d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

This commit was generated by cvs2svn to compensate for changes in r104349,

Browse Source 
which included commits to RCS files with non-trunk default branches.
This commit is contained in:
Poul-Henning Kamp 2002-10-02 07:16:04 +00:00
commit a6ed5f2251
52 changed files with 29055 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
contrib/expat/COPYING Normal file
View File

@ -0,0 +1,22 @@
Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
and Clark Cooper
Copyright (c) 2001, 2002 Expat maintainers.
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.

99
contrib/expat/Changes Normal file
View File

@ -0,0 +1,99 @@
Release 1.95.5 Fri Sep 6 2002
- Added XML_UseForeignDTD() for improved SAX2 support.
- Added XML_GetFeatureList().
- Defined XML_Bool type and the values XML_TRUE and XML_FALSE.
- Use an incomplete struct instead of a void* for the parser
(may not retain).
- Fixed UTF-8 decoding bug that caused legal UTF-8 to be rejected.
- Finally fixed bug where default handler would report DTD
events that were already handled by another handler.
Initial patch contributed by Darryl Miller.
- Removed unnecessary DllMain() function that caused static
linking into a DLL to be difficult.
- Added VC++ projects for building static libraries.
- Reduced line-length for all source code and headers to be
no longer than 80 characters, to help with AS/400 support.
- Reduced memory copying during parsing (SF patch #600964).
- Fixed a variety of bugs: see SF issues 580793, 434664,
483514, 580503, 581069, 584041, 584183, 584832, 585537,
596555, 596678, 598352, 598944, 599715, 600479, 600971.
Release 1.95.4 Fri Jul 12 2002
- Added support for VMS, contributed by Craig Berry. See
vms/README.vms for more information.
- Added Mac OS (classic) support, with a makefile for MPW,
contributed by Thomas Wegner and Daryle Walker.
- Added Borland C++ Builder 5 / BCC 5.5 support, contributed
by Patrick McConnell (SF patch #538032).
- Fixed a variety of bugs: see SF issues 441449, 563184,
564342, 566334, 566901, 569461, 570263, 575168, 579196.
- Made skippedEntityHandler conform to SAX2 (see source comment)
- Re-implemented WFC: Entity Declared from XML 1.0 spec and
added a new error "entity declared in parameter entity":
see SF bug report 569461 and SF patch 578161
- Re-implemented section 5.1 from XML 1.0 spec:
see SF bug report 570263 and SF patch 578161
Release 1.95.3 Mon Jun 3 2002
- Added a project to the MSVC workspace to create a wchar_t
version of the library; the DLLs are named libexpatw.dll.
- Changed the name of the Windows DLLs from expat.dll to
libexpat.dll; this fixes SF bug #432456.
- Added the XML_ParserReset() API function.
- Fixed XML_SetReturnNSTriplet() to work for element names.
- Made the XML_UNICODE builds usable (thanks, Karl!).
- Allow xmlwf to read from standard input.
- Install a man page for xmlwf on Unix systems.
- Fixed many bugs; see SF bug reports 231864, 461380, 464837,
466885, 469226, 477667, 484419, 487840, 494749, 496505,
547350. Other bugs which we can't test as easily may also
have been fixed, especially in the area of build support.
Release 1.95.2 Fri Jul 27 2001
- More changes to make MSVC happy with the build; add a single
workspace to support both the library and xmlwf application.
- Added a Windows installer for Windows users; includes
xmlwf.exe.
- Added compile-time constants that can be used to determine the
Expat version
- Removed a lot of GNU-specific dependencies to aide portability
among the various Unix flavors.
- Fix the UTF-8 BOM bug.
- Cleaned up warning messages for several compilers.
- Added the -Wall, -Wstrict-prototypes options for GCC.
Release 1.95.1 Sun Oct 22 15:11:36 EDT 2000
- Changes to get expat to build under Microsoft compiler
- Removed all aborts and instead return an UNEXPECTED_STATE error.
- Fixed a bug where a stray '%' in an entity value would cause an
abort.
- Defined XML_SetEndNamespaceDeclHandler. Thanks to Darryl Miles for
finding this oversight.
- Changed default patterns in lib/Makefile.in to fit non-GNU makes
Thanks to robin@unrated.net for reporting and providing an
account to test on.
- The reference had the wrong label for XML_SetStartNamespaceDecl.
Reported by an anonymous user.
Release 1.95.0 Fri Sep 29 2000
- XML_ParserCreate_MM
Allows you to set a memory management suite to replace the
standard malloc,realloc, and free.
- XML_SetReturnNSTriplet
If you turn this feature on when namespace processing is in
effect, then qualified, prefixed element and attribute names
are returned as "uri|name|prefix" where '|' is whatever
separator character is used in namespace processing.
- Merged in features from perl-expat
o XML_SetElementDeclHandler
o XML_SetAttlistDeclHandler
o XML_SetXmlDeclHandler
o XML_SetEntityDeclHandler
o StartDoctypeDeclHandler takes 3 additional parameters:
sysid, pubid, has_internal_subset
o Many paired handler setters (like XML_SetElementHandler)
now have corresponding individual handler setters
o XML_GetInputContext for getting the input context of
the current parse position.
- Added reference material
- Packaged into a distribution that builds a sharable library

16
contrib/expat/FREEBSD-upgrade Normal file
View File

@ -0,0 +1,16 @@
$FreeBSD$
eXpat from www.libexpat.org
Imported by:
tar zxvf expat-1.95.5.tar.gz
cd expat-1.95.5
rm -rf bcb5 win32 vms conftools doc/valid-xhtml10.png
vi FREEBSD-upgrade
cvs import -m "Virgin import (trimmed) of eXpat version 1.95.5" \
src/contrib/expat EXPAT v1_95_5
phk@FreeBSD.org

85
contrib/expat/MANIFEST Normal file
View File

@ -0,0 +1,85 @@
Changes
COPYING
MANIFEST
Makefile.in
README
configure
configure.in
expat_config.h.in
bcb5/ExpatGroup.bpg
bcb5/ReadMe.txt
bcb5/elements.bpf
bcb5/elements.bpr
bcb5/elements.mak
bcb5/libexpat.bpf
bcb5/libexpat.bpr
bcb5/libexpat.mak
bcb5/libexpatw.bpf
bcb5/libexpatw.bpr
bcb5/libexpatw.mak
bcb5/makefile.mak
bcb5/outline.bpf
bcb5/outline.bpr
bcb5/outline.mak
bcb5/setup.bat
bcb5/xmlwf.bpf
bcb5/xmlwf.bpr
bcb5/xmlwf.mak
conftools/PrintPath
conftools/ac_c_bigendian_cross.m4
conftools/config.guess
conftools/config.sub
conftools/expat.m4
conftools/install-sh
conftools/libtool.m4
conftools/ltmain.sh
conftools/mkinstalldirs
doc/reference.html
doc/style.css
doc/valid-xhtml10.png
doc/xmlwf.1
doc/xmlwf.sgml
examples/elements.c
examples/outline.c
lib/ascii.h
lib/asciitab.h
lib/expat.h
lib/iasciitab.h
lib/internal.h
lib/latin1tab.h
lib/nametab.h
lib/utf8tab.h
lib/xmlparse.c
lib/xmlrole.c
lib/xmlrole.h
lib/xmltok.c
lib/xmltok.h
lib/xmltok_impl.c
lib/xmltok_impl.h
lib/xmltok_ns.c
lib/winconfig.h
tests/README.txt
tests/chardata.c
tests/chardata.h
tests/runtests.c
tests/xmltest.sh
vms/descrip.mms
vms/expat_config.h
vms/README.vms
win32/expat.iss
win32/MANIFEST.txt
xmlwf/codepage.c
xmlwf/codepage.h
xmlwf/ct.c
xmlwf/filemap.h
xmlwf/readfilemap.c
xmlwf/unixfilemap.c
xmlwf/win32filemap.c
xmlwf/xmlfile.c
xmlwf/xmlfile.h
xmlwf/xmlmime.c
xmlwf/xmlmime.h
xmlwf/xmltchar.h
xmlwf/xmlurl.h
xmlwf/xmlwf.c
xmlwf/xmlwin32url.cxx

171
contrib/expat/Makefile.in Normal file
View File

@ -0,0 +1,171 @@
################################################################
# Process this file with top-level configure script to produce Makefile
#
# Copyright 2000 Clark Cooper
#
# This file is part of EXPAT.
#
# EXPAT is free software; you can redistribute it and/or modify it
# under the terms of the License (based on the MIT/X license) contained
# in the file COPYING that comes with this distribution.
#
# EXPAT 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 EXPAT.
#
SHELL = @SHELL@
srcdir = @srcdir@
top_srcdir = @top_srcdir@
VPATH = @srcdir@
prefix = @prefix@
exec_prefix = @exec_prefix@
bindir = @bindir@
libdir = @libdir@
includedir = @includedir@
mandir = ${prefix}/man/man1
top_builddir = .
INSTALL = @INSTALL@
INSTALL_PROGRAM = @INSTALL_PROGRAM@
INSTALL_DATA = @INSTALL_DATA@
mkinstalldirs = $(SHELL) $(top_srcdir)/conftools/mkinstalldirs
MANFILE = $(srcdir)/doc/xmlwf.1
APIHEADER = $(srcdir)/lib/expat.h
LIBRARY = libexpat.la
default: buildlib xmlwf/xmlwf
buildlib: $(LIBRARY)
all: $(LIBRARY) xmlwf/xmlwf examples/elements examples/outline
clean:
cd lib && rm -f $(LIBRARY) *.o *.lo && rm -rf .libs _libs
cd xmlwf && rm -f xmlwf *.o *.lo && rm -rf .libs _libs
cd examples && rm -f elements outline *.o *.lo && rm -rf .libs _libs
cd tests && rm -rf .libs runtests runtests.o chardata.o
rm -rf .libs libexpat.la
find . -name core | xargs rm -f
distclean: clean
rm -f expat_config.h config.status config.log config.cache libtool
rm -f Makefile
extraclean: distclean
rm -f expat_config.h.in configure
rm -f conftools/ltconfig conftools/ltmain.sh conftools/libtool.m4
check: tests/runtests
tests/runtests
install: xmlwf/xmlwf installlib
$(mkinstalldirs) $(bindir) $(mandir)
$(LIBTOOL) --mode=install $(INSTALL_PROGRAM) xmlwf/xmlwf $(bindir)/xmlwf
$(INSTALL_DATA) $(MANFILE) $(mandir)
installlib: $(LIBRARY) $(APIHEADER)
$(mkinstalldirs) $(libdir) $(includedir)
$(LIBTOOL) --mode=install $(INSTALL) $(LIBRARY) $(libdir)/$(LIBRARY)
$(INSTALL_DATA) $(APIHEADER) $(includedir)
uninstall: uninstalllib
$(LIBTOOL) --mode=uninstall rm -f $(bindir)/xmlwf
rm -f $(mandir)/xmlwf.1
uninstalllib:
$(LIBTOOL) --mode=uninstall rm -f $(libdir)/$(LIBRARY)
rm -f $(includedir)/$(APIHEADER)
# for VPATH builds (invoked by configure)
mkdir-init:
@for d in lib xmlwf examples tests ; do \
(mkdir $$d 2> /dev/null || test 1) ; \
done
CC = @CC@
LIBTOOL = @LIBTOOL@
INCLUDES = -I$(srcdir)/lib -I.
LDFLAGS = @LDFLAGS@
CPPFLAGS = @CPPFLAGS@
CFLAGS = @CFLAGS@
VSNFLAG = -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@
### autoconf this?
LTFLAGS = --silent
COMPILE = $(CC) $(CFLAGS) $(DEFS) $(CPPFLAGS) $(INCLUDES)
LTCOMPILE = $(LIBTOOL) $(LTFLAGS) --mode=compile $(COMPILE)
LINK_LIB = $(LIBTOOL) $(LTFLAGS) --mode=link $(COMPILE) -no-undefined $(VSNFLAG) -rpath $(libdir) $(LDFLAGS) -o $@
LINK_EXE = $(LIBTOOL) $(LTFLAGS) --mode=link $(COMPILE) $(LDFLAGS) -o $@
LIB_OBJS = lib/xmlparse.lo lib/xmltok.lo lib/xmlrole.lo
$(LIBRARY): $(LIB_OBJS)
$(LINK_LIB) $(LIB_OBJS)
lib/xmlparse.lo: lib/xmlparse.c lib/expat.h lib/xmlrole.h lib/xmltok.h \
$(top_builddir)/expat_config.h lib/internal.h
lib/xmlrole.lo: lib/xmlrole.c lib/ascii.h lib/xmlrole.h \
$(top_builddir)/expat_config.h lib/internal.h
lib/xmltok.lo: lib/xmltok.c lib/xmltok_impl.c lib/xmltok_ns.c \
lib/ascii.h lib/asciitab.h lib/iasciitab.h lib/latin1tab.h \
lib/nametab.h lib/utf8tab.h lib/xmltok.h lib/xmltok_impl.h \
$(top_builddir)/expat_config.h
XMLWF_OBJS = xmlwf/xmlwf.o xmlwf/xmlfile.o xmlwf/codepage.o xmlwf/@FILEMAP@.o
xmlwf/xmlwf.o: xmlwf/xmlwf.c
xmlwf/xmlfile.o: xmlwf/xmlfile.c
xmlwf/codepage.o: xmlwf/codepage.c
xmlwf/@FILEMAP@.o: xmlwf/@FILEMAP@.c
xmlwf/xmlwf: $(XMLWF_OBJS) $(LIBRARY)
$(LINK_EXE) $(XMLWF_OBJS) $(LIBRARY)
examples/elements.o: examples/elements.c
examples/elements: examples/elements.o $(LIBRARY)
$(LINK_EXE) $< $(LIBRARY)
examples/outline.o: examples/outline.c
examples/outline: examples/outline.o $(LIBRARY)
$(LINK_EXE) $< $(LIBRARY)
tests/chardata.o: tests/chardata.c tests/chardata.h
tests/runtests.o: tests/runtests.c tests/chardata.h
tests/runtests: tests/runtests.o tests/chardata.o $(LIBRARY)
$(LINK_EXE) $^ -lcheck
tests/xmlts.zip:
wget --output-document=tests/xmlts.zip \
http://www.w3.org/XML/Test/xmlts20020606.zip
tests/XML-Test-Suite: tests/xmlts.zip
cd tests && unzip -q xmlts.zip
run-xmltest: xmlwf/xmlwf tests/XML-Test-Suite
tests/xmltest.sh
.SUFFIXES: .c .lo .o
.c.o:
$(COMPILE) -o $@ -c $<
.c.lo:
$(LTCOMPILE) -o $@ -c $<
.PHONY: buildlib all \
clean distclean extraclean maintainer-clean \
dist distdir \
install uninstall

112
contrib/expat/README Normal file
View File

@ -0,0 +1,112 @@
Expat, Release 1.95.5
This is Expat, a C library for parsing XML, written by James Clark.
Expat is a stream-oriented XML parser. This means that you register
handlers with the parser before starting the parse. These handlers
are called when the parser discovers the associated structures in the
document being parsed. A start tag is an example of the kind of
structures for which you may register handlers.
Windows users should use the expat_win32bin package, which includes
both precompiled libraries and executalbes, and source code for
developers.
Expat is free software. You may copy, distribute, and modify it under
the terms of the License contained in the file COPYING distributed
with this package. This license is the same as the MIT/X Consortium
license.
Versions of Expat that have an odd minor version (the middle number in
the release above), are development releases and should be considered
as beta software. Releases with even minor version numbers are
intended to be production grade software.
If you are building Expat from a check-out from the CVS repository,
you need to run a script that generates the configure script using the
GNU autoconf and libtool tools. To do this, you need to have
autoconf 2.52 or newer and libtool 1.4 or newer. Run the script like
this:
./buildconf.sh
Once this has been done, follow the same instructions as for building
from a source distribution.
To build Expat from a source distribution, you first run the
configuration shell script in the top level distribution directory:
./configure
There are many options which you may provide to configure (which you
can discover by running configure with the --help option). But the
one of most interest is the one that sets the installation directory.
By default, the configure script will set things up to install
libexpat into /usr/local/lib, expat.h into /usr/local/include, and
xmlwf into /usr/local/bin. If, for example, you'd prefer to install
into /home/me/mystuff/lib, /home/me/mystuff/include, and
/home/me/mystuff/bin, you can tell configure about that with:
./configure --prefix=/home/me/mystuff
After running the configure script, the "make" command will build
things and "make install" will install things into their proper
location. Note that you need to have write permission into the
directories into which things will be installed.
If you are interested in building Expat to provide document
information in UTF-16 rather than the default UTF-8, following these
instructions:
1. For UTF-16 output as unsigned short (and version/error
strings as char), run:
./configure CPPFLAGS=-DXML_UNICODE
For UTF-16 output as wchar_t (incl. version/error strings),
run:
./configure CFLAGS="-g -O2 -fshort-wchar" \
CPPFLAGS=-DXML_UNICODE_WCHAR_T
2. Edit the MakeFile, changing:
LIBRARY = libexpat.la
to:
LIBRARY = libexpatw.la
(Note the additional "w" in the library name.)
3. Run "make buildlib" (which builds the library only).
4. Run "make installlib" (which installs the library only).
Note for Solaris users: The "ar" command is usually located in
"/usr/ccs/bin", which is not in the default PATH. You will need to
add this to your path for the "make" command, and probably also switch
to GNU make (the "make" found in /usr/ccs/bin does not seem to work
properly -- appearantly it does not understand .PHONY directives). If
you're using ksh or bash, use this command to build:
PATH=/usr/ccs/bin:$PATH make
When using Expat with a project using autoconf for configuration, you
can use the probing macro in conftools/expat.m4 to determine how to
include Expat. See the comments at the top of that file for more
information.
A reference manual is available in the file doc/reference.html in this
distribution.
The homepage for this project is http://www.libexpat.org/. There
are links there to connect you to the bug reports page. If you need
to report a bug when you don't have access to a browser, you may also
send a bug report by email to expat-bugs@mail.libexpat.org.
Discussion related to the direction of future expat development takes
place on expat-discuss@mail.libexpat.org. Archives of this list and
other Expat-related lists may be found at:
http://mail.libexpat.org/mailman-21/listinfo/

10094
contrib/expat/configure vendored Executable file
View File

File diff suppressed because it is too large Load Diff

124
contrib/expat/configure.in Normal file
View File

@ -0,0 +1,124 @@
dnl configuration script for expat
dnl Process this file with autoconf to produce a configure script.
dnl
dnl Copyright 2000 Clark Cooper
dnl
dnl This file is part of EXPAT.
dnl
dnl EXPAT is free software; you can redistribute it and/or modify it
dnl under the terms of the License (based on the MIT/X license) contained
dnl in the file COPYING that comes with this distribution.
dnl
dnl Ensure that Expat is configured with autoconf 2.52 or newer
AC_PREREQ(2.52)
dnl Get the version number of Expat, using m4's esyscmd() command to run
dnl the command at m4-generation time. This allows us to create an m4
dnl symbol holding the correct version number. AC_INIT() requires the
dnl version number at m4-time, rather than when ./configure is run, so
dnl all this must happen as part of m4, not as part of the shell code
dnl contained in ./configure.
dnl
dnl NOTE: esyscmd() is a GNU M4 extension. Thus, we wrap it in an appropriate
dnl test. I believe this test will work, but I don't have a place with non-
dnl GNU M4 to test it right now.
define([expat_version], ifdef([__gnu__],
[esyscmd(conftools/get-version.sh lib/expat.h)],
[1.95.x]))
AC_INIT(expat, expat_version, expat-bugs@mail.libexpat.org)
undefine([expat_version])
AC_CONFIG_SRCDIR(Makefile.in)
AC_CONFIG_AUX_DIR(conftools)
dnl
dnl Increment LIBREVISION if source code has changed at all
dnl
dnl If the API has changed, increment LIBCURRENT and set LIBREVISION to 0
dnl
dnl If the API changes compatibly (i.e. simply adding a new function
dnl without changing or removing earlier interfaces), then increment LIBAGE.
dnl
dnl If the API changes incompatibly set LIBAGE back to 0
dnl
LIBCURRENT=4
LIBREVISION=0
LIBAGE=4
AC_CONFIG_HEADER(expat_config.h)
sinclude(conftools/libtool.m4)
sinclude(conftools/ac_c_bigendian_cross.m4)
AC_LIBTOOL_WIN32_DLL
AC_PROG_LIBTOOL
AC_SUBST(LIBCURRENT)
AC_SUBST(LIBREVISION)
AC_SUBST(LIBAGE)
dnl Checks for programs.
AC_PROG_CC
AC_PROG_INSTALL
if test "$GCC" = yes ; then
dnl
dnl Be careful about adding the -fexceptions option; some versions of
dnl GCC don't support it and it causes extra warnings that are only
dnl distracting; avoid.
dnl
OLDCFLAGS="$CFLAGS -Wall -Wmissing-prototypes -Wstrict-prototypes"
CFLAGS="$OLDCFLAGS -fexceptions"
AC_MSG_CHECKING(whether gcc accepts -fexceptions)
AC_TRY_COMPILE(,(void)1,
AC_MSG_RESULT(yes),
AC_MSG_RESULT(no); CFLAGS="$OLDCFLAGS")
fi
dnl Checks for header files.
AC_HEADER_STDC
AC_CHECK_HEADERS(fcntl.h unistd.h)
dnl Checks for typedefs, structures, and compiler characteristics.
dnl Note: Avoid using AC_C_BIGENDIAN because it does not
dnl work in a cross compile.
AC_C_BIGENDIAN_CROSS
AC_C_CONST
AC_TYPE_OFF_T
AC_TYPE_SIZE_T
dnl Checks for library functions.
AC_FUNC_MEMCMP
AC_FUNC_MMAP
if test "$ac_cv_func_mmap_fixed_mapped" = "yes"; then
FILEMAP=unixfilemap
else
FILEMAP=readfilemap
fi
AC_SUBST(FILEMAP)
AC_CHECK_FUNCS(memmove bcopy)
dnl some basic configuration
AC_DEFINE([XML_NS], 1,
[Define to make XML Namespaces functionality available.])
AC_DEFINE([XML_DTD], 1,
[Define to make parameter entity parsing functionality available.])
AC_DEFINE([XML_CONTEXT_BYTES], 1024,
[Define to specify how much context to retain around the current parse point.])
AC_CONFIG_FILES(Makefile)
AC_OUTPUT
abs_srcdir="`cd $srcdir && pwd`"
abs_builddir="`pwd`"
if test "$abs_srcdir" != "$abs_builddir"; then
make mkdir-init
fi

1770
contrib/expat/doc/reference.html Normal file
View File

File diff suppressed because it is too large Load Diff

51
contrib/expat/doc/style.css Normal file
View File

@ -0,0 +1,51 @@
body {
background-color: white
}
.noborder {
border-width: 0px;
}
.eg {
padding-left: 1em;
padding-top: .5em;
padding-bottom: .5em;
border: solid thin;
margin: 1em 0;
background-color: tan;
margin-left: 2em;
margin-right: 10%;
}
.handler {
width: 100%;
border-top-width: thin;
margin-bottom: 1em;
}
.handler p {
margin-left: 2em;
}
.setter {
font-weight: bold;
}
.signature {
color: navy;
}
.fcndec {
width: 100%;
border-top-width: thin;
font-weight: bold;
}
.fcndef {
margin-left: 2em;
margin-bottom: 2em;
}
dd {
margin-bottom: 2em;
}

203
contrib/expat/doc/xmlwf.1 Normal file
View File

@ -0,0 +1,203 @@
.\" This manpage has been automatically generated by docbook2man
.\" from a DocBook document. This tool can be found at:
.\" <http://shell.ipoline.com/~elmert/comp/docbook2X/>
.\" Please send any bug reports, improvements, comments, patches,
.\" etc. to Steve Cheng <steve@ggi-project.org>.
.TH "XMLWF" "1" "22 April 2002" "" ""
.SH NAME
xmlwf \- Determines if an XML document is well-formed
.SH SYNOPSIS
\fBxmlwf\fR [ \fB-s\fR] [ \fB-n\fR] [ \fB-p\fR] [ \fB-x\fR] [ \fB-e \fIencoding\fB\fR] [ \fB-w\fR] [ \fB-d \fIoutput-dir\fB\fR] [ \fB-c\fR] [ \fB-m\fR] [ \fB-r\fR] [ \fB-t\fR] [ \fB-v\fR] [ \fBfile ...\fR]
.SH "DESCRIPTION"
.PP
\fBxmlwf\fR uses the Expat library to determine
if an XML document is well-formed. It is non-validating.
.PP
If you do not specify any files on the command-line,
and you have a recent version of xmlwf, the input
file will be read from stdin.
.SH "WELL-FORMED DOCUMENTS"
.PP
A well-formed document must adhere to the
following rules:
.TP 0.2i
\(bu
The file begins with an XML declaration. For instance,
<?xml version="1.0" standalone="yes"?>.
\fBNOTE:\fR xmlwf does not currently
check for a valid XML declaration.
.TP 0.2i
\(bu
Every start tag is either empty (<tag/>)
or has a corresponding end tag.
.TP 0.2i
\(bu
There is exactly one root element. This element must contain
all other elements in the document. Only comments, white
space, and processing instructions may come after the close
of the root element.
.TP 0.2i
\(bu
All elements nest properly.
.TP 0.2i
\(bu
All attribute values are enclosed in quotes (either single
or double).
.PP
If the document has a DTD, and it strictly complies with that
DTD, then the document is also considered \fBvalid\fR.
xmlwf is a non-validating parser -- it does not check the DTD.
However, it does support external entities (see the -x option).
.SH "OPTIONS"
.PP
When an option includes an argument, you may specify the argument either
separate ("d output") or mashed ("-doutput"). xmlwf supports both.
.TP
\fB-c\fR
If the input file is well-formed and xmlwf doesn't
encounter any errors, the input file is simply copied to
the output directory unchanged.
This implies no namespaces (turns off -n) and
requires -d to specify an output file.
.TP
\fB-d output-dir\fR
Specifies a directory to contain transformed
representations of the input files.
By default, -d outputs a canonical representation
(described below).
You can select different output formats using -c and -m.
The output filenames will
be exactly the same as the input filenames or "STDIN" if the input is
coming from STDIN. Therefore, you must be careful that the
output file does not go into the same directory as the input
file. Otherwise, xmlwf will delete the input file before
it generates the output file (just like running
cat < file > file in most shells).
Two structurally equivalent XML documents have a byte-for-byte
identical canonical XML representation.
Note that ignorable white space is considered significant and
is treated equivalently to data.
More on canonical XML can be found at
http://www.jclark.com/xml/canonxml.html .
.TP
\fB-e encoding\fR
Specifies the character encoding for the document, overriding
any document encoding declaration. xmlwf
has four built-in encodings:
US-ASCII,
UTF-8,
UTF-16, and
ISO-8859-1.
Also see the -w option.
.TP
\fB-m\fR
Outputs some strange sort of XML file that completely
describes the the input file, including character postitions.
Requires -d to specify an output file.
.TP
\fB-n\fR
Turns on namespace processing. (describe namespaces)
-c disables namespaces.
.TP
\fB-p\fR
Tells xmlwf to process external DTDs and parameter
entities.
Normally xmlwf never parses parameter entities.
-p tells it to always parse them.
-p implies -x.
.TP
\fB-r\fR
Normally xmlwf memory-maps the XML file before parsing.
-r turns off memory-mapping and uses normal file IO calls instead.
Of course, memory-mapping is automatically turned off
when reading from STDIN.
.TP
\fB-s\fR
Prints an error if the document is not standalone.
A document is standalone if it has no external subset and no
references to parameter entities.
.TP
\fB-t\fR
Turns on timings. This tells Expat to parse the entire file,
but not perform any processing.
This gives a fairly accurate idea of the raw speed of Expat itself
without client overhead.
-t turns off most of the output options (-d, -m -c, ...).
.TP
\fB-v\fR
Prints the version of the Expat library being used, and then exits.
.TP
\fB-w\fR
Enables Windows code pages.
Normally, xmlwf will throw an error if it runs across
an encoding that it is not equipped to handle itself. With
-w, xmlwf will try to use a Windows code page. See
also -e.
.TP
\fB-x\fR
Turns on parsing external entities.
Non-validating parsers are not required to resolve external
entities, or even expand entities at all.
Expat always expands internal entities (?),
but external entity parsing must be enabled explicitly.
External entities are simply entities that obtain their
data from outside the XML file currently being parsed.
This is an example of an internal entity:
.nf
<!ENTITY vers '1.0.2'>
.fi
And here are some examples of external entities:
.nf
<!ENTITY header SYSTEM "header-&vers;.xml"> (parsed)
<!ENTITY logo SYSTEM "logo.png" PNG> (unparsed)
.fi
.TP
\fB--\fR
For some reason, xmlwf specifically ignores "--"
anywhere it appears on the command line.
.PP
Older versions of xmlwf do not support reading from STDIN.
.SH "OUTPUT"
.PP
If an input file is not well-formed, xmlwf outputs
a single line describing the problem to STDOUT.
If a file is well formed, xmlwf outputs nothing.
Note that the result code is \fBnot\fR set.
.SH "BUGS"
.PP
According to the W3C standard, an XML file without a
declaration at the beginning is not considered well-formed.
However, xmlwf allows this to pass.
.PP
xmlwf returns a 0 - noerr result, even if the file is
not well-formed. There is no good way for a program to use
xmlwf to quickly check a file -- it must parse xmlwf's STDOUT.
.PP
The errors should go to STDERR, not stdout.
.PP
There should be a way to get -d to send its output to STDOUT
rather than forcing the user to send it to a file.
.PP
I have no idea why anyone would want to use the -d, -c
and -m options. If someone could explain it to me, I'd
like to add this information to this manpage.
.SH "ALTERNATIVES"
.PP
Here are some XML validators on the web:
.nf
http://www.hcrc.ed.ac.uk/~richard/xml-check.html
http://www.stg.brown.edu/service/xmlvalid/
http://www.scripting.com/frontier5/xml/code/xmlValidator.html
http://www.xml.com/pub/a/tools/ruwf/check.html

440
contrib/expat/doc/xmlwf.sgml Normal file
View File

@ -0,0 +1,440 @@
<!doctype refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN" [
<!-- Process this file with docbook-to-man to generate an nroff manual
page: `docbook-to-man manpage.sgml > manpage.1'. You may view
the manual page with: `docbook-to-man manpage.sgml | nroff -man |
less'. A typical entry in a Makefile or Makefile.am is:
manpage.1: manpage.sgml
docbook-to-man $< > $@
-->
<!-- Fill in your name for FIRSTNAME and SURNAME. -->
<!ENTITY dhfirstname "<firstname>Scott</firstname>">
<!ENTITY dhsurname "<surname>Bronson</surname>">
<!-- Please adjust the date whenever revising the manpage. -->
<!ENTITY dhdate "<date>December 5, 2001</date>">
<!-- SECTION should be 1-8, maybe w/ subsection other parameters are
allowed: see man(7), man(1). -->
<!ENTITY dhsection "<manvolnum>1</manvolnum>">
<!ENTITY dhemail "<email>bronson@rinspin.com</email>">
<!ENTITY dhusername "Scott Bronson">
<!ENTITY dhucpackage "<refentrytitle>XMLWF</refentrytitle>">
<!ENTITY dhpackage "xmlwf">
<!ENTITY debian "<productname>Debian GNU/Linux</productname>">
<!ENTITY gnu "<acronym>GNU</acronym>">
]>
<refentry>
<refentryinfo>
<address>
&dhemail;
</address>
<author>
&dhfirstname;
&dhsurname;
</author>
<copyright>
<year>2001</year>
<holder>&dhusername;</holder>
</copyright>
&dhdate;
</refentryinfo>
<refmeta>
&dhucpackage;
&dhsection;
</refmeta>
<refnamediv>
<refname>&dhpackage;</refname>
<refpurpose>Determines if an XML document is well-formed</refpurpose>
</refnamediv>
<refsynopsisdiv>
<cmdsynopsis>
<command>&dhpackage;</command>
<arg><option>-s</option></arg>
<arg><option>-n</option></arg>
<arg><option>-p</option></arg>
<arg><option>-x</option></arg>
<arg><option>-e <replaceable>encoding</replaceable></option></arg>
<arg><option>-w</option></arg>
<arg><option>-d <replaceable>output-dir</replaceable></option></arg>
<arg><option>-c</option></arg>
<arg><option>-m</option></arg>
<arg><option>-r</option></arg>
<arg><option>-t</option></arg>
<arg><option>-v</option></arg>
<arg>file ...</arg>
</cmdsynopsis>
</refsynopsisdiv>
<refsect1>
<title>DESCRIPTION</title>
<para>
<command>&dhpackage;</command> uses the Expat library to determine
if an XML document is well-formed. It is non-validating.
</para>
<para>
If you do not specify any files on the command-line,
and you have a recent version of &dhpackage;, the input
file will be read from stdin.
</para>
</refsect1>
<refsect1>
<title>WELL-FORMED DOCUMENTS</title>
<para>
A well-formed document must adhere to the
following rules:
</para>
<itemizedlist>
<listitem><para>
The file begins with an XML declaration. For instance,
<literal>&lt;?xml version="1.0" standalone="yes"?&gt;</literal>.
<emphasis>NOTE:</emphasis> &dhpackage; does not currently
check for a valid XML declaration.
</para></listitem>
<listitem><para>
Every start tag is either empty (&lt;tag/&gt;)
or has a corresponding end tag.
</para></listitem>
<listitem><para>
There is exactly one root element. This element must contain
all other elements in the document. Only comments, white
space, and processing instructions may come after the close
of the root element.
</para></listitem>
<listitem><para>
All elements nest properly.
</para></listitem>
<listitem><para>
All attribute values are enclosed in quotes (either single
or double).
</para></listitem>
</itemizedlist>
<para>
If the document has a DTD, and it strictly complies with that
DTD, then the document is also considered <emphasis>valid</emphasis>.
&dhpackage; is a non-validating parser -- it does not check the DTD.
However, it does support external entities (see the -x option).
</para>
</refsect1>
<refsect1>
<title>OPTIONS</title>
<para>
When an option includes an argument, you may specify the argument either
separate ("d output") or mashed ("-doutput"). &dhpackage; supports both.
</para>
<variablelist>
<varlistentry>
<term><option>-c</option></term>
<listitem>
<para>
If the input file is well-formed and &dhpackage; doesn't
encounter any errors, the input file is simply copied to
the output directory unchanged.
This implies no namespaces (turns off -n) and
requires -d to specify an output file.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-d output-dir</option></term>
<listitem>
<para>
Specifies a directory to contain transformed
representations of the input files.
By default, -d outputs a canonical representation
(described below).
You can select different output formats using -c and -m.
</para>
<para>
The output filenames will
be exactly the same as the input filenames or "STDIN" if the input is
coming from STDIN. Therefore, you must be careful that the
output file does not go into the same directory as the input
file. Otherwise, &dhpackage; will delete the input file before
it generates the output file (just like running
<literal>cat &lt; file &gt; file</literal> in most shells).
</para>
<para>
Two structurally equivalent XML documents have a byte-for-byte
identical canonical XML representation.
Note that ignorable white space is considered significant and
is treated equivalently to data.
More on canonical XML can be found at
http://www.jclark.com/xml/canonxml.html .
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-e encoding</option></term>
<listitem>
<para>
Specifies the character encoding for the document, overriding
any document encoding declaration. &dhpackage;
has four built-in encodings:
<literal>US-ASCII</literal>,
<literal>UTF-8</literal>,
<literal>UTF-16</literal>, and
<literal>ISO-8859-1</literal>.
Also see the -w option.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-m</option></term>
<listitem>
<para>
Outputs some strange sort of XML file that completely
describes the the input file, including character postitions.
Requires -d to specify an output file.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-n</option></term>
<listitem>
<para>
Turns on namespace processing. (describe namespaces)
-c disables namespaces.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-p</option></term>
<listitem>
<para>
Tells xmlwf to process external DTDs and parameter
entities.
</para>
<para>
Normally &dhpackage; never parses parameter entities.
-p tells it to always parse them.
-p implies -x.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-r</option></term>
<listitem>
<para>
Normally &dhpackage; memory-maps the XML file before parsing.
-r turns off memory-mapping and uses normal file IO calls instead.
Of course, memory-mapping is automatically turned off
when reading from STDIN.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-s</option></term>
<listitem>
<para>
Prints an error if the document is not standalone.
A document is standalone if it has no external subset and no
references to parameter entities.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-t</option></term>
<listitem>
<para>
Turns on timings. This tells Expat to parse the entire file,
but not perform any processing.
This gives a fairly accurate idea of the raw speed of Expat itself
without client overhead.
-t turns off most of the output options (-d, -m -c, ...).
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-v</option></term>
<listitem>
<para>
Prints the version of the Expat library being used, and then exits.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-w</option></term>
<listitem>
<para>
Enables Windows code pages.
Normally, &dhpackage; will throw an error if it runs across
an encoding that it is not equipped to handle itself. With
-w, &dhpackage; will try to use a Windows code page. See
also -e.
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>-x</option></term>
<listitem>
<para>
Turns on parsing external entities.
</para>
<para>
Non-validating parsers are not required to resolve external
entities, or even expand entities at all.
Expat always expands internal entities (?),
but external entity parsing must be enabled explicitly.
</para>
<para>
External entities are simply entities that obtain their
data from outside the XML file currently being parsed.
</para>
<para>
This is an example of an internal entity:
<literallayout>
&lt;!ENTITY vers '1.0.2'&gt;
</literallayout>
</para>
<para>
And here are some examples of external entities:
<literallayout>
&lt;!ENTITY header SYSTEM "header-&amp;vers;.xml"&gt; (parsed)
&lt;!ENTITY logo SYSTEM "logo.png" PNG&gt; (unparsed)
</literallayout>
</para>
</listitem>
</varlistentry>
<varlistentry>
<term><option>--</option></term>
<listitem>
<para>
For some reason, &dhpackage; specifically ignores "--"
anywhere it appears on the command line.
</para>
</listitem>
</varlistentry>
</variablelist>
<para>
Older versions of &dhpackage; do not support reading from STDIN.
</para>
</refsect1>
<refsect1>
<title>OUTPUT</title>
<para>
If an input file is not well-formed, &dhpackage; outputs
a single line describing the problem to STDOUT.
If a file is well formed, &dhpackage; outputs nothing.
Note that the result code is <emphasis>not</emphasis> set.
</para>
</refsect1>
<refsect1>
<title>BUGS</title>
<para>
According to the W3C standard, an XML file without a
declaration at the beginning is not considered well-formed.
However, &dhpackage; allows this to pass.
</para>
<para>
&dhpackage; returns a 0 - noerr result, even if the file is
not well-formed. There is no good way for a program to use
xmlwf to quickly check a file -- it must parse xmlwf's STDOUT.
</para>
<para>
The errors should go to STDERR, not stdout.
</para>
<para>
There should be a way to get -d to send its output to STDOUT
rather than forcing the user to send it to a file.
</para>
<para>
I have no idea why anyone would want to use the -d, -c
and -m options. If someone could explain it to me, I'd
like to add this information to this manpage.
</para>
</refsect1>
<refsect1>
<title>ALTERNATIVES</title>
<para>
Here are some XML validators on the web:
<literallayout>
http://www.hcrc.ed.ac.uk/~richard/xml-check.html
http://www.stg.brown.edu/service/xmlvalid/
http://www.scripting.com/frontier5/xml/code/xmlValidator.html
http://www.xml.com/pub/a/tools/ruwf/check.html
&nbsp; (on a page with no less than 15 ads! Shame!)
</literallayout>
</para>
</refsect1>
<refsect1>
<title>SEE ALSO</title>
<para>
<literallayout>
The Expat home page: http://www.libexpat.org/
The W3 XML specification: http://www.w3.org/TR/REC-xml
</literallayout>
</para>
</refsect1>
<refsect1>
<title>AUTHOR</title>
<para>
This manual page was written by &dhusername; &dhemail; for
the &debian; system (but may be used by others). Permission is
granted to copy, distribute and/or modify this document under
the terms of the <acronym>GNU</acronym> Free Documentation
License, Version 1.1.
</para>
</refsect1>
</refentry>
<!-- Keep this comment at the end of the file
Local variables:
mode: sgml
sgml-omittag:t
sgml-shorttag:t
sgml-minimize-attributes:nil
sgml-always-quote-attributes:t
sgml-indent-step:2
sgml-indent-data:t
sgml-parent-document:nil
sgml-default-dtd-file:nil
sgml-exposed-tags:nil
sgml-local-catalogs:nil
sgml-local-ecat-files:nil
End:
-->

50
contrib/expat/examples/elements.c Normal file
View File

@ -0,0 +1,50 @@
/* 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 "expat.h"
static 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;
}
static void
endElement(void *userData, const char *name)
{
int *depthPtr = userData;
*depthPtr -= 1;
}
int
main(int argc, char *argv[])
{
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) == XML_STATUS_ERROR) {
fprintf(stderr,
"%s at line %d\n",
XML_ErrorString(XML_GetErrorCode(parser)),
XML_GetCurrentLineNumber(parser));
return 1;
}
} while (!done);
XML_ParserFree(parser);
return 0;
}

90
contrib/expat/examples/outline.c Normal file
View File

@ -0,0 +1,90 @@
/*****************************************************************
* outline.c
*
* Copyright 1999, Clark Cooper
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the license contained in the
* COPYING file that comes with the expat distribution.
*
* 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.
*
* Read an XML document from standard input and print an element
* outline on standard output.
*/
#include <stdio.h>
#include <expat.h>
#define BUFFSIZE 8192
char Buff[BUFFSIZE];
int Depth;
static void
start(void *data, const char *el, const char **attr)
{
int i;
for (i = 0; i < Depth; i++)
printf(" ");
printf("%s", el);
for (i = 0; attr[i]; i += 2) {
printf(" %s='%s'", attr[i], attr[i + 1]);
}
printf("\n");
Depth++;
}
static void
end(void *data, const char *el)
{
Depth--;
}
int
main(int argc, char *argv[])
{
XML_Parser p = XML_ParserCreate(NULL);
if (! p) {
fprintf(stderr, "Couldn't allocate memory for parser\n");
exit(-1);
}
XML_SetElementHandler(p, start, end);
for (;;) {
int done;
int len;
len = fread(Buff, 1, BUFFSIZE, stdin);
if (ferror(stdin)) {
fprintf(stderr, "Read error\n");
exit(-1);
}
done = feof(stdin);
if (XML_Parse(p, Buff, len, done) == XML_STATUS_ERROR) {
fprintf(stderr, "Parse error at line %d:\n%s\n",
XML_GetCurrentLineNumber(p),
XML_ErrorString(XML_GetErrorCode(p)));
exit(-1);
}
if (done)
break;
}
return 0;
}

89
contrib/expat/expat_config.h.in Normal file
View File

@ -0,0 +1,89 @@
/* expat_config.h.in. Generated from configure.in by autoheader. */
/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
#undef BYTEORDER
/* Define to 1 if you have the `bcopy' function. */
#undef HAVE_BCOPY
/* Define to 1 if you have the <dlfcn.h> header file. */
#undef HAVE_DLFCN_H
/* Define to 1 if you have the <fcntl.h> header file. */
#undef HAVE_FCNTL_H
/* Define to 1 if you have the `getpagesize' function. */
#undef HAVE_GETPAGESIZE
/* Define to 1 if you have the <inttypes.h> header file. */
#undef HAVE_INTTYPES_H
/* Define to 1 if you have the `memmove' function. */
#undef HAVE_MEMMOVE
/* Define to 1 if you have the <memory.h> header file. */
#undef HAVE_MEMORY_H
/* Define to 1 if you have a working `mmap' system call. */
#undef HAVE_MMAP
/* Define to 1 if you have the <stdint.h> header file. */
#undef HAVE_STDINT_H
/* Define to 1 if you have the <stdlib.h> header file. */
#undef HAVE_STDLIB_H
/* Define to 1 if you have the <strings.h> header file. */
#undef HAVE_STRINGS_H
/* Define to 1 if you have the <string.h> header file. */
#undef HAVE_STRING_H
/* Define to 1 if you have the <sys/stat.h> header file. */
#undef HAVE_SYS_STAT_H
/* Define to 1 if you have the <sys/types.h> header file. */
#undef HAVE_SYS_TYPES_H
/* Define to 1 if you have the <unistd.h> header file. */
#undef HAVE_UNISTD_H
/* Define to the address where bug reports for this package should be sent. */
#undef PACKAGE_BUGREPORT
/* Define to the full name of this package. */
#undef PACKAGE_NAME
/* Define to the full name and version of this package. */
#undef PACKAGE_STRING
/* Define to the one symbol short name of this package. */
#undef PACKAGE_TARNAME
/* Define to the version of this package. */
#undef PACKAGE_VERSION
/* Define to 1 if you have the ANSI C header files. */
#undef STDC_HEADERS
/* whether byteorder is bigendian */
#undef WORDS_BIGENDIAN
/* Define to specify how much context to retain around the current parse
point. */
#undef XML_CONTEXT_BYTES
/* Define to make parameter entity parsing functionality available. */
#undef XML_DTD
/* Define to make XML Namespaces functionality available. */
#undef XML_NS
/* Define to empty if `const' does not conform to ANSI C. */
#undef const
/* Define to `long' if <sys/types.h> does not define. */
#undef off_t
/* Define to `unsigned' if <sys/types.h> does not define. */
#undef size_t

85
contrib/expat/lib/ascii.h Normal file
View File

@ -0,0 +1,85 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING 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

36
contrib/expat/lib/asciitab.h Normal file
View File

@ -0,0 +1,36 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
/* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML,
/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,

909
contrib/expat/lib/expat.h Normal file
View File

@ -0,0 +1,909 @@
/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#ifndef XmlParse_INCLUDED
#define XmlParse_INCLUDED 1
#ifdef __VMS
/* 0 1 2 3 0 1 2 3
1234567890123456789012345678901 1234567890123456789012345678901 */
#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler
#define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler
#define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler
#define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg
#endif
#include <stdlib.h>
#ifndef XMLPARSEAPI
#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__)
#ifdef _STATIC
#define XMLPARSEAPI(type) type __cdecl
#else
#define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl
#endif
#else
#define XMLPARSEAPI(type) type
#endif
#endif /* not defined XMLPARSEAPI */
#ifdef __cplusplus
extern "C" {
#endif
#ifdef XML_UNICODE_WCHAR_T
#define XML_UNICODE
#endif
struct XML_ParserStruct;
typedef struct XML_ParserStruct *XML_Parser;
#ifdef XML_UNICODE /* Information is UTF-16 encoded. */
#ifdef XML_UNICODE_WCHAR_T
typedef wchar_t XML_Char;
typedef wchar_t XML_LChar;
#else
typedef unsigned short XML_Char;
typedef char XML_LChar;
#endif /* XML_UNICODE_WCHAR_T */
#else /* Information is UTF-8 encoded. */
typedef char XML_Char;
typedef char XML_LChar;
#endif /* XML_UNICODE */
/* Should this be defined using stdbool.h when C99 is available? */
typedef unsigned char XML_Bool;
#define XML_TRUE ((XML_Bool) 1)
#define XML_FALSE ((XML_Bool) 0)
enum XML_Error {
XML_ERROR_NONE,
XML_ERROR_NO_MEMORY,
XML_ERROR_SYNTAX,
XML_ERROR_NO_ELEMENTS,
XML_ERROR_INVALID_TOKEN,
XML_ERROR_UNCLOSED_TOKEN,
XML_ERROR_PARTIAL_CHAR,
XML_ERROR_TAG_MISMATCH,
XML_ERROR_DUPLICATE_ATTRIBUTE,
XML_ERROR_JUNK_AFTER_DOC_ELEMENT,
XML_ERROR_PARAM_ENTITY_REF,
XML_ERROR_UNDEFINED_ENTITY,
XML_ERROR_RECURSIVE_ENTITY_REF,
XML_ERROR_ASYNC_ENTITY,
XML_ERROR_BAD_CHAR_REF,
XML_ERROR_BINARY_ENTITY_REF,
XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
XML_ERROR_MISPLACED_XML_PI,
XML_ERROR_UNKNOWN_ENCODING,
XML_ERROR_INCORRECT_ENCODING,
XML_ERROR_UNCLOSED_CDATA_SECTION,
XML_ERROR_EXTERNAL_ENTITY_HANDLING,
XML_ERROR_NOT_STANDALONE,
XML_ERROR_UNEXPECTED_STATE,
XML_ERROR_ENTITY_DECLARED_IN_PE,
XML_ERROR_FEATURE_REQUIRES_XML_DTD,
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING
};
enum XML_Content_Type {
XML_CTYPE_EMPTY = 1,
XML_CTYPE_ANY,
XML_CTYPE_MIXED,
XML_CTYPE_NAME,
XML_CTYPE_CHOICE,
XML_CTYPE_SEQ
};
enum XML_Content_Quant {
XML_CQUANT_NONE,
XML_CQUANT_OPT,
XML_CQUANT_REP,
XML_CQUANT_PLUS
};
/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be
XML_CQUANT_NONE, and the other fields will be zero or NULL.
If type == XML_CTYPE_MIXED, then quant will be NONE or REP and
numchildren will contain number of elements that may be mixed in
and children point to an array of XML_Content cells that will be
all of XML_CTYPE_NAME type with no quantification.
If type == XML_CTYPE_NAME, then the name points to the name, and
the numchildren field will be zero and children will be NULL. The
quant fields indicates any quantifiers placed on the name.
CHOICE and SEQ will have name NULL, the number of children in
numchildren and children will point, recursively, to an array
of XML_Content cells.
The EMPTY, ANY, and MIXED types will only occur at top level.
*/
typedef struct XML_cp XML_Content;
struct XML_cp {
enum XML_Content_Type type;
enum XML_Content_Quant quant;
XML_Char * name;
unsigned int numchildren;
XML_Content * children;
};
/* This is called for an element declaration. See above for
description of the model argument. It's the caller's responsibility
to free model when finished with it.
*/
typedef void (*XML_ElementDeclHandler) (void *userData,
const XML_Char *name,
XML_Content *model);
XMLPARSEAPI(void)
XML_SetElementDeclHandler(XML_Parser parser,
XML_ElementDeclHandler eldecl);
/* The Attlist declaration handler is called for *each* attribute. So
a single Attlist declaration with multiple attributes declared will
generate multiple calls to this handler. The "default" parameter
may be NULL in the case of the "#IMPLIED" or "#REQUIRED"
keyword. The "isrequired" parameter will be true and the default
value will be NULL in the case of "#REQUIRED". If "isrequired" is
true and default is non-NULL, then this is a "#FIXED" default.
*/
typedef void (*XML_AttlistDeclHandler) (void *userData,
const XML_Char *elname,
const XML_Char *attname,
const XML_Char *att_type,
const XML_Char *dflt,
int isrequired);
XMLPARSEAPI(void)
XML_SetAttlistDeclHandler(XML_Parser parser,
XML_AttlistDeclHandler attdecl);
/* The XML declaration handler is called for *both* XML declarations
and text declarations. The way to distinguish is that the version
parameter will be NULL for text declarations. The encoding
parameter may be NULL for XML declarations. The standalone
parameter will be -1, 0, or 1 indicating respectively that there
was no standalone parameter in the declaration, that it was given
as no, or that it was given as yes.
*/
typedef void (*XML_XmlDeclHandler) (void *userData,
const XML_Char *version,
const XML_Char *encoding,
int standalone);
XMLPARSEAPI(void)
XML_SetXmlDeclHandler(XML_Parser parser,
XML_XmlDeclHandler xmldecl);
typedef struct {
void *(*malloc_fcn)(size_t size);
void *(*realloc_fcn)(void *ptr, size_t size);
void (*free_fcn)(void *ptr);
} XML_Memory_Handling_Suite;
/* Constructs a new parser; encoding is the encoding specified by the
external protocol or NULL if there is none specified.
*/
XMLPARSEAPI(XML_Parser)
XML_ParserCreate(const XML_Char *encoding);
/* 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.
*/
XMLPARSEAPI(XML_Parser)
XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
/* Constructs a new parser using the memory management suit referred to
by memsuite. If memsuite is NULL, then use the standard library memory
suite. If namespaceSeparator is non-NULL it creates a parser with
namespace processing as described above. The character pointed at
will serve as the namespace separator.
All further memory operations used for the created parser will come from
the given suite.
*/
XMLPARSEAPI(XML_Parser)
XML_ParserCreate_MM(const XML_Char *encoding,
const XML_Memory_Handling_Suite *memsuite,
const XML_Char *namespaceSeparator);
/* Prepare a parser object to be re-used. This is particularly
valuable when memory allocation overhead is disproportionatly high,
such as when a large number of small documnents need to be parsed.
All handlers are cleared from the parser, except for the
unknownEncodingHandler. The parser's external state is re-initialized
except for the values of ns and ns_triplets.
Added in Expat 1.95.3.
*/
XMLPARSEAPI(XML_Bool)
XML_ParserReset(XML_Parser parser, const XML_Char *encoding);
/* atts is array of name/value pairs, terminated by 0;
names and values are 0 terminated.
*/
typedef void (*XML_StartElementHandler)(void *userData,
const XML_Char *name,
const XML_Char **atts);
typedef void (*XML_EndElementHandler)(void *userData,
const XML_Char *name);
/* s is not 0 terminated. */
typedef void (*XML_CharacterDataHandler)(void *userData,
const XML_Char *s,
int len);
/* target and data are 0 terminated */
typedef void (*XML_ProcessingInstructionHandler)(void *userData,
const XML_Char *target,
const XML_Char *data);
/* data is 0 terminated */
typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data);
typedef void (*XML_StartCdataSectionHandler)(void *userData);
typedef void (*XML_EndCdataSectionHandler)(void *userData);
/* 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 or UTF-16.
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.
*/
typedef void (*XML_DefaultHandler)(void *userData,
const XML_Char *s,
int len);
/* This is called for the start of the DOCTYPE declaration, before
any DTD or internal subset is parsed.
*/
typedef void (*XML_StartDoctypeDeclHandler)(void *userData,
const XML_Char *doctypeName,
const XML_Char *sysid,
const XML_Char *pubid,
int has_internal_subset);
/* 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 entity declarations. The is_parameter_entity
argument will be non-zero if the entity is a parameter entity, zero
otherwise.
For internal entities (<!ENTITY foo "bar">), value will
be non-NULL and systemId, publicID, and notationName will be NULL.
The value string is NOT nul-terminated; the length is provided in
the value_length argument. Since it is legal to have zero-length
values, do not use this argument to test for internal entities.
For external entities, value will be NULL and systemId will be
non-NULL. The publicId argument will be NULL unless a public
identifier was provided. The notationName argument will have a
non-NULL value only for unparsed entity declarations.
Note that is_parameter_entity can't be changed to XML_Bool, since
that would break binary compatibility.
*/
typedef void (*XML_EntityDeclHandler) (void *userData,
const XML_Char *entityName,
int is_parameter_entity,
const XML_Char *value,
int value_length,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId,
const XML_Char *notationName);
XMLPARSEAPI(void)
XML_SetEntityDeclHandler(XML_Parser parser,
XML_EntityDeclHandler handler);
/* OBSOLETE -- OBSOLETE -- OBSOLETE
This handler has been superceded by the EntityDeclHandler above.
It is provided here for backward compatibility.
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.
*/
typedef void (*XML_UnparsedEntityDeclHandler)(void *userData,
const XML_Char *entityName,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId,
const XML_Char *notationName);
/* 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.
*/
typedef void (*XML_NotationDeclHandler)(void *userData,
const XML_Char *notationName,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId);
/* 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, that is, 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.
If parameter entity parsing is enabled, then in addition to the
conditions above this handler will only be called if the referenced
entity was actually read.
*/
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
XML_ExternalEntityParserCreate.
The parser argument is the parser parsing the entity containing the
reference; it can be passed as the parser argument to
XML_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 XML_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 XML_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
XML_ERROR_EXTERNAL_ENTITY_HANDLING error.
Note that unlike other handlers the first argument is the parser,
not userData.
*/
typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser,
const XML_Char *context,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId);
/* This is called in two situations:
1) An entity reference is encountered for which no declaration
has been read *and* this is not an error.
2) An internal entity reference is read, but not expanded, because
XML_SetDefaultHandler has been called.
Note: skipped parameter entities in declarations and skipped general
entities in attribute values cannot be reported, because
the event would be out of sync with the reporting of the
declarations or attribute values
*/
typedef void (*XML_SkippedEntityHandler)(void *userData,
const XML_Char *entityName,
int is_parameter_entity);
/* This structure is filled in 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, (i.e., 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.
*/
typedef struct {
int map[256];
void *data;
int (*convert)(void *data, const char *s);
void (*release)(void *data);
} XML_Encoding;
/* 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.
*/
typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData,
const XML_Char *name,
XML_Encoding *info);
XMLPARSEAPI(void)
XML_SetElementHandler(XML_Parser parser,
XML_StartElementHandler start,
XML_EndElementHandler end);
XMLPARSEAPI(void)
XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler);
XMLPARSEAPI(void)
XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler);
XMLPARSEAPI(void)
XML_SetCharacterDataHandler(XML_Parser parser,
XML_CharacterDataHandler handler);
XMLPARSEAPI(void)
XML_SetProcessingInstructionHandler(XML_Parser parser,
XML_ProcessingInstructionHandler handler);
XMLPARSEAPI(void)
XML_SetCommentHandler(XML_Parser parser,
XML_CommentHandler handler);
XMLPARSEAPI(void)
XML_SetCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start,
XML_EndCdataSectionHandler end);
XMLPARSEAPI(void)
XML_SetStartCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start);
XMLPARSEAPI(void)
XML_SetEndCdataSectionHandler(XML_Parser parser,
XML_EndCdataSectionHandler end);
/* This sets the default handler and also inhibits expansion of
internal entities. These entity references will be passed to the
default handler, or to the skipped entity handler, if one is set.
*/
XMLPARSEAPI(void)
XML_SetDefaultHandler(XML_Parser parser,
XML_DefaultHandler handler);
/* This sets the default handler but does not inhibit expansion of
internal entities. The entity reference will not be passed to the
default handler.
*/
XMLPARSEAPI(void)
XML_SetDefaultHandlerExpand(XML_Parser parser,
XML_DefaultHandler handler);
XMLPARSEAPI(void)
XML_SetDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start,
XML_EndDoctypeDeclHandler end);
XMLPARSEAPI(void)
XML_SetStartDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start);
XMLPARSEAPI(void)
XML_SetEndDoctypeDeclHandler(XML_Parser parser,
XML_EndDoctypeDeclHandler end);
XMLPARSEAPI(void)
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
XML_UnparsedEntityDeclHandler handler);
XMLPARSEAPI(void)
XML_SetNotationDeclHandler(XML_Parser parser,
XML_NotationDeclHandler handler);
XMLPARSEAPI(void)
XML_SetNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start,
XML_EndNamespaceDeclHandler end);
XMLPARSEAPI(void)
XML_SetStartNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start);
XMLPARSEAPI(void)
XML_SetEndNamespaceDeclHandler(XML_Parser parser,
XML_EndNamespaceDeclHandler end);
XMLPARSEAPI(void)
XML_SetNotStandaloneHandler(XML_Parser parser,
XML_NotStandaloneHandler handler);
XMLPARSEAPI(void)
XML_SetExternalEntityRefHandler(XML_Parser parser,
XML_ExternalEntityRefHandler handler);
/* If a non-NULL value for arg is specified here, then it will be
passed as the first argument to the external entity ref handler
instead of the parser object.
*/
XMLPARSEAPI(void)
XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg);
XMLPARSEAPI(void)
XML_SetSkippedEntityHandler(XML_Parser parser,
XML_SkippedEntityHandler handler);
XMLPARSEAPI(void)
XML_SetUnknownEncodingHandler(XML_Parser parser,
XML_UnknownEncodingHandler handler,
void *encodingHandlerData);
/* 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.
*/
XMLPARSEAPI(void)
XML_DefaultCurrent(XML_Parser parser);
/* If do_nst is non-zero, and namespace processing is in effect, and
a name has a prefix (i.e. an explicit namespace qualifier) then
that name is returned as a triplet in a single string separated by
the separator character specified when the parser was created: URI
+ sep + local_name + sep + prefix.
If do_nst is zero, then namespace information is returned in the
default manner (URI + sep + local_name) whether or not the name
has a prefix.
Note: Calling XML_SetReturnNSTriplet after XML_Parse or
XML_ParseBuffer has no effect.
*/
XMLPARSEAPI(void)
XML_SetReturnNSTriplet(XML_Parser parser, int do_nst);
/* This value is passed as the userData argument to callbacks. */
XMLPARSEAPI(void)
XML_SetUserData(XML_Parser parser, void *userData);
/* Returns the last value set by XML_SetUserData or NULL. */
#define XML_GetUserData(parser) (*(void **)(parser))
/* This is equivalent to supplying an encoding argument to
XML_ParserCreate. On success XML_SetEncoding returns non-zero,
zero otherwise.
Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer
has no effect and returns zero.
*/
XMLPARSEAPI(int)
XML_SetEncoding(XML_Parser parser, const XML_Char *encoding);
/* If this function is called, then the parser will be passed as the
first argument to callbacks instead of userData. The userData will
still be accessible using XML_GetUserData.
*/
XMLPARSEAPI(void)
XML_UseParserAsHandlerArg(XML_Parser parser);
/* If useDTD == XML_TRUE is passed to this function, then the parser
will assume that there is an external subset, even if none is
specified in the document. In such a case the parser will call the
externalEntityRefHandler with a value of NULL for the systemId
argument (the publicId and context arguments will be NULL as well).
Note: If this function is called, then this must be done before
the first call to XML_Parse or XML_ParseBuffer, since it will
have no effect after that. Returns
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING.
Note: If the document does not have a DOCTYPE declaration at all,
then startDoctypeDeclHandler and endDoctypeDeclHandler will not
be called, despite an external subset being parsed.
Note: If XML_DTD is not defined when Expat is compiled, returns
XML_ERROR_FEATURE_REQUIRES_XML_DTD.
*/
XMLPARSEAPI(enum XML_Error)
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
/* 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.
*/
XMLPARSEAPI(int)
XML_SetBase(XML_Parser parser, const XML_Char *base);
XMLPARSEAPI(const XML_Char *)
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.
*/
XMLPARSEAPI(int)
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.
*/
XMLPARSEAPI(int)
XML_GetIdAttributeIndex(XML_Parser parser);
/* Parses some input. Returns XML_STATUS_ERROR 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).
The XML_Status enum gives the possible return values for the
XML_Parse and XML_ParseBuffer functions. Though the return values
for these functions has always been described as a Boolean value,
the implementation, at least for the 1.95.x series, has always
returned exactly one of these values. The preprocessor #defines
are included so this stanza can be added to code that still needs
to support older versions of Expat 1.95.x:
#ifndef XML_STATUS_OK
#define XML_STATUS_OK 1
#define XML_STATUS_ERROR 0
#endif
Otherwise, the #define hackery is quite ugly and would have been dropped.
*/
enum XML_Status {
XML_STATUS_ERROR = 0,
#define XML_STATUS_ERROR XML_STATUS_ERROR
XML_STATUS_OK = 1
#define XML_STATUS_OK XML_STATUS_OK
};
XMLPARSEAPI(enum XML_Status)
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal);
XMLPARSEAPI(void *)
XML_GetBuffer(XML_Parser parser, int len);
XMLPARSEAPI(enum XML_Status)
XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
/* 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.
*/
XMLPARSEAPI(XML_Parser)
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.
Note: If XML_SetParamEntityParsing is called after XML_Parse or
XML_ParseBuffer, then it has no effect and will always return 0.
*/
XMLPARSEAPI(int)
XML_SetParamEntityParsing(XML_Parser parser,
enum XML_ParamEntityParsing parsing);
/* If XML_Parse or XML_ParseBuffer have returned 0, then
XML_GetErrorCode returns information about the error.
*/
XMLPARSEAPI(enum XML_Error)
XML_GetErrorCode(XML_Parser parser);
/* 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.
*/
XMLPARSEAPI(int) XML_GetCurrentLineNumber(XML_Parser parser);
XMLPARSEAPI(int) XML_GetCurrentColumnNumber(XML_Parser parser);
XMLPARSEAPI(long) XML_GetCurrentByteIndex(XML_Parser parser);
/* Return the number of bytes in the current event.
Returns 0 if the event is in an internal entity.
*/
XMLPARSEAPI(int)
XML_GetCurrentByteCount(XML_Parser parser);
/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets
the integer pointed to by offset to the offset within this buffer
of the current parse position, and sets the integer pointed to by size
to the size of this buffer (the number of input bytes). Otherwise
returns a NULL pointer. Also returns a NULL pointer if a parse isn't
active.
NOTE: The character pointer returned should not be used outside
the handler that makes the call.
*/
XMLPARSEAPI(const char *)
XML_GetInputContext(XML_Parser parser,
int *offset,
int *size);
/* For backwards compatibility with previous versions. */
#define XML_GetErrorLineNumber XML_GetCurrentLineNumber
#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
#define XML_GetErrorByteIndex XML_GetCurrentByteIndex
/* Frees memory used by the parser. */
XMLPARSEAPI(void)
XML_ParserFree(XML_Parser parser);
/* Returns a string describing the error. */
XMLPARSEAPI(const XML_LChar *)
XML_ErrorString(enum XML_Error code);
/* Return a string containing the version number of this expat */
XMLPARSEAPI(const XML_LChar *)
XML_ExpatVersion(void);
typedef struct {
int major;
int minor;
int micro;
} XML_Expat_Version;
/* Return an XML_Expat_Version structure containing numeric version
number information for this version of expat.
*/
XMLPARSEAPI(XML_Expat_Version)
XML_ExpatVersionInfo(void);
/* Added in Expat 1.95.5. */
enum XML_FeatureEnum {
XML_FEATURE_END = 0,
XML_FEATURE_UNICODE,
XML_FEATURE_UNICODE_WCHAR_T,
XML_FEATURE_DTD,
XML_FEATURE_CONTEXT_BYTES,
XML_FEATURE_MIN_SIZE,
XML_FEATURE_SIZEOF_XML_CHAR,
XML_FEATURE_SIZEOF_XML_LCHAR
/* Additional features must be added to the end of this enum. */
};
typedef struct {
enum XML_FeatureEnum feature;
XML_LChar *name;
long int value;
} XML_Feature;
XMLPARSEAPI(const XML_Feature *)
XML_GetFeatureList(void);
/* Expat follows the GNU/Linux convention of odd number minor version for
beta/development releases and even number minor version for stable
releases. Micro is bumped with each release, and set to 0 with each
change to major or minor version.
*/
#define XML_MAJOR_VERSION 1
#define XML_MINOR_VERSION 95
#define XML_MICRO_VERSION 5
#ifdef __cplusplus
}
#endif
#endif /* not XmlParse_INCLUDED */

37
contrib/expat/lib/iasciitab.h Normal file
View File

@ -0,0 +1,37 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */
/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
/* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML,
/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,

46
contrib/expat/lib/internal.h Normal file
View File

@ -0,0 +1,46 @@
/* internal.h
Internal definitions used by Expat. This is not needed to compile
client code.
The following definitions are made:
FASTCALL -- Used for most internal functions to specify that the
fastest possible calling convention be used.
inline -- Used for selected internal functions for which inlining
may improve performance on some platforms.
*/
#if defined(__GNUC__)
/* Last minute instability reported with egcs on a RedHat Linux 7.3
box; argh!
*/
/* #define FASTCALL __attribute__((stdcall, regparm(3))) */
#elif defined(WIN32)
/* XXX This seems to have an unexpected negative effect on Windows so
we'll disable it for now on that platform. It may be reconsidered
for a future release if it can be made more effective.
*/
/* #define FASTCALL __fastcall */
#endif
#ifndef FASTCALL
#define FASTCALL
#endif
#ifndef XML_MIN_SIZE
#if !defined(__cplusplus) && !defined(inline)
#ifdef __GNUC__
#define inline __inline
#endif /* __GNUC__ */
#endif
#endif /* XML_MIN_SIZE */
#ifdef __cplusplus
#define inline inline
#else
#ifndef inline
#define inline
#endif
#endif

36
contrib/expat/lib/latin1tab.h Normal file
View File

@ -0,0 +1,36 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
/* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME,
/* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
/* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
/* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
/* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
/* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
/* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,

150
contrib/expat/lib/nametab.h Normal file
View File

@ -0,0 +1,150 @@
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, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF,
0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF,
0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF,
0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
0x0000007F, 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, 0x0000001F, 0x00000000,
0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF,
0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB,
0x40000000, 0xF580C900, 0x00000007, 0x02010800,
0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF,
0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF,
0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF,
0x00000000, 0x00004C40, 0x00000000, 0x00000000,
0x00000007, 0x00000000, 0x00000000, 0x00000000,
0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF,
0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF,
0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000,
0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000,
0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE,
0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF,
0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000,
0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003,
0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD,
0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF,
0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF,
0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE,
0xFFFE007F, 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, 0x03FF3F5F, 0x00000000,
0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF,
0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0x00000000, 0x00000000, 0x1FFF0000, 0x00000002,
0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF,
0x661FFFFF, 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,
0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x15, 0x16, 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, 0x17,
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, 0x18,
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[] = {
0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00,
0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25,
0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13,
0x26, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x27, 0x16, 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, 0x17,
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, 0x18,
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,
};

37
contrib/expat/lib/utf8tab.h Normal file
View File

@ -0,0 +1,37 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2,
/* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
/* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
/* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
/* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3,
/* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4,
/* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
/* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM,

30
contrib/expat/lib/winconfig.h Normal file
View File

@ -0,0 +1,30 @@
/*================================================================
** Copyright 2000, Clark Cooper
** All rights reserved.
**
** This is free software. You are permitted to copy, distribute, or modify
** it under the terms of the MIT/X license (contained in the COPYING file
** with this distribution.)
*/
#ifndef WINCONFIG_H
#define WINCONFIG_H
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#undef WIN32_LEAN_AND_MEAN
#include <memory.h>
#include <string.h>
#define XML_NS 1
#define XML_DTD 1
#define XML_CONTEXT_BYTES 1024
/* we will assume all Windows platforms are little endian */
#define BYTEORDER 1234
/* Windows has memmove() available. */
#define HAVE_MEMMOVE
#endif /* ndef WINCONFIG_H */

5600
contrib/expat/lib/xmlparse.c Normal file
View File

File diff suppressed because it is too large Load Diff

1321
contrib/expat/lib/xmlrole.c Normal file
View File

File diff suppressed because it is too large Load Diff

114
contrib/expat/lib/xmlrole.h Normal file
View File

@ -0,0 +1,114 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#ifndef XmlRole_INCLUDED
#define XmlRole_INCLUDED 1
#ifdef __VMS
/* 0 1 2 3 0 1 2 3
1234567890123456789012345678901 1234567890123456789012345678901 */
#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt
#endif
#include "xmltok.h"
#ifdef __cplusplus
extern "C" {
#endif
enum {
XML_ROLE_ERROR = -1,
XML_ROLE_NONE = 0,
XML_ROLE_XML_DECL,
XML_ROLE_INSTANCE_START,
XML_ROLE_DOCTYPE_NONE,
XML_ROLE_DOCTYPE_NAME,
XML_ROLE_DOCTYPE_SYSTEM_ID,
XML_ROLE_DOCTYPE_PUBLIC_ID,
XML_ROLE_DOCTYPE_INTERNAL_SUBSET,
XML_ROLE_DOCTYPE_CLOSE,
XML_ROLE_GENERAL_ENTITY_NAME,
XML_ROLE_PARAM_ENTITY_NAME,
XML_ROLE_ENTITY_NONE,
XML_ROLE_ENTITY_VALUE,
XML_ROLE_ENTITY_SYSTEM_ID,
XML_ROLE_ENTITY_PUBLIC_ID,
XML_ROLE_ENTITY_COMPLETE,
XML_ROLE_ENTITY_NOTATION_NAME,
XML_ROLE_NOTATION_NONE,
XML_ROLE_NOTATION_NAME,
XML_ROLE_NOTATION_SYSTEM_ID,
XML_ROLE_NOTATION_NO_SYSTEM_ID,
XML_ROLE_NOTATION_PUBLIC_ID,
XML_ROLE_ATTRIBUTE_NAME,
XML_ROLE_ATTRIBUTE_TYPE_CDATA,
XML_ROLE_ATTRIBUTE_TYPE_ID,
XML_ROLE_ATTRIBUTE_TYPE_IDREF,
XML_ROLE_ATTRIBUTE_TYPE_IDREFS,
XML_ROLE_ATTRIBUTE_TYPE_ENTITY,
XML_ROLE_ATTRIBUTE_TYPE_ENTITIES,
XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN,
XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS,
XML_ROLE_ATTRIBUTE_ENUM_VALUE,
XML_ROLE_ATTRIBUTE_NOTATION_VALUE,
XML_ROLE_ATTLIST_NONE,
XML_ROLE_ATTLIST_ELEMENT_NAME,
XML_ROLE_IMPLIED_ATTRIBUTE_VALUE,
XML_ROLE_REQUIRED_ATTRIBUTE_VALUE,
XML_ROLE_DEFAULT_ATTRIBUTE_VALUE,
XML_ROLE_FIXED_ATTRIBUTE_VALUE,
XML_ROLE_ELEMENT_NONE,
XML_ROLE_ELEMENT_NAME,
XML_ROLE_CONTENT_ANY,
XML_ROLE_CONTENT_EMPTY,
XML_ROLE_CONTENT_PCDATA,
XML_ROLE_GROUP_OPEN,
XML_ROLE_GROUP_CLOSE,
XML_ROLE_GROUP_CLOSE_REP,
XML_ROLE_GROUP_CLOSE_OPT,
XML_ROLE_GROUP_CLOSE_PLUS,
XML_ROLE_GROUP_CHOICE,
XML_ROLE_GROUP_SEQUENCE,
XML_ROLE_CONTENT_ELEMENT,
XML_ROLE_CONTENT_ELEMENT_REP,
XML_ROLE_CONTENT_ELEMENT_OPT,
XML_ROLE_CONTENT_ELEMENT_PLUS,
XML_ROLE_PI,
XML_ROLE_COMMENT,
#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
};
typedef struct prolog_state {
int (FASTCALL *handler) (struct prolog_state *state,
int tok,
const char *ptr,
const char *end,
const ENCODING *enc);
unsigned level;
int role_none;
#ifdef XML_DTD
unsigned includeLevel;
int documentEntity;
int inEntityValue;
#endif /* XML_DTD */
} PROLOG_STATE;
void XmlPrologStateInit(PROLOG_STATE *);
#ifdef XML_DTD
void XmlPrologStateInitExternalEntity(PROLOG_STATE *);
#endif /* XML_DTD */
#define XmlTokenRole(state, tok, ptr, end, enc) \
(((state)->handler)(state, tok, ptr, end, enc))
#ifdef __cplusplus
}
#endif
#endif /* not XmlRole_INCLUDED */

1632
contrib/expat/lib/xmltok.c Normal file
View File

File diff suppressed because it is too large Load Diff

312
contrib/expat/lib/xmltok.h Normal file
View File

@ -0,0 +1,312 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#ifndef XmlTok_INCLUDED
#define XmlTok_INCLUDED 1
#ifdef __cplusplus
extern "C" {
#endif
/* The following token may be returned by XmlContentTok */
#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be
start of illegal ]]> sequence */
/* The following tokens may be returned by both XmlPrologTok and
XmlContentTok.
*/
#define XML_TOK_NONE -4 /* The string to be scanned is empty */
#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan;
might be part of CRLF sequence */
#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */
#define XML_TOK_PARTIAL -1 /* only part of a token */
#define XML_TOK_INVALID 0
/* The following tokens are returned by XmlContentTok; some are also
returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok.
*/
#define XML_TOK_START_TAG_WITH_ATTS 1
#define XML_TOK_START_TAG_NO_ATTS 2
#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */
#define XML_TOK_EMPTY_ELEMENT_NO_ATTS 4
#define XML_TOK_END_TAG 5
#define XML_TOK_DATA_CHARS 6
#define XML_TOK_DATA_NEWLINE 7
#define XML_TOK_CDATA_SECT_OPEN 8
#define XML_TOK_ENTITY_REF 9
#define XML_TOK_CHAR_REF 10 /* numeric character reference */
/* The following tokens may be returned by both XmlPrologTok and
XmlContentTok.
*/
#define XML_TOK_PI 11 /* processing instruction */
#define XML_TOK_XML_DECL 12 /* XML decl or text decl */
#define XML_TOK_COMMENT 13
#define XML_TOK_BOM 14 /* Byte order mark */
/* The following tokens are returned only by XmlPrologTok */
#define XML_TOK_PROLOG_S 15
#define XML_TOK_DECL_OPEN 16 /* <!foo */
#define XML_TOK_DECL_CLOSE 17 /* > */
#define XML_TOK_NAME 18
#define XML_TOK_NMTOKEN 19
#define XML_TOK_POUND_NAME 20 /* #name */
#define XML_TOK_OR 21 /* | */
#define XML_TOK_PERCENT 22
#define XML_TOK_OPEN_PAREN 23
#define XML_TOK_CLOSE_PAREN 24
#define XML_TOK_OPEN_BRACKET 25
#define XML_TOK_CLOSE_BRACKET 26
#define XML_TOK_LITERAL 27
#define XML_TOK_PARAM_ENTITY_REF 28
#define XML_TOK_INSTANCE_START 29
/* The following occur only in element type declarations */
#define XML_TOK_NAME_QUESTION 30 /* name? */
#define XML_TOK_NAME_ASTERISK 31 /* name* */
#define XML_TOK_NAME_PLUS 32 /* name+ */
#define XML_TOK_COND_SECT_OPEN 33 /* <![ */
#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */
#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */
#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */
#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */
#define XML_TOK_COMMA 38
/* The following token is returned only by XmlAttributeValueTok */
#define XML_TOK_ATTRIBUTE_VALUE_S 39
/* The following token is returned only by XmlCdataSectionTok */
#define XML_TOK_CDATA_SECT_CLOSE 40
/* With namespace processing this is returned by XmlPrologTok 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
#define XML_ENTITY_VALUE_LITERAL 1
/* The size of the buffer passed to XmlUtf8Encode must be at least this. */
#define XML_UTF8_ENCODE_MAX 4
/* The size of the buffer passed to XmlUtf16Encode must be at least this. */
#define XML_UTF16_ENCODE_MAX 2
typedef struct position {
/* first line and first column are 0 not 1 */
unsigned long lineNumber;
unsigned long columnNumber;
} POSITION;
typedef struct {
const char *name;
const char *valuePtr;
const char *valueEnd;
char normalized;
} ATTRIBUTE;
struct encoding;
typedef struct encoding ENCODING;
typedef int (FASTCALL *SCANNER)(const ENCODING *,
const char *,
const char *,
const char **);
struct encoding {
SCANNER scanners[XML_N_STATES];
SCANNER literalScanners[XML_N_LITERAL_TYPES];
int (FASTCALL *sameName)(const ENCODING *,
const char *,
const char *);
int (FASTCALL *nameMatchesAscii)(const ENCODING *,
const char *,
const char *,
const char *);
int (FASTCALL *nameLength)(const ENCODING *, const char *);
const char *(FASTCALL *skipS)(const ENCODING *, const char *);
int (FASTCALL *getAtts)(const ENCODING *enc,
const char *ptr,
int attsMax,
ATTRIBUTE *atts);
int (FASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr);
int (FASTCALL *predefinedEntityName)(const ENCODING *,
const char *,
const char *);
void (FASTCALL *updatePosition)(const ENCODING *,
const char *ptr,
const char *end,
POSITION *);
int (FASTCALL *isPublicId)(const ENCODING *enc,
const char *ptr,
const char *end,
const char **badPtr);
void (FASTCALL *utf8Convert)(const ENCODING *enc,
const char **fromP,
const char *fromLim,
char **toP,
const char *toLim);
void (FASTCALL *utf16Convert)(const ENCODING *enc,
const char **fromP,
const char *fromLim,
unsigned short **toP,
const unsigned short *toLim);
int minBytesPerChar;
char isUtf8;
char isUtf16;
};
/* Scan the string starting at ptr until the end of the next complete
token, but do not scan past eptr. Return an integer giving the
type of token.
Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set.
Return XML_TOK_PARTIAL when the string does not contain a complete
token; nextTokPtr will not be set.
Return XML_TOK_INVALID when the string does not start a valid
token; nextTokPtr will be set to point to the character which made
the token invalid.
Otherwise the string starts with a valid token; nextTokPtr will be
set to point to the character following the end of that token.
Each data character counts as a single token, but adjacent data
characters may be returned together. Similarly for characters in
the prolog outside literals, comments and processing instructions.
*/
#define XmlTok(enc, state, ptr, end, nextTokPtr) \
(((enc)->scanners[state])(enc, ptr, end, nextTokPtr))
#define XmlPrologTok(enc, ptr, end, nextTokPtr) \
XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr)
#define XmlContentTok(enc, ptr, end, nextTokPtr) \
XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr)
#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.
*/
#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \
(((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr))
#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \
XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr)
#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \
XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr)
#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2))
#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \
(((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2))
#define XmlNameLength(enc, ptr) \
(((enc)->nameLength)(enc, ptr))
#define XmlSkipS(enc, ptr) \
(((enc)->skipS)(enc, ptr))
#define XmlGetAttributes(enc, ptr, attsMax, atts) \
(((enc)->getAtts)(enc, ptr, attsMax, atts))
#define XmlCharRefNumber(enc, ptr) \
(((enc)->charRefNumber)(enc, ptr))
#define XmlPredefinedEntityName(enc, ptr, end) \
(((enc)->predefinedEntityName)(enc, ptr, end))
#define XmlUpdatePosition(enc, ptr, end, pos) \
(((enc)->updatePosition)(enc, ptr, end, pos))
#define XmlIsPublicId(enc, ptr, end, badPtr) \
(((enc)->isPublicId)(enc, ptr, end, badPtr))
#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \
(((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim))
#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \
(((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim))
typedef struct {
ENCODING initEnc;
const ENCODING **encPtr;
} INIT_ENCODING;
int XmlParseXmlDecl(int isGeneralTextEntity,
const ENCODING *enc,
const char *ptr,
const char *end,
const char **badPtr,
const char **versionPtr,
const char **versionEndPtr,
const char **encodingNamePtr,
const ENCODING **namedEncodingPtr,
int *standalonePtr);
int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name);
const ENCODING *XmlGetUtf8InternalEncoding(void);
const ENCODING *XmlGetUtf16InternalEncoding(void);
int XmlUtf8Encode(int charNumber, char *buf);
int XmlUtf16Encode(int charNumber, unsigned short *buf);
int XmlSizeOfUnknownEncoding(void);
ENCODING *
XmlInitUnknownEncoding(void *mem,
int *table,
int (*conv)(void *userData, const char *p),
void *userData);
int XmlParseXmlDeclNS(int isGeneralTextEntity,
const ENCODING *enc,
const char *ptr,
const char *end,
const char **badPtr,
const char **versionPtr,
const char **versionEndPtr,
const char **encodingNamePtr,
const ENCODING **namedEncodingPtr,
int *standalonePtr);
int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name);
const ENCODING *XmlGetUtf8InternalEncodingNS(void);
const ENCODING *XmlGetUtf16InternalEncodingNS(void);
ENCODING *
XmlInitUnknownEncodingNS(void *mem,
int *table,
int (*conv)(void *userData, const char *p),
void *userData);
#ifdef __cplusplus
}
#endif
#endif /* not XmlTok_INCLUDED */

1778
contrib/expat/lib/xmltok_impl.c Normal file
View File

File diff suppressed because it is too large Load Diff

46
contrib/expat/lib/xmltok_impl.h Normal file
View File

@ -0,0 +1,46 @@
/*
Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
enum {
BT_NONXML,
BT_MALFORM,
BT_LT,
BT_AMP,
BT_RSQB,
BT_LEAD2,
BT_LEAD3,
BT_LEAD4,
BT_TRAIL,
BT_CR,
BT_LF,
BT_GT,
BT_QUOT,
BT_APOS,
BT_EQUALS,
BT_QUEST,
BT_EXCL,
BT_SOL,
BT_SEMI,
BT_NUM,
BT_LSQB,
BT_S,
BT_NMSTRT,
BT_COLON,
BT_HEX,
BT_DIGIT,
BT_NAME,
BT_MINUS,
BT_OTHER, /* known not to be a name or name start character */
BT_NONASCII, /* might be a name or name start character */
BT_PERCNT,
BT_LPAR,
BT_RPAR,
BT_AST,
BT_PLUS,
BT_COMMA,
BT_VERBAR
};
#include <stddef.h>

106
contrib/expat/lib/xmltok_ns.c Normal file
View File

@ -0,0 +1,106 @@
const ENCODING *
NS(XmlGetUtf8InternalEncoding)(void)
{
return &ns(internal_utf8_encoding).enc;
}
const ENCODING *
NS(XmlGetUtf16InternalEncoding)(void)
{
#if BYTEORDER == 1234
return &ns(internal_little2_encoding).enc;
#elif BYTEORDER == 4321
return &ns(internal_big2_encoding).enc;
#else
const short n = 1;
return (*(const char *)&n
? &ns(internal_little2_encoding).enc
: &ns(internal_big2_encoding).enc);
#endif
}
static const ENCODING *NS(encodings)[] = {
&ns(latin1_encoding).enc,
&ns(ascii_encoding).enc,
&ns(utf8_encoding).enc,
&ns(big2_encoding).enc,
&ns(big2_encoding).enc,
&ns(little2_encoding).enc,
&ns(utf8_encoding).enc /* NO_ENC */
};
static int FASTCALL
NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
return initScan(NS(encodings), (const INIT_ENCODING *)enc,
XML_PROLOG_STATE, ptr, end, nextTokPtr);
}
static int FASTCALL
NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
return initScan(NS(encodings), (const INIT_ENCODING *)enc,
XML_CONTENT_STATE, ptr, end, nextTokPtr);
}
int
NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr,
const char *name)
{
int i = getEncodingIndex(name);
if (i == UNKNOWN_ENC)
return 0;
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;
p->encPtr = encPtr;
*encPtr = &(p->initEnc);
return 1;
}
static const ENCODING *
NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end)
{
#define ENCODING_MAX 128
char buf[ENCODING_MAX];
char *p = buf;
int i;
XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1);
if (ptr != end)
return 0;
*p = 0;
if (streqci(buf, KW_UTF_16) && enc->minBytesPerChar == 2)
return enc;
i = getEncodingIndex(buf);
if (i == UNKNOWN_ENC)
return 0;
return NS(encodings)[i];
}
int
NS(XmlParseXmlDecl)(int isGeneralTextEntity,
const ENCODING *enc,
const char *ptr,
const char *end,
const char **badPtr,
const char **versionPtr,
const char **versionEndPtr,
const char **encodingName,
const ENCODING **encoding,
int *standalone)
{
return doParseXmlDecl(NS(findEncoding),
isGeneralTextEntity,
enc,
ptr,
end,
badPtr,
versionPtr,
versionEndPtr,
encodingName,
encoding,
standalone);
}

14
contrib/expat/tests/README.txt Normal file
View File

@ -0,0 +1,14 @@
This directory contains the (fledgling) test suite for Expat. The
tests provide general unit testing and regression coverage. The tests
are not expected to be useful examples of Expat usage; see the
examples/ directory for that.
The Expat tests use the "Check" unit testing framework for C. More
information on Check can be found at:
http://check.sourceforge.net/
Check 0.8 must be installed before the unit tests can be compiled & run.
Since both Check and this test suite are young, it can all change in a
later version.

122
contrib/expat/tests/chardata.c Normal file
View File

@ -0,0 +1,122 @@
/* chardata.c
*
*
*/
#include <assert.h>
#include <check.h>
#include <stdio.h>
#include <string.h>
#include "chardata.h"
static int
xmlstrlen(const XML_Char *s)
{
int len = 0;
assert(s != NULL);
while (s[len] != 0)
++len;
return len;
}
void
CharData_Init(CharData *storage)
{
assert(storage != NULL);
storage->count = -1;
}
void
CharData_AppendString(CharData *storage, const char *s)
{
int maxchars = sizeof(storage->data) / sizeof(storage->data[0]);
int len;
assert(s != NULL);
len = strlen(s);
if (storage->count < 0)
storage->count = 0;
if ((len + storage->count) > maxchars) {
len = (maxchars - storage->count);
}
if (len + storage->count < sizeof(storage->data)) {
memcpy(storage->data + storage->count, s, len);
storage->count += len;
}
}
void
CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len)
{
int maxchars;
assert(storage != NULL);
assert(s != NULL);
maxchars = sizeof(storage->data) / sizeof(storage->data[0]);
if (storage->count < 0)
storage->count = 0;
if (len < 0)
len = xmlstrlen(s);
if ((len + storage->count) > maxchars) {
len = (maxchars - storage->count);
}
if (len + storage->count < sizeof(storage->data)) {
memcpy(storage->data + storage->count, s,
len * sizeof(storage->data[0]));
storage->count += len;
}
}
int
CharData_CheckString(CharData *storage, const char *expected)
{
char buffer[1280];
int len;
int count;
assert(storage != NULL);
assert(expected != NULL);
count = (storage->count < 0) ? 0 : storage->count;
len = strlen(expected);
if (len != count) {
if (sizeof(XML_Char) == 1)
sprintf(buffer, "wrong number of data characters:"
" got %d, expected %d:\n%s", count, len, storage->data);
else
sprintf(buffer,
"wrong number of data characters: got %d, expected %d",
count, len);
fail(buffer);
return 0;
}
if (memcmp(expected, storage->data, len) != 0) {
fail("got bad data bytes");
return 0;
}
return 1;
}
int
CharData_CheckXMLChars(CharData *storage, const XML_Char *expected)
{
char buffer[1024];
int len = xmlstrlen(expected);
int count;
assert(storage != NULL);
count = (storage->count < 0) ? 0 : storage->count;
if (len != count) {
sprintf(buffer, "wrong number of data characters: got %d, expected %d",
count, len);
fail(buffer);
return 0;
}
if (memcmp(expected, storage->data, len * sizeof(storage->data[0])) != 0) {
fail("got bad data bytes");
return 0;
}
return 1;
}

32
contrib/expat/tests/chardata.h Normal file
View File

@ -0,0 +1,32 @@
/* chardata.h
Interface to some helper routines used to accumulate and check text
and attribute content.
*/
#ifndef XML_CHARDATA_H
#define XML_CHARDATA_H 1
#ifndef XML_VERSION
#include "expat.h" /* need XML_Char */
#endif
typedef struct {
int count; /* # of chars, < 0 if not set */
XML_Char data[1024];
} CharData;
void CharData_Init(CharData *storage);
void CharData_AppendString(CharData *storage, const char *s);
void CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len);
int CharData_CheckString(CharData *storage, const char *s);
int CharData_CheckXMLChars(CharData *storage, const XML_Char *s);
#endif /* XML_CHARDATA_H */

882
contrib/expat/tests/runtests.c Normal file
View File

@ -0,0 +1,882 @@
#include <assert.h>
#include <check.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "expat.h"
#include "chardata.h"
static XML_Parser parser;
static void
basic_setup(void)
{
parser = XML_ParserCreate(NULL);
if (parser == NULL)
fail("Parser not created.");
}
static void
basic_teardown(void)
{
if (parser != NULL)
XML_ParserFree(parser);
}
/* Generate a failure using the parser state to create an error message;
this should be used when the parser reports an error we weren't
expecting.
*/
static void
_xml_failure(XML_Parser parser, const char *file, int line)
{
char buffer[1024];
sprintf(buffer,
"\n %s (line %d, offset %d)\n reported from %s, line %d",
XML_ErrorString(XML_GetErrorCode(parser)),
XML_GetCurrentLineNumber(parser),
XML_GetCurrentColumnNumber(parser),
file, line);
fail(buffer);
}
#define xml_failure(parser) _xml_failure((parser), __FILE__, __LINE__)
static void
_expect_failure(char *text, enum XML_Error errorCode, char *errorMessage,
char *file, int lineno)
{
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_OK)
fail(errorMessage);
if (XML_GetErrorCode(parser) != errorCode)
_xml_failure(parser, file, lineno);
}
#define expect_failure(text, errorCode, errorMessage) \
_expect_failure((text), (errorCode), (errorMessage), \
__FILE__, __LINE__)
/*
* Character & encoding tests.
*/
START_TEST(test_nul_byte)
{
char text[] = "<doc>\0</doc>";
/* test that a NUL byte (in US-ASCII data) is an error */
if (XML_Parse(parser, text, sizeof(text) - 1, 1) == XML_STATUS_OK)
fail("Parser did not report error on NUL-byte.");
if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)
xml_failure(parser);
}
END_TEST
START_TEST(test_u0000_char)
{
/* test that a NUL byte (in US-ASCII data) is an error */
expect_failure("<doc>&#0;</doc>",
XML_ERROR_BAD_CHAR_REF,
"Parser did not report error on NUL-byte.");
}
END_TEST
START_TEST(test_bom_utf8)
{
/* This test is really just making sure we don't core on a UTF-8 BOM. */
char *text = "\357\273\277<e/>";
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
START_TEST(test_bom_utf16_be)
{
char text[] = "\376\377\0<\0e\0/\0>";
if (XML_Parse(parser, text, sizeof(text) - 1, 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
START_TEST(test_bom_utf16_le)
{
char text[] = "\377\376<\0e\0/\0>\0";
if (XML_Parse(parser, text, sizeof(text) - 1, 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
static void
accumulate_characters(void *userData, const XML_Char *s, int len)
{
CharData_AppendXMLChars((CharData *)userData, s, len);
}
static void
accumulate_attribute(void *userData, const XML_Char *name,
const XML_Char **atts)
{
CharData *storage = (CharData *)userData;
if (storage->count < 0 && atts != NULL && atts[0] != NULL) {
/* "accumulate" the value of the first attribute we see */
CharData_AppendXMLChars(storage, atts[1], -1);
}
}
static void
run_character_check(XML_Char *text, XML_Char *expected)
{
CharData storage;
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetCharacterDataHandler(parser, accumulate_characters);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
CharData_CheckXMLChars(&storage, expected);
}
static void
run_attribute_check(XML_Char *text, XML_Char *expected)
{
CharData storage;
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetStartElementHandler(parser, accumulate_attribute);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
CharData_CheckXMLChars(&storage, expected);
}
/* Regression test for SF bug #491986. */
START_TEST(test_danish_latin1)
{
char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<e>Jørgen æøåÆØÅ</e>";
run_character_check(text,
"J\xC3\xB8rgen \xC3\xA6\xC3\xB8\xC3\xA5\xC3\x86\xC3\x98\xC3\x85");
}
END_TEST
/* Regression test for SF bug #514281. */
START_TEST(test_french_charref_hexidecimal)
{
char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>&#xE9;&#xE8;&#xE0;&#xE7;&#xEA;&#xC8;</doc>";
run_character_check(text,
"\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
}
END_TEST
START_TEST(test_french_charref_decimal)
{
char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>&#233;&#232;&#224;&#231;&#234;&#200;</doc>";
run_character_check(text,
"\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
}
END_TEST
START_TEST(test_french_latin1)
{
char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>\xE9\xE8\xE0\xE7\xEa\xC8</doc>";
run_character_check(text,
"\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
}
END_TEST
START_TEST(test_french_utf8)
{
char *text =
"<?xml version='1.0' encoding='utf-8'?>\n"
"<doc>\xC3\xA9</doc>";
run_character_check(text, "\xC3\xA9");
}
END_TEST
/* Regression test for SF bug #600479.
XXX There should be a test that exercises all legal XML Unicode
characters as PCDATA and attribute value content, and XML Name
characters as part of element and attribute names.
*/
START_TEST(test_utf8_false_rejection)
{
char *text = "<doc>\xEF\xBA\xBF</doc>";
run_character_check(text, "\xEF\xBA\xBF");
}
END_TEST
/* Regression test for SF bug #477667.
This test assures that any 8-bit character followed by a 7-bit
character will not be mistakenly interpreted as a valid UTF-8
sequence.
*/
START_TEST(test_illegal_utf8)
{
char text[100];
int i;
for (i = 128; i <= 255; ++i) {
sprintf(text, "<e>%ccd</e>", i);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_OK) {
sprintf(text,
"expected token error for '%c' (ordinal %d) in UTF-8 text",
i, i);
fail(text);
}
else if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)
xml_failure(parser);
/* Reset the parser since we use the same parser repeatedly. */
XML_ParserReset(parser, NULL);
}
}
END_TEST
START_TEST(test_utf16)
{
/* <?xml version="1.0" encoding="UTF-16"?>
<doc a='123'>some text</doc>
*/
char text[] =
"\000<\000?\000x\000m\000\154\000 \000v\000e\000r\000s\000i\000o"
"\000n\000=\000'\0001\000.\000\060\000'\000 \000e\000n\000c\000o"
"\000d\000i\000n\000g\000=\000'\000U\000T\000F\000-\0001\000\066"
"\000'\000?\000>\000\n"
"\000<\000d\000o\000c\000 \000a\000=\000'\0001\0002\0003\000'"
"\000>\000s\000o\000m\000e\000 \000t\000e\000x\000t\000<\000/"
"\000d\000o\000c\000>";
if (XML_Parse(parser, text, sizeof(text) - 1, 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
START_TEST(test_utf16_le_epilog_newline)
{
int first_chunk_bytes = 17;
char text[] =
"\xFF\xFE" /* BOM */
"<\000e\000/\000>\000" /* document element */
"\r\000\n\000\r\000\n\000"; /* epilog */
if (first_chunk_bytes >= sizeof(text) - 1)
fail("bad value of first_chunk_bytes");
if (XML_Parse(parser, text, first_chunk_bytes, 0) == XML_STATUS_ERROR)
xml_failure(parser);
else {
enum XML_Status rc;
rc = XML_Parse(parser, text + first_chunk_bytes,
sizeof(text) - first_chunk_bytes - 1, 1);
if (rc == XML_STATUS_ERROR)
xml_failure(parser);
}
}
END_TEST
/* Regression test for SF bug #481609. */
START_TEST(test_latin1_umlauts)
{
char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<e a='ä ö ü &#228; &#246; &#252; &#x00E4; &#x0F6; &#xFC;'\n"
" >ä ö ü &#228; &#246; &#252; &#x00E4; &#x0F6; &#xFC;</e>";
char *utf8 =
"\xC3\xA4 \xC3\xB6 \xC3\xBC "
"\xC3\xA4 \xC3\xB6 \xC3\xBC "
"\xC3\xA4 \xC3\xB6 \xC3\xBC";
run_character_check(text, utf8);
XML_ParserReset(parser, NULL);
run_attribute_check(text, utf8);
}
END_TEST
/* Regression test for SF bug #422239 (maybe).
It's not clear that this reproduces enough of the context
of the reported bug.
*/
START_TEST(test_line_count)
{
char *text =
"<e>\n"
" <e/>\n"
"</e>";
int lineno;
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
lineno = XML_GetCurrentLineNumber(parser);
if (lineno != 3) {
char buffer[100];
sprintf(buffer, "expected 3 lines, saw %d", lineno);
fail(buffer);
}
}
END_TEST
/* Regression test for SF bug #478332. */
START_TEST(test_really_long_lines)
{
/* This parses an input line longer than INIT_DATA_BUF_SIZE
characters long (defined to be 1024 in xmlparse.c). We take a
really cheesy approach to building the input buffer, because
this avoids writing bugs in buffer-filling code.
*/
char *text =
"<e>"
/* 64 chars */
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
/* until we have at least 1024 characters on the line: */
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
"</e>";
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
/*
* Element event tests.
*/
static void
end_element_event_handler(void *userData, const XML_Char *name)
{
CharData *storage = (CharData *) userData;
CharData_AppendString(storage, "/");
CharData_AppendXMLChars(storage, name, -1);
}
START_TEST(test_end_element_events)
{
char *text = "<a><b><c/></b><d><f/></d></a>";
char *expected = "/c/b/f/d/a";
CharData storage;
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetEndElementHandler(parser, end_element_event_handler);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
CharData_CheckString(&storage, expected);
}
END_TEST
/*
* Attribute tests.
*/
/* Helpers used by the following test; this checks any "attr" and "refs"
attributes to make sure whitespace has been normalized.
Return true if whitespace has been normalized in a string, using
the rules for attribute value normalization. The 'is_cdata' flag
is needed since CDATA attributes don't need to have multiple
whitespace characters collapsed to a single space, while other
attribute data types do. (Section 3.3.3 of the recommendation.)
*/
static int
is_whitespace_normalized(const XML_Char *s, int is_cdata)
{
int blanks = 0;
int at_start = 1;
while (*s) {
if (*s == ' ')
++blanks;
else if (*s == '\t' || *s == '\n' || *s == '\r')
return 0;
else {
if (at_start) {
at_start = 0;
if (blanks && !is_cdata)
/* illegal leading blanks */
return 0;
}
else if (blanks > 1 && !is_cdata)
return 0;
blanks = 0;
}
++s;
}
if (blanks && !is_cdata)
return 0;
return 1;
}
/* Check the attribute whitespace checker: */
static void
testhelper_is_whitespace_normalized(void)
{
assert(is_whitespace_normalized("abc", 0));
assert(is_whitespace_normalized("abc", 1));
assert(is_whitespace_normalized("abc def ghi", 0));
assert(is_whitespace_normalized("abc def ghi", 1));
assert(!is_whitespace_normalized(" abc def ghi", 0));
assert(is_whitespace_normalized(" abc def ghi", 1));
assert(!is_whitespace_normalized("abc def ghi", 0));
assert(is_whitespace_normalized("abc def ghi", 1));
assert(!is_whitespace_normalized("abc def ghi ", 0));
assert(is_whitespace_normalized("abc def ghi ", 1));
assert(!is_whitespace_normalized(" ", 0));
assert(is_whitespace_normalized(" ", 1));
assert(!is_whitespace_normalized("\t", 0));
assert(!is_whitespace_normalized("\t", 1));
assert(!is_whitespace_normalized("\n", 0));
assert(!is_whitespace_normalized("\n", 1));
assert(!is_whitespace_normalized("\r", 0));
assert(!is_whitespace_normalized("\r", 1));
assert(!is_whitespace_normalized("abc\t def", 1));
}
static void
check_attr_contains_normalized_whitespace(void *userData,
const XML_Char *name,
const XML_Char **atts)
{
int i;
for (i = 0; atts[i] != NULL; i += 2) {
const XML_Char *attrname = atts[i];
const XML_Char *value = atts[i + 1];
if (strcmp("attr", attrname) == 0
|| strcmp("ents", attrname) == 0
|| strcmp("refs", attrname) == 0) {
if (!is_whitespace_normalized(value, 0)) {
char buffer[256];
sprintf(buffer, "attribute value not normalized: %s='%s'",
attrname, value);
fail(buffer);
}
}
}
}
START_TEST(test_attr_whitespace_normalization)
{
char *text =
"<!DOCTYPE doc [\n"
" <!ATTLIST doc\n"
" attr NMTOKENS #REQUIRED\n"
" ents ENTITIES #REQUIRED\n"
" refs IDREFS #REQUIRED>\n"
"]>\n"
"<doc attr=' a b c\t\td\te\t' refs=' id-1 \t id-2\t\t' \n"
" ents=' ent-1 \t\r\n"
" ent-2 ' >\n"
" <e id='id-1'/>\n"
" <e id='id-2'/>\n"
"</doc>";
XML_SetStartElementHandler(parser,
check_attr_contains_normalized_whitespace);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
/*
* XML declaration tests.
*/
START_TEST(test_xmldecl_misplaced)
{
expect_failure("\n"
"<?xml version='1.0'?>\n"
"<a/>",
XML_ERROR_MISPLACED_XML_PI,
"failed to report misplaced XML declaration");
}
END_TEST
/* Regression test for SF bug #584832. */
static int
UnknownEncodingHandler(void *data,const XML_Char *encoding,XML_Encoding *info)
{
if (strcmp(encoding,"unsupported-encoding") == 0) {
int i;
for (i = 0; i < 256; ++i)
info->map[i] = i;
info->data=NULL;
info->convert=NULL;
info->release=NULL;
return 1;
}
return 0;
}
START_TEST(test_unknown_encoding_internal_entity)
{
char *text =
"<?xml version='1.0' encoding='unsupported-encoding'?>\n"
"<!DOCTYPE test [<!ENTITY foo 'bar'>]>\n"
"<test a='&foo;'/>";
XML_SetUnknownEncodingHandler(parser, UnknownEncodingHandler, NULL);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
/* Test that no error is reported for unknown entities if we don't
read an external subset. This was fixed in Expat 1.95.5.
*/
START_TEST(test_wfc_undeclared_entity_unread_external_subset) {
char *text =
"<!DOCTYPE doc SYSTEM 'foo'>\n"
"<doc>&entity;</doc>";
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
/* Test that an error is reported for unknown entities if we don't
have an external subset.
*/
START_TEST(test_wfc_undeclared_entity_no_external_subset) {
expect_failure("<doc>&entity;</doc>",
XML_ERROR_UNDEFINED_ENTITY,
"Parser did not report undefined entity w/out a DTD.");
}
END_TEST
/* Test that an error is reported for unknown entities if we don't
read an external subset, but have been declared standalone.
*/
START_TEST(test_wfc_undeclared_entity_standalone) {
char *text =
"<?xml version='1.0' encoding='us-ascii' standalone='yes'?>\n"
"<!DOCTYPE doc SYSTEM 'foo'>\n"
"<doc>&entity;</doc>";
expect_failure(text,
XML_ERROR_UNDEFINED_ENTITY,
"Parser did not report undefined entity (standalone).");
}
END_TEST
static int
external_entity_loader(XML_Parser parser,
const XML_Char *context,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId)
{
char *text = (char *)XML_GetUserData(parser);
XML_Parser extparser;
extparser = XML_ExternalEntityParserCreate(parser, context, NULL);
if (extparser == NULL)
fail("Could not create external entity parser.");
if (XML_Parse(extparser, text, strlen(text), 1) == XML_STATUS_ERROR) {
xml_failure(parser);
return 0;
}
return 1;
}
/* Test that an error is reported for unknown entities if we have read
an external subset.
*/
START_TEST(test_wfc_undeclared_entity_with_external_subset) {
char *text =
"<?xml version='1.0' encoding='us-ascii'?>\n"
"<!DOCTYPE doc SYSTEM 'foo'>\n"
"<doc>&entity;</doc>";
char *foo_text =
"<!ELEMENT doc (#PCDATA)*>";
XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
XML_SetUserData(parser, foo_text);
XML_SetExternalEntityRefHandler(parser, external_entity_loader);
expect_failure(text,
XML_ERROR_UNDEFINED_ENTITY,
"Parser did not report undefined entity with DTD.");
}
END_TEST
START_TEST(test_wfc_no_recursive_entity_refs)
{
char *text =
"<!DOCTYPE doc [\n"
" <!ENTITY entity '&#38;entity;'>\n"
"]>\n"
"<doc>&entity;</doc>";
expect_failure(text,
XML_ERROR_RECURSIVE_ENTITY_REF,
"Parser did not report recursive entity reference.");
}
END_TEST
/*
* Namespaces tests.
*/
static void
namespace_setup(void)
{
parser = XML_ParserCreateNS(NULL, ' ');
if (parser == NULL)
fail("Parser not created.");
}
static void
namespace_teardown(void)
{
basic_teardown();
}
/* Check that an element name and attribute name match the expected values.
The expected values are passed as an array reference of string pointers
provided as the userData argument; the first is the expected
element name, and the second is the expected attribute name.
*/
static void
triplet_start_checker(void *userData, const XML_Char *name,
const XML_Char **atts)
{
char **elemstr = (char **)userData;
char buffer[1024];
if (strcmp(elemstr[0], name) != 0) {
sprintf(buffer, "unexpected start string: '%s'", name);
fail(buffer);
}
if (strcmp(elemstr[1], atts[0]) != 0) {
sprintf(buffer, "unexpected attribute string: '%s'", atts[0]);
fail(buffer);
}
}
/* Check that the element name passed to the end-element handler matches
the expected value. The expected value is passed as the first element
in an array of strings passed as the userData argument.
*/
static void
triplet_end_checker(void *userData, const XML_Char *name)
{
char **elemstr = (char **)userData;
if (strcmp(elemstr[0], name) != 0) {
char buffer[1024];
sprintf(buffer, "unexpected end string: '%s'", name);
fail(buffer);
}
}
START_TEST(test_return_ns_triplet)
{
char *text =
"<foo:e xmlns:foo='http://expat.sf.net/' bar:a='12'\n"
" xmlns:bar='http://expat.sf.net/'></foo:e>";
char *elemstr[] = {
"http://expat.sf.net/ e foo",
"http://expat.sf.net/ a bar"
};
XML_SetReturnNSTriplet(parser, 1);
XML_SetUserData(parser, elemstr);
XML_SetElementHandler(parser, triplet_start_checker, triplet_end_checker);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
}
END_TEST
static void
overwrite_start_checker(void *userData, const XML_Char *name,
const XML_Char **atts)
{
CharData *storage = (CharData *) userData;
CharData_AppendString(storage, "start ");
CharData_AppendXMLChars(storage, name, -1);
while (*atts != NULL) {
CharData_AppendString(storage, "\nattribute ");
CharData_AppendXMLChars(storage, *atts, -1);
atts += 2;
}
CharData_AppendString(storage, "\n");
}
static void
overwrite_end_checker(void *userData, const XML_Char *name)
{
CharData *storage = (CharData *) userData;
CharData_AppendString(storage, "end ");
CharData_AppendXMLChars(storage, name, -1);
CharData_AppendString(storage, "\n");
}
static void
run_ns_tagname_overwrite_test(char *text, char *result)
{
CharData storage;
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetElementHandler(parser,
overwrite_start_checker, overwrite_end_checker);
if (XML_Parse(parser, text, strlen(text), 1) == XML_STATUS_ERROR)
xml_failure(parser);
CharData_CheckString(&storage, result);
}
/* Regression test for SF bug #566334. */
START_TEST(test_ns_tagname_overwrite)
{
char *text =
"<n:e xmlns:n='http://xml.libexpat.org/'>\n"
" <n:f n:attr='foo'/>\n"
" <n:g n:attr2='bar'/>\n"
"</n:e>";
char *result =
"start http://xml.libexpat.org/ e\n"
"start http://xml.libexpat.org/ f\n"
"attribute http://xml.libexpat.org/ attr\n"
"end http://xml.libexpat.org/ f\n"
"start http://xml.libexpat.org/ g\n"
"attribute http://xml.libexpat.org/ attr2\n"
"end http://xml.libexpat.org/ g\n"
"end http://xml.libexpat.org/ e\n";
run_ns_tagname_overwrite_test(text, result);
}
END_TEST
/* Regression test for SF bug #566334. */
START_TEST(test_ns_tagname_overwrite_triplet)
{
char *text =
"<n:e xmlns:n='http://xml.libexpat.org/'>\n"
" <n:f n:attr='foo'/>\n"
" <n:g n:attr2='bar'/>\n"
"</n:e>";
char *result =
"start http://xml.libexpat.org/ e n\n"
"start http://xml.libexpat.org/ f n\n"
"attribute http://xml.libexpat.org/ attr n\n"
"end http://xml.libexpat.org/ f n\n"
"start http://xml.libexpat.org/ g n\n"
"attribute http://xml.libexpat.org/ attr2 n\n"
"end http://xml.libexpat.org/ g n\n"
"end http://xml.libexpat.org/ e n\n";
XML_SetReturnNSTriplet(parser, 1);
run_ns_tagname_overwrite_test(text, result);
}
END_TEST
static Suite *
make_basic_suite(void)
{
Suite *s = suite_create("basic");
TCase *tc_basic = tcase_create("basic tests");
TCase *tc_namespace = tcase_create("XML namespaces");
suite_add_tcase(s, tc_basic);
tcase_add_checked_fixture(tc_basic, basic_setup, basic_teardown);
tcase_add_test(tc_basic, test_nul_byte);
tcase_add_test(tc_basic, test_u0000_char);
tcase_add_test(tc_basic, test_bom_utf8);
tcase_add_test(tc_basic, test_bom_utf16_be);
tcase_add_test(tc_basic, test_bom_utf16_le);
tcase_add_test(tc_basic, test_illegal_utf8);
tcase_add_test(tc_basic, test_utf16);
tcase_add_test(tc_basic, test_utf16_le_epilog_newline);
tcase_add_test(tc_basic, test_latin1_umlauts);
/* Regression test for SF bug #491986. */
tcase_add_test(tc_basic, test_danish_latin1);
/* Regression test for SF bug #514281. */
tcase_add_test(tc_basic, test_french_charref_hexidecimal);
tcase_add_test(tc_basic, test_french_charref_decimal);
tcase_add_test(tc_basic, test_french_latin1);
tcase_add_test(tc_basic, test_french_utf8);
tcase_add_test(tc_basic, test_utf8_false_rejection);
tcase_add_test(tc_basic, test_line_count);
tcase_add_test(tc_basic, test_really_long_lines);
tcase_add_test(tc_basic, test_end_element_events);
tcase_add_test(tc_basic, test_attr_whitespace_normalization);
tcase_add_test(tc_basic, test_xmldecl_misplaced);
tcase_add_test(tc_basic, test_unknown_encoding_internal_entity);
tcase_add_test(tc_basic,
test_wfc_undeclared_entity_unread_external_subset);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_no_external_subset);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_standalone);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_with_external_subset);
tcase_add_test(tc_basic, test_wfc_no_recursive_entity_refs);
suite_add_tcase(s, tc_namespace);
tcase_add_checked_fixture(tc_namespace,
namespace_setup, namespace_teardown);
tcase_add_test(tc_namespace, test_return_ns_triplet);
tcase_add_test(tc_namespace, test_ns_tagname_overwrite);
tcase_add_test(tc_namespace, test_ns_tagname_overwrite_triplet);
return s;
}
int
main(int argc, char *argv[])
{
int i, nf;
int forking = 0, forking_set = 0;
int verbosity = CK_NORMAL;
Suite *s = make_basic_suite();
SRunner *sr = srunner_create(s);
/* run the tests for internal helper functions */
testhelper_is_whitespace_normalized();
for (i = 1; i < argc; ++i) {
char *opt = argv[i];
if (strcmp(opt, "-v") == 0 || strcmp(opt, "--verbose") == 0)
verbosity = CK_VERBOSE;
else if (strcmp(opt, "-q") == 0 || strcmp(opt, "--quiet") == 0)
verbosity = CK_SILENT;
else if (strcmp(opt, "-f") == 0 || strcmp(opt, "--fork") == 0) {
forking = 1;
forking_set = 1;
}
else if (strcmp(opt, "-n") == 0 || strcmp(opt, "--no-fork") == 0) {
forking = 0;
forking_set = 1;
}
else {
fprintf(stderr, "runtests: unknown option '%s'\n", opt);
return 2;
}
}
if (forking_set)
srunner_set_fork_status(sr, forking ? CK_FORK : CK_NOFORK);
srunner_run_all(sr, verbosity);
nf = srunner_ntests_failed(sr);
srunner_free(sr);
suite_free(s);
return (nf == 0) ? EXIT_SUCCESS : EXIT_FAILURE;
}

137
contrib/expat/tests/xmltest.sh Executable file
View File

@ -0,0 +1,137 @@
#! /bin/sh
# EXPAT TEST SCRIPT FOR W3C XML TEST SUITE
# This script can be used to exercise Expat against the
# w3c.org xml test suite, available from
# http://www.w3.org/XML/Test/xmlts20020606.zip.
# To run this script, first set XMLWF so that xmlwf can be
# found, then set the output directory with OUTPUT.
# The script lists all test cases where Expat shows a discrepancy
# from the expected result. Test cases where only the canonical
# output differs are prefixed with "Output differs:", and a diff file
# is generated in the appropriate subdirectory under $OUTPUT.
# If there are output files provided, the script will use
# output from xmlwf and compare the desired output against it.
# However, one has to take into account that the canonical output
# produced by xmlwf conforms to an older definition of canonical XML
# and does not generate notation declarations.
MYDIR="`dirname \"$0\"`"
cd "$MYDIR"
MYDIR="`pwd`"
XMLWF="`dirname \"$MYDIR\"`/xmlwf/xmlwf"
# XMLWF=/usr/local/bin/xmlwf
TS="$MYDIR/XML-Test-Suite"
# OUTPUT must terminate with the directory separator.
OUTPUT="$TS/out/"
# OUTPUT=/home/tmp/xml-testsuite-out/
RunXmlwfNotWF() {
$XMLWF $1 $2 > outfile || return $?
read outdata < outfile
if test "$outdata" = "" ; then
echo "Well formed: $3$2"
return 1
else
return 0
fi
}
RunXmlwfWF() {
$XMLWF $1 -d "$OUTPUT$3" $2 > outfile || return $?
read outdata < outfile
if test "$outdata" = "" ; then
if [ -f out/$2 ] ; then
diff "$OUTPUT$3$2" out/$2 > outfile
if [ -s outfile ] ; then
cp outfile $OUTPUT$3${2}.diff
echo "Output differs: $3$2"
return 1
fi
fi
return 0
else
echo "In $3: $outdata"
return 1
fi
}
SUCCESS=0
ERROR=0
##########################
# well-formed test cases #
##########################
cd "$TS/xmlconf"
for xmldir in ibm/valid/P*/ \
ibm/invalid/P*/ \
xmltest/valid/ext-sa/ \
xmltest/valid/not-sa/ \
xmltest/invalid/ \
xmltest/invalid/not-sa/ \
xmltest/valid/sa/ \
sun/valid/ \
sun/invalid/ ; do
cd "$TS/xmlconf/$xmldir"
mkdir -p "$OUTPUT$xmldir"
for xmlfile in *.xml ; do
if RunXmlwfWF -p "$xmlfile" "$xmldir" ; then
SUCCESS=`expr $SUCCESS + 1`
else
ERROR=`expr $ERROR + 1`
fi
done
rm outfile
done
cd "$TS/xmlconf/oasis"
mkdir -p "$OUTPUT"oasis/
for xmlfile in *pass*.xml ; do
if RunXmlwfWF -p "$xmlfile" "oasis/" ; then
SUCCESS=`expr $SUCCESS + 1`
else
ERROR=`expr $ERROR + 1`
fi
done
rm outfile
##############################
# not well-formed test cases #
##############################
cd "$TS/xmlconf"
for xmldir in ibm/not-wf/P*/ \
ibm/not-wf/misc/ \
xmltest/not-wf/ext-sa/ \
xmltest/not-wf/not-sa/ \
xmltest/not-wf/sa/ \
sun/not-wf/ ; do
cd "$TS/xmlconf/$xmldir"
for xmlfile in *.xml ; do
if RunXmlwfNotWF -p "$xmlfile" "$xmldir" ; then
SUCCESS=`expr $SUCCESS + 1`
else
ERROR=`expr $ERROR + 1`
fi
done
rm outfile
done
cd "$TS/xmlconf/oasis"
for xmlfile in *fail*.xml ; do
if RunXmlwfNotWF -p "$xmlfile" "oasis/" ; then
SUCCESS=`expr $SUCCESS + 1`
else
ERROR=`expr $ERROR + 1`
fi
done
rm outfile
echo "Passed: $SUCCESS"
echo "Failed: $ERROR"

68
contrib/expat/xmlwf/codepage.c Executable file
View File

@ -0,0 +1,68 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include "codepage.h"
#ifdef WIN32
#define STRICT 1
#define WIN32_LEAN_AND_MEAN 1
#include <windows.h>
int
codepageMap(int cp, int *map)
{
int i;
CPINFO info;
if (!GetCPInfo(cp, &info) || info.MaxCharSize > 2)
return 0;
for (i = 0; i < 256; i++)
map[i] = -1;
if (info.MaxCharSize > 1) {
for (i = 0; i < MAX_LEADBYTES; i++) {
int j, lim;
if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0)
break;
lim = info.LeadByte[i + 1];
for (j = info.LeadByte[i]; j < lim; j++)
map[j] = -2;
}
}
for (i = 0; i < 256; i++) {
if (map[i] == -1) {
char c = (char)i;
unsigned short n;
if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
&c, 1, &n, 1) == 1)
map[i] = n;
}
}
return 1;
}
int
codepageConvert(int cp, const char *p)
{
unsigned short c;
if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
p, 2, &c, 1) == 1)
return c;
return -1;
}
#else /* not WIN32 */
int
codepageMap(int cp, int *map)
{
return 0;
}
int
codepageConvert(int cp, const char *p)
{
return -1;
}
#endif /* not WIN32 */

6
contrib/expat/xmlwf/codepage.h Executable file
View File

@ -0,0 +1,6 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
int codepageMap(int cp, int *map);
int codepageConvert(int cp, const char *p);

147
contrib/expat/xmlwf/ct.c Executable file
View File

@ -0,0 +1,147 @@
#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;
}

17
contrib/expat/xmlwf/filemap.h Executable file
View File

@ -0,0 +1,17 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include <stddef.h>
#ifdef XML_UNICODE
int filemap(const wchar_t *name,
void (*processor)(const void *, size_t,
const wchar_t *, void *arg),
void *arg);
#else
int filemap(const char *name,
void (*processor)(const void *, size_t,
const char *, void *arg),
void *arg);
#endif

76
contrib/expat/xmlwf/readfilemap.c Executable file
View File

@ -0,0 +1,76 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <stdlib.h>
#include <stdio.h>
#ifndef S_ISREG
#ifndef S_IFREG
#define S_IFREG _S_IFREG
#endif
#ifndef S_IFMT
#define S_IFMT _S_IFMT
#endif
#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
#endif /* not S_ISREG */
#ifndef O_BINARY
#ifdef _O_BINARY
#define O_BINARY _O_BINARY
#else
#define O_BINARY 0
#endif
#endif
#include "filemap.h"
int
filemap(const char *name,
void (*processor)(const void *, size_t, const char *, void *arg),
void *arg)
{
size_t nbytes;
int fd;
int n;
struct stat sb;
void *p;
fd = open(name, O_RDONLY|O_BINARY);
if (fd < 0) {
perror(name);
return 0;
}
if (fstat(fd, &sb) < 0) {
perror(name);
return 0;
}
if (!S_ISREG(sb.st_mode)) {
fprintf(stderr, "%s: not a regular file\n", name);
return 0;
}
nbytes = sb.st_size;
p = malloc(nbytes);
if (!p) {
fprintf(stderr, "%s: out of memory\n", name);
return 0;
}
n = read(fd, p, nbytes);
if (n < 0) {
perror(name);
close(fd);
return 0;
}
if (n != nbytes) {
fprintf(stderr, "%s: read unexpected number of bytes\n", name);
close(fd);
return 0;
}
processor(p, nbytes, name, arg);
free(p);
close(fd);
return 1;
}

58
contrib/expat/xmlwf/unixfilemap.c Executable file
View File

@ -0,0 +1,58 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <errno.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#ifndef MAP_FILE
#define MAP_FILE 0
#endif
#include "filemap.h"
int
filemap(const char *name,
void (*processor)(const void *, size_t, const char *, void *arg),
void *arg)
{
int fd;
size_t nbytes;
struct stat sb;
void *p;
fd = open(name, O_RDONLY);
if (fd < 0) {
perror(name);
return 0;
}
if (fstat(fd, &sb) < 0) {
perror(name);
close(fd);
return 0;
}
if (!S_ISREG(sb.st_mode)) {
close(fd);
fprintf(stderr, "%s: not a regular file\n", name);
return 0;
}
nbytes = sb.st_size;
p = (void *)mmap((caddr_t)0, (size_t)nbytes, PROT_READ,
MAP_FILE|MAP_PRIVATE, fd, (off_t)0);
if (p == (void *)-1) {
perror(name);
close(fd);
return 0;
}
processor(p, nbytes, name, arg);
munmap((caddr_t)p, nbytes);
close(fd);
return 1;
}

96
contrib/expat/xmlwf/win32filemap.c Executable file
View File

@ -0,0 +1,96 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#define STRICT 1
#define WIN32_LEAN_AND_MEAN 1
#ifdef XML_UNICODE_WCHAR_T
#ifndef XML_UNICODE
#define XML_UNICODE
#endif
#endif
#ifdef XML_UNICODE
#define UNICODE
#define _UNICODE
#endif /* XML_UNICODE */
#include <windows.h>
#include <stdio.h>
#include <tchar.h>
#include "filemap.h"
static void win32perror(const TCHAR *);
int
filemap(const TCHAR *name,
void (*processor)(const void *, size_t, const TCHAR *, void *arg),
void *arg)
{
HANDLE f;
HANDLE m;
DWORD size;
DWORD sizeHi;
void *p;
f = CreateFile(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING,
FILE_FLAG_SEQUENTIAL_SCAN, NULL);
if (f == INVALID_HANDLE_VALUE) {
win32perror(name);
return 0;
}
size = GetFileSize(f, &sizeHi);
if (size == (DWORD)-1) {
win32perror(name);
return 0;
}
if (sizeHi) {
_ftprintf(stderr, _T("%s: bigger than 2Gb\n"), name);
return 0;
}
/* CreateFileMapping barfs on zero length files */
if (size == 0) {
static const char c = '\0';
processor(&c, 0, name, arg);
CloseHandle(f);
return 1;
}
m = CreateFileMapping(f, NULL, PAGE_READONLY, 0, 0, NULL);
if (m == NULL) {
win32perror(name);
CloseHandle(f);
return 0;
}
p = MapViewOfFile(m, FILE_MAP_READ, 0, 0, 0);
if (p == NULL) {
win32perror(name);
CloseHandle(m);
CloseHandle(f);
return 0;
}
processor(p, size, name, arg);
UnmapViewOfFile(p);
CloseHandle(m);
CloseHandle(f);
return 1;
}
static void
win32perror(const TCHAR *s)
{
LPVOID buf;
if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
| FORMAT_MESSAGE_FROM_SYSTEM,
NULL,
GetLastError(),
MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
(LPTSTR) &buf,
0,
NULL)) {
_ftprintf(stderr, _T("%s: %s"), s, buf);
fflush(stderr);
LocalFree(buf);
}
else
_ftprintf(stderr, _T("%s: unknown Windows error\n"), s);
}

231
contrib/expat/xmlwf/xmlfile.c Executable file
View File

@ -0,0 +1,231 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <fcntl.h>
#ifdef COMPILED_FROM_DSP
#include "winconfig.h"
#else
#include "expat_config.h"
#endif
#include "expat.h"
#include "xmlfile.h"
#include "xmltchar.h"
#include "filemap.h"
#ifdef _MSC_VER
#include <io.h>
#endif
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifndef O_BINARY
#ifdef _O_BINARY
#define O_BINARY _O_BINARY
#else
#define O_BINARY 0
#endif
#endif
#ifdef _DEBUG
#define READ_SIZE 16
#else
#define READ_SIZE (1024*8)
#endif
typedef struct {
XML_Parser parser;
int *retPtr;
} PROCESS_ARGS;
static 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:%d: %s\n"),
filename,
XML_GetErrorLineNumber(parser),
XML_GetErrorColumnNumber(parser),
message);
else
ftprintf(stderr, T("%s: (unknown message %d)\n"), filename, code);
}
static void
processFile(const void *data, size_t size,
const XML_Char *filename, void *args)
{
XML_Parser parser = ((PROCESS_ARGS *)args)->parser;
int *retPtr = ((PROCESS_ARGS *)args)->retPtr;
if (XML_Parse(parser, data, size, 1) == XML_STATUS_ERROR) {
reportError(parser, filename);
*retPtr = 0;
}
else
*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)
{
XML_Char *s;
*toFree = 0;
if (!base
|| *systemId == T('/')
#ifdef WIN32
|| *systemId == T('\\')
|| (isAsciiLetter(systemId[0]) && systemId[1] == T(':'))
#endif
)
return systemId;
*toFree = (XML_Char *)malloc((tcslen(base) + tcslen(systemId) + 2)
* sizeof(XML_Char));
if (!*toFree)
return systemId;
tcscpy(*toFree, base);
s = *toFree;
if (tcsrchr(s, T('/')))
s = tcsrchr(s, T('/')) + 1;
#ifdef WIN32
if (tcsrchr(s, T('\\')))
s = tcsrchr(s, T('\\')) + 1;
#endif
tcscpy(s, systemId);
return *toFree;
}
static int
externalEntityRefFilemap(XML_Parser parser,
const XML_Char *context,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId)
{
int result;
XML_Char *s;
const XML_Char *filename;
XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
PROCESS_ARGS args;
args.retPtr = &result;
args.parser = entParser;
filename = resolveSystemId(base, systemId, &s);
XML_SetBase(entParser, filename);
if (!filemap(filename, processFile, &args))
result = 0;
free(s);
XML_ParserFree(entParser);
return result;
}
static int
processStream(const XML_Char *filename, XML_Parser parser)
{
/* passing NULL for filename means read intput from stdin */
int fd = 0; /* 0 is the fileno for stdin */
if (filename != NULL) {
fd = topen(filename, O_BINARY|O_RDONLY);
if (fd < 0) {
tperror(filename);
return 0;
}
}
for (;;) {
int nread;
char *buf = XML_GetBuffer(parser, READ_SIZE);
if (!buf) {
if (filename != NULL)
close(fd);
ftprintf(stderr, T("%s: out of memory\n"),
filename != NULL ? filename : "xmlwf");
return 0;
}
nread = read(fd, buf, READ_SIZE);
if (nread < 0) {
tperror(filename != NULL ? filename : "STDIN");
if (filename != NULL)
close(fd);
return 0;
}
if (XML_ParseBuffer(parser, nread, nread == 0) == XML_STATUS_ERROR) {
reportError(parser, filename != NULL ? filename : "STDIN");
if (filename != NULL)
close(fd);
return 0;
}
if (nread == 0) {
if (filename != NULL)
close(fd);
break;;
}
}
return 1;
}
static int
externalEntityRefStream(XML_Parser parser,
const XML_Char *context,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId)
{
XML_Char *s;
const XML_Char *filename;
int ret;
XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
filename = resolveSystemId(base, systemId, &s);
XML_SetBase(entParser, filename);
ret = processStream(filename, entParser);
free(s);
XML_ParserFree(entParser);
return ret;
}
int
XML_ProcessFile(XML_Parser parser,
const XML_Char *filename,
unsigned flags)
{
int result;
if (!XML_SetBase(parser, filename)) {
ftprintf(stderr, T("%s: out of memory"), filename);
exit(1);
}
if (flags & XML_EXTERNAL_ENTITIES)
XML_SetExternalEntityRefHandler(parser,
(flags & XML_MAP_FILE)
? externalEntityRefFilemap
: externalEntityRefStream);
if (flags & XML_MAP_FILE) {
PROCESS_ARGS args;
args.retPtr = &result;
args.parser = parser;
if (!filemap(filename, processFile, &args))
result = 0;
}
else
result = processStream(filename, parser);
return result;
}

10
contrib/expat/xmlwf/xmlfile.h Executable file
View File

@ -0,0 +1,10 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#define XML_MAP_FILE 01
#define XML_EXTERNAL_ENTITIES 02
extern int XML_ProcessFile(XML_Parser parser,
const XML_Char *filename,
unsigned flags);

163
contrib/expat/xmlwf/xmlmime.c Executable file
View File

@ -0,0 +1,163 @@
#include <string.h>
#include "xmlmime.h"
static const char *
getTok(const char **pp)
{
/* inComment means one level of nesting; inComment+1 means two levels etc */
enum { inAtom, inString, init, inComment };
int state = init;
const char *tokStart = 0;
for (;;) {
switch (**pp) {
case '\0':
if (state == inAtom)
return tokStart;
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 0
if (!matchkey(p, next, "xml") && charset[0] == '\0')
return;
#endif
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;
}
}
}
break;
}
}
else
p = getTok(&next);
}
}
#ifdef TEST
#include <stdio.h>
int
main(int argc, char *argv[])
{
char buf[CHARSET_MAX];
if (argc <= 1)
return 1;
printf("%s\n", argv[1]);
getXMLCharset(argv[1], buf);
printf("charset=\"%s\"\n", buf);
return 0;
}
#endif /* TEST */

19
contrib/expat/xmlwf/xmlmime.h Executable file
View File

@ -0,0 +1,19 @@
#ifdef __cplusplus
extern "C" {
#endif
/* Registered charset names are at most 40 characters long. */
#define CHARSET_MAX 41
/* Figure out the charset to use from the ContentType.
buf contains the body of the header field (the part after "Content-Type:").
charset gets the charset to use. It must be at least CHARSET_MAX chars
long. charset will be empty if the default charset should be used.
*/
void getXMLCharset(const char *buf, char *charset);
#ifdef __cplusplus
}
#endif

36
contrib/expat/xmlwf/xmltchar.h Executable file
View File

@ -0,0 +1,36 @@
#ifdef XML_UNICODE
#ifndef XML_UNICODE_WCHAR_T
#error xmlwf requires a 16-bit Unicode-compatible wchar_t
#endif
#define T(x) L ## x
#define ftprintf fwprintf
#define tfopen _wfopen
#define fputts fputws
#define puttc putwc
#define tcscmp wcscmp
#define tcscpy wcscpy
#define tcscat wcscat
#define tcschr wcschr
#define tcsrchr wcsrchr
#define tcslen wcslen
#define tperror _wperror
#define topen _wopen
#define tmain wmain
#define tremove _wremove
#else /* not XML_UNICODE */
#define T(x) x
#define ftprintf fprintf
#define tfopen fopen
#define fputts fputs
#define puttc putc
#define tcscmp strcmp
#define tcscpy strcpy
#define tcscat strcat
#define tcschr strchr
#define tcsrchr strrchr
#define tcslen strlen
#define tperror perror
#define topen open
#define tmain main
#define tremove remove
#endif /* not XML_UNICODE */

13
contrib/expat/xmlwf/xmlurl.h Executable file
View File

@ -0,0 +1,13 @@
#ifdef __cplusplus
extern "C" {
#endif
int XML_URLInit();
void XML_URLUninit();
int XML_ProcessURL(XML_Parser parser,
const XML_Char *url,
unsigned flags);
#ifdef __cplusplus
}
#endif

842
contrib/expat/xmlwf/xmlwf.c Executable file
View File

@ -0,0 +1,842 @@
/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
See the file COPYING for copying permission.
*/
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include "expat.h"
#include "codepage.h"
#include "xmlfile.h"
#include "xmltchar.h"
#ifdef _MSC_VER
#include <crtdbg.h>
#endif
/* This ensures proper sorting. */
#define NSSEP T('\001')
static void
characterData(void *userData, const XML_Char *s, int len)
{
FILE *fp = userData;
for (; len > 0; --len, ++s) {
switch (*s) {
case T('&'):
fputts(T("&amp;"), fp);
break;
case T('<'):
fputts(T("&lt;"), fp);
break;
case T('>'):
fputts(T("&gt;"), fp);
break;
#ifdef W3C14N
case 13:
fputts(T("&#xD;"), fp);
break;
#else
case T('"'):
fputts(T("&quot;"), fp);
break;
case 9:
case 10:
case 13:
ftprintf(fp, T("&#%d;"), *s);
break;
#endif
default:
puttc(*s, fp);
break;
}
}
}
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. */
static int
attcmp(const void *att1, const void *att2)
{
return tcscmp(*(const XML_Char **)att1, *(const XML_Char **)att2);
}
static void
startElement(void *userData, const XML_Char *name, const XML_Char **atts)
{
int nAtts;
const XML_Char **p;
FILE *fp = userData;
puttc(T('<'), fp);
fputts(name, fp);
p = atts;
while (*p)
++p;
nAtts = (p - atts) >> 1;
if (nAtts > 1)
qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, attcmp);
while (*atts) {
puttc(T(' '), fp);
fputts(*atts++, fp);
attributeValue(fp, *atts);
atts++;
}
puttc(T('>'), fp);
}
static void
endElement(void *userData, const XML_Char *name)
{
FILE *fp = userData;
puttc(T('<'), fp);
puttc(T('/'), fp);
fputts(name, fp);
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;
int nsi;
const XML_Char **p;
FILE *fp = userData;
const XML_Char *sep;
puttc(T('<'), fp);
sep = tcsrchr(name, NSSEP);
if (sep) {
fputts(T("n1:"), fp);
fputts(sep + 1, fp);
fputts(T(" xmlns:n1"), fp);
attributeValue(fp, name);
nsi = 2;
}
else {
fputts(name, fp);
nsi = 1;
}
p = atts;
while (*p)
++p;
nAtts = (p - atts) >> 1;
if (nAtts > 1)
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("n%d:"), nsi);
fputts(sep + 1, fp);
}
else
fputts(name, fp);
attributeValue(fp, *atts);
if (sep) {
ftprintf(fp, T(" xmlns:n%d"), nsi++);
attributeValue(fp, name);
}
atts++;
}
puttc(T('>'), fp);
}
static void
endElementNS(void *userData, const XML_Char *name)
{
FILE *fp = userData;
const XML_Char *sep;
puttc(T('<'), fp);
puttc(T('/'), fp);
sep = tcsrchr(name, NSSEP);
if (sep) {
fputts(T("n1:"), fp);
fputts(sep + 1, fp);
}
else
fputts(name, fp);
puttc(T('>'), fp);
}
#ifndef W3C14N
static void
processingInstruction(void *userData, const XML_Char *target,
const XML_Char *data)
{
FILE *fp = userData;
puttc(T('<'), fp);
puttc(T('?'), fp);
fputts(target, fp);
puttc(T(' '), fp);
fputts(data, fp);
puttc(T('?'), fp);
puttc(T('>'), fp);
}
#endif /* not W3C14N */
static void
defaultCharacterData(void *userData, const XML_Char *s, int len)
{
XML_DefaultCurrent((XML_Parser) userData);
}
static void
defaultStartElement(void *userData, const XML_Char *name,
const XML_Char **atts)
{
XML_DefaultCurrent((XML_Parser) userData);
}
static void
defaultEndElement(void *userData, const XML_Char *name)
{
XML_DefaultCurrent((XML_Parser) userData);
}
static void
defaultProcessingInstruction(void *userData, const XML_Char *target,
const XML_Char *data)
{
XML_DefaultCurrent((XML_Parser) userData);
}
static void
nopCharacterData(void *userData, const XML_Char *s, int len)
{
}
static void
nopStartElement(void *userData, const XML_Char *name, const XML_Char **atts)
{
}
static void
nopEndElement(void *userData, const XML_Char *name)
{
}
static void
nopProcessingInstruction(void *userData, const XML_Char *target,
const XML_Char *data)
{
}
static void
markup(void *userData, const XML_Char *s, int len)
{
FILE *fp = XML_GetUserData((XML_Parser) userData);
for (; len > 0; --len, ++s)
puttc(*s, fp);
}
static void
metaLocation(XML_Parser parser)
{
const XML_Char *uri = XML_GetBase(parser);
if (uri)
ftprintf(XML_GetUserData(parser), T(" uri=\"%s\""), uri);
ftprintf(XML_GetUserData(parser),
T(" byte=\"%ld\" nbytes=\"%d\" line=\"%d\" col=\"%d\""),
XML_GetCurrentByteIndex(parser),
XML_GetCurrentByteCount(parser),
XML_GetCurrentLineNumber(parser),
XML_GetCurrentColumnNumber(parser));
}
static void
metaStartDocument(void *userData)
{
fputts(T("<document>\n"), XML_GetUserData((XML_Parser) userData));
}
static void
metaEndDocument(void *userData)
{
fputts(T("</document>\n"), XML_GetUserData((XML_Parser) userData));
}
static void
metaStartElement(void *userData, const XML_Char *name,
const XML_Char **atts)
{
XML_Parser parser = (XML_Parser) userData;
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) {
fputts(T(">\n"), fp);
do {
ftprintf(fp, T("<attribute name=\"%s\" value=\""), atts[0]);
characterData(fp, atts[1], tcslen(atts[1]));
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);
}
else
fputts(T("/>\n"), fp);
}
static void
metaEndElement(void *userData, const XML_Char *name)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
ftprintf(fp, T("<endtag name=\"%s\""), name);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaProcessingInstruction(void *userData, const XML_Char *target,
const XML_Char *data)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
ftprintf(fp, T("<pi target=\"%s\" data=\""), target);
characterData(fp, data, tcslen(data));
puttc(T('"'), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaComment(void *userData, const XML_Char *data)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
fputts(T("<comment data=\""), fp);
characterData(fp, data, tcslen(data));
puttc(T('"'), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaStartCdataSection(void *userData)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
fputts(T("<startcdata"), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaEndCdataSection(void *userData)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
fputts(T("<endcdata"), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaCharacterData(void *userData, const XML_Char *s, int len)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
fputts(T("<chars str=\""), fp);
characterData(fp, s, len);
puttc(T('"'), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaStartDoctypeDecl(void *userData,
const XML_Char *doctypeName,
const XML_Char *sysid,
const XML_Char *pubid,
int has_internal_subset)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
ftprintf(fp, T("<startdoctype name=\"%s\""), doctypeName);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaEndDoctypeDecl(void *userData)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
fputts(T("<enddoctype"), fp);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaNotationDecl(void *userData,
const XML_Char *notationName,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
ftprintf(fp, T("<notation name=\"%s\""), notationName);
if (publicId)
ftprintf(fp, T(" public=\"%s\""), publicId);
if (systemId) {
fputts(T(" system=\""), fp);
characterData(fp, systemId, tcslen(systemId));
puttc(T('"'), fp);
}
metaLocation(parser);
fputts(T("/>\n"), fp);
}
static void
metaEntityDecl(void *userData,
const XML_Char *entityName,
int is_param,
const XML_Char *value,
int value_length,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId,
const XML_Char *notationName)
{
XML_Parser parser = (XML_Parser) userData;
FILE *fp = XML_GetUserData(parser);
if (value) {
ftprintf(fp, T("<entity name=\"%s\""), entityName);
metaLocation(parser);
puttc(T('>'), fp);
characterData(fp, value, value_length);
fputts(T("</entity/>\n"), fp);
}
else if (notationName) {
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);
ftprintf(fp, T(" notation=\"%s\""), notationName);
metaLocation(parser);
fputts(T("/>\n"), fp);
}
else {
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
metaStartNamespaceDecl(void *userData,
const XML_Char *prefix,
const XML_Char *uri)
{
XML_Parser parser = (XML_Parser) userData;
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(void *userData, const XML_Char *prefix)
{
XML_Parser parser = (XML_Parser) userData;
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)
{
return codepageConvert(*(int *)data, p);
}
static int
unknownEncoding(void *userData, const XML_Char *name, XML_Encoding *info)
{
int cp;
static const XML_Char prefixL[] = T("windows-");
static const XML_Char prefixU[] = T("WINDOWS-");
int i;
for (i = 0; prefixU[i]; i++)
if (name[i] != prefixU[i] && name[i] != prefixL[i])
return 0;
cp = 0;
for (; name[i]; i++) {
static const XML_Char digits[] = T("0123456789");
const XML_Char *s = tcschr(digits, name[i]);
if (!s)
return 0;
cp *= 10;
cp += s - digits;
if (cp >= 0x10000)
return 0;
}
if (!codepageMap(cp, info->map))
return 0;
info->convert = unknownEncodingConvert;
/* We could just cast the code page integer to a void *,
and avoid the use of release. */
info->release = free;
info->data = malloc(sizeof(int));
if (!info->data)
return 0;
*(int *)info->data = cp;
return 1;
}
static int
notStandalone(void *userData)
{
return 0;
}
static void
showVersion(XML_Char *prog)
{
XML_Char *s = prog;
XML_Char ch;
const XML_Feature *features = XML_GetFeatureList();
while ((ch = *s) != 0) {
if (ch == '/'
#ifdef WIN32
|| ch == '\\'
#endif
)
prog = s + 1;
++s;
}
ftprintf(stdout, T("%s using %s\n"), prog, XML_ExpatVersion());
if (features != NULL && features[0].feature != XML_FEATURE_END) {
int i = 1;
ftprintf(stdout, T("%s"), features[0].name);
if (features[0].value)
ftprintf(stdout, T("=%ld"), features[0].value);
while (features[i].feature != XML_FEATURE_END) {
ftprintf(stdout, T(", %s"), features[i].name);
if (features[i].value)
ftprintf(stdout, T("=%ld"), features[i].value);
++i;
}
ftprintf(stdout, T("\n"));
}
}
static void
usage(const XML_Char *prog, int rc)
{
ftprintf(stderr,
T("usage: %s [-n] [-p] [-r] [-s] [-w] [-x] [-d output-dir] "
"[-e encoding] file ...\n"), prog);
exit(rc);
}
int
tmain(int argc, XML_Char **argv)
{
int i, j;
const XML_Char *outputDir = NULL;
const XML_Char *encoding = NULL;
unsigned processFlags = XML_MAP_FILE;
int windowsCodePages = 0;
int outputType = 0;
int useNamespaces = 0;
int requireStandalone = 0;
int paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
int useStdin = 0;
#ifdef _MSC_VER
_CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF|_CRTDBG_LEAK_CHECK_DF);
#endif
i = 1;
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++;
}
switch (argv[i][j]) {
case T('r'):
processFlags &= ~XML_MAP_FILE;
j++;
break;
case T('s'):
requireStandalone = 1;
j++;
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++;
break;
case T('w'):
windowsCodePages = 1;
j++;
break;
case T('m'):
outputType = 'm';
j++;
break;
case T('c'):
outputType = 'c';
useNamespaces = 0;
j++;
break;
case T('t'):
outputType = 't';
j++;
break;
case T('d'):
if (argv[i][j + 1] == T('\0')) {
if (++i == argc)
usage(argv[0], 2);
outputDir = argv[i];
}
else
outputDir = argv[i] + j + 1;
i++;
j = 0;
break;
case T('e'):
if (argv[i][j + 1] == T('\0')) {
if (++i == argc)
usage(argv[0], 2);
encoding = argv[i];
}
else
encoding = argv[i] + j + 1;
i++;
j = 0;
break;
case T('h'):
usage(argv[0], 0);
return 0;
case T('v'):
showVersion(argv[0]);
return 0;
case T('\0'):
if (j > 1) {
i++;
j = 0;
break;
}
/* fall through */
default:
usage(argv[0], 2);
}
}
if (i == argc) {
useStdin = 1;
processFlags &= ~XML_MAP_FILE;
i--;
}
for (; i < argc; i++) {
FILE *fp = 0;
XML_Char *outName = 0;
int result;
XML_Parser parser;
if (useNamespaces)
parser = XML_ParserCreateNS(encoding, NSSEP);
else
parser = XML_ParserCreate(encoding);
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 = useStdin ? T("STDIN") : argv[i];
if (tcsrchr(file, T('/')))
file = tcsrchr(file, T('/')) + 1;
#ifdef WIN32
if (tcsrchr(file, T('\\')))
file = tcsrchr(file, T('\\')) + 1;
#endif
outName = malloc((tcslen(outputDir) + tcslen(file) + 2)
* sizeof(XML_Char));
tcscpy(outName, outputDir);
tcscat(outName, T("/"));
tcscat(outName, file);
fp = tfopen(outName, T("wb"));
if (!fp) {
tperror(outName);
exit(1);
}
setvbuf(fp, NULL, _IOFBF, 16384);
#ifdef XML_UNICODE
puttc(0xFEFF, fp);
#endif
XML_SetUserData(parser, fp);
switch (outputType) {
case 'm':
XML_UseParserAsHandlerArg(parser);
XML_SetElementHandler(parser, metaStartElement, metaEndElement);
XML_SetProcessingInstructionHandler(parser, metaProcessingInstruction);
XML_SetCommentHandler(parser, metaComment);
XML_SetCdataSectionHandler(parser, metaStartCdataSection,
metaEndCdataSection);
XML_SetCharacterDataHandler(parser, metaCharacterData);
XML_SetDoctypeDeclHandler(parser, metaStartDoctypeDecl,
metaEndDoctypeDecl);
XML_SetEntityDeclHandler(parser, metaEntityDecl);
XML_SetNotationDeclHandler(parser, metaNotationDecl);
XML_SetNamespaceDeclHandler(parser, metaStartNamespaceDecl,
metaEndNamespaceDecl);
metaStartDocument(parser);
break;
case 'c':
XML_UseParserAsHandlerArg(parser);
XML_SetDefaultHandler(parser, markup);
XML_SetElementHandler(parser, defaultStartElement, defaultEndElement);
XML_SetCharacterDataHandler(parser, defaultCharacterData);
XML_SetProcessingInstructionHandler(parser,
defaultProcessingInstruction);
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;
}
}
if (windowsCodePages)
XML_SetUnknownEncodingHandler(parser, unknownEncoding, 0);
result = XML_ProcessFile(parser, useStdin ? NULL : argv[i], processFlags);
if (outputDir) {
if (outputType == 'm')
metaEndDocument(parser);
fclose(fp);
if (!result)
tremove(outName);
free(outName);
}
XML_ParserFree(parser);
}
return 0;
}

395
contrib/expat/xmlwf/xmlwin32url.cxx Executable file
View File

@ -0,0 +1,395 @@
#include "expat.h"
#ifdef XML_UNICODE
#define UNICODE
#endif
#include <windows.h>
#include <urlmon.h>
#include <wininet.h>
#include <stdio.h>
#include <tchar.h>
#include "xmlurl.h"
#include "xmlmime.h"
static int
processURL(XML_Parser parser, IMoniker *baseMoniker, const XML_Char *url);
typedef void (*StopHandler)(void *, HRESULT);
class Callback : public IBindStatusCallback {
public:
// IUnknown methods
STDMETHODIMP QueryInterface(REFIID,void **);
STDMETHODIMP_(ULONG) AddRef();
STDMETHODIMP_(ULONG) Release();
// IBindStatusCallback methods
STDMETHODIMP OnStartBinding(DWORD, IBinding *);
STDMETHODIMP GetPriority(LONG *);
STDMETHODIMP OnLowResource(DWORD);
STDMETHODIMP OnProgress(ULONG, ULONG, ULONG, LPCWSTR);
STDMETHODIMP OnStopBinding(HRESULT, LPCWSTR);
STDMETHODIMP GetBindInfo(DWORD *, BINDINFO *);
STDMETHODIMP OnDataAvailable(DWORD, DWORD, FORMATETC *, STGMEDIUM *);
STDMETHODIMP OnObjectAvailable(REFIID, IUnknown *);
Callback(XML_Parser, IMoniker *, StopHandler, void *);
~Callback();
int externalEntityRef(const XML_Char *context,
const XML_Char *systemId, const XML_Char *publicId);
private:
XML_Parser parser_;
IMoniker *baseMoniker_;
DWORD totalRead_;
ULONG ref_;
IBinding *pBinding_;
StopHandler stopHandler_;
void *stopArg_;
};
STDMETHODIMP_(ULONG)
Callback::AddRef()
{
return ref_++;
}
STDMETHODIMP_(ULONG)
Callback::Release()
{
if (--ref_ == 0) {
delete this;
return 0;
}
return ref_;
}
STDMETHODIMP
Callback::QueryInterface(REFIID riid, void** ppv)
{
if (IsEqualGUID(riid, IID_IUnknown))
*ppv = (IUnknown *)this;
else if (IsEqualGUID(riid, IID_IBindStatusCallback))
*ppv = (IBindStatusCallback *)this;
else
return E_NOINTERFACE;
((LPUNKNOWN)*ppv)->AddRef();
return S_OK;
}
STDMETHODIMP
Callback::OnStartBinding(DWORD, IBinding* pBinding)
{
pBinding_ = pBinding;
pBinding->AddRef();
return S_OK;
}
STDMETHODIMP
Callback::GetPriority(LONG *)
{
return E_NOTIMPL;
}
STDMETHODIMP
Callback::OnLowResource(DWORD)
{
return E_NOTIMPL;
}
STDMETHODIMP
Callback::OnProgress(ULONG, ULONG, ULONG, LPCWSTR)
{
return S_OK;
}
STDMETHODIMP
Callback::OnStopBinding(HRESULT hr, LPCWSTR szError)
{
if (pBinding_) {
pBinding_->Release();
pBinding_ = 0;
}
if (baseMoniker_) {
baseMoniker_->Release();
baseMoniker_ = 0;
}
stopHandler_(stopArg_, hr);
return S_OK;
}
STDMETHODIMP
Callback::GetBindInfo(DWORD* pgrfBINDF, BINDINFO* pbindinfo)
{
*pgrfBINDF = BINDF_ASYNCHRONOUS;
return S_OK;
}
static void
reportError(XML_Parser parser)
{
int code = XML_GetErrorCode(parser);
const XML_Char *message = XML_ErrorString(code);
if (message)
_ftprintf(stderr, _T("%s:%d:%ld: %s\n"),
XML_GetBase(parser),
XML_GetErrorLineNumber(parser),
XML_GetErrorColumnNumber(parser),
message);
else
_ftprintf(stderr, _T("%s: (unknown message %d)\n"),
XML_GetBase(parser), code);
}
STDMETHODIMP
Callback::OnDataAvailable(DWORD grfBSCF,
DWORD dwSize,
FORMATETC *pfmtetc,
STGMEDIUM* pstgmed)
{
if (grfBSCF & BSCF_FIRSTDATANOTIFICATION) {
IWinInetHttpInfo *hp;
HRESULT hr = pBinding_->QueryInterface(IID_IWinInetHttpInfo,
(void **)&hp);
if (SUCCEEDED(hr)) {
char contentType[1024];
DWORD bufSize = sizeof(contentType);
DWORD flags = 0;
contentType[0] = 0;
hr = hp->QueryInfo(HTTP_QUERY_CONTENT_TYPE, contentType,
&bufSize, 0, NULL);
if (SUCCEEDED(hr)) {
char charset[CHARSET_MAX];
getXMLCharset(contentType, charset);
if (charset[0]) {
#ifdef XML_UNICODE
XML_Char wcharset[CHARSET_MAX];
XML_Char *p1 = wcharset;
const char *p2 = charset;
while ((*p1++ = (unsigned char)*p2++) != 0)
;
XML_SetEncoding(parser_, wcharset);
#else
XML_SetEncoding(parser_, charset);
#endif
}
}
hp->Release();
}
}
if (!parser_)
return E_ABORT;
if (pstgmed->tymed == TYMED_ISTREAM) {
while (totalRead_ < dwSize) {
#define READ_MAX (64*1024)
DWORD nToRead = dwSize - totalRead_;
if (nToRead > READ_MAX)
nToRead = READ_MAX;
void *buf = XML_GetBuffer(parser_, nToRead);
if (!buf) {
_ftprintf(stderr, _T("out of memory\n"));
return E_ABORT;
}
DWORD nRead;
HRESULT hr = pstgmed->pstm->Read(buf, nToRead, &nRead);
if (SUCCEEDED(hr)) {
totalRead_ += nRead;
if (!XML_ParseBuffer(parser_,
nRead,
(grfBSCF & BSCF_LASTDATANOTIFICATION) != 0
&& totalRead_ == dwSize)) {
reportError(parser_);
return E_ABORT;
}
}
}
}
return S_OK;
}
STDMETHODIMP
Callback::OnObjectAvailable(REFIID, IUnknown *)
{
return S_OK;
}
int
Callback::externalEntityRef(const XML_Char *context,
const XML_Char *systemId,
const XML_Char *publicId)
{
XML_Parser entParser = XML_ExternalEntityParserCreate(parser_, context, 0);
XML_SetBase(entParser, systemId);
int ret = processURL(entParser, baseMoniker_, systemId);
XML_ParserFree(entParser);
return ret;
}
Callback::Callback(XML_Parser parser, IMoniker *baseMoniker,
StopHandler stopHandler, void *stopArg)
: parser_(parser),
baseMoniker_(baseMoniker),
ref_(0),
pBinding_(0),
totalRead_(0),
stopHandler_(stopHandler),
stopArg_(stopArg)
{
if (baseMoniker_)
baseMoniker_->AddRef();
}
Callback::~Callback()
{
if (pBinding_)
pBinding_->Release();
if (baseMoniker_)
baseMoniker_->Release();
}
static int
externalEntityRef(void *arg,
const XML_Char *context,
const XML_Char *base,
const XML_Char *systemId,
const XML_Char *publicId)
{
return ((Callback *)arg)->externalEntityRef(context, systemId, publicId);
}
static HRESULT
openStream(XML_Parser parser,
IMoniker *baseMoniker,
const XML_Char *uri,
StopHandler stopHandler, void *stopArg)
{
if (!XML_SetBase(parser, uri))
return E_OUTOFMEMORY;
HRESULT hr;
IMoniker *m;
#ifdef XML_UNICODE
hr = CreateURLMoniker(0, uri, &m);
#else
LPWSTR uriw = new wchar_t[strlen(uri) + 1];
for (int i = 0;; i++) {
uriw[i] = uri[i];
if (uriw[i] == 0)
break;
}
hr = CreateURLMoniker(baseMoniker, uriw, &m);
delete [] uriw;
#endif
if (FAILED(hr))
return hr;
IBindStatusCallback *cb = new Callback(parser, m, stopHandler, stopArg);
XML_SetExternalEntityRefHandler(parser, externalEntityRef);
XML_SetExternalEntityRefHandlerArg(parser, cb);
cb->AddRef();
IBindCtx *b;
if (FAILED(hr = CreateAsyncBindCtx(0, cb, 0, &b))) {
cb->Release();
m->Release();
return hr;
}
cb->Release();
IStream *pStream;
hr = m->BindToStorage(b, 0, IID_IStream, (void **)&pStream);
if (SUCCEEDED(hr)) {
if (pStream)
pStream->Release();
}
if (hr == MK_S_ASYNCHRONOUS)
hr = S_OK;
m->Release();
b->Release();
return hr;
}
struct QuitInfo {
const XML_Char *url;
HRESULT hr;
int stop;
};
static void
winPerror(const XML_Char *url, HRESULT hr)
{
LPVOID buf;
if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
| FORMAT_MESSAGE_FROM_HMODULE,
GetModuleHandleA("urlmon.dll"),
hr,
MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
(LPTSTR) &buf,
0,
NULL)
|| FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
| FORMAT_MESSAGE_FROM_SYSTEM,
0,
hr,
MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
(LPTSTR) &buf,
0,
NULL)) {
/* The system error messages seem to end with a newline. */
_ftprintf(stderr, _T("%s: %s"), url, buf);
fflush(stderr);
LocalFree(buf);
}
else
_ftprintf(stderr, _T("%s: error %x\n"), url, hr);
}
static void
threadQuit(void *p, HRESULT hr)
{
QuitInfo *qi = (QuitInfo *)p;
qi->hr = hr;
qi->stop = 1;
}
extern "C"
int
XML_URLInit(void)
{
return SUCCEEDED(CoInitialize(0));
}
extern "C"
void
XML_URLUninit(void)
{
CoUninitialize();
}
static int
processURL(XML_Parser parser, IMoniker *baseMoniker,
const XML_Char *url)
{
QuitInfo qi;
qi.stop = 0;
qi.url = url;
XML_SetBase(parser, url);
HRESULT hr = openStream(parser, baseMoniker, url, threadQuit, &qi);
if (FAILED(hr)) {
winPerror(url, hr);
return 0;
}
else if (FAILED(qi.hr)) {
winPerror(url, qi.hr);
return 0;
}
MSG msg;
while (!qi.stop && GetMessage (&msg, NULL, 0, 0)) {
TranslateMessage (&msg);
DispatchMessage (&msg);
}
return 1;
}
extern "C"
int
XML_ProcessURL(XML_Parser parser,
const XML_Char *url,
unsigned flags)
{
return processURL(parser, 0, url);
}