Add .plg file.

Ifdef other differences on W3C14N.

expat/.gitignore

@@ -0,0 +1,8 @@
+bin
+dbgbin
+Debug
+expat.ncb
+expat.opt
+Release
+expat.zip
+lib

expat/MPL-1_0.html

@@ -1,420 +0,0 @@
-<TITLE>Mozilla Public License version 1.0</TITLE>
-<BODY BGCOLOR="#FFFFFF" TEXT="#000000"
-      LINK="#0000EE" VLINK="#551A8B" ALINK="#FF0000">
-
-<P ALIGN=CENTER>
-  <FONT SIZE="+2"><B>MOZILLA PUBLIC LICENSE</B></FONT><BR>
-  <B>Version 1.0</B>
-</P>
-
-<P><HR WIDTH="20%"><P>
-
-<P><B>1. Definitions.</B>
-<UL>
-
-    <B>1.1. ``Contributor''</B> means each entity that creates or contributes
-    to the creation of Modifications.
-
-    <P><B>1.2. ``Contributor Version''</B> means the combination of the
-    Original Code, prior Modifications used by a Contributor, and the
-    Modifications made by that particular Contributor.
-
-    <P><B>1.3. ``Covered Code''</B> means the Original Code or Modifications
-    or the combination of the Original Code and Modifications, in each case
-    including portions thereof<B>.</B>
-
-    <P><B>1.4. ``Electronic Distribution Mechanism''</B> means a mechanism
-    generally accepted in the software development community for the
-    electronic transfer of data.
-
-    <P><B>1.5. ``Executable''</B> means Covered Code in any form other than
-    Source Code.
-
-    <P><B>1.6. ``Initial Developer''</B> means the individual or entity
-    identified as the Initial Developer in the Source Code notice required by
-    <B>Exhibit A</B>.
-
-    <P><B>1.7. ``Larger Work''</B> means a work which combines Covered Code
-    or portions thereof with code not governed by the terms of this License.
-
-    <P><B>1.8. ``License''</B> means this document.
-
-    <P><B>1.9. ``Modifications''</B> means any addition to or deletion from
-    the substance or structure of either the Original Code or any previous
-    Modifications.  When Covered Code is released as a series of files, a
-    Modification is: 
-
-	<UL>
-
-	<P><B>A.</B> Any addition to or deletion from the contents of a file
-	containing Original Code or previous Modifications.
-
-	<P><B>B.</B> Any new file that contains any part of the Original
-	Code or previous Modifications.
-
-	</UL>
-
-    <P><B>1.10. ``Original Code''</B> means Source Code of computer software
-    code which is described in the Source Code notice required by <B>Exhibit
-    A</B> as Original Code, and which, at the time of its release under this
-    License is not already Covered Code governed by this License.
-
-    <P><B>1.11. ``Source Code''</B> means the preferred form of the Covered
-    Code for making modifications to it, including all modules it contains,
-    plus any associated interface definition files, scripts used to control
-    compilation and installation of an Executable, or a list of source code
-    differential comparisons against either the Original Code or another well
-    known, available Covered Code of the Contributor's choice. The Source
-    Code can be in a compressed or archival form, provided the appropriate
-    decompression or de-archiving software is widely available for no charge.
-
-    <P><B>1.12. ``You''</B> means an individual or a legal entity exercising
-    rights under, and complying with all of the terms of, this License or a
-    future version of this License issued under Section 6.1. For legal
-    entities, ``You'' includes any entity which controls, is controlled by,
-    or is under common control with You. For purposes of this definition,
-    ``control'' means (a) the power, direct or indirect, to cause the
-    direction or management of such entity, whether by contract or otherwise,
-    or (b) ownership of fifty percent (50%) or more of the outstanding shares
-    or beneficial ownership of such entity.
-
-</UL>
-<B>2. Source Code License.</B>
-<UL>
-
-    <B>2.1. The Initial Developer Grant.</B>
-
-    <BR>The Initial Developer hereby grants You a world-wide, royalty-free,
-    non-exclusive license, subject to third party intellectual property
-    claims: 
-
-	<UL>
-
-	<P><B>(a)</B> to use, reproduce, modify, display, perform, sublicense
-	and distribute the Original Code (or portions thereof) with or
-	without Modifications, or as part of a Larger Work; and
-
-        <P><B>(b)</B> under patents now or hereafter owned or controlled by
-        Initial Developer, to make, have made, use and sell (``Utilize'') the
-        Original Code (or portions thereof), but solely to the extent that
-        any such patent is reasonably necessary to enable You to Utilize the
-        Original Code (or portions thereof) and not to any greater extent
-        that may be necessary to Utilize further Modifications or
-        combinations.
-    </UL>
-
-    <P><B>2.2. Contributor Grant.</B>
-
-    <BR>Each Contributor hereby grants You a world-wide, royalty-free,
-    non-exclusive license, subject to third party intellectual property
-    claims: 
-
-    <UL>
-
-    <P><B>(a)</B> to use, reproduce, modify, display, perform, sublicense and
-    distribute the Modifications created by such Contributor (or portions
-    thereof) either on an unmodified basis, with other Modifications, as
-    Covered Code or as part of a Larger Work; and
-
-    <P><B>(b)</B> under patents now or hereafter owned or controlled by
-    Contributor, to Utilize the Contributor Version (or portions thereof),
-    but solely to the extent that any such patent is reasonably necessary to
-    enable You to Utilize the Contributor Version (or portions thereof), and
-    not to any greater extent that may be necessary to Utilize further
-    Modifications or combinations.
-
-    </UL>
-
-</UL>
-<B>3. Distribution Obligations.</B>
-<UL>
-
-    <B>3.1. Application of License.</B>
-
-    <BR>The Modifications which You create or to which You contribute are
-    governed by the terms of this License, including without limitation
-    Section <B>2.2</B>.  The Source Code version of Covered Code may be
-    distributed only under the terms of this License or a future version of
-    this License released under Section <B>6.1</B>, and You must include a
-    copy of this License with every copy of the Source Code You
-    distribute. You may not offer or impose any terms on any Source Code
-    version that alters or restricts the applicable version of this License
-    or the recipients' rights hereunder. However, You may include an
-    additional document offering the additional rights described in Section
-    <B>3.5</B>.
-
-    <P><B>3.2. Availability of Source Code.</B>
-
-    <BR>Any Modification which You create or to which You contribute must be
-    made available in Source Code form under the terms of this License either
-    on the same media as an Executable version or via an accepted Electronic
-    Distribution Mechanism to anyone to whom you made an Executable version
-    available; and if made available via Electronic Distribution Mechanism,
-    must remain available for at least twelve (12) months after the date it
-    initially became available, or at least six (6) months after a subsequent
-    version of that particular Modification has been made available to such
-    recipients. You are responsible for ensuring that the Source Code version
-    remains available even if the Electronic Distribution Mechanism is
-    maintained by a third party.
-
-    <P><B>3.3. Description of Modifications.</B>
-
-    <BR>You must cause all Covered Code to which you contribute to contain a
-    file documenting the changes You made to create that Covered Code and the
-    date of any change. You must include a prominent statement that the
-    Modification is derived, directly or indirectly, from Original Code
-    provided by the Initial Developer and including the name of the Initial
-    Developer in (a) the Source Code, and (b) in any notice in an Executable
-    version or related documentation in which You describe the origin or
-    ownership of the Covered Code.
-
-    <P><B>3.4. Intellectual Property Matters</B>
-    <UL>
-
-	<P><B>(a) Third Party Claims</B>. 
-
-	<BR>If You have knowledge that a party claims an intellectual
-	property right in particular functionality or code (or its
-	utilization under this License), you must include a text file with
-	the source code distribution titled ``LEGAL'' which describes the
-	claim and the party making the claim in sufficient detail that a
-	recipient will know whom to contact. If you obtain such knowledge
-	after You make Your Modification available as described in Section
-	<B>3.2</B>, You shall promptly modify the LEGAL file in all copies
-	You make available thereafter and shall take other steps (such as
-	notifying appropriate mailing lists or newsgroups) reasonably
-	calculated to inform those who received the Covered Code that new
-	knowledge has been obtained.
-
-	<P><B>(b) Contributor APIs</B>. 
-
-	<BR>If Your Modification is an application programming interface and
-	You own or control patents which are reasonably necessary to
-	implement that API, you must also include this information in the
-	LEGAL file.
-
-    </UL>
-
-    <P><B>3.5. Required Notices.</B>
-
-    <BR>You must duplicate the notice in <B>Exhibit A</B> in each file of the
-    Source Code, and this License in any documentation for the Source Code,
-    where You describe recipients' rights relating to Covered Code. If You
-    created one or more Modification(s), You may add your name as a
-    Contributor to the notice described in <B>Exhibit A</B>. If it is not
-    possible to put such notice in a particular Source Code file due to its
-    structure, then you must include such notice in a location (such as a
-    relevant directory file) where a user would be likely to look for such a
-    notice.  You may choose to offer, and to charge a fee for, warranty,
-    support, indemnity or liability obligations to one or more recipients of
-    Covered Code. However, You may do so only on Your own behalf, and not on
-    behalf of the Initial Developer or any Contributor.  You must make it
-    absolutely clear than any such warranty, support, indemnity or liability
-    obligation is offered by You alone, and You hereby agree to indemnify the
-    Initial Developer and every Contributor for any liability incurred by the
-    Initial Developer or such Contributor as a result of warranty, support,
-    indemnity or liability terms You offer.
-
-    <P><B>3.6. Distribution of Executable Versions.</B>
-
-    <BR>You may distribute Covered Code in Executable form only if the
-    requirements of Section <B>3.1-3.5</B> have been met for that Covered
-    Code, and if You include a notice stating that the Source Code version of
-    the Covered Code is available under the terms of this License, including
-    a description of how and where You have fulfilled the obligations of
-    Section <B>3.2</B>.  The notice must be conspicuously included in any
-    notice in an Executable version, related documentation or collateral in
-    which You describe recipients' rights relating to the Covered Code. You
-    may distribute the Executable version of Covered Code under a license of
-    Your choice, which may contain terms different from this License,
-    provided that You are in compliance with the terms of this License and
-    that the license for the Executable version does not attempt to limit or
-    alter the recipient's rights in the Source Code version from the rights
-    set forth in this License. If You distribute the Executable version under
-    a different license You must make it absolutely clear that any terms
-    which differ from this License are offered by You alone, not by the
-    Initial Developer or any Contributor. You hereby agree to indemnify the
-    Initial Developer and every Contributor for any liability incurred by the
-    Initial Developer or such Contributor as a result of any such terms You
-    offer.
-
-    <P><B>3.7. Larger Works.</B>
-
-    <BR>You may create a Larger Work by combining Covered Code with other
-    code not governed by the terms of this License and distribute the Larger
-    Work as a single product. In such a case, You must make sure the
-    requirements of this License are fulfilled for the Covered Code.
-
-</UL>
-<B>4. Inability to Comply Due to Statute or Regulation.</B>
-<UL>
-
-    <P>If it is impossible for You to comply with any of the terms of this
-    License with respect to some or all of the Covered Code due to statute or
-    regulation then You must: (a) comply with the terms of this License to
-    the maximum extent possible; and (b) describe the limitations and the
-    code they affect. Such description must be included in the LEGAL file
-    described in Section <B>3.4</B> and must be included with all
-    distributions of the Source Code. Except to the extent prohibited by
-    statute or regulation, such description must be sufficiently detailed for
-    a recipient of ordinary skill
-    to be able to understand it.
-
-</UL>
-<B>5. Application of this License.</B>
-<UL>
-
-    This License applies to code to which the Initial Developer has attached
-    the notice in <B>Exhibit A</B>, and to related Covered Code.
-
-</UL>
-<B>6. Versions of the License.</B>
-<UL>
-
-    <B>6.1. New Versions</B>. 
-
-    <BR>Netscape Communications Corporation (``Netscape'') may publish
-    revised and/or new versions of the License from time to time.  Each
-    version will be given a distinguishing version number.
-
-    <P><B>6.2. Effect of New Versions</B>. 
-
-    <BR>Once Covered Code has been published under a particular version of
-    the License, You may always continue to use it under the terms of that
-    version. You may also choose to use such Covered Code under the terms of
-    any subsequent version of the License published by Netscape. No one other
-    than Netscape has the right to modify the terms applicable to Covered
-    Code created under this License.
-
-    <P><B>6.3. Derivative Works</B>. 
-
-    <BR>If you create or use a modified version of this License (which you
-    may only do in order to apply it to code which is not already Covered
-    Code governed by this License), you must (a) rename Your license so that
-    the phrases ``Mozilla'', ``MOZILLAPL'', ``MOZPL'', ``Netscape'', ``NPL''
-    or any confusingly similar phrase do not appear anywhere in your license
-    and (b) otherwise make it clear that your version of the license contains
-    terms which differ from the Mozilla Public License and Netscape Public
-    License. (Filling in the name of the Initial Developer, Original Code or
-    Contributor in the notice described in <B>Exhibit A</B> shall not of
-    themselves be deemed to be modifications of this License.)
-
-</UL>
-<B>7. DISCLAIMER OF WARRANTY.</B>
-<UL>
-
-    COVERED CODE IS PROVIDED UNDER THIS LICENSE ON AN ``AS IS'' BASIS,
-    WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
-    WITHOUT LIMITATION, WARRANTIES THAT THE COVERED CODE IS FREE OF DEFECTS,
-    MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR NON-INFRINGING. THE ENTIRE
-    RISK AS TO THE QUALITY AND PERFORMANCE OF THE COVERED CODE IS WITH
-    YOU. SHOULD ANY COVERED CODE PROVE DEFECTIVE IN ANY RESPECT, YOU (NOT THE
-    INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE COST OF ANY
-    NECESSARY SERVICING, REPAIR OR CORRECTION. THIS DISCLAIMER OF WARRANTY
-    CONSTITUTES AN ESSENTIAL PART OF THIS LICENSE. NO USE OF ANY COVERED CODE
-    IS AUTHORIZED HEREUNDER EXCEPT UNDER THIS DISCLAIMER.
-
-</UL>
-<B>8. TERMINATION.</B>
-<UL>
-
-    This License and the rights granted hereunder will terminate
-    automatically if You fail to comply with terms herein and fail to cure
-    such breach within 30 days of becoming aware of the breach. All
-    sublicenses to the Covered Code which are properly granted shall survive
-    any termination of this License.  Provisions which, by their nature, must
-    remain in effect beyond the termination of this License shall survive.
-
-</UL>
-<B>9. LIMITATION OF LIABILITY.</B>
-<UL>
-
-    UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT (INCLUDING
-    NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL THE INITIAL DEVELOPER, ANY
-    OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED CODE, OR ANY SUPPLIER OF
-    ANY OF SUCH PARTIES, BE LIABLE TO YOU OR ANY OTHER PERSON FOR ANY
-    INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES OF ANY CHARACTER
-    INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF GOODWILL, WORK
-    STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER
-    COMMERCIAL DAMAGES OR LOSSES, EVEN IF SUCH PARTY SHALL HAVE BEEN INFORMED
-    OF THE POSSIBILITY OF SUCH DAMAGES. THIS LIMITATION OF LIABILITY SHALL
-    NOT APPLY TO LIABILITY FOR DEATH OR PERSONAL INJURY RESULTING FROM SUCH
-    PARTY'S NEGLIGENCE TO THE EXTENT APPLICABLE LAW PROHIBITS SUCH
-    LIMITATION. SOME JURISDICTIONS DO NOT ALLOW THE EXCLUSION OR LIMITATION
-    OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO THAT EXCLUSION AND LIMITATION
-    MAY NOT APPLY TO YOU.
-
-</UL>
-<B>10. U.S. GOVERNMENT END USERS.</B>
-<UL>
-
-    The Covered Code is a ``commercial item,'' as that term is defined in 48
-    C.F.R. 2.101 (Oct. 1995), consisting of ``commercial computer software''
-    and ``commercial computer software documentation,'' as such terms are
-    used in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48 C.F.R. 12.212
-    and 48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995), all
-    U.S. Government End Users acquire Covered Code with only those rights set
-    forth herein.
-
-</UL>
-<B>11. MISCELLANEOUS.</B>
-<UL>
-
-    This License represents the complete agreement concerning subject matter
-    hereof. If any provision of this License is held to be unenforceable,
-    such provision shall be reformed only to the extent necessary to make it
-    enforceable. This License shall be governed by California law provisions
-    (except to the extent applicable law, if any, provides otherwise),
-    excluding its conflict-of-law provisions. With respect to disputes in
-    which at least one party is a citizen of, or an entity chartered or
-    registered to do business in, the United States of America: (a) unless
-    otherwise agreed in writing, all disputes relating to this License
-    (excepting any dispute relating to intellectual property rights) shall be
-    subject to final and binding arbitration, with the losing party paying
-    all costs of arbitration; (b) any arbitration relating to this Agreement
-    shall be held in Santa Clara County, California, under the auspices of
-    JAMS/EndDispute; and (c) any litigation relating to this Agreement shall
-    be subject to the jurisdiction of the Federal Courts of the Northern
-    District of California, with venue lying in Santa Clara County,
-    California, with the losing party responsible for costs, including
-    without limitation, court costs and reasonable attorneys fees and
-    expenses.  The application of the United Nations Convention on Contracts
-    for the International Sale of Goods is expressly excluded. Any law or
-    regulation which provides that the language of a contract shall be
-    construed against the drafter shall not apply to this License.
-
-</UL>
-<B>12. RESPONSIBILITY FOR CLAIMS.</B>
-<UL>
-
-    Except in cases where another Contributor has failed to comply with
-    Section <B>3.4</B>, You are responsible for damages arising, directly or
-    indirectly, out of Your utilization of rights under this License, based
-    on the number of copies of Covered Code you made available, the revenues
-    you received from utilizing such rights, and other relevant factors. You
-    agree to work with affected parties to distribute responsibility on an
-    equitable basis.
-
-</UL>
-<B>EXHIBIT A.</B>
-<UL>
-
-    ``The contents of this file are subject to the Mozilla Public License
-    Version 1.0 (the "License"); you may not use this file except in
-    compliance with the License. You may obtain a copy of the License at
-    http://www.mozilla.org/MPL/
-
-    <P>Software distributed under the License is distributed on an "AS IS"
-    basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-    License for the specific language governing rights and limitations under
-    the License.
-
-    <P>The Original Code is ______________________________________.
-
-    <P>The Initial Developer of the Original Code is
-    ________________________.  Portions created by ______________________ are
-    Copyright (C) ______ _______________________.  All Rights Reserved.
-
-    <P>Contributor(s): ______________________________________.''
-
-</UL>

expat/Makefile

@@ -1,30 +1,37 @@
 CC=gcc
-# If you know what your system's byte order is, define BYTE_ORDER:
-# use -DBYTE_ORDER=12 for little-endian byte order;
-# use -DBYTE_ORDER=21 for big-endian (network) byte order.
+# If you know what your system's byte order is, define XML_BYTE_ORDER:
+# use -DXML_BYTE_ORDER=12 for little-endian byte order;
+# use -DXML_BYTE_ORDER=21 for big-endian (network) byte order.
 # -DXML_NS adds support for checking of lexical aspects of XML namespaces spec
 # -DXML_MIN_SIZE makes a smaller but slower parser
-CFLAGS=-O2 -Ixmltok -Ixmlparse -DXML_NS
+# -DXML_DTD adds full support for parsing DTDs
+CFLAGS=-Wall -O2 -Ixmltok -Ixmlparse -DXML_NS -DXML_DTD
+AR=ar
 # Use one of the next two lines; unixfilemap is better if it works.
 FILEMAP_OBJ=xmlwf/unixfilemap.o
 #FILEMAP_OBJ=xmlwf/readfilemap.o
-OBJS=xmltok/xmltok.o \
+LIBOBJS=xmltok/xmltok.o \
   xmltok/xmlrole.o \
-  xmlwf/xmlwf.o \
+  xmlparse/xmlparse.o
+
+OBJS=xmlwf/xmlwf.o \
   xmlwf/xmlfile.o \
   xmlwf/codepage.o \
-  xmlparse/xmlparse.o \
-  xmlparse/hashtable.o \
   $(FILEMAP_OBJ)
+LIB=xmlparse/libexpat.a
 EXE=
+XMLWF=xmlwf/xmlwf$(EXE)
 
-all: xmlwf/xmlwf$(EXE)
+all: $(XMLWF)
 
-xmlwf/xmlwf$(EXE): $(OBJS)
-	$(CC) $(CFLAGS) -o $@ $(OBJS)
+$(XMLWF): $(OBJS) $(LIB)
+	$(CC) $(CFLAGS) -o $@ $(OBJS) $(LIB)
+
+$(LIB): $(LIBOBJS)
+	$(AR) rc $(LIB) $(LIBOBJS)
 
 clean:
-	rm -f $(OBJS) xmlwf/xmlwf$(EXE)
+	rm -f $(OBJS) $(LIBOBJS) $(LIB) $(XMLWF)
 
 xmltok/nametab.h: gennmtab/gennmtab$(EXE)
 	rm -f $@

expat/copying.txt

@@ -0,0 +1,20 @@
+Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

expat/demo/demo.c

@@ -1,46 +0,0 @@
-/* This is simple demonstration of how to use expat. This program
-reads an XML document from standard input and writes a line with the
-name of each element to standard output indenting child elements by
-one tab stop more than their parent element. */
-
-#include <stdio.h>
-#include "xmlparse.h"
-
-void startElement(void *userData, const char *name, const char **atts)
-{
-  int i;
-  int *depthPtr = userData;
-  for (i = 0; i < *depthPtr; i++)
-    putchar('\t');
-  puts(name);
-  *depthPtr += 1;
-}
-
-void endElement(void *userData, const char *name)
-{
-  int *depthPtr = userData;
-  *depthPtr -= 1;
-}
-
-int main()
-{
-  char buf[BUFSIZ];
-  XML_Parser parser = XML_ParserCreate(NULL);
-  int done;
-  int depth = 0;
-  XML_SetUserData(parser, &depth);
-  XML_SetElementHandler(parser, startElement, endElement);
-  do {
-    size_t len = fread(buf, 1, sizeof(buf), stdin);
-    done = len < sizeof(buf);
-    if (!XML_Parse(parser, buf, len, done)) {
-      fprintf(stderr,
-	      "%s at line %d\n",
-	      XML_ErrorString(XML_GetErrorCode(parser)),
-	      XML_GetCurrentLineNumber(parser));
-      return 1;
-    }
-  } while (!done);
-  XML_ParserFree(parser);
-  return 0;
-}

expat/expat.dsw

@@ -3,7 +3,7 @@ Microsoft Developer Studio Workspace File, Format Version 6.00
 
 ###############################################################################
 
-Project: "gennmtab"=".\gennmtab\gennmtab.dsp" - Package Owner=<4>
+Project: "gennmtab"=.\gennmtab\gennmtab.dsp - Package Owner=<4>
 
 Package=<5>
 {{{
@@ -15,7 +15,7 @@ Package=<4>
 
 ###############################################################################
 
-Project: "xmlparse"=".\xmlparse\xmlparse.dsp" - Package Owner=<4>
+Project: "xmlparse"=.\xmlparse\xmlparse.dsp - Package Owner=<4>
 
 Package=<5>
 {{{
@@ -30,7 +30,7 @@ Package=<4>
 
 ###############################################################################
 
-Project: "xmltok"=".\xmltok\xmltok.dsp" - Package Owner=<4>
+Project: "xmltok"=.\xmltok\xmltok.dsp - Package Owner=<4>
 
 Package=<5>
 {{{
@@ -38,11 +38,14 @@ Package=<5>
 
 Package=<4>
 {{{
+    Begin Project Dependency
+    Project_Dep_Name gennmtab
+    End Project Dependency
 }}}
 
 ###############################################################################
 
-Project: "xmlwf"=".\xmlwf\xmlwf.dsp" - Package Owner=<4>
+Project: "xmlwf"=.\xmlwf\xmlwf.dsp - Package Owner=<4>
 
 Package=<5>
 {{{

expat/expat.html

@@ -9,20 +9,27 @@
 
 <H1>expat - XML Parser Toolkit</H1>
 
-<H3>Version 19990109</H3>
+<H3>Version 20000512</H3>
 
-<P>Copyright (c) 1998, 1999 James Clark.  Expat is subject to the <A
-HREF="MPL-1_0.html">Mozilla Public License Version 1.0</A>.  You may
-as a special exception <A href="gplelect.html">elect to use the GNU
-General Public License</A>.  Please contact me if you wish to
-negotiate an alternative license.</P>
+<P>Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center
+Ltd.  Expat is freely available with source under a very liberal <a
+href="copying.txt">license</a> (the MIT license).</P>
+
+<P>This is a test version of expat which adds support for parsing
+external DTDs and parameter entities.  Compiling with -DXML_DTD
+enables this support.  There's a new <CODE>-p</CODE> option for xmlwf
+which will cause it to process external DTDs and parameter entities;
+this implies the <CODE>-x</CODE> option.  See the comment above
+<CODE>XML_SetParamEntityParsing</CODE> in <CODE>xmlparse.h</CODE> for
+the API addition that enables this.</P>
 
 <P>Expat is an <A
 HREF="http://www.w3.org/TR/1998/REC-xml-19980210">XML 1.0</A> parser
 written in C. It aims to be fully conforming.  It is currently not a
 validating XML processor.  The current production version of expat can
-be downloaded from <A href = "ftp://ftp.jclark.com/pub/xml/expat.zip"
->ftp://ftp.jclark.com/pub/xml/expat.zip</A>.</P>
+be downloaded from <A href =
+"http://www.ThaiOpenSource.com/dist/expat/expat.zip"
+>http://www.ThaiOpenSource.com/dist/expat/expat.zip</A>.</P>
 
 <P>The directory <SAMP>xmltok</SAMP> contains a low-level library for
 tokenizing XML.  The interface is documented in
@@ -45,16 +52,26 @@ href="http://www.jclark.com/xml/canonxml.html">canonical XML</A> will
 be written to <SAMP>dir/<VAR>f</VAR></SAMP>, where
 <SAMP><VAR>f</VAR></SAMP> is the filename (without any path) of the
 input file.  A <CODE>-x</CODE> option will cause references to
-external general entities to be processed.</P>
+external general entities to be processed.  A <CODE>-s</CODE> option
+will make documents that are not standalone cause an error (a document
+is considered standalone if either it is intrinsically standalone
+because it has no external subset and no references to parameter
+entities in the internal subset or it is declared as standalone in the
+XML declaration).</P>
 
 <P>The <SAMP>bin</SAMP> directory contains Win32 executables.  The
 <SAMP>lib</SAMP> directory contains Win32 import libraries.</P>
 
+<P>Answers to some frequently asked questions about expat can be found
+in the <A
+HREF="http://www.ThaiOpenSource.com/product/expat/expatfaq.html">expat
+FAQ</A>.</P>
+
 <P></P>
 
 <ADDRESS>
 
-<A HREF="mailto:jjc@jclark.com">James Clark</A>
+<A HREF="mailto:jjc@ThaiOpenSource.com">James Clark</A>
 
 </ADDRESS>
 

expat/expat.pj

@@ -1,54 +0,0 @@
---MKS Project--
-$Revision: 1.17 $
-block _mks_variant_projects
-1.11=vp0000.pj, "V1_0maintain"
-end
-EndOptions
-$(projectdir)/MPL-1_0.html a 1.1 
-$(projectdir)/Makefile a 1.10 
-$(projectdir)/expat.dsw a 1.1 
-$(projectdir)/expat.html a 1.14 
-$(projectdir)/expat.mak a 1.14 
-$(projectdir)/expatfaq.html a 1.1 
-$(projectdir)/files.txt a 1.8 
-$(projectdir)/gplelect.html a 1.1 
-$(projectdir)/makedist.ksh a 1.2 
-$(projectdir)/win32files.txt a 1.1 
-$(projectdir)/gennmtab/gennmtab.c a 1.2 
-$(projectdir)/gennmtab/gennmtab.dsp a 1.1 
-$(projectdir)/sample/build.bat a 1.2 
-$(projectdir)/sample/elements.c a 1.1 
-$(projectdir)/xmlparse/hashtable.c a 1.8 
-$(projectdir)/xmlparse/hashtable.h a 1.4 
-$(projectdir)/xmlparse/xmlparse.c a 1.73 
-$(projectdir)/xmlparse/xmlparse.dsp a 1.5 
-$(projectdir)/xmlparse/xmlparse.h a 1.30 
-$(projectdir)/xmltok/asciitab.h a 1.5 
-$(projectdir)/xmltok/dllmain.c a 1.3 
-$(projectdir)/xmltok/iasciitab.h a 1.3 
-$(projectdir)/xmltok/latin1tab.h a 1.2 
-$(projectdir)/xmltok/utf8tab.h a 1.4 
-$(projectdir)/xmltok/xmldef.h a 1.7 
-$(projectdir)/xmltok/xmlrole.c a 1.10 
-$(projectdir)/xmltok/xmlrole.h a 1.5 
-$(projectdir)/xmltok/xmltok.c a 1.44 
-$(projectdir)/xmltok/xmltok.dsp a 1.4 
-$(projectdir)/xmltok/xmltok.h a 1.25 
-$(projectdir)/xmltok/xmltok_impl.c a 1.33 
-$(projectdir)/xmltok/xmltok_impl.h a 1.6 
-$(projectdir)/xmltok/xmltok_ns.c a 1.3 
-$(projectdir)/xmlwf/codepage.c a 1.5 
-$(projectdir)/xmlwf/codepage.h a 1.3 
-$(projectdir)/xmlwf/filemap.h a 1.3 
-$(projectdir)/xmlwf/readfilemap.c a 1.3 
-$(projectdir)/xmlwf/unixfilemap.c a 1.2 
-$(projectdir)/xmlwf/win32filemap.c a 1.6 
-$(projectdir)/xmlwf/xmlfile.c a 1.2 
-$(projectdir)/xmlwf/xmlfile.h a 1.1 
-$(projectdir)/xmlwf/xmlmime.c a 1.1 
-$(projectdir)/xmlwf/xmlmime.h a 1.1 
-$(projectdir)/xmlwf/xmltchar.h a 1.1 
-$(projectdir)/xmlwf/xmlurl.h a 1.1 
-$(projectdir)/xmlwf/xmlwf.c a 1.38 
-$(projectdir)/xmlwf/xmlwf.dsp a 1.2 
-$(projectdir)/xmlwf/xmlwin32url.cxx a 1.1 

expat/expatfaq.html

@@ -12,18 +12,19 @@
 <H4>Where can I get the latest version of expat?</H4>
 
 <p>The latest production version is always available from <a
-href="ftp://ftp.jclark.com/pub/xml/expat.zip"
->ftp://ftp.jclark.com/pub/xml/expat.zip</a>.  The latest test version
-is always available from <a
-href="ftp://ftp.jclark.com/pub/test/expat.zip"
->ftp://ftp.jclark.com/pub/test/expat.zip</a>.</p>
+href="http://www.ThaiOpenSource.com/dist/expat"
+>http://www.ThaiOpenSource.com/dist/expat</a>.  If there is a test
+version, then it will be available from <a
+href="http://www.ThaiOpenSource.com/dist/expat/test"
+>http://www.ThaiOpenSource.com/dist/expat/test</a>.</p>
 
 <H4>Where can I get help in using expat?</H4>
 
 <p>Try the xml-dev mailing list (subscribe by mailing to <a
-href="mailto:majordomo@ic.ac.uk">majordomo@ic.ac.uk</a> with the
-message <code>subscribe xml-dev</code>).  Alternatively try the <a
-href="news:comp.text.xml">comp.text.xml</a> USENET newsgroup.</p>
+href="mailto:majordomo@xml.org&BODY=subscribe%20xml-dev">majordomo@xml.org</a>
+with the message <code>subscribe xml-dev</code>).  Alternatively try
+the <a href="news:comp.text.xml">comp.text.xml</a> USENET
+newsgroup.</p>
 
 <H4>Where is expat's API documented?</H4>
 
@@ -31,6 +32,10 @@ href="news:comp.text.xml">comp.text.xml</a> USENET newsgroup.</p>
 low-level API you can use which is documented in
 <code>xmltok/xmltok.h</code>.</p>
 
+<p>There's also an excellent <a
+href="http://www.xml.com/pub/1999/09/expat/index.html">article</a>
+about expat on XML.com by Clark Cooper.</p>
+
 <H4>Is there a simple example of using expat's API?</H4>
 
 <p>See <code>sample/elements.c</code></p>
@@ -67,21 +72,8 @@ an argument of <code>"iso-8859-1"</code> to
 
 <H4>How can I get expat to read my DTD?</H4>
 
-<p>expat only reads the internal DTD subset.  It doesn't process an
-external DTD nor parameter entity references.  This behaviour is in
-conformance with the XML Recommendation.</p>
-
-<H4>Why does expat give the wrong result for the more complex example in
-Appendix D of the XML Recommendation?</H4>
-
-<P>expat does not process parameter entity references.  (The XML
-Recommendation only requires parsers to process parameter entity
-references when validating. See section 4.4.8.)</P>
-
-<H4>Why does expat give the wrong result for test cases in James
-Clark's test suite in the <code>xmltest/valid/not-sa</code>?</H4>
-
-<P>expat doesn't process parameter entities.</P>
+<p>Compile with <code>-DXML_DTD</code> and call
+<code>XML_SetParamEntityParsing</code>.</p>
 
 <H4>How can I get expat to recover from errors?</H4>
 
@@ -93,9 +85,16 @@ continue normal processing after a fatal error.</p>
 
 <p>Use <code>XML_SetCharacterDataHandler</code>.</p>
 
+<H4>How can I minimize the size of expat?</H4>
+
+<p>Compile with <code>-DXML_MIN_SIZE</code>. With Visual C++, use the
+<code>Win32 MinSize</code> configuration: this creates an
+<code>xmlparse.dll</code> that does not require
+<code>xmltok.dll</code>.</p>
+
 <ADDRESS>
 
-<A HREF="mailto:jjc@jclark.com">James Clark</A>
+<A HREF="mailto:jjc@ThaiOpenSource.com">James Clark</A>
 
 </ADDRESS>
 

expat/files.txt

@@ -1,6 +1,5 @@
 expat.html
-MPL-1_0.html
-gplelect.html
+xmltok/ascii.h
 xmltok/asciitab.h
 xmltok/dllmain.c
 gennmtab/gennmtab.c
@@ -17,8 +16,6 @@ xmltok/xmltok.h
 xmltok/xmltok_impl.c
 xmltok/xmltok_impl.h
 xmltok/xmltok_ns.c
-xmlparse/hashtable.c
-xmlparse/hashtable.h
 xmlparse/xmlparse.c
 xmlparse/xmlparse.h
 xmlwf/codepage.c

expat/gennmtab/.gitignore

@@ -0,0 +1,3 @@
+Debug
+Release
+gennmtab.plg

expat/gennmtab/gennmtab.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <string.h>

expat/gplelect.html

@@ -1,55 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
-"http://www.w3.org/TR/REC-html40/loose.dtd">
-
-<HTML>
-
-<TITLE>Using the GPL for expat</TITLE>
-
-<BODY>
-
-<H1>Using the GPL for expat</H1>
-
-<P>Instead of using the Mozilla Public License, you may instead elect
-to use the <A href="http://www.gnu.org/copyleft/gpl.html">GNU General
-Public License</A> (GPL) for a particular copy of expat.  The election
-to use the GPL is irrevocable for that particular copy.  If you do
-elect to use the GPL, then you must replace the copyright notice on
-each file with the following:</P>
-
-<PRE>
-expat XML parser
-Copyright (C) 1998 James Clark
-
-This program is free software; you can redistribute it and/or
-modify it under the terms of the GNU General Public License
-as published by the Free Software Foundation; either version 2
-of the License, or (at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program; if not, write to the Free Software
-Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
-</PRE>
-
-<P>and you must change readme.html to say that an election has been
-made to use this copy under the GPL.  If you redistribute expat, you
-should also include a copy of the GPL.</P>
-
-<P>Note that I will probably not accept patches under terms that allow
-me to distribute them only under the GPL.</P>
-
-<P></P>
-
-<ADDRESS>
-
-<A HREF="mailto:jjc@jclark.com">James Clark</A>
-
-</ADDRESS>
-
-</BODY>
-
-</HTML>

expat/makedist.bat

@@ -0,0 +1,7 @@
+xcopy /y xmltok\Release\xmltok.lib lib
+xcopy /y xmlparse\Release\xmlparse.lib lib
+rm -f expat.zip
+cd ..
+sed -e 's;^^;expat/;' expat\files.txt | zip -qr expat\expat.zip -@ -ll
+sed -e 's;^^;expat/;' expat\win32files.txt | zip -qr expat\expat.zip -@
+cd expat 

expat/makedist.ksh

@@ -1,9 +0,0 @@
-xcopy xmltok\\Release\\xmltok.lib lib
-xcopy xmlparse\\Release\\xmlparse.lib lib
-rm -fr expat
-mkdir expat
-tar cf - `cat files.txt win32files.txt` | (cd expat; tar xf -)
-(cd expat; flip -u `cat ../files.txt`)
-rm -f expat.zip
-zip -qr expat.zip expat
-rm -fr expat

expat/win32files.txt

@@ -1,5 +1,4 @@
 expat.dsw
-expat.mak
 gennmtab/gennmtab.dsp
 sample/build.bat
 xmlparse/xmlparse.dsp

expat/xmlparse/.gitignore

@@ -0,0 +1,3 @@
+Debug
+Release
+xmlparse.plg

expat/xmlparse/hashtable.c

@@ -1,141 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-csompliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
-*/
-
-#include "xmldef.h"
-
-#ifdef XML_UNICODE_WCHAR_T
-#ifndef XML_UNICODE
-#define XML_UNICODE
-#endif
-#endif
-
-#include "hashtable.h"
-
-#define INIT_SIZE 64
-
-static
-int keyeq(KEY s1, KEY s2)
-{
-  for (; *s1 == *s2; s1++, s2++)
-    if (*s1 == 0)
-      return 1;
-  return 0;
-}
-
-static
-unsigned long hash(KEY s)
-{
-  unsigned long h = 0;
-  while (*s)
-    h = (h << 5) + h + (unsigned char)*s++;
-  return h;
-}
-
-NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize)
-{
-  size_t i;
-  if (table->size == 0) {
-    if (!createSize)
-      return 0;
-    table->v = calloc(INIT_SIZE, sizeof(NAMED *));
-    if (!table->v)
-      return 0;
-    table->size = INIT_SIZE;
-    table->usedLim = INIT_SIZE / 2;
-    i = hash(name) & (table->size - 1);
-  }
-  else {
-    unsigned long h = hash(name);
-    for (i = h & (table->size - 1);
-         table->v[i];
-         i == 0 ? i = table->size - 1 : --i) {
-      if (keyeq(name, table->v[i]->name))
-	return table->v[i];
-    }
-    if (!createSize)
-      return 0;
-    if (table->used == table->usedLim) {
-      /* check for overflow */
-      size_t newSize = table->size * 2;
-      NAMED **newV = calloc(newSize, sizeof(NAMED *));
-      if (!newV)
-	return 0;
-      for (i = 0; i < table->size; i++)
-	if (table->v[i]) {
-	  size_t j;
-	  for (j = hash(table->v[i]->name) & (newSize - 1);
-	       newV[j];
-	       j == 0 ? j = newSize - 1 : --j)
-	    ;
-	  newV[j] = table->v[i];
-	}
-      free(table->v);
-      table->v = newV;
-      table->size = newSize;
-      table->usedLim = newSize/2;
-      for (i = h & (table->size - 1);
-	   table->v[i];
-	   i == 0 ? i = table->size - 1 : --i)
-	;
-    }
-  }
-  table->v[i] = calloc(1, createSize);
-  if (!table->v[i])
-    return 0;
-  table->v[i]->name = name;
-  (table->used)++;
-  return table->v[i];
-}
-
-void hashTableDestroy(HASH_TABLE *table)
-{
-  size_t i;
-  for (i = 0; i < table->size; i++) {
-    NAMED *p = table->v[i];
-    if (p)
-      free(p);
-  }
-  free(table->v);
-}
-
-void hashTableInit(HASH_TABLE *p)
-{
-  p->size = 0;
-  p->usedLim = 0;
-  p->used = 0;
-  p->v = 0;
-}
-
-void hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table)
-{
-  iter->p = table->v;
-  iter->end = iter->p + table->size;
-}
-
-NAMED *hashTableIterNext(HASH_TABLE_ITER *iter)
-{
-  while (iter->p != iter->end) {
-    NAMED *tem = *(iter->p)++;
-    if (tem)
-      return tem;
-  }
-  return 0;
-}
-

expat/xmlparse/hashtable.h

@@ -1,51 +0,0 @@
-/*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
-*/
-
-
-#include <stddef.h>
-
-#ifdef XML_UNICODE
-typedef const wchar_t *KEY;
-#else
-typedef const char *KEY;
-#endif
-
-typedef struct {
-  KEY name;
-} NAMED;
-
-typedef struct {
-  NAMED **v;
-  size_t size;
-  size_t used;
-  size_t usedLim;
-} HASH_TABLE;
-
-NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize);
-void hashTableInit(HASH_TABLE *);
-void hashTableDestroy(HASH_TABLE *);
-
-typedef struct {
-  NAMED **p;
-  NAMED **end;
-} HASH_TABLE_ITER;
-
-void hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *);
-NAMED *hashTableIterNext(HASH_TABLE_ITER *);

expat/xmlparse/xmlparse.dsp

@@ -44,7 +44,7 @@ RSC=rc.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir "."
 # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c
-# ADD CPP /nologo /W3 /GX /O2 /I "..\xmltok" /I "..\xmlwf" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D "XML_NS" /YX /FD /c
+# ADD CPP /nologo /W3 /GX /O2 /I "..\xmltok" /I "..\xmlwf" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /D "NDEBUG" /D "XML_NS" /D "WIN32" /D "_WINDOWS" /D "XML_DTD" /YX /FD /c
 # ADD BASE MTL /nologo /D "NDEBUG" /win32
 # ADD MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x809 /d "NDEBUG"
@@ -54,8 +54,8 @@ BSC32=bscmake.exe
 # ADD BSC32 /nologo
 LINK32=link.exe
 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386
-# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /base:"0x20000000" /subsystem:windows /dll /machine:I386 /out:"..\bin\xmlparse.dll"
-# SUBTRACT LINK32 /profile
+# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /base:"0x20000000" /subsystem:windows /dll /machine:I386 /out:"..\bin\xmlparse.dll" /link50compat
+# SUBTRACT LINK32 /pdb:none
 
 !ELSEIF  "$(CFG)" == "xmlparse - Win32 Debug"
 
@@ -71,7 +71,7 @@ LINK32=link.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir "."
 # ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c
-# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\xmltok" /I "..\xmlwf" /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /YX /FD /c
+# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\xmltok" /I "..\xmlwf" /D "_DEBUG" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /D "WIN32" /D "_WINDOWS" /D "XML_DTD" /YX /FD /c
 # ADD BASE MTL /nologo /D "_DEBUG" /win32
 # ADD MTL /nologo /D "_DEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x809 /d "_DEBUG"
@@ -141,10 +141,6 @@ SOURCE=..\xmltok\dllmain.c
 # End Source File
 # Begin Source File
 
-SOURCE=.\hashtable.c
-# End Source File
-# Begin Source File
-
 SOURCE=.\xmlparse.c
 # End Source File
 # Begin Source File
@@ -187,10 +183,6 @@ SOURCE=..\xmltok\xmltok.c
 # PROP Default_Filter "h;hpp;hxx;hm;inl;fi;fd"
 # Begin Source File
 
-SOURCE=.\hashtable.h
-# End Source File
-# Begin Source File
-
 SOURCE=.\xmlparse.h
 # End Source File
 # End Group

expat/xmlparse/xmlparse.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #ifndef XmlParse_INCLUDED
@@ -127,6 +112,15 @@ typedef void (*XML_DefaultHandler)(void *userData,
 				   const XML_Char *s,
 				   int len);
 
+/* This is called for the start of the DOCTYPE declaration when the
+name of the DOCTYPE is encountered. */
+typedef void (*XML_StartDoctypeDeclHandler)(void *userData,
+					    const XML_Char *doctypeName);
+
+/* This is called for the start of the DOCTYPE declaration when the
+closing > is encountered, but after processing any external subset. */
+typedef void (*XML_EndDoctypeDeclHandler)(void *userData);
+
 /* This is called for a declaration of an unparsed (NDATA)
 entity.  The base argument is whatever was set by XML_SetBase.
 The entityName, systemId and notationName arguments will never be null.
@@ -149,6 +143,38 @@ typedef void (*XML_NotationDeclHandler)(void *userData,
 					const XML_Char *systemId,
 					const XML_Char *publicId);
 
+typedef void (*XML_ExternalParsedEntityDeclHandler)(void *userData,
+						    const XML_Char *entityName,
+						    const XML_Char *base,
+						    const XML_Char *systemId,
+						    const XML_Char *publicId);
+
+typedef void (*XML_InternalParsedEntityDeclHandler)(void *userData,
+						    const XML_Char *entityName,
+						    const XML_Char *replacementText,
+						    int replacementTextLength);
+
+/* When namespace processing is enabled, these are called once for
+each namespace declaration. The call to the start and end element
+handlers occur between the calls to the start and end namespace
+declaration handlers. For an xmlns attribute, prefix will be null.
+For an xmlns="" attribute, uri will be null. */
+
+typedef void (*XML_StartNamespaceDeclHandler)(void *userData,
+					      const XML_Char *prefix,
+					      const XML_Char *uri);
+
+typedef void (*XML_EndNamespaceDeclHandler)(void *userData,
+					    const XML_Char *prefix);
+
+/* This is called if the document is not standalone (it has an
+external subset or a reference to a parameter entity, but does not
+have standalone="yes"). If this handler returns 0, then processing
+will not continue, and the parser will return a
+XML_ERROR_NOT_STANDALONE error. */
+
+typedef int (*XML_NotStandaloneHandler)(void *userData);
+
 /* This is called for a reference to an external parsed general entity.
 The referenced entity is not automatically parsed.
 The application can parse it immediately or later using
@@ -277,6 +303,11 @@ void XMLPARSEAPI
 XML_SetDefaultHandlerExpand(XML_Parser parser,
 		            XML_DefaultHandler handler);
 
+void XMLPARSEAPI
+XML_SetDoctypeDeclHandler(XML_Parser parser,
+			  XML_StartDoctypeDeclHandler start,
+			  XML_EndDoctypeDeclHandler end);
+
 void XMLPARSEAPI
 XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
 				 XML_UnparsedEntityDeclHandler handler);
@@ -285,6 +316,23 @@ void XMLPARSEAPI
 XML_SetNotationDeclHandler(XML_Parser parser,
 			   XML_NotationDeclHandler handler);
 
+void XMLPARSEAPI
+XML_SetExternalParsedEntityDeclHandler(XML_Parser parser,
+				       XML_ExternalParsedEntityDeclHandler handler);
+
+void XMLPARSEAPI
+XML_SetInternalParsedEntityDeclHandler(XML_Parser parser,
+				       XML_InternalParsedEntityDeclHandler handler);
+
+void XMLPARSEAPI
+XML_SetNamespaceDeclHandler(XML_Parser parser,
+			    XML_StartNamespaceDeclHandler start,
+			    XML_EndNamespaceDeclHandler end);
+
+void XMLPARSEAPI
+XML_SetNotStandaloneHandler(XML_Parser parser,
+			    XML_NotStandaloneHandler handler);
+
 void XMLPARSEAPI
 XML_SetExternalEntityRefHandler(XML_Parser parser,
 				XML_ExternalEntityRefHandler handler);
@@ -313,7 +361,7 @@ XML_SetUserData(XML_Parser parser, void *userData);
 #define XML_GetUserData(parser) (*(void **)(parser))
 
 /* This is equivalent to supplying an encoding argument
-to XML_CreateParser. It must not be called after XML_Parse
+to XML_ParserCreate. It must not be called after XML_Parse
 or XML_ParseBuffer. */
 
 int XMLPARSEAPI
@@ -339,6 +387,20 @@ XML_SetBase(XML_Parser parser, const XML_Char *base);
 const XML_Char XMLPARSEAPI *
 XML_GetBase(XML_Parser parser);
 
+/* Returns the number of the attribute/value pairs passed in last call
+to the XML_StartElementHandler that were specified in the start-tag
+rather than defaulted. Each attribute/value pair counts as 2; thus
+this correspondds to an index into the atts array passed to the
+XML_StartElementHandler. */
+
+int XMLPARSEAPI XML_GetSpecifiedAttributeCount(XML_Parser parser);
+
+/* Returns the index of the ID attribute passed in the last call to
+XML_StartElementHandler, or -1 if there is no ID attribute.  Each
+attribute/value pair counts as 2; thus this correspondds to an index
+into the atts array passed to the XML_StartElementHandler. */
+int XMLPARSEAPI XML_GetIdAttributeIndex(XML_Parser parser);
+
 /* Parses some input. Returns 0 if a fatal error is detected.
 The last call to XML_Parse must have isFinal true;
 len may be zero for this call (or any other). */
@@ -369,6 +431,35 @@ XML_ExternalEntityParserCreate(XML_Parser parser,
 			       const XML_Char *context,
 			       const XML_Char *encoding);
 
+enum XML_ParamEntityParsing {
+  XML_PARAM_ENTITY_PARSING_NEVER,
+  XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE,
+  XML_PARAM_ENTITY_PARSING_ALWAYS
+};
+
+/* Controls parsing of parameter entities (including the external DTD
+subset). If parsing of parameter entities is enabled, then references
+to external parameter entities (including the external DTD subset)
+will be passed to the handler set with
+XML_SetExternalEntityRefHandler.  The context passed will be 0.
+Unlike external general entities, external parameter entities can only
+be parsed synchronously.  If the external parameter entity is to be
+parsed, it must be parsed during the call to the external entity ref
+handler: the complete sequence of XML_ExternalEntityParserCreate,
+XML_Parse/XML_ParseBuffer and XML_ParserFree calls must be made during
+this call.  After XML_ExternalEntityParserCreate has been called to
+create the parser for the external parameter entity (context must be 0
+for this call), it is illegal to make any calls on the old parser
+until XML_ParserFree has been called on the newly created parser.  If
+the library has been compiled without support for parameter entity
+parsing (ie without XML_DTD being defined), then
+XML_SetParamEntityParsing will return 0 if parsing of parameter
+entities is requested; otherwise it will return non-zero. */
+
+int XMLPARSEAPI
+XML_SetParamEntityParsing(XML_Parser parser,
+			  enum XML_ParamEntityParsing parsing);
+
 enum XML_Error {
   XML_ERROR_NONE,
   XML_ERROR_NO_MEMORY,
@@ -391,7 +482,8 @@ enum XML_Error {
   XML_ERROR_UNKNOWN_ENCODING,
   XML_ERROR_INCORRECT_ENCODING,
   XML_ERROR_UNCLOSED_CDATA_SECTION,
-  XML_ERROR_EXTERNAL_ENTITY_HANDLING
+  XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+  XML_ERROR_NOT_STANDALONE
 };
 
 /* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode
@@ -411,6 +503,11 @@ int XMLPARSEAPI XML_GetCurrentLineNumber(XML_Parser parser);
 int XMLPARSEAPI XML_GetCurrentColumnNumber(XML_Parser parser);
 long XMLPARSEAPI XML_GetCurrentByteIndex(XML_Parser parser);
 
+/* Return the number of bytes in the current event.
+Returns 0 if the event is in an internal entity. */
+
+int XMLPARSEAPI XML_GetCurrentByteCount(XML_Parser parser);
+
 /* For backwards compatibility with previous versions. */
 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber
 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber

expat/xmlparse/xmlparse.hpp

@@ -0,0 +1,458 @@
+/*
+The contents of this file are subject to the Mozilla Public License
+Version 1.1 (the "License"); you may not use this file except in
+compliance with the License. You may obtain a copy of the License at
+http://www.mozilla.org/MPL/
+
+Software distributed under the License is distributed on an "AS IS"
+basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
+License for the specific language governing rights and limitations
+under the License.
+
+The Original Code is expat.
+
+The Initial Developer of the Original Code is James Clark.
+Portions created by James Clark are Copyright (C) 1998, 1999
+James Clark. All Rights Reserved.
+
+Contributor(s):
+
+Alternatively, the contents of this file may be used under the terms
+of the GNU General Public License (the "GPL"), in which case the
+provisions of the GPL are applicable instead of those above.  If you
+wish to allow use of your version of this file only under the terms of
+the GPL and not to allow others to use your version of this file under
+the MPL, indicate your decision by deleting the provisions above and
+replace them with the notice and other provisions required by the
+GPL. If you do not delete the provisions above, a recipient may use
+your version of this file under either the MPL or the GPL.
+*/
+
+#ifndef XmlParse_INCLUDED
+#define XmlParse_INCLUDED 1
+
+#ifndef XMLPARSEAPI
+#define XMLPARSEAPI /* as nothing */
+#endif
+
+#ifdef XML_UNICODE_WCHAR_T
+
+/* XML_UNICODE_WCHAR_T will work only if sizeof(wchar_t) == 2 and wchar_t
+uses Unicode. */
+/* Information is UTF-16 encoded as wchar_ts */
+
+#ifndef XML_UNICODE
+#define XML_UNICODE
+#endif
+
+#include <stddef.h>
+typedef wchar_t XML_Char;
+typedef wchar_t XML_LChar;
+
+#else /* not XML_UNICODE_WCHAR_T */
+
+#ifdef XML_UNICODE
+
+/* Information is UTF-16 encoded as unsigned shorts */
+typedef unsigned short XML_Char;
+typedef char XML_LChar;
+
+#else /* not XML_UNICODE */
+
+/* Information is UTF-8 encoded. */
+typedef char XML_Char;
+typedef char XML_LChar;
+
+#endif /* not XML_UNICODE */
+
+#endif /* not XML_UNICODE_WCHAR_T */
+
+class XML_ElementHandler {
+ public:
+  /* atts is array of name/value pairs, terminated by 0; names and
+     values are 0 terminated. */
+  virtual void startElement(const XML_Char *name, const XML_Char **atts) = 0;
+  virtual void endElement(const XML_Char *name) = 0;
+};
+
+class XML_CharacterDataHandler {
+ public:
+  /* s is not 0 terminated. */
+  virtual void characterData(const XML_Char *s, int len) = 0;
+};
+
+class XML_ProcessingInstructionHandler {
+ public:
+  /* target and data are 0 terminated */
+  virtual void processingInstruction(const XML_Char *target, const XML_Char *data) = 0;
+};
+
+/* data is 0 terminated */
+class XML_CommentHandler {
+  public:
+  virtual void comment(const XML_Char *data) = 0;
+};
+
+class XML_CdataSectionHandler {
+ public:
+  virtual void startCdataSection() = 0;
+  virtual void endCdataSection() = 0;
+};
+
+class XML_DefaultHandler {
+ public:
+  /* This is called for any characters in the XML document for which
+     there is no applicable handler.  This includes both characters
+     that are part of markup which is of a kind that is not reported
+     (comments, markup declarations), or characters that are part of a
+     construct which could be reported but for which no handler has
+     been supplied. The characters are passed exactly as they were in
+     the XML document except that they will be encoded in UTF-8.  Line
+     boundaries are not normalized.  Note that a byte order mark
+     character is not passed to the default handler.  There are no
+     guarantees about how characters are divided between calls to the
+     default handler: for example, a comment might be split between
+     multiple calls. */
+  virtual void doDefault(const XML_Char *s, int len) = 0;
+};
+
+class XML_DoctypeDeclHandler {
+ public:
+  /* This is called for the start of the DOCTYPE declaration when the
+     name of the DOCTYPE is encountered. */
+  virtual void startDoctypeDecl(const XML_Char *doctypeName) = 0;
+  /* This is called for the start of the DOCTYPE declaration when the
+     closing > is encountered, but after processing any external subset. */
+  virtual void endDoctypeDecl() = 0;
+};
+
+class XML_UnparsedEntityDeclHandler {
+ public:
+  /* This is called for a declaration of an unparsed (NDATA)
+     entity.  The base argument is whatever was set by XML_SetBase.
+     The entityName, systemId and notationName arguments will never be null.
+     The other arguments may be. */
+  virtual void unparsedEntityDecl(const XML_Char *entityName,
+				  const XML_Char *base,
+				  const XML_Char *systemId,
+				  const XML_Char *publicId,
+				  const XML_Char *notationName) = 0;
+};
+
+class XML_NotationDeclHandler {
+ public:
+  /* This is called for a declaration of notation.  The base argument
+     is whatever was set by XML_SetBase.  The notationName will never
+     be null.  The other arguments can be. */
+  virtual void notationDecl(const XML_Char *notationName,
+			    const XML_Char *base,
+			    const XML_Char *systemId,
+			    const XML_Char *publicId) = 0;
+};
+
+class XML_NamespaceDeclHandler {
+ public:
+  /* When namespace processing is enabled, these are called once for
+     each namespace declaration. The call to the start and end element
+     handlers occur between the calls to the start and end namespace
+     declaration handlers. For an xmlns attribute, prefix will be
+     null.  For an xmlns="" attribute, uri will be null. */
+  
+  virtual void startNamespaceDecl(const XML_Char *prefix,
+				  const XML_Char *uri) = 0;
+
+  virtual void endNamespaceDecl(const XML_Char *prefix) = 0;
+};
+
+class XML_NotStandaloneHandler {
+ public:
+  /* This is called if the document is not standalone (it has an
+     external subset or a reference to a parameter entity, but does
+     not have standalone="yes"). If this handler returns 0, then
+     processing will not continue, and the parser will return a
+     ERROR_NOT_STANDALONE error. */
+  virtual int notStandalone() = 0;
+};
+
+class XML_Parser;
+
+class XML_ExternalEntityRefHandler {
+ public:
+  /* This is called for a reference to an external parsed general
+     entity.  The referenced entity is not automatically parsed.  The
+     application can parse it immediately or later using
+     externalEntityParserCreate.  The parser argument is the parser
+     parsing the entity containing the reference; it can be passed as
+     the parser argument to externalEntityParserCreate.  The systemId
+     argument is the system identifier as specified in the entity
+     declaration; it will not be null.  The base argument is the
+     system identifier that should be used as the base for resolving
+     systemId if systemId was relative; this is set by setBase; it may
+     be null.  The publicId argument is the public identifier as
+     specified in the entity declaration, or null if none was
+     specified; the whitespace in the public identifier will have been
+     normalized as required by the XML spec.  The context argument
+     specifies the parsing context in the format expected by the
+     context argument to externalEntityParserCreate; context is valid
+     only until the handler returns, so if the referenced entity is to
+     be parsed later, it must be copied.  The handler should return 0
+     if processing should not continue because of a fatal error in the
+     handling of the external entity.  In this case the calling parser
+     will return an ERROR_EXTERNAL_ENTITY_HANDLING error.  Note that
+     unlike other handlers the first argument is the parser, not
+     userData. */
+
+  virtual int externalEntityRef(XML_Parser *parser,
+				const XML_Char *context,
+				const XML_Char *base,
+				const XML_Char *systemId,
+				const XML_Char *publicId) = 0;
+};
+  
+/* This object is returned by the XML_UnknownEncodingHandler
+to provide information to the parser about encodings that are unknown
+to the parser.
+The map[b] member gives information about byte sequences
+whose first byte is b.
+If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar value c.
+If map[b] is -1, then the byte sequence is malformed.
+If map[b] is -n, where n >= 2, then b is the first byte of an n-byte
+sequence that encodes a single Unicode scalar value.
+The data member will be passed as the first argument to the convert function.
+The convert function is used to convert multibyte sequences;
+s will point to a n-byte sequence where map[(unsigned char)*s] == -n.
+The convert function must return the Unicode scalar value
+represented by this byte sequence or -1 if the byte sequence is malformed.
+The convert function may be null if the encoding is a single-byte encoding,
+that is if map[b] >= -1 for all bytes b.
+When the parser is finished with the encoding, then if release is not null,
+it will call release passing it the data member;
+once release has been called, the convert function will not be called again.
+
+Expat places certain restrictions on the encodings that are supported
+using this mechanism.
+
+1. Every ASCII character that can appear in a well-formed XML document,
+other than the characters
+
+  $@\^`{}~
+
+must be represented by a single byte, and that byte must be the
+same byte that represents that character in ASCII.
+
+2. No character may require more than 4 bytes to encode.
+
+3. All characters encoded must have Unicode scalar values <= 0xFFFF,
+(ie characters that would be encoded by surrogates in UTF-16
+are  not allowed).  Note that this restriction doesn't apply to
+the built-in support for UTF-8 and UTF-16.
+
+4. No Unicode character may be encoded by more than one distinct sequence
+of bytes. */
+
+class XMLPARSEAPI XML_Encoding {
+public:
+  int map[256];
+  virtual int convert(const char *s);
+  virtual void release();
+};
+
+class XML_UnknownEncodingHandler {
+public:
+  /* This is called for an encoding that is unknown to the parser.
+     The encodingHandlerData argument is that which was passed as the
+     second argument to XML_SetUnknownEncodingHandler.  The name
+     argument gives the name of the encoding as specified in the
+     encoding declaration.  If the callback can provide information
+     about the encoding, it must fill in the XML_Encoding structure,
+     and return 1.  Otherwise it must return 0.  If info does not
+     describe a suitable encoding, then the parser will return an
+     XML_UNKNOWN_ENCODING error. */
+  virtual XML_Encoding *unknownEncoding(const XML_Char *name) = 0;
+};
+
+class XMLPARSEAPI XML_Parser {
+ public:
+  /* Constructs a new parser; encoding is the encoding specified by
+     the external protocol or null if there is none specified. */
+  static XML_Parser *parserCreate(const XML_Char *encoding = 0);
+
+  /* Constructs a new parser and namespace processor.  Element type
+     names and attribute names that belong to a namespace will be
+     expanded; unprefixed attribute names are never expanded;
+     unprefixed element type names are expanded only if there is a
+     default namespace. The expanded name is the concatenation of the
+     namespace URI, the namespace separator character, and the local
+     part of the name.  If the namespace separator is '\0' then the
+     namespace URI and the local part will be concatenated without any
+     separator.  When a namespace is not declared, the name and prefix
+     will be passed through without expansion. */
+
+  static XML_Parser *parserCreateNS(const XML_Char *encoding,
+				    XML_Char namespaceSeparator);
+
+  virtual void release() = 0;
+  virtual void setElementHandler(XML_ElementHandler *handler) = 0;
+  virtual void setCharacterDataHandler(XML_CharacterDataHandler *handler) = 0;
+  virtual void setProcessingInstructionHandler(XML_ProcessingInstructionHandler *handler) = 0;
+  virtual void setCommentHandler(XML_CommentHandler *handler) = 0;
+  virtual void setCdataSectionHandler(XML_CdataSectionHandler *handler) = 0;
+
+  /* This sets the default handler and also inhibits expansion of
+     internal entities.  The entity reference will be passed to the
+     default handler. */
+
+  virtual void setDefaultHandler(XML_DefaultHandler *handler) = 0;
+
+  /* This sets the default handler but does not inhibit expansion of
+     internal entities.  The entity reference will not be passed to
+     the default handler. */
+
+  virtual void setDefaultHandlerExpand(XML_DefaultHandler *handler) = 0;
+
+  virtual void setDoctypeDeclHandler(XML_DoctypeDeclHandler *handler) = 0;
+  virtual void setUnparsedEntityDeclHandler(XML_UnparsedEntityDeclHandler *handler) = 0;
+  virtual void setNotationDeclHandler(XML_NotationDeclHandler *handler) = 0;
+  virtual void setNamespaceDeclHandler(XML_NamespaceDeclHandler *handler) = 0;
+  virtual void setNotStandaloneHandler(XML_NotStandaloneHandler *handler) = 0;
+  virtual void setExternalEntityRefHandler(XML_ExternalEntityRefHandler *handler) = 0;
+  virtual void setUnknownEncodingHandler(XML_UnknownEncodingHandler *handler) = 0;
+
+  /* This can be called within a handler for a start element, end
+     element, processing instruction or character data.  It causes the
+     corresponding markup to be passed to the default handler. */
+  virtual void defaultCurrent() = 0;
+
+  /* This is equivalent to supplying an encoding argument
+     to XML_ParserCreate. It must not be called after XML_Parse
+     or XML_ParseBuffer. */
+  virtual int setEncoding(const XML_Char *encoding) = 0;
+
+  /* Sets the base to be used for resolving relative URIs in system
+     identifiers in declarations.  Resolving relative identifiers is
+     left to the application: this value will be passed through as the
+     base argument to the XML_ExternalEntityRefHandler,
+     XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The
+     base argument will be copied.  Returns zero if out of memory,
+     non-zero otherwise. */
+
+  virtual int setBase(const XML_Char *base) = 0;
+
+  virtual const XML_Char *getBase() = 0;
+
+  /* Returns the number of the attributes passed in last call to the
+     XML_StartElementHandler that were specified in the start-tag rather
+     than defaulted. */
+  virtual int getSpecifiedAttributeCount() = 0;
+
+  /* Parses some input. Returns 0 if a fatal error is detected.
+     The last call to XML_Parse must have isFinal true;
+     len may be zero for this call (or any other). */
+  virtual int parse(const char *s, int len, int isFinal) = 0;
+
+  virtual char *getBuffer(int len) = 0;
+
+  virtual int parseBuffer(int len, int isFinal) = 0;
+
+  /* Creates an XML_Parser object that can parse an external general
+     entity; context is a '\0'-terminated string specifying the parse
+     context; encoding is a '\0'-terminated string giving the name of
+     the externally specified encoding, or null if there is no
+     externally specified encoding.  The context string consists of a
+     sequence of tokens separated by formfeeds (\f); a token
+     consisting of a name specifies that the general entity of the
+     name is open; a token of the form prefix=uri specifies the
+     namespace for a particular prefix; a token of the form =uri
+     specifies the default namespace.  This can be called at any point
+     after the first call to an ExternalEntityRefHandler so longer as
+     the parser has not yet been freed.  The new parser is completely
+     independent and may safely be used in a separate thread.  The
+     handlers and userData are initialized from the parser argument.
+     Returns 0 if out of memory.  Otherwise returns a new XML_Parser
+     object. */
+
+  virtual XML_Parser *externalEntityParserCreate(const XML_Char *context,
+						 const XML_Char *encoding) = 0;
+
+  enum ParamEntityParsing {
+    PARAM_ENTITY_PARSING_NEVER,
+    PARAM_ENTITY_PARSING_UNLESS_STANDALONE,
+    PARAM_ENTITY_PARSING_ALWAYS
+  };
+
+  /* Controls parsing of parameter entities (including the external
+     DTD subset). If parsing of parameter entities is enabled, then
+     references to external parameter entities (including the external
+     DTD subset) will be passed to the handler set with
+     XML_SetExternalEntityRefHandler.  The context passed will be 0.
+     Unlike external general entities, external parameter entities can
+     only be parsed synchronously.  If the external parameter entity
+     is to be parsed, it must be parsed during the call to the
+     external entity ref handler: the complete sequence of
+     XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and
+     XML_ParserFree calls must be made during this call.  After
+     XML_ExternalEntityParserCreate has been called to create the
+     parser for the external parameter entity (context must be 0 for
+     this call), it is illegal to make any calls on the old parser
+     until XML_ParserFree has been called on the newly created parser.
+     If the library has been compiled without support for parameter
+     entity parsing (ie without XML_DTD being defined), then
+     XML_SetParamEntityParsing will return 0 if parsing of parameter
+     entities is requested; otherwise it will return non-zero. */
+
+  virtual int setParamEntityParsing(ParamEntityParsing parsing) = 0;
+
+  enum Error {
+    ERROR_NONE,
+    ERROR_NO_MEMORY,
+    ERROR_SYNTAX,
+    ERROR_NO_ELEMENTS,
+    ERROR_INVALID_TOKEN,
+    ERROR_UNCLOSED_TOKEN,
+    ERROR_PARTIAL_CHAR,
+    ERROR_TAG_MISMATCH,
+    ERROR_DUPLICATE_ATTRIBUTE,
+    ERROR_JUNK_AFTER_DOC_ELEMENT,
+    ERROR_PARAM_ENTITY_REF,
+    ERROR_UNDEFINED_ENTITY,
+    ERROR_RECURSIVE_ENTITY_REF,
+    ERROR_ASYNC_ENTITY,
+    ERROR_BAD_CHAR_REF,
+    ERROR_BINARY_ENTITY_REF,
+    ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
+    ERROR_MISPLACED_XML_PI,
+    ERROR_UNKNOWN_ENCODING,
+    ERROR_INCORRECT_ENCODING,
+    ERROR_UNCLOSED_CDATA_SECTION,
+    ERROR_EXTERNAL_ENTITY_HANDLING,
+    ERROR_NOT_STANDALONE
+  };
+
+  /* If parse or XML_parseBuffer have returned 0, then XML_GetErrorCode
+     returns information about the error. */
+  
+  virtual Error getErrorCode() = 0;
+
+  /* These functions return information about the current parse
+     location.  They may be called when XML_Parse or XML_ParseBuffer
+     return 0; in this case the location is the location of the
+     character at which the error was detected.  They may also be
+     called from any other callback called to report some parse event;
+     in this the location is the location of the first of the sequence
+     of characters that generated the event. */
+
+  virtual int getCurrentLineNumber() = 0;
+  virtual int getCurrentColumnNumber() = 0;
+  virtual long getCurrentByteIndex() = 0;
+
+  /* Return the number of bytes in the current event.
+     Returns 0 if the event is in an internal entity. */
+  virtual int getCurrentByteCount() = 0;
+
+  /* Returns a string describing the error. */
+  static const XML_LChar *errorString(int code);
+protected:
+  ~XML_Parser() { }
+};
+
+#endif /* not XmlParse_INCLUDED */

expat/xmltok/.gitignore

@@ -0,0 +1,3 @@
+nametab.h
+Release
+Debug

expat/xmltok/ascii.h

@@ -0,0 +1,86 @@
+/*
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
+*/
+
+#define ASCII_A 0x41
+#define ASCII_B 0x42
+#define ASCII_C 0x43
+#define ASCII_D 0x44
+#define ASCII_E 0x45
+#define ASCII_F 0x46
+#define ASCII_G 0x47
+#define ASCII_H 0x48
+#define ASCII_I 0x49
+#define ASCII_J 0x4A
+#define ASCII_K 0x4B
+#define ASCII_L 0x4C
+#define ASCII_M 0x4D
+#define ASCII_N 0x4E
+#define ASCII_O 0x4F
+#define ASCII_P 0x50
+#define ASCII_Q 0x51
+#define ASCII_R 0x52
+#define ASCII_S 0x53
+#define ASCII_T 0x54
+#define ASCII_U 0x55
+#define ASCII_V 0x56
+#define ASCII_W 0x57
+#define ASCII_X 0x58
+#define ASCII_Y 0x59
+#define ASCII_Z 0x5A
+
+#define ASCII_a 0x61
+#define ASCII_b 0x62
+#define ASCII_c 0x63
+#define ASCII_d 0x64
+#define ASCII_e 0x65
+#define ASCII_f 0x66
+#define ASCII_g 0x67
+#define ASCII_h 0x68
+#define ASCII_i 0x69
+#define ASCII_j 0x6A
+#define ASCII_k 0x6B
+#define ASCII_l 0x6C
+#define ASCII_m 0x6D
+#define ASCII_n 0x6E
+#define ASCII_o 0x6F
+#define ASCII_p 0x70
+#define ASCII_q 0x71
+#define ASCII_r 0x72
+#define ASCII_s 0x73
+#define ASCII_t 0x74
+#define ASCII_u 0x75
+#define ASCII_v 0x76
+#define ASCII_w 0x77
+#define ASCII_x 0x78
+#define ASCII_y 0x79
+#define ASCII_z 0x7A
+
+#define ASCII_0 0x30
+#define ASCII_1 0x31
+#define ASCII_2 0x32
+#define ASCII_3 0x33
+#define ASCII_4 0x34
+#define ASCII_5 0x35
+#define ASCII_6 0x36
+#define ASCII_7 0x37
+#define ASCII_8 0x38
+#define ASCII_9 0x39
+
+#define ASCII_TAB 0x09
+#define ASCII_SPACE 0x20 
+#define ASCII_EXCL 0x21
+#define ASCII_QUOT 0x22
+#define ASCII_AMP 0x26
+#define ASCII_APOS 0x27
+#define ASCII_MINUS 0x2D
+#define ASCII_PERIOD 0x2E
+#define ASCII_COLON 0x3A
+#define ASCII_SEMI 0x3B
+#define ASCII_LT 0x3C
+#define ASCII_EQUALS 0x3D
+#define ASCII_GT 0x3E
+#define ASCII_LSQB 0x5B
+#define ASCII_RSQB 0x5D
+#define ASCII_UNDERSCORE 0x5F

expat/xmltok/asciitab.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 /* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,

expat/xmltok/dllmain.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #define STRICT 1

expat/xmltok/iasciitab.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 /* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */

expat/xmltok/latin1tab.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 /* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,

expat/xmltok/nametab.h

@@ -1,152 +0,0 @@
-static const unsigned namingBitmap[] = {
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0x00000000, 0x04000000, 0x87FFFFFE, 0x07FFFFFE,
-0x00000000, 0x04200400, 0xFF7FFFFF, 0xFF7FFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC3FFFFF,
-0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
-0xFFFFFFFF, 0xF9FF01FF, 0x00000003, 0x0000001F,
-0x00000000, 0x00000000, 0x00000000, 0x04000000,
-0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
-0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
-0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
-0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
-0x000000FF, 0x00000000, 0xFFFF0000, 0x000707FF,
-0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000,
-0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060,
-0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003,
-0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003,
-0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000,
-0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001,
-0xFFF99FE0, 0x23CDFDFF, 0xB0000000, 0x00000003,
-0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000,
-0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003,
-0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003,
-0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000,
-0xFEF02596, 0x200D6CAE, 0x3000001F, 0x00000000,
-0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0x83FFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0xFFFFFF07, 0xFFFFFFFF, 0x03FFFFFF,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF,
-0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF,
-0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF,
-0x00000000, 0x00000000, 0x00000000, 0x80000000,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0x3F2FFC84, 0x01FBFD50, 0x00000000, 0xFFFFFFFF,
-0x00000007, 0x00000000, 0x00000000, 0x00000000,
-0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF,
-0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF,
-0xFFFFFFE0, 0xFFFE1FFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0x00007FFF, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000,
-0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
-0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000,
-0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE,
-0x00000000, 0x04A00400, 0xFF7FFFFF, 0xFF7FFFFF,
-0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
-0xFFFFFFFF, 0xF9FF01FF, 0x00030003, 0x0000001F,
-0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x04000003,
-0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
-0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
-0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
-0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
-0xFFFE00FF, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF,
-0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF,
-0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF,
-0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF,
-0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF,
-0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0,
-0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1,
-0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3,
-0xD63DC7EC, 0xC3BFC718, 0x00803DC7, 0x0000FF80,
-0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3,
-0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3,
-0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3,
-0x00000000, 0x00000000, 0x00000000, 0x00000000,
-0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000,
-0xFEF02596, 0x3BFF6CAE, 0x33FF3F5F, 0x00000000,
-0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF,
-0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000,
-0x0000F000, 0x00007C00, 0x00000000, 0x8000FC00,
-0x00000000, 0x00000000, 0x1FFF0000, 0x00000002,
-0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF,
-0x7E1FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF,
-};
-static const unsigned char nmstrtPages[] = {
-0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00,
-0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
-0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13,
-0x14, 0x15, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x16, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x19,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
-static const unsigned char namePages[] = {
-0x1A, 0x03, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, 0x00,
-0x00, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26,
-0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13,
-0x27, 0x15, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x28, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
-0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x19,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};

expat/xmltok/utf8tab.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 

expat/xmltok/wxmltok.c

@@ -1,2 +0,0 @@
-#define UNICODE 1
-#include "xmltok.c"

expat/xmltok/xmldef.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <string.h>
@@ -41,13 +26,27 @@ Contributor(s):
 /* This file can be used for any definitions needed in
 particular environments. */
 
-#ifdef MOZILLA
+/* Mozilla specific defines */
+
+#ifdef MOZILLA_CLIENT
 
 #include "nspr.h"
-#define malloc(x) PR_Malloc(x)
-#define realloc(x, y) PR_Realloc((x), (y))
+#define malloc(x) PR_Malloc((size_t)(x))
+#define realloc(x, y) PR_Realloc((x), (size_t)(y))
 #define calloc(x, y) PR_Calloc((x),(y))
 #define free(x) PR_Free(x)
+#if PR_BYTES_PER_INT != 4
 #define int int32
+#endif
 
-#endif /* MOZILLA */
+/* Enable Unicode string processing in expat. */
+#ifndef XML_UNICODE
+#define XML_UNICODE
+#endif
+
+/* Enable external parameter entity parsing in expat */
+#ifndef XML_DTD
+#define XML_DTD 1
+#endif
+
+#endif /* MOZILLA_CLIENT */

expat/xmltok/xmlrole.c

@@ -1,25 +1,11 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include "xmldef.h"
 #include "xmlrole.h"
+#include "ascii.h"
 
 /* Doesn't check:
 
@@ -28,11 +14,44 @@ Contributor(s):
 
 */
 
+static const char KW_ANY[] = { ASCII_A, ASCII_N, ASCII_Y, '\0' };
+static const char KW_ATTLIST[] = { ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0' };
+static const char KW_CDATA[] = { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' };
+static const char KW_DOCTYPE[] = { ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0' };
+static const char KW_ELEMENT[] = { ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0' };
+static const char KW_EMPTY[] = { ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0' };
+static const char KW_ENTITIES[] = { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, '\0' };
+static const char KW_ENTITY[] = { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' };
+static const char KW_FIXED[] = { ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0' };
+static const char KW_ID[] = { ASCII_I, ASCII_D, '\0' };
+static const char KW_IDREF[] = { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' };
+static const char KW_IDREFS[] = { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' };
+static const char KW_IGNORE[] = { ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' };
+static const char KW_IMPLIED[] = { ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' };
+static const char KW_INCLUDE[] = { ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' };
+static const char KW_NDATA[] = { ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' };
+static const char KW_NMTOKEN[] = { ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' };
+static const char KW_NMTOKENS[] = { ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, '\0' };
+static const char KW_NOTATION[] = { ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, '\0' };
+static const char KW_PCDATA[] = { ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' };
+static const char KW_PUBLIC[] = { ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0' };
+static const char KW_REQUIRED[] = { ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, ASCII_R, ASCII_E, ASCII_D, '\0' };
+static const char KW_SYSTEM[] = { ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0' };
+
 #ifndef MIN_BYTES_PER_CHAR
 #define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar)
 #endif
 
-typedef int PROLOG_HANDLER(struct prolog_state *state,
+#ifdef XML_DTD
+#define setTopLevel(state) \
+  ((state)->handler = ((state)->documentEntity \
+                       ? internalSubset \
+                       : externalSubset1))
+#else /* not XML_DTD */
+#define setTopLevel(state) ((state)->handler = internalSubset)
+#endif /* not XML_DTD */
+
+typedef int PROLOG_HANDLER(PROLOG_STATE *state,
 			   int tok,
 			   const char *ptr,
 			   const char *end,
@@ -49,11 +68,15 @@ static PROLOG_HANDLER
   attlist7, attlist8, attlist9,
   element0, element1, element2, element3, element4, element5, element6,
   element7,
+#ifdef XML_DTD
+  externalSubset0, externalSubset1,
+  condSect0, condSect1, condSect2,
+#endif /* XML_DTD */
   declClose,
   error;
 
 static
-int syntaxError(PROLOG_STATE *);
+int common(PROLOG_STATE *state, int tok);
 
 static
 int prolog0(PROLOG_STATE *state,
@@ -79,7 +102,8 @@ int prolog0(PROLOG_STATE *state,
   case XML_TOK_DECL_OPEN:
     if (!XmlNameMatchesAscii(enc,
 			     ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			     "DOCTYPE"))
+			     end,
+			     KW_DOCTYPE))
       break;
     state->handler = doctype0;
     return XML_ROLE_NONE;
@@ -87,7 +111,7 @@ int prolog0(PROLOG_STATE *state,
     state->handler = error;
     return XML_ROLE_INSTANCE_START;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -107,7 +131,8 @@ int prolog1(PROLOG_STATE *state,
   case XML_TOK_DECL_OPEN:
     if (!XmlNameMatchesAscii(enc,
 			     ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			     "DOCTYPE"))
+			     end,
+			     KW_DOCTYPE))
       break;
     state->handler = doctype0;
     return XML_ROLE_NONE;
@@ -115,7 +140,7 @@ int prolog1(PROLOG_STATE *state,
     state->handler = error;
     return XML_ROLE_INSTANCE_START;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -135,7 +160,7 @@ int prolog2(PROLOG_STATE *state,
     state->handler = error;
     return XML_ROLE_INSTANCE_START;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -153,7 +178,7 @@ int doctype0(PROLOG_STATE *state,
     state->handler = doctype1;
     return XML_ROLE_DOCTYPE_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -173,17 +198,17 @@ int doctype1(PROLOG_STATE *state,
     state->handler = prolog2;
     return XML_ROLE_DOCTYPE_CLOSE;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "SYSTEM")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) {
       state->handler = doctype3;
       return XML_ROLE_NONE;
     }
-    if (XmlNameMatchesAscii(enc, ptr, "PUBLIC")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) {
       state->handler = doctype2;
       return XML_ROLE_NONE;
     }
     break;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -200,7 +225,7 @@ int doctype2(PROLOG_STATE *state,
     state->handler = doctype3;
     return XML_ROLE_DOCTYPE_PUBLIC_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -217,7 +242,7 @@ int doctype3(PROLOG_STATE *state,
     state->handler = doctype4;
     return XML_ROLE_DOCTYPE_SYSTEM_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -237,7 +262,7 @@ int doctype4(PROLOG_STATE *state,
     state->handler = prolog2;
     return XML_ROLE_DOCTYPE_CLOSE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -254,7 +279,7 @@ int doctype5(PROLOG_STATE *state,
     state->handler = prolog2;
     return XML_ROLE_DOCTYPE_CLOSE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -270,25 +295,29 @@ int internalSubset(PROLOG_STATE *state,
   case XML_TOK_DECL_OPEN:
     if (XmlNameMatchesAscii(enc,
 			    ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			    "ENTITY")) {
+			    end,
+			    KW_ENTITY)) {
       state->handler = entity0;
       return XML_ROLE_NONE;
     }
     if (XmlNameMatchesAscii(enc,
 			    ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			    "ATTLIST")) {
+			    end,
+			    KW_ATTLIST)) {
       state->handler = attlist0;
       return XML_ROLE_NONE;
     }
     if (XmlNameMatchesAscii(enc,
 			    ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			    "ELEMENT")) {
+			    end,
+			    KW_ELEMENT)) {
       state->handler = element0;
       return XML_ROLE_NONE;
     }
     if (XmlNameMatchesAscii(enc,
 			    ptr + 2 * MIN_BYTES_PER_CHAR(enc),
-			    "NOTATION")) {
+			    end,
+			    KW_NOTATION)) {
       state->handler = notation0;
       return XML_ROLE_NONE;
     }
@@ -302,9 +331,56 @@ int internalSubset(PROLOG_STATE *state,
     state->handler = doctype5;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
+#ifdef XML_DTD
+
+static
+int externalSubset0(PROLOG_STATE *state,
+		    int tok,
+		    const char *ptr,
+		    const char *end,
+		    const ENCODING *enc)
+{
+  state->handler = externalSubset1;
+  if (tok == XML_TOK_XML_DECL)
+    return XML_ROLE_TEXT_DECL;
+  return externalSubset1(state, tok, ptr, end, enc);
+}
+
+static
+int externalSubset1(PROLOG_STATE *state,
+		    int tok,
+		    const char *ptr,
+		    const char *end,
+		    const ENCODING *enc)
+{
+  switch (tok) {
+  case XML_TOK_COND_SECT_OPEN:
+    state->handler = condSect0;
+    return XML_ROLE_NONE;
+  case XML_TOK_COND_SECT_CLOSE:
+    if (state->includeLevel == 0)
+      break;
+    state->includeLevel -= 1;
+    return XML_ROLE_NONE;
+  case XML_TOK_PROLOG_S:
+    return XML_ROLE_NONE;
+  case XML_TOK_CLOSE_BRACKET:
+    break;
+  case XML_TOK_NONE:
+    if (state->includeLevel)
+      break;
+    return XML_ROLE_NONE;
+  default:
+    return internalSubset(state, tok, ptr, end, enc);
+  }
+  return common(state, tok);
+}
+
+#endif /* XML_DTD */
+
 static
 int entity0(PROLOG_STATE *state,
 	    int tok,
@@ -322,7 +398,7 @@ int entity0(PROLOG_STATE *state,
     state->handler = entity2;
     return XML_ROLE_GENERAL_ENTITY_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -339,7 +415,7 @@ int entity1(PROLOG_STATE *state,
     state->handler = entity7;
     return XML_ROLE_PARAM_ENTITY_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -353,11 +429,11 @@ int entity2(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "SYSTEM")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) {
       state->handler = entity4;
       return XML_ROLE_NONE;
     }
-    if (XmlNameMatchesAscii(enc, ptr, "PUBLIC")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) {
       state->handler = entity3;
       return XML_ROLE_NONE;
     }
@@ -366,7 +442,7 @@ int entity2(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_ENTITY_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -383,7 +459,7 @@ int entity3(PROLOG_STATE *state,
     state->handler = entity4;
     return XML_ROLE_ENTITY_PUBLIC_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 
@@ -401,7 +477,7 @@ int entity4(PROLOG_STATE *state,
     state->handler = entity5;
     return XML_ROLE_ENTITY_SYSTEM_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -415,16 +491,16 @@ int entity5(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_DECL_CLOSE:
-    state->handler = internalSubset;
-    return XML_ROLE_NONE;
+    setTopLevel(state);
+    return XML_ROLE_EXTERNAL_GENERAL_ENTITY_NO_NOTATION;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "NDATA")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_NDATA)) {
       state->handler = entity6;
       return XML_ROLE_NONE;
     }
     break;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -441,7 +517,7 @@ int entity6(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_ENTITY_NOTATION_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -455,11 +531,11 @@ int entity7(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "SYSTEM")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) {
       state->handler = entity9;
       return XML_ROLE_NONE;
     }
-    if (XmlNameMatchesAscii(enc, ptr, "PUBLIC")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) {
       state->handler = entity8;
       return XML_ROLE_NONE;
     }
@@ -468,7 +544,7 @@ int entity7(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_ENTITY_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -485,7 +561,7 @@ int entity8(PROLOG_STATE *state,
     state->handler = entity9;
     return XML_ROLE_ENTITY_PUBLIC_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -502,7 +578,7 @@ int entity9(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_ENTITY_SYSTEM_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -519,7 +595,7 @@ int notation0(PROLOG_STATE *state,
     state->handler = notation1;
     return XML_ROLE_NOTATION_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -533,17 +609,17 @@ int notation1(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "SYSTEM")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) {
       state->handler = notation3;
       return XML_ROLE_NONE;
     }
-    if (XmlNameMatchesAscii(enc, ptr, "PUBLIC")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) {
       state->handler = notation2;
       return XML_ROLE_NONE;
     }
     break;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -560,7 +636,7 @@ int notation2(PROLOG_STATE *state,
     state->handler = notation4;
     return XML_ROLE_NOTATION_PUBLIC_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -577,7 +653,7 @@ int notation3(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_NOTATION_SYSTEM_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -594,10 +670,10 @@ int notation4(PROLOG_STATE *state,
     state->handler = declClose;
     return XML_ROLE_NOTATION_SYSTEM_ID;
   case XML_TOK_DECL_CLOSE:
-    state->handler = internalSubset;
+    setTopLevel(state);
     return XML_ROLE_NOTATION_NO_SYSTEM_ID;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -615,7 +691,7 @@ int attlist0(PROLOG_STATE *state,
     state->handler = attlist1;
     return XML_ROLE_ATTLIST_ELEMENT_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -629,14 +705,14 @@ int attlist1(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_DECL_CLOSE:
-    state->handler = internalSubset;
+    setTopLevel(state);
     return XML_ROLE_NONE;
   case XML_TOK_NAME:
   case XML_TOK_PREFIXED_NAME:
     state->handler = attlist2;
     return XML_ROLE_ATTRIBUTE_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -652,23 +728,23 @@ int attlist2(PROLOG_STATE *state,
   case XML_TOK_NAME:
     {
       static const char *types[] = {
-	"CDATA",
-        "ID",
-        "IDREF",
-        "IDREFS",
-        "ENTITY",
-        "ENTITIES",
-        "NMTOKEN",
-        "NMTOKENS",
+	KW_CDATA,
+        KW_ID,
+        KW_IDREF,
+        KW_IDREFS,
+        KW_ENTITY,
+        KW_ENTITIES,
+        KW_NMTOKEN,
+        KW_NMTOKENS,
       };
       int i;
       for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++)
-	if (XmlNameMatchesAscii(enc, ptr, types[i])) {
+	if (XmlNameMatchesAscii(enc, ptr, end, types[i])) {
 	  state->handler = attlist8;
 	  return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i;
 	}
     }
-    if (XmlNameMatchesAscii(enc, ptr, "NOTATION")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) {
       state->handler = attlist5;
       return XML_ROLE_NONE;
     }
@@ -677,7 +753,7 @@ int attlist2(PROLOG_STATE *state,
     state->handler = attlist3;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -696,7 +772,7 @@ int attlist3(PROLOG_STATE *state,
     state->handler = attlist4;
     return XML_ROLE_ATTRIBUTE_ENUM_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -716,7 +792,7 @@ int attlist4(PROLOG_STATE *state,
     state->handler = attlist3;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -733,7 +809,7 @@ int attlist5(PROLOG_STATE *state,
     state->handler = attlist6;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 
@@ -751,7 +827,7 @@ int attlist6(PROLOG_STATE *state,
     state->handler = attlist7;
     return XML_ROLE_ATTRIBUTE_NOTATION_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -771,7 +847,7 @@ int attlist7(PROLOG_STATE *state,
     state->handler = attlist6;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 /* default value */
@@ -788,19 +864,22 @@ int attlist8(PROLOG_STATE *state,
   case XML_TOK_POUND_NAME:
     if (XmlNameMatchesAscii(enc,
 			    ptr + MIN_BYTES_PER_CHAR(enc),
-			    "IMPLIED")) {
+			    end,
+			    KW_IMPLIED)) {
       state->handler = attlist1;
       return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE;
     }
     if (XmlNameMatchesAscii(enc,
 			    ptr + MIN_BYTES_PER_CHAR(enc),
-			    "REQUIRED")) {
+			    end,
+			    KW_REQUIRED)) {
       state->handler = attlist1;
       return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE;
     }
     if (XmlNameMatchesAscii(enc,
 			    ptr + MIN_BYTES_PER_CHAR(enc),
-			    "FIXED")) {
+			    end,
+			    KW_FIXED)) {
       state->handler = attlist9;
       return XML_ROLE_NONE;
     }
@@ -809,7 +888,7 @@ int attlist8(PROLOG_STATE *state,
     state->handler = attlist1;
     return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -826,7 +905,7 @@ int attlist9(PROLOG_STATE *state,
     state->handler = attlist1;
     return XML_ROLE_FIXED_ATTRIBUTE_VALUE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -844,7 +923,7 @@ int element0(PROLOG_STATE *state,
     state->handler = element1;
     return XML_ROLE_ELEMENT_NAME;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -858,11 +937,11 @@ int element1(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_NAME:
-    if (XmlNameMatchesAscii(enc, ptr, "EMPTY")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_EMPTY)) {
       state->handler = declClose;
       return XML_ROLE_CONTENT_EMPTY;
     }
-    if (XmlNameMatchesAscii(enc, ptr, "ANY")) {
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_ANY)) {
       state->handler = declClose;
       return XML_ROLE_CONTENT_ANY;
     }
@@ -872,7 +951,7 @@ int element1(PROLOG_STATE *state,
     state->level = 1;
     return XML_ROLE_GROUP_OPEN;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -888,7 +967,8 @@ int element2(PROLOG_STATE *state,
   case XML_TOK_POUND_NAME:
     if (XmlNameMatchesAscii(enc,
 			    ptr + MIN_BYTES_PER_CHAR(enc),
-			    "PCDATA")) {
+			    end,
+			    KW_PCDATA)) {
       state->handler = element3;
       return XML_ROLE_CONTENT_PCDATA;
     }
@@ -911,7 +991,7 @@ int element2(PROLOG_STATE *state,
     state->handler = element7;
     return XML_ROLE_CONTENT_ELEMENT_PLUS;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -932,7 +1012,7 @@ int element3(PROLOG_STATE *state,
     state->handler = element4;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -950,7 +1030,7 @@ int element4(PROLOG_STATE *state,
     state->handler = element5;
     return XML_ROLE_CONTENT_ELEMENT;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -970,7 +1050,7 @@ int element5(PROLOG_STATE *state,
     state->handler = element4;
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -1000,7 +1080,7 @@ int element6(PROLOG_STATE *state,
     state->handler = element7;
     return XML_ROLE_CONTENT_ELEMENT_PLUS;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 static
@@ -1040,9 +1120,72 @@ int element7(PROLOG_STATE *state,
     state->handler = element6;
     return XML_ROLE_GROUP_CHOICE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
+#ifdef XML_DTD
+
+static
+int condSect0(PROLOG_STATE *state,
+	      int tok,
+	      const char *ptr,
+	      const char *end,
+	      const ENCODING *enc)
+{
+  switch (tok) {
+  case XML_TOK_PROLOG_S:
+    return XML_ROLE_NONE;
+  case XML_TOK_NAME:
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_INCLUDE)) {
+      state->handler = condSect1;
+      return XML_ROLE_NONE;
+    }
+    if (XmlNameMatchesAscii(enc, ptr, end, KW_IGNORE)) {
+      state->handler = condSect2;
+      return XML_ROLE_NONE;
+    }
+    break;
+  }
+  return common(state, tok);
+}
+
+static
+int condSect1(PROLOG_STATE *state,
+	      int tok,
+	      const char *ptr,
+	      const char *end,
+	      const ENCODING *enc)
+{
+  switch (tok) {
+  case XML_TOK_PROLOG_S:
+    return XML_ROLE_NONE;
+  case XML_TOK_OPEN_BRACKET:
+    state->handler = externalSubset1;
+    state->includeLevel += 1;
+    return XML_ROLE_NONE;
+  }
+  return common(state, tok);
+}
+
+static
+int condSect2(PROLOG_STATE *state,
+	      int tok,
+	      const char *ptr,
+	      const char *end,
+	      const ENCODING *enc)
+{
+  switch (tok) {
+  case XML_TOK_PROLOG_S:
+    return XML_ROLE_NONE;
+  case XML_TOK_OPEN_BRACKET:
+    state->handler = externalSubset1;
+    return XML_ROLE_IGNORE_SECT;
+  }
+  return common(state, tok);
+}
+
+#endif /* XML_DTD */
+
 static
 int declClose(PROLOG_STATE *state,
 	      int tok,
@@ -1054,10 +1197,10 @@ int declClose(PROLOG_STATE *state,
   case XML_TOK_PROLOG_S:
     return XML_ROLE_NONE;
   case XML_TOK_DECL_CLOSE:
-    state->handler = internalSubset;
+    setTopLevel(state);
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 
 #if 0
@@ -1076,23 +1219,27 @@ int ignore(PROLOG_STATE *state,
   default:
     return XML_ROLE_NONE;
   }
-  return syntaxError(state);
+  return common(state, tok);
 }
 #endif
 
 static
 int error(PROLOG_STATE *state,
-	   int tok,
-	   const char *ptr,
-	   const char *end,
-	   const ENCODING *enc)
+	  int tok,
+	  const char *ptr,
+	  const char *end,
+	  const ENCODING *enc)
 {
   return XML_ROLE_NONE;
 }
 
 static
-int syntaxError(PROLOG_STATE *state)
+int common(PROLOG_STATE *state, int tok)
 {
+#ifdef XML_DTD
+  if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF)
+    return XML_ROLE_INNER_PARAM_ENTITY_REF;
+#endif
   state->handler = error;
   return XML_ROLE_ERROR;
 }
@@ -1100,4 +1247,19 @@ int syntaxError(PROLOG_STATE *state)
 void XmlPrologStateInit(PROLOG_STATE *state)
 {
   state->handler = prolog0;
+#ifdef XML_DTD
+  state->documentEntity = 1;
+  state->includeLevel = 0;
+#endif /* XML_DTD */
 }
+
+#ifdef XML_DTD
+
+void XmlPrologStateInitExternalEntity(PROLOG_STATE *state)
+{
+  state->handler = externalSubset0;
+  state->documentEntity = 0;
+  state->includeLevel = 0;
+}
+
+#endif /* XML_DTD */

expat/xmltok/xmlrole.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #ifndef XmlRole_INCLUDED
@@ -77,7 +62,13 @@ enum {
   XML_ROLE_CONTENT_ELEMENT_REP,
   XML_ROLE_CONTENT_ELEMENT_OPT,
   XML_ROLE_CONTENT_ELEMENT_PLUS,
-  XML_ROLE_PARAM_ENTITY_REF
+#ifdef XML_DTD
+  XML_ROLE_TEXT_DECL,
+  XML_ROLE_IGNORE_SECT,
+  XML_ROLE_INNER_PARAM_ENTITY_REF,
+#endif /* XML_DTD */
+  XML_ROLE_PARAM_ENTITY_REF,
+  XML_ROLE_EXTERNAL_GENERAL_ENTITY_NO_NOTATION
 };
 
 typedef struct prolog_state {
@@ -87,9 +78,16 @@ typedef struct prolog_state {
 		 const char *end,
 		 const ENCODING *enc);
   unsigned level;
+#ifdef XML_DTD
+  unsigned includeLevel;
+  int documentEntity;
+#endif /* XML_DTD */
 } PROLOG_STATE;
 
 void XMLTOKAPI XmlPrologStateInit(PROLOG_STATE *);
+#ifdef XML_DTD
+void XMLTOKAPI XmlPrologStateInitExternalEntity(PROLOG_STATE *);
+#endif /* XML_DTD */
 
 #define XmlTokenRole(state, tok, ptr, end, enc) \
  (((state)->handler)(state, tok, ptr, end, enc))

expat/xmltok/xmltok.c

@@ -1,29 +1,21 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include "xmldef.h"
 #include "xmltok.h"
 #include "nametab.h"
 
+#ifdef XML_DTD
+#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok)
+#else
+#define IGNORE_SECTION_TOK_VTABLE /* as nothing */
+#endif
+
 #define VTABLE1 \
-  { PREFIX(prologTok), PREFIX(contentTok), PREFIX(cdataSectionTok) }, \
+  { PREFIX(prologTok), PREFIX(contentTok), \
+    PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \
   { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \
   PREFIX(sameName), \
   PREFIX(nameMatchesAscii), \
@@ -176,6 +168,7 @@ struct normal_encoding {
 static int checkCharRefNumber(int);
 
 #include "xmltok_impl.h"
+#include "ascii.h"
 
 #ifdef XML_MIN_SIZE
 #define sb_isNameMin isNever
@@ -213,7 +206,7 @@ int sb_byteToAscii(const ENCODING *enc, const char *p)
   return *p;
 }
 #else
-#define BYTE_TO_ASCII(enc, p) (*p)
+#define BYTE_TO_ASCII(enc, p) (*(p))
 #endif
 
 #define IS_NAME_CHAR(enc, p, n) \
@@ -658,7 +651,7 @@ int little2_isNmstrtMin(const ENCODING *enc, const char *p)
 
 static const struct normal_encoding little2_encoding_ns = { 
   { VTABLE, 2, 0,
-#if BYTE_ORDER == 12
+#if XML_BYTE_ORDER == 12
     1
 #else
     0
@@ -675,7 +668,7 @@ static const struct normal_encoding little2_encoding_ns = {
 
 static const struct normal_encoding little2_encoding = { 
   { VTABLE, 2, 0,
-#if BYTE_ORDER == 12
+#if XML_BYTE_ORDER == 12
     1
 #else
     0
@@ -690,7 +683,7 @@ static const struct normal_encoding little2_encoding = {
   STANDARD_VTABLE(little2_)
 };
 
-#if BYTE_ORDER != 21
+#if XML_BYTE_ORDER != 21
 
 #ifdef XML_NS
 
@@ -797,7 +790,7 @@ int big2_isNmstrtMin(const ENCODING *enc, const char *p)
 
 static const struct normal_encoding big2_encoding_ns = {
   { VTABLE, 2, 0,
-#if BYTE_ORDER == 21
+#if XML_BYTE_ORDER == 21
   1
 #else
   0
@@ -814,7 +807,7 @@ static const struct normal_encoding big2_encoding_ns = {
 
 static const struct normal_encoding big2_encoding = {
   { VTABLE, 2, 0,
-#if BYTE_ORDER == 21
+#if XML_BYTE_ORDER == 21
   1
 #else
   0
@@ -829,7 +822,7 @@ static const struct normal_encoding big2_encoding = {
   STANDARD_VTABLE(big2_)
 };
 
-#if BYTE_ORDER != 12
+#if XML_BYTE_ORDER != 12
 
 #ifdef XML_NS
 
@@ -865,10 +858,10 @@ int streqci(const char *s1, const char *s2)
   for (;;) {
     char c1 = *s1++;
     char c2 = *s2++;
-    if ('a' <= c1 && c1 <= 'z')
-      c1 += 'A' - 'a';
-    if ('a' <= c2 && c2 <= 'z')
-      c2 += 'A' - 'a';
+    if (ASCII_a <= c1 && c1 <= ASCII_z)
+      c1 += ASCII_A - ASCII_a;
+    if (ASCII_a <= c2 && c2 <= ASCII_z)
+      c2 += ASCII_A - ASCII_a;
     if (c1 != c2)
       return 0;
     if (!c1)
@@ -900,10 +893,10 @@ static
 int isSpace(int c)
 {
   switch (c) {
-  case ' ':
-  case '\r':
-  case '\n':
-  case '\t':
+  case 0x20:
+  case 0xD:
+  case 0xA:
+  case 0x9:	
     return 1;
   }
   return 0;
@@ -916,6 +909,7 @@ int parsePseudoAttribute(const ENCODING *enc,
 			 const char *ptr,
 			 const char *end,
 			 const char **namePtr,
+			 const char **nameEndPtr,
 			 const char **valPtr,
 			 const char **nextTokPtr)
 {
@@ -943,13 +937,16 @@ int parsePseudoAttribute(const ENCODING *enc,
       *nextTokPtr = ptr;
       return 0;
     }
-    if (c == '=')
+    if (c == ASCII_EQUALS) {
+      *nameEndPtr = ptr;
       break;
+    }
     if (isSpace(c)) {
+      *nameEndPtr = ptr;
       do {
 	ptr += enc->minBytesPerChar;
       } while (isSpace(c = toAscii(enc, ptr, end)));
-      if (c != '=') {
+      if (c != ASCII_EQUALS) {
 	*nextTokPtr = ptr;
 	return 0;
       }
@@ -967,7 +964,7 @@ int parsePseudoAttribute(const ENCODING *enc,
     ptr += enc->minBytesPerChar;
     c = toAscii(enc, ptr, end);
   }
-  if (c != '"' && c != '\'') {
+  if (c != ASCII_QUOT && c != ASCII_APOS) {
     *nextTokPtr = ptr;
     return 0;
   }
@@ -978,12 +975,12 @@ int parsePseudoAttribute(const ENCODING *enc,
     c = toAscii(enc, ptr, end);
     if (c == open)
       break;
-    if (!('a' <= c && c <= 'z')
-	&& !('A' <= c && c <= 'Z')
-	&& !('0' <= c && c <= '9')
-	&& c != '.'
-	&& c != '-'
-	&& c != '_') {
+    if (!(ASCII_a <= c && c <= ASCII_z)
+	&& !(ASCII_A <= c && c <= ASCII_Z)
+	&& !(ASCII_0 <= c && c <= ASCII_9)
+	&& c != ASCII_PERIOD
+	&& c != ASCII_MINUS
+	&& c != ASCII_UNDERSCORE) {
       *nextTokPtr = ptr;
       return 0;
     }
@@ -992,6 +989,26 @@ int parsePseudoAttribute(const ENCODING *enc,
   return 1;
 }
 
+static const char KW_version[] = {
+  ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0'
+};
+
+static const char KW_encoding[] = {
+  ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, ASCII_i, ASCII_n, ASCII_g, '\0'
+};
+
+static const char KW_standalone[] = {
+  ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, ASCII_l, ASCII_o, ASCII_n, ASCII_e, '\0'
+};
+
+static const char KW_yes[] = {
+  ASCII_y, ASCII_e, ASCII_s,  '\0'
+};
+
+static const char KW_no[] = {
+  ASCII_n, ASCII_o,  '\0'
+};
+
 static
 int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
 		                                     const char *,
@@ -1008,13 +1025,14 @@ int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
 {
   const char *val = 0;
   const char *name = 0;
+  const char *nameEnd = 0;
   ptr += 5 * enc->minBytesPerChar;
   end -= 2 * enc->minBytesPerChar;
-  if (!parsePseudoAttribute(enc, ptr, end, &name, &val, &ptr) || !name) {
+  if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) || !name) {
     *badPtr = ptr;
     return 0;
   }
-  if (!XmlNameMatchesAscii(enc, name, "version")) {
+  if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) {
     if (!isGeneralTextEntity) {
       *badPtr = name;
       return 0;
@@ -1023,7 +1041,7 @@ int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
   else {
     if (versionPtr)
       *versionPtr = val;
-    if (!parsePseudoAttribute(enc, ptr, end, &name, &val, &ptr)) {
+    if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) {
       *badPtr = ptr;
       return 0;
     }
@@ -1036,9 +1054,9 @@ int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
       return 1;
     }
   }
-  if (XmlNameMatchesAscii(enc, name, "encoding")) {
+  if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) {
     int c = toAscii(enc, val, end);
-    if (!('a' <= c && c <= 'z') && !('A' <= c && c <= 'Z')) {
+    if (!(ASCII_a <= c && c <= ASCII_z) && !(ASCII_A <= c && c <= ASCII_Z)) {
       *badPtr = val;
       return 0;
     }
@@ -1046,22 +1064,22 @@ int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
       *encodingName = val;
     if (encoding)
       *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar);
-    if (!parsePseudoAttribute(enc, ptr, end, &name, &val, &ptr)) {
+    if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) {
       *badPtr = ptr;
       return 0;
     }
     if (!name)
       return 1;
   }
-  if (!XmlNameMatchesAscii(enc, name, "standalone") || isGeneralTextEntity) {
+  if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) || isGeneralTextEntity) {
     *badPtr = name;
     return 0;
   }
-  if (XmlNameMatchesAscii(enc, val, "yes")) {
+  if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) {
     if (standalone)
       *standalone = 1;
   }
-  else if (XmlNameMatchesAscii(enc, val, "no")) {
+  else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) {
     if (standalone)
       *standalone = 0;
   }
@@ -1158,7 +1176,7 @@ struct unknown_encoding {
   char utf8[256][4];
 };
 
-int XmlSizeOfUnknownEncoding()
+int XmlSizeOfUnknownEncoding(void)
 {
   return sizeof(struct unknown_encoding);
 }
@@ -1253,7 +1271,7 @@ XmlInitUnknownEncoding(void *mem,
 {
   int i;
   struct unknown_encoding *e = mem;
-  for (i = 0; i < sizeof(struct normal_encoding); i++)
+  for (i = 0; i < (int)sizeof(struct normal_encoding); i++)
     ((char *)mem)[i] = ((char *)&latin1_encoding)[i];
   for (i = 0; i < 128; i++)
     if (latin1_encoding.type[i] != BT_OTHER
@@ -1338,21 +1356,40 @@ enum {
   NO_ENC
 };
 
+static const char KW_ISO_8859_1[] = {
+  ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, ASCII_5, ASCII_9, ASCII_MINUS, ASCII_1, '\0'
+};
+static const char KW_US_ASCII[] = {
+  ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, ASCII_C, ASCII_I, ASCII_I, '\0'
+};
+static const char KW_UTF_8[] =	{
+  ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0'
+};
+static const char KW_UTF_16[] =	{
+  ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0'
+};
+static const char KW_UTF_16BE[] = {
+  ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_B, ASCII_E, '\0'
+};
+static const char KW_UTF_16LE[] = {
+  ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_L, ASCII_E, '\0'
+};
+
 static
 int getEncodingIndex(const char *name)
 {
   static const char *encodingNames[] = {
-    "ISO-8859-1",
-    "US-ASCII",
-    "UTF-8",
-    "UTF-16",
-    "UTF-16BE"
-    "UTF-16LE",
+    KW_ISO_8859_1,
+    KW_US_ASCII,
+    KW_UTF_8,
+    KW_UTF_16,
+    KW_UTF_16BE,
+    KW_UTF_16LE,
   };
   int i;
   if (name == 0)
     return NO_ENC;
-  for (i = 0; i < sizeof(encodingNames)/sizeof(encodingNames[0]); i++)
+  for (i = 0; i < (int)(sizeof(encodingNames)/sizeof(encodingNames[0])); i++)
     if (streqci(name, encodingNames[i]))
       return i;
   return UNKNOWN_ENC;
@@ -1361,7 +1398,8 @@ int getEncodingIndex(const char *name)
 /* For binary compatibility, we store the index of the encoding specified
 at initialization in the isUtf16 member. */
 
-#define INIT_ENC_INDEX(enc) ((enc)->initEnc.isUtf16)
+#define INIT_ENC_INDEX(enc) ((int)(enc)->initEnc.isUtf16)
+#define SET_INIT_ENC_INDEX(enc, i) ((enc)->initEnc.isUtf16 = (char)i)
 
 /* This is what detects the encoding.
 encodingTable maps from encoding indices to encodings;
@@ -1386,9 +1424,11 @@ int initScan(const ENCODING **encodingTable,
   encPtr = enc->encPtr;
   if (ptr + 1 == end) {
     /* only a single byte available for auto-detection */
+#ifndef XML_DTD /* FIXME */
     /* a well-formed document entity must have more than one byte */
     if (state != XML_CONTENT_STATE)
       return XML_TOK_PARTIAL;
+#endif
     /* so we're parsing an external text entity... */
     /* if UTF-16 was externally specified, then we need at least 2 bytes */
     switch (INIT_ENC_INDEX(enc)) {
@@ -1510,7 +1550,7 @@ XmlInitUnknownEncodingNS(void *mem,
 {
   ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData);
   if (enc)
-    ((struct normal_encoding *)enc)->type[':'] = BT_COLON;
+    ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON;
   return enc;
 }
 

expat/xmltok/xmltok.dsp

@@ -43,7 +43,7 @@ RSC=rc.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir "."
 # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c
-# ADD CPP /nologo /MT /W3 /GX /O2 /D XMLTOKAPI=__declspec(dllexport) /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D "XML_NS" /YX /FD /c
+# ADD CPP /nologo /MT /W3 /GX /O2 /D "NDEBUG" /D "XML_NS" /D XMLTOKAPI=__declspec(dllexport) /D "WIN32" /D "_WINDOWS" /D "XML_DTD" /YX /FD /c
 # ADD BASE MTL /nologo /D "NDEBUG" /win32
 # ADD MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x809 /d "NDEBUG"
@@ -53,7 +53,8 @@ BSC32=bscmake.exe
 # ADD BSC32 /nologo
 LINK32=link.exe
 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386
-# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /machine:I386 /out:"..\bin\xmltok.dll"
+# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /machine:I386 /out:"..\bin\xmltok.dll" /link50compat
+# SUBTRACT LINK32 /pdb:none
 
 !ELSEIF  "$(CFG)" == "xmltok - Win32 Debug"
 
@@ -69,7 +70,7 @@ LINK32=link.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir "."
 # ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c
-# ADD CPP /nologo /MTd /W3 /Gm /GX /ZI /Od /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllexport) /YX /FD /c
+# ADD CPP /nologo /MTd /W3 /Gm /GX /ZI /Od /D "_DEBUG" /D XMLTOKAPI=__declspec(dllexport) /D "WIN32" /D "_WINDOWS" /D "XML_DTD" /D "XML_NS" /YX /FD /c
 # ADD BASE MTL /nologo /D "_DEBUG" /win32
 # ADD MTL /nologo /D "_DEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x809 /d "_DEBUG"
@@ -96,6 +97,41 @@ SOURCE=.\dllmain.c
 # End Source File
 # Begin Source File
 
+SOURCE=..\gennmtab\gennmtab.c
+
+!IF  "$(CFG)" == "xmltok - Win32 Release"
+
+# PROP Ignore_Default_Tool 1
+# Begin Custom Build - Creating nametab.h
+InputDir=\home\work\xmls\gennmtab
+OutDir=.\Release
+ProjDir=.
+InputPath=..\gennmtab\gennmtab.c
+
+"$(ProjDir)\nametab.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
+	$(InputDir)\$(OutDir)\gennmtab >$(ProjDir)\nametab.h
+
+# End Custom Build
+
+!ELSEIF  "$(CFG)" == "xmltok - Win32 Debug"
+
+# PROP Ignore_Default_Tool 1
+# Begin Custom Build - Creating nametab.h
+InputDir=\home\work\xmls\gennmtab
+OutDir=.\Debug
+ProjDir=.
+InputPath=..\gennmtab\gennmtab.c
+
+"$(ProjDir)\nametab.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
+	$(InputDir)\$(OutDir)\gennmtab >$(ProjDir)\nametab.h
+
+# End Custom Build
+
+!ENDIF 
+
+# End Source File
+# Begin Source File
+
 SOURCE=.\xmlrole.c
 # End Source File
 # Begin Source File

expat/xmltok/xmltok.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #ifndef XmlTok_INCLUDED
@@ -98,10 +83,22 @@ extern "C" {
    for a name with a colon. */
 #define XML_TOK_PREFIXED_NAME 41
 
+#ifdef XML_DTD
+#define XML_TOK_IGNORE_SECT 42
+#endif /* XML_DTD */
+
+#ifdef XML_DTD
+#define XML_N_STATES 4
+#else /* not XML_DTD */
 #define XML_N_STATES 3
+#endif /* not XML_DTD */
+
 #define XML_PROLOG_STATE 0
 #define XML_CONTENT_STATE 1
 #define XML_CDATA_SECTION_STATE 2
+#ifdef XML_DTD
+#define XML_IGNORE_SECTION_STATE 3
+#endif /* XML_DTD */
 
 #define XML_N_LITERAL_TYPES 2
 #define XML_ATTRIBUTE_VALUE_LITERAL 0
@@ -140,7 +137,7 @@ struct encoding {
   int (*sameName)(const ENCODING *,
 	          const char *, const char *);
   int (*nameMatchesAscii)(const ENCODING *,
-			  const char *, const char *);
+			  const char *, const char *, const char *);
   int (*nameLength)(const ENCODING *, const char *);
   const char *(*skipS)(const ENCODING *, const char *);
   int (*getAtts)(const ENCODING *enc, const char *ptr,
@@ -201,6 +198,13 @@ literals, comments and processing instructions.
 #define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \
    XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr)
 
+#ifdef XML_DTD
+
+#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \
+   XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr)
+
+#endif /* XML_DTD */
+
 /* This is used for performing a 2nd-level tokenization on
 the content of a literal that has already been returned by XmlTok. */ 
 
@@ -215,8 +219,8 @@ the content of a literal that has already been returned by XmlTok. */
 
 #define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2))
 
-#define XmlNameMatchesAscii(enc, ptr1, ptr2) \
-  (((enc)->nameMatchesAscii)(enc, ptr1, ptr2))
+#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \
+  (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2))
 
 #define XmlNameLength(enc, ptr) \
   (((enc)->nameLength)(enc, ptr))
@@ -261,16 +265,16 @@ int XMLTOKAPI XmlParseXmlDecl(int isGeneralTextEntity,
 			      int *standalonePtr);
 
 int XMLTOKAPI XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name);
-const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncoding();
-const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncoding();
+const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncoding(void);
+const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncoding(void);
 int XMLTOKAPI XmlUtf8Encode(int charNumber, char *buf);
 int XMLTOKAPI XmlUtf16Encode(int charNumber, unsigned short *buf);
 
-int XMLTOKAPI XmlSizeOfUnknownEncoding();
+int XMLTOKAPI XmlSizeOfUnknownEncoding(void);
 ENCODING XMLTOKAPI *
 XmlInitUnknownEncoding(void *mem,
 		       int *table,
-		       int (*convert)(void *userData, const char *p),
+		       int (*conv)(void *userData, const char *p),
 		       void *userData);
 
 int XMLTOKAPI XmlParseXmlDeclNS(int isGeneralTextEntity,
@@ -283,12 +287,12 @@ int XMLTOKAPI XmlParseXmlDeclNS(int isGeneralTextEntity,
 			        const ENCODING **namedEncodingPtr,
 			        int *standalonePtr);
 int XMLTOKAPI XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name);
-const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncodingNS();
-const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncodingNS();
+const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncodingNS(void);
+const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncodingNS(void);
 ENCODING XMLTOKAPI *
 XmlInitUnknownEncodingNS(void *mem,
 		         int *table,
-		         int (*convert)(void *userData, const char *p),
+		         int (*conv)(void *userData, const char *p),
 		         void *userData);
 #ifdef __cplusplus
 }

expat/xmltok/xmltok_impl.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #ifndef IS_INVALID_CHAR
@@ -107,7 +92,7 @@ int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
 			const char **nextTokPtr)
 {
   if (ptr != end) {
-    if (!CHAR_MATCHES(enc, ptr, '-')) {
+    if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
       *nextTokPtr = ptr;
       return XML_TOK_INVALID;
     }
@@ -118,10 +103,10 @@ int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
       case BT_MINUS:
 	if ((ptr += MINBPC(enc)) == end)
 	  return XML_TOK_PARTIAL;
-	if (CHAR_MATCHES(enc, ptr, '-')) {
+	if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) {
 	  if ((ptr += MINBPC(enc)) == end)
 	    return XML_TOK_PARTIAL;
-	  if (!CHAR_MATCHES(enc, ptr, '>')) {
+	  if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
 	    *nextTokPtr = ptr;
 	    return XML_TOK_INVALID;
 	  }
@@ -195,9 +180,9 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
   if (end - ptr != MINBPC(enc)*3)
     return 1;
   switch (BYTE_TO_ASCII(enc, ptr)) {
-  case 'x':
+  case ASCII_x:
     break;
-  case 'X':
+  case ASCII_X:
     upper = 1;
     break;
   default:
@@ -205,9 +190,9 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
   }
   ptr += MINBPC(enc);
   switch (BYTE_TO_ASCII(enc, ptr)) {
-  case 'm':
+  case ASCII_m:
     break;
-  case 'M':
+  case ASCII_M:
     upper = 1;
     break;
   default:
@@ -215,9 +200,9 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
   }
   ptr += MINBPC(enc);
   switch (BYTE_TO_ASCII(enc, ptr)) {
-  case 'l':
+  case ASCII_l:
     break;
-  case 'L':
+  case ASCII_L:
     upper = 1;
     break;
   default:
@@ -261,7 +246,7 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
 	  ptr += MINBPC(enc);
 	  if (ptr == end)
 	    return XML_TOK_PARTIAL;
-	  if (CHAR_MATCHES(enc, ptr, '>')) {
+	  if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
 	    *nextTokPtr = ptr + MINBPC(enc);
 	    return tok;
 	  }
@@ -280,7 +265,7 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
       ptr += MINBPC(enc);
       if (ptr == end)
 	return XML_TOK_PARTIAL;
-      if (CHAR_MATCHES(enc, ptr, '>')) {
+      if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
 	*nextTokPtr = ptr + MINBPC(enc);
 	return tok;
       }
@@ -298,12 +283,13 @@ static
 int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end,
 			     const char **nextTokPtr)
 {
+  static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, ASCII_LSQB };
   int i;
   /* CDATA[ */
   if (end - ptr < 6 * MINBPC(enc))
     return XML_TOK_PARTIAL;
   for (i = 0; i < 6; i++, ptr += MINBPC(enc)) {
-    if (!CHAR_MATCHES(enc, ptr, "CDATA["[i])) {
+    if (!CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) {
       *nextTokPtr = ptr;
       return XML_TOK_INVALID;
     }
@@ -332,12 +318,12 @@ int PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *en
     ptr += MINBPC(enc);
     if (ptr == end)
       return XML_TOK_PARTIAL;
-    if (!CHAR_MATCHES(enc, ptr, ']'))
+    if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB))
       break;
     ptr += MINBPC(enc);
     if (ptr == end)
       return XML_TOK_PARTIAL;
-    if (!CHAR_MATCHES(enc, ptr, '>')) {
+    if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
       ptr -= MINBPC(enc);
       break;
     }
@@ -475,7 +461,7 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
 			const char **nextTokPtr)
 {
   if (ptr != end) {
-    if (CHAR_MATCHES(enc, ptr, 'x'))
+    if (CHAR_MATCHES(enc, ptr, ASCII_x))
       return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
     switch (BYTE_TYPE(enc, ptr)) {
     case BT_DIGIT:
@@ -668,7 +654,7 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
 	    ptr += MINBPC(enc);
 	    if (ptr == end)
 	      return XML_TOK_PARTIAL;
-	    if (!CHAR_MATCHES(enc, ptr, '>')) {
+	    if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
 	      *nextTokPtr = ptr;
 	      return XML_TOK_INVALID;
 	    }
@@ -777,7 +763,7 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
       ptr += MINBPC(enc);
       if (ptr == end)
 	return XML_TOK_PARTIAL;
-      if (!CHAR_MATCHES(enc, ptr, '>')) {
+      if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
 	*nextTokPtr = ptr;
 	return XML_TOK_INVALID;
       }
@@ -826,12 +812,12 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
     ptr += MINBPC(enc);
     if (ptr == end)
       return XML_TOK_TRAILING_RSQB;
-    if (!CHAR_MATCHES(enc, ptr, ']'))
+    if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB))
       break;
     ptr += MINBPC(enc);
     if (ptr == end)
       return XML_TOK_TRAILING_RSQB;
-    if (!CHAR_MATCHES(enc, ptr, '>')) {
+    if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) {
       ptr -= MINBPC(enc);
       break;
     }
@@ -856,12 +842,12 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
 #undef LEAD_CASE
     case BT_RSQB:
       if (ptr + MINBPC(enc) != end) {
-	 if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ']')) {
+	 if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) {
 	   ptr += MINBPC(enc);
 	   break;
 	 }
 	 if (ptr + 2*MINBPC(enc) != end) {
-	   if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), '>')) {
+	   if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) {
 	     ptr += MINBPC(enc);
 	     break;
 	   }
@@ -943,7 +929,7 @@ int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
       return XML_TOK_INVALID;
     }
   }
-  return XML_TOK_PARTIAL;
+  return -XML_TOK_POUND_NAME;
 }
 
 static
@@ -961,7 +947,7 @@ int PREFIX(scanLit)(int open, const ENCODING *enc,
       if (t != open)
 	break;
       if (ptr == end)
-	return XML_TOK_PARTIAL;
+	return -XML_TOK_LITERAL;
       *nextTokPtr = ptr;
       switch (BYTE_TYPE(enc, ptr)) {
       case BT_S: case BT_CR: case BT_LF:
@@ -1023,7 +1009,7 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
     }
   case BT_CR:
     if (ptr + MINBPC(enc) == end)
-      return XML_TOK_TRAILING_CR;
+      return -XML_TOK_PROLOG_S;
     /* fall through */
   case BT_S: case BT_LF:
     for (;;) {
@@ -1056,11 +1042,11 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
   case BT_RSQB:
     ptr += MINBPC(enc);
     if (ptr == end)
-      return XML_TOK_PARTIAL;
-    if (CHAR_MATCHES(enc, ptr, ']')) {
+      return -XML_TOK_CLOSE_BRACKET;
+    if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) {
       if (ptr + MINBPC(enc) == end)
 	return XML_TOK_PARTIAL;
-      if (CHAR_MATCHES(enc, ptr + MINBPC(enc), '>')) {
+      if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) {
 	*nextTokPtr = ptr + 2*MINBPC(enc);
 	return XML_TOK_COND_SECT_CLOSE;
       }
@@ -1073,7 +1059,7 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
   case BT_RPAR:
     ptr += MINBPC(enc);
     if (ptr == end)
-      return XML_TOK_PARTIAL;
+      return -XML_TOK_CLOSE_PAREN;
     switch (BYTE_TYPE(enc, ptr)) {
     case BT_AST:
       *nextTokPtr = ptr + MINBPC(enc);
@@ -1203,7 +1189,7 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
       return XML_TOK_INVALID;
     }
   }
-  return XML_TOK_PARTIAL;
+  return -tok;
 }
 
 static
@@ -1316,6 +1302,61 @@ int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end
   return XML_TOK_DATA_CHARS;
 }
 
+#ifdef XML_DTD
+
+static
+int PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
+			     const char **nextTokPtr)
+{
+  int level = 0;
+  if (MINBPC(enc) > 1) {
+    size_t n = end - ptr;
+    if (n & (MINBPC(enc) - 1)) {
+      n &= ~(MINBPC(enc) - 1);
+      end = ptr + n;
+    }
+  }
+  while (ptr != end) {
+    switch (BYTE_TYPE(enc, ptr)) {
+    INVALID_CASES(ptr, nextTokPtr)
+    case BT_LT:
+      if ((ptr += MINBPC(enc)) == end)
+	return XML_TOK_PARTIAL;
+      if (CHAR_MATCHES(enc, ptr, ASCII_EXCL)) {
+	if ((ptr += MINBPC(enc)) == end)
+	  return XML_TOK_PARTIAL;
+	if (CHAR_MATCHES(enc, ptr, ASCII_LSQB)) {
+	  ++level;
+	  ptr += MINBPC(enc);
+	}
+      }
+      break;
+    case BT_RSQB:
+      if ((ptr += MINBPC(enc)) == end)
+	return XML_TOK_PARTIAL;
+      if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) {
+	if ((ptr += MINBPC(enc)) == end)
+	  return XML_TOK_PARTIAL;
+	if (CHAR_MATCHES(enc, ptr, ASCII_GT)) {
+	  ptr += MINBPC(enc);
+	  if (level == 0) {
+	    *nextTokPtr = ptr;
+	    return XML_TOK_IGNORE_SECT;
+	  }
+	  --level;
+	}
+      }
+      break;
+    default:
+      ptr += MINBPC(enc);
+      break;
+    }
+  }
+  return XML_TOK_PARTIAL;
+}
+
+#endif /* XML_DTD */
+
 static
 int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
 		       const char **badPtr)
@@ -1347,7 +1388,7 @@ int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
 #endif
       break;
     case BT_S:
-      if (CHAR_MATCHES(enc, ptr, '\t')) {
+      if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) {
 	*badPtr = ptr;
 	return 0;
       }
@@ -1381,7 +1422,8 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
 {
   enum { other, inName, inValue } state = inName;
   int nAtts = 0;
-  int open;
+  int open = 0; /* defined when state == inValue;
+		   initialization just to shut up compilers */
 
   for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) {
     switch (BYTE_TYPE(enc, ptr)) {
@@ -1442,8 +1484,8 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
 	       && nAtts < attsMax
 	       && atts[nAtts].normalized
 	       && (ptr == atts[nAtts].valuePtr
-		   || BYTE_TO_ASCII(enc, ptr) != ' '
-		   || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ' '
+		   || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE
+		   || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE
 	           || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open))
 	atts[nAtts].normalized = 0;
       break;
@@ -1473,22 +1515,22 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
   int result = 0;
   /* skip &# */
   ptr += 2*MINBPC(enc);
-  if (CHAR_MATCHES(enc, ptr, 'x')) {
-    for (ptr += MINBPC(enc); !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
+  if (CHAR_MATCHES(enc, ptr, ASCII_x)) {
+    for (ptr += MINBPC(enc); !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) {
       int c = BYTE_TO_ASCII(enc, ptr);
       switch (c) {
-      case '0': case '1': case '2': case '3': case '4':
-      case '5': case '6': case '7': case '8': case '9':
+      case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4:
+      case ASCII_5: case ASCII_6: case ASCII_7: case ASCII_8: case ASCII_9:
 	result <<= 4;
-	result |= (c - '0');
+	result |= (c - ASCII_0);
 	break;
-      case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
+      case ASCII_A: case ASCII_B: case ASCII_C: case ASCII_D: case ASCII_E: case ASCII_F:
 	result <<= 4;
-	result += 10 + (c - 'A');
+	result += 10 + (c - ASCII_A);
 	break;
-      case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
+      case ASCII_a: case ASCII_b: case ASCII_c: case ASCII_d: case ASCII_e: case ASCII_f:
 	result <<= 4;
-	result += 10 + (c - 'a');
+	result += 10 + (c - ASCII_a);
 	break;
       }
       if (result >= 0x110000)
@@ -1496,10 +1538,10 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
     }
   }
   else {
-    for (; !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
+    for (; !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) {
       int c = BYTE_TO_ASCII(enc, ptr);
       result *= 10;
-      result += (c - '0');
+      result += (c - ASCII_0);
       if (result >= 0x110000)
 	return -1;
     }
@@ -1512,46 +1554,46 @@ int PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, const cha
 {
   switch ((end - ptr)/MINBPC(enc)) {
   case 2:
-    if (CHAR_MATCHES(enc, ptr + MINBPC(enc), 't')) {
+    if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) {
       switch (BYTE_TO_ASCII(enc, ptr)) {
-      case 'l':
-	return '<';
-      case 'g':
-	return '>';
+      case ASCII_l:
+	return ASCII_LT;
+      case ASCII_g:
+	return ASCII_GT;
       }
     }
     break;
   case 3:
-    if (CHAR_MATCHES(enc, ptr, 'a')) {
+    if (CHAR_MATCHES(enc, ptr, ASCII_a)) {
       ptr += MINBPC(enc);
-      if (CHAR_MATCHES(enc, ptr, 'm')) {
+      if (CHAR_MATCHES(enc, ptr, ASCII_m)) {
 	ptr += MINBPC(enc);
-	if (CHAR_MATCHES(enc, ptr, 'p'))
-	  return '&';
+	if (CHAR_MATCHES(enc, ptr, ASCII_p))
+	  return ASCII_AMP;
       }
     }
     break;
   case 4:
     switch (BYTE_TO_ASCII(enc, ptr)) {
-    case 'q':
+    case ASCII_q:
       ptr += MINBPC(enc);
-      if (CHAR_MATCHES(enc, ptr, 'u')) {
+      if (CHAR_MATCHES(enc, ptr, ASCII_u)) {
 	ptr += MINBPC(enc);
-	if (CHAR_MATCHES(enc, ptr, 'o')) {
+	if (CHAR_MATCHES(enc, ptr, ASCII_o)) {
 	  ptr += MINBPC(enc);
-  	  if (CHAR_MATCHES(enc, ptr, 't'))
-	    return '"';
+  	  if (CHAR_MATCHES(enc, ptr, ASCII_t))
+	    return ASCII_QUOT;
 	}
       }
       break;
-    case 'a':
+    case ASCII_a:
       ptr += MINBPC(enc);
-      if (CHAR_MATCHES(enc, ptr, 'p')) {
+      if (CHAR_MATCHES(enc, ptr, ASCII_p)) {
 	ptr += MINBPC(enc);
-	if (CHAR_MATCHES(enc, ptr, 'o')) {
+	if (CHAR_MATCHES(enc, ptr, ASCII_o)) {
 	  ptr += MINBPC(enc);
-  	  if (CHAR_MATCHES(enc, ptr, 's'))
-	    return '\'';
+  	  if (CHAR_MATCHES(enc, ptr, ASCII_s))
+	    return ASCII_APOS;
 	}
       }
       break;
@@ -1625,29 +1667,16 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
 }
 
 static
-int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, const char *ptr2)
+int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1,
+			     const char *end1, const char *ptr2)
 {
   for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
+    if (ptr1 == end1)
+      return 0;
     if (!CHAR_MATCHES(enc, ptr1, *ptr2))
       return 0;
   }
-  switch (BYTE_TYPE(enc, ptr1)) {
-  case BT_LEAD2:
-  case BT_LEAD3:
-  case BT_LEAD4:
-  case BT_NONASCII:
-  case BT_NMSTRT:
-#ifdef XML_NS
-  case BT_COLON:
-#endif
-  case BT_HEX:
-  case BT_DIGIT:
-  case BT_NAME:
-  case BT_MINUS:
-    return 0;
-  default:
-    return 1;
-  }
+  return ptr1 == end1;
 }
 
 static

expat/xmltok/xmltok_impl.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 enum {

expat/xmltok/xmltok_ns.c

@@ -1,13 +1,13 @@
-const ENCODING *NS(XmlGetUtf8InternalEncoding)()
+const ENCODING *NS(XmlGetUtf8InternalEncoding)(void)
 {
   return &ns(internal_utf8_encoding).enc;
 }
 
-const ENCODING *NS(XmlGetUtf16InternalEncoding)()
+const ENCODING *NS(XmlGetUtf16InternalEncoding)(void)
 {
-#if BYTE_ORDER == 12
+#if XML_BYTE_ORDER == 12
   return &ns(internal_little2_encoding).enc;
-#elif BYTE_ORDER == 21
+#elif XML_BYTE_ORDER == 21
   return &ns(internal_big2_encoding).enc;
 #else
   const short n = 1;
@@ -45,7 +45,7 @@ int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, const char *n
   int i = getEncodingIndex(name);
   if (i == UNKNOWN_ENC)
     return 0;
-  INIT_ENC_INDEX(p) = (char)i;
+  SET_INIT_ENC_INDEX(p, i);
   p->initEnc.scanners[XML_PROLOG_STATE] = NS(initScanProlog);
   p->initEnc.scanners[XML_CONTENT_STATE] = NS(initScanContent);
   p->initEnc.updatePosition = initUpdatePosition;
@@ -65,7 +65,7 @@ const ENCODING *NS(findEncoding)(const ENCODING *enc, const char *ptr, const cha
   if (ptr != end)
     return 0;
   *p = 0;
-  if (streqci(buf, "UTF-16") && enc->minBytesPerChar == 2)
+  if (streqci(buf, KW_UTF_16) && enc->minBytesPerChar == 2)
     return enc;
   i = getEncodingIndex(buf);
   if (i == UNKNOWN_ENC)

expat/xmlwf/.gitignore

@@ -0,0 +1,3 @@
+Debug
+Release
+xmlwf.plg

expat/xmlwf/codepage.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include "codepage.h"

expat/xmlwf/codepage.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 int codepageMap(int cp, int *map);

expat/xmlwf/ct.c

@@ -0,0 +1,145 @@
+#define CHARSET_MAX 41
+
+static
+const char *getTok(const char **pp)
+{
+  enum { inAtom, inString, init, inComment };
+  int state = init;
+  const char *tokStart = 0;
+  for (;;) {
+    switch (**pp) {
+    case '\0':
+      return 0;
+    case ' ':
+    case '\r':
+    case '\t':
+    case '\n':
+      if (state == inAtom)
+	return tokStart;
+      break;
+    case '(':
+      if (state == inAtom)
+	return tokStart;
+      if (state != inString)
+	state++;
+      break;
+    case ')':
+      if (state > init)
+	--state;
+      else if (state != inString)
+	return 0;
+      break;
+    case ';':
+    case '/':
+    case '=':
+      if (state == inAtom)
+	return tokStart;
+      if (state == init)
+	return (*pp)++;
+      break;
+    case '\\':
+      ++*pp;
+      if (**pp == '\0')
+	return 0;
+      break;
+    case '"':
+      switch (state) {
+      case inString:
+	++*pp;
+	return tokStart;
+      case inAtom:
+	return tokStart;
+      case init:
+	tokStart = *pp;
+	state = inString;
+	break;
+      }
+      break;
+    default:
+      if (state == init) {
+	tokStart = *pp;
+	state = inAtom;
+      }
+      break;
+    }
+    ++*pp;
+  }
+  /* not reached */
+}
+
+/* key must be lowercase ASCII */
+
+static
+int matchkey(const char *start, const char *end, const char *key)
+{
+  if (!start)
+    return 0;
+  for (; start != end; start++, key++)
+    if (*start != *key && *start != 'A' + (*key - 'a'))
+      return 0;
+  return *key == '\0';
+}
+
+void getXMLCharset(const char *buf, char *charset)
+{
+  const char *next, *p;
+
+  charset[0] = '\0';
+  next = buf;
+  p = getTok(&next);
+  if (matchkey(p, next, "text"))
+    strcpy(charset, "us-ascii");
+  else if (!matchkey(p, next, "application"))
+    return;
+  p = getTok(&next);
+  if (!p || *p != '/')
+    return;
+  p = getTok(&next);
+  if (matchkey(p, next, "xml"))
+    isXml = 1;
+  p = getTok(&next);
+  while (p) {
+    if (*p == ';') {
+      p = getTok(&next);
+      if (matchkey(p, next, "charset")) {
+	p = getTok(&next);
+	if (p && *p == '=') {
+	  p = getTok(&next);
+	  if (p) {
+	    char *s = charset;
+	    if (*p == '"') {
+	      while (++p != next - 1) {
+		if (*p == '\\')
+		  ++p;
+		if (s == charset + CHARSET_MAX - 1) {
+		  charset[0] = '\0';
+		  break;
+		}
+		*s++ = *p;
+	      }
+	      *s++ = '\0';
+	    }
+	    else {
+	      if (next - p > CHARSET_MAX - 1)
+		break;
+	      while (p != next)
+		*s++ = *p++;
+	      *s = 0;
+	      break;
+	    }
+	  }
+	}
+      }
+    }
+  else
+    p = getTok(&next);
+  }
+}
+
+int main(int argc, char **argv)
+{
+  char buf[CHARSET_MAX];
+  getXMLCharset(argv[1], buf);
+  printf("charset = \"%s\"\n", buf);
+  return 0;
+}

expat/xmlwf/filemap.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 

expat/xmlwf/readfilemap.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <sys/types.h>

expat/xmlwf/unixfilemap.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <sys/types.h>

expat/xmlwf/win32filemap.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #define STRICT 1

expat/xmlwf/xmlfile.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <stdio.h>
@@ -63,7 +48,7 @@ void reportError(XML_Parser parser, const XML_Char *filename)
   int code = XML_GetErrorCode(parser);
   const XML_Char *message = XML_ErrorString(code);
   if (message)
-    ftprintf(stdout, T("%s:%d:%ld: %s\n"),
+    ftprintf(stdout, T("%s:%d:%d: %s\n"),
 	     filename,
 	     XML_GetErrorLineNumber(parser),
 	     XML_GetErrorColumnNumber(parser),
@@ -88,12 +73,16 @@ void processFile(const void *data,
     *retPtr = 1;
 }
 
+#ifdef WIN32
+
 static
 int isAsciiLetter(XML_Char c)
 {
   return (T('a') <= c && c <= T('z')) || (T('A') <= c && c <= T('Z'));
 }
 
+#endif /* WIN32 */
+
 static
 const XML_Char *resolveSystemId(const XML_Char *base, const XML_Char *systemId, XML_Char **toFree)
 {

expat/xmlwf/xmlfile.h

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #define XML_MAP_FILE 01

expat/xmlwf/xmlwf.c

@@ -1,21 +1,6 @@
 /*
-The contents of this file are subject to the Mozilla Public License
-Version 1.0 (the "License"); you may not use this file except in
-compliance with the License. You may obtain a copy of the License at
-http://www.mozilla.org/MPL/
-
-Software distributed under the License is distributed on an "AS IS"
-basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
-License for the specific language governing rights and limitations
-under the License.
-
-The Original Code is expat.
-
-The Initial Developer of the Original Code is James Clark.
-Portions created by James Clark are Copyright (C) 1998
-James Clark. All Rights Reserved.
-
-Contributor(s):
+Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
+See the file copying.txt for copying permission.
 */
 
 #include <stdio.h>
@@ -32,6 +17,8 @@ Contributor(s):
 #include <crtdbg.h>
 #endif
 
+/* This ensures proper sorting. */
+
 #define NSSEP T('\001')
 
 static void characterData(void *userData, const XML_Char *s, int len)
@@ -48,6 +35,11 @@ static void characterData(void *userData, const XML_Char *s, int len)
     case T('>'):
       fputts(T("&gt;"), fp);
       break;
+#ifdef W3C14N
+    case 13:
+      fputts(T("&#xD;"), fp);
+      break;
+#else
     case T('"'):
       fputts(T("&quot;"), fp);
       break;
@@ -56,6 +48,7 @@ static void characterData(void *userData, const XML_Char *s, int len)
     case 13:
       ftprintf(fp, T("&#%d;"), *s);
       break;
+#endif
     default:
       puttc(*s, fp);
       break;
@@ -63,6 +56,53 @@ static void characterData(void *userData, const XML_Char *s, int len)
   }
 }
 
+static void attributeValue(FILE *fp, const XML_Char *s)
+{
+  puttc(T('='), fp);
+  puttc(T('"'), fp);
+  for (;;) {
+    switch (*s) {
+    case 0:
+    case NSSEP:
+      puttc(T('"'), fp);
+      return;
+    case T('&'):
+      fputts(T("&amp;"), fp);
+      break;
+    case T('<'):
+      fputts(T("&lt;"), fp);
+      break;
+    case T('"'):
+      fputts(T("&quot;"), fp);
+      break;
+#ifdef W3C14N
+    case 9:
+      fputts(T("&#x9;"), fp);
+      break;
+    case 10:
+      fputts(T("&#xA;"), fp);
+      break;
+    case 13:
+      fputts(T("&#xD;"), fp);
+      break;
+#else
+    case T('>'):
+      fputts(T("&gt;"), fp);
+      break;
+    case 9:
+    case 10:
+    case 13:
+      ftprintf(fp, T("&#%d;"), *s);
+      break;
+#endif
+    default:
+      puttc(*s, fp);
+      break;
+    }
+    s++;
+  }
+}
+
 /* Lexicographically comparing UTF-8 encoded attribute values,
 is equivalent to lexicographically comparing based on the character number. */
 
@@ -88,10 +128,7 @@ static void startElement(void *userData, const XML_Char *name, const XML_Char **
   while (*atts) {
     puttc(T(' '), fp);
     fputts(*atts++, fp);
-    puttc(T('='), fp);
-    puttc(T('"'), fp);
-    characterData(userData, *atts, tcslen(*atts));
-    puttc(T('"'), fp);
+    attributeValue(fp, *atts);
     atts++;
   }
   puttc(T('>'), fp);
@@ -106,6 +143,17 @@ static void endElement(void *userData, const XML_Char *name)
   puttc(T('>'), fp);
 }
 
+static int nsattcmp(const void *p1, const void *p2)
+{
+  const XML_Char *att1 = *(const XML_Char **)p1;
+  const XML_Char *att2 = *(const XML_Char **)p2;
+  int sep1 = (tcsrchr(att1, NSSEP) != 0);
+  int sep2 = (tcsrchr(att1, NSSEP) != 0);
+  if (sep1 != sep2)
+    return sep1 - sep2;
+  return tcscmp(att1, att2);
+}
+
 static void startElementNS(void *userData, const XML_Char *name, const XML_Char **atts)
 {
   int nAtts;
@@ -117,16 +165,15 @@ static void startElementNS(void *userData, const XML_Char *name, const XML_Char
 
   sep = tcsrchr(name, NSSEP);
   if (sep) {
-    fputts(T("ns0:"), fp);
+    fputts(T("n1:"), fp);
     fputts(sep + 1, fp);
-    fputts(T(" xmlns:ns0=\""), fp);
-    characterData(userData, name, sep - name);
-    puttc(T('"'), fp);
-    nsi = 1;
+    fputts(T(" xmlns:n1"), fp);
+    attributeValue(fp, name);
+    nsi = 2;
   }
   else {
     fputts(name, fp);
-    nsi = 0;
+    nsi = 1;
   }
 
   p = atts;
@@ -134,24 +181,22 @@ static void startElementNS(void *userData, const XML_Char *name, const XML_Char
     ++p;
   nAtts = (p - atts) >> 1;
   if (nAtts > 1)
-    qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, attcmp);
+    qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, nsattcmp);
   while (*atts) {
     name = *atts++;
     sep = tcsrchr(name, NSSEP);
+    puttc(T(' '), fp);
     if (sep) {
-      ftprintf(fp, T(" xmlns:ns%d=\""), nsi);
-      characterData(userData, name, sep - name);
-      puttc(T('"'), fp);
-      name = sep + 1;
-      ftprintf(fp, T(" ns%d:"), nsi++);
+      ftprintf(fp, T("n%d:"), nsi);
+      fputts(sep + 1, fp);
     }
     else
-      puttc(T(' '), fp);
-    fputts(name, fp);
-    puttc(T('='), fp);
-    puttc(T('"'), fp);
-    characterData(userData, *atts, tcslen(*atts));
-    puttc(T('"'), fp);
+      fputts(name, fp);
+    attributeValue(fp, *atts);
+    if (sep) {
+      ftprintf(fp, T(" xmlns:n%d"), nsi++);
+      attributeValue(fp, name);
+    }
     atts++;
   }
   puttc(T('>'), fp);
@@ -165,7 +210,7 @@ static void endElementNS(void *userData, const XML_Char *name)
   puttc(T('/'), fp);
   sep = tcsrchr(name, NSSEP);
   if (sep) {
-    fputts(T("ns0:"), fp);
+    fputts(T("n1:"), fp);
     fputts(sep + 1, fp);
   }
   else
@@ -173,6 +218,8 @@ static void endElementNS(void *userData, const XML_Char *name)
   puttc(T('>'), fp);
 }
 
+#ifndef W3C14N
+
 static void processingInstruction(void *userData, const XML_Char *target, const XML_Char *data)
 {
   FILE *fp = userData;
@@ -185,6 +232,8 @@ static void processingInstruction(void *userData, const XML_Char *target, const
   puttc(T('>'), fp);
 }
 
+#endif /* not W3C14N */
+
 static void defaultCharacterData(XML_Parser parser, const XML_Char *s, int len)
 {
   XML_DefaultCurrent(parser);
@@ -235,8 +284,9 @@ void metaLocation(XML_Parser parser)
   if (uri)
     ftprintf(XML_GetUserData(parser), T(" uri=\"%s\""), uri);
   ftprintf(XML_GetUserData(parser),
-           T(" byte=\"%ld\" line=\"%d\" col=\"%d\""),
+           T(" byte=\"%ld\" nbytes=\"%d\" line=\"%d\" col=\"%d\""),
 	   XML_GetCurrentByteIndex(parser),
+	   XML_GetCurrentByteCount(parser),
 	   XML_GetCurrentLineNumber(parser),
 	   XML_GetCurrentColumnNumber(parser));
 }
@@ -257,6 +307,15 @@ static
 void metaStartElement(XML_Parser parser, const XML_Char *name, const XML_Char **atts)
 {
   FILE *fp = XML_GetUserData(parser);
+  const XML_Char **specifiedAttsEnd
+    = atts + XML_GetSpecifiedAttributeCount(parser);
+  const XML_Char **idAttPtr;
+  int idAttIndex = XML_GetIdAttributeIndex(parser);
+  if (idAttIndex < 0)
+    idAttPtr = 0;
+  else
+    idAttPtr = atts + idAttIndex;
+    
   ftprintf(fp, T("<starttag name=\"%s\""), name);
   metaLocation(parser);
   if (*atts) {
@@ -264,7 +323,12 @@ void metaStartElement(XML_Parser parser, const XML_Char *name, const XML_Char **
     do {
       ftprintf(fp, T("<attribute name=\"%s\" value=\""), atts[0]);
       characterData(fp, atts[1], tcslen(atts[1]));
-      fputts(T("\"/>\n"), fp);
+      if (atts >= specifiedAttsEnd)
+	fputts(T("\" defaulted=\"yes\"/>\n"), fp);
+      else if (atts == idAttPtr)
+	fputts(T("\" id=\"yes\"/>\n"), fp);
+      else
+	fputts(T("\"/>\n"), fp);
     } while (*(atts += 2));
     fputts(T("</starttag>\n"), fp);
   }
@@ -332,13 +396,31 @@ void metaCharacterData(XML_Parser parser, const XML_Char *s, int len)
   fputts(T("/>\n"), fp);
 }
 
+static
+void metaStartDoctypeDecl(XML_Parser parser, const XML_Char *doctypeName)
+{
+  FILE *fp = XML_GetUserData(parser);
+  ftprintf(fp, T("<startdoctype name=\"%s\""), doctypeName);
+  metaLocation(parser);
+  fputts(T("/>\n"), fp);
+}
+
+static
+void metaEndDoctypeDecl(XML_Parser parser)
+{
+  FILE *fp = XML_GetUserData(parser);
+  fputts(T("<enddoctype"), fp);
+  metaLocation(parser);
+  fputts(T("/>\n"), fp);
+}
+
 static
 void metaUnparsedEntityDecl(XML_Parser parser,
-			       const XML_Char *entityName,
-			       const XML_Char *base,
-			       const XML_Char *systemId,
-			       const XML_Char *publicId,
-			       const XML_Char *notationName)
+			    const XML_Char *entityName,
+			    const XML_Char *base,
+			    const XML_Char *systemId,
+			    const XML_Char *publicId,
+			    const XML_Char *notationName)
 {
   FILE *fp = XML_GetUserData(parser);
   ftprintf(fp, T("<entity name=\"%s\""), entityName);
@@ -373,6 +455,66 @@ void metaNotationDecl(XML_Parser parser,
 }
 
 
+static
+void metaExternalParsedEntityDecl(XML_Parser parser,
+				  const XML_Char *entityName,
+				  const XML_Char *base,
+				  const XML_Char *systemId,
+				  const XML_Char *publicId)
+{
+  FILE *fp = XML_GetUserData(parser);
+  ftprintf(fp, T("<entity name=\"%s\""), entityName);
+  if (publicId)
+    ftprintf(fp, T(" public=\"%s\""), publicId);
+  fputts(T(" system=\""), fp);
+  characterData(fp, systemId, tcslen(systemId));
+  puttc(T('"'), fp);
+  metaLocation(parser);
+  fputts(T("/>\n"), fp);
+}
+
+static
+void metaInternalParsedEntityDecl(XML_Parser parser,
+				  const XML_Char *entityName,
+				  const XML_Char *text,
+				  int textLen)
+{
+  FILE *fp = XML_GetUserData(parser);
+  ftprintf(fp, T("<entity name=\"%s\""), entityName);
+  metaLocation(parser);
+  puttc(T('>'), fp);
+  characterData(fp, text, textLen);
+  fputts(T("</entity/>\n"), fp);
+}
+
+static
+void metaStartNamespaceDecl(XML_Parser parser,
+			    const XML_Char *prefix,
+			    const XML_Char *uri)
+{
+  FILE *fp = XML_GetUserData(parser);
+  fputts(T("<startns"), fp);
+  if (prefix)
+    ftprintf(fp, T(" prefix=\"%s\""), prefix);
+  if (uri) {
+    fputts(T(" ns=\""), fp);
+    characterData(fp, uri, tcslen(uri));
+    fputts(T("\"/>\n"), fp);
+  }
+  else
+    fputts(T("/>\n"), fp);
+}
+
+static
+void metaEndNamespaceDecl(XML_Parser parser, const XML_Char *prefix)
+{
+  FILE *fp = XML_GetUserData(parser);
+  if (!prefix)
+    fputts(T("<endns/>\n"), fp);
+  else
+    ftprintf(fp, T("<endns prefix=\"%s\"/>\n"), prefix);
+}
+
 static
 int unknownEncodingConvert(void *data, const char *p)
 {
@@ -417,67 +559,85 @@ int unknownEncoding(void *userData,
   return 1;
 }
 
+static
+int notStandalone(void *userData)
+{
+  return 0;
+}
+
 static
 void usage(const XML_Char *prog)
 {
-  ftprintf(stderr, T("usage: %s [-n] [-r] [-w] [-x] [-d output-dir] [-e encoding] file ...\n"), prog);
+  ftprintf(stderr, T("usage: %s [-n] [-p] [-r] [-s] [-w] [-x] [-d output-dir] [-e encoding] file ...\n"), prog);
   exit(1);
 }
 
 int tmain(int argc, XML_Char **argv)
 {
-  int i;
+  int i, j;
   const XML_Char *outputDir = 0;
   const XML_Char *encoding = 0;
   unsigned processFlags = XML_MAP_FILE;
   int windowsCodePages = 0;
   int outputType = 0;
   int useNamespaces = 0;
+  int requireStandalone = 0;
+  int paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
 
 #ifdef _MSC_VER
   _CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF|_CRTDBG_LEAK_CHECK_DF);
 #endif
 
   i = 1;
-  while (i < argc && argv[i][0] == T('-')) {
-    int j;
-    if (argv[i][1] == T('-') && argv[i][2] == T('\0')) {
-      i++;
-      break;
+  j = 0;
+  while (i < argc) {
+    if (j == 0) {
+      if (argv[i][0] != T('-'))
+	break;
+      if (argv[i][1] == T('-') && argv[i][2] == T('\0')) {
+	i++;
+	break;
+      }
+      j++;
     }
-    j = 1;
-    if (argv[i][j] == T('r')) {
+    switch (argv[i][j]) {
+    case T('r'):
       processFlags &= ~XML_MAP_FILE;
       j++;
-    }
-    if (argv[i][j] == T('n')) {
-      useNamespaces = 1;
-      outputType = 0;
+      break;
+    case T('s'):
+      requireStandalone = 1;
       j++;
-    }
-    if (argv[i][j] == T('x')) {
+      break;
+    case T('n'):
+      useNamespaces = 1;
+      j++;
+      break;
+    case T('p'):
+      paramEntityParsing = XML_PARAM_ENTITY_PARSING_ALWAYS;
+      /* fall through */
+    case T('x'):
       processFlags |= XML_EXTERNAL_ENTITIES;
       j++;
-    }
-    if (argv[i][j] == T('w')) {
+      break;
+    case T('w'):
       windowsCodePages = 1;
       j++;
-    }
-    if (argv[i][j] == T('m')) {
+      break;
+    case T('m'):
       outputType = 'm';
-      useNamespaces = 0;
       j++;
-    }
-    if (argv[i][j] == T('c')) {
+      break;
+    case T('c'):
       outputType = 'c';
       useNamespaces = 0;
       j++;
-    }
-    if (argv[i][j] == T('t')) {
+      break;
+    case T('t'):
       outputType = 't';
       j++;
-    }
-    if (argv[i][j] == T('d')) {
+      break;
+    case T('d'):
       if (argv[i][j + 1] == T('\0')) {
 	if (++i == argc)
 	  usage(argv[0]);
@@ -486,8 +646,9 @@ int tmain(int argc, XML_Char **argv)
       else
 	outputDir = argv[i] + j + 1;
       i++;
-    }
-    else if (argv[i][j] == T('e')) {
+      j = 0;
+      break;
+    case T('e'):
       if (argv[i][j + 1] == T('\0')) {
 	if (++i == argc)
 	  usage(argv[0]);
@@ -496,11 +657,18 @@ int tmain(int argc, XML_Char **argv)
       else
 	encoding = argv[i] + j + 1;
       i++;
-    }
-    else if (argv[i][j] == T('\0') && j > 1)
-      i++;
-    else
+      j = 0;
+      break;
+    case T('\0'):
+      if (j > 1) {
+	i++;
+	j = 0;
+	break;
+      }
+      /* fall through */
+    default:
       usage(argv[0]);
+    }
   }
   if (i == argc)
     usage(argv[0]);
@@ -513,7 +681,18 @@ int tmain(int argc, XML_Char **argv)
       parser = XML_ParserCreateNS(encoding, NSSEP);
     else
       parser = XML_ParserCreate(encoding);
-    if (outputDir) {
+    if (requireStandalone)
+      XML_SetNotStandaloneHandler(parser, notStandalone);
+    XML_SetParamEntityParsing(parser, paramEntityParsing);
+    if (outputType == 't') {
+      /* This is for doing timings; this gives a more realistic estimate of
+	 the parsing time. */
+      outputDir = 0;
+      XML_SetElementHandler(parser, nopStartElement, nopEndElement);
+      XML_SetCharacterDataHandler(parser, nopCharacterData);
+      XML_SetProcessingInstructionHandler(parser, nopProcessingInstruction);
+    }
+    else if (outputDir) {
       const XML_Char *file = argv[i];
       if (tcsrchr(file, T('/')))
 	file = tcsrchr(file, T('/')) + 1;
@@ -543,8 +722,12 @@ int tmain(int argc, XML_Char **argv)
 	XML_SetCommentHandler(parser, metaComment);
 	XML_SetCdataSectionHandler(parser, metaStartCdataSection, metaEndCdataSection);
 	XML_SetCharacterDataHandler(parser, metaCharacterData);
+	XML_SetDoctypeDeclHandler(parser, metaStartDoctypeDecl, metaEndDoctypeDecl);
 	XML_SetUnparsedEntityDeclHandler(parser, metaUnparsedEntityDecl);
 	XML_SetNotationDeclHandler(parser, metaNotationDecl);
+	XML_SetExternalParsedEntityDeclHandler(parser, metaExternalParsedEntityDecl);
+	XML_SetInternalParsedEntityDeclHandler(parser, metaInternalParsedEntityDecl);
+	XML_SetNamespaceDeclHandler(parser, metaStartNamespaceDecl, metaEndNamespaceDecl);
 	metaStartDocument(parser);
 	break;
       case 'c':
@@ -554,20 +737,15 @@ int tmain(int argc, XML_Char **argv)
 	XML_SetCharacterDataHandler(parser, defaultCharacterData);
 	XML_SetProcessingInstructionHandler(parser, defaultProcessingInstruction);
 	break;
-      case 't':
-	/* This is for doing timings; this gives a more realistic estimate of
-	   the parsing time. */
-	XML_SetElementHandler(parser, nopStartElement, nopEndElement);
-	XML_SetCharacterDataHandler(parser, nopCharacterData);
-	XML_SetProcessingInstructionHandler(parser, nopProcessingInstruction);
-	break;
       default:
 	if (useNamespaces)
 	  XML_SetElementHandler(parser, startElementNS, endElementNS);
 	else
 	  XML_SetElementHandler(parser, startElement, endElement);
 	XML_SetCharacterDataHandler(parser, characterData);
+#ifndef W3C14N
 	XML_SetProcessingInstructionHandler(parser, processingInstruction);
+#endif /* not W3C14N */
 	break;
       }
     }