Commit c1aa3d82 authored by Jim Fulton's avatar Jim Fulton

major update with expat 1.1 and new pyexpat

parent 773b9f8b
# Universal Makefile to build Python extensions. # Universal Unix Makefile for Python extensions
# # =============================================
# Instructions:
# # Short Instructions
# 0) Build and install the basic Python 1.5 distribution. You must # ------------------
# also install the headers ("make inclinstall") and the binary library
# files ("make libainstall"). # 1. Build and install Python (1.5 or newer).
# # 2. "make -f Makefile.pre.in boot"
# 1) Edit Makefile.pre.in (not any other file!!!) to change the # 3. "make"
# definition of installdir (and possibly exec_installdir). These # You should now have a shared library.
# should match the prefix and exec_prefix used when installing Python.
# Alternatively, you can specify a value for installdir on the # Long Instructions
# "make -f Makefile.pre.in Makefile" command line (see below). This # -----------------
# is probably easier since it avoids editing Makefile.pre.in at all...
# # Build *and install* the basic Python 1.5 distribution. See the
# 2) Copy Setup.in to Setup and edit Setup to change the selection of # Python README for instructions. (This version of Makefile.pre.in
# modules you want to use. Read the comments in the core Python's # only withs with Python 1.5, alpha 3 or newer.)
# Modules/Setup.in for more detailed instructions.
# # Create a file Setup.in for your extension. This file follows the
# 3) Run "make Makefile -f Makefile.pre.in". This creates Makefile # format of the Modules/Setup.in file; see the instructions there.
# For a simple module called "spam" on file "spammodule.c", it can
# contain a single line:
# spam spammodule.c
# You can build as many modules as you want in the same directory --
# just have a separate line for each of them in the Setup.in file.
# If you want to build your extension as a shared library, insert a
# line containing just the string
# *shared*
# at the top of your Setup.in file.
# Note that the build process copies Setup.in to Setup, and then works
# with Setup. It doesn't overwrite Setup when Setup.in is changed, so
# while you're in the process of debugging your Setup.in file, you may
# want to edit Setup instead, and copy it back to Setup.in later.
# (All this is done so you can distribute your extension easily and
# someone else can select the modules they actually want to build by
# commenting out lines in the Setup file, without editing the
# original. Editing Setup is also used to specify nonstandard
# locations for include or library files.)
# Copy this file (Misc/Makefile.pre.in) to the directory containing
# your extension.
# Run "make -f Makefile.pre.in boot". This creates Makefile
# (producing Makefile.pre and sedscript as intermediate files) and # (producing Makefile.pre and sedscript as intermediate files) and
# config.c. Values for installdir, srcdir, VPATH, LINKPATH, OPT, # config.c, incorporating the values for sys.prefix, sys.exec_prefix
# BASELIB and BASESETUP on the make command line will be incorporated # and sys.version from the installed Python binary. For this to work,
# in the final Makefile. # the python binary must be on your path. If this fails, try
# # make -f Makefile.pre.in Makefile VERSION=1.5 installdir=<prefix>
# 4) Run "make". This creates a Python executable. The set of # where <prefix> is the prefix used to install Python for installdir
# built-in modules and features is a superset of that of the basic # (and possibly similar for exec_installdir=<exec_prefix>).
# Python -- additions are taken from ./Setup.
# # Note: "make boot" implies "make clobber" -- it assumes that when you
# If you don't actually want to install the Python headers and # bootstrap you may have changed platforms so it removes all previous
# binary library files, you can edit the "Fixed definitions" section # output files.
# below to point directly into the source and/or build tree.
# # If you are building your extension as a shared library (your
# Setup.in file starts with *shared*), run "make" or "make sharedmods"
# to build the shared library files. If you are building a statically
# linked Python binary (the only solution of your platform doesn't
# support shared libraries, and sometimes handy if you want to
# distribute or install the resulting Python binary), run "make
# python".
# Note: Each time you edit Makefile.pre.in or Setup, you must run # Note: Each time you edit Makefile.pre.in or Setup, you must run
# "make Makefile" before running "make". # "make Makefile" before running "make".
#
# Hint: if you want to use VPATH, you can start in an empty # Hint: if you want to use VPATH, you can start in an empty
# subdirectory and say (e.g.): # subdirectory and say (e.g.):
# make -f ../Makefile.pre.in VERSION=1.5 srcdir=.. VPATH=.. Makefile # make -f ../Makefile.pre.in boot srcdir=.. VPATH=..
# === Variables that you just *have* to customize manually ===
# (You can also specify their values on the command line for # === Bootstrap variables (edited through "make boot") ===
# "make -f Makefile.pre.in VERSION=1.5 Makefile".)
# The prefix used by "make inclinstall libainstall" of core python # The prefix used by "make inclinstall libainstall" of core python
installdir= /ufs/jack/src/python/build.irix6/tmp installdir= /usr/local
# The exec_prefix used by the same # The exec_prefix used by the same
exec_installdir=$(installdir) exec_installdir=$(installdir)
...@@ -57,16 +86,16 @@ exec_installdir=$(installdir) ...@@ -57,16 +86,16 @@ exec_installdir=$(installdir)
srcdir= . srcdir= .
VPATH= . VPATH= .
# === Variables that you may want to customize === # === Variables that you may want to customize (rarely) ===
# Add possible -L options here # (Static) build target
LINKPATH= TARGET= python
# You may want to change this to -O # Installed python binary (used only by boot target)
OPT= -g PYTHON= python
# Add more -I and -D options here # Add more -I and -D options here
CFLAGS= $(OPT) -I$(INCLUDEPY) -I$(LIBPL) $(DEFS) CFLAGS= $(OPT) -I$(INCLUDEPY) -I$(EXECINCLUDEPY) $(DEFS)
# These two variables can be set in Setup to merge extensions. # These two variables can be set in Setup to merge extensions.
# See example[23]. # See example[23].
...@@ -84,6 +113,11 @@ MODLIBS= _MODLIBS_ ...@@ -84,6 +113,11 @@ MODLIBS= _MODLIBS_
VERSION= @VERSION@ VERSION= @VERSION@
CC= @CC@ CC= @CC@
LINKCC= @LINKCC@
SGI_ABI= @SGI_ABI@
OPT= @OPT@
LDFLAGS= @LDFLAGS@
LDLAST= @LDLAST@
DEFS= @DEFS@ DEFS= @DEFS@
LIBS= @LIBS@ LIBS= @LIBS@
LIBM= @LIBM@ LIBM= @LIBM@
...@@ -94,6 +128,7 @@ SO= @SO@ ...@@ -94,6 +128,7 @@ SO= @SO@
LDSHARED= @LDSHARED@ LDSHARED= @LDSHARED@
CCSHARED= @CCSHARED@ CCSHARED= @CCSHARED@
LINKFORSHARED= @LINKFORSHARED@ LINKFORSHARED= @LINKFORSHARED@
#@SET_CCC@
# Install prefix for architecture-independent files # Install prefix for architecture-independent files
prefix= /usr/local prefix= /usr/local
...@@ -101,8 +136,15 @@ prefix= /usr/local ...@@ -101,8 +136,15 @@ prefix= /usr/local
# Install prefix for architecture-dependent files # Install prefix for architecture-dependent files
exec_prefix= $(prefix) exec_prefix= $(prefix)
# Uncomment the following two lines for AIX
#LINKCC= $(LIBPL)/makexp_aix $(LIBPL)/python.exp "" $(LIBRARY); $(PURIFY) $(CC)
#LDSHARED= $(LIBPL)/ld_so_aix $(CC) -bI:$(LIBPL)/python.exp
# === Fixed definitions === # === Fixed definitions ===
# Shell used by make (some versions default to the login shell, which is bad)
SHELL= /bin/sh
# Expanded directories # Expanded directories
BINDIR= $(exec_installdir)/bin BINDIR= $(exec_installdir)/bin
LIBDIR= $(exec_prefix)/lib LIBDIR= $(exec_prefix)/lib
...@@ -114,40 +156,64 @@ SCRIPTDIR= $(prefix)/lib ...@@ -114,40 +156,64 @@ SCRIPTDIR= $(prefix)/lib
BINLIBDEST= $(LIBDIR)/python$(VERSION) BINLIBDEST= $(LIBDIR)/python$(VERSION)
LIBDEST= $(SCRIPTDIR)/python$(VERSION) LIBDEST= $(SCRIPTDIR)/python$(VERSION)
INCLUDEPY= $(INCLUDEDIR)/python$(VERSION) INCLUDEPY= $(INCLUDEDIR)/python$(VERSION)
EXECINCLUDEPY= $(exec_installdir)/include/python$(VERSION)
LIBP= $(exec_installdir)/lib/python$(VERSION) LIBP= $(exec_installdir)/lib/python$(VERSION)
DESTSHARED= $(BINLIBDEST)/site-packages
LIBPL= $(LIBP)/config LIBPL= $(LIBP)/config
PYTHONLIBS= $(LIBPL)/libModules.a \ PYTHONLIBS= $(LIBPL)/libpython$(VERSION).a
$(LIBPL)/libPython.a \
$(LIBPL)/libObjects.a \
$(LIBPL)/libParser.a
MAKESETUP= $(LIBPL)/makesetup MAKESETUP= $(LIBPL)/makesetup
MAKEFILE= $(LIBPL)/Makefile MAKEFILE= $(LIBPL)/Makefile
CONFIGC= $(LIBPL)/config.c CONFIGC= $(LIBPL)/config.c
CONFIGCIN= $(LIBPL)/config.c.in CONFIGCIN= $(LIBPL)/config.c.in
SETUP= $(LIBPL)/Setup SETUP= $(LIBPL)/Setup.thread $(LIBPL)/Setup.local $(LIBPL)/Setup
SYSLIBS= $(LIBM) $(LIBC) SYSLIBS= $(LIBM) $(LIBC)
ADDOBJS= $(LIBPL)/main.o getpath.o config.o ADDOBJS= $(LIBPL)/python.o config.o
# Portable install script (configure doesn't always guess right)
INSTALL= $(LIBPL)/install-sh -c
# Shared libraries must be installed with executable mode on some systems;
# rather than figuring out exactly which, we always give them executable mode.
# Also, making them read-only seems to be a good idea...
INSTALL_SHARED= ${INSTALL} -m 555
# === Fixed rules === # === Fixed rules ===
all: python # Default target. This builds shared libraries only
default: sharedmods
sharedmods: $(SHAREDMODS) # Build everything
all: static sharedmods
python: $(ADDOBJS) lib.a $(PYTHONLIBS) Makefile $(BASELIB) # Build shared libraries from our extension modules
$(CC) $(ADDOBJS) lib.a $(PYTHONLIBS) \ sharedmods: $(SHAREDMODS)
$(LINKPATH) $(BASELIB) $(MODLIBS) $(LIBS) $(SYSLIBS) -o python
# Build a static Python binary containing our extension modules
static: $(TARGET)
$(TARGET): $(ADDOBJS) lib.a $(PYTHONLIBS) Makefile $(BASELIB)
$(LINKCC) $(LDFLAGS) $(LINKFORSHARED) \
$(ADDOBJS) lib.a $(PYTHONLIBS) \
$(LINKPATH) $(BASELIB) $(MODLIBS) $(LIBS) $(SYSLIBS) \
-o $(TARGET) $(LDLAST)
install: sharedmods
if test ! -d $(DESTSHARED) ; then \
mkdir $(DESTSHARED) ; else true ; fi
-for i in X $(SHAREDMODS); do \
if test $$i != X; \
then $(INSTALL_SHARED) $$i $(DESTSHARED)/$$i; \
fi; \
done
# Build the library containing our extension modules
lib.a: $(MODOBJS) lib.a: $(MODOBJS)
-rm -f lib.a -rm -f lib.a
ar cr lib.a $(MODOBJS) ar cr lib.a $(MODOBJS)
-$(RANLIB) lib.a || \ -$(RANLIB) lib.a
echo "don't worry if ranlib fails -- probably SYSV or equiv"
# This runs makesetup *twice* to use the BASESETUP definition from Setup # This runs makesetup *twice* to use the BASESETUP definition from Setup
config.c Makefile: Makefile.pre Setup $(BASESETUP) $(MAKESETUP) config.c Makefile: Makefile.pre Setup $(BASESETUP) $(MAKESETUP)
...@@ -155,20 +221,20 @@ config.c Makefile: Makefile.pre Setup $(BASESETUP) $(MAKESETUP) ...@@ -155,20 +221,20 @@ config.c Makefile: Makefile.pre Setup $(BASESETUP) $(MAKESETUP)
-m Makefile.pre -c $(CONFIGCIN) Setup -n $(BASESETUP) $(SETUP) -m Makefile.pre -c $(CONFIGCIN) Setup -n $(BASESETUP) $(SETUP)
$(MAKE) -f Makefile do-it-again $(MAKE) -f Makefile do-it-again
# Internal target to run makesetup for the second time
do-it-again: do-it-again:
$(MAKESETUP) \ $(MAKESETUP) \
-m Makefile.pre -c $(CONFIGCIN) Setup -n $(BASESETUP) $(SETUP) -m Makefile.pre -c $(CONFIGCIN) Setup -n $(BASESETUP) $(SETUP)
# Make config.o from the config.c created by makesetup
config.o: config.c config.o: config.c
$(CC) $(CFLAGS) -c config.c $(CC) $(CFLAGS) -c config.c
getpath.o: $(LIBPL)/getpath.c Makefile
$(CC) $(CFLAGS) -DPYTHONPATH=\"$(PYTHONPATH)\" -c $(LIBPL)/getpath.c
# Setup is copied from Setup.in *only* if it doesn't yet exist # Setup is copied from Setup.in *only* if it doesn't yet exist
Setup: Setup:
cp $(srcdir)/Setup.in Setup cp $(srcdir)/Setup.in Setup
# Make the intermediate Makefile.pre from Makefile.pre.in
Makefile.pre: Makefile.pre.in sedscript Makefile.pre: Makefile.pre.in sedscript
sed -f sedscript $(srcdir)/Makefile.pre.in >Makefile.pre sed -f sedscript $(srcdir)/Makefile.pre.in >Makefile.pre
...@@ -176,12 +242,20 @@ Makefile.pre: Makefile.pre.in sedscript ...@@ -176,12 +242,20 @@ Makefile.pre: Makefile.pre.in sedscript
P=prefix P=prefix
E=exec_prefix E=exec_prefix
H=Generated automatically from Makefile.pre.in by sedscript. H=Generated automatically from Makefile.pre.in by sedscript.
L=LINKFORSHARED
# Make the sed script used to create Makefile.pre from Makefile.pre.in
sedscript: $(MAKEFILE) sedscript: $(MAKEFILE)
sed -n \ sed -n \
-e '1s/.*/1i\\/p' \ -e '1s/.*/1i\\/p' \
-e '2s%.*%# $H%p' \ -e '2s%.*%# $H%p' \
-e '/^VERSION=/s/^VERSION=[ ]*\(.*\)/s%@VERSION[@]%\1%/p' \ -e '/^VERSION=/s/^VERSION=[ ]*\(.*\)/s%@VERSION[@]%\1%/p' \
-e '/^CC=/s/^CC=[ ]*\(.*\)/s%@CC[@]%\1%/p' \ -e '/^CC=/s/^CC=[ ]*\(.*\)/s%@CC[@]%\1%/p' \
-e '/^CCC=/s/^CCC=[ ]*\(.*\)/s%#@SET_CCC[@]%CCC=\1%/p' \
-e '/^LINKCC=/s/^LINKCC=[ ]*\(.*\)/s%@LINKCC[@]%\1%/p' \
-e '/^OPT=/s/^OPT=[ ]*\(.*\)/s%@OPT[@]%\1%/p' \
-e '/^LDFLAGS=/s/^LDFLAGS=[ ]*\(.*\)/s%@LDFLAGS[@]%\1%/p' \
-e '/^LDLAST=/s/^LDLAST=[ ]*\(.*\)/s%@LDLAST[@]%\1%/p' \
-e '/^DEFS=/s/^DEFS=[ ]*\(.*\)/s%@DEFS[@]%\1%/p' \ -e '/^DEFS=/s/^DEFS=[ ]*\(.*\)/s%@DEFS[@]%\1%/p' \
-e '/^LIBS=/s/^LIBS=[ ]*\(.*\)/s%@LIBS[@]%\1%/p' \ -e '/^LIBS=/s/^LIBS=[ ]*\(.*\)/s%@LIBS[@]%\1%/p' \
-e '/^LIBM=/s/^LIBM=[ ]*\(.*\)/s%@LIBM[@]%\1%/p' \ -e '/^LIBM=/s/^LIBM=[ ]*\(.*\)/s%@LIBM[@]%\1%/p' \
...@@ -191,26 +265,41 @@ sedscript: $(MAKEFILE) ...@@ -191,26 +265,41 @@ sedscript: $(MAKEFILE)
-e '/^SO=/s/^SO=[ ]*\(.*\)/s%@SO[@]%\1%/p' \ -e '/^SO=/s/^SO=[ ]*\(.*\)/s%@SO[@]%\1%/p' \
-e '/^LDSHARED=/s/^LDSHARED=[ ]*\(.*\)/s%@LDSHARED[@]%\1%/p' \ -e '/^LDSHARED=/s/^LDSHARED=[ ]*\(.*\)/s%@LDSHARED[@]%\1%/p' \
-e '/^CCSHARED=/s/^CCSHARED=[ ]*\(.*\)/s%@CCSHARED[@]%\1%/p' \ -e '/^CCSHARED=/s/^CCSHARED=[ ]*\(.*\)/s%@CCSHARED[@]%\1%/p' \
-e '/^LINKFORSHARED=/s/^LINKFORSHARED=[ ]*\(.*\)/s%@LINKFORSHARED[@]%\1%/p' \ -e '/^SGI_ABI=/s/^SGI_ABI=[ ]*\(.*\)/s%@SGI_ABI[@]%\1%/p' \
-e '/^$L=/s/^$L=[ ]*\(.*\)/s%@$L[@]%\1%/p' \
-e '/^$P=/s/^$P=\(.*\)/s%^$P=.*%$P=\1%/p' \ -e '/^$P=/s/^$P=\(.*\)/s%^$P=.*%$P=\1%/p' \
-e '/^$E=/s/^$E=\(.*\)/s%^$E=.*%$E=\1%/p' \ -e '/^$E=/s/^$E=\(.*\)/s%^$E=.*%$E=\1%/p' \
$(MAKEFILE) >sedscript $(MAKEFILE) >sedscript
( \ echo "/^#@SET_CCC@/d" >>sedscript
echo "/^installdir=/s%=.*%= $(installdir)%"; \ echo "/^installdir=/s%=.*%= $(installdir)%" >>sedscript
echo "/^exec_installdir=/s%=.*%=$(exec_installdir)%"; \ echo "/^exec_installdir=/s%=.*%=$(exec_installdir)%" >>sedscript
echo "/^srcdir=/s%=.*%= $(srcdir)%"; \ echo "/^srcdir=/s%=.*%= $(srcdir)%" >>sedscript
echo "/^VPATH=/s%=.*%= $(VPATH)%"; \ echo "/^VPATH=/s%=.*%= $(VPATH)%" >>sedscript
echo "/^LINKPATH=/s%=.*%= $(LINKPATH)%"; \ echo "/^LINKPATH=/s%=.*%= $(LINKPATH)%" >>sedscript
echo "/^OPT=/s%=.*%= $(OPT)%"; \ echo "/^BASELIB=/s%=.*%= $(BASELIB)%" >>sedscript
echo "/^BASELIB=/s%=.*%= $(BASELIB)%"; \ echo "/^BASESETUP=/s%=.*%= $(BASESETUP)%" >>sedscript
echo "/^BASESETUP=/s%=.*%= $(BASESETUP)%"; \
) >>sedscript # Bootstrap target
boot: clobber
VERSION=`$(PYTHON) -c "import sys; print sys.version[:3]"`; \
installdir=`$(PYTHON) -c "import sys; print sys.prefix"`; \
exec_installdir=`$(PYTHON) -c "import sys; print sys.exec_prefix"`; \
$(MAKE) -f $(srcdir)/Makefile.pre.in VPATH=$(VPATH) srcdir=$(srcdir) \
VERSION=$$VERSION \
installdir=$$installdir \
exec_installdir=$$exec_installdir \
Makefile
# Handy target to remove intermediate files and backups
clean: clean:
-rm -f *.o *~ -rm -f *.o *~
# Handy target to remove everything that is easily regenerated
clobber: clean clobber: clean
-rm -f python lib.a sedscript config.c Makefile.pre -rm -f *.a tags TAGS config.c Makefile.pre $(TARGET) sedscript
-rm -f *.so *.sl so_locations
# Handy target to remove everything you don't want to distribute
distclean: clobber distclean: clobber
-rm -f Makefile Setup -rm -f Makefile Setup
*shared* *shared*
pyexpat pyexpat.o expat/libexpat.a -Iexpat/xmlparse pyexpat pyexpat.c -DXML_NS -Iexpat/xmlparse -Iexpat/xmltok expat/xmlparse/xmlparse.c expat/xmlparse/hashtable.c expat/xmltok/xmlrole.c expat/xmltok/xmltok.c
CC=cc CC=gcc
CFLAGS=-O2 -Ixmltok -Ixmlparse # If you know what your system's byte order is, define XML_BYTE_ORDER:
# use -DXML_BYTE_ORDER=12 for little-endian byte order;
# use -DXML_BYTE_ORDER=21 for big-endian (network) byte order.
# -DXML_NS adds support for checking of lexical aspects of XML namespaces spec
# -DXML_MIN_SIZE makes a smaller but slower parser
CFLAGS=-O2 -Ixmltok -Ixmlparse -DXML_NS
# Use one of the next two lines; unixfilemap is better if it works. # Use one of the next two lines; unixfilemap is better if it works.
FILEMAP_OBJ=xmlwf/unixfilemap.o FILEMAP_OBJ=xmlwf/unixfilemap.o
#FILEMAP_OBJ=xmlwf/readfilemap.o #FILEMAP_OBJ=xmlwf/readfilemap.o
OBJS=xmltok/xmltok.o \ OBJS=xmltok/xmltok.o \
xmltok/xmlrole.o \ xmltok/xmlrole.o \
xmlwf/xmlwf.o \ xmlwf/xmlwf.o \
xmlwf/xmlfile.o \
xmlwf/codepage.o \
xmlparse/xmlparse.o \ xmlparse/xmlparse.o \
xmlparse/hashtable.o \ xmlparse/hashtable.o \
$(FILEMAP_OBJ) $(FILEMAP_OBJ)
EXE= EXE=
all: xmlwf/xmlwf$(EXE) all: xmlwf/xmlwf$(EXE)
libexpat.a: $(OBJS)
ar cr libexpat.a $(OBJS)
xmlwf/xmlwf$(EXE): $(OBJS) xmlwf/xmlwf$(EXE): $(OBJS)
$(CC) $(CFLAGS) -o $@ $(OBJS) $(CC) $(CFLAGS) -o $@ $(OBJS)
......
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
"http://www.w3.org/TR/REC-html40/loose.dtd"> "http://www.w3.org/TR/REC-html40/loose.dtd">
<HTML> <HTML>
<TITLE>expat</TITLE> <TITLE>expat</TITLE>
<BODY> <BODY>
<H1>expat - XML Parser Toolkit</H1> <H1>expat - XML Parser Toolkit</H1>
<H3>Version 19980405</H3>
<P> <H3>Version 1.1</H3>
Copyright (c) 1998 James Clark. Expat is subject to the <A
HREF="MPL-1_0.html">Mozilla Public License Version 1.0</A>. You may <P>Copyright (c) 1998, 1999 James Clark. Expat is subject to the <A
not use expat except in compliance with this license. Please contact HREF="http://www.mozilla.org/NPL/NPL-1_1Final.html">Mozilla Public
me if you wish to negotiate an alternative license.</P><P> License Version 1.1</A>. Alternatively you may use expat under the <A
Expat is an <A HREF="http://www.w3.org/TR/1998/REC-xml-19980210">XML href="http://www.gnu.org/copyleft/gpl.html">GNU General Public
1.0</A> parser written in C. It aims to be fully conforming. It is License</A> instead. Please contact me if you wish to negotiate an
currently not a validating XML processor. alternative license.</P>
Expat can be downloaded from <A href =
"ftp://ftp.jclark.com/pub/xml/expat.zip">ftp://ftp.jclark.com/pub/xml/expat.zip</A>. <P>Expat is an <A
This is a beta-test version.</P> HREF="http://www.w3.org/TR/1998/REC-xml-19980210">XML 1.0</A> parser
<P> written in C. It aims to be fully conforming. It is currently not a
The directory <SAMP>xmltok</SAMP> contains a low-level library for validating XML processor. The current production version of expat can
tokenizing XML. The interface is documented in <SAMP>xmltok/xmltok.h</SAMP>.</P> be downloaded from <A href = "ftp://ftp.jclark.com/pub/xml/expat.zip"
<P> >ftp://ftp.jclark.com/pub/xml/expat.zip</A>.</P>
The directory <SAMP>xmlparse</SAMP> contains an XML parser library
<P>The directory <SAMP>xmltok</SAMP> contains a low-level library for
tokenizing XML. The interface is documented in
<SAMP>xmltok/xmltok.h</SAMP>.</P>
<P>The directory <SAMP>xmlparse</SAMP> contains an XML parser library
which is built on top of the <SAMP>xmltok</SAMP> library. The which is built on top of the <SAMP>xmltok</SAMP> library. The
interface is documented in <SAMP>xmlparse/xmlparse.h</SAMP>.</P> interface is documented in <SAMP>xmlparse/xmlparse.h</SAMP>. The
<P> directory <SAMP>sample</SAMP> contains a simple example program using
The directory <SAMP>xmlwf</SAMP> contains the <SAMP>xmlwf</SAMP> this interface; <SAMP>sample/build.bat</SAMP> is a batch file to build
the example using Visual C++.</P>
<P>The directory <SAMP>xmlwf</SAMP> contains the <SAMP>xmlwf</SAMP>
application, which uses the <SAMP>xmlparse</SAMP> library. The application, which uses the <SAMP>xmlparse</SAMP> library. The
arguments to <SAMP>xmlwf</SAMP> are one or more files which are each arguments to <SAMP>xmlwf</SAMP> are one or more files which are each
to be checked for well-formedness. An option <SAMP>-d to be checked for well-formedness. An option <SAMP>-d
...@@ -33,10 +45,29 @@ file the corresponding <A ...@@ -33,10 +45,29 @@ file the corresponding <A
href="http://www.jclark.com/xml/canonxml.html">canonical XML</A> will href="http://www.jclark.com/xml/canonxml.html">canonical XML</A> will
be written to <SAMP>dir/<VAR>f</VAR></SAMP>, where be written to <SAMP>dir/<VAR>f</VAR></SAMP>, where
<SAMP><VAR>f</VAR></SAMP> is the filename (without any path) of the <SAMP><VAR>f</VAR></SAMP> is the filename (without any path) of the
input file.</P> input file. A <CODE>-x</CODE> option will cause references to
external general entities to be processed. A <CODE>-s</CODE> option
will make documents that are not standalone cause an error (a document
is considered standalone if either it is intrinsically standalone
because it has no external subset and no references to parameter
entities in the internal subset or it is declared as standalone in the
XML declaration).</P>
<P>The <SAMP>bin</SAMP> directory contains Win32 executables. The
<SAMP>lib</SAMP> directory contains Win32 import libraries.</P>
<P>Answers to some frequently asked questions about expat can be found
in the <A HREF="http://www.jclark.com/xml/expatfaq.html">expat
FAQ</A>.</P>
<P></P> <P></P>
<ADDRESS> <ADDRESS>
<A HREF="mailto:jjc@jclark.com">James Clark</A> <A HREF="mailto:jjc@jclark.com">James Clark</A>
</ADDRESS> </ADDRESS>
</BODY> </BODY>
</HTML> </HTML>
# Microsoft Developer Studio Generated NMAKE File, Format Version 4.20 # Microsoft Developer Studio Generated NMAKE File, Format Version 4.20
# ** DO NOT EDIT ** # ** DO NOT EDIT **
# TARGTYPE "Win32 (x86) Console Application" 0x0103 # TARGTYPE "Win32 (x86) Console Application" 0x0103
# TARGTYPE "Win32 (x86) Dynamic-Link Library" 0x0102 # TARGTYPE "Win32 (x86) Dynamic-Link Library" 0x0102
!IF "$(CFG)" == "" !IF "$(CFG)" == ""
CFG=xmltok - Win32 Debug CFG=xmltok - Win32 Debug
!MESSAGE No configuration specified. Defaulting to xmltok - Win32 Debug. !MESSAGE No configuration specified. Defaulting to xmltok - Win32 Debug.
!ENDIF !ENDIF
!IF "$(CFG)" != "xmlwf - Win32 Release" && "$(CFG)" != "xmlwf - Win32 Debug" &&\ !IF "$(CFG)" != "xmlwf - Win32 Release" && "$(CFG)" != "xmlwf - Win32 Debug" &&\
"$(CFG)" != "gennmtab - Win32 Release" && "$(CFG)" != "gennmtab - Win32 Debug"\ "$(CFG)" != "gennmtab - Win32 Release" && "$(CFG)" != "gennmtab - Win32 Debug"\
&& "$(CFG)" != "xmlparse - Win32 Release" && "$(CFG)" !=\ && "$(CFG)" != "xmlparse - Win32 Release" && "$(CFG)" !=\
"xmlparse - Win32 Debug" && "$(CFG)" != "xmltok - Win32 Release" && "$(CFG)" !=\ "xmlparse - Win32 Debug" && "$(CFG)" != "xmltok - Win32 Release" && "$(CFG)" !=\
"xmltok - Win32 Debug" "xmltok - Win32 Debug"
!MESSAGE Invalid configuration "$(CFG)" specified. !MESSAGE Invalid configuration "$(CFG)" specified.
!MESSAGE You can specify a configuration when running NMAKE on this makefile !MESSAGE You can specify a configuration when running NMAKE on this makefile
!MESSAGE by defining the macro CFG on the command line. For example: !MESSAGE by defining the macro CFG on the command line. For example:
!MESSAGE !MESSAGE
!MESSAGE NMAKE /f "expat.mak" CFG="xmltok - Win32 Debug" !MESSAGE NMAKE /f "expat.mak" CFG="xmltok - Win32 Debug"
!MESSAGE !MESSAGE
!MESSAGE Possible choices for configuration are: !MESSAGE Possible choices for configuration are:
!MESSAGE !MESSAGE
!MESSAGE "xmlwf - Win32 Release" (based on "Win32 (x86) Console Application") !MESSAGE "xmlwf - Win32 Release" (based on "Win32 (x86) Console Application")
!MESSAGE "xmlwf - Win32 Debug" (based on "Win32 (x86) Console Application") !MESSAGE "xmlwf - Win32 Debug" (based on "Win32 (x86) Console Application")
!MESSAGE "gennmtab - Win32 Release" (based on\ !MESSAGE "gennmtab - Win32 Release" (based on\
"Win32 (x86) Console Application") "Win32 (x86) Console Application")
!MESSAGE "gennmtab - Win32 Debug" (based on "Win32 (x86) Console Application") !MESSAGE "gennmtab - Win32 Debug" (based on "Win32 (x86) Console Application")
!MESSAGE "xmlparse - Win32 Release" (based on\ !MESSAGE "xmlparse - Win32 Release" (based on\
"Win32 (x86) Dynamic-Link Library") "Win32 (x86) Dynamic-Link Library")
!MESSAGE "xmlparse - Win32 Debug" (based on "Win32 (x86) Dynamic-Link Library") !MESSAGE "xmlparse - Win32 Debug" (based on "Win32 (x86) Dynamic-Link Library")
!MESSAGE "xmltok - Win32 Release" (based on "Win32 (x86) Dynamic-Link Library") !MESSAGE "xmltok - Win32 Release" (based on "Win32 (x86) Dynamic-Link Library")
!MESSAGE "xmltok - Win32 Debug" (based on "Win32 (x86) Dynamic-Link Library") !MESSAGE "xmltok - Win32 Debug" (based on "Win32 (x86) Dynamic-Link Library")
!MESSAGE !MESSAGE
!ERROR An invalid configuration is specified. !ERROR An invalid configuration is specified.
!ENDIF !ENDIF
!IF "$(OS)" == "Windows_NT" !IF "$(OS)" == "Windows_NT"
NULL= NULL=
!ELSE !ELSE
NULL=nul NULL=nul
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Project # Begin Project
# PROP Target_Last_Scanned "xmltok - Win32 Debug" # PROP Target_Last_Scanned "xmltok - Win32 Debug"
!IF "$(CFG)" == "xmlwf - Win32 Release" !IF "$(CFG)" == "xmlwf - Win32 Release"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0 # PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "xmlwf\Release" # PROP BASE Output_Dir "xmlwf\Release"
# PROP BASE Intermediate_Dir "xmlwf\Release" # PROP BASE Intermediate_Dir "xmlwf\Release"
# PROP BASE Target_Dir "xmlwf" # PROP BASE Target_Dir "xmlwf"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 0 # PROP Use_Debug_Libraries 0
# PROP Output_Dir "xmlwf\Release" # PROP Output_Dir "xmlwf\Release"
# PROP Intermediate_Dir "xmlwf\Release" # PROP Intermediate_Dir "xmlwf\Release"
# PROP Target_Dir "xmlwf" # PROP Target_Dir "xmlwf"
OUTDIR=.\xmlwf\Release OUTDIR=.\xmlwf\Release
INTDIR=.\xmlwf\Release INTDIR=.\xmlwf\Release
ALL : "xmlparse - Win32 Release" ".\bin\xmlwf.exe" ALL : "xmlparse - Win32 Release" ".\bin\xmlwf.exe"
CLEAN : CLEAN :
-@erase "$(INTDIR)\codepage.obj"
-@erase "$(INTDIR)\win32filemap.obj" -@erase "$(INTDIR)\win32filemap.obj"
-@erase "$(INTDIR)\xmlwf.obj" -@erase "$(INTDIR)\xmlwf.obj"
-@erase ".\bin\xmlwf.exe" -@erase ".\bin\xmlwf.exe"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c # ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c
# ADD CPP /nologo /W3 /GX /O2 /I "." /I "xmlparse" /D "NDEBUG" /D "WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllimport) /YX /c # ADD CPP /nologo /W3 /GX /O2 /I "." /I "xmlparse" /D "NDEBUG" /D "WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllimport) /YX /c
CPP_PROJ=/nologo /ML /W3 /GX /O2 /I "." /I "xmlparse" /D "NDEBUG" /D "WIN32" /D\ CPP_PROJ=/nologo /ML /W3 /GX /O2 /I "." /I "xmlparse" /D "NDEBUG" /D "WIN32" /D\
"_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D\ "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D\
XMLPARSEAPI=__declspec(dllimport) /Fp"$(INTDIR)/xmlwf.pch" /YX /Fo"$(INTDIR)/"\ XMLPARSEAPI=__declspec(dllimport) /Fp"$(INTDIR)/xmlwf.pch" /YX /Fo"$(INTDIR)/"\
/c /c
CPP_OBJS=.\xmlwf\Release/ CPP_OBJS=.\xmlwf\Release/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "NDEBUG" # ADD BASE RSC /l 0x809 /d "NDEBUG"
# ADD RSC /l 0x809 /d "NDEBUG" # ADD RSC /l 0x809 /d "NDEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlwf.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlwf.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386
# ADD LINK32 setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 /out:"bin/xmlwf.exe" # ADD LINK32 setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 /out:"bin/xmlwf.exe"
LINK32_FLAGS=setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib\ LINK32_FLAGS=setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib\
comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib\ comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib\
odbc32.lib odbccp32.lib /nologo /subsystem:console /incremental:no\ odbc32.lib odbccp32.lib /nologo /subsystem:console /incremental:no\
/pdb:"$(OUTDIR)/xmlwf.pdb" /machine:I386 /out:"bin/xmlwf.exe" /pdb:"$(OUTDIR)/xmlwf.pdb" /machine:I386 /out:"bin/xmlwf.exe"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\codepage.obj" \
"$(INTDIR)\win32filemap.obj" \ "$(INTDIR)\win32filemap.obj" \
"$(INTDIR)\xmlwf.obj" \ "$(INTDIR)\xmlwf.obj" \
".\xmlparse\Release\xmlparse.lib" ".\xmlparse\Release\xmlparse.lib"
".\bin\xmlwf.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\bin\xmlwf.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "xmlwf - Win32 Debug" !ELSEIF "$(CFG)" == "xmlwf - Win32 Debug"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1 # PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "xmlwf\Debug" # PROP BASE Output_Dir "xmlwf\Debug"
# PROP BASE Intermediate_Dir "xmlwf\Debug" # PROP BASE Intermediate_Dir "xmlwf\Debug"
# PROP BASE Target_Dir "xmlwf" # PROP BASE Target_Dir "xmlwf"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 1 # PROP Use_Debug_Libraries 1
# PROP Output_Dir "xmlwf\Debug" # PROP Output_Dir "xmlwf\Debug"
# PROP Intermediate_Dir "xmlwf\Debug" # PROP Intermediate_Dir "xmlwf\Debug"
# PROP Target_Dir "xmlwf" # PROP Target_Dir "xmlwf"
OUTDIR=.\xmlwf\Debug OUTDIR=.\xmlwf\Debug
INTDIR=.\xmlwf\Debug INTDIR=.\xmlwf\Debug
ALL : "xmlparse - Win32 Debug" ".\dbgbin\xmlwf.exe" ALL : "xmlparse - Win32 Debug" ".\dbgbin\xmlwf.exe"
CLEAN : CLEAN :
-@erase "$(INTDIR)\codepage.obj"
-@erase "$(INTDIR)\vc40.idb" -@erase "$(INTDIR)\vc40.idb"
-@erase "$(INTDIR)\vc40.pdb" -@erase "$(INTDIR)\vc40.pdb"
-@erase "$(INTDIR)\win32filemap.obj" -@erase "$(INTDIR)\win32filemap.obj"
-@erase "$(INTDIR)\xmlwf.obj" -@erase "$(INTDIR)\xmlwf.obj"
-@erase "$(OUTDIR)\xmlwf.pdb" -@erase "$(OUTDIR)\xmlwf.pdb"
-@erase ".\dbgbin\xmlwf.exe" -@erase ".\dbgbin\xmlwf.exe"
-@erase ".\dbgbin\xmlwf.ilk" -@erase ".\dbgbin\xmlwf.ilk"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c # ADD BASE CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c
# ADD CPP /nologo /MDd /W3 /Gm /GX /Zi /Od /I "." /I "xmlparse" /D "_DEBUG" /D "WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllimport) /YX /c # ADD CPP /nologo /MDd /W3 /Gm /GX /Zi /Od /I "." /I "xmlparse" /D "_DEBUG" /D "WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllimport) /YX /c
CPP_PROJ=/nologo /MDd /W3 /Gm /GX /Zi /Od /I "." /I "xmlparse" /D "_DEBUG" /D\ CPP_PROJ=/nologo /MDd /W3 /Gm /GX /Zi /Od /I "." /I "xmlparse" /D "_DEBUG" /D\
"WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D\ "WIN32" /D "_CONSOLE" /D XMLTOKAPI=__declspec(dllimport) /D\
XMLPARSEAPI=__declspec(dllimport) /Fp"$(INTDIR)/xmlwf.pch" /YX /Fo"$(INTDIR)/"\ XMLPARSEAPI=__declspec(dllimport) /Fp"$(INTDIR)/xmlwf.pch" /YX /Fo"$(INTDIR)/"\
/Fd"$(INTDIR)/" /c /Fd"$(INTDIR)/" /c
CPP_OBJS=.\xmlwf\Debug/ CPP_OBJS=.\xmlwf\Debug/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "_DEBUG" # ADD BASE RSC /l 0x809 /d "_DEBUG"
# ADD RSC /l 0x809 /d "_DEBUG" # ADD RSC /l 0x809 /d "_DEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlwf.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlwf.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386
# ADD LINK32 setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /out:"dbgbin/xmlwf.exe" # ADD LINK32 setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /out:"dbgbin/xmlwf.exe"
LINK32_FLAGS=setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib\ LINK32_FLAGS=setargv.obj kernel32.lib user32.lib gdi32.lib winspool.lib\
comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib\ comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib\
odbc32.lib odbccp32.lib /nologo /subsystem:console /incremental:yes\ odbc32.lib odbccp32.lib /nologo /subsystem:console /incremental:yes\
/pdb:"$(OUTDIR)/xmlwf.pdb" /debug /machine:I386 /out:"dbgbin/xmlwf.exe" /pdb:"$(OUTDIR)/xmlwf.pdb" /debug /machine:I386 /out:"dbgbin/xmlwf.exe"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\codepage.obj" \
"$(INTDIR)\win32filemap.obj" \ "$(INTDIR)\win32filemap.obj" \
"$(INTDIR)\xmlwf.obj" \ "$(INTDIR)\xmlwf.obj" \
".\xmlparse\Debug\xmlparse.lib" ".\xmlparse\Debug\xmlparse.lib"
".\dbgbin\xmlwf.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\dbgbin\xmlwf.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "gennmtab - Win32 Release" !ELSEIF "$(CFG)" == "gennmtab - Win32 Release"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0 # PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "gennmtab\Release" # PROP BASE Output_Dir "gennmtab\Release"
# PROP BASE Intermediate_Dir "gennmtab\Release" # PROP BASE Intermediate_Dir "gennmtab\Release"
# PROP BASE Target_Dir "gennmtab" # PROP BASE Target_Dir "gennmtab"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 0 # PROP Use_Debug_Libraries 0
# PROP Output_Dir "gennmtab\Release" # PROP Output_Dir "gennmtab\Release"
# PROP Intermediate_Dir "gennmtab\Release" # PROP Intermediate_Dir "gennmtab\Release"
# PROP Target_Dir "gennmtab" # PROP Target_Dir "gennmtab"
OUTDIR=.\gennmtab\Release OUTDIR=.\gennmtab\Release
INTDIR=.\gennmtab\Release INTDIR=.\gennmtab\Release
ALL : "$(OUTDIR)\gennmtab.exe" ALL : "$(OUTDIR)\gennmtab.exe"
CLEAN : CLEAN :
-@erase "$(INTDIR)\gennmtab.obj" -@erase "$(INTDIR)\gennmtab.obj"
-@erase "$(OUTDIR)\gennmtab.exe" -@erase "$(OUTDIR)\gennmtab.exe"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c # ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c
# ADD CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c # ADD CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /YX /c
CPP_PROJ=/nologo /ML /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE"\ CPP_PROJ=/nologo /ML /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE"\
/Fp"$(INTDIR)/gennmtab.pch" /YX /Fo"$(INTDIR)/" /c /Fp"$(INTDIR)/gennmtab.pch" /YX /Fo"$(INTDIR)/" /c
CPP_OBJS=.\gennmtab\Release/ CPP_OBJS=.\gennmtab\Release/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "NDEBUG" # ADD BASE RSC /l 0x809 /d "NDEBUG"
# ADD RSC /l 0x809 /d "NDEBUG" # ADD RSC /l 0x809 /d "NDEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/gennmtab.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/gennmtab.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 # ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /subsystem:console /incremental:no\ odbccp32.lib /nologo /subsystem:console /incremental:no\
/pdb:"$(OUTDIR)/gennmtab.pdb" /machine:I386 /out:"$(OUTDIR)/gennmtab.exe" /pdb:"$(OUTDIR)/gennmtab.pdb" /machine:I386 /out:"$(OUTDIR)/gennmtab.exe"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\gennmtab.obj" "$(INTDIR)\gennmtab.obj"
"$(OUTDIR)\gennmtab.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) "$(OUTDIR)\gennmtab.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "gennmtab - Win32 Debug" !ELSEIF "$(CFG)" == "gennmtab - Win32 Debug"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1 # PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "gennmtab\Debug" # PROP BASE Output_Dir "gennmtab\Debug"
# PROP BASE Intermediate_Dir "gennmtab\Debug" # PROP BASE Intermediate_Dir "gennmtab\Debug"
# PROP BASE Target_Dir "gennmtab" # PROP BASE Target_Dir "gennmtab"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 1 # PROP Use_Debug_Libraries 1
# PROP Output_Dir "gennmtab\Debug" # PROP Output_Dir "gennmtab\Debug"
# PROP Intermediate_Dir "gennmtab\Debug" # PROP Intermediate_Dir "gennmtab\Debug"
# PROP Target_Dir "gennmtab" # PROP Target_Dir "gennmtab"
OUTDIR=.\gennmtab\Debug OUTDIR=.\gennmtab\Debug
INTDIR=.\gennmtab\Debug INTDIR=.\gennmtab\Debug
ALL : "$(OUTDIR)\gennmtab.exe" ALL : "$(OUTDIR)\gennmtab.exe"
CLEAN : CLEAN :
-@erase "$(INTDIR)\gennmtab.obj" -@erase "$(INTDIR)\gennmtab.obj"
-@erase "$(INTDIR)\vc40.idb" -@erase "$(INTDIR)\vc40.idb"
-@erase "$(INTDIR)\vc40.pdb" -@erase "$(INTDIR)\vc40.pdb"
-@erase "$(OUTDIR)\gennmtab.exe" -@erase "$(OUTDIR)\gennmtab.exe"
-@erase "$(OUTDIR)\gennmtab.ilk" -@erase "$(OUTDIR)\gennmtab.ilk"
-@erase "$(OUTDIR)\gennmtab.pdb" -@erase "$(OUTDIR)\gennmtab.pdb"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c # ADD BASE CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c
# ADD CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c # ADD CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /YX /c
CPP_PROJ=/nologo /MLd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE"\ CPP_PROJ=/nologo /MLd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE"\
/Fp"$(INTDIR)/gennmtab.pch" /YX /Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c /Fp"$(INTDIR)/gennmtab.pch" /YX /Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c
CPP_OBJS=.\gennmtab\Debug/ CPP_OBJS=.\gennmtab\Debug/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "_DEBUG" # ADD BASE RSC /l 0x809 /d "_DEBUG"
# ADD RSC /l 0x809 /d "_DEBUG" # ADD RSC /l 0x809 /d "_DEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/gennmtab.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/gennmtab.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 # ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /subsystem:console /incremental:yes\ odbccp32.lib /nologo /subsystem:console /incremental:yes\
/pdb:"$(OUTDIR)/gennmtab.pdb" /debug /machine:I386\ /pdb:"$(OUTDIR)/gennmtab.pdb" /debug /machine:I386\
/out:"$(OUTDIR)/gennmtab.exe" /out:"$(OUTDIR)/gennmtab.exe"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\gennmtab.obj" "$(INTDIR)\gennmtab.obj"
"$(OUTDIR)\gennmtab.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) "$(OUTDIR)\gennmtab.exe" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "xmlparse - Win32 Release" !ELSEIF "$(CFG)" == "xmlparse - Win32 Release"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0 # PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "xmlparse\Release" # PROP BASE Output_Dir "xmlparse\Release"
# PROP BASE Intermediate_Dir "xmlparse\Release" # PROP BASE Intermediate_Dir "xmlparse\Release"
# PROP BASE Target_Dir "xmlparse" # PROP BASE Target_Dir "xmlparse"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 0 # PROP Use_Debug_Libraries 0
# PROP Output_Dir "xmlparse\Release" # PROP Output_Dir "xmlparse\Release"
# PROP Intermediate_Dir "xmlparse\Release" # PROP Intermediate_Dir "xmlparse\Release"
# PROP Target_Dir "xmlparse" # PROP Target_Dir "xmlparse"
OUTDIR=.\xmlparse\Release OUTDIR=.\xmlparse\Release
INTDIR=.\xmlparse\Release INTDIR=.\xmlparse\Release
ALL : "xmltok - Win32 Release" ".\bin\xmlparse.dll" ALL : "xmltok - Win32 Release" ".\bin\xmlparse.dll"
CLEAN : CLEAN :
-@erase "$(INTDIR)\hashtable.obj" -@erase "$(INTDIR)\hashtable.obj"
-@erase "$(INTDIR)\xmlparse.obj" -@erase "$(INTDIR)\xmlparse.obj"
-@erase "$(OUTDIR)\xmlparse.exp" -@erase "$(OUTDIR)\xmlparse.exp"
-@erase "$(OUTDIR)\xmlparse.lib" -@erase "$(OUTDIR)\xmlparse.lib"
-@erase ".\bin\xmlparse.dll" -@erase ".\bin\xmlparse.dll"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c
# ADD CPP /nologo /W3 /GX /O2 /I "xmltok" /I "xmlwf" /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /YX /c # ADD CPP /nologo /W3 /GX /O2 /I "xmltok" /I "xmlwf" /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /YX /c
CPP_PROJ=/nologo /ML /W3 /GX /O2 /I "xmltok" /I "xmlwf" /D "NDEBUG" /D "WIN32"\ CPP_PROJ=/nologo /ML /W3 /GX /O2 /I "xmltok" /I "xmlwf" /D "NDEBUG" /D "WIN32"\
/D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D\ /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D\
XMLPARSEAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmlparse.pch" /YX\ XMLPARSEAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmlparse.pch" /YX\
/Fo"$(INTDIR)/" /c /Fo"$(INTDIR)/" /c
CPP_OBJS=.\xmlparse\Release/ CPP_OBJS=.\xmlparse\Release/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
MTL=mktyplib.exe MTL=mktyplib.exe
# ADD BASE MTL /nologo /D "NDEBUG" /win32 # ADD BASE MTL /nologo /D "NDEBUG" /win32
# ADD MTL /nologo /D "NDEBUG" /win32 # ADD MTL /nologo /D "NDEBUG" /win32
MTL_PROJ=/nologo /D "NDEBUG" /win32 MTL_PROJ=/nologo /D "NDEBUG" /win32
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "NDEBUG" # ADD BASE RSC /l 0x809 /d "NDEBUG"
# ADD RSC /l 0x809 /d "NDEBUG" # ADD RSC /l 0x809 /d "NDEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlparse.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlparse.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /base:0x20000000 /subsystem:windows /dll /machine:I386 /out:"bin/xmlparse.dll"
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386 /out:"bin/xmlparse.dll"
# SUBTRACT LINK32 /profile # SUBTRACT LINK32 /profile
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /base:0x20000000 /subsystem:windows /dll /incremental:no\
odbccp32.lib /nologo /subsystem:windows /dll /incremental:no\
/pdb:"$(OUTDIR)/xmlparse.pdb" /machine:I386 /out:"bin/xmlparse.dll"\ /pdb:"$(OUTDIR)/xmlparse.pdb" /machine:I386 /out:"bin/xmlparse.dll"\
/implib:"$(OUTDIR)/xmlparse.lib" /implib:"$(OUTDIR)/xmlparse.lib"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\hashtable.obj" \ "$(INTDIR)\hashtable.obj" \
"$(INTDIR)\xmlparse.obj" \ "$(INTDIR)\xmlparse.obj" \
".\xmltok\Release\xmltok.lib" ".\xmltok\Release\xmltok.lib"
".\bin\xmlparse.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\bin\xmlparse.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "xmlparse - Win32 Debug" !ELSEIF "$(CFG)" == "xmlparse - Win32 Debug"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1 # PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "xmlparse\Debug" # PROP BASE Output_Dir "xmlparse\Debug"
# PROP BASE Intermediate_Dir "xmlparse\Debug" # PROP BASE Intermediate_Dir "xmlparse\Debug"
# PROP BASE Target_Dir "xmlparse" # PROP BASE Target_Dir "xmlparse"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 1 # PROP Use_Debug_Libraries 1
# PROP Output_Dir "xmlparse\Debug" # PROP Output_Dir "xmlparse\Debug"
# PROP Intermediate_Dir "xmlparse\Debug" # PROP Intermediate_Dir "xmlparse\Debug"
# PROP Target_Dir "xmlparse" # PROP Target_Dir "xmlparse"
OUTDIR=.\xmlparse\Debug OUTDIR=.\xmlparse\Debug
INTDIR=.\xmlparse\Debug INTDIR=.\xmlparse\Debug
ALL : "xmltok - Win32 Debug" ".\dbgbin\xmlparse.dll" ALL : "xmltok - Win32 Debug" ".\dbgbin\xmlparse.dll"
CLEAN : CLEAN :
-@erase "$(INTDIR)\hashtable.obj" -@erase "$(INTDIR)\hashtable.obj"
-@erase "$(INTDIR)\vc40.idb" -@erase "$(INTDIR)\vc40.idb"
-@erase "$(INTDIR)\vc40.pdb" -@erase "$(INTDIR)\vc40.pdb"
-@erase "$(INTDIR)\xmlparse.obj" -@erase "$(INTDIR)\xmlparse.obj"
-@erase "$(OUTDIR)\xmlparse.exp" -@erase "$(OUTDIR)\xmlparse.exp"
-@erase "$(OUTDIR)\xmlparse.lib" -@erase "$(OUTDIR)\xmlparse.lib"
-@erase "$(OUTDIR)\xmlparse.pdb" -@erase "$(OUTDIR)\xmlparse.pdb"
-@erase ".\dbgbin\xmlparse.dll" -@erase ".\dbgbin\xmlparse.dll"
-@erase ".\dbgbin\xmlparse.ilk" -@erase ".\dbgbin\xmlparse.ilk"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c # ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c
# ADD CPP /nologo /MDd /W3 /Gm /GX /Zi /Od /I "xmltok" /I "xmlwf" /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /YX /c # ADD CPP /nologo /MDd /W3 /Gm /GX /Zi /Od /I "xmltok" /I "xmlwf" /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D XMLPARSEAPI=__declspec(dllexport) /YX /c
CPP_PROJ=/nologo /MDd /W3 /Gm /GX /Zi /Od /I "xmltok" /I "xmlwf" /D "_DEBUG" /D\ CPP_PROJ=/nologo /MDd /W3 /Gm /GX /Zi /Od /I "xmltok" /I "xmlwf" /D "_DEBUG" /D\
"WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D\ "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllimport) /D\
XMLPARSEAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmlparse.pch" /YX\ XMLPARSEAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmlparse.pch" /YX\
/Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c /Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c
CPP_OBJS=.\xmlparse\Debug/ CPP_OBJS=.\xmlparse\Debug/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
MTL=mktyplib.exe MTL=mktyplib.exe
# ADD BASE MTL /nologo /D "_DEBUG" /win32 # ADD BASE MTL /nologo /D "_DEBUG" /win32
# ADD MTL /nologo /D "_DEBUG" /win32 # ADD MTL /nologo /D "_DEBUG" /win32
MTL_PROJ=/nologo /D "_DEBUG" /win32 MTL_PROJ=/nologo /D "_DEBUG" /win32
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "_DEBUG" # ADD BASE RSC /l 0x809 /d "_DEBUG"
# ADD RSC /l 0x809 /d "_DEBUG" # ADD RSC /l 0x809 /d "_DEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlparse.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmlparse.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /base:0x20000000 /subsystem:windows /dll /debug /machine:I386 /out:"dbgbin/xmlparse.dll"
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 /out:"dbgbin/xmlparse.dll"
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /base:0x20000000 /subsystem:windows /dll /incremental:yes\
odbccp32.lib /nologo /subsystem:windows /dll /incremental:yes\
/pdb:"$(OUTDIR)/xmlparse.pdb" /debug /machine:I386 /out:"dbgbin/xmlparse.dll"\ /pdb:"$(OUTDIR)/xmlparse.pdb" /debug /machine:I386 /out:"dbgbin/xmlparse.dll"\
/implib:"$(OUTDIR)/xmlparse.lib" /implib:"$(OUTDIR)/xmlparse.lib"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\hashtable.obj" \ "$(INTDIR)\hashtable.obj" \
"$(INTDIR)\xmlparse.obj" \ "$(INTDIR)\xmlparse.obj" \
".\xmltok\Debug\xmltok.lib" ".\xmltok\Debug\xmltok.lib"
".\dbgbin\xmlparse.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\dbgbin\xmlparse.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "xmltok - Win32 Release" !ELSEIF "$(CFG)" == "xmltok - Win32 Release"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0 # PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "xmltok\Release" # PROP BASE Output_Dir "xmltok\Release"
# PROP BASE Intermediate_Dir "xmltok\Release" # PROP BASE Intermediate_Dir "xmltok\Release"
# PROP BASE Target_Dir "xmltok" # PROP BASE Target_Dir "xmltok"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 0 # PROP Use_Debug_Libraries 0
# PROP Output_Dir "xmltok\Release" # PROP Output_Dir "xmltok\Release"
# PROP Intermediate_Dir "xmltok\Release" # PROP Intermediate_Dir "xmltok\Release"
# PROP Target_Dir "xmltok" # PROP Target_Dir "xmltok"
OUTDIR=.\xmltok\Release OUTDIR=.\xmltok\Release
INTDIR=.\xmltok\Release INTDIR=.\xmltok\Release
ALL : ".\bin\xmltok.dll" ALL : ".\bin\xmltok.dll"
CLEAN : CLEAN :
-@erase "$(INTDIR)\dllmain.obj" -@erase "$(INTDIR)\dllmain.obj"
-@erase "$(INTDIR)\xmlrole.obj" -@erase "$(INTDIR)\xmlrole.obj"
-@erase "$(INTDIR)\xmltok.obj" -@erase "$(INTDIR)\xmltok.obj"
-@erase "$(OUTDIR)\xmltok.exp" -@erase "$(OUTDIR)\xmltok.exp"
-@erase "$(OUTDIR)\xmltok.lib" -@erase "$(OUTDIR)\xmltok.lib"
-@erase ".\bin\xmltok.dll" -@erase ".\bin\xmltok.dll"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /c
# ADD CPP /nologo /MT /W3 /GX /O2 /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllexport) /YX /c # ADD CPP /nologo /MT /W3 /GX /O2 /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllexport) /YX /c
CPP_PROJ=/nologo /MT /W3 /GX /O2 /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D\ CPP_PROJ=/nologo /MT /W3 /GX /O2 /D "NDEBUG" /D "WIN32" /D "_WINDOWS" /D\
XMLTOKAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmltok.pch" /YX /Fo"$(INTDIR)/"\ XMLTOKAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmltok.pch" /YX /Fo"$(INTDIR)/"\
/c /c
CPP_OBJS=.\xmltok\Release/ CPP_OBJS=.\xmltok\Release/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
MTL=mktyplib.exe MTL=mktyplib.exe
# ADD BASE MTL /nologo /D "NDEBUG" /win32 # ADD BASE MTL /nologo /D "NDEBUG" /win32
# ADD MTL /nologo /D "NDEBUG" /win32 # ADD MTL /nologo /D "NDEBUG" /win32
MTL_PROJ=/nologo /D "NDEBUG" /win32 MTL_PROJ=/nologo /D "NDEBUG" /win32
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "NDEBUG" # ADD BASE RSC /l 0x809 /d "NDEBUG"
# ADD RSC /l 0x809 /d "NDEBUG" # ADD RSC /l 0x809 /d "NDEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmltok.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmltok.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /machine:I386 /out:"bin/xmltok.dll" # ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /machine:I386 /out:"bin/xmltok.dll"
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /incremental:no\ odbccp32.lib /nologo /entry:"DllMain" /subsystem:windows /dll /incremental:no\
/pdb:"$(OUTDIR)/xmltok.pdb" /machine:I386 /out:"bin/xmltok.dll"\ /pdb:"$(OUTDIR)/xmltok.pdb" /machine:I386 /out:"bin/xmltok.dll"\
/implib:"$(OUTDIR)/xmltok.lib" /implib:"$(OUTDIR)/xmltok.lib"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\dllmain.obj" \ "$(INTDIR)\dllmain.obj" \
"$(INTDIR)\xmlrole.obj" \ "$(INTDIR)\xmlrole.obj" \
"$(INTDIR)\xmltok.obj" "$(INTDIR)\xmltok.obj"
".\bin\xmltok.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\bin\xmltok.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ELSEIF "$(CFG)" == "xmltok - Win32 Debug" !ELSEIF "$(CFG)" == "xmltok - Win32 Debug"
# PROP BASE Use_MFC 0 # PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1 # PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "xmltok\Debug" # PROP BASE Output_Dir "xmltok\Debug"
# PROP BASE Intermediate_Dir "xmltok\Debug" # PROP BASE Intermediate_Dir "xmltok\Debug"
# PROP BASE Target_Dir "xmltok" # PROP BASE Target_Dir "xmltok"
# PROP Use_MFC 0 # PROP Use_MFC 0
# PROP Use_Debug_Libraries 1 # PROP Use_Debug_Libraries 1
# PROP Output_Dir "xmltok\Debug" # PROP Output_Dir "xmltok\Debug"
# PROP Intermediate_Dir "xmltok\Debug" # PROP Intermediate_Dir "xmltok\Debug"
# PROP Target_Dir "xmltok" # PROP Target_Dir "xmltok"
OUTDIR=.\xmltok\Debug OUTDIR=.\xmltok\Debug
INTDIR=.\xmltok\Debug INTDIR=.\xmltok\Debug
ALL : ".\dbgbin\xmltok.dll" ALL : ".\dbgbin\xmltok.dll"
CLEAN : CLEAN :
-@erase "$(INTDIR)\dllmain.obj" -@erase "$(INTDIR)\dllmain.obj"
-@erase "$(INTDIR)\vc40.idb" -@erase "$(INTDIR)\vc40.idb"
-@erase "$(INTDIR)\vc40.pdb" -@erase "$(INTDIR)\vc40.pdb"
-@erase "$(INTDIR)\xmlrole.obj" -@erase "$(INTDIR)\xmlrole.obj"
-@erase "$(INTDIR)\xmltok.obj" -@erase "$(INTDIR)\xmltok.obj"
-@erase "$(OUTDIR)\xmltok.exp" -@erase "$(OUTDIR)\xmltok.exp"
-@erase "$(OUTDIR)\xmltok.lib" -@erase "$(OUTDIR)\xmltok.lib"
-@erase "$(OUTDIR)\xmltok.pdb" -@erase "$(OUTDIR)\xmltok.pdb"
-@erase ".\dbgbin\xmltok.dll" -@erase ".\dbgbin\xmltok.dll"
-@erase ".\dbgbin\xmltok.ilk" -@erase ".\dbgbin\xmltok.ilk"
"$(OUTDIR)" : "$(OUTDIR)" :
if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)" if not exist "$(OUTDIR)/$(NULL)" mkdir "$(OUTDIR)"
CPP=cl.exe CPP=cl.exe
# ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c # ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /c
# ADD CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllexport) /YX /c # ADD CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "_DEBUG" /D "WIN32" /D "_WINDOWS" /D XMLTOKAPI=__declspec(dllexport) /YX /c
CPP_PROJ=/nologo /MTd /W3 /Gm /GX /Zi /Od /D "_DEBUG" /D "WIN32" /D "_WINDOWS"\ CPP_PROJ=/nologo /MTd /W3 /Gm /GX /Zi /Od /D "_DEBUG" /D "WIN32" /D "_WINDOWS"\
/D XMLTOKAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmltok.pch" /YX\ /D XMLTOKAPI=__declspec(dllexport) /Fp"$(INTDIR)/xmltok.pch" /YX\
/Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c /Fo"$(INTDIR)/" /Fd"$(INTDIR)/" /c
CPP_OBJS=.\xmltok\Debug/ CPP_OBJS=.\xmltok\Debug/
CPP_SBRS=.\. CPP_SBRS=.\.
.c{$(CPP_OBJS)}.obj: .c{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_OBJS)}.obj: .cpp{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_OBJS)}.obj: .cxx{$(CPP_OBJS)}.obj:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.c{$(CPP_SBRS)}.sbr: .c{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cpp{$(CPP_SBRS)}.sbr: .cpp{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
.cxx{$(CPP_SBRS)}.sbr: .cxx{$(CPP_SBRS)}.sbr:
$(CPP) $(CPP_PROJ) $< $(CPP) $(CPP_PROJ) $<
MTL=mktyplib.exe MTL=mktyplib.exe
# ADD BASE MTL /nologo /D "_DEBUG" /win32 # ADD BASE MTL /nologo /D "_DEBUG" /win32
# ADD MTL /nologo /D "_DEBUG" /win32 # ADD MTL /nologo /D "_DEBUG" /win32
MTL_PROJ=/nologo /D "_DEBUG" /win32 MTL_PROJ=/nologo /D "_DEBUG" /win32
RSC=rc.exe RSC=rc.exe
# ADD BASE RSC /l 0x809 /d "_DEBUG" # ADD BASE RSC /l 0x809 /d "_DEBUG"
# ADD RSC /l 0x809 /d "_DEBUG" # ADD RSC /l 0x809 /d "_DEBUG"
BSC32=bscmake.exe BSC32=bscmake.exe
# ADD BASE BSC32 /nologo # ADD BASE BSC32 /nologo
# ADD BSC32 /nologo # ADD BSC32 /nologo
BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmltok.bsc" BSC32_FLAGS=/nologo /o"$(OUTDIR)/xmltok.bsc"
BSC32_SBRS= \ BSC32_SBRS= \
LINK32=link.exe LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 /out:"dbgbin/xmltok.dll" # ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 /out:"dbgbin/xmltok.dll"
LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\ LINK32_FLAGS=kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib\
advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\ advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib\
odbccp32.lib /nologo /subsystem:windows /dll /incremental:yes\ odbccp32.lib /nologo /subsystem:windows /dll /incremental:yes\
/pdb:"$(OUTDIR)/xmltok.pdb" /debug /machine:I386 /out:"dbgbin/xmltok.dll"\ /pdb:"$(OUTDIR)/xmltok.pdb" /debug /machine:I386 /out:"dbgbin/xmltok.dll"\
/implib:"$(OUTDIR)/xmltok.lib" /implib:"$(OUTDIR)/xmltok.lib"
LINK32_OBJS= \ LINK32_OBJS= \
"$(INTDIR)\dllmain.obj" \ "$(INTDIR)\dllmain.obj" \
"$(INTDIR)\xmlrole.obj" \ "$(INTDIR)\xmlrole.obj" \
"$(INTDIR)\xmltok.obj" "$(INTDIR)\xmltok.obj"
".\dbgbin\xmltok.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS) ".\dbgbin\xmltok.dll" : "$(OUTDIR)" $(DEF_FILE) $(LINK32_OBJS)
$(LINK32) @<< $(LINK32) @<<
$(LINK32_FLAGS) $(LINK32_OBJS) $(LINK32_FLAGS) $(LINK32_OBJS)
<< <<
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Target # Begin Target
# Name "xmlwf - Win32 Release" # Name "xmlwf - Win32 Release"
# Name "xmlwf - Win32 Debug" # Name "xmlwf - Win32 Debug"
!IF "$(CFG)" == "xmlwf - Win32 Release" !IF "$(CFG)" == "xmlwf - Win32 Release"
!ELSEIF "$(CFG)" == "xmlwf - Win32 Debug" !ELSEIF "$(CFG)" == "xmlwf - Win32 Debug"
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlwf\xmlwf.c SOURCE=.\xmlwf\xmlwf.c
DEP_CPP_XMLWF=\ DEP_CPP_XMLWF=\
".\xmlparse\xmlparse.h"\ ".\xmlparse\xmlparse.h"\
".\xmlwf\codepage.h"\
".\xmlwf\filemap.h"\ ".\xmlwf\filemap.h"\
"$(INTDIR)\xmlwf.obj" : $(SOURCE) $(DEP_CPP_XMLWF) "$(INTDIR)" "$(INTDIR)\xmlwf.obj" : $(SOURCE) $(DEP_CPP_XMLWF) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE) $(CPP) $(CPP_PROJ) $(SOURCE)
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlwf\win32filemap.c SOURCE=.\xmlwf\win32filemap.c
DEP_CPP_WIN32=\ DEP_CPP_WIN32=\
".\xmlwf\filemap.h"\ ".\xmlwf\filemap.h"\
"$(INTDIR)\win32filemap.obj" : $(SOURCE) $(DEP_CPP_WIN32) "$(INTDIR)" "$(INTDIR)\win32filemap.obj" : $(SOURCE) $(DEP_CPP_WIN32) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE) $(CPP) $(CPP_PROJ) $(SOURCE)
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlwf\unixfilemap.c SOURCE=.\xmlwf\unixfilemap.c
DEP_CPP_UNIXF=\ DEP_CPP_UNIXF=\
".\xmlwf\filemap.h"\ ".\xmlwf\filemap.h"\
{$(INCLUDE)}"\sys\stat.h"\ {$(INCLUDE)}"\sys\stat.h"\
{$(INCLUDE)}"\sys\TYPES.H"\ {$(INCLUDE)}"\sys\TYPES.H"\
# PROP Exclude_From_Build 1 # PROP Exclude_From_Build 1
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlwf\readfilemap.c SOURCE=.\xmlwf\readfilemap.c
DEP_CPP_READF=\ DEP_CPP_READF=\
{$(INCLUDE)}"\sys\stat.h"\ {$(INCLUDE)}"\sys\stat.h"\
{$(INCLUDE)}"\sys\TYPES.H"\ {$(INCLUDE)}"\sys\TYPES.H"\
# PROP Exclude_From_Build 1 # PROP Exclude_From_Build 1
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Project Dependency # Begin Project Dependency
# Project_Dep_Name "xmlparse" # Project_Dep_Name "xmlparse"
!IF "$(CFG)" == "xmlwf - Win32 Release" !IF "$(CFG)" == "xmlwf - Win32 Release"
"xmlparse - Win32 Release" : "xmlparse - Win32 Release" :
$(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmlparse - Win32 Release" $(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmlparse - Win32 Release"
!ELSEIF "$(CFG)" == "xmlwf - Win32 Debug" !ELSEIF "$(CFG)" == "xmlwf - Win32 Debug"
"xmlparse - Win32 Debug" : "xmlparse - Win32 Debug" :
$(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmlparse - Win32 Debug" $(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmlparse - Win32 Debug"
!ENDIF
# End Project Dependency
################################################################################
# Begin Source File
!ENDIF SOURCE=.\xmlwf\codepage.c
DEP_CPP_CODEP=\
".\xmlwf\codepage.h"\
"$(INTDIR)\codepage.obj" : $(SOURCE) $(DEP_CPP_CODEP) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
# End Project Dependency
# End Source File
# End Target # End Target
################################################################################ ################################################################################
# Begin Target # Begin Target
# Name "gennmtab - Win32 Release" # Name "gennmtab - Win32 Release"
# Name "gennmtab - Win32 Debug" # Name "gennmtab - Win32 Debug"
!IF "$(CFG)" == "gennmtab - Win32 Release" !IF "$(CFG)" == "gennmtab - Win32 Release"
!ELSEIF "$(CFG)" == "gennmtab - Win32 Debug" !ELSEIF "$(CFG)" == "gennmtab - Win32 Debug"
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\gennmtab\gennmtab.c SOURCE=.\gennmtab\gennmtab.c
"$(INTDIR)\gennmtab.obj" : $(SOURCE) "$(INTDIR)" "$(INTDIR)\gennmtab.obj" : $(SOURCE) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE) $(CPP) $(CPP_PROJ) $(SOURCE)
# End Source File # End Source File
# End Target # End Target
################################################################################ ################################################################################
# Begin Target # Begin Target
# Name "xmlparse - Win32 Release" # Name "xmlparse - Win32 Release"
# Name "xmlparse - Win32 Debug" # Name "xmlparse - Win32 Debug"
!IF "$(CFG)" == "xmlparse - Win32 Release" !IF "$(CFG)" == "xmlparse - Win32 Release"
!ELSEIF "$(CFG)" == "xmlparse - Win32 Debug" !ELSEIF "$(CFG)" == "xmlparse - Win32 Debug"
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlparse\xmlparse.c SOURCE=.\xmlparse\xmlparse.c
DEP_CPP_XMLPA=\ !IF "$(CFG)" == "xmlparse - Win32 Release"
DEP_CPP_XMLPA=\
".\xmlparse\hashtable.h"\ ".\xmlparse\hashtable.h"\
".\xmlparse\xmlparse.h"\ ".\xmlparse\xmlparse.h"\
".\xmltok\xmldef.h"\ ".\xmltok\xmldef.h"\
".\xmltok\xmlrole.h"\ ".\xmltok\xmlrole.h"\
".\xmltok\xmltok.h"\ ".\xmltok\xmltok.h"\
NODEP_CPP_XMLPA=\ NODEP_CPP_XMLPA=\
".\xmltok\nspr.h"\ ".\xmltok\nspr.h"\
"$(INTDIR)\xmlparse.obj" : $(SOURCE) $(DEP_CPP_XMLPA) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ELSEIF "$(CFG)" == "xmlparse - Win32 Debug"
"$(INTDIR)\xmlparse.obj" : $(SOURCE) $(DEP_CPP_XMLPA) "$(INTDIR)" DEP_CPP_XMLPA=\
".\xmlparse\hashtable.h"\
".\xmlparse\xmlparse.h"\
".\xmltok\xmldef.h"\
".\xmltok\xmlrole.h"\
".\xmltok\xmltok.h"\
$(CPP) $(CPP_PROJ) $(SOURCE) NODEP_CPP_XMLPA=\
".\xmltok\nspr.h"\
"$(INTDIR)\xmlparse.obj" : $(SOURCE) $(DEP_CPP_XMLPA) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ENDIF
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmlparse\hashtable.c SOURCE=.\xmlparse\hashtable.c
DEP_CPP_HASHT=\ !IF "$(CFG)" == "xmlparse - Win32 Release"
DEP_CPP_HASHT=\
".\xmlparse\hashtable.h"\ ".\xmlparse\hashtable.h"\
".\xmltok\xmldef.h"\ ".\xmltok\xmldef.h"\
NODEP_CPP_HASHT=\ NODEP_CPP_HASHT=\
".\xmltok\nspr.h"\ ".\xmltok\nspr.h"\
"$(INTDIR)\hashtable.obj" : $(SOURCE) $(DEP_CPP_HASHT) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ELSEIF "$(CFG)" == "xmlparse - Win32 Debug"
"$(INTDIR)\hashtable.obj" : $(SOURCE) $(DEP_CPP_HASHT) "$(INTDIR)" DEP_CPP_HASHT=\
".\xmlparse\hashtable.h"\
".\xmltok\xmldef.h"\
$(CPP) $(CPP_PROJ) $(SOURCE) NODEP_CPP_HASHT=\
".\xmltok\nspr.h"\
"$(INTDIR)\hashtable.obj" : $(SOURCE) $(DEP_CPP_HASHT) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ENDIF
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Project Dependency # Begin Project Dependency
# Project_Dep_Name "xmltok" # Project_Dep_Name "xmltok"
!IF "$(CFG)" == "xmlparse - Win32 Release" !IF "$(CFG)" == "xmlparse - Win32 Release"
"xmltok - Win32 Release" : "xmltok - Win32 Release" :
$(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmltok - Win32 Release" $(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmltok - Win32 Release"
!ELSEIF "$(CFG)" == "xmlparse - Win32 Debug" !ELSEIF "$(CFG)" == "xmlparse - Win32 Debug"
"xmltok - Win32 Debug" : "xmltok - Win32 Debug" :
$(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmltok - Win32 Debug" $(MAKE) /$(MAKEFLAGS) /F ".\expat.mak" CFG="xmltok - Win32 Debug"
!ENDIF !ENDIF
# End Project Dependency # End Project Dependency
# End Target # End Target
################################################################################ ################################################################################
# Begin Target # Begin Target
# Name "xmltok - Win32 Release" # Name "xmltok - Win32 Release"
# Name "xmltok - Win32 Debug" # Name "xmltok - Win32 Debug"
!IF "$(CFG)" == "xmltok - Win32 Release" !IF "$(CFG)" == "xmltok - Win32 Release"
!ELSEIF "$(CFG)" == "xmltok - Win32 Debug" !ELSEIF "$(CFG)" == "xmltok - Win32 Debug"
!ENDIF !ENDIF
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmltok\xmlrole.c SOURCE=.\xmltok\xmlrole.c
DEP_CPP_XMLRO=\ !IF "$(CFG)" == "xmltok - Win32 Release"
DEP_CPP_XMLRO=\
".\xmltok\xmldef.h"\ ".\xmltok\xmldef.h"\
".\xmltok\xmlrole.h"\ ".\xmltok\xmlrole.h"\
".\xmltok\xmltok.h"\ ".\xmltok\xmltok.h"\
NODEP_CPP_XMLRO=\ NODEP_CPP_XMLRO=\
".\xmltok\nspr.h"\ ".\xmltok\nspr.h"\
"$(INTDIR)\xmlrole.obj" : $(SOURCE) $(DEP_CPP_XMLRO) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ELSEIF "$(CFG)" == "xmltok - Win32 Debug"
"$(INTDIR)\xmlrole.obj" : $(SOURCE) $(DEP_CPP_XMLRO) "$(INTDIR)" DEP_CPP_XMLRO=\
".\xmltok\xmldef.h"\
".\xmltok\xmlrole.h"\
".\xmltok\xmltok.h"\
$(CPP) $(CPP_PROJ) $(SOURCE) NODEP_CPP_XMLRO=\
".\xmltok\nspr.h"\
"$(INTDIR)\xmlrole.obj" : $(SOURCE) $(DEP_CPP_XMLRO) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ENDIF
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmltok\xmltok.c SOURCE=.\xmltok\xmltok.c
DEP_CPP_XMLTO=\ !IF "$(CFG)" == "xmltok - Win32 Release"
DEP_CPP_XMLTO=\
".\xmltok\asciitab.h"\ ".\xmltok\asciitab.h"\
".\xmltok\iasciitab.h"\ ".\xmltok\iasciitab.h"\
".\xmltok\latin1tab.h"\ ".\xmltok\latin1tab.h"\
".\xmltok\nametab.h"\ ".\xmltok\nametab.h"\
".\xmltok\utf8tab.h"\ ".\xmltok\utf8tab.h"\
".\xmltok\xmldef.h"\ ".\xmltok\xmldef.h"\
".\xmltok\xmltok.h"\ ".\xmltok\xmltok.h"\
".\xmltok\xmltok_impl.c"\ ".\xmltok\xmltok_impl.c"\
".\xmltok\xmltok_impl.h"\ ".\xmltok\xmltok_impl.h"\
NODEP_CPP_XMLTO=\ NODEP_CPP_XMLTO=\
".\xmltok\nspr.h"\ ".\xmltok\nspr.h"\
"$(INTDIR)\xmltok.obj" : $(SOURCE) $(DEP_CPP_XMLTO) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ELSEIF "$(CFG)" == "xmltok - Win32 Debug"
"$(INTDIR)\xmltok.obj" : $(SOURCE) $(DEP_CPP_XMLTO) "$(INTDIR)" DEP_CPP_XMLTO=\
".\xmltok\asciitab.h"\
".\xmltok\iasciitab.h"\
".\xmltok\latin1tab.h"\
".\xmltok\nametab.h"\
".\xmltok\utf8tab.h"\
".\xmltok\xmldef.h"\
".\xmltok\xmltok.h"\
".\xmltok\xmltok_impl.c"\
".\xmltok\xmltok_impl.h"\
$(CPP) $(CPP_PROJ) $(SOURCE) NODEP_CPP_XMLTO=\
".\xmltok\nspr.h"\
"$(INTDIR)\xmltok.obj" : $(SOURCE) $(DEP_CPP_XMLTO) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
!ENDIF
# End Source File # End Source File
################################################################################ ################################################################################
# Begin Source File # Begin Source File
SOURCE=.\xmltok\dllmain.c SOURCE=.\xmltok\dllmain.c
!IF "$(CFG)" == "xmltok - Win32 Release"
"$(INTDIR)\dllmain.obj" : $(SOURCE) "$(INTDIR)" "$(INTDIR)\dllmain.obj" : $(SOURCE) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE) $(CPP) $(CPP_PROJ) $(SOURCE)
!ELSEIF "$(CFG)" == "xmltok - Win32 Debug"
"$(INTDIR)\dllmain.obj" : $(SOURCE) "$(INTDIR)"
$(CPP) $(CPP_PROJ) $(SOURCE)
# End Source File
# End Target !ENDIF
# End Source File
# End Target
# End Project # End Project
################################################################################ ################################################################################
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at csompliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
Software distributed under the License is distributed on an "AS IS" Software distributed under the License is distributed on an "AS IS"
...@@ -12,21 +12,45 @@ under the License. ...@@ -12,21 +12,45 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include "xmldef.h" #include "xmldef.h"
#ifdef XML_UNICODE_WCHAR_T
#ifndef XML_UNICODE
#define XML_UNICODE
#endif
#endif
#include "hashtable.h" #include "hashtable.h"
#include <stdlib.h>
#include <string.h>
#define INIT_SIZE 64 #define INIT_SIZE 64
static static
unsigned long hash(const char *s) int keyeq(KEY s1, KEY s2)
{
for (; *s1 == *s2; s1++, s2++)
if (*s1 == 0)
return 1;
return 0;
}
static
unsigned long hash(KEY s)
{ {
unsigned long h = 0; unsigned long h = 0;
while (*s) while (*s)
...@@ -34,7 +58,7 @@ unsigned long hash(const char *s) ...@@ -34,7 +58,7 @@ unsigned long hash(const char *s)
return h; return h;
} }
NAMED *lookup(HASH_TABLE *table, const char *name, size_t createSize) NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize)
{ {
size_t i; size_t i;
if (table->size == 0) { if (table->size == 0) {
...@@ -52,7 +76,7 @@ NAMED *lookup(HASH_TABLE *table, const char *name, size_t createSize) ...@@ -52,7 +76,7 @@ NAMED *lookup(HASH_TABLE *table, const char *name, size_t createSize)
for (i = h & (table->size - 1); for (i = h & (table->size - 1);
table->v[i]; table->v[i];
i == 0 ? i = table->size - 1 : --i) { i == 0 ? i = table->size - 1 : --i) {
if (strcmp(name, table->v[i]->name) == 0) if (keyeq(name, table->v[i]->name))
return table->v[i]; return table->v[i];
} }
if (!createSize) if (!createSize)
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,17 +12,41 @@ under the License. ...@@ -12,17 +12,41 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include <stddef.h> #include <stddef.h>
#ifdef XML_UNICODE
#ifdef XML_UNICODE_WCHAR_T
typedef const wchar_t *KEY;
#else /* not XML_UNICODE_WCHAR_T */
typedef const unsigned short *KEY;
#endif /* not XML_UNICODE_WCHAR_T */
#else /* not XML_UNICODE */
typedef const char *KEY;
#endif /* not XML_UNICODE */
typedef struct { typedef struct {
const char *name; KEY name;
} NAMED; } NAMED;
typedef struct { typedef struct {
...@@ -32,7 +56,7 @@ typedef struct { ...@@ -32,7 +56,7 @@ typedef struct {
size_t usedLim; size_t usedLim;
} HASH_TABLE; } HASH_TABLE;
NAMED *lookup(HASH_TABLE *table, const char *name, size_t createSize); NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize);
void hashTableInit(HASH_TABLE *); void hashTableInit(HASH_TABLE *);
void hashTableDestroy(HASH_TABLE *); void hashTableDestroy(HASH_TABLE *);
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,76 +12,150 @@ under the License. ...@@ -12,76 +12,150 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include "xmldef.h" #include "xmldef.h"
#include "xmlparse.h" #include "xmlparse.h"
#ifdef XML_UNICODE
#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX
#define XmlConvert XmlUtf16Convert
#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding
#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS
#define XmlEncode XmlUtf16Encode
#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1))
typedef unsigned short ICHAR;
#else
#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX
#define XmlConvert XmlUtf8Convert
#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding
#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS
#define XmlEncode XmlUtf8Encode
#define MUST_CONVERT(enc, s) (!(enc)->isUtf8)
typedef char ICHAR;
#endif
#ifndef XML_NS
#define XmlInitEncodingNS XmlInitEncoding
#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding
#undef XmlGetInternalEncodingNS
#define XmlGetInternalEncodingNS XmlGetInternalEncoding
#define XmlParseXmlDeclNS XmlParseXmlDecl
#endif
#ifdef XML_UNICODE_WCHAR_T
#define XML_T(x) L ## x
#else
#define XML_T(x) x
#endif
/* Round up n to be a multiple of sz, where sz is a power of 2. */
#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))
#include "xmltok.h" #include "xmltok.h"
#include "xmlrole.h" #include "xmlrole.h"
#include "hashtable.h" #include "hashtable.h"
#include <stdlib.h> #define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */
#include <string.h>
#define INIT_TAG_BUF_SIZE 32
#define INIT_DATA_BUF_SIZE 1024 #define INIT_DATA_BUF_SIZE 1024
#define INIT_ATTS_SIZE 16 #define INIT_ATTS_SIZE 16
#define INIT_BLOCK_SIZE 1024 #define INIT_BLOCK_SIZE 1024
#define INIT_BUFFER_SIZE 1024 #define INIT_BUFFER_SIZE 1024
#define EXPAND_SPARE 24
typedef struct binding {
struct prefix *prefix;
struct binding *nextTagBinding;
struct binding *prevPrefixBinding;
const struct attribute_id *attId;
XML_Char *uri;
int uriLen;
int uriAlloc;
} BINDING;
typedef struct prefix {
const XML_Char *name;
BINDING *binding;
} PREFIX;
typedef struct {
const XML_Char *str;
const XML_Char *localPart;
int uriLen;
} TAG_NAME;
typedef struct tag { typedef struct tag {
struct tag *parent; struct tag *parent;
const char *rawName; const char *rawName;
int rawNameLength; int rawNameLength;
const char *name; TAG_NAME name;
char *buf; char *buf;
char *bufEnd; char *bufEnd;
BINDING *bindings;
} TAG; } TAG;
typedef struct { typedef struct {
const char *name; const XML_Char *name;
const char *textPtr; const XML_Char *textPtr;
int textLen; int textLen;
const char *systemId; const XML_Char *systemId;
const char *publicId; const XML_Char *base;
const char *notation; const XML_Char *publicId;
const XML_Char *notation;
char open; char open;
char magic;
} ENTITY; } ENTITY;
typedef struct block { typedef struct block {
struct block *next; struct block *next;
int size; int size;
char s[1]; XML_Char s[1];
} BLOCK; } BLOCK;
typedef struct { typedef struct {
BLOCK *blocks; BLOCK *blocks;
BLOCK *freeBlocks; BLOCK *freeBlocks;
const char *end; const XML_Char *end;
char *ptr; XML_Char *ptr;
char *start; XML_Char *start;
} STRING_POOL; } STRING_POOL;
/* The byte before the name is a scratch byte used to determine whether /* The XML_Char before the name is used to determine whether
an attribute has been specified. */ an attribute has been specified. */
typedef struct { typedef struct attribute_id {
char *name; XML_Char *name;
PREFIX *prefix;
char maybeTokenized; char maybeTokenized;
char xmlns;
} ATTRIBUTE_ID; } ATTRIBUTE_ID;
typedef struct { typedef struct {
const ATTRIBUTE_ID *id; const ATTRIBUTE_ID *id;
char isCdata; char isCdata;
const char *value; const XML_Char *value;
} DEFAULT_ATTRIBUTE; } DEFAULT_ATTRIBUTE;
typedef struct { typedef struct {
const char *name; const XML_Char *name;
PREFIX *prefix;
int nDefaultAtts; int nDefaultAtts;
int allocDefaultAtts; int allocDefaultAtts;
DEFAULT_ATTRIBUTE *defaultAtts; DEFAULT_ATTRIBUTE *defaultAtts;
...@@ -91,27 +165,54 @@ typedef struct { ...@@ -91,27 +165,54 @@ typedef struct {
HASH_TABLE generalEntities; HASH_TABLE generalEntities;
HASH_TABLE elementTypes; HASH_TABLE elementTypes;
HASH_TABLE attributeIds; HASH_TABLE attributeIds;
HASH_TABLE prefixes;
STRING_POOL pool; STRING_POOL pool;
int complete; int complete;
int standalone; int standalone;
const XML_Char *base;
PREFIX defaultPrefix;
} DTD; } DTD;
typedef struct open_internal_entity {
const char *internalEventPtr;
const char *internalEventEndPtr;
struct open_internal_entity *next;
ENTITY *entity;
} OPEN_INTERNAL_ENTITY;
typedef enum XML_Error Processor(XML_Parser parser, typedef enum XML_Error Processor(XML_Parser parser,
const char *start, const char *start,
const char *end, const char *end,
const char **endPtr); const char **endPtr);
static Processor prologProcessor; static Processor prologProcessor;
static Processor prologInitProcessor;
static Processor contentProcessor; static Processor contentProcessor;
static Processor cdataSectionProcessor;
static Processor epilogProcessor; static Processor epilogProcessor;
static Processor errorProcessor; static Processor errorProcessor;
static Processor externalEntityInitProcessor;
static Processor externalEntityInitProcessor2;
static Processor externalEntityInitProcessor3;
static Processor externalEntityContentProcessor;
static enum XML_Error
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName);
static enum XML_Error
processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *, const char *);
static enum XML_Error
initializeEncoding(XML_Parser parser);
static enum XML_Error static enum XML_Error
doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc,
const char *start, const char *end, const char **endPtr); const char *start, const char *end, const char **endPtr);
static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, const char *tagName, const char *s); static enum XML_Error
doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, const char *end, const char **nextPtr);
static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, const char *s,
TAG_NAME *tagNamePtr, BINDING **bindingsPtr);
static
int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr);
static int static int
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, int isCdata, const char *dfltValue); defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, int isCdata, const XML_Char *dfltValue);
static enum XML_Error static enum XML_Error
storeAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *, storeAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *,
STRING_POOL *); STRING_POOL *);
...@@ -120,158 +221,376 @@ appendAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const cha ...@@ -120,158 +221,376 @@ appendAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const cha
STRING_POOL *); STRING_POOL *);
static ATTRIBUTE_ID * static ATTRIBUTE_ID *
getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *);
static enum XML_Error static enum XML_Error
storeEntityValue(XML_Parser parser, const char *start, const char *end); storeEntityValue(XML_Parser parser, const char *start, const char *end);
static int static int
reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
static int
reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
static void
reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, const char *end);
static const XML_Char *getContext(XML_Parser parser);
static int setContext(XML_Parser parser, const XML_Char *context);
static void normalizePublicId(XML_Char *s);
static int dtdInit(DTD *); static int dtdInit(DTD *);
static void dtdDestroy(DTD *); static void dtdDestroy(DTD *);
static int dtdCopy(DTD *newDtd, const DTD *oldDtd);
static void poolInit(STRING_POOL *); static void poolInit(STRING_POOL *);
static void poolClear(STRING_POOL *); static void poolClear(STRING_POOL *);
static void poolDestroy(STRING_POOL *); static void poolDestroy(STRING_POOL *);
static char *poolAppend(STRING_POOL *pool, const ENCODING *enc, static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc,
const char *ptr, const char *end); const char *ptr, const char *end);
static char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc,
const char *ptr, const char *end); const char *ptr, const char *end);
static int poolGrow(STRING_POOL *pool); static int poolGrow(STRING_POOL *pool);
static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s);
static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n);
#define poolStart(pool) ((pool)->start) #define poolStart(pool) ((pool)->start)
#define poolEnd(pool) ((pool)->ptr) #define poolEnd(pool) ((pool)->ptr)
#define poolLength(pool) ((pool)->ptr - (pool)->start) #define poolLength(pool) ((pool)->ptr - (pool)->start)
#define poolChop(pool) ((void)--(pool->ptr)) #define poolChop(pool) ((void)--(pool->ptr))
#define poolLastByte(pool) (((pool)->ptr)[-1]) #define poolLastChar(pool) (((pool)->ptr)[-1])
#define poolDiscard(pool) ((pool)->ptr = (pool)->start) #define poolDiscard(pool) ((pool)->ptr = (pool)->start)
#define poolFinish(pool) ((pool)->start = (pool)->ptr) #define poolFinish(pool) ((pool)->start = (pool)->ptr)
#define poolAppendByte(pool, c) \ #define poolAppendChar(pool, c) \
(((pool)->ptr == (pool)->end && !poolGrow(pool)) \ (((pool)->ptr == (pool)->end && !poolGrow(pool)) \
? 0 \ ? 0 \
: ((*((pool)->ptr)++ = c), 1)) : ((*((pool)->ptr)++ = c), 1))
typedef struct { typedef struct {
char *buffer; /* The first member must be userData so that the XML_GetUserData macro works. */
void *m_userData;
void *m_handlerArg;
char *m_buffer;
/* first character to be parsed */ /* first character to be parsed */
const char *bufferPtr; const char *m_bufferPtr;
/* past last character to be parsed */ /* past last character to be parsed */
char *bufferEnd; char *m_bufferEnd;
/* allocated end of buffer */ /* allocated end of buffer */
const char *bufferLim; const char *m_bufferLim;
long bufferEndByteIndex; long m_parseEndByteIndex;
char *dataBuf; const char *m_parseEndPtr;
char *dataBufEnd; XML_Char *m_dataBuf;
void *userData; XML_Char *m_dataBufEnd;
XML_StartElementHandler startElementHandler; XML_StartElementHandler m_startElementHandler;
XML_EndElementHandler endElementHandler; XML_EndElementHandler m_endElementHandler;
XML_CharacterDataHandler characterDataHandler; XML_CharacterDataHandler m_characterDataHandler;
XML_ProcessingInstructionHandler processingInstructionHandler; XML_ProcessingInstructionHandler m_processingInstructionHandler;
const ENCODING *encoding; XML_CommentHandler m_commentHandler;
INIT_ENCODING initEncoding; XML_StartCdataSectionHandler m_startCdataSectionHandler;
PROLOG_STATE prologState; XML_EndCdataSectionHandler m_endCdataSectionHandler;
Processor *processor; XML_DefaultHandler m_defaultHandler;
enum XML_Error errorCode; XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler;
const char *errorPtr; XML_NotationDeclHandler m_notationDeclHandler;
int tagLevel; XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler;
ENTITY *declEntity; XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler;
ELEMENT_TYPE *declElementType; XML_NotStandaloneHandler m_notStandaloneHandler;
ATTRIBUTE_ID *declAttributeId; XML_ExternalEntityRefHandler m_externalEntityRefHandler;
char declAttributeIsCdata; void *m_externalEntityRefHandlerArg;
DTD dtd; XML_UnknownEncodingHandler m_unknownEncodingHandler;
TAG *tagStack; const ENCODING *m_encoding;
TAG *freeTagList; INIT_ENCODING m_initEncoding;
int attsSize; const XML_Char *m_protocolEncodingName;
ATTRIBUTE *atts; int m_ns;
POSITION position; void *m_unknownEncodingMem;
long errorByteIndex; void *m_unknownEncodingData;
STRING_POOL tempPool; void *m_unknownEncodingHandlerData;
STRING_POOL temp2Pool; void (*m_unknownEncodingRelease)(void *);
char *groupConnector; PROLOG_STATE m_prologState;
unsigned groupSize; Processor *m_processor;
int hadExternalDoctype; enum XML_Error m_errorCode;
const char *m_eventPtr;
const char *m_eventEndPtr;
const char *m_positionPtr;
OPEN_INTERNAL_ENTITY *m_openInternalEntities;
int m_defaultExpandInternalEntities;
int m_tagLevel;
ENTITY *m_declEntity;
const XML_Char *m_declNotationName;
const XML_Char *m_declNotationPublicId;
ELEMENT_TYPE *m_declElementType;
ATTRIBUTE_ID *m_declAttributeId;
char m_declAttributeIsCdata;
DTD m_dtd;
TAG *m_tagStack;
TAG *m_freeTagList;
BINDING *m_inheritedBindings;
BINDING *m_freeBindingList;
int m_attsSize;
int m_nSpecifiedAtts;
ATTRIBUTE *m_atts;
POSITION m_position;
STRING_POOL m_tempPool;
STRING_POOL m_temp2Pool;
char *m_groupConnector;
unsigned m_groupSize;
int m_hadExternalDoctype;
XML_Char m_namespaceSeparator;
} Parser; } Parser;
#define userData (((Parser *)parser)->userData) #define userData (((Parser *)parser)->m_userData)
#define startElementHandler (((Parser *)parser)->startElementHandler) #define handlerArg (((Parser *)parser)->m_handlerArg)
#define endElementHandler (((Parser *)parser)->endElementHandler) #define startElementHandler (((Parser *)parser)->m_startElementHandler)
#define characterDataHandler (((Parser *)parser)->characterDataHandler) #define endElementHandler (((Parser *)parser)->m_endElementHandler)
#define processingInstructionHandler (((Parser *)parser)->processingInstructionHandler) #define characterDataHandler (((Parser *)parser)->m_characterDataHandler)
#define encoding (((Parser *)parser)->encoding) #define processingInstructionHandler (((Parser *)parser)->m_processingInstructionHandler)
#define initEncoding (((Parser *)parser)->initEncoding) #define commentHandler (((Parser *)parser)->m_commentHandler)
#define prologState (((Parser *)parser)->prologState) #define startCdataSectionHandler (((Parser *)parser)->m_startCdataSectionHandler)
#define processor (((Parser *)parser)->processor) #define endCdataSectionHandler (((Parser *)parser)->m_endCdataSectionHandler)
#define errorCode (((Parser *)parser)->errorCode) #define defaultHandler (((Parser *)parser)->m_defaultHandler)
#define errorPtr (((Parser *)parser)->errorPtr) #define unparsedEntityDeclHandler (((Parser *)parser)->m_unparsedEntityDeclHandler)
#define errorByteIndex (((Parser *)parser)->errorByteIndex) #define notationDeclHandler (((Parser *)parser)->m_notationDeclHandler)
#define position (((Parser *)parser)->position) #define startNamespaceDeclHandler (((Parser *)parser)->m_startNamespaceDeclHandler)
#define tagLevel (((Parser *)parser)->tagLevel) #define endNamespaceDeclHandler (((Parser *)parser)->m_endNamespaceDeclHandler)
#define buffer (((Parser *)parser)->buffer) #define notStandaloneHandler (((Parser *)parser)->m_notStandaloneHandler)
#define bufferPtr (((Parser *)parser)->bufferPtr) #define externalEntityRefHandler (((Parser *)parser)->m_externalEntityRefHandler)
#define bufferEnd (((Parser *)parser)->bufferEnd) #define externalEntityRefHandlerArg (((Parser *)parser)->m_externalEntityRefHandlerArg)
#define bufferEndByteIndex (((Parser *)parser)->bufferEndByteIndex) #define unknownEncodingHandler (((Parser *)parser)->m_unknownEncodingHandler)
#define bufferLim (((Parser *)parser)->bufferLim) #define encoding (((Parser *)parser)->m_encoding)
#define dataBuf (((Parser *)parser)->dataBuf) #define initEncoding (((Parser *)parser)->m_initEncoding)
#define dataBufEnd (((Parser *)parser)->dataBufEnd) #define unknownEncodingMem (((Parser *)parser)->m_unknownEncodingMem)
#define dtd (((Parser *)parser)->dtd) #define unknownEncodingData (((Parser *)parser)->m_unknownEncodingData)
#define declEntity (((Parser *)parser)->declEntity) #define unknownEncodingHandlerData \
#define declElementType (((Parser *)parser)->declElementType) (((Parser *)parser)->m_unknownEncodingHandlerData)
#define declAttributeId (((Parser *)parser)->declAttributeId) #define unknownEncodingRelease (((Parser *)parser)->m_unknownEncodingRelease)
#define declAttributeIsCdata (((Parser *)parser)->declAttributeIsCdata) #define protocolEncodingName (((Parser *)parser)->m_protocolEncodingName)
#define freeTagList (((Parser *)parser)->freeTagList) #define ns (((Parser *)parser)->m_ns)
#define tagStack (((Parser *)parser)->tagStack) #define prologState (((Parser *)parser)->m_prologState)
#define atts (((Parser *)parser)->atts) #define processor (((Parser *)parser)->m_processor)
#define attsSize (((Parser *)parser)->attsSize) #define errorCode (((Parser *)parser)->m_errorCode)
#define tempPool (((Parser *)parser)->tempPool) #define eventPtr (((Parser *)parser)->m_eventPtr)
#define temp2Pool (((Parser *)parser)->temp2Pool) #define eventEndPtr (((Parser *)parser)->m_eventEndPtr)
#define groupConnector (((Parser *)parser)->groupConnector) #define positionPtr (((Parser *)parser)->m_positionPtr)
#define groupSize (((Parser *)parser)->groupSize) #define position (((Parser *)parser)->m_position)
#define hadExternalDoctype (((Parser *)parser)->hadExternalDoctype) #define openInternalEntities (((Parser *)parser)->m_openInternalEntities)
#define defaultExpandInternalEntities (((Parser *)parser)->m_defaultExpandInternalEntities)
XML_Parser XML_ParserCreate(const char *encodingName) #define tagLevel (((Parser *)parser)->m_tagLevel)
#define buffer (((Parser *)parser)->m_buffer)
#define bufferPtr (((Parser *)parser)->m_bufferPtr)
#define bufferEnd (((Parser *)parser)->m_bufferEnd)
#define parseEndByteIndex (((Parser *)parser)->m_parseEndByteIndex)
#define parseEndPtr (((Parser *)parser)->m_parseEndPtr)
#define bufferLim (((Parser *)parser)->m_bufferLim)
#define dataBuf (((Parser *)parser)->m_dataBuf)
#define dataBufEnd (((Parser *)parser)->m_dataBufEnd)
#define dtd (((Parser *)parser)->m_dtd)
#define declEntity (((Parser *)parser)->m_declEntity)
#define declNotationName (((Parser *)parser)->m_declNotationName)
#define declNotationPublicId (((Parser *)parser)->m_declNotationPublicId)
#define declElementType (((Parser *)parser)->m_declElementType)
#define declAttributeId (((Parser *)parser)->m_declAttributeId)
#define declAttributeIsCdata (((Parser *)parser)->m_declAttributeIsCdata)
#define freeTagList (((Parser *)parser)->m_freeTagList)
#define freeBindingList (((Parser *)parser)->m_freeBindingList)
#define inheritedBindings (((Parser *)parser)->m_inheritedBindings)
#define tagStack (((Parser *)parser)->m_tagStack)
#define atts (((Parser *)parser)->m_atts)
#define attsSize (((Parser *)parser)->m_attsSize)
#define nSpecifiedAtts (((Parser *)parser)->m_nSpecifiedAtts)
#define tempPool (((Parser *)parser)->m_tempPool)
#define temp2Pool (((Parser *)parser)->m_temp2Pool)
#define groupConnector (((Parser *)parser)->m_groupConnector)
#define groupSize (((Parser *)parser)->m_groupSize)
#define hadExternalDoctype (((Parser *)parser)->m_hadExternalDoctype)
#define namespaceSeparator (((Parser *)parser)->m_namespaceSeparator)
#ifdef _MSC_VER
#ifdef _DEBUG
Parser *asParser(XML_Parser parser)
{
return parser;
}
#endif
#endif
XML_Parser XML_ParserCreate(const XML_Char *encodingName)
{ {
XML_Parser parser = malloc(sizeof(Parser)); XML_Parser parser = malloc(sizeof(Parser));
if (!parser) if (!parser)
return parser; return parser;
processor = prologProcessor; processor = prologInitProcessor;
XmlPrologStateInit(&prologState); XmlPrologStateInit(&prologState);
userData = 0; userData = 0;
handlerArg = 0;
startElementHandler = 0; startElementHandler = 0;
endElementHandler = 0; endElementHandler = 0;
characterDataHandler = 0; characterDataHandler = 0;
processingInstructionHandler = 0; processingInstructionHandler = 0;
commentHandler = 0;
startCdataSectionHandler = 0;
endCdataSectionHandler = 0;
defaultHandler = 0;
unparsedEntityDeclHandler = 0;
notationDeclHandler = 0;
startNamespaceDeclHandler = 0;
endNamespaceDeclHandler = 0;
notStandaloneHandler = 0;
externalEntityRefHandler = 0;
externalEntityRefHandlerArg = parser;
unknownEncodingHandler = 0;
buffer = 0; buffer = 0;
bufferPtr = 0; bufferPtr = 0;
bufferEnd = 0; bufferEnd = 0;
bufferEndByteIndex = 0; parseEndByteIndex = 0;
parseEndPtr = 0;
bufferLim = 0; bufferLim = 0;
declElementType = 0; declElementType = 0;
declAttributeId = 0; declAttributeId = 0;
declEntity = 0; declEntity = 0;
declNotationName = 0;
declNotationPublicId = 0;
memset(&position, 0, sizeof(POSITION)); memset(&position, 0, sizeof(POSITION));
errorCode = XML_ERROR_NONE; errorCode = XML_ERROR_NONE;
errorByteIndex = 0; eventPtr = 0;
errorPtr = 0; eventEndPtr = 0;
positionPtr = 0;
openInternalEntities = 0;
tagLevel = 0; tagLevel = 0;
tagStack = 0; tagStack = 0;
freeTagList = 0; freeTagList = 0;
freeBindingList = 0;
inheritedBindings = 0;
attsSize = INIT_ATTS_SIZE; attsSize = INIT_ATTS_SIZE;
atts = malloc(attsSize * sizeof(ATTRIBUTE)); atts = malloc(attsSize * sizeof(ATTRIBUTE));
dataBuf = malloc(INIT_DATA_BUF_SIZE); nSpecifiedAtts = 0;
dataBuf = malloc(INIT_DATA_BUF_SIZE * sizeof(XML_Char));
groupSize = 0; groupSize = 0;
groupConnector = 0; groupConnector = 0;
hadExternalDoctype = 0; hadExternalDoctype = 0;
unknownEncodingMem = 0;
unknownEncodingRelease = 0;
unknownEncodingData = 0;
unknownEncodingHandlerData = 0;
namespaceSeparator = '!';
ns = 0;
poolInit(&tempPool); poolInit(&tempPool);
poolInit(&temp2Pool); poolInit(&temp2Pool);
if (!dtdInit(&dtd) || !atts || !dataBuf) { protocolEncodingName = encodingName ? poolCopyString(&tempPool, encodingName) : 0;
if (!dtdInit(&dtd) || !atts || !dataBuf
|| (encodingName && !protocolEncodingName)) {
XML_ParserFree(parser); XML_ParserFree(parser);
return 0; return 0;
} }
dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE; dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;
if (!XmlInitEncoding(&initEncoding, &encoding, encodingName)) { XmlInitEncoding(&initEncoding, &encoding, 0);
errorCode = XML_ERROR_UNKNOWN_ENCODING; return parser;
processor = errorProcessor; }
XML_Parser XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep)
{
static
const XML_Char implicitContext[] = {
XML_T('x'), XML_T('m'), XML_T('l'), XML_T('='),
XML_T('h'), XML_T('t'), XML_T('t'), XML_T('p'), XML_T(':'),
XML_T('/'), XML_T('/'), XML_T('w'), XML_T('w'), XML_T('w'),
XML_T('.'), XML_T('w'), XML_T('3'),
XML_T('.'), XML_T('o'), XML_T('r'), XML_T('g'),
XML_T('/'), XML_T('X'), XML_T('M'), XML_T('L'),
XML_T('/'), XML_T('1'), XML_T('9'), XML_T('9'), XML_T('8'),
XML_T('/'), XML_T('n'), XML_T('a'), XML_T('m'), XML_T('e'),
XML_T('s'), XML_T('p'), XML_T('a'), XML_T('c'), XML_T('e'),
XML_T('\0')
};
XML_Parser parser = XML_ParserCreate(encodingName);
if (parser) {
XmlInitEncodingNS(&initEncoding, &encoding, 0);
ns = 1;
namespaceSeparator = nsSep;
}
if (!setContext(parser, implicitContext)) {
XML_ParserFree(parser);
return 0;
}
return parser;
}
int XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)
{
if (!encodingName)
protocolEncodingName = 0;
else {
protocolEncodingName = poolCopyString(&tempPool, encodingName);
if (!protocolEncodingName)
return 0;
}
return 1;
}
XML_Parser XML_ExternalEntityParserCreate(XML_Parser oldParser,
const XML_Char *context,
const XML_Char *encodingName)
{
XML_Parser parser = oldParser;
DTD *oldDtd = &dtd;
XML_StartElementHandler oldStartElementHandler = startElementHandler;
XML_EndElementHandler oldEndElementHandler = endElementHandler;
XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler;
XML_ProcessingInstructionHandler oldProcessingInstructionHandler = processingInstructionHandler;
XML_CommentHandler oldCommentHandler = commentHandler;
XML_StartCdataSectionHandler oldStartCdataSectionHandler = startCdataSectionHandler;
XML_EndCdataSectionHandler oldEndCdataSectionHandler = endCdataSectionHandler;
XML_DefaultHandler oldDefaultHandler = defaultHandler;
XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler = startNamespaceDeclHandler;
XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler = endNamespaceDeclHandler;
XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;
XML_ExternalEntityRefHandler oldExternalEntityRefHandler = externalEntityRefHandler;
XML_UnknownEncodingHandler oldUnknownEncodingHandler = unknownEncodingHandler;
void *oldUserData = userData;
void *oldHandlerArg = handlerArg;
int oldDefaultExpandInternalEntities = defaultExpandInternalEntities;
void *oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;
parser = (ns
? XML_ParserCreateNS(encodingName, namespaceSeparator)
: XML_ParserCreate(encodingName));
if (!parser)
return 0;
startElementHandler = oldStartElementHandler;
endElementHandler = oldEndElementHandler;
characterDataHandler = oldCharacterDataHandler;
processingInstructionHandler = oldProcessingInstructionHandler;
commentHandler = oldCommentHandler;
startCdataSectionHandler = oldStartCdataSectionHandler;
endCdataSectionHandler = oldEndCdataSectionHandler;
defaultHandler = oldDefaultHandler;
startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
notStandaloneHandler = oldNotStandaloneHandler;
externalEntityRefHandler = oldExternalEntityRefHandler;
unknownEncodingHandler = oldUnknownEncodingHandler;
userData = oldUserData;
if (oldUserData == oldHandlerArg)
handlerArg = userData;
else
handlerArg = parser;
if (oldExternalEntityRefHandlerArg != oldParser)
externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
if (!dtdCopy(&dtd, oldDtd) || !setContext(parser, context)) {
XML_ParserFree(parser);
return 0;
} }
processor = externalEntityInitProcessor;
return parser; return parser;
} }
static
void destroyBindings(BINDING *bindings)
{
for (;;) {
BINDING *b = bindings;
if (!b)
break;
bindings = b->nextTagBinding;
free(b->uri);
free(b);
}
}
void XML_ParserFree(XML_Parser parser) void XML_ParserFree(XML_Parser parser)
{ {
for (;;) { for (;;) {
...@@ -285,8 +604,11 @@ void XML_ParserFree(XML_Parser parser) ...@@ -285,8 +604,11 @@ void XML_ParserFree(XML_Parser parser)
p = tagStack; p = tagStack;
tagStack = tagStack->parent; tagStack = tagStack->parent;
free(p->buf); free(p->buf);
destroyBindings(p->bindings);
free(p); free(p);
} }
destroyBindings(freeBindingList);
destroyBindings(inheritedBindings);
poolDestroy(&tempPool); poolDestroy(&tempPool);
poolDestroy(&temp2Pool); poolDestroy(&temp2Pool);
dtdDestroy(&dtd); dtdDestroy(&dtd);
...@@ -294,14 +616,48 @@ void XML_ParserFree(XML_Parser parser) ...@@ -294,14 +616,48 @@ void XML_ParserFree(XML_Parser parser)
free(groupConnector); free(groupConnector);
free(buffer); free(buffer);
free(dataBuf); free(dataBuf);
free(unknownEncodingMem);
if (unknownEncodingRelease)
unknownEncodingRelease(unknownEncodingData);
free(parser); free(parser);
} }
void XML_UseParserAsHandlerArg(XML_Parser parser)
{
handlerArg = parser;
}
void XML_SetUserData(XML_Parser parser, void *p) void XML_SetUserData(XML_Parser parser, void *p)
{ {
if (handlerArg == userData)
handlerArg = userData = p;
else
userData = p; userData = p;
} }
int XML_SetBase(XML_Parser parser, const XML_Char *p)
{
if (p) {
p = poolCopyString(&dtd.pool, p);
if (!p)
return 0;
dtd.base = p;
}
else
dtd.base = 0;
return 1;
}
const XML_Char *XML_GetBase(XML_Parser parser)
{
return dtd.base;
}
int XML_GetSpecifiedAttributeCount(XML_Parser parser)
{
return nSpecifiedAtts;
}
void XML_SetElementHandler(XML_Parser parser, void XML_SetElementHandler(XML_Parser parser,
XML_StartElementHandler start, XML_StartElementHandler start,
XML_EndElementHandler end) XML_EndElementHandler end)
...@@ -322,44 +678,120 @@ void XML_SetProcessingInstructionHandler(XML_Parser parser, ...@@ -322,44 +678,120 @@ void XML_SetProcessingInstructionHandler(XML_Parser parser,
processingInstructionHandler = handler; processingInstructionHandler = handler;
} }
void XML_SetCommentHandler(XML_Parser parser,
XML_CommentHandler handler)
{
commentHandler = handler;
}
void XML_SetCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start,
XML_EndCdataSectionHandler end)
{
startCdataSectionHandler = start;
endCdataSectionHandler = end;
}
void XML_SetDefaultHandler(XML_Parser parser,
XML_DefaultHandler handler)
{
defaultHandler = handler;
defaultExpandInternalEntities = 0;
}
void XML_SetDefaultHandlerExpand(XML_Parser parser,
XML_DefaultHandler handler)
{
defaultHandler = handler;
defaultExpandInternalEntities = 1;
}
void XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
XML_UnparsedEntityDeclHandler handler)
{
unparsedEntityDeclHandler = handler;
}
void XML_SetNotationDeclHandler(XML_Parser parser,
XML_NotationDeclHandler handler)
{
notationDeclHandler = handler;
}
void XML_SetNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start,
XML_EndNamespaceDeclHandler end)
{
startNamespaceDeclHandler = start;
endNamespaceDeclHandler = end;
}
void XML_SetNotStandaloneHandler(XML_Parser parser,
XML_NotStandaloneHandler handler)
{
notStandaloneHandler = handler;
}
void XML_SetExternalEntityRefHandler(XML_Parser parser,
XML_ExternalEntityRefHandler handler)
{
externalEntityRefHandler = handler;
}
void XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg)
{
if (arg)
externalEntityRefHandlerArg = arg;
else
externalEntityRefHandlerArg = parser;
}
void XML_SetUnknownEncodingHandler(XML_Parser parser,
XML_UnknownEncodingHandler handler,
void *data)
{
unknownEncodingHandler = handler;
unknownEncodingHandlerData = data;
}
int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
{ {
bufferEndByteIndex += len;
if (len == 0) { if (len == 0) {
if (!isFinal) if (!isFinal)
return 1; return 1;
errorCode = processor(parser, bufferPtr, bufferEnd, 0); positionPtr = bufferPtr;
return errorCode == XML_ERROR_NONE; errorCode = processor(parser, bufferPtr, parseEndPtr = bufferEnd, 0);
if (errorCode == XML_ERROR_NONE)
return 1;
eventEndPtr = eventPtr;
return 0;
} }
else if (bufferPtr == bufferEnd) { else if (bufferPtr == bufferEnd) {
const char *end; const char *end;
int nLeftOver; int nLeftOver;
parseEndByteIndex += len;
positionPtr = s;
if (isFinal) { if (isFinal) {
errorCode = processor(parser, s, s + len, 0); errorCode = processor(parser, s, parseEndPtr = s + len, 0);
if (errorCode == XML_ERROR_NONE) if (errorCode == XML_ERROR_NONE)
return 1; return 1;
if (errorPtr) { eventEndPtr = eventPtr;
errorByteIndex = bufferEndByteIndex - (s + len - errorPtr);
XmlUpdatePosition(encoding, s, errorPtr, &position);
}
return 0; return 0;
} }
errorCode = processor(parser, s, s + len, &end); errorCode = processor(parser, s, parseEndPtr = s + len, &end);
if (errorCode != XML_ERROR_NONE) { if (errorCode != XML_ERROR_NONE) {
if (errorPtr) { eventEndPtr = eventPtr;
errorByteIndex = bufferEndByteIndex - (s + len - errorPtr);
XmlUpdatePosition(encoding, s, errorPtr, &position);
}
return 0; return 0;
} }
XmlUpdatePosition(encoding, s, end, &position); XmlUpdatePosition(encoding, positionPtr, end, &position);
nLeftOver = s + len - end; nLeftOver = s + len - end;
if (nLeftOver) { if (nLeftOver) {
if (buffer == 0 || nLeftOver > bufferLim - buffer) { if (buffer == 0 || nLeftOver > bufferLim - buffer) {
/* FIXME avoid integer overflow */ /* FIXME avoid integer overflow */
buffer = realloc(buffer, len * 2); buffer = buffer == 0 ? malloc(len * 2) : realloc(buffer, len * 2);
if (!buffer) { if (!buffer) {
errorCode = XML_ERROR_NO_MEMORY; errorCode = XML_ERROR_NO_MEMORY;
eventPtr = eventEndPtr = 0;
return 0; return 0;
} }
bufferLim = buffer + len * 2; bufferLim = buffer + len * 2;
...@@ -379,19 +811,18 @@ int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) ...@@ -379,19 +811,18 @@ int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
int XML_ParseBuffer(XML_Parser parser, int len, int isFinal) int XML_ParseBuffer(XML_Parser parser, int len, int isFinal)
{ {
const char *start = bufferPtr; const char *start = bufferPtr;
positionPtr = start;
bufferEnd += len; bufferEnd += len;
errorCode = processor(parser, bufferPtr, bufferEnd, parseEndByteIndex += len;
errorCode = processor(parser, start, parseEndPtr = bufferEnd,
isFinal ? (const char **)0 : &bufferPtr); isFinal ? (const char **)0 : &bufferPtr);
if (errorCode == XML_ERROR_NONE) { if (errorCode == XML_ERROR_NONE) {
if (!isFinal) if (!isFinal)
XmlUpdatePosition(encoding, start, bufferPtr, &position); XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
return 1; return 1;
} }
else { else {
if (errorPtr) { eventEndPtr = eventPtr;
errorByteIndex = bufferEndByteIndex - (bufferEnd - errorPtr);
XmlUpdatePosition(encoding, start, errorPtr, &position);
}
return 0; return 0;
} }
} }
...@@ -431,49 +862,82 @@ void *XML_GetBuffer(XML_Parser parser, int len) ...@@ -431,49 +862,82 @@ void *XML_GetBuffer(XML_Parser parser, int len)
return bufferEnd; return bufferEnd;
} }
int XML_GetErrorCode(XML_Parser parser) enum XML_Error XML_GetErrorCode(XML_Parser parser)
{ {
return errorCode; return errorCode;
} }
int XML_GetErrorLineNumber(XML_Parser parser) long XML_GetCurrentByteIndex(XML_Parser parser)
{
if (eventPtr)
return parseEndByteIndex - (parseEndPtr - eventPtr);
return -1;
}
int XML_GetCurrentByteCount(XML_Parser parser)
{
if (eventEndPtr && eventPtr)
return eventEndPtr - eventPtr;
return 0;
}
int XML_GetCurrentLineNumber(XML_Parser parser)
{ {
if (eventPtr) {
XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
positionPtr = eventPtr;
}
return position.lineNumber + 1; return position.lineNumber + 1;
} }
int XML_GetErrorColumnNumber(XML_Parser parser) int XML_GetCurrentColumnNumber(XML_Parser parser)
{ {
if (eventPtr) {
XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
positionPtr = eventPtr;
}
return position.columnNumber; return position.columnNumber;
} }
long XML_GetErrorByteIndex(XML_Parser parser) void XML_DefaultCurrent(XML_Parser parser)
{ {
return errorByteIndex; if (defaultHandler) {
if (openInternalEntities)
reportDefault(parser,
ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding(),
openInternalEntities->internalEventPtr,
openInternalEntities->internalEventEndPtr);
else
reportDefault(parser, encoding, eventPtr, eventEndPtr);
}
} }
const char *XML_ErrorString(int code) const XML_LChar *XML_ErrorString(int code)
{ {
static const char *message[] = { static const XML_LChar *message[] = {
0, 0,
"out of memory", XML_T("out of memory"),
"syntax error", XML_T("syntax error"),
"no element found", XML_T("no element found"),
"not well-formed", XML_T("not well-formed"),
"unclosed token", XML_T("unclosed token"),
"unclosed token", XML_T("unclosed token"),
"mismatched tag", XML_T("mismatched tag"),
"duplicate attribute", XML_T("duplicate attribute"),
"junk after document element", XML_T("junk after document element"),
"parameter entity reference not allowed within declaration in internal subset", XML_T("illegal parameter entity reference"),
"undefined entity", XML_T("undefined entity"),
"recursive entity reference", XML_T("recursive entity reference"),
"asynchronous entity", XML_T("asynchronous entity"),
"reference to invalid character number", XML_T("reference to invalid character number"),
"reference to binary entity", XML_T("reference to binary entity"),
"reference to external entity in attribute", XML_T("reference to external entity in attribute"),
"xml processing instruction not at start of external entity", XML_T("xml processing instruction not at start of external entity"),
"unknown encoding", XML_T("unknown encoding"),
"encoding specified in XML declaration is incorrect" XML_T("encoding specified in XML declaration is incorrect"),
XML_T("unclosed CDATA section"),
XML_T("error in processing external entity reference"),
XML_T("document is not standalone")
}; };
if (code > 0 && code < sizeof(message)/sizeof(message[0])) if (code > 0 && code < sizeof(message)/sizeof(message[0]))
return message[code]; return message[code];
...@@ -489,6 +953,96 @@ enum XML_Error contentProcessor(XML_Parser parser, ...@@ -489,6 +953,96 @@ enum XML_Error contentProcessor(XML_Parser parser,
return doContent(parser, 0, encoding, start, end, endPtr); return doContent(parser, 0, encoding, start, end, endPtr);
} }
static
enum XML_Error externalEntityInitProcessor(XML_Parser parser,
const char *start,
const char *end,
const char **endPtr)
{
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
processor = externalEntityInitProcessor2;
return externalEntityInitProcessor2(parser, start, end, endPtr);
}
static
enum XML_Error externalEntityInitProcessor2(XML_Parser parser,
const char *start,
const char *end,
const char **endPtr)
{
const char *next;
int tok = XmlContentTok(encoding, start, end, &next);
switch (tok) {
case XML_TOK_BOM:
start = next;
break;
case XML_TOK_PARTIAL:
if (endPtr) {
*endPtr = start;
return XML_ERROR_NONE;
}
eventPtr = start;
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
if (endPtr) {
*endPtr = start;
return XML_ERROR_NONE;
}
eventPtr = start;
return XML_ERROR_PARTIAL_CHAR;
}
processor = externalEntityInitProcessor3;
return externalEntityInitProcessor3(parser, start, end, endPtr);
}
static
enum XML_Error externalEntityInitProcessor3(XML_Parser parser,
const char *start,
const char *end,
const char **endPtr)
{
const char *next;
int tok = XmlContentTok(encoding, start, end, &next);
switch (tok) {
case XML_TOK_XML_DECL:
{
enum XML_Error result = processXmlDecl(parser, 1, start, next);
if (result != XML_ERROR_NONE)
return result;
start = next;
}
break;
case XML_TOK_PARTIAL:
if (endPtr) {
*endPtr = start;
return XML_ERROR_NONE;
}
eventPtr = start;
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
if (endPtr) {
*endPtr = start;
return XML_ERROR_NONE;
}
eventPtr = start;
return XML_ERROR_PARTIAL_CHAR;
}
processor = externalEntityContentProcessor;
tagLevel = 1;
return doContent(parser, 1, encoding, start, end, endPtr);
}
static
enum XML_Error externalEntityContentProcessor(XML_Parser parser,
const char *start,
const char *end,
const char **endPtr)
{
return doContent(parser, 1, encoding, start, end, endPtr);
}
static enum XML_Error static enum XML_Error
doContent(XML_Parser parser, doContent(XML_Parser parser,
int startTagLevel, int startTagLevel,
...@@ -497,95 +1051,146 @@ doContent(XML_Parser parser, ...@@ -497,95 +1051,146 @@ doContent(XML_Parser parser,
const char *end, const char *end,
const char **nextPtr) const char **nextPtr)
{ {
const ENCODING *utf8 = XmlGetInternalEncoding(XML_UTF8_ENCODING); const ENCODING *internalEnc = ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding();
const char **eventPP;
const char **eventEndPP;
if (enc == encoding) {
eventPP = &eventPtr;
eventEndPP = &eventEndPtr;
}
else {
eventPP = &(openInternalEntities->internalEventPtr);
eventEndPP = &(openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
for (;;) { for (;;) {
const char *next; const char *next = s; /* XmlContentTok doesn't always set the last arg */
int tok = XmlContentTok(enc, s, end, &next); int tok = XmlContentTok(enc, s, end, &next);
*eventEndPP = next;
switch (tok) { switch (tok) {
case XML_TOK_TRAILING_CR: case XML_TOK_TRAILING_CR:
if (nextPtr) {
*nextPtr = s;
return XML_ERROR_NONE;
}
*eventEndPP = end;
if (characterDataHandler) {
XML_Char c = 0xA;
characterDataHandler(handlerArg, &c, 1);
}
else if (defaultHandler)
reportDefault(parser, enc, s, end);
if (startTagLevel == 0)
return XML_ERROR_NO_ELEMENTS;
if (tagLevel != startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
return XML_ERROR_NONE;
case XML_TOK_NONE: case XML_TOK_NONE:
if (nextPtr) { if (nextPtr) {
*nextPtr = s; *nextPtr = s;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
if (startTagLevel > 0) { if (startTagLevel > 0) {
if (tagLevel != startTagLevel) { if (tagLevel != startTagLevel)
errorPtr = s;
return XML_ERROR_ASYNC_ENTITY; return XML_ERROR_ASYNC_ENTITY;
}
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
errorPtr = s;
return XML_ERROR_NO_ELEMENTS; return XML_ERROR_NO_ELEMENTS;
case XML_TOK_INVALID: case XML_TOK_INVALID:
errorPtr = next; *eventPP = next;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL: case XML_TOK_PARTIAL:
if (nextPtr) { if (nextPtr) {
*nextPtr = s; *nextPtr = s;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
errorPtr = s;
return XML_ERROR_UNCLOSED_TOKEN; return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR: case XML_TOK_PARTIAL_CHAR:
if (nextPtr) { if (nextPtr) {
*nextPtr = s; *nextPtr = s;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
errorPtr = s;
return XML_ERROR_PARTIAL_CHAR; return XML_ERROR_PARTIAL_CHAR;
case XML_TOK_ENTITY_REF: case XML_TOK_ENTITY_REF:
{ {
const char *name = poolStoreString(&dtd.pool, enc, const XML_Char *name;
ENTITY *entity;
XML_Char ch = XmlPredefinedEntityName(enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (ch) {
if (characterDataHandler)
characterDataHandler(handlerArg, &ch, 1);
else if (defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
name = poolStoreString(&dtd.pool, enc,
s + enc->minBytesPerChar, s + enc->minBytesPerChar,
next - enc->minBytesPerChar); next - enc->minBytesPerChar);
ENTITY *entity;
if (!name) if (!name)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0); entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0);
poolDiscard(&dtd.pool); poolDiscard(&dtd.pool);
if (!entity) { if (!entity) {
if (dtd.complete || dtd.standalone) { if (dtd.complete || dtd.standalone)
errorPtr = s;
return XML_ERROR_UNDEFINED_ENTITY; return XML_ERROR_UNDEFINED_ENTITY;
} if (defaultHandler)
reportDefault(parser, enc, s, next);
break; break;
} }
if (entity->magic) { if (entity->open)
if (characterDataHandler)
characterDataHandler(userData, entity->textPtr, entity->textLen);
break;
}
if (entity->open) {
errorPtr = s;
return XML_ERROR_RECURSIVE_ENTITY_REF; return XML_ERROR_RECURSIVE_ENTITY_REF;
} if (entity->notation)
if (entity->notation) {
errorPtr = s;
return XML_ERROR_BINARY_ENTITY_REF; return XML_ERROR_BINARY_ENTITY_REF;
}
if (entity) { if (entity) {
if (entity->textPtr) { if (entity->textPtr) {
enum XML_Error result; enum XML_Error result;
OPEN_INTERNAL_ENTITY openEntity;
if (defaultHandler && !defaultExpandInternalEntities) {
reportDefault(parser, enc, s, next);
break;
}
entity->open = 1; entity->open = 1;
openEntity.next = openInternalEntities;
openInternalEntities = &openEntity;
openEntity.entity = entity;
openEntity.internalEventPtr = 0;
openEntity.internalEventEndPtr = 0;
result = doContent(parser, result = doContent(parser,
tagLevel, tagLevel,
utf8, internalEnc,
entity->textPtr, (char *)entity->textPtr,
entity->textPtr + entity->textLen, (char *)(entity->textPtr + entity->textLen),
0); 0);
entity->open = 0; entity->open = 0;
if (result) { openInternalEntities = openEntity.next;
errorPtr = s; if (result)
return result; return result;
} }
else if (externalEntityRefHandler) {
const XML_Char *context;
entity->open = 1;
context = getContext(parser);
entity->open = 0;
if (!context)
return XML_ERROR_NO_MEMORY;
if (!externalEntityRefHandler(externalEntityRefHandlerArg,
context,
dtd.base,
entity->systemId,
entity->publicId))
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
poolDiscard(&tempPool);
} }
else if (defaultHandler)
reportDefault(parser, enc, s, next);
} }
break; break;
} }
case XML_TOK_START_TAG_WITH_ATTS: case XML_TOK_START_TAG_WITH_ATTS:
if (!startElementHandler) { if (!startElementHandler) {
enum XML_Error result = storeAtts(parser, enc, 0, s); enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
if (result) if (result)
return result; return result;
} }
...@@ -606,13 +1211,18 @@ doContent(XML_Parser parser, ...@@ -606,13 +1211,18 @@ doContent(XML_Parser parser,
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
} }
tag->bindings = 0;
tag->parent = tagStack; tag->parent = tagStack;
tagStack = tag; tagStack = tag;
tag->name.localPart = 0;
tag->rawName = s + enc->minBytesPerChar; tag->rawName = s + enc->minBytesPerChar;
tag->rawNameLength = XmlNameLength(enc, tag->rawName); tag->rawNameLength = XmlNameLength(enc, tag->rawName);
if (nextPtr) { if (nextPtr) {
if (tag->rawNameLength > tag->bufEnd - tag->buf) { /* Need to guarantee that:
tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)) <= tag->bufEnd - sizeof(XML_Char) */
if (tag->rawNameLength + (int)(sizeof(XML_Char) - 1) + (int)sizeof(XML_Char) > tag->bufEnd - tag->buf) {
int bufSize = tag->rawNameLength * 4; int bufSize = tag->rawNameLength * 4;
bufSize = ROUND_UP(bufSize, sizeof(XML_Char));
tag->buf = realloc(tag->buf, bufSize); tag->buf = realloc(tag->buf, bufSize);
if (!tag->buf) if (!tag->buf)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
...@@ -624,18 +1234,19 @@ doContent(XML_Parser parser, ...@@ -624,18 +1234,19 @@ doContent(XML_Parser parser,
++tagLevel; ++tagLevel;
if (startElementHandler) { if (startElementHandler) {
enum XML_Error result; enum XML_Error result;
char *toPtr; XML_Char *toPtr;
const char *rawNameEnd = tag->rawName + tag->rawNameLength;
for (;;) { for (;;) {
const char *rawNameEnd = tag->rawName + tag->rawNameLength;
const char *fromPtr = tag->rawName; const char *fromPtr = tag->rawName;
int bufSize; int bufSize;
toPtr = tag->buf;
if (nextPtr) if (nextPtr)
toPtr += tag->rawNameLength; toPtr = (XML_Char *)(tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)));
tag->name = toPtr; else
XmlConvert(enc, XML_UTF8_ENCODING, toPtr = (XML_Char *)tag->buf;
tag->name.str = toPtr;
XmlConvert(enc,
&fromPtr, rawNameEnd, &fromPtr, rawNameEnd,
&toPtr, tag->bufEnd - 1); (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
if (fromPtr == rawNameEnd) if (fromPtr == rawNameEnd)
break; break;
bufSize = (tag->bufEnd - tag->buf) << 1; bufSize = (tag->bufEnd - tag->buf) << 1;
...@@ -643,21 +1254,26 @@ doContent(XML_Parser parser, ...@@ -643,21 +1254,26 @@ doContent(XML_Parser parser,
if (!tag->buf) if (!tag->buf)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
tag->bufEnd = tag->buf + bufSize; tag->bufEnd = tag->buf + bufSize;
if (nextPtr)
tag->rawName = tag->buf;
} }
*toPtr = 0; *toPtr = XML_T('\0');
result = storeAtts(parser, enc, tag->name, s); result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
if (result) if (result)
return result; return result;
startElementHandler(userData, tag->name, (const char **)atts); startElementHandler(handlerArg, tag->name.str, (const XML_Char **)atts);
poolClear(&tempPool); poolClear(&tempPool);
} }
else else {
tag->name = 0; tag->name.str = 0;
if (defaultHandler)
reportDefault(parser, enc, s, next);
}
break; break;
} }
case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: case XML_TOK_EMPTY_ELEMENT_WITH_ATTS:
if (!startElementHandler) { if (!startElementHandler) {
enum XML_Error result = storeAtts(parser, enc, 0, s); enum XML_Error result = storeAtts(parser, enc, s, 0, 0);
if (result) if (result)
return result; return result;
} }
...@@ -665,30 +1281,44 @@ doContent(XML_Parser parser, ...@@ -665,30 +1281,44 @@ doContent(XML_Parser parser,
case XML_TOK_EMPTY_ELEMENT_NO_ATTS: case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
if (startElementHandler || endElementHandler) { if (startElementHandler || endElementHandler) {
const char *rawName = s + enc->minBytesPerChar; const char *rawName = s + enc->minBytesPerChar;
const char *name = poolStoreString(&tempPool, enc, rawName, enum XML_Error result;
rawName BINDING *bindings = 0;
+ XmlNameLength(enc, rawName)); TAG_NAME name;
if (!name) name.str = poolStoreString(&tempPool, enc, rawName,
rawName + XmlNameLength(enc, rawName));
if (!name.str)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
poolFinish(&tempPool); poolFinish(&tempPool);
if (startElementHandler) { result = storeAtts(parser, enc, s, &name, &bindings);
enum XML_Error result = storeAtts(parser, enc, name, s);
if (result) if (result)
return result; return result;
startElementHandler(userData, name, (const char **)atts); poolFinish(&tempPool);
if (startElementHandler)
startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
if (endElementHandler) {
if (startElementHandler)
*eventPP = *eventEndPP;
endElementHandler(handlerArg, name.str);
} }
if (endElementHandler)
endElementHandler(userData, name);
poolClear(&tempPool); poolClear(&tempPool);
} while (bindings) {
BINDING *b = bindings;
if (endNamespaceDeclHandler)
endNamespaceDeclHandler(handlerArg, b->prefix->name);
bindings = bindings->nextTagBinding;
b->nextTagBinding = freeBindingList;
freeBindingList = b;
b->prefix->binding = b->prevPrefixBinding;
}
}
else if (defaultHandler)
reportDefault(parser, enc, s, next);
if (tagLevel == 0) if (tagLevel == 0)
return epilogProcessor(parser, next, end, nextPtr); return epilogProcessor(parser, next, end, nextPtr);
break; break;
case XML_TOK_END_TAG: case XML_TOK_END_TAG:
if (tagLevel == startTagLevel) { if (tagLevel == startTagLevel)
errorPtr = s;
return XML_ERROR_ASYNC_ENTITY; return XML_ERROR_ASYNC_ENTITY;
}
else { else {
int len; int len;
const char *rawName; const char *rawName;
...@@ -700,21 +1330,29 @@ doContent(XML_Parser parser, ...@@ -700,21 +1330,29 @@ doContent(XML_Parser parser,
len = XmlNameLength(enc, rawName); len = XmlNameLength(enc, rawName);
if (len != tag->rawNameLength if (len != tag->rawNameLength
|| memcmp(tag->rawName, rawName, len) != 0) { || memcmp(tag->rawName, rawName, len) != 0) {
errorPtr = rawName; *eventPP = rawName;
return XML_ERROR_TAG_MISMATCH; return XML_ERROR_TAG_MISMATCH;
} }
--tagLevel; --tagLevel;
if (endElementHandler) { if (endElementHandler && tag->name.str) {
if (tag->name) if (tag->name.localPart) {
endElementHandler(userData, tag->name); XML_Char *to = (XML_Char *)tag->name.str + tag->name.uriLen;
else { const XML_Char *from = tag->name.localPart;
const char *name = poolStoreString(&tempPool, enc, rawName, while ((*to++ = *from++) != 0)
rawName + len); ;
if (!name) }
return XML_ERROR_NO_MEMORY; endElementHandler(handlerArg, tag->name.str);
endElementHandler(userData, name); }
poolClear(&tempPool); else if (defaultHandler)
} reportDefault(parser, enc, s, next);
while (tag->bindings) {
BINDING *b = tag->bindings;
if (endNamespaceDeclHandler)
endNamespaceDeclHandler(handlerArg, b->prefix->name);
tag->bindings = tag->bindings->nextTagBinding;
b->nextTagBinding = freeBindingList;
freeBindingList = b;
b->prefix->binding = b->prevPrefixBinding;
} }
if (tagLevel == 0) if (tagLevel == 0)
return epilogProcessor(parser, next, end, nextPtr); return epilogProcessor(parser, next, end, nextPtr);
...@@ -723,82 +1361,163 @@ doContent(XML_Parser parser, ...@@ -723,82 +1361,163 @@ doContent(XML_Parser parser,
case XML_TOK_CHAR_REF: case XML_TOK_CHAR_REF:
{ {
int n = XmlCharRefNumber(enc, s); int n = XmlCharRefNumber(enc, s);
if (n < 0) { if (n < 0)
errorPtr = s;
return XML_ERROR_BAD_CHAR_REF; return XML_ERROR_BAD_CHAR_REF;
}
if (characterDataHandler) { if (characterDataHandler) {
char buf[XML_MAX_BYTES_PER_CHAR]; XML_Char buf[XML_ENCODE_MAX];
characterDataHandler(userData, buf, XmlEncode(utf8, n, buf)); characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
} }
else if (defaultHandler)
reportDefault(parser, enc, s, next);
} }
break; break;
case XML_TOK_XML_DECL: case XML_TOK_XML_DECL:
errorPtr = s;
return XML_ERROR_MISPLACED_XML_PI; return XML_ERROR_MISPLACED_XML_PI;
case XML_TOK_DATA_NEWLINE: case XML_TOK_DATA_NEWLINE:
if (characterDataHandler) { if (characterDataHandler) {
char c = '\n'; XML_Char c = 0xA;
characterDataHandler(userData, &c, 1); characterDataHandler(handlerArg, &c, 1);
} }
else if (defaultHandler)
reportDefault(parser, enc, s, next);
break; break;
case XML_TOK_CDATA_SECTION: case XML_TOK_CDATA_SECT_OPEN:
if (characterDataHandler) { {
const char *lim = next - enc->minBytesPerChar * 3; enum XML_Error result;
s += enc->minBytesPerChar * 9; if (startCdataSectionHandler)
do { startCdataSectionHandler(handlerArg);
char *dataPtr = dataBuf; #if 0
XmlConvert(enc, XML_UTF8_ENCODING, &s, lim, &dataPtr, dataBufEnd); /* Suppose you doing a transformation on a document that involves
characterDataHandler(userData, dataBuf, dataPtr - dataBuf); changing only the character data. You set up a defaultHandler
} while (s != lim); and a characterDataHandler. The defaultHandler simply copies
characters through. The characterDataHandler does the transformation
and writes the characters out escaping them as necessary. This case
will fail to work if we leave out the following two lines (because &
and < inside CDATA sections will be incorrectly escaped).
However, now we have a start/endCdataSectionHandler, so it seems
easier to let the user deal with this. */
else if (characterDataHandler)
characterDataHandler(handlerArg, dataBuf, 0);
#endif
else if (defaultHandler)
reportDefault(parser, enc, s, next);
result = doCdataSection(parser, enc, &next, end, nextPtr);
if (!next) {
processor = cdataSectionProcessor;
return result;
}
} }
break; break;
case XML_TOK_DATA_CHARS: case XML_TOK_TRAILING_RSQB:
if (nextPtr) {
*nextPtr = s;
return XML_ERROR_NONE;
}
if (characterDataHandler) { if (characterDataHandler) {
do { if (MUST_CONVERT(enc, s)) {
char *dataPtr = dataBuf; ICHAR *dataPtr = (ICHAR *)dataBuf;
XmlConvert(enc, XML_UTF8_ENCODING, &s, next, &dataPtr, dataBufEnd); XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
characterDataHandler(userData, dataBuf, dataPtr - dataBuf); characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
} while (s != next);
} }
break; else
characterDataHandler(handlerArg,
(XML_Char *)s,
(XML_Char *)end - (XML_Char *)s);
}
else if (defaultHandler)
reportDefault(parser, enc, s, end);
if (startTagLevel == 0) {
*eventPP = end;
return XML_ERROR_NO_ELEMENTS;
}
if (tagLevel != startTagLevel) {
*eventPP = end;
return XML_ERROR_ASYNC_ENTITY;
}
return XML_ERROR_NONE;
case XML_TOK_DATA_CHARS:
if (characterDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
ICHAR *dataPtr = (ICHAR *)dataBuf;
XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
*eventEndPP = s;
characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
if (s == next)
break;
*eventPP = s;
}
}
else
characterDataHandler(handlerArg,
(XML_Char *)s,
(XML_Char *)next - (XML_Char *)s);
}
else if (defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_PI: case XML_TOK_PI:
if (!reportProcessingInstruction(parser, enc, s, next)) if (!reportProcessingInstruction(parser, enc, s, next))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
break; break;
case XML_TOK_COMMENT:
if (!reportComment(parser, enc, s, next))
return XML_ERROR_NO_MEMORY;
break;
default:
if (defaultHandler)
reportDefault(parser, enc, s, next);
break;
} }
s = next; *eventPP = s = next;
} }
/* not reached */ /* not reached */
} }
/* If tagName is non-null, build a real list of attributes, /* If tagNamePtr is non-null, build a real list of attributes,
otherwise just check the attributes for well-formedness. */ otherwise just check the attributes for well-formedness. */
static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc,
const char *tagName, const char *s) const char *s, TAG_NAME *tagNamePtr,
BINDING **bindingsPtr)
{ {
ELEMENT_TYPE *elementType = 0; ELEMENT_TYPE *elementType = 0;
int nDefaultAtts = 0; int nDefaultAtts = 0;
const char **appAtts = (const char **)atts; const XML_Char **appAtts;
int attIndex = 0;
int i; int i;
int n; int n;
int nPrefixes = 0;
if (tagName) { BINDING *binding;
elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagName, 0); const XML_Char *localPart;
if (elementType)
if (tagNamePtr) {
elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, 0);
if (!elementType) {
tagNamePtr->str = poolCopyString(&dtd.pool, tagNamePtr->str);
if (!tagNamePtr->str)
return XML_ERROR_NO_MEMORY;
elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, sizeof(ELEMENT_TYPE));
if (!elementType)
return XML_ERROR_NO_MEMORY;
if (ns && !setElementTypePrefix(parser, elementType))
return XML_ERROR_NO_MEMORY;
}
nDefaultAtts = elementType->nDefaultAtts; nDefaultAtts = elementType->nDefaultAtts;
} }
n = XmlGetAttributes(enc, s, attsSize, atts); n = XmlGetAttributes(enc, s, attsSize, atts);
if (n + nDefaultAtts > attsSize) { if (n + nDefaultAtts > attsSize) {
attsSize = 2*n; int oldAttsSize = attsSize;
attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
atts = realloc((void *)atts, attsSize * sizeof(ATTRIBUTE)); atts = realloc((void *)atts, attsSize * sizeof(ATTRIBUTE));
if (!atts) if (!atts)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
if (n > attsSize) if (n > oldAttsSize)
XmlGetAttributes(enc, s, n, atts); XmlGetAttributes(enc, s, n, atts);
} }
appAtts = (const XML_Char **)atts;
for (i = 0; i < n; i++) { for (i = 0; i < n; i++) {
ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name, ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name,
atts[i].name atts[i].name
...@@ -806,11 +1525,12 @@ static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, ...@@ -806,11 +1525,12 @@ static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc,
if (!attId) if (!attId)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
if ((attId->name)[-1]) { if ((attId->name)[-1]) {
errorPtr = atts[i].name; if (enc == encoding)
eventPtr = atts[i].name;
return XML_ERROR_DUPLICATE_ATTRIBUTE; return XML_ERROR_DUPLICATE_ATTRIBUTE;
} }
(attId->name)[-1] = 1; (attId->name)[-1] = 1;
appAtts[i << 1] = attId->name; appAtts[attIndex++] = attId->name;
if (!atts[i].normalized) { if (!atts[i].normalized) {
enum XML_Error result; enum XML_Error result;
int isCdata = 1; int isCdata = 1;
...@@ -830,109 +1550,480 @@ static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, ...@@ -830,109 +1550,480 @@ static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc,
&tempPool); &tempPool);
if (result) if (result)
return result; return result;
if (tagName) { if (tagNamePtr) {
appAtts[(i << 1) + 1] = poolStart(&tempPool); appAtts[attIndex] = poolStart(&tempPool);
poolFinish(&tempPool); poolFinish(&tempPool);
} }
else else
poolDiscard(&tempPool); poolDiscard(&tempPool);
} }
else if (tagName) { else if (tagNamePtr) {
appAtts[(i << 1) + 1] = poolStoreString(&tempPool, enc, atts[i].valuePtr, atts[i].valueEnd); appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, atts[i].valueEnd);
if (appAtts[(i << 1) + 1] == 0) if (appAtts[attIndex] == 0)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
poolFinish(&tempPool); poolFinish(&tempPool);
} }
if (attId->prefix && tagNamePtr) {
if (attId->xmlns) {
if (!addBinding(parser, attId->prefix, attId, appAtts[attIndex], bindingsPtr))
return XML_ERROR_NO_MEMORY;
--attIndex;
}
else {
attIndex++;
nPrefixes++;
(attId->name)[-1] = 2;
}
} }
if (tagName) { else
attIndex++;
}
nSpecifiedAtts = attIndex;
if (tagNamePtr) {
int j; int j;
for (j = 0; j < nDefaultAtts; j++) { for (j = 0; j < nDefaultAtts; j++) {
const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + j; const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + j;
if (!(da->id->name)[-1] && da->value) { if (!(da->id->name)[-1] && da->value) {
if (da->id->prefix) {
if (da->id->xmlns) {
if (!addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr))
return XML_ERROR_NO_MEMORY;
}
else {
(da->id->name)[-1] = 2;
nPrefixes++;
appAtts[attIndex++] = da->id->name;
appAtts[attIndex++] = da->value;
}
}
else {
(da->id->name)[-1] = 1; (da->id->name)[-1] = 1;
appAtts[i << 1] = da->id->name; appAtts[attIndex++] = da->id->name;
appAtts[(i << 1) + 1] = da->value; appAtts[attIndex++] = da->value;
i++; }
}
}
appAtts[attIndex] = 0;
}
i = 0;
if (nPrefixes) {
for (; i < attIndex; i += 2) {
if (appAtts[i][-1] == 2) {
ATTRIBUTE_ID *id;
((XML_Char *)(appAtts[i]))[-1] = 0;
id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, appAtts[i], 0);
if (id->prefix->binding) {
int j;
const BINDING *b = id->prefix->binding;
const XML_Char *s = appAtts[i];
for (j = 0; j < b->uriLen; j++) {
if (!poolAppendChar(&tempPool, b->uri[j]))
return XML_ERROR_NO_MEMORY;
}
while (*s++ != ':')
;
do {
if (!poolAppendChar(&tempPool, *s))
return XML_ERROR_NO_MEMORY;
} while (*s++);
appAtts[i] = poolStart(&tempPool);
poolFinish(&tempPool);
}
if (!--nPrefixes)
break;
}
else
((XML_Char *)(appAtts[i]))[-1] = 0;
}
} }
for (; i < attIndex; i += 2)
((XML_Char *)(appAtts[i]))[-1] = 0;
if (!tagNamePtr)
return XML_ERROR_NONE;
for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding)
binding->attId->name[-1] = 0;
if (elementType->prefix) {
binding = elementType->prefix->binding;
if (!binding)
return XML_ERROR_NONE;
localPart = tagNamePtr->str;
while (*localPart++ != XML_T(':'))
;
} }
appAtts[i << 1] = 0; else if (dtd.defaultPrefix.binding) {
binding = dtd.defaultPrefix.binding;
localPart = tagNamePtr->str;
}
else
return XML_ERROR_NONE;
tagNamePtr->localPart = localPart;
tagNamePtr->uriLen = binding->uriLen;
i = binding->uriLen;
do {
if (i == binding->uriAlloc) {
binding->uri = realloc(binding->uri, binding->uriAlloc *= 2);
if (!binding->uri)
return XML_ERROR_NO_MEMORY;
} }
while (i-- > 0) binding->uri[i++] = *localPart;
((char *)appAtts[i << 1])[-1] = 0; } while (*localPart++);
tagNamePtr->str = binding->uri;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
static enum XML_Error static
prologProcessor(XML_Parser parser, int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr)
const char *s, {
BINDING *b;
int len;
for (len = 0; uri[len]; len++)
;
if (namespaceSeparator)
len++;
if (freeBindingList) {
b = freeBindingList;
if (len > b->uriAlloc) {
b->uri = realloc(b->uri, len + EXPAND_SPARE);
if (!b->uri)
return 0;
b->uriAlloc = len + EXPAND_SPARE;
}
freeBindingList = b->nextTagBinding;
}
else {
b = malloc(sizeof(BINDING));
if (!b)
return 0;
b->uri = malloc(sizeof(XML_Char) * len + EXPAND_SPARE);
if (!b->uri) {
free(b);
return 0;
}
b->uriAlloc = len;
}
b->uriLen = len;
memcpy(b->uri, uri, len * sizeof(XML_Char));
if (namespaceSeparator)
b->uri[len - 1] = namespaceSeparator;
b->prefix = prefix;
b->attId = attId;
b->prevPrefixBinding = prefix->binding;
if (*uri == XML_T('\0') && prefix == &dtd.defaultPrefix)
prefix->binding = 0;
else
prefix->binding = b;
b->nextTagBinding = *bindingsPtr;
*bindingsPtr = b;
if (startNamespaceDeclHandler)
startNamespaceDeclHandler(handlerArg, prefix->name,
prefix->binding ? uri : 0);
return 1;
}
/* The idea here is to avoid using stack for each CDATA section when
the whole file is parsed with one call. */
static
enum XML_Error cdataSectionProcessor(XML_Parser parser,
const char *start,
const char *end,
const char **endPtr)
{
enum XML_Error result = doCdataSection(parser, encoding, &start, end, endPtr);
if (start) {
processor = contentProcessor;
return contentProcessor(parser, start, end, endPtr);
}
return result;
}
/* startPtr gets set to non-null is the section is closed, and to null if
the section is not yet closed. */
static
enum XML_Error doCdataSection(XML_Parser parser,
const ENCODING *enc,
const char **startPtr,
const char *end, const char *end,
const char **nextPtr) const char **nextPtr)
{ {
const char *s = *startPtr;
const char **eventPP;
const char **eventEndPP;
if (enc == encoding) {
eventPP = &eventPtr;
*eventPP = s;
eventEndPP = &eventEndPtr;
}
else {
eventPP = &(openInternalEntities->internalEventPtr);
eventEndPP = &(openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
*startPtr = 0;
for (;;) { for (;;) {
const char *next; const char *next;
int tok = XmlPrologTok(encoding, s, end, &next); int tok = XmlCdataSectionTok(enc, s, end, &next);
if (tok <= 0) { *eventEndPP = next;
if (nextPtr != 0 && tok != XML_TOK_INVALID) { switch (tok) {
*nextPtr = s; case XML_TOK_CDATA_SECT_CLOSE:
if (endCdataSectionHandler)
endCdataSectionHandler(handlerArg);
#if 0
/* see comment under XML_TOK_CDATA_SECT_OPEN */
else if (characterDataHandler)
characterDataHandler(handlerArg, dataBuf, 0);
#endif
else if (defaultHandler)
reportDefault(parser, enc, s, next);
*startPtr = next;
return XML_ERROR_NONE; return XML_ERROR_NONE;
case XML_TOK_DATA_NEWLINE:
if (characterDataHandler) {
XML_Char c = 0xA;
characterDataHandler(handlerArg, &c, 1);
} }
switch (tok) { else if (defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_DATA_CHARS:
if (characterDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
ICHAR *dataPtr = (ICHAR *)dataBuf;
XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
*eventEndPP = next;
characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
if (s == next)
break;
*eventPP = s;
}
}
else
characterDataHandler(handlerArg,
(XML_Char *)s,
(XML_Char *)next - (XML_Char *)s);
}
else if (defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_INVALID: case XML_TOK_INVALID:
errorPtr = next; *eventPP = next;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_NONE:
return XML_ERROR_NO_ELEMENTS;
case XML_TOK_PARTIAL:
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR: case XML_TOK_PARTIAL_CHAR:
if (nextPtr) {
*nextPtr = s;
return XML_ERROR_NONE;
}
return XML_ERROR_PARTIAL_CHAR; return XML_ERROR_PARTIAL_CHAR;
case XML_TOK_TRAILING_CR: case XML_TOK_PARTIAL:
errorPtr = s + encoding->minBytesPerChar; case XML_TOK_NONE:
return XML_ERROR_NO_ELEMENTS; if (nextPtr) {
*nextPtr = s;
return XML_ERROR_NONE;
}
return XML_ERROR_UNCLOSED_CDATA_SECTION;
default: default:
abort(); abort();
} }
*eventPP = s = next;
} }
switch (XmlTokenRole(&prologState, tok, s, next, encoding)) { /* not reached */
case XML_ROLE_XML_DECL: }
{
static enum XML_Error
initializeEncoding(XML_Parser parser)
{
const char *s;
#ifdef XML_UNICODE
char encodingBuf[128];
if (!protocolEncodingName)
s = 0;
else {
int i;
for (i = 0; protocolEncodingName[i]; i++) {
if (i == sizeof(encodingBuf) - 1
|| protocolEncodingName[i] >= 0x80
|| protocolEncodingName[i] < 0) {
encodingBuf[0] = '\0';
break;
}
encodingBuf[i] = (char)protocolEncodingName[i];
}
encodingBuf[i] = '\0';
s = encodingBuf;
}
#else
s = protocolEncodingName;
#endif
if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s))
return XML_ERROR_NONE;
return handleUnknownEncoding(parser, protocolEncodingName);
}
static enum XML_Error
processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
const char *s, const char *next)
{
const char *encodingName = 0; const char *encodingName = 0;
const ENCODING *newEncoding = 0; const ENCODING *newEncoding = 0;
const char *version; const char *version;
int standalone = -1; int standalone = -1;
if (!XmlParseXmlDecl(0, if (!(ns
? XmlParseXmlDeclNS
: XmlParseXmlDecl)(isGeneralTextEntity,
encoding, encoding,
s, s,
next, next,
&errorPtr, &eventPtr,
&version, &version,
&encodingName, &encodingName,
&newEncoding, &newEncoding,
&standalone)) &standalone))
return XML_ERROR_SYNTAX; return XML_ERROR_SYNTAX;
if (!isGeneralTextEntity && standalone == 1)
dtd.standalone = 1;
if (defaultHandler)
reportDefault(parser, encoding, s, next);
if (!protocolEncodingName) {
if (newEncoding) { if (newEncoding) {
if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) { if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) {
errorPtr = encodingName; eventPtr = encodingName;
return XML_ERROR_INCORRECT_ENCODING; return XML_ERROR_INCORRECT_ENCODING;
} }
encoding = newEncoding; encoding = newEncoding;
} }
else if (encodingName) { else if (encodingName) {
errorPtr = encodingName; enum XML_Error result;
const XML_Char *s = poolStoreString(&tempPool,
encoding,
encodingName,
encodingName
+ XmlNameLength(encoding, encodingName));
if (!s)
return XML_ERROR_NO_MEMORY;
result = handleUnknownEncoding(parser, s);
poolDiscard(&tempPool);
if (result == XML_ERROR_UNKNOWN_ENCODING)
eventPtr = encodingName;
return result;
}
}
return XML_ERROR_NONE;
}
static enum XML_Error
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
{
if (unknownEncodingHandler) {
XML_Encoding info;
int i;
for (i = 0; i < 256; i++)
info.map[i] = -1;
info.convert = 0;
info.data = 0;
info.release = 0;
if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, &info)) {
ENCODING *enc;
unknownEncodingMem = malloc(XmlSizeOfUnknownEncoding());
if (!unknownEncodingMem) {
if (info.release)
info.release(info.data);
return XML_ERROR_NO_MEMORY;
}
enc = (ns
? XmlInitUnknownEncodingNS
: XmlInitUnknownEncoding)(unknownEncodingMem,
info.map,
info.convert,
info.data);
if (enc) {
unknownEncodingData = info.data;
unknownEncodingRelease = info.release;
encoding = enc;
return XML_ERROR_NONE;
}
}
if (info.release)
info.release(info.data);
}
return XML_ERROR_UNKNOWN_ENCODING; return XML_ERROR_UNKNOWN_ENCODING;
}
static enum XML_Error
prologInitProcessor(XML_Parser parser,
const char *s,
const char *end,
const char **nextPtr)
{
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
processor = prologProcessor;
return prologProcessor(parser, s, end, nextPtr);
}
static enum XML_Error
prologProcessor(XML_Parser parser,
const char *s,
const char *end,
const char **nextPtr)
{
for (;;) {
const char *next;
int tok = XmlPrologTok(encoding, s, end, &next);
if (tok <= 0) {
if (nextPtr != 0 && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
} }
if (standalone == 1) switch (tok) {
dtd.standalone = 1; case XML_TOK_INVALID:
break; eventPtr = next;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_NONE:
return XML_ERROR_NO_ELEMENTS;
case XML_TOK_PARTIAL:
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
return XML_ERROR_PARTIAL_CHAR;
case XML_TOK_TRAILING_CR:
eventPtr = s + encoding->minBytesPerChar;
return XML_ERROR_NO_ELEMENTS;
default:
abort();
}
}
switch (XmlTokenRole(&prologState, tok, s, next, encoding)) {
case XML_ROLE_XML_DECL:
{
enum XML_Error result = processXmlDecl(parser, 0, s, next);
if (result != XML_ERROR_NONE)
return result;
} }
break;
case XML_ROLE_DOCTYPE_SYSTEM_ID: case XML_ROLE_DOCTYPE_SYSTEM_ID:
if (!dtd.standalone
&& notStandaloneHandler
&& !notStandaloneHandler(handlerArg))
return XML_ERROR_NOT_STANDALONE;
hadExternalDoctype = 1; hadExternalDoctype = 1;
break; break;
case XML_ROLE_DOCTYPE_PUBLIC_ID: case XML_ROLE_DOCTYPE_PUBLIC_ID:
case XML_ROLE_ENTITY_PUBLIC_ID: case XML_ROLE_ENTITY_PUBLIC_ID:
case XML_ROLE_NOTATION_PUBLIC_ID: if (!XmlIsPublicId(encoding, s, next, &eventPtr))
if (!XmlIsPublicId(encoding, s, next, &errorPtr))
return XML_ERROR_SYNTAX; return XML_ERROR_SYNTAX;
if (declEntity) {
XML_Char *tem = poolStoreString(&dtd.pool,
encoding,
s + encoding->minBytesPerChar,
next - encoding->minBytesPerChar);
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
declEntity->publicId = tem;
poolFinish(&dtd.pool);
}
break; break;
case XML_ROLE_INSTANCE_START: case XML_ROLE_INSTANCE_START:
processor = contentProcessor; processor = contentProcessor;
...@@ -941,7 +2032,7 @@ prologProcessor(XML_Parser parser, ...@@ -941,7 +2032,7 @@ prologProcessor(XML_Parser parser,
return contentProcessor(parser, s, end, nextPtr); return contentProcessor(parser, s, end, nextPtr);
case XML_ROLE_ATTLIST_ELEMENT_NAME: case XML_ROLE_ATTLIST_ELEMENT_NAME:
{ {
const char *name = poolStoreString(&dtd.pool, encoding, s, next); const XML_Char *name = poolStoreString(&dtd.pool, encoding, s, next);
if (!name) if (!name)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
declElementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, name, sizeof(ELEMENT_TYPE)); declElementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, name, sizeof(ELEMENT_TYPE));
...@@ -949,8 +2040,11 @@ prologProcessor(XML_Parser parser, ...@@ -949,8 +2040,11 @@ prologProcessor(XML_Parser parser,
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
if (declElementType->name != name) if (declElementType->name != name)
poolDiscard(&dtd.pool); poolDiscard(&dtd.pool);
else else {
poolFinish(&dtd.pool); poolFinish(&dtd.pool);
if (!setElementTypePrefix(parser, declElementType))
return XML_ERROR_NO_MEMORY;
}
break; break;
} }
case XML_ROLE_ATTRIBUTE_NAME: case XML_ROLE_ATTRIBUTE_NAME:
...@@ -971,7 +2065,7 @@ prologProcessor(XML_Parser parser, ...@@ -971,7 +2065,7 @@ prologProcessor(XML_Parser parser,
case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE:
case XML_ROLE_FIXED_ATTRIBUTE_VALUE: case XML_ROLE_FIXED_ATTRIBUTE_VALUE:
{ {
const char *attVal; const XML_Char *attVal;
enum XML_Error result enum XML_Error result
= storeAttributeValue(parser, encoding, declAttributeIsCdata, = storeAttributeValue(parser, encoding, declAttributeIsCdata,
s + encoding->minBytesPerChar, s + encoding->minBytesPerChar,
...@@ -1000,6 +2094,7 @@ prologProcessor(XML_Parser parser, ...@@ -1000,6 +2094,7 @@ prologProcessor(XML_Parser parser,
next - encoding->minBytesPerChar); next - encoding->minBytesPerChar);
if (!declEntity->systemId) if (!declEntity->systemId)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
declEntity->base = dtd.base;
poolFinish(&dtd.pool); poolFinish(&dtd.pool);
} }
break; break;
...@@ -1009,11 +2104,26 @@ prologProcessor(XML_Parser parser, ...@@ -1009,11 +2104,26 @@ prologProcessor(XML_Parser parser,
if (!declEntity->notation) if (!declEntity->notation)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
poolFinish(&dtd.pool); poolFinish(&dtd.pool);
if (unparsedEntityDeclHandler) {
eventPtr = eventEndPtr = s;
unparsedEntityDeclHandler(handlerArg,
declEntity->name,
declEntity->base,
declEntity->systemId,
declEntity->publicId,
declEntity->notation);
}
} }
break; break;
case XML_ROLE_GENERAL_ENTITY_NAME: case XML_ROLE_GENERAL_ENTITY_NAME:
{ {
const char *name = poolStoreString(&dtd.pool, encoding, s, next); const XML_Char *name;
if (XmlPredefinedEntityName(encoding, s, next)) {
declEntity = 0;
break;
}
name = poolStoreString(&dtd.pool, encoding, s, next);
if (!name) if (!name)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
if (dtd.complete) { if (dtd.complete) {
...@@ -1036,8 +2146,61 @@ prologProcessor(XML_Parser parser, ...@@ -1036,8 +2146,61 @@ prologProcessor(XML_Parser parser,
case XML_ROLE_PARAM_ENTITY_NAME: case XML_ROLE_PARAM_ENTITY_NAME:
declEntity = 0; declEntity = 0;
break; break;
case XML_ROLE_NOTATION_NAME:
declNotationPublicId = 0;
declNotationName = 0;
if (notationDeclHandler) {
declNotationName = poolStoreString(&tempPool, encoding, s, next);
if (!declNotationName)
return XML_ERROR_NO_MEMORY;
poolFinish(&tempPool);
}
break;
case XML_ROLE_NOTATION_PUBLIC_ID:
if (!XmlIsPublicId(encoding, s, next, &eventPtr))
return XML_ERROR_SYNTAX;
if (declNotationName) {
XML_Char *tem = poolStoreString(&tempPool,
encoding,
s + encoding->minBytesPerChar,
next - encoding->minBytesPerChar);
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
declNotationPublicId = tem;
poolFinish(&tempPool);
}
break;
case XML_ROLE_NOTATION_SYSTEM_ID:
if (declNotationName && notationDeclHandler) {
const XML_Char *systemId
= poolStoreString(&tempPool, encoding,
s + encoding->minBytesPerChar,
next - encoding->minBytesPerChar);
if (!systemId)
return XML_ERROR_NO_MEMORY;
eventPtr = eventEndPtr = s;
notationDeclHandler(handlerArg,
declNotationName,
dtd.base,
systemId,
declNotationPublicId);
}
poolClear(&tempPool);
break;
case XML_ROLE_NOTATION_NO_SYSTEM_ID:
if (declNotationPublicId && notationDeclHandler) {
eventPtr = eventEndPtr = s;
notationDeclHandler(handlerArg,
declNotationName,
dtd.base,
0,
declNotationPublicId);
}
poolClear(&tempPool);
break;
case XML_ROLE_ERROR: case XML_ROLE_ERROR:
errorPtr = s; eventPtr = s;
switch (tok) { switch (tok) {
case XML_TOK_PARAM_ENTITY_REF: case XML_TOK_PARAM_ENTITY_REF:
return XML_ERROR_PARAM_ENTITY_REF; return XML_ERROR_PARAM_ENTITY_REF;
...@@ -1059,29 +2222,54 @@ prologProcessor(XML_Parser parser, ...@@ -1059,29 +2222,54 @@ prologProcessor(XML_Parser parser,
break; break;
case XML_ROLE_GROUP_SEQUENCE: case XML_ROLE_GROUP_SEQUENCE:
if (groupConnector[prologState.level] == '|') { if (groupConnector[prologState.level] == '|') {
errorPtr = s; eventPtr = s;
return XML_ERROR_SYNTAX; return XML_ERROR_SYNTAX;
} }
groupConnector[prologState.level] = ','; groupConnector[prologState.level] = ',';
break; break;
case XML_ROLE_GROUP_CHOICE: case XML_ROLE_GROUP_CHOICE:
if (groupConnector[prologState.level] == ',') { if (groupConnector[prologState.level] == ',') {
errorPtr = s; eventPtr = s;
return XML_ERROR_SYNTAX; return XML_ERROR_SYNTAX;
} }
groupConnector[prologState.level] = '|'; groupConnector[prologState.level] = '|';
break; break;
case XML_ROLE_PARAM_ENTITY_REF: case XML_ROLE_PARAM_ENTITY_REF:
if (!dtd.standalone
&& notStandaloneHandler
&& !notStandaloneHandler(handlerArg))
return XML_ERROR_NOT_STANDALONE;
dtd.complete = 0; dtd.complete = 0;
break; break;
case XML_ROLE_NONE: case XML_ROLE_NONE:
switch (tok) { switch (tok) {
case XML_TOK_PI: case XML_TOK_PI:
eventPtr = s;
eventEndPtr = next;
if (!reportProcessingInstruction(parser, encoding, s, next)) if (!reportProcessingInstruction(parser, encoding, s, next))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
break; break;
case XML_TOK_COMMENT:
eventPtr = s;
eventEndPtr = next;
if (!reportComment(parser, encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
}
break;
} }
if (defaultHandler) {
switch (tok) {
case XML_TOK_PI:
case XML_TOK_COMMENT:
case XML_TOK_BOM:
case XML_TOK_XML_DECL:
break; break;
default:
eventPtr = s;
eventEndPtr = next;
reportDefault(parser, encoding, s, next);
}
} }
s = next; s = next;
} }
...@@ -1095,44 +2283,53 @@ enum XML_Error epilogProcessor(XML_Parser parser, ...@@ -1095,44 +2283,53 @@ enum XML_Error epilogProcessor(XML_Parser parser,
const char **nextPtr) const char **nextPtr)
{ {
processor = epilogProcessor; processor = epilogProcessor;
eventPtr = s;
for (;;) { for (;;) {
const char *next; const char *next;
int tok = XmlPrologTok(encoding, s, end, &next); int tok = XmlPrologTok(encoding, s, end, &next);
eventEndPtr = next;
switch (tok) { switch (tok) {
case XML_TOK_TRAILING_CR: case XML_TOK_TRAILING_CR:
if (defaultHandler) {
eventEndPtr = end;
reportDefault(parser, encoding, s, end);
}
/* fall through */
case XML_TOK_NONE: case XML_TOK_NONE:
if (nextPtr) if (nextPtr)
*nextPtr = end; *nextPtr = end;
return XML_ERROR_NONE; return XML_ERROR_NONE;
case XML_TOK_PROLOG_S: case XML_TOK_PROLOG_S:
case XML_TOK_COMMENT: if (defaultHandler)
reportDefault(parser, encoding, s, next);
break; break;
case XML_TOK_PI: case XML_TOK_PI:
if (!reportProcessingInstruction(parser, encoding, s, next)) if (!reportProcessingInstruction(parser, encoding, s, next))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
break; break;
case XML_TOK_COMMENT:
if (!reportComment(parser, encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
case XML_TOK_INVALID: case XML_TOK_INVALID:
errorPtr = next; eventPtr = next;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL: case XML_TOK_PARTIAL:
if (nextPtr) { if (nextPtr) {
*nextPtr = s; *nextPtr = s;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
errorPtr = s;
return XML_ERROR_UNCLOSED_TOKEN; return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR: case XML_TOK_PARTIAL_CHAR:
if (nextPtr) { if (nextPtr) {
*nextPtr = s; *nextPtr = s;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
errorPtr = s;
return XML_ERROR_PARTIAL_CHAR; return XML_ERROR_PARTIAL_CHAR;
default: default:
errorPtr = s;
return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; return XML_ERROR_JUNK_AFTER_DOC_ELEMENT;
} }
s = next; eventPtr = s = next;
} }
} }
...@@ -1153,9 +2350,9 @@ storeAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, ...@@ -1153,9 +2350,9 @@ storeAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, end, pool); enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, end, pool);
if (result) if (result)
return result; return result;
if (!isCdata && poolLength(pool) && poolLastByte(pool) == ' ') if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20)
poolChop(pool); poolChop(pool);
if (!poolAppendByte(pool, 0)) if (!poolAppendChar(pool, XML_T('\0')))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
return XML_ERROR_NONE; return XML_ERROR_NONE;
} }
...@@ -1165,7 +2362,7 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, ...@@ -1165,7 +2362,7 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
const char *ptr, const char *end, const char *ptr, const char *end,
STRING_POOL *pool) STRING_POOL *pool)
{ {
const ENCODING *utf8 = XmlGetInternalEncoding(XML_UTF8_ENCODING); const ENCODING *internalEnc = ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding();
for (;;) { for (;;) {
const char *next; const char *next;
int tok = XmlAttributeValueTok(enc, ptr, end, &next); int tok = XmlAttributeValueTok(enc, ptr, end, &next);
...@@ -1173,31 +2370,35 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, ...@@ -1173,31 +2370,35 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
case XML_TOK_NONE: case XML_TOK_NONE:
return XML_ERROR_NONE; return XML_ERROR_NONE;
case XML_TOK_INVALID: case XML_TOK_INVALID:
errorPtr = next; if (enc == encoding)
eventPtr = next;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL: case XML_TOK_PARTIAL:
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_CHAR_REF: case XML_TOK_CHAR_REF:
{ {
char buf[XML_MAX_BYTES_PER_CHAR]; XML_Char buf[XML_ENCODE_MAX];
int i; int i;
int n = XmlCharRefNumber(enc, ptr); int n = XmlCharRefNumber(enc, ptr);
if (n < 0) { if (n < 0) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_BAD_CHAR_REF; return XML_ERROR_BAD_CHAR_REF;
} }
if (!isCdata if (!isCdata
&& n == ' ' && n == 0x20 /* space */
&& (poolLength(pool) == 0 || poolLastByte(pool) == ' ')) && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
break; break;
n = XmlEncode(utf8, n, buf); n = XmlEncode(n, (ICHAR *)buf);
if (!n) { if (!n) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_BAD_CHAR_REF; return XML_ERROR_BAD_CHAR_REF;
} }
for (i = 0; i < n; i++) { for (i = 0; i < n; i++) {
if (!poolAppendByte(pool, buf[i])) if (!poolAppendChar(pool, buf[i]))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
} }
} }
...@@ -1212,57 +2413,62 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, ...@@ -1212,57 +2413,62 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata,
/* fall through */ /* fall through */
case XML_TOK_ATTRIBUTE_VALUE_S: case XML_TOK_ATTRIBUTE_VALUE_S:
case XML_TOK_DATA_NEWLINE: case XML_TOK_DATA_NEWLINE:
if (!isCdata && (poolLength(pool) == 0 || poolLastByte(pool) == ' ')) if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
break; break;
if (!poolAppendByte(pool, ' ')) if (!poolAppendChar(pool, 0x20))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
break; break;
case XML_TOK_ENTITY_REF: case XML_TOK_ENTITY_REF:
{ {
const char *name = poolStoreString(&temp2Pool, enc, const XML_Char *name;
ENTITY *entity;
XML_Char ch = XmlPredefinedEntityName(enc,
ptr + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (ch) {
if (!poolAppendChar(pool, ch))
return XML_ERROR_NO_MEMORY;
break;
}
name = poolStoreString(&temp2Pool, enc,
ptr + enc->minBytesPerChar, ptr + enc->minBytesPerChar,
next - enc->minBytesPerChar); next - enc->minBytesPerChar);
ENTITY *entity;
if (!name) if (!name)
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0); entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0);
poolDiscard(&temp2Pool); poolDiscard(&temp2Pool);
if (!entity) { if (!entity) {
if (dtd.complete) { if (dtd.complete) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_UNDEFINED_ENTITY; return XML_ERROR_UNDEFINED_ENTITY;
} }
} }
else if (entity->open) { else if (entity->open) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_RECURSIVE_ENTITY_REF; return XML_ERROR_RECURSIVE_ENTITY_REF;
} }
else if (entity->notation) { else if (entity->notation) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_BINARY_ENTITY_REF; return XML_ERROR_BINARY_ENTITY_REF;
} }
else if (entity->magic) {
int i;
for (i = 0; i < entity->textLen; i++)
if (!poolAppendByte(pool, entity->textPtr[i]))
return XML_ERROR_NO_MEMORY;
}
else if (!entity->textPtr) { else if (!entity->textPtr) {
errorPtr = ptr; if (enc == encoding)
eventPtr = ptr;
return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF;
} }
else { else {
enum XML_Error result; enum XML_Error result;
const char *textEnd = entity->textPtr + entity->textLen; const XML_Char *textEnd = entity->textPtr + entity->textLen;
entity->open = 1; entity->open = 1;
result = appendAttributeValue(parser, utf8, isCdata, entity->textPtr, textEnd, pool); result = appendAttributeValue(parser, internalEnc, isCdata, (char *)entity->textPtr, (char *)textEnd, pool);
entity->open = 0; entity->open = 0;
if (result) { if (result)
errorPtr = ptr;
return result; return result;
} }
} }
}
break; break;
default: default:
abort(); abort();
...@@ -1277,7 +2483,7 @@ enum XML_Error storeEntityValue(XML_Parser parser, ...@@ -1277,7 +2483,7 @@ enum XML_Error storeEntityValue(XML_Parser parser,
const char *entityTextPtr, const char *entityTextPtr,
const char *entityTextEnd) const char *entityTextEnd)
{ {
const ENCODING *utf8 = XmlGetInternalEncoding(XML_UTF8_ENCODING); const ENCODING *internalEnc = ns ? XmlGetInternalEncodingNS() : XmlGetInternalEncoding();
STRING_POOL *pool = &(dtd.pool); STRING_POOL *pool = &(dtd.pool);
entityTextPtr += encoding->minBytesPerChar; entityTextPtr += encoding->minBytesPerChar;
entityTextEnd -= encoding->minBytesPerChar; entityTextEnd -= encoding->minBytesPerChar;
...@@ -1286,7 +2492,7 @@ enum XML_Error storeEntityValue(XML_Parser parser, ...@@ -1286,7 +2492,7 @@ enum XML_Error storeEntityValue(XML_Parser parser,
int tok = XmlEntityValueTok(encoding, entityTextPtr, entityTextEnd, &next); int tok = XmlEntityValueTok(encoding, entityTextPtr, entityTextEnd, &next);
switch (tok) { switch (tok) {
case XML_TOK_PARAM_ENTITY_REF: case XML_TOK_PARAM_ENTITY_REF:
errorPtr = entityTextPtr; eventPtr = entityTextPtr;
return XML_ERROR_SYNTAX; return XML_ERROR_SYNTAX;
case XML_TOK_NONE: case XML_TOK_NONE:
if (declEntity) { if (declEntity) {
...@@ -1308,20 +2514,20 @@ enum XML_Error storeEntityValue(XML_Parser parser, ...@@ -1308,20 +2514,20 @@ enum XML_Error storeEntityValue(XML_Parser parser,
case XML_TOK_DATA_NEWLINE: case XML_TOK_DATA_NEWLINE:
if (pool->end == pool->ptr && !poolGrow(pool)) if (pool->end == pool->ptr && !poolGrow(pool))
return XML_ERROR_NO_MEMORY; return XML_ERROR_NO_MEMORY;
*(pool->ptr)++ = '\n'; *(pool->ptr)++ = 0xA;
break; break;
case XML_TOK_CHAR_REF: case XML_TOK_CHAR_REF:
{ {
char buf[XML_MAX_BYTES_PER_CHAR]; XML_Char buf[XML_ENCODE_MAX];
int i; int i;
int n = XmlCharRefNumber(encoding, entityTextPtr); int n = XmlCharRefNumber(encoding, entityTextPtr);
if (n < 0) { if (n < 0) {
errorPtr = entityTextPtr; eventPtr = entityTextPtr;
return XML_ERROR_BAD_CHAR_REF; return XML_ERROR_BAD_CHAR_REF;
} }
n = XmlEncode(utf8, n, buf); n = XmlEncode(n, (ICHAR *)buf);
if (!n) { if (!n) {
errorPtr = entityTextPtr; eventPtr = entityTextPtr;
return XML_ERROR_BAD_CHAR_REF; return XML_ERROR_BAD_CHAR_REF;
} }
for (i = 0; i < n; i++) { for (i = 0; i < n; i++) {
...@@ -1332,10 +2538,10 @@ enum XML_Error storeEntityValue(XML_Parser parser, ...@@ -1332,10 +2538,10 @@ enum XML_Error storeEntityValue(XML_Parser parser,
} }
break; break;
case XML_TOK_PARTIAL: case XML_TOK_PARTIAL:
errorPtr = entityTextPtr; eventPtr = entityTextPtr;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
case XML_TOK_INVALID: case XML_TOK_INVALID:
errorPtr = next; eventPtr = next;
return XML_ERROR_INVALID_TOKEN; return XML_ERROR_INVALID_TOKEN;
default: default:
abort(); abort();
...@@ -1346,36 +2552,42 @@ enum XML_Error storeEntityValue(XML_Parser parser, ...@@ -1346,36 +2552,42 @@ enum XML_Error storeEntityValue(XML_Parser parser,
} }
static void static void
normalizeLines(char *s) normalizeLines(XML_Char *s)
{ {
char *p; XML_Char *p;
s = strchr(s, '\r'); for (;; s++) {
if (!s) if (*s == XML_T('\0'))
return; return;
if (*s == 0xD)
break;
}
p = s; p = s;
while (*s) { do {
if (*s == '\r') { if (*s == 0xD) {
*p++ = '\n'; *p++ = 0xA;
if (*++s == '\n') if (*++s == 0xA)
s++; s++;
} }
else else
*p++ = *s++; *p++ = *s++;
} } while (*s);
*p = '\0'; *p = XML_T('\0');
} }
static int static int
reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end) reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
{ {
const char *target; const XML_Char *target;
char *data; XML_Char *data;
const char *tem; const char *tem;
if (!processingInstructionHandler) if (!processingInstructionHandler) {
if (defaultHandler)
reportDefault(parser, enc, start, end);
return 1; return 1;
target = start + enc->minBytesPerChar * 2; }
tem = target + XmlNameLength(enc, target); start += enc->minBytesPerChar * 2;
target = poolStoreString(&tempPool, enc, target, tem); tem = start + XmlNameLength(enc, start);
target = poolStoreString(&tempPool, enc, start, tem);
if (!target) if (!target)
return 0; return 0;
poolFinish(&tempPool); poolFinish(&tempPool);
...@@ -1385,22 +2597,73 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char * ...@@ -1385,22 +2597,73 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *
if (!data) if (!data)
return 0; return 0;
normalizeLines(data); normalizeLines(data);
processingInstructionHandler(userData, target, data); processingInstructionHandler(handlerArg, target, data);
poolClear(&tempPool); poolClear(&tempPool);
return 1; return 1;
} }
static int static int
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, const char *value) reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
{
XML_Char *data;
if (!commentHandler) {
if (defaultHandler)
reportDefault(parser, enc, start, end);
return 1;
}
data = poolStoreString(&tempPool,
enc,
start + enc->minBytesPerChar * 4,
end - enc->minBytesPerChar * 3);
if (!data)
return 0;
normalizeLines(data);
commentHandler(handlerArg, data);
poolClear(&tempPool);
return 1;
}
static void
reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, const char *end)
{
if (MUST_CONVERT(enc, s)) {
const char **eventPP;
const char **eventEndPP;
if (enc == encoding) {
eventPP = &eventPtr;
eventEndPP = &eventEndPtr;
}
else {
eventPP = &(openInternalEntities->internalEventPtr);
eventEndPP = &(openInternalEntities->internalEventEndPtr);
}
do {
ICHAR *dataPtr = (ICHAR *)dataBuf;
XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
*eventEndPP = s;
defaultHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf);
*eventPP = s;
} while (s != end);
}
else
defaultHandler(handlerArg, (XML_Char *)s, (XML_Char *)end - (XML_Char *)s);
}
static int
defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, const XML_Char *value)
{ {
DEFAULT_ATTRIBUTE *att; DEFAULT_ATTRIBUTE *att;
if (type->nDefaultAtts == type->allocDefaultAtts) { if (type->nDefaultAtts == type->allocDefaultAtts) {
if (type->allocDefaultAtts == 0) if (type->allocDefaultAtts == 0) {
type->allocDefaultAtts = 8; type->allocDefaultAtts = 8;
else type->defaultAtts = malloc(type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE));
}
else {
type->allocDefaultAtts *= 2; type->allocDefaultAtts *= 2;
type->defaultAtts = realloc(type->defaultAtts, type->defaultAtts = realloc(type->defaultAtts,
type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE)); type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE));
}
if (!type->defaultAtts) if (!type->defaultAtts)
return 0; return 0;
} }
...@@ -1414,12 +2677,39 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, const char ...@@ -1414,12 +2677,39 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, const char
return 1; return 1;
} }
static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
{
const XML_Char *name;
for (name = elementType->name; *name; name++) {
if (*name == XML_T(':')) {
PREFIX *prefix;
const XML_Char *s;
for (s = elementType->name; s != name; s++) {
if (!poolAppendChar(&dtd.pool, *s))
return 0;
}
if (!poolAppendChar(&dtd.pool, XML_T('\0')))
return 0;
prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX));
if (!prefix)
return 0;
if (prefix->name == poolStart(&dtd.pool))
poolFinish(&dtd.pool);
else
poolDiscard(&dtd.pool);
elementType->prefix = prefix;
}
}
return 1;
}
static ATTRIBUTE_ID * static ATTRIBUTE_ID *
getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end) getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end)
{ {
ATTRIBUTE_ID *id; ATTRIBUTE_ID *id;
const char *name; const XML_Char *name;
if (!poolAppendByte(&dtd.pool, 0)) if (!poolAppendChar(&dtd.pool, XML_T('\0')))
return 0; return 0;
name = poolStoreString(&dtd.pool, enc, start, end); name = poolStoreString(&dtd.pool, enc, start, end);
if (!name) if (!name)
...@@ -1430,30 +2720,205 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const ...@@ -1430,30 +2720,205 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const
return 0; return 0;
if (id->name != name) if (id->name != name)
poolDiscard(&dtd.pool); poolDiscard(&dtd.pool);
else {
poolFinish(&dtd.pool);
if (!ns)
;
else if (name[0] == 'x'
&& name[1] == 'm'
&& name[2] == 'l'
&& name[3] == 'n'
&& name[4] == 's'
&& (name[5] == XML_T('\0') || name[5] == XML_T(':'))) {
if (name[5] == '\0')
id->prefix = &dtd.defaultPrefix;
else else
id->prefix = (PREFIX *)lookup(&dtd.prefixes, name + 6, sizeof(PREFIX));
id->xmlns = 1;
}
else {
int i;
for (i = 0; name[i]; i++) {
if (name[i] == XML_T(':')) {
int j;
for (j = 0; j < i; j++) {
if (!poolAppendChar(&dtd.pool, name[j]))
return 0;
}
if (!poolAppendChar(&dtd.pool, XML_T('\0')))
return 0;
id->prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX));
if (id->prefix->name == poolStart(&dtd.pool))
poolFinish(&dtd.pool); poolFinish(&dtd.pool);
else
poolDiscard(&dtd.pool);
break;
}
}
}
}
return id; return id;
} }
static int dtdInit(DTD *p) #define CONTEXT_SEP XML_T('\f')
static
const XML_Char *getContext(XML_Parser parser)
{ {
static const char *names[] = { "lt", "amp", "gt", "quot", "apos" }; HASH_TABLE_ITER iter;
static const char chars[] = { '<', '&', '>', '"', '\'' }; int needSep = 0;
if (dtd.defaultPrefix.binding) {
int i; int i;
int len;
if (!poolAppendChar(&tempPool, XML_T('=')))
return 0;
len = dtd.defaultPrefix.binding->uriLen;
if (namespaceSeparator != XML_T('\0'))
len--;
for (i = 0; i < len; i++)
if (!poolAppendChar(&tempPool, dtd.defaultPrefix.binding->uri[i]))
return 0;
needSep = 1;
}
poolInit(&(p->pool)); hashTableIterInit(&iter, &(dtd.prefixes));
hashTableInit(&(p->generalEntities)); for (;;) {
for (i = 0; i < 5; i++) { int i;
ENTITY *entity = (ENTITY *)lookup(&(p->generalEntities), names[i], sizeof(ENTITY)); int len;
if (!entity) const XML_Char *s;
PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter);
if (!prefix)
break;
if (!prefix->binding)
continue;
if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
return 0;
for (s = prefix->name; *s; s++)
if (!poolAppendChar(&tempPool, *s))
return 0;
if (!poolAppendChar(&tempPool, XML_T('=')))
return 0;
len = prefix->binding->uriLen;
if (namespaceSeparator != XML_T('\0'))
len--;
for (i = 0; i < len; i++)
if (!poolAppendChar(&tempPool, prefix->binding->uri[i]))
return 0;
needSep = 1;
}
hashTableIterInit(&iter, &(dtd.generalEntities));
for (;;) {
const XML_Char *s;
ENTITY *e = (ENTITY *)hashTableIterNext(&iter);
if (!e)
break;
if (!e->open)
continue;
if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
return 0;
for (s = e->name; *s; s++)
if (!poolAppendChar(&tempPool, *s))
return 0;
needSep = 1;
}
if (!poolAppendChar(&tempPool, XML_T('\0')))
return 0;
return tempPool.start;
}
static
int setContext(XML_Parser parser, const XML_Char *context)
{
const XML_Char *s = context;
while (*context != XML_T('\0')) {
if (*s == CONTEXT_SEP || *s == XML_T('\0')) {
ENTITY *e;
if (!poolAppendChar(&tempPool, XML_T('\0')))
return 0;
e = (ENTITY *)lookup(&dtd.generalEntities, poolStart(&tempPool), 0);
if (e)
e->open = 1;
if (*s != XML_T('\0'))
s++;
context = s;
poolDiscard(&tempPool);
}
else if (*s == '=') {
PREFIX *prefix;
if (poolLength(&tempPool) == 0)
prefix = &dtd.defaultPrefix;
else {
if (!poolAppendChar(&tempPool, XML_T('\0')))
return 0;
prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&tempPool), sizeof(PREFIX));
if (!prefix)
return 0;
if (prefix->name == poolStart(&tempPool))
poolFinish(&tempPool);
else
poolDiscard(&tempPool);
}
for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); context++)
if (!poolAppendChar(&tempPool, *context))
return 0;
if (!poolAppendChar(&tempPool, XML_T('\0')))
return 0;
if (!addBinding(parser, prefix, 0, poolStart(&tempPool), &inheritedBindings))
return 0;
poolDiscard(&tempPool);
if (*context != XML_T('\0'))
++context;
s = context;
}
else {
if (!poolAppendChar(&tempPool, *s))
return 0; return 0;
entity->textPtr = chars + i; s++;
entity->textLen = 1; }
entity->magic = 1; }
return 1;
}
static
void normalizePublicId(XML_Char *publicId)
{
XML_Char *p = publicId;
XML_Char *s;
for (s = publicId; *s; s++) {
switch (*s) {
case 0x20:
case 0xD:
case 0xA:
if (p != publicId && p[-1] != 0x20)
*p++ = 0x20;
break;
default:
*p++ = *s;
}
} }
if (p != publicId && p[-1] == 0x20)
--p;
*p = XML_T('\0');
}
static int dtdInit(DTD *p)
{
poolInit(&(p->pool));
hashTableInit(&(p->generalEntities));
hashTableInit(&(p->elementTypes)); hashTableInit(&(p->elementTypes));
hashTableInit(&(p->attributeIds)); hashTableInit(&(p->attributeIds));
hashTableInit(&(p->prefixes));
p->complete = 1; p->complete = 1;
p->standalone = 0;
p->base = 0;
p->defaultPrefix.name = 0;
p->defaultPrefix.binding = 0;
return 1; return 1;
} }
...@@ -1465,14 +2930,164 @@ static void dtdDestroy(DTD *p) ...@@ -1465,14 +2930,164 @@ static void dtdDestroy(DTD *p)
ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter);
if (!e) if (!e)
break; break;
if (e->allocDefaultAtts != 0)
free(e->defaultAtts); free(e->defaultAtts);
} }
hashTableDestroy(&(p->generalEntities)); hashTableDestroy(&(p->generalEntities));
hashTableDestroy(&(p->elementTypes)); hashTableDestroy(&(p->elementTypes));
hashTableDestroy(&(p->attributeIds)); hashTableDestroy(&(p->attributeIds));
hashTableDestroy(&(p->prefixes));
poolDestroy(&(p->pool)); poolDestroy(&(p->pool));
} }
/* Do a deep copy of the DTD. Return 0 for out of memory; non-zero otherwise.
The new DTD has already been initialized. */
static int dtdCopy(DTD *newDtd, const DTD *oldDtd)
{
HASH_TABLE_ITER iter;
if (oldDtd->base) {
const XML_Char *tem = poolCopyString(&(newDtd->pool), oldDtd->base);
if (!tem)
return 0;
newDtd->base = tem;
}
/* Copy the prefix table. */
hashTableIterInit(&iter, &(oldDtd->prefixes));
for (;;) {
const XML_Char *name;
const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter);
if (!oldP)
break;
name = poolCopyString(&(newDtd->pool), oldP->name);
if (!name)
return 0;
if (!lookup(&(newDtd->prefixes), name, sizeof(PREFIX)))
return 0;
}
hashTableIterInit(&iter, &(oldDtd->attributeIds));
/* Copy the attribute id table. */
for (;;) {
ATTRIBUTE_ID *newA;
const XML_Char *name;
const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter);
if (!oldA)
break;
/* Remember to allocate the scratch byte before the name. */
if (!poolAppendChar(&(newDtd->pool), XML_T('\0')))
return 0;
name = poolCopyString(&(newDtd->pool), oldA->name);
if (!name)
return 0;
++name;
newA = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), name, sizeof(ATTRIBUTE_ID));
if (!newA)
return 0;
newA->maybeTokenized = oldA->maybeTokenized;
if (oldA->prefix) {
newA->xmlns = oldA->xmlns;
if (oldA->prefix == &oldDtd->defaultPrefix)
newA->prefix = &newDtd->defaultPrefix;
else
newA->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldA->prefix->name, 0);
}
}
/* Copy the element type table. */
hashTableIterInit(&iter, &(oldDtd->elementTypes));
for (;;) {
int i;
ELEMENT_TYPE *newE;
const XML_Char *name;
const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter);
if (!oldE)
break;
name = poolCopyString(&(newDtd->pool), oldE->name);
if (!name)
return 0;
newE = (ELEMENT_TYPE *)lookup(&(newDtd->elementTypes), name, sizeof(ELEMENT_TYPE));
if (!newE)
return 0;
if (oldE->nDefaultAtts) {
newE->defaultAtts = (DEFAULT_ATTRIBUTE *)malloc(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE));
if (!newE->defaultAtts)
return 0;
}
newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts;
if (oldE->prefix)
newE->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldE->prefix->name, 0);
for (i = 0; i < newE->nDefaultAtts; i++) {
newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0);
newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata;
if (oldE->defaultAtts[i].value) {
newE->defaultAtts[i].value = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value);
if (!newE->defaultAtts[i].value)
return 0;
}
else
newE->defaultAtts[i].value = 0;
}
}
/* Copy the entity table. */
hashTableIterInit(&iter, &(oldDtd->generalEntities));
for (;;) {
ENTITY *newE;
const XML_Char *name;
const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter);
if (!oldE)
break;
name = poolCopyString(&(newDtd->pool), oldE->name);
if (!name)
return 0;
newE = (ENTITY *)lookup(&(newDtd->generalEntities), name, sizeof(ENTITY));
if (!newE)
return 0;
if (oldE->systemId) {
const XML_Char *tem = poolCopyString(&(newDtd->pool), oldE->systemId);
if (!tem)
return 0;
newE->systemId = tem;
if (oldE->base) {
if (oldE->base == oldDtd->base)
newE->base = newDtd->base;
tem = poolCopyString(&(newDtd->pool), oldE->base);
if (!tem)
return 0;
newE->base = tem;
}
}
else {
const XML_Char *tem = poolCopyStringN(&(newDtd->pool), oldE->textPtr, oldE->textLen);
if (!tem)
return 0;
newE->textPtr = tem;
newE->textLen = oldE->textLen;
}
if (oldE->notation) {
const XML_Char *tem = poolCopyString(&(newDtd->pool), oldE->notation);
if (!tem)
return 0;
newE->notation = tem;
}
}
newDtd->complete = oldDtd->complete;
newDtd->standalone = oldDtd->standalone;
return 1;
}
static static
void poolInit(STRING_POOL *pool) void poolInit(STRING_POOL *pool)
{ {
...@@ -1526,13 +3141,13 @@ void poolDestroy(STRING_POOL *pool) ...@@ -1526,13 +3141,13 @@ void poolDestroy(STRING_POOL *pool)
} }
static static
char *poolAppend(STRING_POOL *pool, const ENCODING *enc, XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc,
const char *ptr, const char *end) const char *ptr, const char *end)
{ {
if (!pool->ptr && !poolGrow(pool)) if (!pool->ptr && !poolGrow(pool))
return 0; return 0;
for (;;) { for (;;) {
XmlConvert(enc, XML_UTF8_ENCODING, &ptr, end, &(pool->ptr), pool->end); XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end);
if (ptr == end) if (ptr == end)
break; break;
if (!poolGrow(pool)) if (!poolGrow(pool))
...@@ -1541,9 +3156,33 @@ char *poolAppend(STRING_POOL *pool, const ENCODING *enc, ...@@ -1541,9 +3156,33 @@ char *poolAppend(STRING_POOL *pool, const ENCODING *enc,
return pool->start; return pool->start;
} }
static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s)
{
do {
if (!poolAppendChar(pool, *s))
return 0;
} while (*s++);
s = pool->start;
poolFinish(pool);
return s;
}
static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n)
{
if (!pool->ptr && !poolGrow(pool))
return 0;
for (; n > 0; --n, s++) {
if (!poolAppendChar(pool, *s))
return 0;
}
s = pool->start;
poolFinish(pool);
return s;
}
static static
char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc,
const char *ptr, const char *end) const char *ptr, const char *end)
{ {
if (!poolAppend(pool, enc, ptr, end)) if (!poolAppend(pool, enc, ptr, end))
...@@ -1572,7 +3211,7 @@ int poolGrow(STRING_POOL *pool) ...@@ -1572,7 +3211,7 @@ int poolGrow(STRING_POOL *pool)
pool->freeBlocks->next = pool->blocks; pool->freeBlocks->next = pool->blocks;
pool->blocks = pool->freeBlocks; pool->blocks = pool->freeBlocks;
pool->freeBlocks = tem; pool->freeBlocks = tem;
memcpy(pool->blocks->s, pool->start, pool->end - pool->start); memcpy(pool->blocks->s, pool->start, (pool->end - pool->start) * sizeof(XML_Char));
pool->ptr = pool->blocks->s + (pool->ptr - pool->start); pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
pool->start = pool->blocks->s; pool->start = pool->blocks->s;
pool->end = pool->start + pool->blocks->size; pool->end = pool->start + pool->blocks->size;
...@@ -1581,7 +3220,7 @@ int poolGrow(STRING_POOL *pool) ...@@ -1581,7 +3220,7 @@ int poolGrow(STRING_POOL *pool)
} }
if (pool->blocks && pool->start == pool->blocks->s) { if (pool->blocks && pool->start == pool->blocks->s) {
int blockSize = (pool->end - pool->start)*2; int blockSize = (pool->end - pool->start)*2;
pool->blocks = realloc(pool->blocks, offsetof(BLOCK, s) + blockSize); pool->blocks = realloc(pool->blocks, offsetof(BLOCK, s) + blockSize * sizeof(XML_Char));
if (!pool->blocks) if (!pool->blocks)
return 0; return 0;
pool->blocks->size = blockSize; pool->blocks->size = blockSize;
...@@ -1596,13 +3235,13 @@ int poolGrow(STRING_POOL *pool) ...@@ -1596,13 +3235,13 @@ int poolGrow(STRING_POOL *pool)
blockSize = INIT_BLOCK_SIZE; blockSize = INIT_BLOCK_SIZE;
else else
blockSize *= 2; blockSize *= 2;
tem = malloc(offsetof(BLOCK, s) + blockSize); tem = malloc(offsetof(BLOCK, s) + blockSize * sizeof(XML_Char));
if (!tem) if (!tem)
return 0; return 0;
tem->size = blockSize; tem->size = blockSize;
tem->next = pool->blocks; tem->next = pool->blocks;
pool->blocks = tem; pool->blocks = tem;
memcpy(tem->s, pool->start, pool->ptr - pool->start); memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char));
pool->ptr = tem->s + (pool->ptr - pool->start); pool->ptr = tem->s + (pool->ptr - pool->start);
pool->start = tem->s; pool->start = tem->s;
pool->end = tem->s + blockSize; pool->end = tem->s + blockSize;
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#ifndef XmlParse_INCLUDED #ifndef XmlParse_INCLUDED
...@@ -31,32 +41,237 @@ extern "C" { ...@@ -31,32 +41,237 @@ extern "C" {
typedef void *XML_Parser; typedef void *XML_Parser;
/* Constructs a new parser; encoding should be the name of the charset from #ifdef XML_UNICODE_WCHAR_T
the Content-Type header if the Content-Type is text/xml, or null otherwise. */
XML_Parser XMLPARSEAPI /* XML_UNICODE_WCHAR_T will work only if sizeof(wchar_t) == 2 and wchar_t
XML_ParserCreate(const char *encoding); uses Unicode. */
/* Information is UTF-16 encoded as wchar_ts */
#ifndef XML_UNICODE
#define XML_UNICODE
#endif
#include <stddef.h>
typedef wchar_t XML_Char;
typedef wchar_t XML_LChar;
#else /* not XML_UNICODE_WCHAR_T */
#ifdef XML_UNICODE
/* Information is UTF-16 encoded as unsigned shorts */
typedef unsigned short XML_Char;
typedef char XML_LChar;
#else /* not XML_UNICODE */
/* Information is UTF-8 encoded. */ /* Information is UTF-8 encoded. */
typedef char XML_Char;
typedef char XML_LChar;
#endif /* not XML_UNICODE */
#endif /* not XML_UNICODE_WCHAR_T */
/* atts is array of name/value pairs, terminated by NULL; /* Constructs a new parser; encoding is the encoding specified by the external
names and values are '\0' terminated. */ protocol or null if there is none specified. */
XML_Parser XMLPARSEAPI
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. */
XML_Parser XMLPARSEAPI
XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
/* atts is array of name/value pairs, terminated by 0;
names and values are 0 terminated. */
typedef void (*XML_StartElementHandler)(void *userData, typedef void (*XML_StartElementHandler)(void *userData,
const char *name, const XML_Char *name,
const char **atts); const XML_Char **atts);
typedef void (*XML_EndElementHandler)(void *userData, typedef void (*XML_EndElementHandler)(void *userData,
const char *name); const XML_Char *name);
/* s is not 0 terminated. */
typedef void (*XML_CharacterDataHandler)(void *userData, typedef void (*XML_CharacterDataHandler)(void *userData,
const char *s, const XML_Char *s,
int len); int len);
/* target and data are '\0' terminated */ /* target and data are 0 terminated */
typedef void (*XML_ProcessingInstructionHandler)(void *userData, typedef void (*XML_ProcessingInstructionHandler)(void *userData,
const char *target, const XML_Char *target,
const char *data); 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. 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 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 (it has an
external subset or a reference to a parameter entity, but does not
have standalone="yes"). If this handler returns 0, then processing
will not continue, and the parser will return a
XML_ERROR_NOT_STANDALONE error. */
typedef int (*XML_NotStandaloneHandler)(void *userData);
/* This is called for a reference to an external parsed general entity.
The referenced entity is not automatically parsed.
The application can parse it immediately or later using
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 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,
(ie characters that would be encoded by surrogates in UTF-16
are not allowed). Note that this restriction doesn't apply to
the built-in support for UTF-8 and UTF-16.
4. No Unicode character may be encoded by more than one distinct sequence
of bytes. */
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);
void XMLPARSEAPI void XMLPARSEAPI
XML_SetElementHandler(XML_Parser parser, XML_SetElementHandler(XML_Parser parser,
...@@ -70,11 +285,106 @@ XML_SetCharacterDataHandler(XML_Parser parser, ...@@ -70,11 +285,106 @@ XML_SetCharacterDataHandler(XML_Parser parser,
void XMLPARSEAPI void XMLPARSEAPI
XML_SetProcessingInstructionHandler(XML_Parser parser, XML_SetProcessingInstructionHandler(XML_Parser parser,
XML_ProcessingInstructionHandler handler); XML_ProcessingInstructionHandler handler);
void XMLPARSEAPI
XML_SetCommentHandler(XML_Parser parser,
XML_CommentHandler handler);
void XMLPARSEAPI
XML_SetCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start,
XML_EndCdataSectionHandler end);
/* This sets the default handler and also inhibits expansion of internal entities.
The entity reference will be passed to the default handler. */
void XMLPARSEAPI
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. */
void XMLPARSEAPI
XML_SetDefaultHandlerExpand(XML_Parser parser,
XML_DefaultHandler handler);
void XMLPARSEAPI
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
XML_UnparsedEntityDeclHandler handler);
void XMLPARSEAPI
XML_SetNotationDeclHandler(XML_Parser parser,
XML_NotationDeclHandler handler);
void XMLPARSEAPI
XML_SetNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start,
XML_EndNamespaceDeclHandler end);
void XMLPARSEAPI
XML_SetNotStandaloneHandler(XML_Parser parser,
XML_NotStandaloneHandler handler);
void XMLPARSEAPI
XML_SetExternalEntityRefHandler(XML_Parser parser,
XML_ExternalEntityRefHandler handler);
/* 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. */
void XMLPARSEAPI
XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg);
void XMLPARSEAPI
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. */
void XMLPARSEAPI XML_DefaultCurrent(XML_Parser parser);
/* This value is passed as the userData argument to callbacks. */ /* This value is passed as the userData argument to callbacks. */
void XMLPARSEAPI void XMLPARSEAPI
XML_SetUserData(XML_Parser parser, void *userData); 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_CreateParser. It must not be called after XML_Parse
or XML_ParseBuffer. */
int XMLPARSEAPI
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. */
void XMLPARSEAPI
XML_UseParserAsHandlerArg(XML_Parser parser);
/* 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. */
int XMLPARSEAPI
XML_SetBase(XML_Parser parser, const XML_Char *base);
const XML_Char XMLPARSEAPI *
XML_GetBase(XML_Parser parser);
/* Returns the number of the attributes passed in last call to the
XML_StartElementHandler that were specified in the start-tag rather
than defaulted. */
int XMLPARSEAPI XML_GetSpecifiedAttributeCount(XML_Parser parser);
/* Parses some input. Returns 0 if a fatal error is detected. /* Parses some input. Returns 0 if a fatal error is detected.
The last call to XML_Parse must have isFinal true; The last call to XML_Parse must have isFinal true;
len may be zero for this call (or any other). */ len may be zero for this call (or any other). */
...@@ -87,8 +397,23 @@ XML_GetBuffer(XML_Parser parser, int len); ...@@ -87,8 +397,23 @@ XML_GetBuffer(XML_Parser parser, int len);
int XMLPARSEAPI int XMLPARSEAPI
XML_ParseBuffer(XML_Parser parser, int len, int isFinal); XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
/* If XML_Parser or XML_ParseEnd have returned 0, then XML_GetError* /* Creates an XML_Parser object that can parse an external general entity;
returns information about the error. */ 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. */
XML_Parser XMLPARSEAPI
XML_ExternalEntityParserCreate(XML_Parser parser,
const XML_Char *context,
const XML_Char *encoding);
enum XML_Error { enum XML_Error {
XML_ERROR_NONE, XML_ERROR_NONE,
...@@ -110,19 +435,45 @@ enum XML_Error { ...@@ -110,19 +435,45 @@ enum XML_Error {
XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
XML_ERROR_MISPLACED_XML_PI, XML_ERROR_MISPLACED_XML_PI,
XML_ERROR_UNKNOWN_ENCODING, XML_ERROR_UNKNOWN_ENCODING,
XML_ERROR_INCORRECT_ENCODING XML_ERROR_INCORRECT_ENCODING,
XML_ERROR_UNCLOSED_CDATA_SECTION,
XML_ERROR_EXTERNAL_ENTITY_HANDLING,
XML_ERROR_NOT_STANDALONE
}; };
int XMLPARSEAPI XML_GetErrorCode(XML_Parser parser); /* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode
int XMLPARSEAPI XML_GetErrorLineNumber(XML_Parser parser); returns information about the error. */
int XMLPARSEAPI XML_GetErrorColumnNumber(XML_Parser parser);
long XMLPARSEAPI XML_GetErrorByteIndex(XML_Parser parser); enum XML_Error XMLPARSEAPI 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. */
int XMLPARSEAPI XML_GetCurrentLineNumber(XML_Parser parser);
int XMLPARSEAPI XML_GetCurrentColumnNumber(XML_Parser parser);
long XMLPARSEAPI XML_GetCurrentByteIndex(XML_Parser parser);
/* Return the number of bytes in the current event.
Returns 0 if the event is in an internal entity. */
int XMLPARSEAPI XML_GetCurrentByteCount(XML_Parser parser);
/* For backwards compatibility with previous versions. */
#define XML_GetErrorLineNumber XML_GetCurrentLineNumber
#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
#define XML_GetErrorByteIndex XML_GetCurrentByteIndex
/* Frees memory used by the parser. */
void XMLPARSEAPI void XMLPARSEAPI
XML_ParserFree(XML_Parser parser); XML_ParserFree(XML_Parser parser);
const char XMLPARSEAPI * /* Returns a string describing the error. */
XML_ErrorString(int code); const XML_LChar XMLPARSEAPI *XML_ErrorString(int code);
#ifdef __cplusplus #ifdef __cplusplus
} }
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, /* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
...@@ -32,7 +42,7 @@ Contributor(s): ...@@ -32,7 +42,7 @@ Contributor(s):
/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_NMSTRT, BT_SEMI, /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,12 +12,25 @@ under the License. ...@@ -12,12 +12,25 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#define STRICT 1
#define WIN32_LEAN_AND_MEAN 1
#include <windows.h> #include <windows.h>
BOOL WINAPI DllMain(HANDLE hInst, ULONG ul_reason_for_call, LPVOID lpReserved) BOOL WINAPI DllMain(HANDLE hInst, ULONG ul_reason_for_call, LPVOID lpReserved)
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ /* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */
...@@ -33,7 +43,7 @@ Contributor(s): ...@@ -33,7 +43,7 @@ Contributor(s):
/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_NMSTRT, BT_SEMI, /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, /* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,19 +12,50 @@ under the License. ...@@ -12,19 +12,50 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include <string.h>
#ifdef XML_WINLIB
#define WIN32_LEAN_AND_MEAN
#define STRICT
#include <windows.h>
#define malloc(x) HeapAlloc(GetProcessHeap(), 0, (x))
#define calloc(x, y) HeapAlloc(GetProcessHeap(), HEAP_ZERO_MEMORY, (x)*(y))
#define free(x) HeapFree(GetProcessHeap(), 0, (x))
#define realloc(x, y) HeapReAlloc(GetProcessHeap(), 0, x, y)
#define abort() /* as nothing */
#else /* not XML_WINLIB */
#include <stdlib.h>
#endif /* not XML_WINLIB */
/* This file can be used for any definitions needed in /* This file can be used for any definitions needed in
particular environments. */ particular environments. */
#ifdef MOZILLA #ifdef MOZILLA
#include "nspr.h" #include "nspr.h"
#define malloc(x) PR_Calloc(1,(x)) #define malloc(x) PR_Malloc(x)
#define realloc(x, y) PR_Realloc((x), (y))
#define calloc(x, y) PR_Calloc((x),(y)) #define calloc(x, y) PR_Calloc((x),(y))
#define free(x) PR_Free(x) #define free(x) PR_Free(x)
#define int int32 #define int int32
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include "xmldef.h" #include "xmldef.h"
...@@ -149,6 +159,7 @@ int doctype0(PROLOG_STATE *state, ...@@ -149,6 +159,7 @@ int doctype0(PROLOG_STATE *state,
case XML_TOK_PROLOG_S: case XML_TOK_PROLOG_S:
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = doctype1; state->handler = doctype1;
return XML_ROLE_DOCTYPE_NAME; return XML_ROLE_DOCTYPE_NAME;
} }
...@@ -594,7 +605,7 @@ int notation4(PROLOG_STATE *state, ...@@ -594,7 +605,7 @@ int notation4(PROLOG_STATE *state,
return XML_ROLE_NOTATION_SYSTEM_ID; return XML_ROLE_NOTATION_SYSTEM_ID;
case XML_TOK_DECL_CLOSE: case XML_TOK_DECL_CLOSE:
state->handler = internalSubset; state->handler = internalSubset;
return XML_ROLE_NONE; return XML_ROLE_NOTATION_NO_SYSTEM_ID;
} }
return syntaxError(state); return syntaxError(state);
} }
...@@ -610,6 +621,7 @@ int attlist0(PROLOG_STATE *state, ...@@ -610,6 +621,7 @@ int attlist0(PROLOG_STATE *state,
case XML_TOK_PROLOG_S: case XML_TOK_PROLOG_S:
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = attlist1; state->handler = attlist1;
return XML_ROLE_ATTLIST_ELEMENT_NAME; return XML_ROLE_ATTLIST_ELEMENT_NAME;
} }
...@@ -630,6 +642,7 @@ int attlist1(PROLOG_STATE *state, ...@@ -630,6 +642,7 @@ int attlist1(PROLOG_STATE *state,
state->handler = internalSubset; state->handler = internalSubset;
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = attlist2; state->handler = attlist2;
return XML_ROLE_ATTRIBUTE_NAME; return XML_ROLE_ATTRIBUTE_NAME;
} }
...@@ -689,6 +702,7 @@ int attlist3(PROLOG_STATE *state, ...@@ -689,6 +702,7 @@ int attlist3(PROLOG_STATE *state,
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NMTOKEN: case XML_TOK_NMTOKEN:
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = attlist4; state->handler = attlist4;
return XML_ROLE_ATTRIBUTE_ENUM_VALUE; return XML_ROLE_ATTRIBUTE_ENUM_VALUE;
} }
...@@ -836,6 +850,7 @@ int element0(PROLOG_STATE *state, ...@@ -836,6 +850,7 @@ int element0(PROLOG_STATE *state,
case XML_TOK_PROLOG_S: case XML_TOK_PROLOG_S:
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = element1; state->handler = element1;
return XML_ROLE_ELEMENT_NAME; return XML_ROLE_ELEMENT_NAME;
} }
...@@ -893,6 +908,7 @@ int element2(PROLOG_STATE *state, ...@@ -893,6 +908,7 @@ int element2(PROLOG_STATE *state,
state->handler = element6; state->handler = element6;
return XML_ROLE_GROUP_OPEN; return XML_ROLE_GROUP_OPEN;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = element7; state->handler = element7;
return XML_ROLE_CONTENT_ELEMENT; return XML_ROLE_CONTENT_ELEMENT;
case XML_TOK_NAME_QUESTION: case XML_TOK_NAME_QUESTION:
...@@ -940,6 +956,7 @@ int element4(PROLOG_STATE *state, ...@@ -940,6 +956,7 @@ int element4(PROLOG_STATE *state,
case XML_TOK_PROLOG_S: case XML_TOK_PROLOG_S:
return XML_ROLE_NONE; return XML_ROLE_NONE;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = element5; state->handler = element5;
return XML_ROLE_CONTENT_ELEMENT; return XML_ROLE_CONTENT_ELEMENT;
} }
...@@ -980,6 +997,7 @@ int element6(PROLOG_STATE *state, ...@@ -980,6 +997,7 @@ int element6(PROLOG_STATE *state,
state->level += 1; state->level += 1;
return XML_ROLE_GROUP_OPEN; return XML_ROLE_GROUP_OPEN;
case XML_TOK_NAME: case XML_TOK_NAME:
case XML_TOK_PREFIXED_NAME:
state->handler = element7; state->handler = element7;
return XML_ROLE_CONTENT_ELEMENT; return XML_ROLE_CONTENT_ELEMENT;
case XML_TOK_NAME_QUESTION: case XML_TOK_NAME_QUESTION:
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#ifndef XmlRole_INCLUDED #ifndef XmlRole_INCLUDED
...@@ -44,6 +54,7 @@ enum { ...@@ -44,6 +54,7 @@ enum {
XML_ROLE_ENTITY_NOTATION_NAME, XML_ROLE_ENTITY_NOTATION_NAME,
XML_ROLE_NOTATION_NAME, XML_ROLE_NOTATION_NAME,
XML_ROLE_NOTATION_SYSTEM_ID, XML_ROLE_NOTATION_SYSTEM_ID,
XML_ROLE_NOTATION_NO_SYSTEM_ID,
XML_ROLE_NOTATION_PUBLIC_ID, XML_ROLE_NOTATION_PUBLIC_ID,
XML_ROLE_ATTRIBUTE_NAME, XML_ROLE_ATTRIBUTE_NAME,
XML_ROLE_ATTRIBUTE_TYPE_CDATA, XML_ROLE_ATTRIBUTE_TYPE_CDATA,
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#include "xmldef.h" #include "xmldef.h"
...@@ -23,7 +33,7 @@ Contributor(s): ...@@ -23,7 +33,7 @@ Contributor(s):
#include "nametab.h" #include "nametab.h"
#define VTABLE1 \ #define VTABLE1 \
{ PREFIX(prologTok), PREFIX(contentTok) }, \ { PREFIX(prologTok), PREFIX(contentTok), PREFIX(cdataSectionTok) }, \
{ PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \ { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \
PREFIX(sameName), \ PREFIX(sameName), \
PREFIX(nameMatchesAscii), \ PREFIX(nameMatchesAscii), \
...@@ -31,14 +41,11 @@ Contributor(s): ...@@ -31,14 +41,11 @@ Contributor(s):
PREFIX(skipS), \ PREFIX(skipS), \
PREFIX(getAtts), \ PREFIX(getAtts), \
PREFIX(charRefNumber), \ PREFIX(charRefNumber), \
PREFIX(predefinedEntityName), \
PREFIX(updatePosition), \ PREFIX(updatePosition), \
PREFIX(isPublicId) PREFIX(isPublicId)
#define VTABLE2 \ #define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16)
PREFIX(encode), \
{ PREFIX(toUtf8) }
#define VTABLE VTABLE1, VTABLE2
#define UCS2_GET_NAMING(pages, hi, lo) \ #define UCS2_GET_NAMING(pages, hi, lo) \
(namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F))) (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F)))
...@@ -81,29 +88,173 @@ We need 8 bits to index into pages, 3 bits to add to that index and ...@@ -81,29 +88,173 @@ We need 8 bits to index into pages, 3 bits to add to that index and
#define UTF8_INVALID4(p) ((*p) == 0xF4 && ((p)[1] & 0x30) != 0) #define UTF8_INVALID4(p) ((*p) == 0xF4 && ((p)[1] & 0x30) != 0)
static
int isNever(const ENCODING *enc, const char *p)
{
return 0;
}
static
int utf8_isName2(const ENCODING *enc, const char *p)
{
return UTF8_GET_NAMING2(namePages, (const unsigned char *)p);
}
static
int utf8_isName3(const ENCODING *enc, const char *p)
{
return UTF8_GET_NAMING3(namePages, (const unsigned char *)p);
}
#define utf8_isName4 isNever
static
int utf8_isNmstrt2(const ENCODING *enc, const char *p)
{
return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p);
}
static
int utf8_isNmstrt3(const ENCODING *enc, const char *p)
{
return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p);
}
#define utf8_isNmstrt4 isNever
#define utf8_isInvalid2 isNever
static
int utf8_isInvalid3(const ENCODING *enc, const char *p)
{
return UTF8_INVALID3((const unsigned char *)p);
}
static
int utf8_isInvalid4(const ENCODING *enc, const char *p)
{
return UTF8_INVALID4((const unsigned char *)p);
}
struct normal_encoding { struct normal_encoding {
ENCODING enc; ENCODING enc;
unsigned char type[256]; unsigned char type[256];
#ifdef XML_MIN_SIZE
int (*byteType)(const ENCODING *, const char *);
int (*isNameMin)(const ENCODING *, const char *);
int (*isNmstrtMin)(const ENCODING *, const char *);
int (*byteToAscii)(const ENCODING *, const char *);
int (*charMatches)(const ENCODING *, const char *, int);
#endif /* XML_MIN_SIZE */
int (*isName2)(const ENCODING *, const char *);
int (*isName3)(const ENCODING *, const char *);
int (*isName4)(const ENCODING *, const char *);
int (*isNmstrt2)(const ENCODING *, const char *);
int (*isNmstrt3)(const ENCODING *, const char *);
int (*isNmstrt4)(const ENCODING *, const char *);
int (*isInvalid2)(const ENCODING *, const char *);
int (*isInvalid3)(const ENCODING *, const char *);
int (*isInvalid4)(const ENCODING *, const char *);
}; };
#ifdef XML_MIN_SIZE
#define STANDARD_VTABLE(E) \
E ## byteType, \
E ## isNameMin, \
E ## isNmstrtMin, \
E ## byteToAscii, \
E ## charMatches,
#else
#define STANDARD_VTABLE(E) /* as nothing */
#endif
#define NORMAL_VTABLE(E) \
E ## isName2, \
E ## isName3, \
E ## isName4, \
E ## isNmstrt2, \
E ## isNmstrt3, \
E ## isNmstrt4, \
E ## isInvalid2, \
E ## isInvalid3, \
E ## isInvalid4
static int checkCharRefNumber(int); static int checkCharRefNumber(int);
#include "xmltok_impl.h" #include "xmltok_impl.h"
#ifdef XML_MIN_SIZE
#define sb_isNameMin isNever
#define sb_isNmstrtMin isNever
#endif
#ifdef XML_MIN_SIZE
#define MINBPC(enc) ((enc)->minBytesPerChar)
#else
/* minimum bytes per character */ /* minimum bytes per character */
#define MINBPC 1 #define MINBPC(enc) 1
#define BYTE_TYPE(enc, p) \ #endif
#define SB_BYTE_TYPE(enc, p) \
(((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)])
#ifdef XML_MIN_SIZE
static
int sb_byteType(const ENCODING *enc, const char *p)
{
return SB_BYTE_TYPE(enc, p);
}
#define BYTE_TYPE(enc, p) \
(((const struct normal_encoding *)(enc))->byteType(enc, p))
#else
#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p)
#endif
#ifdef XML_MIN_SIZE
#define BYTE_TO_ASCII(enc, p) \
(((const struct normal_encoding *)(enc))->byteToAscii(enc, p))
static
int sb_byteToAscii(const ENCODING *enc, const char *p)
{
return *p;
}
#else
#define BYTE_TO_ASCII(enc, p) (*p) #define BYTE_TO_ASCII(enc, p) (*p)
#define IS_NAME_CHAR(enc, p, n) UTF8_GET_NAMING(namePages, p, n) #endif
#define IS_NMSTRT_CHAR(enc, p, n) UTF8_GET_NAMING(nmstrtPages, p, n)
#define IS_NAME_CHAR(enc, p, n) \
(((const struct normal_encoding *)(enc))->isName ## n(enc, p))
#define IS_NMSTRT_CHAR(enc, p, n) \
(((const struct normal_encoding *)(enc))->isNmstrt ## n(enc, p))
#define IS_INVALID_CHAR(enc, p, n) \ #define IS_INVALID_CHAR(enc, p, n) \
((n) == 3 \ (((const struct normal_encoding *)(enc))->isInvalid ## n(enc, p))
? UTF8_INVALID3((const unsigned char *)(p)) \
: ((n) == 4 ? UTF8_INVALID4((const unsigned char *)(p)) : 0)) #ifdef XML_MIN_SIZE
#define IS_NAME_CHAR_MINBPC(enc, p) \
(((const struct normal_encoding *)(enc))->isNameMin(enc, p))
#define IS_NMSTRT_CHAR_MINBPC(enc, p) \
(((const struct normal_encoding *)(enc))->isNmstrtMin(enc, p))
#else
#define IS_NAME_CHAR_MINBPC(enc, p) (0)
#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0)
#endif
#ifdef XML_MIN_SIZE
#define CHAR_MATCHES(enc, p, c) \
(((const struct normal_encoding *)(enc))->charMatches(enc, p, c))
static
int sb_charMatches(const ENCODING *enc, const char *p, int c)
{
return *p == c;
}
#else
/* c is an ASCII character */ /* c is an ASCII character */
#define CHAR_MATCHES(enc, p, c) (*(p) == c) #define CHAR_MATCHES(enc, p, c) (*(p) == c)
#endif
#define PREFIX(ident) normal_ ## ident #define PREFIX(ident) normal_ ## ident
#include "xmltok_impl.c" #include "xmltok_impl.c"
...@@ -113,51 +264,18 @@ static int checkCharRefNumber(int); ...@@ -113,51 +264,18 @@ static int checkCharRefNumber(int);
#undef BYTE_TO_ASCII #undef BYTE_TO_ASCII
#undef CHAR_MATCHES #undef CHAR_MATCHES
#undef IS_NAME_CHAR #undef IS_NAME_CHAR
#undef IS_NAME_CHAR_MINBPC
#undef IS_NMSTRT_CHAR #undef IS_NMSTRT_CHAR
#undef IS_NMSTRT_CHAR_MINBPC
#undef IS_INVALID_CHAR #undef IS_INVALID_CHAR
enum { enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */
/* cvalN is value of masked first byte of N byte sequence */ UTF8_cval1 = 0x00,
cval1 = 0x00, UTF8_cval2 = 0xc0,
cval2 = 0xc0, UTF8_cval3 = 0xe0,
cval3 = 0xe0, UTF8_cval4 = 0xf0
cval4 = 0xf0,
/* minN is minimum legal resulting value for N byte sequence */
min2 = 0x80,
min3 = 0x800,
min4 = 0x10000
}; };
static
int utf8_encode(const ENCODING *enc, int c, char *buf)
{
if (c < 0)
return 0;
if (c < min2) {
buf[0] = (c | cval1);
return 1;
}
if (c < min3) {
buf[0] = ((c >> 6) | cval2);
buf[1] = ((c & 0x3f) | 0x80);
return 2;
}
if (c < min4) {
buf[0] = ((c >> 12) | cval3);
buf[1] = (((c >> 6) & 0x3f) | 0x80);
buf[2] = ((c & 0x3f) | 0x80);
return 3;
}
if (c < 0x110000) {
buf[0] = ((c >> 18) | cval4);
buf[1] = (((c >> 12) & 0x3f) | 0x80);
buf[2] = (((c >> 6) & 0x3f) | 0x80);
buf[3] = ((c & 0x3f) | 0x80);
return 4;
}
return 0;
}
static static
void utf8_toUtf8(const ENCODING *enc, void utf8_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim, const char **fromP, const char *fromLim,
...@@ -177,33 +295,90 @@ void utf8_toUtf8(const ENCODING *enc, ...@@ -177,33 +295,90 @@ void utf8_toUtf8(const ENCODING *enc,
*toP = to; *toP = to;
} }
static
void utf8_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
unsigned short *to = *toP;
const char *from = *fromP;
while (from != fromLim && to != toLim) {
switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) {
case BT_LEAD2:
*to++ = ((from[0] & 0x1f) << 6) | (from[1] & 0x3f);
from += 2;
break;
case BT_LEAD3:
*to++ = ((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f);
from += 3;
break;
case BT_LEAD4:
{
unsigned long n;
if (to + 1 == toLim)
break;
n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f);
n -= 0x10000;
to[0] = (unsigned short)((n >> 10) | 0xD800);
to[1] = (unsigned short)((n & 0x3FF) | 0xDC00);
to += 2;
from += 4;
}
break;
default:
*to++ = *from++;
break;
}
}
*fromP = from;
*toP = to;
}
#ifdef XML_NS
static const struct normal_encoding utf8_encoding_ns = {
{ VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
{
#include "asciitab.h"
#include "utf8tab.h"
},
STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
};
#endif
static const struct normal_encoding utf8_encoding = { static const struct normal_encoding utf8_encoding = {
{ VTABLE1, utf8_encode, { utf8_toUtf8 }, 1 }, { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
{ {
#define BT_COLON BT_NMSTRT
#include "asciitab.h" #include "asciitab.h"
#undef BT_COLON
#include "utf8tab.h" #include "utf8tab.h"
} },
STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
}; };
static const struct normal_encoding internal_utf8_encoding = { #ifdef XML_NS
{ VTABLE1, utf8_encode, { utf8_toUtf8 }, 1 },
static const struct normal_encoding internal_utf8_encoding_ns = {
{ VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
{ {
#include "iasciitab.h" #include "iasciitab.h"
#include "utf8tab.h" #include "utf8tab.h"
} },
STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
}; };
static #endif
int latin1_encode(const ENCODING *enc, int c, char *buf)
{ static const struct normal_encoding internal_utf8_encoding = {
if (c < 0) { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 },
return 0; {
if (c <= 0xFF) { #define BT_COLON BT_NMSTRT
buf[0] = (char)c; #include "iasciitab.h"
return 1; #undef BT_COLON
} #include "utf8tab.h"
return 0; },
} STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)
};
static static
void latin1_toUtf8(const ENCODING *enc, void latin1_toUtf8(const ENCODING *enc,
...@@ -218,7 +393,7 @@ void latin1_toUtf8(const ENCODING *enc, ...@@ -218,7 +393,7 @@ void latin1_toUtf8(const ENCODING *enc,
if (c & 0x80) { if (c & 0x80) {
if (toLim - *toP < 2) if (toLim - *toP < 2)
break; break;
*(*toP)++ = ((c >> 6) | cval2); *(*toP)++ = ((c >> 6) | UTF8_cval2);
*(*toP)++ = ((c & 0x3f) | 0x80); *(*toP)++ = ((c & 0x3f) | 0x80);
(*fromP)++; (*fromP)++;
} }
...@@ -230,17 +405,71 @@ void latin1_toUtf8(const ENCODING *enc, ...@@ -230,17 +405,71 @@ void latin1_toUtf8(const ENCODING *enc,
} }
} }
static
void latin1_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
while (*fromP != fromLim && *toP != toLim)
*(*toP)++ = (unsigned char)*(*fromP)++;
}
#ifdef XML_NS
static const struct normal_encoding latin1_encoding_ns = {
{ VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 },
{
#include "asciitab.h"
#include "latin1tab.h"
},
STANDARD_VTABLE(sb_)
};
#endif
static const struct normal_encoding latin1_encoding = { static const struct normal_encoding latin1_encoding = {
{ VTABLE1, latin1_encode, { latin1_toUtf8 }, 1 }, { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 },
{ {
#define BT_COLON BT_NMSTRT
#include "asciitab.h" #include "asciitab.h"
#undef BT_COLON
#include "latin1tab.h" #include "latin1tab.h"
} },
STANDARD_VTABLE(sb_)
};
static
void ascii_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
while (*fromP != fromLim && *toP != toLim)
*(*toP)++ = *(*fromP)++;
}
#ifdef XML_NS
static const struct normal_encoding ascii_encoding_ns = {
{ VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 },
{
#include "asciitab.h"
/* BT_NONXML == 0 */
},
STANDARD_VTABLE(sb_)
}; };
#define latin1tab (latin1_encoding.type) #endif
#undef PREFIX static const struct normal_encoding ascii_encoding = {
{ VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 },
{
#define BT_COLON BT_NMSTRT
#include "asciitab.h"
#undef BT_COLON
/* BT_NONXML == 0 */
},
STANDARD_VTABLE(sb_)
};
static int unicode_byte_type(char hi, char lo) static int unicode_byte_type(char hi, char lo)
{ {
...@@ -260,28 +489,9 @@ static int unicode_byte_type(char hi, char lo) ...@@ -260,28 +489,9 @@ static int unicode_byte_type(char hi, char lo)
return BT_NONASCII; return BT_NONASCII;
} }
#define DEFINE_UTF16_ENCODE \ #define DEFINE_UTF16_TO_UTF8(E) \
static \
int PREFIX(encode)(const ENCODING *enc, int charNum, char *buf) \
{ \
if (charNum < 0) \
return 0; \
if (charNum < 0x10000) { \
SET2(buf, charNum); \
return 2; \
} \
if (charNum < 0x110000) { \
charNum -= 0x10000; \
SET2(buf, (charNum >> 10) + 0xD800); \
SET2(buf + 2, (charNum & 0x3FF) + 0xDC00); \
return 4; \
} \
return 0; \
}
#define DEFINE_UTF16_TO_UTF8 \
static \ static \
void PREFIX(toUtf8)(const ENCODING *enc, \ void E ## toUtf8(const ENCODING *enc, \
const char **fromP, const char *fromLim, \ const char **fromP, const char *fromLim, \
char **toP, const char *toLim) \ char **toP, const char *toLim) \
{ \ { \
...@@ -308,7 +518,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \ ...@@ -308,7 +518,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \
*fromP = from; \ *fromP = from; \
return; \ return; \
} \ } \
*(*toP)++ = ((lo >> 6) | (hi << 2) | cval2); \ *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \
*(*toP)++ = ((lo & 0x3f) | 0x80); \ *(*toP)++ = ((lo & 0x3f) | 0x80); \
break; \ break; \
default: \ default: \
...@@ -317,7 +527,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \ ...@@ -317,7 +527,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \
return; \ return; \
} \ } \
/* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \
*(*toP)++ = ((hi >> 4) | cval3); \ *(*toP)++ = ((hi >> 4) | UTF8_cval3); \
*(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \
*(*toP)++ = ((lo & 0x3f) | 0x80); \ *(*toP)++ = ((lo & 0x3f) | 0x80); \
break; \ break; \
...@@ -327,7 +537,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \ ...@@ -327,7 +537,7 @@ void PREFIX(toUtf8)(const ENCODING *enc, \
return; \ return; \
} \ } \
plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \
*(*toP)++ = ((plane >> 2) | cval4); \ *(*toP)++ = ((plane >> 2) | UTF8_cval4); \
*(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \
from += 2; \ from += 2; \
lo2 = GET_LO(from); \ lo2 = GET_LO(from); \
...@@ -342,196 +552,354 @@ void PREFIX(toUtf8)(const ENCODING *enc, \ ...@@ -342,196 +552,354 @@ void PREFIX(toUtf8)(const ENCODING *enc, \
*fromP = from; \ *fromP = from; \
} }
#define PREFIX(ident) little2_ ## ident #define DEFINE_UTF16_TO_UTF16(E) \
#define MINBPC 2 static \
#define BYTE_TYPE(enc, p) \ void E ## toUtf16(const ENCODING *enc, \
((p)[1] == 0 ? latin1tab[(unsigned char)*(p)] : unicode_byte_type((p)[1], (p)[0])) const char **fromP, const char *fromLim, \
#define BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1) unsigned short **toP, const unsigned short *toLim) \
#define CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c) { \
#define IS_NAME_CHAR(enc, p, n) \ /* Avoid copying first half only of surrogate */ \
UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) if (fromLim - *fromP > ((toLim - *toP) << 1) \
#define IS_NMSTRT_CHAR(enc, p, n) \ && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) \
UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) fromLim -= 2; \
for (; *fromP != fromLim && *toP != toLim; *fromP += 2) \
#include "xmltok_impl.c" *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \
}
#define SET2(ptr, ch) \ #define SET2(ptr, ch) \
(((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8))) (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8)))
#define GET_LO(ptr) ((unsigned char)(ptr)[0]) #define GET_LO(ptr) ((unsigned char)(ptr)[0])
#define GET_HI(ptr) ((unsigned char)(ptr)[1]) #define GET_HI(ptr) ((unsigned char)(ptr)[1])
DEFINE_UTF16_ENCODE DEFINE_UTF16_TO_UTF8(little2_)
DEFINE_UTF16_TO_UTF8 DEFINE_UTF16_TO_UTF16(little2_)
#undef SET2 #undef SET2
#undef GET_LO #undef GET_LO
#undef GET_HI #undef GET_HI
#undef MINBPC
#undef BYTE_TYPE
#undef BYTE_TO_ASCII
#undef CHAR_MATCHES
#undef IS_NAME_CHAR
#undef IS_NMSTRT_CHAR
#undef IS_INVALID_CHAR
static const struct encoding little2_encoding = { VTABLE, 2 };
#undef PREFIX
#define PREFIX(ident) big2_ ## ident
#define MINBPC 2
/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */
#define BYTE_TYPE(enc, p) \
((p)[0] == 0 ? latin1tab[(unsigned char)(p)[1]] : unicode_byte_type((p)[0], (p)[1]))
#define BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1)
#define CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c)
#define IS_NAME_CHAR(enc, p, n) \
UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1])
#define IS_NMSTRT_CHAR(enc, p, n) \
UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1])
#include "xmltok_impl.c"
#define SET2(ptr, ch) \ #define SET2(ptr, ch) \
(((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF))) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF)))
#define GET_LO(ptr) ((unsigned char)(ptr)[1]) #define GET_LO(ptr) ((unsigned char)(ptr)[1])
#define GET_HI(ptr) ((unsigned char)(ptr)[0]) #define GET_HI(ptr) ((unsigned char)(ptr)[0])
DEFINE_UTF16_ENCODE DEFINE_UTF16_TO_UTF8(big2_)
DEFINE_UTF16_TO_UTF8 DEFINE_UTF16_TO_UTF16(big2_)
#undef SET2 #undef SET2
#undef GET_LO #undef GET_LO
#undef GET_HI #undef GET_HI
#undef MINBPC
#undef BYTE_TYPE
#undef BYTE_TO_ASCII
#undef CHAR_MATCHES
#undef IS_NAME_CHAR
#undef IS_NMSTRT_CHAR
#undef IS_INVALID_CHAR
static const struct encoding big2_encoding = { VTABLE, 2 }; #define LITTLE2_BYTE_TYPE(enc, p) \
((p)[1] == 0 \
? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \
: unicode_byte_type((p)[1], (p)[0]))
#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1)
#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c)
#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \
UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0])
#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \
UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0])
#undef PREFIX #ifdef XML_MIN_SIZE
static static
int streqci(const char *s1, const char *s2) int little2_byteType(const ENCODING *enc, const char *p)
{ {
for (;;) { return LITTLE2_BYTE_TYPE(enc, p);
char c1 = *s1++;
char c2 = *s2++;
if ('a' <= c1 && c1 <= 'z')
c1 += 'A' - 'a';
if ('a' <= c2 && c2 <= 'z')
c2 += 'A' - 'a';
if (c1 != c2)
return 0;
if (!c1)
break;
}
return 1;
} }
static static
int initScan(const ENCODING *enc, int state, const char *ptr, const char *end, int little2_byteToAscii(const ENCODING *enc, const char *p)
const char **nextTokPtr)
{ {
const ENCODING **encPtr; return LITTLE2_BYTE_TO_ASCII(enc, p);
if (ptr == end)
return XML_TOK_NONE;
encPtr = ((const INIT_ENCODING *)enc)->encPtr;
if (ptr + 1 == end) {
switch ((unsigned char)*ptr) {
case 0xFE:
case 0xFF:
case 0x00:
case 0x3C:
return XML_TOK_PARTIAL;
}
}
else {
switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) {
case 0x003C:
*encPtr = &big2_encoding;
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
case 0xFEFF:
*nextTokPtr = ptr + 2;
*encPtr = &big2_encoding;
return XML_TOK_BOM;
case 0x3C00:
*encPtr = &little2_encoding;
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
case 0xFFFE:
*nextTokPtr = ptr + 2;
*encPtr = &little2_encoding;
return XML_TOK_BOM;
}
}
*encPtr = &utf8_encoding.enc;
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
} }
static static
int initScanProlog(const ENCODING *enc, const char *ptr, const char *end, int little2_charMatches(const ENCODING *enc, const char *p, int c)
const char **nextTokPtr)
{ {
return initScan(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr); return LITTLE2_CHAR_MATCHES(enc, p, c);
} }
static static
int initScanContent(const ENCODING *enc, const char *ptr, const char *end, int little2_isNameMin(const ENCODING *enc, const char *p)
const char **nextTokPtr)
{ {
return initScan(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr); return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p);
} }
static static
void initUpdatePosition(const ENCODING *enc, const char *ptr, int little2_isNmstrtMin(const ENCODING *enc, const char *p)
const char *end, POSITION *pos)
{ {
normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p);
} }
const ENCODING *XmlGetInternalEncoding(int e) #undef VTABLE
{ #define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16
switch (e) {
case XML_UTF8_ENCODING:
return &internal_utf8_encoding.enc;
}
return 0;
}
int XmlInitEncoding(INIT_ENCODING *p, const ENCODING **encPtr, const char *name) #else /* not XML_MIN_SIZE */
#undef PREFIX
#define PREFIX(ident) little2_ ## ident
#define MINBPC(enc) 2
/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */
#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p)
#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p)
#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c)
#define IS_NAME_CHAR(enc, p, n) 0
#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p)
#define IS_NMSTRT_CHAR(enc, p, n) (0)
#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p)
#include "xmltok_impl.c"
#undef MINBPC
#undef BYTE_TYPE
#undef BYTE_TO_ASCII
#undef CHAR_MATCHES
#undef IS_NAME_CHAR
#undef IS_NAME_CHAR_MINBPC
#undef IS_NMSTRT_CHAR
#undef IS_NMSTRT_CHAR_MINBPC
#undef IS_INVALID_CHAR
#endif /* not XML_MIN_SIZE */
#ifdef XML_NS
static const struct normal_encoding little2_encoding_ns = {
{ VTABLE, 2, 0,
#if XML_BYTE_ORDER == 12
1
#else
0
#endif
},
{
#include "asciitab.h"
#include "latin1tab.h"
},
STANDARD_VTABLE(little2_)
};
#endif
static const struct normal_encoding little2_encoding = {
{ VTABLE, 2, 0,
#if XML_BYTE_ORDER == 12
1
#else
0
#endif
},
{
#define BT_COLON BT_NMSTRT
#include "asciitab.h"
#undef BT_COLON
#include "latin1tab.h"
},
STANDARD_VTABLE(little2_)
};
#if XML_BYTE_ORDER != 21
#ifdef XML_NS
static const struct normal_encoding internal_little2_encoding_ns = {
{ VTABLE, 2, 0, 1 },
{
#include "iasciitab.h"
#include "latin1tab.h"
},
STANDARD_VTABLE(little2_)
};
#endif
static const struct normal_encoding internal_little2_encoding = {
{ VTABLE, 2, 0, 1 },
{
#define BT_COLON BT_NMSTRT
#include "iasciitab.h"
#undef BT_COLON
#include "latin1tab.h"
},
STANDARD_VTABLE(little2_)
};
#endif
#define BIG2_BYTE_TYPE(enc, p) \
((p)[0] == 0 \
? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \
: unicode_byte_type((p)[0], (p)[1]))
#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1)
#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c)
#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \
UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1])
#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \
UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1])
#ifdef XML_MIN_SIZE
static
int big2_byteType(const ENCODING *enc, const char *p)
{ {
if (name) { return BIG2_BYTE_TYPE(enc, p);
if (streqci(name, "ISO-8859-1")) { }
*encPtr = &latin1_encoding.enc;
return 1; static
} int big2_byteToAscii(const ENCODING *enc, const char *p)
if (streqci(name, "UTF-8")) { {
*encPtr = &utf8_encoding.enc; return BIG2_BYTE_TO_ASCII(enc, p);
return 1; }
}
if (!streqci(name, "UTF-16")) static
int big2_charMatches(const ENCODING *enc, const char *p, int c)
{
return BIG2_CHAR_MATCHES(enc, p, c);
}
static
int big2_isNameMin(const ENCODING *enc, const char *p)
{
return BIG2_IS_NAME_CHAR_MINBPC(enc, p);
}
static
int big2_isNmstrtMin(const ENCODING *enc, const char *p)
{
return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p);
}
#undef VTABLE
#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16
#else /* not XML_MIN_SIZE */
#undef PREFIX
#define PREFIX(ident) big2_ ## ident
#define MINBPC(enc) 2
/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */
#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p)
#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p)
#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c)
#define IS_NAME_CHAR(enc, p, n) 0
#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p)
#define IS_NMSTRT_CHAR(enc, p, n) (0)
#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p)
#include "xmltok_impl.c"
#undef MINBPC
#undef BYTE_TYPE
#undef BYTE_TO_ASCII
#undef CHAR_MATCHES
#undef IS_NAME_CHAR
#undef IS_NAME_CHAR_MINBPC
#undef IS_NMSTRT_CHAR
#undef IS_NMSTRT_CHAR_MINBPC
#undef IS_INVALID_CHAR
#endif /* not XML_MIN_SIZE */
#ifdef XML_NS
static const struct normal_encoding big2_encoding_ns = {
{ VTABLE, 2, 0,
#if XML_BYTE_ORDER == 21
1
#else
0
#endif
},
{
#include "asciitab.h"
#include "latin1tab.h"
},
STANDARD_VTABLE(big2_)
};
#endif
static const struct normal_encoding big2_encoding = {
{ VTABLE, 2, 0,
#if XML_BYTE_ORDER == 21
1
#else
0
#endif
},
{
#define BT_COLON BT_NMSTRT
#include "asciitab.h"
#undef BT_COLON
#include "latin1tab.h"
},
STANDARD_VTABLE(big2_)
};
#if XML_BYTE_ORDER != 12
#ifdef XML_NS
static const struct normal_encoding internal_big2_encoding_ns = {
{ VTABLE, 2, 0, 1 },
{
#include "iasciitab.h"
#include "latin1tab.h"
},
STANDARD_VTABLE(big2_)
};
#endif
static const struct normal_encoding internal_big2_encoding = {
{ VTABLE, 2, 0, 1 },
{
#define BT_COLON BT_NMSTRT
#include "iasciitab.h"
#undef BT_COLON
#include "latin1tab.h"
},
STANDARD_VTABLE(big2_)
};
#endif
#undef PREFIX
static
int streqci(const char *s1, const char *s2)
{
for (;;) {
char c1 = *s1++;
char c2 = *s2++;
if ('a' <= c1 && c1 <= 'z')
c1 += 'A' - 'a';
if ('a' <= c2 && c2 <= 'z')
c2 += 'A' - 'a';
if (c1 != c2)
return 0; return 0;
if (!c1)
break;
} }
p->initEnc.scanners[XML_PROLOG_STATE] = initScanProlog;
p->initEnc.scanners[XML_CONTENT_STATE] = initScanContent;
p->initEnc.updatePosition = initUpdatePosition;
p->initEnc.minBytesPerChar = 1;
p->encPtr = encPtr;
*encPtr = &(p->initEnc);
return 1; return 1;
} }
static
void initUpdatePosition(const ENCODING *enc, const char *ptr,
const char *end, POSITION *pos)
{
normal_updatePosition(&utf8_encoding.enc, ptr, end, pos);
}
static static
int toAscii(const ENCODING *enc, const char *ptr, const char *end) int toAscii(const ENCODING *enc, const char *ptr, const char *end)
{ {
char buf[1]; char buf[1];
char *p = buf; char *p = buf;
XmlConvert(enc, XML_UTF8_ENCODING, &ptr, end, &p, p + 1); XmlUtf8Convert(enc, &ptr, end, &p, p + 1);
if (p == buf) if (p == buf)
return -1; return -1;
else else
...@@ -542,10 +910,10 @@ static ...@@ -542,10 +910,10 @@ static
int isSpace(int c) int isSpace(int c)
{ {
switch (c) { switch (c) {
case ' ': case 0x20:
case '\r': case 0xD:
case '\n': case 0xA:
case '\t': case 0x9:
return 1; return 1;
} }
return 0; return 0;
...@@ -635,34 +1003,10 @@ int parsePseudoAttribute(const ENCODING *enc, ...@@ -635,34 +1003,10 @@ int parsePseudoAttribute(const ENCODING *enc,
} }
static static
const ENCODING *findEncoding(const ENCODING *enc, const char *ptr, const char *end) int doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *,
{ const char *,
#define ENCODING_MAX 128 const char *),
char buf[ENCODING_MAX]; int isGeneralTextEntity,
char *p = buf;
int i;
XmlConvert(enc, XML_UTF8_ENCODING, &ptr, end, &p, p + ENCODING_MAX - 1);
if (ptr != end)
return 0;
*p = 0;
for (i = 0; buf[i]; i++) {
if ('a' <= buf[i] && buf[i] <= 'z')
buf[i] += 'A' - 'a';
}
if (streqci(buf, "UTF-8"))
return &utf8_encoding.enc;
if (streqci(buf, "ISO-8859-1"))
return &latin1_encoding.enc;
if (streqci(buf, "UTF-16")) {
static const unsigned short n = 1;
if (enc->minBytesPerChar == 2)
return enc;
return &big2_encoding;
}
return 0;
}
int XmlParseXmlDecl(int isGeneralTextEntity,
const ENCODING *enc, const ENCODING *enc,
const char *ptr, const char *ptr,
const char *end, const char *end,
...@@ -693,9 +1037,15 @@ int XmlParseXmlDecl(int isGeneralTextEntity, ...@@ -693,9 +1037,15 @@ int XmlParseXmlDecl(int isGeneralTextEntity,
*badPtr = ptr; *badPtr = ptr;
return 0; return 0;
} }
if (!name) if (!name) {
if (isGeneralTextEntity) {
/* a TextDecl must have an EncodingDecl */
*badPtr = ptr;
return 0;
}
return 1; return 1;
} }
}
if (XmlNameMatchesAscii(enc, name, "encoding")) { if (XmlNameMatchesAscii(enc, name, "encoding")) {
int c = toAscii(enc, val, end); int c = toAscii(enc, val, end);
if (!('a' <= c && c <= 'z') && !('A' <= c && c <= 'Z')) { if (!('a' <= c && c <= 'z') && !('A' <= c && c <= 'Z')) {
...@@ -705,7 +1055,7 @@ int XmlParseXmlDecl(int isGeneralTextEntity, ...@@ -705,7 +1055,7 @@ int XmlParseXmlDecl(int isGeneralTextEntity,
if (encodingName) if (encodingName)
*encodingName = val; *encodingName = val;
if (encoding) if (encoding)
*encoding = findEncoding(enc, val, ptr - enc->minBytesPerChar); *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar);
if (!parsePseudoAttribute(enc, ptr, end, &name, &val, &ptr)) { if (!parsePseudoAttribute(enc, ptr, end, &name, &val, &ptr)) {
*badPtr = ptr; *badPtr = ptr;
return 0; return 0;
...@@ -757,3 +1107,421 @@ int checkCharRefNumber(int result) ...@@ -757,3 +1107,421 @@ int checkCharRefNumber(int result)
return result; return result;
} }
int XmlUtf8Encode(int c, char *buf)
{
enum {
/* minN is minimum legal resulting value for N byte sequence */
min2 = 0x80,
min3 = 0x800,
min4 = 0x10000
};
if (c < 0)
return 0;
if (c < min2) {
buf[0] = (c | UTF8_cval1);
return 1;
}
if (c < min3) {
buf[0] = ((c >> 6) | UTF8_cval2);
buf[1] = ((c & 0x3f) | 0x80);
return 2;
}
if (c < min4) {
buf[0] = ((c >> 12) | UTF8_cval3);
buf[1] = (((c >> 6) & 0x3f) | 0x80);
buf[2] = ((c & 0x3f) | 0x80);
return 3;
}
if (c < 0x110000) {
buf[0] = ((c >> 18) | UTF8_cval4);
buf[1] = (((c >> 12) & 0x3f) | 0x80);
buf[2] = (((c >> 6) & 0x3f) | 0x80);
buf[3] = ((c & 0x3f) | 0x80);
return 4;
}
return 0;
}
int XmlUtf16Encode(int charNum, unsigned short *buf)
{
if (charNum < 0)
return 0;
if (charNum < 0x10000) {
buf[0] = charNum;
return 1;
}
if (charNum < 0x110000) {
charNum -= 0x10000;
buf[0] = (charNum >> 10) + 0xD800;
buf[1] = (charNum & 0x3FF) + 0xDC00;
return 2;
}
return 0;
}
struct unknown_encoding {
struct normal_encoding normal;
int (*convert)(void *userData, const char *p);
void *userData;
unsigned short utf16[256];
char utf8[256][4];
};
int XmlSizeOfUnknownEncoding()
{
return sizeof(struct unknown_encoding);
}
static
int unknown_isName(const ENCODING *enc, const char *p)
{
int c = ((const struct unknown_encoding *)enc)
->convert(((const struct unknown_encoding *)enc)->userData, p);
if (c & ~0xFFFF)
return 0;
return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF);
}
static
int unknown_isNmstrt(const ENCODING *enc, const char *p)
{
int c = ((const struct unknown_encoding *)enc)
->convert(((const struct unknown_encoding *)enc)->userData, p);
if (c & ~0xFFFF)
return 0;
return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF);
}
static
int unknown_isInvalid(const ENCODING *enc, const char *p)
{
int c = ((const struct unknown_encoding *)enc)
->convert(((const struct unknown_encoding *)enc)->userData, p);
return (c & ~0xFFFF) || checkCharRefNumber(c) < 0;
}
static
void unknown_toUtf8(const ENCODING *enc,
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
char buf[XML_UTF8_ENCODE_MAX];
for (;;) {
const char *utf8;
int n;
if (*fromP == fromLim)
break;
utf8 = ((const struct unknown_encoding *)enc)->utf8[(unsigned char)**fromP];
n = *utf8++;
if (n == 0) {
int c = ((const struct unknown_encoding *)enc)
->convert(((const struct unknown_encoding *)enc)->userData, *fromP);
n = XmlUtf8Encode(c, buf);
if (n > toLim - *toP)
break;
utf8 = buf;
*fromP += ((const struct normal_encoding *)enc)->type[(unsigned char)**fromP]
- (BT_LEAD2 - 2);
}
else {
if (n > toLim - *toP)
break;
(*fromP)++;
}
do {
*(*toP)++ = *utf8++;
} while (--n != 0);
}
}
static
void unknown_toUtf16(const ENCODING *enc,
const char **fromP, const char *fromLim,
unsigned short **toP, const unsigned short *toLim)
{
while (*fromP != fromLim && *toP != toLim) {
unsigned short c
= ((const struct unknown_encoding *)enc)->utf16[(unsigned char)**fromP];
if (c == 0) {
c = (unsigned short)((const struct unknown_encoding *)enc)
->convert(((const struct unknown_encoding *)enc)->userData, *fromP);
*fromP += ((const struct normal_encoding *)enc)->type[(unsigned char)**fromP]
- (BT_LEAD2 - 2);
}
else
(*fromP)++;
*(*toP)++ = c;
}
}
ENCODING *
XmlInitUnknownEncoding(void *mem,
int *table,
int (*convert)(void *userData, const char *p),
void *userData)
{
int i;
struct unknown_encoding *e = mem;
for (i = 0; i < sizeof(struct normal_encoding); i++)
((char *)mem)[i] = ((char *)&latin1_encoding)[i];
for (i = 0; i < 128; i++)
if (latin1_encoding.type[i] != BT_OTHER
&& latin1_encoding.type[i] != BT_NONXML
&& table[i] != i)
return 0;
for (i = 0; i < 256; i++) {
int c = table[i];
if (c == -1) {
e->normal.type[i] = BT_MALFORM;
/* This shouldn't really get used. */
e->utf16[i] = 0xFFFF;
e->utf8[i][0] = 1;
e->utf8[i][1] = 0;
}
else if (c < 0) {
if (c < -4)
return 0;
e->normal.type[i] = BT_LEAD2 - (c + 2);
e->utf8[i][0] = 0;
e->utf16[i] = 0;
}
else if (c < 0x80) {
if (latin1_encoding.type[c] != BT_OTHER
&& latin1_encoding.type[c] != BT_NONXML
&& c != i)
return 0;
e->normal.type[i] = latin1_encoding.type[c];
e->utf8[i][0] = 1;
e->utf8[i][1] = (char)c;
e->utf16[i] = c == 0 ? 0xFFFF : c;
}
else if (checkCharRefNumber(c) < 0) {
e->normal.type[i] = BT_NONXML;
/* This shouldn't really get used. */
e->utf16[i] = 0xFFFF;
e->utf8[i][0] = 1;
e->utf8[i][1] = 0;
}
else {
if (c > 0xFFFF)
return 0;
if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff))
e->normal.type[i] = BT_NMSTRT;
else if (UCS2_GET_NAMING(namePages, c >> 8, c & 0xff))
e->normal.type[i] = BT_NAME;
else
e->normal.type[i] = BT_OTHER;
e->utf8[i][0] = (char)XmlUtf8Encode(c, e->utf8[i] + 1);
e->utf16[i] = c;
}
}
e->userData = userData;
e->convert = convert;
if (convert) {
e->normal.isName2 = unknown_isName;
e->normal.isName3 = unknown_isName;
e->normal.isName4 = unknown_isName;
e->normal.isNmstrt2 = unknown_isNmstrt;
e->normal.isNmstrt3 = unknown_isNmstrt;
e->normal.isNmstrt4 = unknown_isNmstrt;
e->normal.isInvalid2 = unknown_isInvalid;
e->normal.isInvalid3 = unknown_isInvalid;
e->normal.isInvalid4 = unknown_isInvalid;
}
e->normal.enc.utf8Convert = unknown_toUtf8;
e->normal.enc.utf16Convert = unknown_toUtf16;
return &(e->normal.enc);
}
/* If this enumeration is changed, getEncodingIndex and encodings
must also be changed. */
enum {
UNKNOWN_ENC = -1,
ISO_8859_1_ENC = 0,
US_ASCII_ENC,
UTF_8_ENC,
UTF_16_ENC,
UTF_16BE_ENC,
UTF_16LE_ENC,
/* must match encodingNames up to here */
NO_ENC
};
static
int getEncodingIndex(const char *name)
{
static const char *encodingNames[] = {
"ISO-8859-1",
"US-ASCII",
"UTF-8",
"UTF-16",
"UTF-16BE"
"UTF-16LE",
};
int i;
if (name == 0)
return NO_ENC;
for (i = 0; i < sizeof(encodingNames)/sizeof(encodingNames[0]); i++)
if (streqci(name, encodingNames[i]))
return i;
return UNKNOWN_ENC;
}
/* For binary compatibility, we store the index of the encoding specified
at initialization in the isUtf16 member. */
#define INIT_ENC_INDEX(enc) ((enc)->initEnc.isUtf16)
/* This is what detects the encoding.
encodingTable maps from encoding indices to encodings;
INIT_ENC_INDEX(enc) is the index of the external (protocol) specified encoding;
state is XML_CONTENT_STATE if we're parsing an external text entity,
and XML_PROLOG_STATE otherwise.
*/
static
int initScan(const ENCODING **encodingTable,
const INIT_ENCODING *enc,
int state,
const char *ptr,
const char *end,
const char **nextTokPtr)
{
const ENCODING **encPtr;
if (ptr == end)
return XML_TOK_NONE;
encPtr = enc->encPtr;
if (ptr + 1 == end) {
/* only a single byte available for auto-detection */
/* a well-formed document entity must have more than one byte */
if (state != XML_CONTENT_STATE)
return XML_TOK_PARTIAL;
/* so we're parsing an external text entity... */
/* if UTF-16 was externally specified, then we need at least 2 bytes */
switch (INIT_ENC_INDEX(enc)) {
case UTF_16_ENC:
case UTF_16LE_ENC:
case UTF_16BE_ENC:
return XML_TOK_PARTIAL;
}
switch ((unsigned char)*ptr) {
case 0xFE:
case 0xFF:
case 0xEF: /* possibly first byte of UTF-8 BOM */
if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
&& state == XML_CONTENT_STATE)
break;
/* fall through */
case 0x00:
case 0x3C:
return XML_TOK_PARTIAL;
}
}
else {
switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) {
case 0xFEFF:
if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
&& state == XML_CONTENT_STATE)
break;
*nextTokPtr = ptr + 2;
*encPtr = encodingTable[UTF_16BE_ENC];
return XML_TOK_BOM;
/* 00 3C is handled in the default case */
case 0x3C00:
if ((INIT_ENC_INDEX(enc) == UTF_16BE_ENC
|| INIT_ENC_INDEX(enc) == UTF_16_ENC)
&& state == XML_CONTENT_STATE)
break;
*encPtr = encodingTable[UTF_16LE_ENC];
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
case 0xFFFE:
if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC
&& state == XML_CONTENT_STATE)
break;
*nextTokPtr = ptr + 2;
*encPtr = encodingTable[UTF_16LE_ENC];
return XML_TOK_BOM;
case 0xEFBB:
/* Maybe a UTF-8 BOM (EF BB BF) */
/* If there's an explicitly specified (external) encoding
of ISO-8859-1 or some flavour of UTF-16
and this is an external text entity,
don't look for the BOM,
because it might be a legal data. */
if (state == XML_CONTENT_STATE) {
int e = INIT_ENC_INDEX(enc);
if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC || e == UTF_16LE_ENC || e == UTF_16_ENC)
break;
}
if (ptr + 2 == end)
return XML_TOK_PARTIAL;
if ((unsigned char)ptr[2] == 0xBF) {
*encPtr = encodingTable[UTF_8_ENC];
return XML_TOK_BOM;
}
break;
default:
if (ptr[0] == '\0') {
/* 0 isn't a legal data character. Furthermore a document entity can only
start with ASCII characters. So the only way this can fail to be big-endian
UTF-16 if it it's an external parsed general entity that's labelled as
UTF-16LE. */
if (state == XML_CONTENT_STATE && INIT_ENC_INDEX(enc) == UTF_16LE_ENC)
break;
*encPtr = encodingTable[UTF_16BE_ENC];
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
}
else if (ptr[1] == '\0') {
/* We could recover here in the case:
- parsing an external entity
- second byte is 0
- no externally specified encoding
- no encoding declaration
by assuming UTF-16LE. But we don't, because this would mean when
presented just with a single byte, we couldn't reliably determine
whether we needed further bytes. */
if (state == XML_CONTENT_STATE)
break;
*encPtr = encodingTable[UTF_16LE_ENC];
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
}
break;
}
}
*encPtr = encodingTable[INIT_ENC_INDEX(enc)];
return XmlTok(*encPtr, state, ptr, end, nextTokPtr);
}
#define NS(x) x
#define ns(x) x
#include "xmltok_ns.c"
#undef NS
#undef ns
#ifdef XML_NS
#define NS(x) x ## NS
#define ns(x) x ## _ns
#include "xmltok_ns.c"
#undef NS
#undef ns
ENCODING *
XmlInitUnknownEncodingNS(void *mem,
int *table,
int (*convert)(void *userData, const char *p),
void *userData)
{
ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData);
if (enc)
((struct normal_encoding *)enc)->type[':'] = BT_COLON;
return enc;
}
#endif /* XML_NS */
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#ifndef XmlTok_INCLUDED #ifndef XmlTok_INCLUDED
...@@ -29,6 +39,9 @@ extern "C" { ...@@ -29,6 +39,9 @@ extern "C" {
#define XMLTOKAPI /* as nothing */ #define XMLTOKAPI /* as nothing */
#endif #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 */ /* 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_NONE -4 /* The string to be scanned is empty */
#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan; #define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan;
...@@ -38,7 +51,7 @@ extern "C" { ...@@ -38,7 +51,7 @@ extern "C" {
#define XML_TOK_INVALID 0 #define XML_TOK_INVALID 0
/* The following tokens are returned by XmlContentTok; some are also /* The following tokens are returned by XmlContentTok; some are also
returned by XmlAttributeValueTok and XmlEntityTok */ returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok */
#define XML_TOK_START_TAG_WITH_ATTS 1 #define XML_TOK_START_TAG_WITH_ATTS 1
#define XML_TOK_START_TAG_NO_ATTS 2 #define XML_TOK_START_TAG_NO_ATTS 2
...@@ -47,7 +60,7 @@ extern "C" { ...@@ -47,7 +60,7 @@ extern "C" {
#define XML_TOK_END_TAG 5 #define XML_TOK_END_TAG 5
#define XML_TOK_DATA_CHARS 6 #define XML_TOK_DATA_CHARS 6
#define XML_TOK_DATA_NEWLINE 7 #define XML_TOK_DATA_NEWLINE 7
#define XML_TOK_CDATA_SECTION 8 #define XML_TOK_CDATA_SECT_OPEN 8
#define XML_TOK_ENTITY_REF 9 #define XML_TOK_ENTITY_REF 9
#define XML_TOK_CHAR_REF 10 /* numeric character reference */ #define XML_TOK_CHAR_REF 10 /* numeric character reference */
...@@ -85,25 +98,29 @@ extern "C" { ...@@ -85,25 +98,29 @@ extern "C" {
#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ #define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */
#define XML_TOK_COMMA 38 #define XML_TOK_COMMA 38
/* The following tokens is returned only by XmlAttributeValueTok */ /* The following token is returned only by XmlAttributeValueTok */
#define XML_TOK_ATTRIBUTE_VALUE_S 39 #define XML_TOK_ATTRIBUTE_VALUE_S 39
#define XML_N_STATES 2 /* 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
#define XML_N_STATES 3
#define XML_PROLOG_STATE 0 #define XML_PROLOG_STATE 0
#define XML_CONTENT_STATE 1 #define XML_CONTENT_STATE 1
#define XML_CDATA_SECTION_STATE 2
#define XML_N_LITERAL_TYPES 2 #define XML_N_LITERAL_TYPES 2
#define XML_ATTRIBUTE_VALUE_LITERAL 0 #define XML_ATTRIBUTE_VALUE_LITERAL 0
#define XML_ENTITY_VALUE_LITERAL 1 #define XML_ENTITY_VALUE_LITERAL 1
#define XML_N_INTERNAL_ENCODINGS 1 /* The size of the buffer passed to XmlUtf8Encode must be at least this. */
#define XML_UTF8_ENCODING 0 #define XML_UTF8_ENCODE_MAX 4
#if 0 /* The size of the buffer passed to XmlUtf16Encode must be at least this. */
#define XML_UTF16_ENCODING 1 #define XML_UTF16_ENCODE_MAX 2
#define XML_UCS4_ENCODING 2
#endif
#define XML_MAX_BYTES_PER_CHAR 4
typedef struct position { typedef struct position {
/* first line and first column are 0 not 1 */ /* first line and first column are 0 not 1 */
...@@ -139,21 +156,26 @@ struct encoding { ...@@ -139,21 +156,26 @@ struct encoding {
int (*getAtts)(const ENCODING *enc, const char *ptr, int (*getAtts)(const ENCODING *enc, const char *ptr,
int attsMax, ATTRIBUTE *atts); int attsMax, ATTRIBUTE *atts);
int (*charRefNumber)(const ENCODING *enc, const char *ptr); int (*charRefNumber)(const ENCODING *enc, const char *ptr);
int (*predefinedEntityName)(const ENCODING *, const char *, const char *);
void (*updatePosition)(const ENCODING *, void (*updatePosition)(const ENCODING *,
const char *ptr, const char *ptr,
const char *end, const char *end,
POSITION *); POSITION *);
int (*isPublicId)(const ENCODING *enc, const char *ptr, const char *end, int (*isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
const char **badPtr); const char **badPtr);
int (*encode)(const ENCODING *enc, void (*utf8Convert)(const ENCODING *enc,
int charNum,
char *buf);
void (*convert[XML_N_INTERNAL_ENCODINGS])(const ENCODING *enc,
const char **fromP, const char **fromP,
const char *fromLim, const char *fromLim,
char **toP, char **toP,
const char *toLim); const char *toLim);
void (*utf16Convert)(const ENCODING *enc,
const char **fromP,
const char *fromLim,
unsigned short **toP,
const unsigned short *toLim);
int minBytesPerChar; int minBytesPerChar;
char isUtf8;
char isUtf16;
}; };
/* /*
...@@ -186,6 +208,9 @@ literals, comments and processing instructions. ...@@ -186,6 +208,9 @@ literals, comments and processing instructions.
#define XmlContentTok(enc, ptr, end, nextTokPtr) \ #define XmlContentTok(enc, ptr, end, nextTokPtr) \
XmlTok(enc, XML_CONTENT_STATE, 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)
/* This is used for performing a 2nd-level tokenization on /* This is used for performing a 2nd-level tokenization on
the content of a literal that has already been returned by XmlTok. */ the content of a literal that has already been returned by XmlTok. */
...@@ -215,17 +240,20 @@ the content of a literal that has already been returned by XmlTok. */ ...@@ -215,17 +240,20 @@ the content of a literal that has already been returned by XmlTok. */
#define XmlCharRefNumber(enc, ptr) \ #define XmlCharRefNumber(enc, ptr) \
(((enc)->charRefNumber)(enc, ptr)) (((enc)->charRefNumber)(enc, ptr))
#define XmlPredefinedEntityName(enc, ptr, end) \
(((enc)->predefinedEntityName)(enc, ptr, end))
#define XmlUpdatePosition(enc, ptr, end, pos) \ #define XmlUpdatePosition(enc, ptr, end, pos) \
(((enc)->updatePosition)(enc, ptr, end, pos)) (((enc)->updatePosition)(enc, ptr, end, pos))
#define XmlIsPublicId(enc, ptr, end, badPtr) \ #define XmlIsPublicId(enc, ptr, end, badPtr) \
(((enc)->isPublicId)(enc, ptr, end, badPtr)) (((enc)->isPublicId)(enc, ptr, end, badPtr))
#define XmlEncode(enc, ch, buf) \ #define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \
(((enc)->encode)(enc, ch, buf)) (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim))
#define XmlConvert(enc, targetEnc, fromP, fromLim, toP, toLim) \ #define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \
(((enc)->convert[targetEnc])(enc, fromP, fromLim, toP, toLim)) (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim))
typedef struct { typedef struct {
ENCODING initEnc; ENCODING initEnc;
...@@ -243,8 +271,35 @@ int XMLTOKAPI XmlParseXmlDecl(int isGeneralTextEntity, ...@@ -243,8 +271,35 @@ int XMLTOKAPI XmlParseXmlDecl(int isGeneralTextEntity,
int *standalonePtr); int *standalonePtr);
int XMLTOKAPI XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); int XMLTOKAPI XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name);
const ENCODING XMLTOKAPI *XmlGetInternalEncoding(int); const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncoding();
const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncoding();
int XMLTOKAPI XmlUtf8Encode(int charNumber, char *buf);
int XMLTOKAPI XmlUtf16Encode(int charNumber, unsigned short *buf);
int XMLTOKAPI XmlSizeOfUnknownEncoding();
ENCODING XMLTOKAPI *
XmlInitUnknownEncoding(void *mem,
int *table,
int (*conv)(void *userData, const char *p),
void *userData);
int XMLTOKAPI XmlParseXmlDeclNS(int isGeneralTextEntity,
const ENCODING *enc,
const char *ptr,
const char *end,
const char **badPtr,
const char **versionPtr,
const char **encodingNamePtr,
const ENCODING **namedEncodingPtr,
int *standalonePtr);
int XMLTOKAPI XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name);
const ENCODING XMLTOKAPI *XmlGetUtf8InternalEncodingNS();
const ENCODING XMLTOKAPI *XmlGetUtf16InternalEncodingNS();
ENCODING XMLTOKAPI *
XmlInitUnknownEncodingNS(void *mem,
int *table,
int (*conv)(void *userData, const char *p),
void *userData);
#ifdef __cplusplus #ifdef __cplusplus
} }
#endif #endif
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
#ifndef IS_INVALID_CHAR #ifndef IS_INVALID_CHAR
...@@ -56,7 +66,7 @@ Contributor(s): ...@@ -56,7 +66,7 @@ Contributor(s):
#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ #define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \
case BT_NONASCII: \ case BT_NONASCII: \
if (!IS_NAME_CHAR(enc, ptr, MINBPC)) { \ if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \
*nextTokPtr = ptr; \ *nextTokPtr = ptr; \
return XML_TOK_INVALID; \ return XML_TOK_INVALID; \
} \ } \
...@@ -65,7 +75,7 @@ Contributor(s): ...@@ -65,7 +75,7 @@ Contributor(s):
case BT_DIGIT: \ case BT_DIGIT: \
case BT_NAME: \ case BT_NAME: \
case BT_MINUS: \ case BT_MINUS: \
ptr += MINBPC; \ ptr += MINBPC(enc); \
break; \ break; \
CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \
CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \
...@@ -84,13 +94,13 @@ Contributor(s): ...@@ -84,13 +94,13 @@ Contributor(s):
#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ #define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \
case BT_NONASCII: \ case BT_NONASCII: \
if (!IS_NMSTRT_CHAR(enc, ptr, MINBPC)) { \ if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \
*nextTokPtr = ptr; \ *nextTokPtr = ptr; \
return XML_TOK_INVALID; \ return XML_TOK_INVALID; \
} \ } \
case BT_NMSTRT: \ case BT_NMSTRT: \
case BT_HEX: \ case BT_HEX: \
ptr += MINBPC; \ ptr += MINBPC(enc); \
break; \ break; \
CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \
CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \
...@@ -111,26 +121,26 @@ int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -111,26 +121,26 @@ int PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
ptr += MINBPC; ptr += MINBPC(enc);
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr) INVALID_CASES(ptr, nextTokPtr)
case BT_MINUS: case BT_MINUS:
if ((ptr += MINBPC) == end) if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (CHAR_MATCHES(enc, ptr, '-')) { if (CHAR_MATCHES(enc, ptr, '-')) {
if ((ptr += MINBPC) == end) if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (!CHAR_MATCHES(enc, ptr, '>')) { if (!CHAR_MATCHES(enc, ptr, '>')) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_COMMENT; return XML_TOK_COMMENT;
} }
/* fall through */ break;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -148,13 +158,13 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -148,13 +158,13 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_MINUS: case BT_MINUS:
return PREFIX(scanComment)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_LSQB: case BT_LSQB:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_COND_SECT_OPEN; return XML_TOK_COND_SECT_OPEN;
case BT_NMSTRT: case BT_NMSTRT:
case BT_HEX: case BT_HEX:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -163,10 +173,10 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -163,10 +173,10 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_PERCNT: case BT_PERCNT:
if (ptr + MINBPC == end) if (ptr + MINBPC(enc) == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
/* don't allow <!ENTITY% foo "whatever"> */ /* don't allow <!ENTITY% foo "whatever"> */
switch (BYTE_TYPE(enc, ptr + MINBPC)) { switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) {
case BT_S: case BT_CR: case BT_LF: case BT_PERCNT: case BT_S: case BT_CR: case BT_LF: case BT_PERCNT:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
...@@ -177,7 +187,7 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -177,7 +187,7 @@ int PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_DECL_OPEN; return XML_TOK_DECL_OPEN;
case BT_NMSTRT: case BT_NMSTRT:
case BT_HEX: case BT_HEX:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -192,7 +202,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -192,7 +202,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
{ {
int upper = 0; int upper = 0;
*tokPtr = XML_TOK_PI; *tokPtr = XML_TOK_PI;
if (end - ptr != MINBPC*3) if (end - ptr != MINBPC(enc)*3)
return 1; return 1;
switch (BYTE_TO_ASCII(enc, ptr)) { switch (BYTE_TO_ASCII(enc, ptr)) {
case 'x': case 'x':
...@@ -203,7 +213,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -203,7 +213,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
default: default:
return 1; return 1;
} }
ptr += MINBPC; ptr += MINBPC(enc);
switch (BYTE_TO_ASCII(enc, ptr)) { switch (BYTE_TO_ASCII(enc, ptr)) {
case 'm': case 'm':
break; break;
...@@ -213,7 +223,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -213,7 +223,7 @@ int PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end,
default: default:
return 1; return 1;
} }
ptr += MINBPC; ptr += MINBPC(enc);
switch (BYTE_TO_ASCII(enc, ptr)) { switch (BYTE_TO_ASCII(enc, ptr)) {
case 'l': case 'l':
break; break;
...@@ -253,21 +263,21 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -253,21 +263,21 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
ptr += MINBPC; ptr += MINBPC(enc);
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr) INVALID_CASES(ptr, nextTokPtr)
case BT_QUEST: case BT_QUEST:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (CHAR_MATCHES(enc, ptr, '>')) { if (CHAR_MATCHES(enc, ptr, '>')) {
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return tok; return tok;
} }
break; break;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -277,11 +287,11 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -277,11 +287,11 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (CHAR_MATCHES(enc, ptr, '>')) { if (CHAR_MATCHES(enc, ptr, '>')) {
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return tok; return tok;
} }
/* fall through */ /* fall through */
...@@ -293,38 +303,99 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -293,38 +303,99 @@ int PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
} }
/* ptr points to character following "<![" */
static static
int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end, int PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr) const char **nextTokPtr)
{ {
int i; int i;
/* CDATA[]]> */ /* CDATA[ */
if (end - ptr < 9 * MINBPC) if (end - ptr < 6 * MINBPC(enc))
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
for (i = 0; i < 6; i++, ptr += MINBPC) { for (i = 0; i < 6; i++, ptr += MINBPC(enc)) {
if (!CHAR_MATCHES(enc, ptr, "CDATA["[i])) { if (!CHAR_MATCHES(enc, ptr, "CDATA["[i])) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
} }
end -= 2 * MINBPC; *nextTokPtr = ptr;
while (ptr != end) { return XML_TOK_CDATA_SECT_OPEN;
}
static
int PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr)
{
if (ptr == end)
return XML_TOK_NONE;
if (MINBPC(enc) > 1) {
size_t n = end - ptr;
if (n & (MINBPC(enc) - 1)) {
n &= ~(MINBPC(enc) - 1);
if (n == 0)
return XML_TOK_PARTIAL;
end = ptr + n;
}
}
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
INVALID_CASES(ptr, nextTokPtr)
case BT_RSQB: case BT_RSQB:
if (CHAR_MATCHES(enc, ptr + MINBPC, ']') ptr += MINBPC(enc);
&& CHAR_MATCHES(enc, ptr + 2 * MINBPC, '>')) { if (ptr == end)
*nextTokPtr = ptr + 3 * MINBPC; return XML_TOK_PARTIAL;
return XML_TOK_CDATA_SECTION; if (!CHAR_MATCHES(enc, ptr, ']'))
break;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
if (!CHAR_MATCHES(enc, ptr, '>')) {
ptr -= MINBPC(enc);
break;
} }
/* fall through */ *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CDATA_SECT_CLOSE;
case BT_CR:
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC(enc);
*nextTokPtr = ptr;
return XML_TOK_DATA_NEWLINE;
case BT_LF:
*nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_DATA_NEWLINE;
INVALID_CASES(ptr, nextTokPtr)
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break;
} }
while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \
if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \
*nextTokPtr = ptr; \
return XML_TOK_DATA_CHARS; \
} \
ptr += n; \
break;
LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
#undef LEAD_CASE
case BT_NONXML:
case BT_MALFORM:
case BT_TRAIL:
case BT_CR:
case BT_LF:
case BT_RSQB:
*nextTokPtr = ptr;
return XML_TOK_DATA_CHARS;
default:
ptr += MINBPC(enc);
break;
} }
return XML_TOK_PARTIAL; }
*nextTokPtr = ptr;
return XML_TOK_DATA_CHARS;
} }
/* ptr points to character following "</" */ /* ptr points to character following "</" */
...@@ -345,12 +416,12 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -345,12 +416,12 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
for (ptr += MINBPC; ptr != end; ptr += MINBPC) { for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
break; break;
case BT_GT: case BT_GT:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_END_TAG; return XML_TOK_END_TAG;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -358,8 +429,14 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -358,8 +429,14 @@ int PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end,
} }
} }
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
#ifdef XML_NS
case BT_COLON:
/* no need to check qname syntax here, since end-tag must match exactly */
ptr += MINBPC(enc);
break;
#endif
case BT_GT: case BT_GT:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_END_TAG; return XML_TOK_END_TAG;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -384,13 +461,13 @@ int PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end ...@@ -384,13 +461,13 @@ int PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
for (ptr += MINBPC; ptr != end; ptr += MINBPC) { for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT: case BT_DIGIT:
case BT_HEX: case BT_HEX:
break; break;
case BT_SEMI: case BT_SEMI:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CHAR_REF; return XML_TOK_CHAR_REF;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -409,7 +486,7 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -409,7 +486,7 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
{ {
if (ptr != end) { if (ptr != end) {
if (CHAR_MATCHES(enc, ptr, 'x')) if (CHAR_MATCHES(enc, ptr, 'x'))
return PREFIX(scanHexCharRef)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT: case BT_DIGIT:
break; break;
...@@ -417,12 +494,12 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -417,12 +494,12 @@ int PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
for (ptr += MINBPC; ptr != end; ptr += MINBPC) { for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT: case BT_DIGIT:
break; break;
case BT_SEMI: case BT_SEMI:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CHAR_REF; return XML_TOK_CHAR_REF;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -442,9 +519,9 @@ int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -442,9 +519,9 @@ int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(end, ptr, end, nextTokPtr) CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_NUM: case BT_NUM:
return PREFIX(scanCharRef)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
...@@ -453,7 +530,7 @@ int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -453,7 +530,7 @@ int PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end,
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI: case BT_SEMI:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_ENTITY_REF; return XML_TOK_ENTITY_REF;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -469,14 +546,35 @@ static ...@@ -469,14 +546,35 @@ static
int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr) const char **nextTokPtr)
{ {
#ifdef XML_NS
int hadColon = 0;
#endif
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
case BT_COLON:
if (hadColon) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
hadColon = 1;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
break;
#endif
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
for (;;) { for (;;) {
int t; int t;
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
t = BYTE_TYPE(enc, ptr); t = BYTE_TYPE(enc, ptr);
...@@ -496,9 +594,12 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -496,9 +594,12 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
case BT_EQUALS: case BT_EQUALS:
{ {
int open; int open;
#ifdef XML_NS
hadColon = 0;
#endif
for (;;) { for (;;) {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
open = BYTE_TYPE(enc, ptr); open = BYTE_TYPE(enc, ptr);
...@@ -514,7 +615,7 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -514,7 +615,7 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
} }
ptr += MINBPC; ptr += MINBPC(enc);
/* in attribute value */ /* in attribute value */
for (;;) { for (;;) {
int t; int t;
...@@ -527,7 +628,7 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -527,7 +628,7 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
INVALID_CASES(ptr, nextTokPtr) INVALID_CASES(ptr, nextTokPtr)
case BT_AMP: case BT_AMP:
{ {
int tok = PREFIX(scanRef)(enc, ptr + MINBPC, end, &ptr); int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr);
if (tok <= 0) { if (tok <= 0) {
if (tok == XML_TOK_INVALID) if (tok == XML_TOK_INVALID)
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -539,13 +640,29 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -539,13 +640,29 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) {
case BT_S:
case BT_CR:
case BT_LF:
break;
case BT_SOL:
goto sol;
case BT_GT:
goto gt;
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
/* ptr points to closing quote */ /* ptr points to closing quote */
for (;;) { for (;;) {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
...@@ -553,17 +670,19 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -553,17 +670,19 @@ int PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
continue; continue;
case BT_GT: case BT_GT:
*nextTokPtr = ptr + MINBPC; gt:
*nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_START_TAG_WITH_ATTS; return XML_TOK_START_TAG_WITH_ATTS;
case BT_SOL: case BT_SOL:
ptr += MINBPC; sol:
ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (!CHAR_MATCHES(enc, ptr, '>')) { if (!CHAR_MATCHES(enc, ptr, '>')) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; return XML_TOK_EMPTY_ELEMENT_WITH_ATTS;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -587,36 +706,60 @@ static ...@@ -587,36 +706,60 @@ static
int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
const char **nextTokPtr) const char **nextTokPtr)
{ {
#ifdef XML_NS
int hadColon;
#endif
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_EXCL: case BT_EXCL:
if ((ptr += MINBPC) == end) if ((ptr += MINBPC(enc)) == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_MINUS: case BT_MINUS:
return PREFIX(scanComment)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_LSQB: case BT_LSQB:
return PREFIX(scanCdataSection)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), end, nextTokPtr);
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
case BT_QUEST: case BT_QUEST:
return PREFIX(scanPi)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_SOL: case BT_SOL:
return PREFIX(scanEndTag)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanEndTag)(enc, ptr + MINBPC(enc), end, nextTokPtr);
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
#ifdef XML_NS
hadColon = 0;
#endif
/* we have a start-tag */ /* we have a start-tag */
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
#ifdef XML_NS
case BT_COLON:
if (hadColon) {
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
hadColon = 1;
ptr += MINBPC(enc);
if (ptr == end)
return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default:
*nextTokPtr = ptr;
return XML_TOK_INVALID;
}
break;
#endif
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
{ {
ptr += MINBPC; ptr += MINBPC(enc);
while (ptr != end) { while (ptr != end) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
...@@ -625,7 +768,7 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -625,7 +768,7 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
case BT_SOL: case BT_SOL:
goto sol; goto sol;
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
ptr += MINBPC; ptr += MINBPC(enc);
continue; continue;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -637,18 +780,18 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -637,18 +780,18 @@ int PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end,
} }
case BT_GT: case BT_GT:
gt: gt:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_START_TAG_NO_ATTS; return XML_TOK_START_TAG_NO_ATTS;
case BT_SOL: case BT_SOL:
sol: sol:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (!CHAR_MATCHES(enc, ptr, '>')) { if (!CHAR_MATCHES(enc, ptr, '>')) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_EMPTY_ELEMENT_NO_ATTS; return XML_TOK_EMPTY_ELEMENT_NO_ATTS;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -664,51 +807,49 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -664,51 +807,49 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
{ {
if (ptr == end) if (ptr == end)
return XML_TOK_NONE; return XML_TOK_NONE;
#if MINBPC > 1 if (MINBPC(enc) > 1) {
{
size_t n = end - ptr; size_t n = end - ptr;
if (n & (MINBPC - 1)) { if (n & (MINBPC(enc) - 1)) {
n &= ~(MINBPC - 1); n &= ~(MINBPC(enc) - 1);
if (n == 0) if (n == 0)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
end = ptr + n; end = ptr + n;
} }
} }
#endif
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_LT: case BT_LT:
return PREFIX(scanLt)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanLt)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_AMP: case BT_AMP:
return PREFIX(scanRef)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_CR: case BT_CR:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_TRAILING_CR; return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF) if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC; ptr += MINBPC(enc);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
case BT_LF: case BT_LF:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
case BT_RSQB: case BT_RSQB:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_TRAILING_RSQB;
if (!CHAR_MATCHES(enc, ptr, ']')) if (!CHAR_MATCHES(enc, ptr, ']'))
break; break;
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_TRAILING_RSQB;
if (!CHAR_MATCHES(enc, ptr, '>')) { if (!CHAR_MATCHES(enc, ptr, '>')) {
ptr -= MINBPC; ptr -= MINBPC(enc);
break; break;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
INVALID_CASES(ptr, nextTokPtr) INVALID_CASES(ptr, nextTokPtr)
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
while (ptr != end) { while (ptr != end) {
...@@ -724,17 +865,17 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -724,17 +865,17 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
#undef LEAD_CASE #undef LEAD_CASE
case BT_RSQB: case BT_RSQB:
if (ptr + MINBPC != end) { if (ptr + MINBPC(enc) != end) {
if (!CHAR_MATCHES(enc, ptr + MINBPC, ']')) { if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ']')) {
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
if (ptr + 2*MINBPC != end) { if (ptr + 2*MINBPC(enc) != end) {
if (!CHAR_MATCHES(enc, ptr + 2*MINBPC, '>')) { if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), '>')) {
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
*nextTokPtr = ptr + 2*MINBPC; *nextTokPtr = ptr + 2*MINBPC(enc);
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
} }
...@@ -749,7 +890,7 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -749,7 +890,7 @@ int PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -766,7 +907,7 @@ int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -766,7 +907,7 @@ int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(end, ptr, end, nextTokPtr) CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: case BT_S: case BT_LF: case BT_CR: case BT_PERCNT:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_PERCENT; return XML_TOK_PERCENT;
...@@ -778,7 +919,7 @@ int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -778,7 +919,7 @@ int PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end,
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
case BT_SEMI: case BT_SEMI:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_PARAM_ENTITY_REF; return XML_TOK_PARAM_ENTITY_REF;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -795,7 +936,7 @@ int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -795,7 +936,7 @@ int PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end,
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
CHECK_NMSTRT_CASES(end, ptr, end, nextTokPtr) CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr)
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
...@@ -826,7 +967,7 @@ int PREFIX(scanLit)(int open, const ENCODING *enc, ...@@ -826,7 +967,7 @@ int PREFIX(scanLit)(int open, const ENCODING *enc,
INVALID_CASES(ptr, nextTokPtr) INVALID_CASES(ptr, nextTokPtr)
case BT_QUOT: case BT_QUOT:
case BT_APOS: case BT_APOS:
ptr += MINBPC; ptr += MINBPC(enc);
if (t != open) if (t != open)
break; break;
if (ptr == end) if (ptr == end)
...@@ -840,7 +981,7 @@ int PREFIX(scanLit)(int open, const ENCODING *enc, ...@@ -840,7 +981,7 @@ int PREFIX(scanLit)(int open, const ENCODING *enc,
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -854,51 +995,49 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -854,51 +995,49 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
int tok; int tok;
if (ptr == end) if (ptr == end)
return XML_TOK_NONE; return XML_TOK_NONE;
#if MINBPC > 1 if (MINBPC(enc) > 1) {
{
size_t n = end - ptr; size_t n = end - ptr;
if (n & (MINBPC - 1)) { if (n & (MINBPC(enc) - 1)) {
n &= ~(MINBPC - 1); n &= ~(MINBPC(enc) - 1);
if (n == 0) if (n == 0)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
end = ptr + n; end = ptr + n;
} }
} }
#endif
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_QUOT: case BT_QUOT:
return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_APOS: case BT_APOS:
return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_LT: case BT_LT:
{ {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_EXCL: case BT_EXCL:
return PREFIX(scanDecl)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_QUEST: case BT_QUEST:
return PREFIX(scanPi)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_NMSTRT: case BT_NMSTRT:
case BT_HEX: case BT_HEX:
case BT_NONASCII: case BT_NONASCII:
case BT_LEAD2: case BT_LEAD2:
case BT_LEAD3: case BT_LEAD3:
case BT_LEAD4: case BT_LEAD4:
*nextTokPtr = ptr - MINBPC; *nextTokPtr = ptr - MINBPC(enc);
return XML_TOK_INSTANCE_START; return XML_TOK_INSTANCE_START;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
case BT_CR: case BT_CR:
if (ptr + MINBPC == end) if (ptr + MINBPC(enc) == end)
return XML_TOK_TRAILING_CR; return XML_TOK_TRAILING_CR;
/* fall through */ /* fall through */
case BT_S: case BT_LF: case BT_S: case BT_LF:
for (;;) { for (;;) {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
break; break;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
...@@ -906,7 +1045,7 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -906,7 +1045,7 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
break; break;
case BT_CR: case BT_CR:
/* don't split CR/LF pair */ /* don't split CR/LF pair */
if (ptr + MINBPC != end) if (ptr + MINBPC(enc) != end)
break; break;
/* fall through */ /* fall through */
default: default:
...@@ -917,43 +1056,43 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -917,43 +1056,43 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_PROLOG_S; return XML_TOK_PROLOG_S;
case BT_PERCNT: case BT_PERCNT:
return PREFIX(scanPercent)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr);
case BT_COMMA: case BT_COMMA:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_COMMA; return XML_TOK_COMMA;
case BT_LSQB: case BT_LSQB:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_OPEN_BRACKET; return XML_TOK_OPEN_BRACKET;
case BT_RSQB: case BT_RSQB:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (CHAR_MATCHES(enc, ptr, ']')) { if (CHAR_MATCHES(enc, ptr, ']')) {
if (ptr + MINBPC == end) if (ptr + MINBPC(enc) == end)
return XML_TOK_PARTIAL; return XML_TOK_PARTIAL;
if (CHAR_MATCHES(enc, ptr + MINBPC, '>')) { if (CHAR_MATCHES(enc, ptr + MINBPC(enc), '>')) {
*nextTokPtr = ptr + 2*MINBPC; *nextTokPtr = ptr + 2*MINBPC(enc);
return XML_TOK_COND_SECT_CLOSE; return XML_TOK_COND_SECT_CLOSE;
} }
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_CLOSE_BRACKET; return XML_TOK_CLOSE_BRACKET;
case BT_LPAR: case BT_LPAR:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_OPEN_PAREN; return XML_TOK_OPEN_PAREN;
case BT_RPAR: case BT_RPAR:
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_INVALID; return XML_TOK_PARTIAL;
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_AST: case BT_AST:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CLOSE_PAREN_ASTERISK; return XML_TOK_CLOSE_PAREN_ASTERISK;
case BT_QUEST: case BT_QUEST:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CLOSE_PAREN_QUESTION; return XML_TOK_CLOSE_PAREN_QUESTION;
case BT_PLUS: case BT_PLUS:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_CLOSE_PAREN_PLUS; return XML_TOK_CLOSE_PAREN_PLUS;
case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF: case BT_S:
case BT_GT: case BT_COMMA: case BT_VERBAR: case BT_GT: case BT_COMMA: case BT_VERBAR:
...@@ -964,13 +1103,13 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -964,13 +1103,13 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
case BT_VERBAR: case BT_VERBAR:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_OR; return XML_TOK_OR;
case BT_GT: case BT_GT:
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_DECL_CLOSE; return XML_TOK_DECL_CLOSE;
case BT_NUM: case BT_NUM:
return PREFIX(scanPoundName)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr);
#define LEAD_CASE(n) \ #define LEAD_CASE(n) \
case BT_LEAD ## n: \ case BT_LEAD ## n: \
if (end - ptr < n) \ if (end - ptr < n) \
...@@ -992,22 +1131,25 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -992,22 +1131,25 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
case BT_NMSTRT: case BT_NMSTRT:
case BT_HEX: case BT_HEX:
tok = XML_TOK_NAME; tok = XML_TOK_NAME;
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
case BT_DIGIT: case BT_DIGIT:
case BT_NAME: case BT_NAME:
case BT_MINUS: case BT_MINUS:
#ifdef XML_NS
case BT_COLON:
#endif
tok = XML_TOK_NMTOKEN; tok = XML_TOK_NMTOKEN;
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
case BT_NONASCII: case BT_NONASCII:
if (IS_NMSTRT_CHAR(enc, ptr, MINBPC)) { if (IS_NMSTRT_CHAR_MINBPC(enc, ptr)) {
ptr += MINBPC; ptr += MINBPC(enc);
tok = XML_TOK_NAME; tok = XML_TOK_NAME;
break; break;
} }
if (IS_NAME_CHAR(enc, ptr, MINBPC)) { if (IS_NAME_CHAR_MINBPC(enc, ptr)) {
ptr += MINBPC; ptr += MINBPC(enc);
tok = XML_TOK_NMTOKEN; tok = XML_TOK_NMTOKEN;
break; break;
} }
...@@ -1024,26 +1166,47 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -1024,26 +1166,47 @@ int PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
case BT_S: case BT_CR: case BT_LF: case BT_S: case BT_CR: case BT_LF:
*nextTokPtr = ptr; *nextTokPtr = ptr;
return tok; return tok;
#ifdef XML_NS
case BT_COLON:
ptr += MINBPC(enc);
switch (tok) {
case XML_TOK_NAME:
if (ptr == end)
return XML_TOK_PARTIAL;
tok = XML_TOK_PREFIXED_NAME;
switch (BYTE_TYPE(enc, ptr)) {
CHECK_NAME_CASES(enc, ptr, end, nextTokPtr)
default:
tok = XML_TOK_NMTOKEN;
break;
}
break;
case XML_TOK_PREFIXED_NAME:
tok = XML_TOK_NMTOKEN;
break;
}
break;
#endif
case BT_PLUS: case BT_PLUS:
if (tok != XML_TOK_NAME) { if (tok == XML_TOK_NMTOKEN) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_NAME_PLUS; return XML_TOK_NAME_PLUS;
case BT_AST: case BT_AST:
if (tok != XML_TOK_NAME) { if (tok == XML_TOK_NMTOKEN) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_NAME_ASTERISK; return XML_TOK_NAME_ASTERISK;
case BT_QUEST: case BT_QUEST:
if (tok != XML_TOK_NAME) { if (tok == XML_TOK_NMTOKEN) {
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_INVALID; return XML_TOK_INVALID;
} }
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_NAME_QUESTION; return XML_TOK_NAME_QUESTION;
default: default:
*nextTokPtr = ptr; *nextTokPtr = ptr;
...@@ -1069,7 +1232,7 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char * ...@@ -1069,7 +1232,7 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *
#undef LEAD_CASE #undef LEAD_CASE
case BT_AMP: case BT_AMP:
if (ptr == start) if (ptr == start)
return PREFIX(scanRef)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_LT: case BT_LT:
...@@ -1078,18 +1241,18 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char * ...@@ -1078,18 +1241,18 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *
return XML_TOK_INVALID; return XML_TOK_INVALID;
case BT_LF: case BT_LF:
if (ptr == start) { if (ptr == start) {
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_CR: case BT_CR:
if (ptr == start) { if (ptr == start) {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_TRAILING_CR; return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF) if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC; ptr += MINBPC(enc);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
} }
...@@ -1097,13 +1260,13 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char * ...@@ -1097,13 +1260,13 @@ int PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_S: case BT_S:
if (ptr == start) { if (ptr == start) {
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_ATTRIBUTE_VALUE_S; return XML_TOK_ATTRIBUTE_VALUE_S;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -1127,35 +1290,35 @@ int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end ...@@ -1127,35 +1290,35 @@ int PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end
#undef LEAD_CASE #undef LEAD_CASE
case BT_AMP: case BT_AMP:
if (ptr == start) if (ptr == start)
return PREFIX(scanRef)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_PERCNT: case BT_PERCNT:
if (ptr == start) if (ptr == start)
return PREFIX(scanPercent)(enc, ptr + MINBPC, end, nextTokPtr); return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_LF: case BT_LF:
if (ptr == start) { if (ptr == start) {
*nextTokPtr = ptr + MINBPC; *nextTokPtr = ptr + MINBPC(enc);
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
case BT_CR: case BT_CR:
if (ptr == start) { if (ptr == start) {
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr == end) if (ptr == end)
return XML_TOK_TRAILING_CR; return XML_TOK_TRAILING_CR;
if (BYTE_TYPE(enc, ptr) == BT_LF) if (BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC; ptr += MINBPC(enc);
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_NEWLINE; return XML_TOK_DATA_NEWLINE;
} }
*nextTokPtr = ptr; *nextTokPtr = ptr;
return XML_TOK_DATA_CHARS; return XML_TOK_DATA_CHARS;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
} }
...@@ -1167,9 +1330,9 @@ static ...@@ -1167,9 +1330,9 @@ static
int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
const char **badPtr) const char **badPtr)
{ {
ptr += MINBPC; ptr += MINBPC(enc);
end -= MINBPC; end -= MINBPC(enc);
for (; ptr != end; ptr += MINBPC) { for (; ptr != end; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
case BT_DIGIT: case BT_DIGIT:
case BT_HEX: case BT_HEX:
...@@ -1189,6 +1352,9 @@ int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, ...@@ -1189,6 +1352,9 @@ int PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
case BT_AST: case BT_AST:
case BT_PERCNT: case BT_PERCNT:
case BT_NUM: case BT_NUM:
#ifdef XML_NS
case BT_COLON:
#endif
break; break;
case BT_S: case BT_S:
if (CHAR_MATCHES(enc, ptr, '\t')) { if (CHAR_MATCHES(enc, ptr, '\t')) {
...@@ -1227,7 +1393,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr, ...@@ -1227,7 +1393,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
int nAtts = 0; int nAtts = 0;
int open; int open;
for (ptr += MINBPC;; ptr += MINBPC) { for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) {
switch (BYTE_TYPE(enc, ptr)) { switch (BYTE_TYPE(enc, ptr)) {
#define START_NAME \ #define START_NAME \
if (state == other) { \ if (state == other) { \
...@@ -1238,7 +1404,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr, ...@@ -1238,7 +1404,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
state = inName; \ state = inName; \
} }
#define LEAD_CASE(n) \ #define LEAD_CASE(n) \
case BT_LEAD ## n: START_NAME ptr += (n - MINBPC); break; case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break;
LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4)
#undef LEAD_CASE #undef LEAD_CASE
case BT_NONASCII: case BT_NONASCII:
...@@ -1249,38 +1415,46 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr, ...@@ -1249,38 +1415,46 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
#undef START_NAME #undef START_NAME
case BT_QUOT: case BT_QUOT:
if (state != inValue) { if (state != inValue) {
atts[nAtts].valuePtr = ptr + MINBPC; if (nAtts < attsMax)
atts[nAtts].valuePtr = ptr + MINBPC(enc);
state = inValue; state = inValue;
open = BT_QUOT; open = BT_QUOT;
} }
else if (open == BT_QUOT) { else if (open == BT_QUOT) {
state = other; state = other;
atts[nAtts++].valueEnd = ptr; if (nAtts < attsMax)
atts[nAtts].valueEnd = ptr;
nAtts++;
} }
break; break;
case BT_APOS: case BT_APOS:
if (state != inValue) { if (state != inValue) {
atts[nAtts].valuePtr = ptr + MINBPC; if (nAtts < attsMax)
atts[nAtts].valuePtr = ptr + MINBPC(enc);
state = inValue; state = inValue;
open = BT_APOS; open = BT_APOS;
} }
else if (open == BT_APOS) { else if (open == BT_APOS) {
state = other; state = other;
atts[nAtts++].valueEnd = ptr; if (nAtts < attsMax)
atts[nAtts].valueEnd = ptr;
nAtts++;
} }
break; break;
case BT_AMP: case BT_AMP:
if (nAtts < attsMax)
atts[nAtts].normalized = 0; atts[nAtts].normalized = 0;
break; break;
case BT_S: case BT_S:
if (state == inName) if (state == inName)
state = other; state = other;
else if (state == inValue else if (state == inValue
&& nAtts < attsMax
&& atts[nAtts].normalized && atts[nAtts].normalized
&& (ptr == atts[nAtts].valuePtr && (ptr == atts[nAtts].valuePtr
|| BYTE_TO_ASCII(enc, ptr) != ' ' || BYTE_TO_ASCII(enc, ptr) != ' '
|| BYTE_TO_ASCII(enc, ptr + MINBPC) == ' ' || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ' '
|| BYTE_TYPE(enc, ptr + MINBPC) == open)) || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open))
atts[nAtts].normalized = 0; atts[nAtts].normalized = 0;
break; break;
case BT_CR: case BT_LF: case BT_CR: case BT_LF:
...@@ -1288,7 +1462,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr, ...@@ -1288,7 +1462,7 @@ int PREFIX(getAtts)(const ENCODING *enc, const char *ptr,
Apart from that we could just change state on the quote. */ Apart from that we could just change state on the quote. */
if (state == inName) if (state == inName)
state = other; state = other;
else if (state == inValue) else if (state == inValue && nAtts < attsMax)
atts[nAtts].normalized = 0; atts[nAtts].normalized = 0;
break; break;
case BT_GT: case BT_GT:
...@@ -1308,9 +1482,9 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) ...@@ -1308,9 +1482,9 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
{ {
int result = 0; int result = 0;
/* skip &# */ /* skip &# */
ptr += 2*MINBPC; ptr += 2*MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'x')) { if (CHAR_MATCHES(enc, ptr, 'x')) {
for (ptr += MINBPC; !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC) { for (ptr += MINBPC(enc); !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
int c = BYTE_TO_ASCII(enc, ptr); int c = BYTE_TO_ASCII(enc, ptr);
switch (c) { switch (c) {
case '0': case '1': case '2': case '3': case '4': case '0': case '1': case '2': case '3': case '4':
...@@ -1332,7 +1506,7 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) ...@@ -1332,7 +1506,7 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
} }
} }
else { else {
for (; !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC) { for (; !CHAR_MATCHES(enc, ptr, ';'); ptr += MINBPC(enc)) {
int c = BYTE_TO_ASCII(enc, ptr); int c = BYTE_TO_ASCII(enc, ptr);
result *= 10; result *= 10;
result += (c - '0'); result += (c - '0');
...@@ -1343,6 +1517,59 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) ...@@ -1343,6 +1517,59 @@ int PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr)
return checkCharRefNumber(result); return checkCharRefNumber(result);
} }
static
int PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, const char *end)
{
switch ((end - ptr)/MINBPC(enc)) {
case 2:
if (CHAR_MATCHES(enc, ptr + MINBPC(enc), 't')) {
switch (BYTE_TO_ASCII(enc, ptr)) {
case 'l':
return '<';
case 'g':
return '>';
}
}
break;
case 3:
if (CHAR_MATCHES(enc, ptr, 'a')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'm')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'p'))
return '&';
}
}
break;
case 4:
switch (BYTE_TO_ASCII(enc, ptr)) {
case 'q':
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'u')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'o')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 't'))
return '"';
}
}
break;
case 'a':
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'p')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 'o')) {
ptr += MINBPC(enc);
if (CHAR_MATCHES(enc, ptr, 's'))
return '\'';
}
}
break;
}
}
return 0;
}
static static
int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
{ {
...@@ -1360,36 +1587,40 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) ...@@ -1360,36 +1587,40 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
break; break;
case BT_NONASCII: case BT_NONASCII:
case BT_NMSTRT: case BT_NMSTRT:
#ifdef XML_NS
case BT_COLON:
#endif
case BT_HEX: case BT_HEX:
case BT_DIGIT: case BT_DIGIT:
case BT_NAME: case BT_NAME:
case BT_MINUS: case BT_MINUS:
if (*ptr2++ != *ptr1++) if (*ptr2++ != *ptr1++)
return 0; return 0;
#if MINBPC > 1 if (MINBPC(enc) > 1) {
if (*ptr2++ != *ptr1++) if (*ptr2++ != *ptr1++)
return 0; return 0;
#if MINBPC > 2 if (MINBPC(enc) > 2) {
if (*ptr2++ != *ptr1++) if (*ptr2++ != *ptr1++)
return 0; return 0;
#if MINBPC > 3 if (MINBPC(enc) > 3) {
if (*ptr2++ != *ptr1++) if (*ptr2++ != *ptr1++)
return 0; return 0;
#endif }
#endif }
#endif }
break; break;
default: default:
#if MINBPC == 1 if (MINBPC(enc) == 1 && *ptr1 == *ptr2)
if (*ptr1 == *ptr2)
return 1; return 1;
#endif
switch (BYTE_TYPE(enc, ptr2)) { switch (BYTE_TYPE(enc, ptr2)) {
case BT_LEAD2: case BT_LEAD2:
case BT_LEAD3: case BT_LEAD3:
case BT_LEAD4: case BT_LEAD4:
case BT_NONASCII: case BT_NONASCII:
case BT_NMSTRT: case BT_NMSTRT:
#ifdef XML_NS
case BT_COLON:
#endif
case BT_HEX: case BT_HEX:
case BT_DIGIT: case BT_DIGIT:
case BT_NAME: case BT_NAME:
...@@ -1406,8 +1637,8 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) ...@@ -1406,8 +1637,8 @@ int PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
static static
int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, const char *ptr2) int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, const char *ptr2)
{ {
for (; *ptr2; ptr1 += MINBPC, ptr2++) { for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
if (!CHAR_MATCHES(end, ptr1, *ptr2)) if (!CHAR_MATCHES(enc, ptr1, *ptr2))
return 0; return 0;
} }
switch (BYTE_TYPE(enc, ptr1)) { switch (BYTE_TYPE(enc, ptr1)) {
...@@ -1416,6 +1647,9 @@ int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, const char * ...@@ -1416,6 +1647,9 @@ int PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, const char *
case BT_LEAD4: case BT_LEAD4:
case BT_NONASCII: case BT_NONASCII:
case BT_NMSTRT: case BT_NMSTRT:
#ifdef XML_NS
case BT_COLON:
#endif
case BT_HEX: case BT_HEX:
case BT_DIGIT: case BT_DIGIT:
case BT_NAME: case BT_NAME:
...@@ -1438,11 +1672,14 @@ int PREFIX(nameLength)(const ENCODING *enc, const char *ptr) ...@@ -1438,11 +1672,14 @@ int PREFIX(nameLength)(const ENCODING *enc, const char *ptr)
#undef LEAD_CASE #undef LEAD_CASE
case BT_NONASCII: case BT_NONASCII:
case BT_NMSTRT: case BT_NMSTRT:
#ifdef XML_NS
case BT_COLON:
#endif
case BT_HEX: case BT_HEX:
case BT_DIGIT: case BT_DIGIT:
case BT_NAME: case BT_NAME:
case BT_MINUS: case BT_MINUS:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
default: default:
return ptr - start; return ptr - start;
...@@ -1458,7 +1695,7 @@ const char *PREFIX(skipS)(const ENCODING *enc, const char *ptr) ...@@ -1458,7 +1695,7 @@ const char *PREFIX(skipS)(const ENCODING *enc, const char *ptr)
case BT_LF: case BT_LF:
case BT_CR: case BT_CR:
case BT_S: case BT_S:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
default: default:
return ptr; return ptr;
...@@ -1483,17 +1720,17 @@ void PREFIX(updatePosition)(const ENCODING *enc, ...@@ -1483,17 +1720,17 @@ void PREFIX(updatePosition)(const ENCODING *enc,
case BT_LF: case BT_LF:
pos->columnNumber = (unsigned)-1; pos->columnNumber = (unsigned)-1;
pos->lineNumber++; pos->lineNumber++;
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
case BT_CR: case BT_CR:
pos->lineNumber++; pos->lineNumber++;
ptr += MINBPC; ptr += MINBPC(enc);
if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF) if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF)
ptr += MINBPC; ptr += MINBPC(enc);
pos->columnNumber = (unsigned)-1; pos->columnNumber = (unsigned)-1;
break; break;
default: default:
ptr += MINBPC; ptr += MINBPC(enc);
break; break;
} }
pos->columnNumber++; pos->columnNumber++;
......
/* /*
The contents of this file are subject to the Mozilla Public License The contents of this file are subject to the Mozilla Public License
Version 1.0 (the "License"); you may not use this file except in Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/ http://www.mozilla.org/MPL/
...@@ -12,10 +12,20 @@ under the License. ...@@ -12,10 +12,20 @@ under the License.
The Original Code is expat. The Original Code is expat.
The Initial Developer of the Original Code is James Clark. The Initial Developer of the Original Code is James Clark.
Portions created by James Clark are Copyright (C) 1998 Portions created by James Clark are Copyright (C) 1998, 1999
James Clark. All Rights Reserved. James Clark. All Rights Reserved.
Contributor(s): Contributor(s):
Alternatively, the contents of this file may be used under the terms
of the GNU General Public License (the "GPL"), in which case the
provisions of the GPL are applicable instead of those above. If you
wish to allow use of your version of this file only under the terms of
the GPL and not to allow others to use your version of this file under
the MPL, indicate your decision by deleting the provisions above and
replace them with the notice and other provisions required by the
GPL. If you do not delete the provisions above, a recipient may use
your version of this file under either the MPL or the GPL.
*/ */
enum { enum {
...@@ -42,6 +52,7 @@ enum { ...@@ -42,6 +52,7 @@ enum {
BT_LSQB, BT_LSQB,
BT_S, BT_S,
BT_NMSTRT, BT_NMSTRT,
BT_COLON,
BT_HEX, BT_HEX,
BT_DIGIT, BT_DIGIT,
BT_NAME, BT_NAME,
......
const ENCODING *NS(XmlGetUtf8InternalEncoding)()
{
return &ns(internal_utf8_encoding).enc;
}
const ENCODING *NS(XmlGetUtf16InternalEncoding)()
{
#if XML_BYTE_ORDER == 12
return &ns(internal_little2_encoding).enc;
#elif XML_BYTE_ORDER == 21
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 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 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;
INIT_ENC_INDEX(p) = (char)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, "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 **encodingName,
const ENCODING **encoding,
int *standalone)
{
return doParseXmlDecl(NS(findEncoding),
isGeneralTextEntity,
enc,
ptr,
end,
badPtr,
versionPtr,
encodingName,
encoding,
standalone);
}
...@@ -33,11 +33,6 @@ PERFORMANCE OF THIS SOFTWARE. ...@@ -33,11 +33,6 @@ PERFORMANCE OF THIS SOFTWARE.
#include "xmlparse.h" #include "xmlparse.h"
#include <setjmp.h> #include <setjmp.h>
/*
** The version number should match the one in _checkversion
*/
#define VERSION "1.3"
static PyObject *ErrorObject; static PyObject *ErrorObject;
/* ----------------------------------------------------- */ /* ----------------------------------------------------- */
...@@ -51,6 +46,16 @@ typedef struct { ...@@ -51,6 +46,16 @@ typedef struct {
PyObject *EndElementHandler; PyObject *EndElementHandler;
PyObject *CharacterDataHandler; PyObject *CharacterDataHandler;
PyObject *ProcessingInstructionHandler; PyObject *ProcessingInstructionHandler;
PyObject *CommentHandler;
PyObject *StartCdataSectionHandler;
PyObject *EndCdataSectionHandler;
PyObject *DefaultHandler;
PyObject *UnparsedEntityDeclHandler;
PyObject *NotationDeclHandler;
PyObject *StartNamespaceDeclHandler;
PyObject *EndNamespaceDeclHandler;
PyObject *NotStandaloneHandler;
int attrdict;
int jmpbuf_valid; int jmpbuf_valid;
jmp_buf jmpbuf; jmp_buf jmpbuf;
} xmlparseobject; } xmlparseobject;
...@@ -59,126 +64,333 @@ staticforward PyTypeObject Xmlparsetype; ...@@ -59,126 +64,333 @@ staticforward PyTypeObject Xmlparsetype;
/* Callback routines */ /* Callback routines */
static void static void
my_StartElementHandler(userdata, name, atts) my_StartElementHandler(void *userdata, const char *name, const char **atts) {
void *userdata;
char *name;
char **atts;
{
xmlparseobject *self = (xmlparseobject *)userdata; xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args; PyObject *args;
PyObject *rv; PyObject *rv;
PyObject *attrs_obj; PyObject *attrs_obj;
int attrs_len; int attrs_len;
char **attrs_p; const char **attrs_p, **attrs_k;
if (self->StartElementHandler if (self->StartElementHandler != Py_None) {
&& self->StartElementHandler != Py_None) { if (self->attrdict) {
if( (attrs_obj = PyDict_New()) == NULL )
goto err;
for(attrs_len=0, attrs_p = atts;
*attrs_p;
attrs_p++, attrs_len++) {
if (attrs_len%2) {
rv=PyString_FromString(*attrs_p);
if (! rv) {
Py_DECREF(attrs_obj);
goto err;
}
if (PyDict_SetItemString(
attrs_obj,
(char*)*attrs_k, rv)
< 0) {
Py_DECREF(attrs_obj);
goto err;
}
Py_DECREF(rv);
}
else attrs_k=attrs_p;
}
}
else {
for(attrs_len=0, attrs_p = atts; for(attrs_len=0, attrs_p = atts;
*attrs_p; *attrs_p;
attrs_p++, attrs_len++); attrs_p++, attrs_len++);
if( (attrs_obj = PyList_New(attrs_len)) == NULL ) if( (attrs_obj = PyList_New(attrs_len)) == NULL )
return; goto err;
for(attrs_len=0, attrs_p = atts; *attrs_p; for(attrs_len=0, attrs_p = atts; *attrs_p;
attrs_p++, attrs_len++) { attrs_p++, attrs_len++) {
PyList_SetItem(attrs_obj, attrs_len, rv=PyString_FromString(*attrs_p);
PyString_FromString(*attrs_p)); if (! rv) {
Py_DECREF(attrs_obj);
goto err;
}
PyList_SET_ITEM(attrs_obj, attrs_len, rv);
}
} }
args = Py_BuildValue("(sO)", name, attrs_obj); args = Py_BuildValue("(sO)", name, attrs_obj);
Py_XDECREF(attrs_obj); Py_DECREF(attrs_obj);
if (!args) return; if (!args) goto err;
rv = PyEval_CallObject(self->StartElementHandler, args); rv = PyEval_CallObject(self->StartElementHandler, args);
Py_XDECREF(args); Py_DECREF(args);
if (rv == NULL) { if (rv == NULL) goto err;
if (self->jmpbuf_valid) Py_DECREF(rv);
longjmp(self->jmpbuf, 1); }
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in StartElementHandler()\n"); PySys_WriteStderr("Exception in StartElementHandler()\n");
PyErr_Clear(); PyErr_Clear();
}
Py_XDECREF(rv);
}
} }
static void static void
my_EndElementHandler(userdata, name) my_EndElementHandler(void *userdata, const char *name) {
void *userdata;
char *name;
{
xmlparseobject *self = (xmlparseobject *)userdata; xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args; PyObject *args;
PyObject *rv; PyObject *rv;
if (self->EndElementHandler if (self->EndElementHandler != Py_None) {
&& self->EndElementHandler != Py_None) {
args = Py_BuildValue("(s)", name); args = Py_BuildValue("(s)", name);
if (!args) return; if (!args) goto err;
rv = PyEval_CallObject(self->EndElementHandler, args); rv = PyEval_CallObject(self->EndElementHandler, args);
Py_XDECREF(args); Py_DECREF(args);
if (rv == NULL) { if (rv == NULL) goto err;
if (self->jmpbuf_valid) Py_DECREF(rv);
longjmp(self->jmpbuf, 1); }
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in EndElementHandler()\n"); PySys_WriteStderr("Exception in EndElementHandler()\n");
PyErr_Clear(); PyErr_Clear();
} }
static void
my_DefaultHandler(void *userdata, const char *data, int len) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args;
PyObject *rv;
if (self->DefaultHandler != Py_None) {
args = Py_BuildValue("(s#)", data, len);
if (!args) goto err;
rv = PyEval_CallObject(self->DefaultHandler, args);
Py_XDECREF(args);
if (rv == NULL) goto err;
Py_XDECREF(rv); Py_XDECREF(rv);
} }
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in DefaultHandler()\n");
PyErr_Clear();
} }
static void static void
my_CharacterDataHandler(userdata, data, len) my_CharacterDataHandler(void *userdata, const char *data, int len) {
void *userdata;
char *data;
int len;
{
xmlparseobject *self = (xmlparseobject *)userdata; xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args; PyObject *args;
PyObject *rv; PyObject *rv;
if (self->CharacterDataHandler if (self->CharacterDataHandler != Py_None) {
&& self->CharacterDataHandler != Py_None) {
args = Py_BuildValue("(s#)", data, len); args = Py_BuildValue("(s#)", data, len);
if (!args) return; if (!args) goto err;
rv = PyEval_CallObject(self->CharacterDataHandler, args); rv = PyEval_CallObject(self->CharacterDataHandler, args);
Py_XDECREF(args); Py_DECREF(args);
if (rv == NULL) { if (rv == NULL) goto err;
if (self->jmpbuf_valid) Py_DECREF(rv);
longjmp(self->jmpbuf, 1); }
else my_DefaultHandler(userdata, data, len);
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in CharacterDataHandler()\n"); PySys_WriteStderr("Exception in CharacterDataHandler()\n");
PyErr_Clear(); PyErr_Clear();
}
Py_XDECREF(rv);
}
} }
static void static void
my_ProcessingInstructionHandler(userdata, target, data) my_ProcessingInstructionHandler(void *userdata,
void *userdata; const char *target, const char *data) {
char *target;
char *data;
{
xmlparseobject *self = (xmlparseobject *)userdata; xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args; PyObject *args;
PyObject *rv; PyObject *rv;
if (self->ProcessingInstructionHandler if (self->ProcessingInstructionHandler != Py_None) {
&& self->ProcessingInstructionHandler != Py_None) {
args = Py_BuildValue("(ss)", target, data); args = Py_BuildValue("(ss)", target, data);
if (!args) return; if (!args) goto err;
rv = PyEval_CallObject(self->ProcessingInstructionHandler, rv = PyEval_CallObject(self->ProcessingInstructionHandler,
args); args);
Py_XDECREF(args); Py_DECREF(args);
if (rv == NULL) { if (rv == NULL) goto err;
if (self->jmpbuf_valid) Py_DECREF(rv);
longjmp(self->jmpbuf, 1); }
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in ProcessingInstructionHandler()\n"); PySys_WriteStderr("Exception in ProcessingInstructionHandler()\n");
PyErr_Clear(); PyErr_Clear();
}
static void
my_CommentHandler(void *userdata, const char *data) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args;
PyObject *rv;
if (self->CommentHandler != Py_None) {
args = Py_BuildValue("(s)", data);
if (!args) goto err;
rv = PyEval_CallObject(self->CommentHandler, args);
Py_DECREF(args);
if (rv == NULL) goto err;
Py_DECREF(rv);
} }
Py_XDECREF(rv); return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in CommentHandler()\n");
PyErr_Clear();
}
static void
my_StartCdataSectionHandler(void *userdata) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *rv;
if (self->StartCdataSectionHandler != Py_None) {
rv = PyEval_CallObject(self->StartCdataSectionHandler, NULL);
if (rv == NULL) goto err;
Py_DECREF(rv);
}
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in StartCdataSectionHandler()\n");
PyErr_Clear();
}
static void
my_EndCdataSectionHandler(void *userdata) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *rv;
if (self->EndCdataSectionHandler != Py_None) {
rv = PyEval_CallObject(self->EndCdataSectionHandler, NULL);
if (rv == NULL) goto err;
Py_DECREF(rv);
} }
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in EndCdataSectionHandler()\n");
PyErr_Clear();
} }
static void
my_UnparsedEntityDeclHandler(void * userdata,
const char *entityName,
const char *base,
const char *systemId,
const char *publicId,
const char *notationName)
{
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args, *rv=0;
if (self->UnparsedEntityDeclHandler != Py_None) {
args = Py_BuildValue("sssss",
entityName, base, systemId,
publicId, notationName);
if (args == NULL) goto err;
rv = PyEval_CallObject(self->UnparsedEntityDeclHandler,
args);
Py_DECREF(args);
if (rv == NULL) goto err;
Py_DECREF(rv);
}
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in UnparsedEntityDeclHandler()\n");
PyErr_Clear();
}
static void
my_NotationDeclHandler(void * userdata,
const char *notationName,
const char *base,
const char *systemId,
const char *publicId)
{
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args, *rv=0;
if (self->NotationDeclHandler != Py_None) {
args = Py_BuildValue("ssss",
notationName, base, systemId, publicId);
if (args == NULL) goto err;
rv = PyEval_CallObject(self->NotationDeclHandler, args);
Py_DECREF(args);
if (rv == NULL) goto err;
Py_DECREF(rv);
}
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in NotationDeclHandler()\n");
PyErr_Clear();
}
static void
my_StartNamespaceDeclHandler(void *userdata,
const char *prefix, const char *uri) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args;
PyObject *rv;
if (self->StartNamespaceDeclHandler != Py_None) {
args = Py_BuildValue("(ss)", prefix, uri);
if (!args) goto err;
rv = PyEval_CallObject(self->StartNamespaceDeclHandler, args);
Py_DECREF(args);
if (rv == NULL) goto err;
Py_DECREF(rv);
}
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in StartNamespaceDeclHandler()\n");
PyErr_Clear();
}
static void
my_EndNamespaceDeclHandler(void *userdata, const char *prefix) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *args;
PyObject *rv;
if (self->EndNamespaceDeclHandler != Py_None) {
args = Py_BuildValue("(s)", prefix);
if (!args) goto err;
rv = PyEval_CallObject(self->EndNamespaceDeclHandler, args);
Py_DECREF(args);
if (rv == NULL) goto err;
Py_DECREF(rv);
}
return;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in EndNamespaceDeclHandler()\n");
PyErr_Clear();
}
static int
my_NotStandaloneHandler(void *userdata) {
xmlparseobject *self = (xmlparseobject *)userdata;
PyObject *rv;
int irv;
if (self->NotStandaloneHandler != Py_None) {
rv = PyEval_CallObject(self->StartCdataSectionHandler, NULL);
if (rv == NULL) goto err;
irv=PyObject_IsTrue(rv);
Py_DECREF(rv);
return irv;
}
return 1;
err:
if (self->jmpbuf_valid) longjmp(self->jmpbuf, 1);
PySys_WriteStderr("Exception in NotStandaloneHandler()\n");
PyErr_Clear();
return 0;
}
/* ---------------------------------------------------------------- */ /* ---------------------------------------------------------------- */
...@@ -187,10 +399,7 @@ static char xmlparse_Parse__doc__[] = ...@@ -187,10 +399,7 @@ static char xmlparse_Parse__doc__[] =
; ;
static PyObject * static PyObject *
xmlparse_Parse(self, args) xmlparse_Parse(xmlparseobject *self, PyObject *args) {
xmlparseobject *self;
PyObject *args;
{
char *s; char *s;
int slen; int slen;
int isFinal = 0; int isFinal = 0;
...@@ -220,47 +429,72 @@ static struct PyMethodDef xmlparse_methods[] = { ...@@ -220,47 +429,72 @@ static struct PyMethodDef xmlparse_methods[] = {
static xmlparseobject * static xmlparseobject *
newxmlparseobject(encoding) newxmlparseobject(char *encoding, char *namespace_separator, int attrdict) {
char *encoding;
{
xmlparseobject *self; xmlparseobject *self;
self = PyObject_NEW(xmlparseobject, &Xmlparsetype); self = PyObject_NEW(xmlparseobject, &Xmlparsetype);
if (self == NULL) if (self == NULL)
return NULL; return NULL;
self->StartElementHandler = Py_None;
Py_INCREF(Py_None); #define INIT_HANDLER(N) self->N=Py_None; Py_INCREF(Py_None)
self->EndElementHandler = Py_None; INIT_HANDLER(StartElementHandler);
Py_INCREF(Py_None); INIT_HANDLER(EndElementHandler);
self->CharacterDataHandler = Py_None; INIT_HANDLER(CharacterDataHandler);
Py_INCREF(Py_None); INIT_HANDLER(ProcessingInstructionHandler);
self->ProcessingInstructionHandler = Py_None; INIT_HANDLER(CommentHandler);
Py_INCREF(Py_None); INIT_HANDLER(StartCdataSectionHandler);
INIT_HANDLER(EndCdataSectionHandler);
INIT_HANDLER(DefaultHandler);
INIT_HANDLER(UnparsedEntityDeclHandler);
INIT_HANDLER(NotationDeclHandler);
INIT_HANDLER(StartNamespaceDeclHandler);
INIT_HANDLER(EndNamespaceDeclHandler);
INIT_HANDLER(NotStandaloneHandler);
#undef INIT_HANDLER
self->attrdict=attrdict;
if (namespace_separator) {
if ((self->itself = XML_ParserCreateNS(encoding,
*namespace_separator))
== NULL ) {
PyErr_SetString(PyExc_RuntimeError,
"XML_ParserCreateNS failed");
Py_DECREF(self);
return NULL;
}
}
else {
if ((self->itself = XML_ParserCreate(encoding)) == NULL ) { if ((self->itself = XML_ParserCreate(encoding)) == NULL ) {
PyErr_SetString(PyExc_RuntimeError, "XML_ParserCreate failed"); PyErr_SetString(PyExc_RuntimeError,
"XML_ParserCreate failed");
Py_DECREF(self); Py_DECREF(self);
return NULL; return NULL;
} }
}
XML_SetUserData(self->itself, (void *)self); XML_SetUserData(self->itself, (void *)self);
XML_SetElementHandler(self->itself, my_StartElementHandler,
my_EndElementHandler);
XML_SetCharacterDataHandler(self->itself, my_CharacterDataHandler);
XML_SetProcessingInstructionHandler(self->itself,
my_ProcessingInstructionHandler);
return self; return self;
} }
static void static void
xmlparse_dealloc(self) xmlparse_dealloc(xmlparseobject *self) {
xmlparseobject *self; Py_DECREF(self->StartElementHandler);
{ Py_DECREF(self->EndElementHandler);
Py_XDECREF(self->StartElementHandler); Py_DECREF(self->CharacterDataHandler);
Py_XDECREF(self->EndElementHandler); Py_DECREF(self->ProcessingInstructionHandler);
Py_XDECREF(self->CharacterDataHandler); Py_DECREF(self->CommentHandler);
Py_XDECREF(self->ProcessingInstructionHandler); Py_DECREF(self->StartCdataSectionHandler);
Py_DECREF(self->EndCdataSectionHandler);
Py_DECREF(self->DefaultHandler);
Py_DECREF(self->UnparsedEntityDeclHandler);
Py_DECREF(self->NotationDeclHandler);
Py_DECREF(self->StartNamespaceDeclHandler);
Py_DECREF(self->EndNamespaceDeclHandler);
Py_DECREF(self->NotStandaloneHandler);
if (self->itself) if (self->itself)
XML_ParserFree(self->itself); XML_ParserFree(self->itself);
self->itself = NULL; self->itself = NULL;
...@@ -268,28 +502,28 @@ xmlparse_dealloc(self) ...@@ -268,28 +502,28 @@ xmlparse_dealloc(self)
} }
static PyObject * static PyObject *
xmlparse_getattr(self, name) xmlparse_getattr(xmlparseobject *self, char *name) {
xmlparseobject *self;
char *name;
{
long rv; long rv;
if (strcmp(name, "StartElementHandler") == 0) { #define GET_HANDLER(N) \
Py_INCREF(self->StartElementHandler); if (strcmp(name, #N) == 0) { \
return self->StartElementHandler; Py_INCREF(self->N); \
} return self->N; \
if (strcmp(name, "EndElementHandler") == 0) {
Py_INCREF(self->EndElementHandler);
return self->EndElementHandler;
}
if (strcmp(name, "CharacterDataHandler") == 0) {
Py_INCREF(self->CharacterDataHandler);
return self->CharacterDataHandler;
}
if (strcmp(name, "ProcessingInstructionHandler") == 0) {
Py_INCREF(self->ProcessingInstructionHandler);
return self->ProcessingInstructionHandler;
} }
GET_HANDLER(StartElementHandler);
GET_HANDLER(EndElementHandler);
GET_HANDLER(CharacterDataHandler);
GET_HANDLER(ProcessingInstructionHandler);
GET_HANDLER(CommentHandler);
GET_HANDLER(StartCdataSectionHandler);
GET_HANDLER(EndCdataSectionHandler);
GET_HANDLER(DefaultHandler);
GET_HANDLER(UnparsedEntityDeclHandler);
GET_HANDLER(NotationDeclHandler);
GET_HANDLER(StartNamespaceDeclHandler);
GET_HANDLER(EndNamespaceDeclHandler);
GET_HANDLER(NotStandaloneHandler);
#undef GET_HANDLER
if (strcmp(name, "ErrorCode") == 0) if (strcmp(name, "ErrorCode") == 0)
return Py_BuildValue("l", return Py_BuildValue("l",
...@@ -304,52 +538,100 @@ xmlparse_getattr(self, name) ...@@ -304,52 +538,100 @@ xmlparse_getattr(self, name)
return Py_BuildValue("l", return Py_BuildValue("l",
XML_GetErrorByteIndex(self->itself)); XML_GetErrorByteIndex(self->itself));
if (strcmp(name, "__members__") == 0)
return Py_BuildValue("sssssssssssssssss",
"StartElementHandler",
"EndElementHandler",
"CharacterDataHandler",
"ProcessingInstructionHandler",
"CommentHandler",
"StartCdataSectionHandler",
"EndCdataSectionHandler",
"DefaultHandler",
"UnparsedEntityDeclHandler",
"NotationDeclHandler",
"StartNamespaceDeclHandler",
"EndNamespaceDeclHandler",
"NotStandaloneHandler",
"ErrorCode", "ErrorLineNumber",
"ErrorColumnNumber", "ErrorByteIndex");
return Py_FindMethod(xmlparse_methods, (PyObject *)self, name); return Py_FindMethod(xmlparse_methods, (PyObject *)self, name);
} }
static int static int
xmlparse_setattr(self, name, v) xmlparse_setattr(xmlparseobject *self, char *name, PyObject *v) {
xmlparseobject *self;
char *name;
PyObject *v;
{
/* Set attribute 'name' to value 'v'. v==NULL means delete */ /* Set attribute 'name' to value 'v'. v==NULL means delete */
if (v==NULL) { if (v==NULL) v=Py_None;
PyErr_SetString(PyExc_RuntimeError, "Cannot delete attribute");
return -1; #define XMLSETHANDLERS(N) XML_Set ## N(self->itself, \
} my_Start ## N, my_End ## N)
if (strcmp(name, "StartElementHandler") == 0) { #define SET_HANDLER(N) Py_XDECREF(self->N); self->N = v; Py_INCREF(v);
Py_XDECREF(self->StartElementHandler);
self->StartElementHandler = v; if (strncmp(name, "Start", 5)==0) {
Py_INCREF(v); if (strcmp(name+5, "ElementHandler") == 0) {
SET_HANDLER(StartElementHandler);
XMLSETHANDLERS(ElementHandler);
return 0;
}
if (strcmp(name+5, "CDataSectionHandler") == 0) {
SET_HANDLER(StartCdataSectionHandler);
XMLSETHANDLERS(CdataSectionHandler);
return 0;
}
if (strcmp(name+5, "NamespaceDeclHandler") == 0) {
SET_HANDLER(StartNamespaceDeclHandler);
XMLSETHANDLERS(NamespaceDeclHandler);
return 0; return 0;
} }
if (strcmp(name, "EndElementHandler") == 0) { }
Py_XDECREF(self->EndElementHandler);
self->EndElementHandler = v; else if (strncmp(name, "End", 3)==0) {
Py_INCREF(v); if (strcmp(name+3, "ElementHandler") == 0) {
SET_HANDLER(EndElementHandler);
XMLSETHANDLERS(ElementHandler);
return 0; return 0;
} }
if (strcmp(name, "CharacterDataHandler") == 0) { if (strcmp(name+3, "CDataSectionHandler") == 0) {
Py_XDECREF(self->CharacterDataHandler); SET_HANDLER(EndCdataSectionHandler);
self->CharacterDataHandler = v; XMLSETHANDLERS(CdataSectionHandler);
Py_INCREF(v);
return 0; return 0;
} }
if (strcmp(name, "ProcessingInstructionHandler") == 0) { if (strcmp(name+3, "NamespaceDeclHandler") == 0) {
Py_XDECREF(self->ProcessingInstructionHandler); SET_HANDLER(EndNamespaceDeclHandler);
self->ProcessingInstructionHandler = v; XMLSETHANDLERS(NamespaceDeclHandler);
Py_INCREF(v);
return 0; return 0;
} }
}
#undef SET_HANDLER
#undef XMLSETHANDLERS
else {
#define SET_HANDLER(N) \
if (strcmp(name, #N) == 0) { \
Py_XDECREF(self->N); \
self->N = v; \
Py_INCREF(v); \
XML_Set ## N(self->itself, my_ ## N); \
return 0; \
}
SET_HANDLER(CharacterDataHandler);
SET_HANDLER(ProcessingInstructionHandler);
SET_HANDLER(CommentHandler);
SET_HANDLER(DefaultHandler);
SET_HANDLER(UnparsedEntityDeclHandler);
SET_HANDLER(NotationDeclHandler);
SET_HANDLER(NotStandaloneHandler);
}
#undef SET_HANDLER
PyErr_SetString(PyExc_AttributeError, name);
return -1; return -1;
} }
static char Xmlparsetype__doc__[] =
"XML parser"
;
static PyTypeObject Xmlparsetype = { static PyTypeObject Xmlparsetype = {
PyObject_HEAD_INIT(NULL) PyObject_HEAD_INIT(NULL)
0, /*ob_size*/ 0, /*ob_size*/
...@@ -372,7 +654,7 @@ static PyTypeObject Xmlparsetype = { ...@@ -372,7 +654,7 @@ static PyTypeObject Xmlparsetype = {
/* Space for future expansion */ /* Space for future expansion */
0L,0L,0L,0L, 0L,0L,0L,0L,
Xmlparsetype__doc__ /* Documentation string */ "XML parser"
}; };
/* End of code for xmlparser objects */ /* End of code for xmlparser objects */
...@@ -380,19 +662,24 @@ static PyTypeObject Xmlparsetype = { ...@@ -380,19 +662,24 @@ static PyTypeObject Xmlparsetype = {
static char pyexpat_ParserCreate__doc__[] = static char pyexpat_ParserCreate__doc__[] =
"([encoding]) - Return a new XML parser object" "([encoding, namespace_separator]) - Return a new XML parser object"
; ;
static PyObject * static PyObject *
pyexpat_ParserCreate(self, args) pyexpat_ParserCreate(PyObject *notused, PyObject *args, PyObject *kw) {
PyObject *self; /* Not used */ char *encoding = NULL, *namespace_separator=NULL;
PyObject *args; PyObject *attrdict=NULL;
{ static char *kwlist[] = {"encoding", "namespace_separator",
char *encoding = NULL; "attrdict", NULL};
if (!PyArg_ParseTuple(args, "|s", &encoding)) if (!PyArg_ParseTupleAndKeywords(args, kw, "|zsO", kwlist,
&encoding, &namespace_separator,
&attrdict))
return NULL; return NULL;
return (PyObject *)newxmlparseobject(encoding); return (PyObject *)newxmlparseobject(encoding, namespace_separator,
attrdict
? PyObject_IsTrue(attrdict)
: 0);
} }
static char pyexpat_ErrorString__doc__[] = static char pyexpat_ErrorString__doc__[] =
...@@ -400,10 +687,7 @@ static char pyexpat_ErrorString__doc__[] = ...@@ -400,10 +687,7 @@ static char pyexpat_ErrorString__doc__[] =
; ;
static PyObject * static PyObject *
pyexpat_ErrorString(self, args) pyexpat_ErrorString(PyObject *notused, PyObject *args) {
PyObject *self; /* Not used */
PyObject *args;
{
long code; long code;
if (!PyArg_ParseTuple(args, "l", &code)) if (!PyArg_ParseTuple(args, "l", &code))
...@@ -415,7 +699,7 @@ pyexpat_ErrorString(self, args) ...@@ -415,7 +699,7 @@ pyexpat_ErrorString(self, args)
static struct PyMethodDef pyexpat_methods[] = { static struct PyMethodDef pyexpat_methods[] = {
{"ParserCreate", (PyCFunction)pyexpat_ParserCreate, {"ParserCreate", (PyCFunction)pyexpat_ParserCreate,
METH_VARARGS, pyexpat_ParserCreate__doc__}, METH_VARARGS | METH_KEYWORDS, pyexpat_ParserCreate__doc__},
{"ErrorString", (PyCFunction)pyexpat_ErrorString, {"ErrorString", (PyCFunction)pyexpat_ErrorString,
METH_VARARGS, pyexpat_ErrorString__doc__}, METH_VARARGS, pyexpat_ErrorString__doc__},
...@@ -430,24 +714,23 @@ static char pyexpat_module_documentation[] = ...@@ -430,24 +714,23 @@ static char pyexpat_module_documentation[] =
; ;
void void
initpyexpat() initpyexpat() {
{
PyObject *m, *d; PyObject *m, *d;
char *rev="$Revision: 1.6 $";
Xmlparsetype.ob_type = &PyType_Type; Xmlparsetype.ob_type = &PyType_Type;
/* Create the module and add the functions */
m = Py_InitModule4("pyexpat", pyexpat_methods, m = Py_InitModule4("pyexpat", pyexpat_methods,
pyexpat_module_documentation, pyexpat_module_documentation,
(PyObject*)NULL,PYTHON_API_VERSION); (PyObject*)NULL,PYTHON_API_VERSION);
/* Add some symbolic constants to the module */
d = PyModule_GetDict(m); d = PyModule_GetDict(m);
ErrorObject = PyString_FromString("pyexpat.error"); ErrorObject = PyString_FromString("pyexpat.error");
PyDict_SetItemString(d, "error", ErrorObject); PyDict_SetItemString(d, "error", ErrorObject);
/* XXXX Add constants here */ PyDict_SetItemString(d,"__version__",
PyDict_SetItemString(d, "version", PyString_FromString(VERSION)); PyString_FromStringAndSize(rev+11,
strlen(rev+11)-2));
#define MYCONST(name) \ #define MYCONST(name) \
PyDict_SetItemString(d, #name, PyInt_FromLong(name)) PyDict_SetItemString(d, #name, PyInt_FromLong(name))
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment