocks->size) {
|
|
BLOCK *tem = pool->freeBlocks->next;
|
|
pool->freeBlocks->next = pool->blocks;
|
|
pool->blocks = pool->freeBlocks;
|
|
pool->freeBlocks = tem;
|
|
memcpy(pool->blocks->s, pool->start,
|
|
(pool->end - pool->start) * sizeof(XML_Char));
|
|
pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
|
|
pool->start = pool->blocks->s;
|
|
pool->end = pool->start + pool->blocks->size;
|
|
return XML_TRUE;
|
|
}
|
|
}
|
|
if (pool->blocks && pool->start == pool->blocks->s) {
|
|
int blockSize = (int)(pool->end - pool->start)*2;
|
|
pool->blocks = (BLOCK *)
|
|
pool->mem->realloc_fcn(pool->blocks,
|
|
(offsetof(BLOCK, s)
|
|
+ blockSize * sizeof(XML_Char)));
|
|
if (pool->blocks == NULL)
|
|
return XML_FALSE;
|
|
pool->blocks->size = blockSize;
|
|
pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
|
|
pool->start = pool->blocks->s;
|
|
pool->end = pool->start + blockSize;
|
|
}
|
|
else {
|
|
BLOCK *tem;
|
|
int blockSize = (int)(pool->end - pool->start);
|
|
if (blockSize < INIT_BLOCK_SIZE)
|
|
blockSize = INIT_BLOCK_SIZE;
|
|
else
|
|
blockSize *= 2;
|
|
tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s)
|
|
+ blockSize * sizeof(XML_Char));
|
|
if (!tem)
|
|
return XML_FALSE;
|
|
tem->size = blockSize;
|
|
tem->next = pool->blocks;
|
|
pool->blocks = tem;
|
|
if (pool->ptr != pool->start)
|
|
memcpy(tem->s, pool->start,
|
|
(pool->ptr - pool->start) * sizeof(XML_Char));
|
|
pool->ptr = tem->s + (pool->ptr - pool->start);
|
|
pool->start = tem->s;
|
|
pool->end = tem->s + blockSize;
|
|
}
|
|
return XML_TRUE;
|
|
}
|
|
|
|
static int FASTCALL
|
|
nextScaffoldPart(XML_Parser parser)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
CONTENT_SCAFFOLD * me;
|
|
int next;
|
|
|
|
if (!dtd->scaffIndex) {
|
|
dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int));
|
|
if (!dtd->scaffIndex)
|
|
return -1;
|
|
dtd->scaffIndex[0] = 0;
|
|
}
|
|
|
|
if (dtd->scaffCount >= dtd->scaffSize) {
|
|
CONTENT_SCAFFOLD *temp;
|
|
if (dtd->scaffold) {
|
|
temp = (CONTENT_SCAFFOLD *)
|
|
REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
|
|
if (temp == NULL)
|
|
return -1;
|
|
dtd->scaffSize *= 2;
|
|
}
|
|
else {
|
|
temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS
|
|
* sizeof(CONTENT_SCAFFOLD));
|
|
if (temp == NULL)
|
|
return -1;
|
|
dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS;
|
|
}
|
|
dtd->scaffold = temp;
|
|
}
|
|
next = dtd->scaffCount++;
|
|
me = &dtd->scaffold[next];
|
|
if (dtd->scaffLevel) {
|
|
CONTENT_SCAFFOLD *parent = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel-1]];
|
|
if (parent->lastchild) {
|
|
dtd->scaffold[parent->lastchild].nextsib = next;
|
|
}
|
|
if (!parent->childcnt)
|
|
parent->firstchild = next;
|
|
parent->lastchild = next;
|
|
parent->childcnt++;
|
|
}
|
|
me->firstchild = me->lastchild = me->childcnt = me->nextsib = 0;
|
|
return next;
|
|
}
|
|
|
|
static void
|
|
build_node(XML_Parser parser,
|
|
int src_node,
|
|
XML_Content *dest,
|
|
XML_Content **contpos,
|
|
XML_Char **strpos)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
dest->type = dtd->scaffold[src_node].type;
|
|
dest->quant = dtd->scaffold[src_node].quant;
|
|
if (dest->type == XML_CTYPE_NAME) {
|
|
const XML_Char *src;
|
|
dest->name = *strpos;
|
|
src = dtd->scaffold[src_node].name;
|
|
for (;;) {
|
|
*(*strpos)++ = *src;
|
|
if (!*src)
|
|
break;
|
|
src++;
|
|
}
|
|
dest->numchildren = 0;
|
|
dest->children = NULL;
|
|
}
|
|
else {
|
|
unsigned int i;
|
|
int cn;
|
|
dest->numchildren = dtd->scaffold[src_node].childcnt;
|
|
dest->children = *contpos;
|
|
*contpos += dest->numchildren;
|
|
for (i = 0, cn = dtd->scaffold[src_node].firstchild;
|
|
i < dest->numchildren;
|
|
i++, cn = dtd->scaffold[cn].nextsib) {
|
|
build_node(parser, cn, &(dest->children[i]), contpos, strpos);
|
|
}
|
|
dest->name = NULL;
|
|
}
|
|
}
|
|
|
|
static XML_Content *
|
|
build_model (XML_Parser parser)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
XML_Content *ret;
|
|
XML_Content *cpos;
|
|
XML_Char * str;
|
|
int allocsize = (dtd->scaffCount * sizeof(XML_Content)
|
|
+ (dtd->contentStringLen * sizeof(XML_Char)));
|
|
|
|
ret = (XML_Content *)MALLOC(allocsize);
|
|
if (!ret)
|
|
return NULL;
|
|
|
|
str = (XML_Char *) (&ret[dtd->scaffCount]);
|
|
cpos = &ret[1];
|
|
|
|
build_node(parser, 0, ret, &cpos, &str);
|
|
return ret;
|
|
}
|
|
|
|
static ELEMENT_TYPE *
|
|
getElementType(XML_Parser parser,
|
|
const ENCODING *enc,
|
|
const char *ptr,
|
|
const char *end)
|
|
{
|
|
DTD * const dtd = _dtd; /* save one level of indirection */
|
|
const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end);
|
|
ELEMENT_TYPE *ret;
|
|
|
|
if (!name)
|
|
return NULL;
|
|
ret = (ELEMENT_TYPE *) lookup(&dtd->elementTypes, name, sizeof(ELEMENT_TYPE));
|
|
if (!ret)
|
|
return NULL;
|
|
if (ret->name != name)
|
|
poolDiscard(&dtd->pool);
|
|
else {
|
|
poolFinish(&dtd->pool);
|
|
if (!setElementTypePrefix(parser, ret))
|
|
return NULL;
|
|
}
|
|
return ret;
|
|
}
|