diff options
Diffstat (limited to '3rdparty/expat/lib')
24 files changed, 2761 insertions, 668 deletions
diff --git a/3rdparty/expat/lib/Makefile.am b/3rdparty/expat/lib/Makefile.am index 05343e235d8..1958f322f31 100644 --- a/3rdparty/expat/lib/Makefile.am +++ b/3rdparty/expat/lib/Makefile.am @@ -6,7 +6,9 @@ # \___/_/\_\ .__/ \__,_|\__| # |_| XML parser # -# Copyright (c) 2017 Expat development team +# Copyright (c) 2017-2024 Sebastian Pipping <sebastian@pipping.org> +# Copyright (c) 2017 Tomasz Kłoczko <kloczek@fedoraproject.org> +# Copyright (c) 2019 David Loffredo <loffredo@steptools.com> # Licensed under the MIT license: # # Permission is hereby granted, free of charge, to any person obtaining @@ -34,9 +36,13 @@ include_HEADERS = \ expat_external.h lib_LTLIBRARIES = libexpat.la +if WITH_TESTS +noinst_LTLIBRARIES = libtestpat.la +endif libexpat_la_LDFLAGS = \ @AM_LDFLAGS@ \ + @LIBM@ \ -no-undefined \ -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@ @@ -45,6 +51,12 @@ libexpat_la_SOURCES = \ xmltok.c \ xmlrole.c +if WITH_TESTS +libtestpat_la_CPPFLAGS = -DXML_TESTING + +libtestpat_la_SOURCES = $(libexpat_la_SOURCES) +endif + doc_DATA = \ ../AUTHORS \ ../Changes @@ -63,8 +75,7 @@ EXTRA_DIST = \ iasciitab.h \ internal.h \ latin1tab.h \ - libexpat.def \ - libexpatw.def \ + libexpat.def.cmake \ nametab.h \ siphash.h \ utf8tab.h \ diff --git a/3rdparty/expat/lib/Makefile.in b/3rdparty/expat/lib/Makefile.in index 10f20d5533d..1a97e85fc41 100644 --- a/3rdparty/expat/lib/Makefile.in +++ b/3rdparty/expat/lib/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.16.2 from Makefile.am. +# Makefile.in generated by automake 1.16.5 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2020 Free Software Foundation, Inc. +# Copyright (C) 1994-2021 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -22,7 +22,9 @@ # \___/_/\_\ .__/ \__,_|\__| # |_| XML parser # -# Copyright (c) 2017 Expat development team +# Copyright (c) 2017-2024 Sebastian Pipping <sebastian@pipping.org> +# Copyright (c) 2017 Tomasz Kłoczko <kloczek@fedoraproject.org> +# Copyright (c) 2019 David Loffredo <loffredo@steptools.com> # Licensed under the MIT license: # # Permission is hereby granted, free of charge, to any person obtaining @@ -133,6 +135,8 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/libtool.m4 \ $(top_srcdir)/conftools/ax-append-compile-flags.m4 \ $(top_srcdir)/conftools/ax-append-link-flags.m4 \ $(top_srcdir)/conftools/expatcfg-compiler-supports-visibility.m4 \ + $(top_srcdir)/conftools/ax-cxx-compile-stdcxx.m4 \ + $(top_srcdir)/conftools/ax-cxx-compile-stdcxx-11.m4 \ $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) @@ -171,7 +175,7 @@ am__uninstall_files_from_dir = { \ } am__installdirs = "$(DESTDIR)$(libdir)" "$(DESTDIR)$(docdir)" \ "$(DESTDIR)$(includedir)" -LTLIBRARIES = $(lib_LTLIBRARIES) +LTLIBRARIES = $(lib_LTLIBRARIES) $(noinst_LTLIBRARIES) libexpat_la_LIBADD = am_libexpat_la_OBJECTS = xmlparse.lo xmltok.lo xmlrole.lo libexpat_la_OBJECTS = $(am_libexpat_la_OBJECTS) @@ -182,6 +186,13 @@ am__v_lt_1 = libexpat_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(libexpat_la_LDFLAGS) $(LDFLAGS) -o $@ +libtestpat_la_LIBADD = +am__libtestpat_la_SOURCES_DIST = xmlparse.c xmltok.c xmlrole.c +am__objects_1 = libtestpat_la-xmlparse.lo libtestpat_la-xmltok.lo \ + libtestpat_la-xmlrole.lo +@WITH_TESTS_TRUE@am_libtestpat_la_OBJECTS = $(am__objects_1) +libtestpat_la_OBJECTS = $(am_libtestpat_la_OBJECTS) +@WITH_TESTS_TRUE@am_libtestpat_la_rpath = AM_V_P = $(am__v_P_@AM_V@) am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) am__v_P_0 = false @@ -197,8 +208,10 @@ am__v_at_1 = DEFAULT_INCLUDES = -I.@am__isrc@ -I$(top_builddir) depcomp = $(SHELL) $(top_srcdir)/conftools/depcomp am__maybe_remake_depfiles = depfiles -am__depfiles_remade = ./$(DEPDIR)/xmlparse.Plo ./$(DEPDIR)/xmlrole.Plo \ - ./$(DEPDIR)/xmltok.Plo +am__depfiles_remade = ./$(DEPDIR)/libtestpat_la-xmlparse.Plo \ + ./$(DEPDIR)/libtestpat_la-xmlrole.Plo \ + ./$(DEPDIR)/libtestpat_la-xmltok.Plo ./$(DEPDIR)/xmlparse.Plo \ + ./$(DEPDIR)/xmlrole.Plo ./$(DEPDIR)/xmltok.Plo am__mv = mv -f COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) @@ -218,8 +231,9 @@ AM_V_CCLD = $(am__v_CCLD_@AM_V@) am__v_CCLD_ = $(am__v_CCLD_@AM_DEFAULT_V@) am__v_CCLD_0 = @echo " CCLD " $@; am__v_CCLD_1 = -SOURCES = $(libexpat_la_SOURCES) -DIST_SOURCES = $(libexpat_la_SOURCES) +SOURCES = $(libexpat_la_SOURCES) $(libtestpat_la_SOURCES) +DIST_SOURCES = $(libexpat_la_SOURCES) \ + $(am__libtestpat_la_SOURCES_DIST) am__can_run_installinfo = \ case $$AM_UPDATE_INFO_DIR in \ n|no|NO) false;; \ @@ -244,8 +258,6 @@ am__define_uniq_tagged_files = \ unique=`for i in $$list; do \ if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ done | $(am__uniquify_input)` -ETAGS = etags -CTAGS = ctags am__DIST_COMMON = $(srcdir)/Makefile.in \ $(top_srcdir)/conftools/depcomp DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) @@ -265,8 +277,10 @@ AWK = @AWK@ CC = @CC@ CCDEPMODE = @CCDEPMODE@ CFLAGS = @CFLAGS@ -CPP = @CPP@ +CMAKE_SHARED_LIBRARY_PREFIX = @CMAKE_SHARED_LIBRARY_PREFIX@ CPPFLAGS = @CPPFLAGS@ +CSCOPE = @CSCOPE@ +CTAGS = @CTAGS@ CXX = @CXX@ CXXCPP = @CXXCPP@ CXXDEPMODE = @CXXDEPMODE@ @@ -282,10 +296,20 @@ ECHO_C = @ECHO_C@ ECHO_N = @ECHO_N@ ECHO_T = @ECHO_T@ EGREP = @EGREP@ +ETAGS = @ETAGS@ EXEEXT = @EXEEXT@ +EXPAT_ATTR_INFO = @EXPAT_ATTR_INFO@ +EXPAT_CHAR_TYPE = @EXPAT_CHAR_TYPE@ +EXPAT_CONTEXT_BYTES = @EXPAT_CONTEXT_BYTES@ +EXPAT_DTD = @EXPAT_DTD@ +EXPAT_LARGE_SIZE = @EXPAT_LARGE_SIZE@ +EXPAT_MIN_SIZE = @EXPAT_MIN_SIZE@ +EXPAT_NS = @EXPAT_NS@ FGREP = @FGREP@ +FILECMD = @FILECMD@ FILEMAP = @FILEMAP@ GREP = @GREP@ +HAVE_CXX11 = @HAVE_CXX11@ INSTALL = @INSTALL@ INSTALL_DATA = @INSTALL_DATA@ INSTALL_PROGRAM = @INSTALL_PROGRAM@ @@ -295,6 +319,8 @@ LD = @LD@ LDFLAGS = @LDFLAGS@ LIBAGE = @LIBAGE@ LIBCURRENT = @LIBCURRENT@ +LIBDIR_BASENAME = @LIBDIR_BASENAME@ +LIBM = @LIBM@ LIBOBJS = @LIBOBJS@ LIBREVISION = @LIBREVISION@ LIBS = @LIBS@ @@ -303,6 +329,7 @@ LIPO = @LIPO@ LN_S = @LN_S@ LTLIBOBJS = @LTLIBOBJS@ LT_SYS_LIBRARY_PATH = @LT_SYS_LIBRARY_PATH@ +MAINT = @MAINT@ MAKEINFO = @MAKEINFO@ MANIFEST_TOOL = @MANIFEST_TOOL@ MKDIR_P = @MKDIR_P@ @@ -324,9 +351,12 @@ RANLIB = @RANLIB@ SED = @SED@ SET_MAKE = @SET_MAKE@ SHELL = @SHELL@ +SIZEOF_VOID_P = @SIZEOF_VOID_P@ +SO_MAJOR = @SO_MAJOR@ +SO_MINOR = @SO_MINOR@ +SO_PATCH = @SO_PATCH@ STRIP = @STRIP@ VERSION = @VERSION@ -_EXPAT_OUTPUT_NAME = @_EXPAT_OUTPUT_NAME@ abs_builddir = @abs_builddir@ abs_srcdir = @abs_srcdir@ abs_top_builddir = @abs_top_builddir@ @@ -387,8 +417,10 @@ include_HEADERS = \ expat_external.h lib_LTLIBRARIES = libexpat.la +@WITH_TESTS_TRUE@noinst_LTLIBRARIES = libtestpat.la libexpat_la_LDFLAGS = \ @AM_LDFLAGS@ \ + @LIBM@ \ -no-undefined \ -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@ @@ -397,6 +429,8 @@ libexpat_la_SOURCES = \ xmltok.c \ xmlrole.c +@WITH_TESTS_TRUE@libtestpat_la_CPPFLAGS = -DXML_TESTING +@WITH_TESTS_TRUE@libtestpat_la_SOURCES = $(libexpat_la_SOURCES) doc_DATA = \ ../AUTHORS \ ../Changes @@ -409,8 +443,7 @@ EXTRA_DIST = \ iasciitab.h \ internal.h \ latin1tab.h \ - libexpat.def \ - libexpatw.def \ + libexpat.def.cmake \ nametab.h \ siphash.h \ utf8tab.h \ @@ -425,7 +458,7 @@ all: all-am .SUFFIXES: .SUFFIXES: .c .lo .o .obj -$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) +$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(am__configure_deps) @for dep in $?; do \ case '$(am__configure_deps)' in \ *$$dep*) \ @@ -449,9 +482,9 @@ Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status $(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh -$(top_srcdir)/configure: $(am__configure_deps) +$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps) cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh -$(ACLOCAL_M4): $(am__aclocal_m4_deps) +$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps) cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh $(am__aclocal_m4_deps): @@ -490,15 +523,32 @@ clean-libLTLIBRARIES: rm -f $${locs}; \ } +clean-noinstLTLIBRARIES: + -test -z "$(noinst_LTLIBRARIES)" || rm -f $(noinst_LTLIBRARIES) + @list='$(noinst_LTLIBRARIES)'; \ + locs=`for p in $$list; do echo $$p; done | \ + sed 's|^[^/]*$$|.|; s|/[^/]*$$||; s|$$|/so_locations|' | \ + sort -u`; \ + test -z "$$locs" || { \ + echo rm -f $${locs}; \ + rm -f $${locs}; \ + } + libexpat.la: $(libexpat_la_OBJECTS) $(libexpat_la_DEPENDENCIES) $(EXTRA_libexpat_la_DEPENDENCIES) $(AM_V_CCLD)$(libexpat_la_LINK) -rpath $(libdir) $(libexpat_la_OBJECTS) $(libexpat_la_LIBADD) $(LIBS) +libtestpat.la: $(libtestpat_la_OBJECTS) $(libtestpat_la_DEPENDENCIES) $(EXTRA_libtestpat_la_DEPENDENCIES) + $(AM_V_CCLD)$(LINK) $(am_libtestpat_la_rpath) $(libtestpat_la_OBJECTS) $(libtestpat_la_LIBADD) $(LIBS) + mostlyclean-compile: -rm -f *.$(OBJEXT) distclean-compile: -rm -f *.tab.c +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/libtestpat_la-xmlparse.Plo@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/libtestpat_la-xmlrole.Plo@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/libtestpat_la-xmltok.Plo@am__quote@ # am--include-marker @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xmlparse.Plo@am__quote@ # am--include-marker @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xmlrole.Plo@am__quote@ # am--include-marker @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xmltok.Plo@am__quote@ # am--include-marker @@ -530,6 +580,27 @@ am--depfiles: $(am__depfiles_remade) @AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ @am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LTCOMPILE) -c -o $@ $< +libtestpat_la-xmlparse.lo: xmlparse.c +@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT libtestpat_la-xmlparse.lo -MD -MP -MF $(DEPDIR)/libtestpat_la-xmlparse.Tpo -c -o libtestpat_la-xmlparse.lo `test -f 'xmlparse.c' || echo '$(srcdir)/'`xmlparse.c +@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/libtestpat_la-xmlparse.Tpo $(DEPDIR)/libtestpat_la-xmlparse.Plo +@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='xmlparse.c' object='libtestpat_la-xmlparse.lo' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o libtestpat_la-xmlparse.lo `test -f 'xmlparse.c' || echo '$(srcdir)/'`xmlparse.c + +libtestpat_la-xmltok.lo: xmltok.c +@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT libtestpat_la-xmltok.lo -MD -MP -MF $(DEPDIR)/libtestpat_la-xmltok.Tpo -c -o libtestpat_la-xmltok.lo `test -f 'xmltok.c' || echo '$(srcdir)/'`xmltok.c +@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/libtestpat_la-xmltok.Tpo $(DEPDIR)/libtestpat_la-xmltok.Plo +@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='xmltok.c' object='libtestpat_la-xmltok.lo' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o libtestpat_la-xmltok.lo `test -f 'xmltok.c' || echo '$(srcdir)/'`xmltok.c + +libtestpat_la-xmlrole.lo: xmlrole.c +@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT libtestpat_la-xmlrole.lo -MD -MP -MF $(DEPDIR)/libtestpat_la-xmlrole.Tpo -c -o libtestpat_la-xmlrole.lo `test -f 'xmlrole.c' || echo '$(srcdir)/'`xmlrole.c +@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/libtestpat_la-xmlrole.Tpo $(DEPDIR)/libtestpat_la-xmlrole.Plo +@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='xmlrole.c' object='libtestpat_la-xmlrole.lo' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(libtestpat_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o libtestpat_la-xmlrole.lo `test -f 'xmlrole.c' || echo '$(srcdir)/'`xmlrole.c + mostlyclean-libtool: -rm -f *.lo @@ -629,7 +700,6 @@ cscopelist-am: $(am__tagged_files) distclean-tags: -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags - distdir: $(BUILT_SOURCES) $(MAKE) $(AM_MAKEFLAGS) distdir-am @@ -703,10 +773,13 @@ maintainer-clean-generic: clean: clean-am clean-am: clean-generic clean-libLTLIBRARIES clean-libtool \ - mostlyclean-am + clean-noinstLTLIBRARIES mostlyclean-am distclean: distclean-am - -rm -f ./$(DEPDIR)/xmlparse.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmlparse.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmlrole.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmltok.Plo + -rm -f ./$(DEPDIR)/xmlparse.Plo -rm -f ./$(DEPDIR)/xmlrole.Plo -rm -f ./$(DEPDIR)/xmltok.Plo -rm -f Makefile @@ -755,7 +828,10 @@ install-ps-am: installcheck-am: maintainer-clean: maintainer-clean-am - -rm -f ./$(DEPDIR)/xmlparse.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmlparse.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmlrole.Plo + -rm -f ./$(DEPDIR)/libtestpat_la-xmltok.Plo + -rm -f ./$(DEPDIR)/xmlparse.Plo -rm -f ./$(DEPDIR)/xmlrole.Plo -rm -f ./$(DEPDIR)/xmltok.Plo -rm -f Makefile @@ -780,16 +856,17 @@ uninstall-am: uninstall-docDATA uninstall-includeHEADERS \ .MAKE: install-am install-data-am install-strip .PHONY: CTAGS GTAGS TAGS all all-am am--depfiles check check-am clean \ - clean-generic clean-libLTLIBRARIES clean-libtool cscopelist-am \ - ctags ctags-am distclean distclean-compile distclean-generic \ - distclean-libtool distclean-tags distdir dvi dvi-am html \ - html-am info info-am install install-am install-data \ - install-data-am install-data-hook install-docDATA install-dvi \ - install-dvi-am install-exec install-exec-am install-html \ - install-html-am install-includeHEADERS install-info \ - install-info-am install-libLTLIBRARIES install-man install-pdf \ - install-pdf-am install-ps install-ps-am install-strip \ - installcheck installcheck-am installdirs maintainer-clean \ + clean-generic clean-libLTLIBRARIES clean-libtool \ + clean-noinstLTLIBRARIES cscopelist-am ctags ctags-am distclean \ + distclean-compile distclean-generic distclean-libtool \ + distclean-tags distdir dvi dvi-am html html-am info info-am \ + install install-am install-data install-data-am \ + install-data-hook install-docDATA install-dvi install-dvi-am \ + install-exec install-exec-am install-html install-html-am \ + install-includeHEADERS install-info install-info-am \ + install-libLTLIBRARIES install-man install-pdf install-pdf-am \ + install-ps install-ps-am install-strip installcheck \ + installcheck-am installdirs maintainer-clean \ maintainer-clean-generic mostlyclean mostlyclean-compile \ mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \ tags tags-am uninstall uninstall-am uninstall-docDATA \ diff --git a/3rdparty/expat/lib/ascii.h b/3rdparty/expat/lib/ascii.h index c3587e57332..1f594d2e54b 100644 --- a/3rdparty/expat/lib/ascii.h +++ b/3rdparty/expat/lib/ascii.h @@ -6,8 +6,11 @@ \___/_/\_\ .__/ \__,_|\__| |_| XML parser - Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 1999-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2007 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/asciitab.h b/3rdparty/expat/lib/asciitab.h index 63b1d1b4482..af766fb2478 100644 --- a/3rdparty/expat/lib/asciitab.h +++ b/3rdparty/expat/lib/asciitab.h @@ -7,7 +7,9 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/expat.h b/3rdparty/expat/lib/expat.h index cb828db155f..610e1ddc0e9 100644 --- a/3rdparty/expat/lib/expat.h +++ b/3rdparty/expat/lib/expat.h @@ -7,7 +7,18 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2005 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2025 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Cristian Rodríguez <crrodriguez@opensuse.org> + Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2022 Thijs Schreijer <thijs@thijsschreijer.nl> + Copyright (c) 2023 Hanno Böck <hanno@gentoo.org> + Copyright (c) 2023 Sony Corporation / Snild Dolkow <snild@sony.com> + Copyright (c) 2024 Taichi Haradaguchi <20001722@ymail.ne.jp> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -115,7 +126,13 @@ enum XML_Error { XML_ERROR_RESERVED_PREFIX_XMLNS, XML_ERROR_RESERVED_NAMESPACE_URI, /* Added in 2.2.1. */ - XML_ERROR_INVALID_ARGUMENT + XML_ERROR_INVALID_ARGUMENT, + /* Added in 2.3.0. */ + XML_ERROR_NO_BUFFER, + /* Added in 2.4.0. */ + XML_ERROR_AMPLIFICATION_LIMIT_BREACH, + /* Added in 2.6.4. */ + XML_ERROR_NOT_STARTED, }; enum XML_Content_Type { @@ -163,8 +180,10 @@ struct XML_cp { }; /* This is called for an element declaration. See above for - description of the model argument. It's the caller's responsibility - to free model when finished with it. + description of the model argument. It's the user code's responsibility + to free model when finished with it. See XML_FreeContentModel. + There is no need to free the model from the handler, it can be kept + around and freed at a later stage. */ typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, const XML_Char *name, @@ -226,6 +245,17 @@ XML_ParserCreate(const XML_Char *encoding); and the local part will be concatenated without any separator. It is a programming error to use the separator '\0' with namespace triplets (see XML_SetReturnNSTriplet). + If a namespace separator is chosen that can be part of a URI or + part of an XML name, splitting an expanded name back into its + 1, 2 or 3 original parts on application level in the element handler + may end up vulnerable, so these are advised against; sane choices for + a namespace separator are e.g. '\n' (line feed) and '|' (pipe). + + Note that Expat does not validate namespace URIs (beyond encoding) + against RFC 3986 today (and is not required to do so with regard to + the XML 1.0 namespaces specification) but it may start doing that + in future releases. Before that, an application using Expat must + be ready to receive namespace URIs containing non-URI characters. */ XMLPARSEAPI(XML_Parser) XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); @@ -244,7 +274,7 @@ XML_ParserCreate_MM(const XML_Char *encoding, const XML_Memory_Handling_Suite *memsuite, const XML_Char *namespaceSeparator); -/* Prepare a parser object to be re-used. This is particularly +/* Prepare a parser object to be reused. This is particularly valuable when memory allocation overhead is disproportionately high, such as when a large number of small documnents need to be parsed. All handlers are cleared from the parser, except for the @@ -306,7 +336,7 @@ typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, const XML_Char *pubid, int has_internal_subset); -/* This is called for the start of the DOCTYPE declaration when the +/* This is called for the end of the DOCTYPE declaration when the closing > is encountered, but after processing any external subset. */ @@ -513,7 +543,7 @@ typedef struct { Otherwise it must return XML_STATUS_ERROR. If info does not describe a suitable encoding, then the parser will - return an XML_UNKNOWN_ENCODING error. + return an XML_ERROR_UNKNOWN_ENCODING error. */ typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, const XML_Char *name, @@ -926,7 +956,7 @@ XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); XMLPARSEAPI(int) XML_GetCurrentByteCount(XML_Parser parser); -/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets +/* If XML_CONTEXT_BYTES is >=1, returns the input buffer, sets the integer pointed to by offset to the offset within this buffer of the current parse position, and sets the integer pointed to by size to the size of this buffer (the number of input bytes). Otherwise @@ -997,7 +1027,12 @@ enum XML_FeatureEnum { XML_FEATURE_SIZEOF_XML_LCHAR, XML_FEATURE_NS, XML_FEATURE_LARGE_SIZE, - XML_FEATURE_ATTR_INFO + XML_FEATURE_ATTR_INFO, + /* Added in Expat 2.4.0. */ + XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, + XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT, + /* Added in Expat 2.6.0. */ + XML_FEATURE_GE /* Additional features must be added to the end of this enum. */ }; @@ -1010,12 +1045,30 @@ typedef struct { XMLPARSEAPI(const XML_Feature *) XML_GetFeatureList(void); +#if defined(XML_DTD) || (defined(XML_GE) && XML_GE == 1) +/* Added in Expat 2.4.0 for XML_DTD defined and + * added in Expat 2.6.0 for XML_GE == 1. */ +XMLPARSEAPI(XML_Bool) +XML_SetBillionLaughsAttackProtectionMaximumAmplification( + XML_Parser parser, float maximumAmplificationFactor); + +/* Added in Expat 2.4.0 for XML_DTD defined and + * added in Expat 2.6.0 for XML_GE == 1. */ +XMLPARSEAPI(XML_Bool) +XML_SetBillionLaughsAttackProtectionActivationThreshold( + XML_Parser parser, unsigned long long activationThresholdBytes); +#endif + +/* Added in Expat 2.6.0. */ +XMLPARSEAPI(XML_Bool) +XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled); + /* Expat follows the semantic versioning convention. - See http://semver.org. + See https://semver.org */ #define XML_MAJOR_VERSION 2 -#define XML_MINOR_VERSION 2 -#define XML_MICRO_VERSION 10 +#define XML_MINOR_VERSION 7 +#define XML_MICRO_VERSION 1 #ifdef __cplusplus } diff --git a/3rdparty/expat/lib/expat_config.h b/3rdparty/expat/lib/expat_config.h new file mode 100644 index 00000000000..2272814cf03 --- /dev/null +++ b/3rdparty/expat/lib/expat_config.h @@ -0,0 +1,6 @@ +/* expat_config.h. Dummy file to satisfy build process. */ + +#ifndef EXPAT_CONFIG_H +#define EXPAT_CONFIG_H 1 + +#endif // ndef EXPAT_CONFIG_H diff --git a/3rdparty/expat/lib/expat_external.h b/3rdparty/expat/lib/expat_external.h index b3b6e74d9d2..8829f770910 100644 --- a/3rdparty/expat/lib/expat_external.h +++ b/3rdparty/expat/lib/expat_external.h @@ -7,7 +7,14 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2004 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016 Cristian Rodríguez <crrodriguez@opensuse.org> + Copyright (c) 2016-2019 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2018 Yury Gribov <tetra2005@gmail.com> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/iasciitab.h b/3rdparty/expat/lib/iasciitab.h index ea97cfcf678..5d8646f2a31 100644 --- a/3rdparty/expat/lib/iasciitab.h +++ b/3rdparty/expat/lib/iasciitab.h @@ -7,7 +7,9 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/internal.h b/3rdparty/expat/lib/internal.h index 60913dab762..6bde6ae6b31 100644 --- a/3rdparty/expat/lib/internal.h +++ b/3rdparty/expat/lib/internal.h @@ -25,8 +25,14 @@ \___/_/\_\ .__/ \__,_|\__| |_| XML parser - Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2003 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2016-2025 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2018 Yury Gribov <tetra2005@gmail.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2023-2024 Sony Corporation / Snild Dolkow <snild@sony.com> + Copyright (c) 2024 Taichi Haradaguchi <20001722@ymail.ne.jp> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -101,22 +107,72 @@ # endif #endif +#include <limits.h> // ULONG_MAX + +#if defined(_WIN32) \ + && (! defined(__USE_MINGW_ANSI_STDIO) \ + || (1 - __USE_MINGW_ANSI_STDIO - 1 == 0)) +# define EXPAT_FMT_ULL(midpart) "%" midpart "I64u" +# if defined(_WIN64) // Note: modifiers "td" and "zu" do not work for MinGW +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "I64d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "I64u" +# else +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u" +# endif +#else +# define EXPAT_FMT_ULL(midpart) "%" midpart "llu" +# if ! defined(ULONG_MAX) +# error Compiler did not define ULONG_MAX for us +# elif ULONG_MAX == 18446744073709551615u // 2^64-1 +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "ld" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "lu" +# elif defined(EMSCRIPTEN) // 32bit mode Emscripten +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "ld" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "zu" +# else +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u" +# endif +#endif + #ifndef UNUSED_P # define UNUSED_P(p) (void)p #endif +/* NOTE BEGIN If you ever patch these defaults to greater values + for non-attack XML payload in your environment, + please file a bug report with libexpat. Thank you! +*/ +#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT \ + 100.0f +#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT \ + 8388608 // 8 MiB, 2^23 +/* NOTE END */ + +#include "expat.h" // so we can use type XML_Parser below + #ifdef __cplusplus extern "C" { #endif -#ifdef XML_ENABLE_VISIBILITY -# if XML_ENABLE_VISIBILITY -__attribute__((visibility("default"))) -# endif +void _INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef); + +#if defined(XML_GE) && XML_GE == 1 +unsigned long long testingAccountingGetCountBytesDirect(XML_Parser parser); +unsigned long long testingAccountingGetCountBytesIndirect(XML_Parser parser); +const char *unsignedCharToPrintable(unsigned char c); +#endif + +extern +#if ! defined(XML_TESTING) + const +#endif + XML_Bool g_reparseDeferralEnabledDefault; // written ONLY in runtests.c +#if defined(XML_TESTING) +extern unsigned int g_bytesScanned; // used for testing only #endif -void -_INTERNAL_trim_to_complete_utf8_characters(const char *from, - const char **fromLimRef); #ifdef __cplusplus } diff --git a/3rdparty/expat/lib/latin1tab.h b/3rdparty/expat/lib/latin1tab.h index 6f916041355..b681d278af6 100644 --- a/3rdparty/expat/lib/latin1tab.h +++ b/3rdparty/expat/lib/latin1tab.h @@ -7,7 +7,9 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/libexpat.def b/3rdparty/expat/lib/libexpat.def.cmake index 16faf5955e7..10ee9cd6f99 100644 --- a/3rdparty/expat/lib/libexpat.def +++ b/3rdparty/expat/lib/libexpat.def.cmake @@ -1,6 +1,5 @@ ; DEF file for MS VC++ -LIBRARY EXPORTS XML_DefaultCurrent @1 XML_ErrorString @2 @@ -72,7 +71,11 @@ EXPORTS XML_ResumeParser @64 XML_GetParsingStatus @65 ; added with version 2.1.1 -; XML_GetAttributeInfo @66 +@_EXPAT_COMMENT_ATTR_INFO@ XML_GetAttributeInfo @66 XML_SetHashSalt @67 -; added with version 2.2.5 - _INTERNAL_trim_to_complete_utf8_characters @68 +; internal @68 removed with version 2.3.1 +; added with version 2.4.0 +@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetBillionLaughsAttackProtectionActivationThreshold @69 +@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetBillionLaughsAttackProtectionMaximumAmplification @70 +; added with version 2.6.0 + XML_SetReparseDeferralEnabled @71 diff --git a/3rdparty/expat/lib/libexpatw.def b/3rdparty/expat/lib/libexpatw.def deleted file mode 100644 index 16faf5955e7..00000000000 --- a/3rdparty/expat/lib/libexpatw.def +++ /dev/null @@ -1,78 +0,0 @@ -; DEF file for MS VC++ - -LIBRARY -EXPORTS - XML_DefaultCurrent @1 - XML_ErrorString @2 - XML_ExpatVersion @3 - XML_ExpatVersionInfo @4 - XML_ExternalEntityParserCreate @5 - XML_GetBase @6 - XML_GetBuffer @7 - XML_GetCurrentByteCount @8 - XML_GetCurrentByteIndex @9 - XML_GetCurrentColumnNumber @10 - XML_GetCurrentLineNumber @11 - XML_GetErrorCode @12 - XML_GetIdAttributeIndex @13 - XML_GetInputContext @14 - XML_GetSpecifiedAttributeCount @15 - XML_Parse @16 - XML_ParseBuffer @17 - XML_ParserCreate @18 - XML_ParserCreateNS @19 - XML_ParserCreate_MM @20 - XML_ParserFree @21 - XML_SetAttlistDeclHandler @22 - XML_SetBase @23 - XML_SetCdataSectionHandler @24 - XML_SetCharacterDataHandler @25 - XML_SetCommentHandler @26 - XML_SetDefaultHandler @27 - XML_SetDefaultHandlerExpand @28 - XML_SetDoctypeDeclHandler @29 - XML_SetElementDeclHandler @30 - XML_SetElementHandler @31 - XML_SetEncoding @32 - XML_SetEndCdataSectionHandler @33 - XML_SetEndDoctypeDeclHandler @34 - XML_SetEndElementHandler @35 - XML_SetEndNamespaceDeclHandler @36 - XML_SetEntityDeclHandler @37 - XML_SetExternalEntityRefHandler @38 - XML_SetExternalEntityRefHandlerArg @39 - XML_SetNamespaceDeclHandler @40 - XML_SetNotStandaloneHandler @41 - XML_SetNotationDeclHandler @42 - XML_SetParamEntityParsing @43 - XML_SetProcessingInstructionHandler @44 - XML_SetReturnNSTriplet @45 - XML_SetStartCdataSectionHandler @46 - XML_SetStartDoctypeDeclHandler @47 - XML_SetStartElementHandler @48 - XML_SetStartNamespaceDeclHandler @49 - XML_SetUnknownEncodingHandler @50 - XML_SetUnparsedEntityDeclHandler @51 - XML_SetUserData @52 - XML_SetXmlDeclHandler @53 - XML_UseParserAsHandlerArg @54 -; added with version 1.95.3 - XML_ParserReset @55 - XML_SetSkippedEntityHandler @56 -; added with version 1.95.5 - XML_GetFeatureList @57 - XML_UseForeignDTD @58 -; added with version 1.95.6 - XML_FreeContentModel @59 - XML_MemMalloc @60 - XML_MemRealloc @61 - XML_MemFree @62 -; added with version 1.95.8 - XML_StopParser @63 - XML_ResumeParser @64 - XML_GetParsingStatus @65 -; added with version 2.1.1 -; XML_GetAttributeInfo @66 - XML_SetHashSalt @67 -; added with version 2.2.5 - _INTERNAL_trim_to_complete_utf8_characters @68 diff --git a/3rdparty/expat/lib/nametab.h b/3rdparty/expat/lib/nametab.h index 3681df348ee..63485446b96 100644 --- a/3rdparty/expat/lib/nametab.h +++ b/3rdparty/expat/lib/nametab.h @@ -6,8 +6,8 @@ \___/_/\_\ .__/ \__,_|\__| |_| XML parser - Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/siphash.h b/3rdparty/expat/lib/siphash.h index bfee65a332f..04f6f74585b 100644 --- a/3rdparty/expat/lib/siphash.h +++ b/3rdparty/expat/lib/siphash.h @@ -11,6 +11,9 @@ * -------------------------------------------------------------------------- * HISTORY: * + * 2020-10-03 (Sebastian Pipping) + * - Drop support for Visual Studio 9.0/2008 and earlier + * * 2019-08-03 (Sebastian Pipping) * - Mark part of sip24_valid as to be excluded from clang-format * - Re-format code using clang-format 9 @@ -96,22 +99,14 @@ #define SIPHASH_H #include <stddef.h> /* size_t */ - -#if defined(_WIN32) && defined(_MSC_VER) && (_MSC_VER < 1600) -/* For vs2003/7.1 up to vs2008/9.0; _MSC_VER 1600 is vs2010/10.0 */ -typedef unsigned __int8 uint8_t; -typedef unsigned __int32 uint32_t; -typedef unsigned __int64 uint64_t; -#else -# include <stdint.h> /* uint64_t uint32_t uint8_t */ -#endif +#include <stdint.h> /* uint64_t uint32_t uint8_t */ /* * Workaround to not require a C++11 compiler for using ULL suffix * if this code is included and compiled as C++; related GCC warning is: * warning: use of C++11 long long integer constant [-Wlong-long] */ -#define _SIP_ULL(high, low) (((uint64_t)high << 32) | low) +#define SIP_ULL(high, low) ((((uint64_t)high) << 32) | (low)) #define SIP_ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b)))) @@ -131,8 +126,7 @@ typedef unsigned __int64 uint64_t; | ((uint64_t)((p)[4]) << 32) | ((uint64_t)((p)[5]) << 40) \ | ((uint64_t)((p)[6]) << 48) | ((uint64_t)((p)[7]) << 56)) -#define SIPHASH_INITIALIZER \ - { 0, 0, 0, 0, {0}, 0, 0 } +#define SIPHASH_INITIALIZER {0, 0, 0, 0, {0}, 0, 0} struct siphash { uint64_t v0, v1, v2, v3; @@ -195,10 +189,10 @@ sip_round(struct siphash *H, const int rounds) { static struct siphash * sip24_init(struct siphash *H, const struct sipkey *key) { - H->v0 = _SIP_ULL(0x736f6d65U, 0x70736575U) ^ key->k[0]; - H->v1 = _SIP_ULL(0x646f7261U, 0x6e646f6dU) ^ key->k[1]; - H->v2 = _SIP_ULL(0x6c796765U, 0x6e657261U) ^ key->k[0]; - H->v3 = _SIP_ULL(0x74656462U, 0x79746573U) ^ key->k[1]; + H->v0 = SIP_ULL(0x736f6d65U, 0x70736575U) ^ key->k[0]; + H->v1 = SIP_ULL(0x646f7261U, 0x6e646f6dU) ^ key->k[1]; + H->v2 = SIP_ULL(0x6c796765U, 0x6e657261U) ^ key->k[0]; + H->v3 = SIP_ULL(0x74656462U, 0x79746573U) ^ key->k[1]; H->p = H->buf; H->c = 0; diff --git a/3rdparty/expat/lib/utf8tab.h b/3rdparty/expat/lib/utf8tab.h index a22986acbb9..88efcf91cc1 100644 --- a/3rdparty/expat/lib/utf8tab.h +++ b/3rdparty/expat/lib/utf8tab.h @@ -7,7 +7,9 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining diff --git a/3rdparty/expat/lib/winconfig.h b/3rdparty/expat/lib/winconfig.h index 562a4a82dc1..05805514ec7 100644 --- a/3rdparty/expat/lib/winconfig.h +++ b/3rdparty/expat/lib/winconfig.h @@ -6,8 +6,11 @@ \___/_/\_\ .__/ \__,_|\__| |_| XML parser - Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2005 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017-2023 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2023 Orgad Shaneh <orgad.shaneh@audiocodes.com> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -33,24 +36,13 @@ #ifndef WINCONFIG_H #define WINCONFIG_H -#define WIN32_LEAN_AND_MEAN +#ifndef WIN32_LEAN_AND_MEAN +# define WIN32_LEAN_AND_MEAN +#endif #include <windows.h> #undef WIN32_LEAN_AND_MEAN #include <memory.h> #include <string.h> -#if defined(HAVE_EXPAT_CONFIG_H) /* e.g. MinGW */ -# include <expat_config.h> -#else /* !defined(HAVE_EXPAT_CONFIG_H) */ - -# define XML_NS 1 -# define XML_DTD 1 -# define XML_CONTEXT_BYTES 1024 - -/* we will assume all Windows platforms are little endian */ -# define BYTEORDER 1234 - -#endif /* !defined(HAVE_EXPAT_CONFIG_H) */ - #endif /* ndef WINCONFIG_H */ diff --git a/3rdparty/expat/lib/xmlparse.c b/3rdparty/expat/lib/xmlparse.c index dfc316ca36c..38a2d9657b6 100644 --- a/3rdparty/expat/lib/xmlparse.c +++ b/3rdparty/expat/lib/xmlparse.c @@ -1,4 +1,4 @@ -/* 5cd169f2942b85c05e0b1b96f9990f91ac3d07e470ad7ce906ac8590c8ed4f35 (2.2.10+) +/* d19ae032c224863c1527ba44d228cc34b99192c3a4c5a27af1f4e054d45ee031 (2.7.1+) __ __ _ ___\ \/ /_ __ __ _| |_ / _ \\ /| '_ \ / _` | __| @@ -7,7 +7,40 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2006 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016 Eric Rahm <erahm@mozilla.com> + Copyright (c) 2016-2025 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Gaurav <g.gupta@samsung.com> + Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> + Copyright (c) 2016 Gustavo Grieco <gustavo.grieco@imag.fr> + Copyright (c) 2016 Pascal Cuoq <cuoq@trust-in-soft.com> + Copyright (c) 2016 Ed Schouten <ed@nuxi.nl> + Copyright (c) 2017-2022 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2017 Václav Slavík <vaclav@slavik.io> + Copyright (c) 2017 Viktor Szakats <commit@vsz.me> + Copyright (c) 2017 Chanho Park <chanho61.park@samsung.com> + Copyright (c) 2017 Rolf Eike Beer <eike@sf-mail.de> + Copyright (c) 2017 Hans Wennborg <hans@chromium.org> + Copyright (c) 2018 Anton Maklakov <antmak.pub@gmail.com> + Copyright (c) 2018 Benjamin Peterson <benjamin@python.org> + Copyright (c) 2018 Marco Maggi <marco.maggi-ipsu@poste.it> + Copyright (c) 2018 Mariusz Zaborski <oshogbo@vexillium.org> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2019-2020 Ben Wagner <bungeman@chromium.org> + Copyright (c) 2019 Vadim Zeitlin <vadim@zeitlins.org> + Copyright (c) 2021 Donghee Na <donghee.na@python.org> + Copyright (c) 2022 Samanta Navarro <ferivoz@riseup.net> + Copyright (c) 2022 Jeffrey Walton <noloader@gmail.com> + Copyright (c) 2022 Jann Horn <jannh@google.com> + Copyright (c) 2022 Sean McBride <sean@rogue-research.com> + Copyright (c) 2023 Owain Davies <owaind@bath.edu> + Copyright (c) 2023-2024 Sony Corporation / Snild Dolkow <snild@sony.com> + Copyright (c) 2024-2025 Berkay Eren Ürün <berkay.ueruen@siemens.com> + Copyright (c) 2024 Hanno Böck <hanno@gentoo.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -30,8 +63,27 @@ USE OR OTHER DEALINGS IN THE SOFTWARE. */ -#if ! defined(_GNU_SOURCE) -# define _GNU_SOURCE 1 /* syscall prototype */ +#define XML_BUILDING_EXPAT 1 + +#include "expat_config.h" + +#if ! defined(XML_GE) || (1 - XML_GE - 1 == 2) || (XML_GE < 0) || (XML_GE > 1) +# error XML_GE (for general entities) must be defined, non-empty, either 1 or 0 (0 to disable, 1 to enable; 1 is a common default) +#endif + +#if defined(XML_DTD) && XML_GE == 0 +# error Either undefine XML_DTD or define XML_GE to 1. +#endif + +#if ! defined(XML_CONTEXT_BYTES) || (1 - XML_CONTEXT_BYTES - 1 == 2) \ + || (XML_CONTEXT_BYTES + 0 < 0) +# error XML_CONTEXT_BYTES must be defined, non-empty and >=0 (0 to disable, >=1 to enable; 1024 is a common default) +#endif + +#if defined(HAVE_SYSCALL_GETRANDOM) +# if ! defined(_GNU_SOURCE) +# define _GNU_SOURCE 1 /* syscall prototype */ +# endif #endif #ifdef _WIN32 @@ -41,23 +93,15 @@ # endif #endif +#include <stdbool.h> #include <stddef.h> #include <string.h> /* memset(), memcpy() */ #include <assert.h> #include <limits.h> /* UINT_MAX */ #include <stdio.h> /* fprintf */ #include <stdlib.h> /* getenv, rand_s */ - -#if defined(_WIN32) && defined(_MSC_VER) && (_MSC_VER < 1600) -/* vs2008/9.0 and earlier lack stdint.h; _MSC_VER 1600 is vs2010/10.0 */ -# if defined(_WIN64) -typedef unsigned __int64 uintptr_t; -# else -typedef unsigned __int32 uintptr_t; -# endif -#else -# include <stdint.h> /* uintptr_t */ -#endif +#include <stdint.h> /* uintptr_t */ +#include <math.h> /* isnan */ #ifdef _WIN32 # define getpid GetCurrentProcessId @@ -69,13 +113,9 @@ typedef unsigned __int32 uintptr_t; # include <errno.h> #endif -#define XML_BUILDING_EXPAT 1 - #ifdef _WIN32 # include "winconfig.h" -#elif defined(HAVE_EXPAT_CONFIG_H) -# include <expat_config.h> -#endif /* ndef _WIN32 */ +#endif #include "ascii.h" #include "expat.h" @@ -112,11 +152,11 @@ typedef unsigned __int32 uintptr_t; Your options include: \ * Linux >=3.17 + glibc >=2.25 (getrandom): HAVE_GETRANDOM, \ * Linux >=3.17 + glibc (including <2.25) (syscall SYS_getrandom): HAVE_SYSCALL_GETRANDOM, \ - * BSD / macOS >=10.7 (arc4random_buf): HAVE_ARC4RANDOM_BUF, \ - * BSD / macOS (including <10.7) (arc4random): HAVE_ARC4RANDOM, \ + * BSD / macOS >=10.7 / glibc >=2.36 (arc4random_buf): HAVE_ARC4RANDOM_BUF, \ + * BSD / macOS (including <10.7) / glibc >=2.36 (arc4random): HAVE_ARC4RANDOM, \ * libbsd (arc4random_buf): HAVE_ARC4RANDOM_BUF + HAVE_LIBBSD, \ * libbsd (arc4random): HAVE_ARC4RANDOM + HAVE_LIBBSD, \ - * Linux (including <3.17) / BSD / macOS (including <10.7) (/dev/urandom): XML_DEV_URANDOM, \ + * Linux (including <3.17) / BSD / macOS (including <10.7) / Solaris >=8 (/dev/urandom): XML_DEV_URANDOM, \ * Windows >=Vista (rand_s): _WIN32. \ \ If insist on not using any of these, bypass this error by defining \ @@ -172,11 +212,13 @@ typedef char ICHAR; #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)) +#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) /* Do safe (NULL-aware) pointer arithmetic */ #define EXPAT_SAFE_PTR_DIFF(p, q) (((p) && (q)) ? ((p) - (q)) : 0) +#define EXPAT_MIN(a, b) (((a) < (b)) ? (a) : (b)) + #include "internal.h" #include "xmltok.h" #include "xmlrole.h" @@ -208,7 +250,7 @@ static void copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key); it odd, since odd numbers are always relative prime to a power of 2. */ #define SECOND_HASH(hash, mask, power) \ - ((((hash) & ~(mask)) >> ((power)-1)) & ((mask) >> 2)) + ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2)) #define PROBE_STEP(hash, mask, power) \ ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) @@ -254,13 +296,13 @@ typedef struct { The name of the element is stored in both the document and API encodings. The memory buffer 'buf' is a separately-allocated memory area which stores the name. During the XML_Parse()/ - XMLParseBuffer() when the element is open, the memory for the 'raw' + XML_ParseBuffer() when the element is open, the memory for the 'raw' version of the name (in the document encoding) is shared with the document buffer. If the element is open across calls to XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to contain the 'raw' name as well. - A parser re-uses these structures, maintaining a list of allocated + A parser reuses these structures, maintaining a list of allocated TAG objects in a free list. */ typedef struct tag { @@ -283,6 +325,10 @@ typedef struct { const XML_Char *publicId; const XML_Char *notation; XML_Bool open; + XML_Bool hasMore; /* true if entity has not been completely processed */ + /* An entity can be open while being already completely processed (hasMore == + XML_FALSE). The reason is the delayed closing of entities until their inner + entities are processed and closed */ XML_Bool is_param; XML_Bool is_internal; /* true if declared in internal subset outside PE */ } ENTITY; @@ -373,6 +419,12 @@ typedef struct { int *scaffIndex; } DTD; +enum EntityType { + ENTITY_INTERNAL, + ENTITY_ATTRIBUTE, + ENTITY_VALUE, +}; + typedef struct open_internal_entity { const char *internalEventPtr; const char *internalEventEndPtr; @@ -380,8 +432,34 @@ typedef struct open_internal_entity { ENTITY *entity; int startTagLevel; XML_Bool betweenDecl; /* WFC: PE Between Declarations */ + enum EntityType type; } OPEN_INTERNAL_ENTITY; +enum XML_Account { + XML_ACCOUNT_DIRECT, /* bytes directly passed to the Expat parser */ + XML_ACCOUNT_ENTITY_EXPANSION, /* intermediate bytes produced during entity + expansion */ + XML_ACCOUNT_NONE /* i.e. do not account, was accounted already */ +}; + +#if XML_GE == 1 +typedef unsigned long long XmlBigCount; +typedef struct accounting { + XmlBigCount countBytesDirect; + XmlBigCount countBytesIndirect; + unsigned long debugLevel; + float maximumAmplificationFactor; // >=1.0 + unsigned long long activationThresholdBytes; +} ACCOUNTING; + +typedef struct entity_stats { + unsigned int countEverOpened; + unsigned int currentDepth; + unsigned int maximumDepthSeen; + unsigned long debugLevel; +} ENTITY_STATS; +#endif /* XML_GE == 1 */ + typedef enum XML_Error PTRCALL Processor(XML_Parser parser, const char *start, const char *end, const char **endPtr); @@ -412,43 +490,59 @@ static enum XML_Error initializeEncoding(XML_Parser parser); static enum XML_Error doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, int tok, const char *next, const char **nextPtr, - XML_Bool haveMore, XML_Bool allowClosingDoctype); -static enum XML_Error processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl); + XML_Bool haveMore, XML_Bool allowClosingDoctype, + enum XML_Account account); +static enum XML_Error processEntity(XML_Parser parser, ENTITY *entity, + XML_Bool betweenDecl, enum EntityType type); static enum XML_Error doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, const char *start, const char *end, const char **endPtr, - XML_Bool haveMore); -static enum XML_Error doCdataSection(XML_Parser parser, const ENCODING *, + XML_Bool haveMore, enum XML_Account account); +static enum XML_Error doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, const char *end, - const char **nextPtr, XML_Bool haveMore); + const char **nextPtr, XML_Bool haveMore, + enum XML_Account account); #ifdef XML_DTD -static enum XML_Error doIgnoreSection(XML_Parser parser, const ENCODING *, +static enum XML_Error doIgnoreSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, const char *end, const char **nextPtr, XML_Bool haveMore); #endif /* XML_DTD */ static void freeBindings(XML_Parser parser, BINDING *bindings); -static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, - const char *s, TAG_NAME *tagNamePtr, - BINDING **bindingsPtr); +static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, + const char *attStr, TAG_NAME *tagNamePtr, + BINDING **bindingsPtr, + enum XML_Account account); static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr); -static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, - XML_Bool isId, const XML_Char *dfltValue, - XML_Parser parser); -static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *, - XML_Bool isCdata, const char *, - const char *, STRING_POOL *); -static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *, - XML_Bool isCdata, const char *, - const char *, STRING_POOL *); +static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, + XML_Bool isCdata, XML_Bool isId, + const XML_Char *value, XML_Parser parser); +static enum XML_Error storeAttributeValue(XML_Parser parser, + const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, + STRING_POOL *pool, + enum XML_Account account); +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, STRING_POOL *pool, + enum XML_Account account, const char **nextPtr); static ATTRIBUTE_ID *getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); -static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); +static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType); +#if XML_GE == 1 static enum XML_Error storeEntityValue(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end); + const char *start, const char *end, + enum XML_Account account, + const char **nextPtr); +static enum XML_Error callStoreEntityValue(XML_Parser parser, + const ENCODING *enc, + const char *start, const char *end, + enum XML_Account account); +#else +static enum XML_Error storeSelfEntityValue(XML_Parser parser, ENTITY *entity); +#endif static int reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); static int reportComment(XML_Parser parser, const ENCODING *enc, @@ -468,21 +562,22 @@ static void dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms); static int dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms); -static int copyEntityTable(XML_Parser oldParser, HASH_TABLE *, STRING_POOL *, - const HASH_TABLE *); +static int copyEntityTable(XML_Parser oldParser, HASH_TABLE *newTable, + STRING_POOL *newPool, const HASH_TABLE *oldTable); static NAMED *lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize); -static void FASTCALL hashTableInit(HASH_TABLE *, +static void FASTCALL hashTableInit(HASH_TABLE *table, const XML_Memory_Handling_Suite *ms); -static void FASTCALL hashTableClear(HASH_TABLE *); -static void FASTCALL hashTableDestroy(HASH_TABLE *); -static void FASTCALL hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); -static NAMED *FASTCALL hashTableIterNext(HASH_TABLE_ITER *); +static void FASTCALL hashTableClear(HASH_TABLE *table); +static void FASTCALL hashTableDestroy(HASH_TABLE *table); +static void FASTCALL hashTableIterInit(HASH_TABLE_ITER *iter, + const HASH_TABLE *table); +static NAMED *FASTCALL hashTableIterNext(HASH_TABLE_ITER *iter); -static void FASTCALL poolInit(STRING_POOL *, +static void FASTCALL poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms); -static void FASTCALL poolClear(STRING_POOL *); -static void FASTCALL poolDestroy(STRING_POOL *); +static void FASTCALL poolClear(STRING_POOL *pool); +static void FASTCALL poolDestroy(STRING_POOL *pool); static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc, const char *ptr, const char *end); static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, @@ -512,8 +607,35 @@ static XML_Parser parserCreate(const XML_Char *encodingName, static void parserInit(XML_Parser parser, const XML_Char *encodingName); +#if XML_GE == 1 +static float accountingGetCurrentAmplification(XML_Parser rootParser); +static void accountingReportStats(XML_Parser originParser, const char *epilog); +static void accountingOnAbort(XML_Parser originParser); +static void accountingReportDiff(XML_Parser rootParser, + unsigned int levelsAwayFromRootParser, + const char *before, const char *after, + ptrdiff_t bytesMore, int source_line, + enum XML_Account account); +static XML_Bool accountingDiffTolerated(XML_Parser originParser, int tok, + const char *before, const char *after, + int source_line, + enum XML_Account account); + +static void entityTrackingReportStats(XML_Parser parser, ENTITY *entity, + const char *action, int sourceLine); +static void entityTrackingOnOpen(XML_Parser parser, ENTITY *entity, + int sourceLine); +static void entityTrackingOnClose(XML_Parser parser, ENTITY *entity, + int sourceLine); + +static XML_Parser getRootParserOf(XML_Parser parser, + unsigned int *outLevelDiff); +#endif /* XML_GE == 1 */ + +static unsigned long getDebugLevel(const char *variableName, + unsigned long defaultDebugLevel); + #define poolStart(pool) ((pool)->start) -#define poolEnd(pool) ((pool)->ptr) #define poolLength(pool) ((pool)->ptr - (pool)->start) #define poolChop(pool) ((void)--(pool->ptr)) #define poolLastChar(pool) (((pool)->ptr)[-1]) @@ -524,21 +646,41 @@ static void parserInit(XML_Parser parser, const XML_Char *encodingName); ? 0 \ : ((*((pool)->ptr)++ = c), 1)) +#if ! defined(XML_TESTING) +const +#endif + XML_Bool g_reparseDeferralEnabledDefault + = XML_TRUE; // write ONLY in runtests.c +#if defined(XML_TESTING) +unsigned int g_bytesScanned = 0; // used for testing only +#endif + struct XML_ParserStruct { /* The first member must be m_userData so that the XML_GetUserData macro works. */ void *m_userData; void *m_handlerArg; - char *m_buffer; + + // How the four parse buffer pointers below relate in time and space: + // + // m_buffer <= m_bufferPtr <= m_bufferEnd <= m_bufferLim + // | | | | + // <--parsed-->| | | + // <---parsing--->| | + // <--unoccupied-->| + // <---------total-malloced/realloced-------->| + + char *m_buffer; // malloc/realloc base pointer of parse buffer const XML_Memory_Handling_Suite m_mem; - /* first character to be parsed */ - const char *m_bufferPtr; - /* past last character to be parsed */ - char *m_bufferEnd; - /* allocated end of m_buffer */ - const char *m_bufferLim; + const char *m_bufferPtr; // first character to be parsed + char *m_bufferEnd; // past last character to be parsed + const char *m_bufferLim; // allocated end of m_buffer + XML_Index m_parseEndByteIndex; const char *m_parseEndPtr; + size_t m_partialTokenBytesBefore; /* used in heuristic to avoid O(n^2) */ + XML_Bool m_reparseDeferralEnabled; + int m_lastBufferRequestSize; XML_Char *m_dataBuf; XML_Char *m_dataBufEnd; XML_StartElementHandler m_startElementHandler; @@ -582,6 +724,10 @@ struct XML_ParserStruct { const char *m_positionPtr; OPEN_INTERNAL_ENTITY *m_openInternalEntities; OPEN_INTERNAL_ENTITY *m_freeInternalEntities; + OPEN_INTERNAL_ENTITY *m_openAttributeEntities; + OPEN_INTERNAL_ENTITY *m_freeAttributeEntities; + OPEN_INTERNAL_ENTITY *m_openValueEntities; + OPEN_INTERNAL_ENTITY *m_freeValueEntities; XML_Bool m_defaultExpandInternalEntities; int m_tagLevel; ENTITY *m_declEntity; @@ -625,6 +771,11 @@ struct XML_ParserStruct { enum XML_ParamEntityParsing m_paramEntityParsing; #endif unsigned long m_hash_secret_salt; +#if XML_GE == 1 + ACCOUNTING m_accounting; + ENTITY_STATS m_entity_stats; +#endif + XML_Bool m_reenter; }; #define MALLOC(parser, s) (parser->m_mem.malloc_fcn((s))) @@ -638,11 +789,11 @@ XML_ParserCreate(const XML_Char *encodingName) { XML_Parser XMLCALL XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) { - XML_Char tmp[2]; - *tmp = nsSep; + XML_Char tmp[2] = {nsSep, 0}; return XML_ParserCreate_MM(encodingName, NULL, tmp); } +// "xml=http://www.w3.org/XML/1998/namespace" static const XML_Char implicitContext[] = {ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, @@ -809,9 +960,8 @@ gather_time_entropy(void) { static unsigned long ENTROPY_DEBUG(const char *label, unsigned long entropy) { - const char *const EXPAT_ENTROPY_DEBUG = getenv("EXPAT_ENTROPY_DEBUG"); - if (EXPAT_ENTROPY_DEBUG && ! strcmp(EXPAT_ENTROPY_DEBUG, "1")) { - fprintf(stderr, "Entropy: %s --> 0x%0*lx (%lu bytes)\n", label, + if (getDebugLevel("EXPAT_ENTROPY_DEBUG", 0) >= 1u) { + fprintf(stderr, "expat: Entropy: %s --> 0x%0*lx (%lu bytes)\n", label, (int)sizeof(entropy) * 2, entropy, (unsigned long)sizeof(entropy)); } return entropy; @@ -867,6 +1017,71 @@ get_hash_secret_salt(XML_Parser parser) { return parser->m_hash_secret_salt; } +static enum XML_Error +callProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + const size_t have_now = EXPAT_SAFE_PTR_DIFF(end, start); + + if (parser->m_reparseDeferralEnabled + && ! parser->m_parsingStatus.finalBuffer) { + // Heuristic: don't try to parse a partial token again until the amount of + // available data has increased significantly. + const size_t had_before = parser->m_partialTokenBytesBefore; + // ...but *do* try anyway if we're close to causing a reallocation. + size_t available_buffer + = EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer); +#if XML_CONTEXT_BYTES > 0 + available_buffer -= EXPAT_MIN(available_buffer, XML_CONTEXT_BYTES); +#endif + available_buffer + += EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd); + // m_lastBufferRequestSize is never assigned a value < 0, so the cast is ok + const bool enough + = (have_now >= 2 * had_before) + || ((size_t)parser->m_lastBufferRequestSize > available_buffer); + + if (! enough) { + *endPtr = start; // callers may expect this to be set + return XML_ERROR_NONE; + } + } +#if defined(XML_TESTING) + g_bytesScanned += (unsigned)have_now; +#endif + // Run in a loop to eliminate dangerous recursion depths + enum XML_Error ret; + *endPtr = start; + while (1) { + // Use endPtr as the new start in each iteration, since it will + // be set to the next start point by m_processor. + ret = parser->m_processor(parser, *endPtr, end, endPtr); + + // Make parsing status (and in particular XML_SUSPENDED) take + // precedence over re-enter flag when they disagree + if (parser->m_parsingStatus.parsing != XML_PARSING) { + parser->m_reenter = XML_FALSE; + } + + if (! parser->m_reenter) { + break; + } + + parser->m_reenter = XML_FALSE; + if (ret != XML_ERROR_NONE) + return ret; + } + + if (ret == XML_ERROR_NONE) { + // if we consumed nothing, remember what we had on this parse attempt. + if (*endPtr == start) { + parser->m_partialTokenBytesBefore = have_now; + } else { + parser->m_partialTokenBytesBefore = 0; + } + } + return ret; +} + static XML_Bool /* only valid for root parser */ startParsing(XML_Parser parser) { /* hash functions must be initialized before setContext() is called */ @@ -896,7 +1111,7 @@ parserCreate(const XML_Char *encodingName, if (memsuite) { XML_Memory_Handling_Suite *mtemp; - parser = (XML_Parser)memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); + parser = memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); if (parser != NULL) { mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); mtemp->malloc_fcn = memsuite->malloc_fcn; @@ -966,6 +1181,8 @@ parserCreate(const XML_Char *encodingName, parser->m_freeBindingList = NULL; parser->m_freeTagList = NULL; parser->m_freeInternalEntities = NULL; + parser->m_freeAttributeEntities = NULL; + parser->m_freeValueEntities = NULL; parser->m_groupSize = 0; parser->m_groupConnector = NULL; @@ -988,6 +1205,14 @@ parserCreate(const XML_Char *encodingName, parserInit(parser, encodingName); if (encodingName && ! parser->m_protocolEncodingName) { + if (dtd) { + // We need to stop the upcoming call to XML_ParserFree from happily + // destroying parser->m_dtd because the DTD is shared with the parent + // parser and the only guard that keeps XML_ParserFree from destroying + // parser->m_dtd is parser->m_isParamEntity but it will be set to + // XML_TRUE only later in XML_ExternalEntityParserCreate (or not at all). + parser->m_dtd = NULL; + } XML_ParserFree(parser); return NULL; } @@ -1040,6 +1265,9 @@ parserInit(XML_Parser parser, const XML_Char *encodingName) { parser->m_bufferEnd = parser->m_buffer; parser->m_parseEndByteIndex = 0; parser->m_parseEndPtr = NULL; + parser->m_partialTokenBytesBefore = 0; + parser->m_reparseDeferralEnabled = g_reparseDeferralEnabledDefault; + parser->m_lastBufferRequestSize = 0; parser->m_declElementType = NULL; parser->m_declAttributeId = NULL; parser->m_declEntity = NULL; @@ -1057,6 +1285,8 @@ parserInit(XML_Parser parser, const XML_Char *encodingName) { parser->m_eventEndPtr = NULL; parser->m_positionPtr = NULL; parser->m_openInternalEntities = NULL; + parser->m_openAttributeEntities = NULL; + parser->m_openValueEntities = NULL; parser->m_defaultExpandInternalEntities = XML_TRUE; parser->m_tagLevel = 0; parser->m_tagStack = NULL; @@ -1067,12 +1297,26 @@ parserInit(XML_Parser parser, const XML_Char *encodingName) { parser->m_unknownEncodingData = NULL; parser->m_parentParser = NULL; parser->m_parsingStatus.parsing = XML_INITIALIZED; + // Reentry can only be triggered inside m_processor calls + parser->m_reenter = XML_FALSE; #ifdef XML_DTD parser->m_isParamEntity = XML_FALSE; parser->m_useForeignDTD = XML_FALSE; parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; #endif parser->m_hash_secret_salt = 0; + +#if XML_GE == 1 + memset(&parser->m_accounting, 0, sizeof(ACCOUNTING)); + parser->m_accounting.debugLevel = getDebugLevel("EXPAT_ACCOUNTING_DEBUG", 0u); + parser->m_accounting.maximumAmplificationFactor + = EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT; + parser->m_accounting.activationThresholdBytes + = EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT; + + memset(&parser->m_entity_stats, 0, sizeof(ENTITY_STATS)); + parser->m_entity_stats.debugLevel = getDebugLevel("EXPAT_ENTITY_DEBUG", 0u); +#endif } /* moves list of bindings to m_freeBindingList */ @@ -1114,6 +1358,24 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { openEntity->next = parser->m_freeInternalEntities; parser->m_freeInternalEntities = openEntity; } + /* move m_openAttributeEntities to m_freeAttributeEntities (i.e. same task but + * for attributes) */ + openEntityList = parser->m_openAttributeEntities; + while (openEntityList) { + OPEN_INTERNAL_ENTITY *openEntity = openEntityList; + openEntityList = openEntity->next; + openEntity->next = parser->m_freeAttributeEntities; + parser->m_freeAttributeEntities = openEntity; + } + /* move m_openValueEntities to m_freeValueEntities (i.e. same task but + * for value entities) */ + openEntityList = parser->m_openValueEntities; + while (openEntityList) { + OPEN_INTERNAL_ENTITY *openEntity = openEntityList; + openEntityList = openEntity->next; + openEntity->next = parser->m_freeValueEntities; + parser->m_freeValueEntities = openEntity; + } moveToFreeBindingList(parser, parser->m_inheritedBindings); FREE(parser, parser->m_unknownEncodingMem); if (parser->m_unknownEncodingRelease) @@ -1127,6 +1389,19 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { return XML_TRUE; } +static XML_Bool +parserBusy(XML_Parser parser) { + switch (parser->m_parsingStatus.parsing) { + case XML_PARSING: + case XML_SUSPENDED: + return XML_TRUE; + case XML_INITIALIZED: + case XML_FINISHED: + default: + return XML_FALSE; + } +} + enum XML_Status XMLCALL XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { if (parser == NULL) @@ -1135,8 +1410,7 @@ XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { XXX There's no way for the caller to determine which of the XXX possible error cases caused the XML_STATUS_ERROR return. */ - if (parser->m_parsingStatus.parsing == XML_PARSING - || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parserBusy(parser)) return XML_STATUS_ERROR; /* Get rid of any previous encoding name */ @@ -1197,6 +1471,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, to worry which hash secrets each table has. */ unsigned long oldhash_secret_salt; + XML_Bool oldReparseDeferralEnabled; /* Validate the oldParser parameter before we pull everything out of it */ if (oldParser == NULL) @@ -1241,6 +1516,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, to worry which hash secrets each table has. */ oldhash_secret_salt = parser->m_hash_secret_salt; + oldReparseDeferralEnabled = parser->m_reparseDeferralEnabled; #ifdef XML_DTD if (! context) @@ -1253,8 +1529,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, would be otherwise. */ if (parser->m_ns) { - XML_Char tmp[2]; - *tmp = parser->m_namespaceSeparator; + XML_Char tmp[2] = {parser->m_namespaceSeparator, 0}; parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); } else { parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); @@ -1294,6 +1569,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, parser->m_defaultExpandInternalEntities = oldDefaultExpandInternalEntities; parser->m_ns_triplets = oldns_triplets; parser->m_hash_secret_salt = oldhash_secret_salt; + parser->m_reparseDeferralEnabled = oldReparseDeferralEnabled; parser->m_parentParser = oldParser; #ifdef XML_DTD parser->m_paramEntityParsing = oldParamEntityParsing; @@ -1371,7 +1647,34 @@ XML_ParserFree(XML_Parser parser) { entityList = entityList->next; FREE(parser, openEntity); } - + /* free m_openAttributeEntities and m_freeAttributeEntities */ + entityList = parser->m_openAttributeEntities; + for (;;) { + OPEN_INTERNAL_ENTITY *openEntity; + if (entityList == NULL) { + if (parser->m_freeAttributeEntities == NULL) + break; + entityList = parser->m_freeAttributeEntities; + parser->m_freeAttributeEntities = NULL; + } + openEntity = entityList; + entityList = entityList->next; + FREE(parser, openEntity); + } + /* free m_openValueEntities and m_freeValueEntities */ + entityList = parser->m_openValueEntities; + for (;;) { + OPEN_INTERNAL_ENTITY *openEntity; + if (entityList == NULL) { + if (parser->m_freeValueEntities == NULL) + break; + entityList = parser->m_freeValueEntities; + parser->m_freeValueEntities = NULL; + } + openEntity = entityList; + entityList = entityList->next; + FREE(parser, openEntity); + } destroyBindings(parser->m_freeBindingList, parser); destroyBindings(parser->m_inheritedBindings, parser); poolDestroy(&parser->m_tempPool); @@ -1413,8 +1716,7 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { return XML_ERROR_INVALID_ARGUMENT; #ifdef XML_DTD /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING - || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parserBusy(parser)) return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; parser->m_useForeignDTD = useDTD; return XML_ERROR_NONE; @@ -1429,8 +1731,7 @@ XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { if (parser == NULL) return; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING - || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parserBusy(parser)) return; parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE; } @@ -1699,8 +2000,7 @@ XML_SetParamEntityParsing(XML_Parser parser, if (parser == NULL) return 0; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING - || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parserBusy(parser)) return 0; #ifdef XML_DTD parser->m_paramEntityParsing = peParsing; @@ -1717,8 +2017,7 @@ XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt) { if (parser->m_parentParser) return XML_SetHashSalt(parser->m_parentParser, hash_salt); /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING - || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parserBusy(parser)) return 0; parser->m_hash_secret_salt = hash_salt; return 1; @@ -1748,55 +2047,8 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { parser->m_parsingStatus.parsing = XML_PARSING; } - if (len == 0) { - parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - if (! isFinal) - return XML_STATUS_OK; - parser->m_positionPtr = parser->m_bufferPtr; - parser->m_parseEndPtr = parser->m_bufferEnd; - - /* If data are left over from last buffer, and we now know that these - data are the final chunk of input, then we have to check them again - to detect errors based on that fact. - */ - parser->m_errorCode - = parser->m_processor(parser, parser->m_bufferPtr, - parser->m_parseEndPtr, &parser->m_bufferPtr); - - if (parser->m_errorCode == XML_ERROR_NONE) { - switch (parser->m_parsingStatus.parsing) { - case XML_SUSPENDED: - /* It is hard to be certain, but it seems that this case - * cannot occur. This code is cleaning up a previous parse - * with no new data (since len == 0). Changing the parsing - * state requires getting to execute a handler function, and - * there doesn't seem to be an opportunity for that while in - * this circumstance. - * - * Given the uncertainty, we retain the code but exclude it - * from coverage tests. - * - * LCOV_EXCL_START - */ - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, - parser->m_bufferPtr, &parser->m_position); - parser->m_positionPtr = parser->m_bufferPtr; - return XML_STATUS_SUSPENDED; - /* LCOV_EXCL_STOP */ - case XML_INITIALIZED: - case XML_PARSING: - parser->m_parsingStatus.parsing = XML_FINISHED; - /* fall through */ - default: - return XML_STATUS_OK; - } - } - parser->m_eventEndPtr = parser->m_eventPtr; - parser->m_processor = errorProcessor; - return XML_STATUS_ERROR; - } -#ifndef XML_CONTEXT_BYTES - else if (parser->m_bufferPtr == parser->m_bufferEnd) { +#if XML_CONTEXT_BYTES == 0 + if (parser->m_bufferPtr == parser->m_bufferEnd) { const char *end; int nLeftOver; enum XML_Status result; @@ -1807,12 +2059,15 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { parser->m_processor = errorProcessor; return XML_STATUS_ERROR; } + // though this isn't a buffer request, we assume that `len` is the app's + // preferred buffer fill size, and therefore save it here. + parser->m_lastBufferRequestSize = len; parser->m_parseEndByteIndex += len; parser->m_positionPtr = s; parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; parser->m_errorCode - = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end); + = callProcessor(parser, s, parser->m_parseEndPtr = s + len, &end); if (parser->m_errorCode != XML_ERROR_NONE) { parser->m_eventEndPtr = parser->m_eventPtr; @@ -1839,23 +2094,25 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { &parser->m_position); nLeftOver = s + len - end; if (nLeftOver) { - if (parser->m_buffer == NULL - || nLeftOver > parser->m_bufferLim - parser->m_buffer) { - /* avoid _signed_ integer overflow */ - char *temp = NULL; - const int bytesToAllocate = (int)((unsigned)len * 2U); - if (bytesToAllocate > 0) { - temp = (char *)REALLOC(parser, parser->m_buffer, bytesToAllocate); - } - if (temp == NULL) { - parser->m_errorCode = XML_ERROR_NO_MEMORY; - parser->m_eventPtr = parser->m_eventEndPtr = NULL; - parser->m_processor = errorProcessor; - return XML_STATUS_ERROR; - } - parser->m_buffer = temp; - parser->m_bufferLim = parser->m_buffer + bytesToAllocate; + // Back up and restore the parsing status to avoid XML_ERROR_SUSPENDED + // (and XML_ERROR_FINISHED) from XML_GetBuffer. + const enum XML_Parsing originalStatus = parser->m_parsingStatus.parsing; + parser->m_parsingStatus.parsing = XML_PARSING; + void *const temp = XML_GetBuffer(parser, nLeftOver); + parser->m_parsingStatus.parsing = originalStatus; + // GetBuffer may have overwritten this, but we want to remember what the + // app requested, not how many bytes were left over after parsing. + parser->m_lastBufferRequestSize = len; + if (temp == NULL) { + // NOTE: parser->m_errorCode has already been set by XML_GetBuffer(). + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; } + // Since we know that the buffer was empty and XML_CONTEXT_BYTES is 0, we + // don't have any data to preserve, and can copy straight into the start + // of the buffer rather than the GetBuffer return pointer (which may be + // pointing further into the allocated buffer). memcpy(parser->m_buffer, end, nLeftOver); } parser->m_bufferPtr = parser->m_buffer; @@ -1866,16 +2123,15 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { parser->m_eventEndPtr = parser->m_bufferPtr; return result; } -#endif /* not defined XML_CONTEXT_BYTES */ - else { - void *buff = XML_GetBuffer(parser, len); - if (buff == NULL) - return XML_STATUS_ERROR; - else { - memcpy(buff, s, len); - return XML_ParseBuffer(parser, len, isFinal); - } +#endif /* XML_CONTEXT_BYTES == 0 */ + void *buff = XML_GetBuffer(parser, len); + if (buff == NULL) + return XML_STATUS_ERROR; + if (len > 0) { + assert(s != NULL); // make sure s==NULL && len!=0 was rejected above + memcpy(buff, s, len); } + return XML_ParseBuffer(parser, len, isFinal); } enum XML_Status XMLCALL @@ -1885,6 +2141,12 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { if (parser == NULL) return XML_STATUS_ERROR; + + if (len < 0) { + parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT; + return XML_STATUS_ERROR; + } + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: parser->m_errorCode = XML_ERROR_SUSPENDED; @@ -1893,6 +2155,12 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; case XML_INITIALIZED: + /* Has someone called XML_GetBuffer successfully before? */ + if (! parser->m_bufferPtr) { + parser->m_errorCode = XML_ERROR_NO_BUFFER; + return XML_STATUS_ERROR; + } + if (parser->m_parentParser == NULL && ! startParsing(parser)) { parser->m_errorCode = XML_ERROR_NO_MEMORY; return XML_STATUS_ERROR; @@ -1909,8 +2177,8 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { parser->m_parseEndByteIndex += len; parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - parser->m_errorCode = parser->m_processor( - parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr); + parser->m_errorCode = callProcessor(parser, start, parser->m_parseEndPtr, + &parser->m_bufferPtr); if (parser->m_errorCode != XML_ERROR_NONE) { parser->m_eventEndPtr = parser->m_eventPtr; @@ -1955,10 +2223,14 @@ XML_GetBuffer(XML_Parser parser, int len) { default:; } - if (len > EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd)) { -#ifdef XML_CONTEXT_BYTES + // whether or not the request succeeds, `len` seems to be the app's preferred + // buffer fill size; remember it. + parser->m_lastBufferRequestSize = len; + if (len > EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd) + || parser->m_buffer == NULL) { +#if XML_CONTEXT_BYTES > 0 int keep; -#endif /* defined XML_CONTEXT_BYTES */ +#endif /* XML_CONTEXT_BYTES > 0 */ /* Do not invoke signed arithmetic overflow: */ int neededSize = (int)((unsigned)len + (unsigned)EXPAT_SAFE_PTR_DIFF( @@ -1967,15 +2239,21 @@ XML_GetBuffer(XML_Parser parser, int len) { parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; } -#ifdef XML_CONTEXT_BYTES +#if XML_CONTEXT_BYTES > 0 keep = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer); if (keep > XML_CONTEXT_BYTES) keep = XML_CONTEXT_BYTES; + /* Detect and prevent integer overflow */ + if (keep > INT_MAX - neededSize) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } neededSize += keep; -#endif /* defined XML_CONTEXT_BYTES */ - if (neededSize - <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { -#ifdef XML_CONTEXT_BYTES +#endif /* XML_CONTEXT_BYTES > 0 */ + if (parser->m_buffer && parser->m_bufferPtr + && neededSize + <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { +#if XML_CONTEXT_BYTES > 0 if (keep < EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer)) { int offset = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer) @@ -1988,19 +2266,17 @@ XML_GetBuffer(XML_Parser parser, int len) { parser->m_bufferPtr -= offset; } #else - if (parser->m_buffer && parser->m_bufferPtr) { - memmove(parser->m_buffer, parser->m_bufferPtr, - EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); - parser->m_bufferEnd - = parser->m_buffer - + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); - parser->m_bufferPtr = parser->m_buffer; - } -#endif /* not defined XML_CONTEXT_BYTES */ + memmove(parser->m_buffer, parser->m_bufferPtr, + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + parser->m_bufferPtr = parser->m_buffer; +#endif /* XML_CONTEXT_BYTES > 0 */ } else { char *newBuf; int bufferSize - = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferPtr); + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer); if (bufferSize == 0) bufferSize = INIT_BUFFER_SIZE; do { @@ -2017,7 +2293,7 @@ XML_GetBuffer(XML_Parser parser, int len) { return NULL; } parser->m_bufferLim = newBuf + bufferSize; -#ifdef XML_CONTEXT_BYTES +#if XML_CONTEXT_BYTES > 0 if (parser->m_bufferPtr) { memcpy(newBuf, &parser->m_bufferPtr[-keep], EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) @@ -2047,7 +2323,7 @@ XML_GetBuffer(XML_Parser parser, int len) { parser->m_bufferEnd = newBuf; } parser->m_bufferPtr = parser->m_buffer = newBuf; -#endif /* not defined XML_CONTEXT_BYTES */ +#endif /* XML_CONTEXT_BYTES > 0 */ } parser->m_eventPtr = parser->m_eventEndPtr = NULL; parser->m_positionPtr = NULL; @@ -2055,11 +2331,19 @@ XML_GetBuffer(XML_Parser parser, int len) { return parser->m_bufferEnd; } +static void +triggerReenter(XML_Parser parser) { + parser->m_reenter = XML_TRUE; +} + enum XML_Status XMLCALL XML_StopParser(XML_Parser parser, XML_Bool resumable) { if (parser == NULL) return XML_STATUS_ERROR; switch (parser->m_parsingStatus.parsing) { + case XML_INITIALIZED: + parser->m_errorCode = XML_ERROR_NOT_STARTED; + return XML_STATUS_ERROR; case XML_SUSPENDED: if (resumable) { parser->m_errorCode = XML_ERROR_SUSPENDED; @@ -2070,7 +2354,7 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable) { case XML_FINISHED: parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; - default: + case XML_PARSING: if (resumable) { #ifdef XML_DTD if (parser->m_isParamEntity) { @@ -2081,6 +2365,9 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable) { parser->m_parsingStatus.parsing = XML_SUSPENDED; } else parser->m_parsingStatus.parsing = XML_FINISHED; + break; + default: + assert(0); } return XML_STATUS_OK; } @@ -2097,7 +2384,7 @@ XML_ResumeParser(XML_Parser parser) { } parser->m_parsingStatus.parsing = XML_PARSING; - parser->m_errorCode = parser->m_processor( + parser->m_errorCode = callProcessor( parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); if (parser->m_errorCode != XML_ERROR_NONE) { @@ -2161,7 +2448,7 @@ XML_GetCurrentByteCount(XML_Parser parser) { const char *XMLCALL XML_GetInputContext(XML_Parser parser, int *offset, int *size) { -#ifdef XML_CONTEXT_BYTES +#if XML_CONTEXT_BYTES > 0 if (parser == NULL) return NULL; if (parser->m_eventPtr && parser->m_buffer) { @@ -2175,7 +2462,7 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size) { (void)parser; (void)offset; (void)size; -#endif /* defined XML_CONTEXT_BYTES */ +#endif /* XML_CONTEXT_BYTES > 0 */ return (const char *)0; } @@ -2337,6 +2624,17 @@ XML_ErrorString(enum XML_Error code) { /* Added in 2.2.5. */ case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */ return XML_L("invalid argument"); + /* Added in 2.3.0. */ + case XML_ERROR_NO_BUFFER: + return XML_L( + "a successful prior call to function XML_GetBuffer is required"); + /* Added in 2.4.0. */ + case XML_ERROR_AMPLIFICATION_LIMIT_BREACH: + return XML_L( + "limit on input amplification factor (from DTD and entities) breached"); + /* Added in 2.6.4. */ + case XML_ERROR_NOT_STARTED: + return XML_L("parser not started"); } return NULL; } @@ -2373,41 +2671,87 @@ XML_ExpatVersionInfo(void) { const XML_Feature *XMLCALL XML_GetFeatureList(void) { - static const XML_Feature features[] - = {{XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), - sizeof(XML_Char)}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), - sizeof(XML_LChar)}, + static const XML_Feature features[] = { + {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, #ifdef XML_UNICODE - {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, #endif #ifdef XML_UNICODE_WCHAR_T - {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, #endif #ifdef XML_DTD - {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, #endif -#ifdef XML_CONTEXT_BYTES - {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), - XML_CONTEXT_BYTES}, +#if XML_CONTEXT_BYTES > 0 + {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), + XML_CONTEXT_BYTES}, #endif #ifdef XML_MIN_SIZE - {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, #endif #ifdef XML_NS - {XML_FEATURE_NS, XML_L("XML_NS"), 0}, + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, #endif #ifdef XML_LARGE_SIZE - {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, + {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, #endif #ifdef XML_ATTR_INFO - {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, + {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, +#endif +#if XML_GE == 1 + /* Added in Expat 2.4.0 for XML_DTD defined and + * added in Expat 2.6.0 for XML_GE == 1. */ + {XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, + XML_L("XML_BLAP_MAX_AMP"), + (long int) + EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT}, + {XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT, + XML_L("XML_BLAP_ACT_THRES"), + EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT}, + /* Added in Expat 2.6.0. */ + {XML_FEATURE_GE, XML_L("XML_GE"), 0}, #endif - {XML_FEATURE_END, NULL, 0}}; + {XML_FEATURE_END, NULL, 0}}; return features; } +#if XML_GE == 1 +XML_Bool XMLCALL +XML_SetBillionLaughsAttackProtectionMaximumAmplification( + XML_Parser parser, float maximumAmplificationFactor) { + if ((parser == NULL) || (parser->m_parentParser != NULL) + || isnan(maximumAmplificationFactor) + || (maximumAmplificationFactor < 1.0f)) { + return XML_FALSE; + } + parser->m_accounting.maximumAmplificationFactor = maximumAmplificationFactor; + return XML_TRUE; +} + +XML_Bool XMLCALL +XML_SetBillionLaughsAttackProtectionActivationThreshold( + XML_Parser parser, unsigned long long activationThresholdBytes) { + if ((parser == NULL) || (parser->m_parentParser != NULL)) { + return XML_FALSE; + } + parser->m_accounting.activationThresholdBytes = activationThresholdBytes; + return XML_TRUE; +} +#endif /* XML_GE == 1 */ + +XML_Bool XMLCALL +XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled) { + if (parser != NULL && (enabled == XML_TRUE || enabled == XML_FALSE)) { + parser->m_reparseDeferralEnabled = enabled; + return XML_TRUE; + } + return XML_FALSE; +} + /* Initially tag->rawName always points into the parse buffer; for those TAG instances opened while the current parse buffer was processed, and not yet closed, we need to store tag->rawName in a more @@ -2419,6 +2763,7 @@ storeRawNames(XML_Parser parser) { while (tag) { int bufSize; int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1); + size_t rawNameLen; char *rawNameBuf = tag->buf + nameLen; /* Stop if already stored. Since m_tagStack is a stack, we can stop at the first entry that has already been copied; everything @@ -2427,10 +2772,14 @@ storeRawNames(XML_Parser parser) { */ if (tag->rawName == rawNameBuf) break; - /* For re-use purposes we need to ensure that the + /* For reuse purposes we need to ensure that the size of tag->buf is a multiple of sizeof(XML_Char). */ - bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); + rawNameLen = ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); + /* Detect and prevent integer overflow. */ + if (rawNameLen > (size_t)INT_MAX - nameLen) + return XML_FALSE; + bufSize = nameLen + (int)rawNameLen; if (bufSize > tag->bufEnd - tag->buf) { char *temp = (char *)REALLOC(parser, tag->buf, bufSize); if (temp == NULL) @@ -2460,9 +2809,10 @@ storeRawNames(XML_Parser parser) { static enum XML_Error PTRCALL contentProcessor(XML_Parser parser, const char *start, const char *end, const char **endPtr) { - enum XML_Error result - = doContent(parser, 0, parser->m_encoding, start, end, endPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer); + enum XML_Error result = doContent( + parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, start, end, + endPtr, (XML_Bool)! parser->m_parsingStatus.finalBuffer, + XML_ACCOUNT_DIRECT); if (result == XML_ERROR_NONE) { if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; @@ -2487,6 +2837,14 @@ externalEntityInitProcessor2(XML_Parser parser, const char *start, int tok = XmlContentTok(parser->m_encoding, start, end, &next); switch (tok) { case XML_TOK_BOM: +#if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, start, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif /* XML_GE == 1 */ + /* If we are at the end of the buffer, this would cause the next stage, i.e. externalEntityInitProcessor3, to pass control directly to doContent (by detecting XML_TOK_NONE) without processing any xml text @@ -2524,6 +2882,10 @@ externalEntityInitProcessor3(XML_Parser parser, const char *start, const char *next = start; /* XmlContentTok doesn't always set the last arg */ parser->m_eventPtr = start; tok = XmlContentTok(parser->m_encoding, start, end, &next); + /* Note: These bytes are accounted later in: + - processXmlDecl + - externalEntityContentProcessor + */ parser->m_eventEndPtr = next; switch (tok) { @@ -2538,6 +2900,11 @@ externalEntityInitProcessor3(XML_Parser parser, const char *start, return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; + case XML_PARSING: + if (parser->m_reenter) { + return XML_ERROR_UNEXPECTED_STATE; // LCOV_EXCL_LINE + } + /* Fall through */ default: start = next; } @@ -2565,7 +2932,8 @@ externalEntityContentProcessor(XML_Parser parser, const char *start, const char *end, const char **endPtr) { enum XML_Error result = doContent(parser, 1, parser->m_encoding, start, end, endPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer); + (XML_Bool)! parser->m_parsingStatus.finalBuffer, + XML_ACCOUNT_ENTITY_EXPANSION); if (result == XML_ERROR_NONE) { if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; @@ -2576,7 +2944,7 @@ externalEntityContentProcessor(XML_Parser parser, const char *start, static enum XML_Error doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, const char *s, const char *end, const char **nextPtr, - XML_Bool haveMore) { + XML_Bool haveMore, enum XML_Account account) { /* save one level of indirection */ DTD *const dtd = parser->m_dtd; @@ -2594,6 +2962,17 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, for (;;) { const char *next = s; /* XmlContentTok doesn't always set the last arg */ int tok = XmlContentTok(enc, s, end, &next); +#if XML_GE == 1 + const char *accountAfter + = ((tok == XML_TOK_TRAILING_RSQB) || (tok == XML_TOK_TRAILING_CR)) + ? (haveMore ? s /* i.e. 0 bytes */ : end) + : next; + if (! accountingDiffTolerated(parser, tok, s, accountAfter, __LINE__, + account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif *eventEndPP = next; switch (tok) { case XML_TOK_TRAILING_CR: @@ -2649,6 +3028,14 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, XML_Char ch = (XML_Char)XmlPredefinedEntityName( enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); if (ch) { +#if XML_GE == 1 + /* NOTE: We are replacing 4-6 characters original input for 1 character + * so there is no amplification and hence recording without + * protection. */ + accountingDiffTolerated(parser, tok, (char *)&ch, + ((char *)&ch) + sizeof(XML_Char), __LINE__, + XML_ACCOUNT_ENTITY_EXPANSION); +#endif /* XML_GE == 1 */ if (parser->m_characterDataHandler) parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1); else if (parser->m_defaultHandler) @@ -2691,7 +3078,7 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, reportDefault(parser, enc, s, next); break; } - result = processInternalEntity(parser, entity, XML_FALSE); + result = processEntity(parser, entity, XML_FALSE, ENTITY_INTERNAL); if (result != XML_ERROR_NONE) return result; } else if (parser->m_externalEntityRefHandler) { @@ -2767,7 +3154,8 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, } tag->name.str = (XML_Char *)tag->buf; *toPtr = XML_T('\0'); - result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); + result + = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings), account); if (result) return result; if (parser->m_startElementHandler) @@ -2791,7 +3179,8 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, if (! name.str) return XML_ERROR_NO_MEMORY; poolFinish(&parser->m_tempPool); - result = storeAtts(parser, enc, s, &name, &bindings); + result = storeAtts(parser, enc, s, &name, &bindings, + XML_ACCOUNT_NONE /* token spans whole start tag */); if (result != XML_ERROR_NONE) { freeBindings(parser, bindings); return result; @@ -2815,7 +3204,9 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, } if ((parser->m_tagLevel == 0) && (parser->m_parsingStatus.parsing != XML_FINISHED)) { - if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_SUSPENDED + || (parser->m_parsingStatus.parsing == XML_PARSING + && parser->m_reenter)) parser->m_processor = epilogProcessor; else return epilogProcessor(parser, next, end, nextPtr); @@ -2828,9 +3219,6 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, int len; const char *rawName; TAG *tag = parser->m_tagStack; - parser->m_tagStack = tag->parent; - tag->parent = parser->m_freeTagList; - parser->m_freeTagList = tag; rawName = s + enc->minBytesPerChar * 2; len = XmlNameLength(enc, rawName); if (len != tag->rawNameLength @@ -2838,6 +3226,9 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, *eventPP = rawName; return XML_ERROR_TAG_MISMATCH; } + parser->m_tagStack = tag->parent; + tag->parent = parser->m_freeTagList; + parser->m_freeTagList = tag; --parser->m_tagLevel; if (parser->m_endElementHandler) { const XML_Char *localPart; @@ -2847,13 +3238,13 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, if (parser->m_ns && localPart) { /* localPart and prefix may have been overwritten in tag->name.str, since this points to the binding->uri - buffer which gets re-used; so we have to add them again + buffer which gets reused; so we have to add them again */ uri = (XML_Char *)tag->name.str + tag->name.uriLen; /* don't need to check for space - already done in storeAtts() */ while (*localPart) *uri++ = *localPart++; - prefix = (XML_Char *)tag->name.prefix; + prefix = tag->name.prefix; if (parser->m_ns_triplets && prefix) { *uri++ = parser->m_namespaceSeparator; while (*prefix) @@ -2876,7 +3267,9 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, } if ((parser->m_tagLevel == 0) && (parser->m_parsingStatus.parsing != XML_FINISHED)) { - if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_SUSPENDED + || (parser->m_parsingStatus.parsing == XML_PARSING + && parser->m_reenter)) parser->m_processor = epilogProcessor; else return epilogProcessor(parser, next, end, nextPtr); @@ -2920,13 +3313,14 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, However, now we have a start/endCdataSectionHandler, so it seems easier to let the user deal with this. */ - else if (0 && parser->m_characterDataHandler) + else if ((0) && parser->m_characterDataHandler) parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0); /* END disabled code */ else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); - result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); + result + = doCdataSection(parser, enc, &next, end, nextPtr, haveMore, account); if (result != XML_ERROR_NONE) return result; else if (! next) { @@ -2948,8 +3342,8 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); } else parser->m_characterDataHandler( - parser->m_handlerArg, (XML_Char *)s, - (int)((XML_Char *)end - (XML_Char *)s)); + parser->m_handlerArg, (const XML_Char *)s, + (int)((const XML_Char *)end - (const XML_Char *)s)); } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, end); /* We are at the end of the final buffer, should we check for @@ -2982,8 +3376,8 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, *eventPP = s; } } else - charDataHandler(parser->m_handlerArg, (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); + charDataHandler(parser->m_handlerArg, (const XML_Char *)s, + (int)((const XML_Char *)next - (const XML_Char *)s)); } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); } break; @@ -3008,14 +3402,22 @@ doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, break; /* LCOV_EXCL_STOP */ } - *eventPP = s = next; switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: + *eventPP = next; *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: + *eventPP = next; return XML_ERROR_ABORTED; + case XML_PARSING: + if (parser->m_reenter) { + *nextPtr = next; + return XML_ERROR_NONE; + } + /* Fall through */ default:; + *eventPP = s = next; } } /* not reached */ @@ -3055,7 +3457,8 @@ freeBindings(XML_Parser parser, BINDING *bindings) { */ static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, - TAG_NAME *tagNamePtr, BINDING **bindingsPtr) { + TAG_NAME *tagNamePtr, BINDING **bindingsPtr, + enum XML_Account account) { DTD *const dtd = parser->m_dtd; /* save one level of indirection */ ELEMENT_TYPE *elementType; int nDefaultAtts; @@ -3087,13 +3490,38 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, /* get the attributes from the tokenizer */ n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts); + + /* Detect and prevent integer overflow */ + if (n > INT_MAX - nDefaultAtts) { + return XML_ERROR_NO_MEMORY; + } + if (n + nDefaultAtts > parser->m_attsSize) { int oldAttsSize = parser->m_attsSize; ATTRIBUTE *temp; #ifdef XML_ATTR_INFO XML_AttrInfo *temp2; #endif + + /* Detect and prevent integer overflow */ + if ((nDefaultAtts > INT_MAX - INIT_ATTS_SIZE) + || (n > INT_MAX - (nDefaultAtts + INIT_ATTS_SIZE))) { + return XML_ERROR_NO_MEMORY; + } + parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(ATTRIBUTE)) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } +#endif + temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, parser->m_attsSize * sizeof(ATTRIBUTE)); if (temp == NULL) { @@ -3102,6 +3530,17 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, } parser->m_atts = temp; #ifdef XML_ATTR_INFO + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +# if UINT_MAX >= SIZE_MAX + if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(XML_AttrInfo)) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } +# endif + temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, parser->m_attsSize * sizeof(XML_AttrInfo)); if (temp2 == NULL) { @@ -3165,7 +3604,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, /* normalize the attribute value */ result = storeAttributeValue( parser, enc, isCdata, parser->m_atts[i].valuePtr, - parser->m_atts[i].valueEnd, &parser->m_tempPool); + parser->m_atts[i].valueEnd, &parser->m_tempPool, account); if (result) return result; appAtts[attIndex] = poolStart(&parser->m_tempPool); @@ -3240,7 +3679,13 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, if (nPrefixes) { int j; /* hash table index */ unsigned long version = parser->m_nsAttsVersion; - int nsAttsSize = (int)1 << parser->m_nsAttsPower; + + /* Detect and prevent invalid shift */ + if (parser->m_nsAttsPower >= sizeof(unsigned int) * 8 /* bits per byte */) { + return XML_ERROR_NO_MEMORY; + } + + unsigned int nsAttsSize = 1u << parser->m_nsAttsPower; unsigned char oldNsAttsPower = parser->m_nsAttsPower; /* size of hash table must be at least 2 * (# of prefixed attributes) */ if ((nPrefixes << 1) @@ -3251,7 +3696,28 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, ; if (parser->m_nsAttsPower < 3) parser->m_nsAttsPower = 3; - nsAttsSize = (int)1 << parser->m_nsAttsPower; + + /* Detect and prevent invalid shift */ + if (parser->m_nsAttsPower >= sizeof(nsAttsSize) * 8 /* bits per byte */) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; + return XML_ERROR_NO_MEMORY; + } + + nsAttsSize = 1u << parser->m_nsAttsPower; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (nsAttsSize > (size_t)(-1) / sizeof(NS_ATT)) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; + return XML_ERROR_NO_MEMORY; + } +#endif + temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, nsAttsSize * sizeof(NS_ATT)); if (! temp) { @@ -3409,9 +3875,31 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, tagNamePtr->prefixLen = prefixLen; for (i = 0; localPart[i++];) ; /* i includes null terminator */ + + /* Detect and prevent integer overflow */ + if (binding->uriLen > INT_MAX - prefixLen + || i > INT_MAX - (binding->uriLen + prefixLen)) { + return XML_ERROR_NO_MEMORY; + } + n = i + binding->uriLen + prefixLen; if (n > binding->uriAlloc) { TAG *p; + + /* Detect and prevent integer overflow */ + if (n > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(n + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char)); if (! uri) return XML_ERROR_NO_MEMORY; @@ -3436,12 +3924,124 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, return XML_ERROR_NONE; } +static XML_Bool +is_rfc3986_uri_char(XML_Char candidate) { + // For the RFC 3986 ANBF grammar see + // https://datatracker.ietf.org/doc/html/rfc3986#appendix-A + + switch (candidate) { + // From rule "ALPHA" (uppercase half) + case 'A': + case 'B': + case 'C': + case 'D': + case 'E': + case 'F': + case 'G': + case 'H': + case 'I': + case 'J': + case 'K': + case 'L': + case 'M': + case 'N': + case 'O': + case 'P': + case 'Q': + case 'R': + case 'S': + case 'T': + case 'U': + case 'V': + case 'W': + case 'X': + case 'Y': + case 'Z': + + // From rule "ALPHA" (lowercase half) + case 'a': + case 'b': + case 'c': + case 'd': + case 'e': + case 'f': + case 'g': + case 'h': + case 'i': + case 'j': + case 'k': + case 'l': + case 'm': + case 'n': + case 'o': + case 'p': + case 'q': + case 'r': + case 's': + case 't': + case 'u': + case 'v': + case 'w': + case 'x': + case 'y': + case 'z': + + // From rule "DIGIT" + case '0': + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + + // From rule "pct-encoded" + case '%': + + // From rule "unreserved" + case '-': + case '.': + case '_': + case '~': + + // From rule "gen-delims" + case ':': + case '/': + case '?': + case '#': + case '[': + case ']': + case '@': + + // From rule "sub-delims" + case '!': + case '$': + case '&': + case '\'': + case '(': + case ')': + case '*': + case '+': + case ',': + case ';': + case '=': + return XML_TRUE; + + default: + return XML_FALSE; + } +} + /* addBinding() overwrites the value of prefix->binding without checking. Therefore one must keep track of the old value outside of addBinding(). */ static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr) { + // "http://www.w3.org/XML/1998/namespace" static const XML_Char xmlNamespace[] = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, @@ -3452,6 +4052,7 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0'}; static const int xmlLen = (int)sizeof(xmlNamespace) / sizeof(XML_Char) - 1; + // "http://www.w3.org/2000/xmlns/" static const XML_Char xmlnsNamespace[] = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, @@ -3491,6 +4092,29 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (! mustBeXML && isXMLNS && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) isXMLNS = XML_FALSE; + + // NOTE: While Expat does not validate namespace URIs against RFC 3986 + // today (and is not REQUIRED to do so with regard to the XML 1.0 + // namespaces specification) we have to at least make sure, that + // the application on top of Expat (that is likely splitting expanded + // element names ("qualified names") of form + // "[uri sep] local [sep prefix] '\0'" back into 1, 2 or 3 pieces + // in its element handler code) cannot be confused by an attacker + // putting additional namespace separator characters into namespace + // declarations. That would be ambiguous and not to be expected. + // + // While the HTML API docs of function XML_ParserCreateNS have been + // advising against use of a namespace separator character that can + // appear in a URI for >20 years now, some widespread applications + // are using URI characters (':' (colon) in particular) for a + // namespace separator, in practice. To keep these applications + // functional, we only reject namespaces URIs containing the + // application-chosen namespace separator if the chosen separator + // is a non-URI character with regard to RFC 3986. + if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator) + && ! is_rfc3986_uri_char(uri[len])) { + return XML_ERROR_SYNTAX; + } } isXML = isXML && len == xmlLen; isXMLNS = isXMLNS && len == xmlnsLen; @@ -3507,6 +4131,21 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (parser->m_freeBindingList) { b = parser->m_freeBindingList; if (len > b->uriAlloc) { + /* Detect and prevent integer overflow */ + if (len > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + XML_Char *temp = (XML_Char *)REALLOC( parser, b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE)); if (temp == NULL) @@ -3519,6 +4158,21 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, b = (BINDING *)MALLOC(parser, sizeof(BINDING)); if (! b) return XML_ERROR_NO_MEMORY; + + /* Detect and prevent integer overflow */ + if (len > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + b->uri = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE)); if (! b->uri) { @@ -3554,9 +4208,9 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, static enum XML_Error PTRCALL cdataSectionProcessor(XML_Parser parser, const char *start, const char *end, const char **endPtr) { - enum XML_Error result - = doCdataSection(parser, parser->m_encoding, &start, end, endPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer); + enum XML_Error result = doCdataSection( + parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_ACCOUNT_DIRECT); if (result != XML_ERROR_NONE) return result; if (start) { @@ -3576,7 +4230,8 @@ cdataSectionProcessor(XML_Parser parser, const char *start, const char *end, */ static enum XML_Error doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, - const char *end, const char **nextPtr, XML_Bool haveMore) { + const char *end, const char **nextPtr, XML_Bool haveMore, + enum XML_Account account) { const char *s = *startPtr; const char **eventPP; const char **eventEndPP; @@ -3594,6 +4249,14 @@ doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, for (;;) { const char *next = s; /* in case of XML_TOK_NONE or XML_TOK_PARTIAL */ int tok = XmlCdataSectionTok(enc, s, end, &next); +#if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#else + UNUSED_P(account); +#endif *eventEndPP = next; switch (tok) { case XML_TOK_CDATA_SECT_CLOSE: @@ -3601,7 +4264,7 @@ doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, parser->m_endCdataSectionHandler(parser->m_handlerArg); /* BEGIN disabled code */ /* see comment under XML_TOK_CDATA_SECT_OPEN */ - else if (0 && parser->m_characterDataHandler) + else if ((0) && parser->m_characterDataHandler) parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0); /* END disabled code */ @@ -3637,8 +4300,8 @@ doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, *eventPP = s; } } else - charDataHandler(parser->m_handlerArg, (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); + charDataHandler(parser->m_handlerArg, (const XML_Char *)s, + (int)((const XML_Char *)next - (const XML_Char *)s)); } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); } break; @@ -3671,14 +4334,21 @@ doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, /* LCOV_EXCL_STOP */ } - *eventPP = s = next; switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: + *eventPP = next; *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: + *eventPP = next; return XML_ERROR_ABORTED; + case XML_PARSING: + if (parser->m_reenter) { + return XML_ERROR_UNEXPECTED_STATE; // LCOV_EXCL_LINE + } + /* Fall through */ default:; + *eventPP = s = next; } } /* not reached */ @@ -3738,6 +4408,13 @@ doIgnoreSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, *eventPP = s; *startPtr = NULL; tok = XmlIgnoreSectionTok(enc, s, end, &next); +# if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +# endif *eventEndPP = next; switch (tok) { case XML_TOK_IGNORE_SECT: @@ -3787,7 +4464,7 @@ initializeEncoding(XML_Parser parser) { const char *s; #ifdef XML_UNICODE char encodingBuf[128]; - /* See comments abount `protoclEncodingName` in parserInit() */ + /* See comments about `protocolEncodingName` in parserInit() */ if (! parser->m_protocolEncodingName) s = NULL; else { @@ -3819,9 +4496,18 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *s, const XML_Char *storedEncName = NULL; const ENCODING *newEncoding = NULL; const char *version = NULL; - const char *versionend; + const char *versionend = NULL; const XML_Char *storedversion = NULL; int standalone = -1; + +#if XML_GE == 1 + if (! accountingDiffTolerated(parser, XML_TOK_XML_DECL, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif + if (! (parser->m_ns ? XmlParseXmlDeclNS : XmlParseXmlDecl)( isGeneralTextEntity, parser->m_encoding, s, next, &parser->m_eventPtr, &version, &versionend, &encodingName, &newEncoding, &standalone)) { @@ -3971,6 +4657,10 @@ entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, for (;;) { tok = XmlPrologTok(parser->m_encoding, start, end, &next); + /* Note: Except for XML_TOK_BOM below, these bytes are accounted later in: + - storeEntityValue + - processXmlDecl + */ parser->m_eventEndPtr = next; if (tok <= 0) { if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { @@ -3989,7 +4679,8 @@ entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, break; } /* found end of entity value - can store it now */ - return storeEntityValue(parser, parser->m_encoding, s, end); + return storeEntityValue(parser, parser->m_encoding, s, end, + XML_ACCOUNT_DIRECT, NULL); } else if (tok == XML_TOK_XML_DECL) { enum XML_Error result; result = processXmlDecl(parser, 0, start, next); @@ -4007,17 +4698,25 @@ entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, parser->m_processor = entityValueProcessor; return entityValueProcessor(parser, next, end, nextPtr); } - /* If we are at the end of the buffer, this would cause XmlPrologTok to - return XML_TOK_NONE on the next call, which would then cause the - function to exit with *nextPtr set to s - that is what we want for other - tokens, but not for the BOM - we would rather like to skip it; - then, when this routine is entered the next time, XmlPrologTok will - return XML_TOK_INVALID, since the BOM is still in the buffer + /* XmlPrologTok has now set the encoding based on the BOM it found, and we + must move s and nextPtr forward to consume the BOM. + + If we didn't, and got XML_TOK_NONE from the next XmlPrologTok call, we + would leave the BOM in the buffer and return. On the next call to this + function, our XmlPrologTok call would return XML_TOK_INVALID, since it + is not valid to have multiple BOMs. */ - else if (tok == XML_TOK_BOM && next == end - && ! parser->m_parsingStatus.finalBuffer) { + else if (tok == XML_TOK_BOM) { +# if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +# endif + *nextPtr = next; - return XML_ERROR_NONE; + s = next; } /* If we get this token, we have the start of what might be a normal tag, but not a declaration (i.e. it doesn't begin with @@ -4058,16 +4757,24 @@ externalParEntProcessor(XML_Parser parser, const char *s, const char *end, } /* This would cause the next stage, i.e. doProlog to be passed XML_TOK_BOM. However, when parsing an external subset, doProlog will not accept a BOM - as valid, and report a syntax error, so we have to skip the BOM + as valid, and report a syntax error, so we have to skip the BOM, and + account for the BOM bytes. */ else if (tok == XML_TOK_BOM) { + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } + s = next; tok = XmlPrologTok(parser->m_encoding, s, end, &next); } parser->m_processor = prologProcessor; return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE, + XML_ACCOUNT_DIRECT); } static enum XML_Error PTRCALL @@ -4080,6 +4787,9 @@ entityValueProcessor(XML_Parser parser, const char *s, const char *end, for (;;) { tok = XmlPrologTok(enc, start, end, &next); + /* Note: These bytes are accounted later in: + - storeEntityValue + */ if (tok <= 0) { if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; @@ -4097,7 +4807,7 @@ entityValueProcessor(XML_Parser parser, const char *s, const char *end, break; } /* found end of entity value - can store it now */ - return storeEntityValue(parser, enc, s, end); + return storeEntityValue(parser, enc, s, end, XML_ACCOUNT_DIRECT, NULL); } start = next; } @@ -4111,13 +4821,14 @@ prologProcessor(XML_Parser parser, const char *s, const char *end, const char *next = s; int tok = XmlPrologTok(parser->m_encoding, s, end, &next); return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE, + XML_ACCOUNT_DIRECT); } static enum XML_Error doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, int tok, const char *next, const char **nextPtr, XML_Bool haveMore, - XML_Bool allowClosingDoctype) { + XML_Bool allowClosingDoctype, enum XML_Account account) { #ifdef XML_DTD static const XML_Char externalSubsetName[] = {ASCII_HASH, '\0'}; #endif /* XML_DTD */ @@ -4144,6 +4855,10 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, static const XML_Char enumValueSep[] = {ASCII_PIPE, '\0'}; static const XML_Char enumValueStart[] = {ASCII_LPAREN, '\0'}; +#ifndef XML_DTD + UNUSED_P(account); +#endif + /* save one level of indirection */ DTD *const dtd = parser->m_dtd; @@ -4208,6 +4923,21 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, } } role = XmlTokenRole(&parser->m_prologState, tok, s, next, enc); +#if XML_GE == 1 + switch (role) { + case XML_ROLE_INSTANCE_START: // bytes accounted in contentProcessor + case XML_ROLE_XML_DECL: // bytes accounted in processXmlDecl +# ifdef XML_DTD + case XML_ROLE_TEXT_DECL: // bytes accounted in processXmlDecl +# endif + break; + default: + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } + } +#endif switch (role) { case XML_ROLE_XML_DECL: { enum XML_Error result = processXmlDecl(parser, 0, s, next); @@ -4472,10 +5202,10 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, parser->m_handlerArg, parser->m_declElementType->name, parser->m_declAttributeId->name, parser->m_declAttributeType, 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); - poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } } + poolClear(&parser->m_tempPool); break; case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: case XML_ROLE_FIXED_ATTRIBUTE_VALUE: @@ -4483,7 +5213,8 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, const XML_Char *attVal; enum XML_Error result = storeAttributeValue( parser, enc, parser->m_declAttributeIsCdata, - s + enc->minBytesPerChar, next - enc->minBytesPerChar, &dtd->pool); + s + enc->minBytesPerChar, next - enc->minBytesPerChar, &dtd->pool, + XML_ACCOUNT_NONE); if (result) return result; attVal = poolStart(&dtd->pool); @@ -4516,8 +5247,12 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, break; case XML_ROLE_ENTITY_VALUE: if (dtd->keepProcessing) { - enum XML_Error result = storeEntityValue( - parser, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); +#if XML_GE == 1 + // This will store the given replacement text in + // parser->m_declEntity->textPtr. + enum XML_Error result = callStoreEntityValue( + parser, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar, + XML_ACCOUNT_NONE); if (parser->m_declEntity) { parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool); parser->m_declEntity->textLen @@ -4535,6 +5270,25 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, poolDiscard(&dtd->entityValuePool); if (result != XML_ERROR_NONE) return result; +#else + // This will store "&entity123;" in parser->m_declEntity->textPtr + // to end up as "&entity123;" in the handler. + if (parser->m_declEntity != NULL) { + const enum XML_Error result + = storeSelfEntityValue(parser, parser->m_declEntity); + if (result != XML_ERROR_NONE) + return result; + + if (parser->m_entityDeclHandler) { + *eventEndPP = s; + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, parser->m_declEntity->textPtr, + parser->m_declEntity->textLen, parser->m_curBase, 0, 0, 0); + handleDefault = XML_FALSE; + } + } +#endif } break; case XML_ROLE_DOCTYPE_SYSTEM_ID: @@ -4593,6 +5347,16 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, } break; case XML_ROLE_ENTITY_COMPLETE: +#if XML_GE == 0 + // This will store "&entity123;" in entity->textPtr + // to end up as "&entity123;" in the handler. + if (parser->m_declEntity != NULL) { + const enum XML_Error result + = storeSelfEntityValue(parser, parser->m_declEntity); + if (result != XML_ERROR_NONE) + return result; + } +#endif if (dtd->keepProcessing && parser->m_declEntity && parser->m_entityDeclHandler) { *eventEndPP = s; @@ -4776,6 +5540,11 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, if (parser->m_prologState.level >= parser->m_groupSize) { if (parser->m_groupSize) { { + /* Detect and prevent integer overflow */ + if (parser->m_groupSize > (unsigned int)(-1) / 2u) { + return XML_ERROR_NO_MEMORY; + } + char *const new_connector = (char *)REALLOC( parser, parser->m_groupConnector, parser->m_groupSize *= 2); if (new_connector == NULL) { @@ -4786,6 +5555,16 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, } if (dtd->scaffIndex) { + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (parser->m_groupSize > (size_t)(-1) / sizeof(int)) { + return XML_ERROR_NO_MEMORY; + } +#endif + int *const new_scaff_index = (int *)REALLOC( parser, dtd->scaffIndex, parser->m_groupSize * sizeof(int)); if (new_scaff_index == NULL) @@ -4866,7 +5645,7 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, * * If 'standalone' is false, the DTD must have no * parameter entities or we wouldn't have passed the outer - * 'if' statement. That measn the only entity in the hash + * 'if' statement. That means the only entity in the hash * table is the external subset name "#" which cannot be * given as a parameter entity name in XML syntax, so the * lookup must have returned NULL and we don't even reach @@ -4898,7 +5677,7 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, enum XML_Error result; XML_Bool betweenDecl = (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); - result = processInternalEntity(parser, entity, betweenDecl); + result = processEntity(parser, entity, betweenDecl, ENTITY_INTERNAL); if (result != XML_ERROR_NONE) return result; handleDefault = XML_FALSE; @@ -4907,12 +5686,15 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; + entityTrackingOnOpen(parser, entity, __LINE__); if (! parser->m_externalEntityRefHandler( parser->m_externalEntityRefHandlerArg, 0, entity->base, entity->systemId, entity->publicId)) { + entityTrackingOnClose(parser, entity, __LINE__); entity->open = XML_FALSE; return XML_ERROR_EXTERNAL_ENTITY_HANDLING; } + entityTrackingOnClose(parser, entity, __LINE__); entity->open = XML_FALSE; handleDefault = XML_FALSE; if (! dtd->paramEntityRead) { @@ -4991,7 +5773,7 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, if (dtd->in_eldecl) { ELEMENT_TYPE *el; const XML_Char *name; - int nameLen; + size_t nameLen; const char *nxt = (quant == XML_CQUANT_NONE ? next : next - enc->minBytesPerChar); int myindex = nextScaffoldPart(parser); @@ -5007,7 +5789,13 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, nameLen = 0; for (; name[nameLen++];) ; - dtd->contentStringLen += nameLen; + + /* Detect and prevent integer overflow */ + if (nameLen > UINT_MAX - dtd->contentStringLen) { + return XML_ERROR_NO_MEMORY; + } + + dtd->contentStringLen += (unsigned)nameLen; if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } @@ -5094,6 +5882,12 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; + case XML_PARSING: + if (parser->m_reenter) { + *nextPtr = next; + return XML_ERROR_NONE; + } + /* Fall through */ default: s = next; tok = XmlPrologTok(enc, s, end, &next); @@ -5110,6 +5904,13 @@ epilogProcessor(XML_Parser parser, const char *s, const char *end, for (;;) { const char *next = NULL; int tok = XmlPrologTok(parser->m_encoding, s, end, &next); +#if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif parser->m_eventEndPtr = next; switch (tok) { /* report partial linebreak - it might be the last token */ @@ -5154,28 +5955,58 @@ epilogProcessor(XML_Parser parser, const char *s, const char *end, default: return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; } - parser->m_eventPtr = s = next; switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: + parser->m_eventPtr = next; *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: + parser->m_eventPtr = next; return XML_ERROR_ABORTED; + case XML_PARSING: + if (parser->m_reenter) { + return XML_ERROR_UNEXPECTED_STATE; // LCOV_EXCL_LINE + } + /* Fall through */ default:; + parser->m_eventPtr = s = next; } } } static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl) { - const char *textStart, *textEnd; - const char *next; - enum XML_Error result; - OPEN_INTERNAL_ENTITY *openEntity; +processEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl, + enum EntityType type) { + OPEN_INTERNAL_ENTITY *openEntity, **openEntityList, **freeEntityList; + switch (type) { + case ENTITY_INTERNAL: + parser->m_processor = internalEntityProcessor; + openEntityList = &parser->m_openInternalEntities; + freeEntityList = &parser->m_freeInternalEntities; + break; + case ENTITY_ATTRIBUTE: + openEntityList = &parser->m_openAttributeEntities; + freeEntityList = &parser->m_freeAttributeEntities; + break; + case ENTITY_VALUE: + openEntityList = &parser->m_openValueEntities; + freeEntityList = &parser->m_freeValueEntities; + break; + /* default case serves merely as a safety net in case of a + * wrong entityType. Therefore we exclude the following lines + * from the test coverage. + * + * LCOV_EXCL_START + */ + default: + // Should not reach here + assert(0); + /* LCOV_EXCL_STOP */ + } - if (parser->m_freeInternalEntities) { - openEntity = parser->m_freeInternalEntities; - parser->m_freeInternalEntities = openEntity->next; + if (*freeEntityList) { + openEntity = *freeEntityList; + *freeEntityList = openEntity->next; } else { openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY)); @@ -5183,48 +6014,34 @@ processInternalEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl) { return XML_ERROR_NO_MEMORY; } entity->open = XML_TRUE; + entity->hasMore = XML_TRUE; +#if XML_GE == 1 + entityTrackingOnOpen(parser, entity, __LINE__); +#endif entity->processed = 0; - openEntity->next = parser->m_openInternalEntities; - parser->m_openInternalEntities = openEntity; + openEntity->next = *openEntityList; + *openEntityList = openEntity; openEntity->entity = entity; + openEntity->type = type; openEntity->startTagLevel = parser->m_tagLevel; openEntity->betweenDecl = betweenDecl; openEntity->internalEventPtr = NULL; openEntity->internalEventEndPtr = NULL; - textStart = (const char *)entity->textPtr; - textEnd = (const char *)(entity->textPtr + entity->textLen); - /* Set a safe default value in case 'next' does not get set */ - next = textStart; - -#ifdef XML_DTD - if (entity->is_param) { - int tok - = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, - tok, next, &next, XML_FALSE, XML_FALSE); - } else -#endif /* XML_DTD */ - result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, - textStart, textEnd, &next, XML_FALSE); - if (result == XML_ERROR_NONE) { - if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) { - entity->processed = (int)(next - textStart); - parser->m_processor = internalEntityProcessor; - } else { - entity->open = XML_FALSE; - parser->m_openInternalEntities = openEntity->next; - /* put openEntity back in list of free instances */ - openEntity->next = parser->m_freeInternalEntities; - parser->m_freeInternalEntities = openEntity; - } + // Only internal entities make use of the reenter flag + // therefore no need to set it for other entity types + if (type == ENTITY_INTERNAL) { + triggerReenter(parser); } - return result; + return XML_ERROR_NONE; } static enum XML_Error PTRCALL internalEntityProcessor(XML_Parser parser, const char *s, const char *end, const char **nextPtr) { + UNUSED_P(s); + UNUSED_P(end); + UNUSED_P(nextPtr); ENTITY *entity; const char *textStart, *textEnd; const char *next; @@ -5234,53 +6051,67 @@ internalEntityProcessor(XML_Parser parser, const char *s, const char *end, return XML_ERROR_UNEXPECTED_STATE; entity = openEntity->entity; - textStart = ((const char *)entity->textPtr) + entity->processed; - textEnd = (const char *)(entity->textPtr + entity->textLen); - /* Set a safe default value in case 'next' does not get set */ - next = textStart; -#ifdef XML_DTD - if (entity->is_param) { - int tok - = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, - tok, next, &next, XML_FALSE, XML_TRUE); - } else -#endif /* XML_DTD */ - result = doContent(parser, openEntity->startTagLevel, - parser->m_internalEncoding, textStart, textEnd, &next, - XML_FALSE); + // This will return early + if (entity->hasMore) { + textStart = ((const char *)entity->textPtr) + entity->processed; + textEnd = (const char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + next = textStart; + + if (entity->is_param) { + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_FALSE, + XML_ACCOUNT_ENTITY_EXPANSION); + } else { + result = doContent(parser, openEntity->startTagLevel, + parser->m_internalEncoding, textStart, textEnd, &next, + XML_FALSE, XML_ACCOUNT_ENTITY_EXPANSION); + } - if (result != XML_ERROR_NONE) - return result; - else if (textEnd != next - && parser->m_parsingStatus.parsing == XML_SUSPENDED) { - entity->processed = (int)(next - (const char *)entity->textPtr); + if (result != XML_ERROR_NONE) + return result; + // Check if entity is complete, if not, mark down how much of it is + // processed + if (textEnd != next + && (parser->m_parsingStatus.parsing == XML_SUSPENDED + || (parser->m_parsingStatus.parsing == XML_PARSING + && parser->m_reenter))) { + entity->processed = (int)(next - (const char *)entity->textPtr); + return result; + } + + // Entity is complete. We cannot close it here since we need to first + // process its possible inner entities (which are added to the + // m_openInternalEntities during doProlog or doContent calls above) + entity->hasMore = XML_FALSE; + triggerReenter(parser); return result; - } else { - entity->open = XML_FALSE; - parser->m_openInternalEntities = openEntity->next; - /* put openEntity back in list of free instances */ - openEntity->next = parser->m_freeInternalEntities; - parser->m_freeInternalEntities = openEntity; - } + } // End of entity processing, "if" block will return here -#ifdef XML_DTD - if (entity->is_param) { - int tok; - parser->m_processor = prologProcessor; - tok = XmlPrologTok(parser->m_encoding, s, end, &next); - return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); - } else -#endif /* XML_DTD */ - { - parser->m_processor = contentProcessor; - /* see externalEntityContentProcessor vs contentProcessor */ - return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, - s, end, nextPtr, - (XML_Bool)! parser->m_parsingStatus.finalBuffer); + // Remove fully processed openEntity from open entity list. +#if XML_GE == 1 + entityTrackingOnClose(parser, entity, __LINE__); +#endif + // openEntity is m_openInternalEntities' head, as we set it at the start of + // this function and we skipped doProlog and doContent calls with hasMore set + // to false. This means we can directly remove the head of + // m_openInternalEntities + assert(parser->m_openInternalEntities == openEntity); + entity->open = XML_FALSE; + parser->m_openInternalEntities = parser->m_openInternalEntities->next; + + /* put openEntity back in list of free instances */ + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; + + if (parser->m_openInternalEntities == NULL) { + parser->m_processor = entity->is_param ? prologProcessor : contentProcessor; } + triggerReenter(parser); + return XML_ERROR_NONE; } static enum XML_Error PTRCALL @@ -5294,9 +6125,72 @@ errorProcessor(XML_Parser parser, const char *s, const char *end, static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, STRING_POOL *pool) { - enum XML_Error result - = appendAttributeValue(parser, enc, isCdata, ptr, end, pool); + const char *ptr, const char *end, STRING_POOL *pool, + enum XML_Account account) { + const char *next = ptr; + enum XML_Error result = XML_ERROR_NONE; + + while (1) { + if (! parser->m_openAttributeEntities) { + result = appendAttributeValue(parser, enc, isCdata, next, end, pool, + account, &next); + } else { + OPEN_INTERNAL_ENTITY *const openEntity = parser->m_openAttributeEntities; + if (! openEntity) + return XML_ERROR_UNEXPECTED_STATE; + + ENTITY *const entity = openEntity->entity; + const char *const textStart + = ((const char *)entity->textPtr) + entity->processed; + const char *const textEnd + = (const char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + const char *nextInEntity = textStart; + if (entity->hasMore) { + result = appendAttributeValue( + parser, parser->m_internalEncoding, isCdata, textStart, textEnd, + pool, XML_ACCOUNT_ENTITY_EXPANSION, &nextInEntity); + if (result != XML_ERROR_NONE) + break; + // Check if entity is complete, if not, mark down how much of it is + // processed. A XML_SUSPENDED check here is not required as + // appendAttributeValue will never suspend the parser. + if (textEnd != nextInEntity) { + entity->processed + = (int)(nextInEntity - (const char *)entity->textPtr); + continue; + } + + // Entity is complete. We cannot close it here since we need to first + // process its possible inner entities (which are added to the + // m_openAttributeEntities during appendAttributeValue) + entity->hasMore = XML_FALSE; + continue; + } // End of entity processing, "if" block skips the rest + + // Remove fully processed openEntity from open entity list. +#if XML_GE == 1 + entityTrackingOnClose(parser, entity, __LINE__); +#endif + // openEntity is m_openAttributeEntities' head, since we set it at the + // start of this function and because we skipped appendAttributeValue call + // with hasMore set to false. This means we can directly remove the head + // of m_openAttributeEntities + assert(parser->m_openAttributeEntities == openEntity); + entity->open = XML_FALSE; + parser->m_openAttributeEntities = parser->m_openAttributeEntities->next; + + /* put openEntity back in list of free instances */ + openEntity->next = parser->m_freeAttributeEntities; + parser->m_freeAttributeEntities = openEntity; + } + + // Break if an error occurred or there is nothing left to process + if (result || (parser->m_openAttributeEntities == NULL && end == next)) { + break; + } + } + if (result) return result; if (! isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) @@ -5308,13 +6202,28 @@ storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, STRING_POOL *pool) { + const char *ptr, const char *end, STRING_POOL *pool, + enum XML_Account account, const char **nextPtr) { DTD *const dtd = parser->m_dtd; /* save one level of indirection */ +#ifndef XML_DTD + UNUSED_P(account); +#endif + for (;;) { - const char *next; + const char *next + = ptr; /* XmlAttributeValueTok doesn't always set the last arg */ int tok = XmlAttributeValueTok(enc, ptr, end, &next); +#if XML_GE == 1 + if (! accountingDiffTolerated(parser, tok, ptr, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif switch (tok) { case XML_TOK_NONE: + if (nextPtr) { + *nextPtr = next; + } return XML_ERROR_NONE; case XML_TOK_INVALID: if (enc == parser->m_encoding) @@ -5372,6 +6281,14 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, XML_Char ch = (XML_Char)XmlPredefinedEntityName( enc, ptr + enc->minBytesPerChar, next - enc->minBytesPerChar); if (ch) { +#if XML_GE == 1 + /* NOTE: We are replacing 4-6 characters original input for 1 character + * so there is no amplification and hence recording without + * protection. */ + accountingDiffTolerated(parser, tok, (char *)&ch, + ((char *)&ch) + sizeof(XML_Char), __LINE__, + XML_ACCOUNT_ENTITY_EXPANSION); +#endif /* XML_GE == 1 */ if (! poolAppendChar(pool, ch)) return XML_ERROR_NO_MEMORY; break; @@ -5447,14 +6364,11 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; } else { enum XML_Error result; - const XML_Char *textEnd = entity->textPtr + entity->textLen; - entity->open = XML_TRUE; - result = appendAttributeValue(parser, parser->m_internalEncoding, - isCdata, (const char *)entity->textPtr, - (const char *)textEnd, pool); - entity->open = XML_FALSE; - if (result) - return result; + result = processEntity(parser, entity, XML_FALSE, ENTITY_ATTRIBUTE); + if ((result == XML_ERROR_NONE) && (nextPtr != NULL)) { + *nextPtr = next; + } + return result; } } break; default: @@ -5479,16 +6393,20 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, /* not reached */ } +#if XML_GE == 1 static enum XML_Error storeEntityValue(XML_Parser parser, const ENCODING *enc, - const char *entityTextPtr, const char *entityTextEnd) { + const char *entityTextPtr, const char *entityTextEnd, + enum XML_Account account, const char **nextPtr) { DTD *const dtd = parser->m_dtd; /* save one level of indirection */ STRING_POOL *pool = &(dtd->entityValuePool); enum XML_Error result = XML_ERROR_NONE; -#ifdef XML_DTD +# ifdef XML_DTD int oldInEntityValue = parser->m_prologState.inEntityValue; parser->m_prologState.inEntityValue = 1; -#endif /* XML_DTD */ +# else + UNUSED_P(account); +# endif /* XML_DTD */ /* never return Null for the value argument in EntityDeclHandler, since this would indicate an external entity; therefore we have to make sure that entityValuePool.start is not null */ @@ -5497,12 +6415,22 @@ storeEntityValue(XML_Parser parser, const ENCODING *enc, return XML_ERROR_NO_MEMORY; } + const char *next; for (;;) { - const char *next; + next + = entityTextPtr; /* XmlEntityValueTok doesn't always set the last arg */ int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next); + + if (! accountingDiffTolerated(parser, tok, entityTextPtr, next, __LINE__, + account)) { + accountingOnAbort(parser); + result = XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + goto endEntityValue; + } + switch (tok) { case XML_TOK_PARAM_ENTITY_REF: -#ifdef XML_DTD +# ifdef XML_DTD if (parser->m_isParamEntity || enc != parser->m_encoding) { const XML_Char *name; ENTITY *entity; @@ -5525,7 +6453,7 @@ storeEntityValue(XML_Parser parser, const ENCODING *enc, dtd->keepProcessing = dtd->standalone; goto endEntityValue; } - if (entity->open) { + if (entity->open || (entity == parser->m_declEntity)) { if (enc == parser->m_encoding) parser->m_eventPtr = entityTextPtr; result = XML_ERROR_RECURSIVE_ENTITY_REF; @@ -5535,30 +6463,28 @@ storeEntityValue(XML_Parser parser, const ENCODING *enc, if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; + entityTrackingOnOpen(parser, entity, __LINE__); if (! parser->m_externalEntityRefHandler( parser->m_externalEntityRefHandlerArg, 0, entity->base, entity->systemId, entity->publicId)) { + entityTrackingOnClose(parser, entity, __LINE__); entity->open = XML_FALSE; result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; goto endEntityValue; } + entityTrackingOnClose(parser, entity, __LINE__); entity->open = XML_FALSE; if (! dtd->paramEntityRead) dtd->keepProcessing = dtd->standalone; } else dtd->keepProcessing = dtd->standalone; } else { - entity->open = XML_TRUE; - result = storeEntityValue( - parser, parser->m_internalEncoding, (const char *)entity->textPtr, - (const char *)(entity->textPtr + entity->textLen)); - entity->open = XML_FALSE; - if (result) - goto endEntityValue; + result = processEntity(parser, entity, XML_FALSE, ENTITY_VALUE); + goto endEntityValue; } break; } -#endif /* XML_DTD */ +# endif /* XML_DTD */ /* In the internal subset, PE references are not legal within markup declarations, e.g entity values in this case. */ parser->m_eventPtr = entityTextPtr; @@ -5639,12 +6565,113 @@ storeEntityValue(XML_Parser parser, const ENCODING *enc, entityTextPtr = next; } endEntityValue: -#ifdef XML_DTD +# ifdef XML_DTD parser->m_prologState.inEntityValue = oldInEntityValue; -#endif /* XML_DTD */ +# endif /* XML_DTD */ + // If 'nextPtr' is given, it should be updated during the processing + if (nextPtr != NULL) { + *nextPtr = next; + } return result; } +static enum XML_Error +callStoreEntityValue(XML_Parser parser, const ENCODING *enc, + const char *entityTextPtr, const char *entityTextEnd, + enum XML_Account account) { + const char *next = entityTextPtr; + enum XML_Error result = XML_ERROR_NONE; + while (1) { + if (! parser->m_openValueEntities) { + result + = storeEntityValue(parser, enc, next, entityTextEnd, account, &next); + } else { + OPEN_INTERNAL_ENTITY *const openEntity = parser->m_openValueEntities; + if (! openEntity) + return XML_ERROR_UNEXPECTED_STATE; + + ENTITY *const entity = openEntity->entity; + const char *const textStart + = ((const char *)entity->textPtr) + entity->processed; + const char *const textEnd + = (const char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + const char *nextInEntity = textStart; + if (entity->hasMore) { + result = storeEntityValue(parser, parser->m_internalEncoding, textStart, + textEnd, XML_ACCOUNT_ENTITY_EXPANSION, + &nextInEntity); + if (result != XML_ERROR_NONE) + break; + // Check if entity is complete, if not, mark down how much of it is + // processed. A XML_SUSPENDED check here is not required as + // appendAttributeValue will never suspend the parser. + if (textEnd != nextInEntity) { + entity->processed + = (int)(nextInEntity - (const char *)entity->textPtr); + continue; + } + + // Entity is complete. We cannot close it here since we need to first + // process its possible inner entities (which are added to the + // m_openValueEntities during storeEntityValue) + entity->hasMore = XML_FALSE; + continue; + } // End of entity processing, "if" block skips the rest + + // Remove fully processed openEntity from open entity list. +# if XML_GE == 1 + entityTrackingOnClose(parser, entity, __LINE__); +# endif + // openEntity is m_openValueEntities' head, since we set it at the + // start of this function and because we skipped storeEntityValue call + // with hasMore set to false. This means we can directly remove the head + // of m_openValueEntities + assert(parser->m_openValueEntities == openEntity); + entity->open = XML_FALSE; + parser->m_openValueEntities = parser->m_openValueEntities->next; + + /* put openEntity back in list of free instances */ + openEntity->next = parser->m_freeValueEntities; + parser->m_freeValueEntities = openEntity; + } + + // Break if an error occurred or there is nothing left to process + if (result + || (parser->m_openValueEntities == NULL && entityTextEnd == next)) { + break; + } + } + + return result; +} + +#else /* XML_GE == 0 */ + +static enum XML_Error +storeSelfEntityValue(XML_Parser parser, ENTITY *entity) { + // This will store "&entity123;" in entity->textPtr + // to end up as "&entity123;" in the handler. + const char *const entity_start = "&"; + const char *const entity_end = ";"; + + STRING_POOL *const pool = &(parser->m_dtd->entityValuePool); + if (! poolAppendString(pool, entity_start) + || ! poolAppendString(pool, entity->name) + || ! poolAppendString(pool, entity_end)) { + poolDiscard(pool); + return XML_ERROR_NO_MEMORY; + } + + entity->textPtr = poolStart(pool); + entity->textLen = (int)(poolLength(pool)); + poolFinish(pool); + + return XML_ERROR_NONE; +} + +#endif /* XML_GE == 0 */ + static void FASTCALL normalizeLines(XML_Char *s) { XML_Char *p; @@ -5755,8 +6782,9 @@ reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, } while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); } else - parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, - (int)((XML_Char *)end - (XML_Char *)s)); + parser->m_defaultHandler( + parser->m_handlerArg, (const XML_Char *)s, + (int)((const XML_Char *)end - (const XML_Char *)s)); } static int @@ -5784,7 +6812,24 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, } } else { DEFAULT_ATTRIBUTE *temp; + + /* Detect and prevent integer overflow */ + if (type->allocDefaultAtts > INT_MAX / 2) { + return 0; + } + int count = type->allocDefaultAtts * 2; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)count > (size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE)) { + return 0; + } +#endif + temp = (DEFAULT_ATTRIBUTE *)REALLOC(parser, type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE))); if (temp == NULL) @@ -5843,7 +6888,7 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, name = poolStoreString(&dtd->pool, enc, start, end); if (! name) return NULL; - /* skip quotation mark - its storage will be re-used (like in name[-1]) */ + /* skip quotation mark - its storage will be reused (like in name[-1]) */ ++name; id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); @@ -5993,6 +7038,10 @@ getContext(XML_Parser parser) { static XML_Bool setContext(XML_Parser parser, const XML_Char *context) { + if (context == NULL) { + return XML_FALSE; + } + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *s = context; @@ -6074,7 +7123,7 @@ normalizePublicId(XML_Char *publicId) { static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms) { - DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD)); + DTD *p = ms->malloc_fcn(sizeof(DTD)); if (p == NULL) return p; poolInit(&(p->pool), ms); @@ -6247,8 +7296,18 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, if (! newE) return 0; if (oldE->nDefaultAtts) { - newE->defaultAtts = (DEFAULT_ATTRIBUTE *)ms->malloc_fcn( - oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((size_t)oldE->nDefaultAtts + > ((size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE))) { + return 0; + } +#endif + newE->defaultAtts + = ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); if (! newE->defaultAtts) { return 0; } @@ -6410,7 +7469,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { /* table->size is a power of 2 */ table->size = (size_t)1 << INIT_POWER; tsize = table->size * sizeof(NAMED *); - table->v = (NAMED **)table->mem->malloc_fcn(tsize); + table->v = table->mem->malloc_fcn(tsize); if (! table->v) { table->size = 0; return NULL; @@ -6435,10 +7494,22 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { /* check for overflow (table is half full) */ if (table->used >> (table->power - 1)) { unsigned char newPower = table->power + 1; + + /* Detect and prevent invalid shift */ + if (newPower >= sizeof(unsigned long) * 8 /* bits per byte */) { + return NULL; + } + size_t newSize = (size_t)1 << newPower; unsigned long newMask = (unsigned long)newSize - 1; + + /* Detect and prevent integer overflow */ + if (newSize > (size_t)(-1) / sizeof(NAMED *)) { + return NULL; + } + size_t tsize = newSize * sizeof(NAMED *); - NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); + NAMED **newV = table->mem->malloc_fcn(tsize); if (! newV) return NULL; memset(newV, 0, tsize); @@ -6467,7 +7538,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { } } } - table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); + table->v[i] = table->mem->malloc_fcn(createSize); if (! table->v[i]) return NULL; memset(table->v[i], 0, createSize); @@ -6571,7 +7642,7 @@ poolAppend(STRING_POOL *pool, const ENCODING *enc, const char *ptr, return NULL; for (;;) { const enum XML_Convert_Result convert_res = XmlConvert( - enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + enc, &ptr, end, (ICHAR **)&(pool->ptr), (const ICHAR *)pool->end); if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) break; @@ -6755,7 +7826,7 @@ poolGrow(STRING_POOL *pool) { if (bytesToAllocate == 0) return XML_FALSE; - tem = (BLOCK *)pool->mem->malloc_fcn(bytesToAllocate); + tem = pool->mem->malloc_fcn(bytesToAllocate); if (! tem) return XML_FALSE; tem->size = blockSize; @@ -6777,6 +7848,15 @@ nextScaffoldPart(XML_Parser parser) { int next; if (! dtd->scaffIndex) { + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (parser->m_groupSize > ((size_t)(-1) / sizeof(int))) { + return -1; + } +#endif dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int)); if (! dtd->scaffIndex) return -1; @@ -6786,6 +7866,20 @@ nextScaffoldPart(XML_Parser parser) { if (dtd->scaffCount >= dtd->scaffSize) { CONTENT_SCAFFOLD *temp; if (dtd->scaffold) { + /* Detect and prevent integer overflow */ + if (dtd->scaffSize > UINT_MAX / 2u) { + return -1; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (dtd->scaffSize > (size_t)(-1) / 2u / sizeof(CONTENT_SCAFFOLD)) { + return -1; + } +#endif + temp = (CONTENT_SCAFFOLD *)REALLOC( parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); if (temp == NULL) @@ -6817,55 +7911,130 @@ nextScaffoldPart(XML_Parser parser) { return next; } -static void -build_node(XML_Parser parser, int src_node, XML_Content *dest, - XML_Content **contpos, XML_Char **strpos) { - DTD *const dtd = parser->m_dtd; /* save one level of indirection */ - dest->type = dtd->scaffold[src_node].type; - dest->quant = dtd->scaffold[src_node].quant; - if (dest->type == XML_CTYPE_NAME) { - const XML_Char *src; - dest->name = *strpos; - src = dtd->scaffold[src_node].name; - for (;;) { - *(*strpos)++ = *src; - if (! *src) - break; - src++; - } - dest->numchildren = 0; - dest->children = NULL; - } else { - unsigned int i; - int cn; - dest->numchildren = dtd->scaffold[src_node].childcnt; - dest->children = *contpos; - *contpos += dest->numchildren; - for (i = 0, cn = dtd->scaffold[src_node].firstchild; i < dest->numchildren; - i++, cn = dtd->scaffold[cn].nextsib) { - build_node(parser, cn, &(dest->children[i]), contpos, strpos); - } - dest->name = NULL; - } -} - static XML_Content * build_model(XML_Parser parser) { + /* Function build_model transforms the existing parser->m_dtd->scaffold + * array of CONTENT_SCAFFOLD tree nodes into a new array of + * XML_Content tree nodes followed by a gapless list of zero-terminated + * strings. */ DTD *const dtd = parser->m_dtd; /* save one level of indirection */ XML_Content *ret; - XML_Content *cpos; - XML_Char *str; - int allocsize = (dtd->scaffCount * sizeof(XML_Content) - + (dtd->contentStringLen * sizeof(XML_Char))); + XML_Char *str; /* the current string writing location */ + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (dtd->scaffCount > (size_t)(-1) / sizeof(XML_Content)) { + return NULL; + } + if (dtd->contentStringLen > (size_t)(-1) / sizeof(XML_Char)) { + return NULL; + } +#endif + if (dtd->scaffCount * sizeof(XML_Content) + > (size_t)(-1) - dtd->contentStringLen * sizeof(XML_Char)) { + return NULL; + } + + const size_t allocsize = (dtd->scaffCount * sizeof(XML_Content) + + (dtd->contentStringLen * sizeof(XML_Char))); ret = (XML_Content *)MALLOC(parser, allocsize); if (! ret) return NULL; - str = (XML_Char *)(&ret[dtd->scaffCount]); - cpos = &ret[1]; + /* What follows is an iterative implementation (of what was previously done + * recursively in a dedicated function called "build_node". The old recursive + * build_node could be forced into stack exhaustion from input as small as a + * few megabyte, and so that was a security issue. Hence, a function call + * stack is avoided now by resolving recursion.) + * + * The iterative approach works as follows: + * + * - We have two writing pointers, both walking up the result array; one does + * the work, the other creates "jobs" for its colleague to do, and leads + * the way: + * + * - The faster one, pointer jobDest, always leads and writes "what job + * to do" by the other, once they reach that place in the + * array: leader "jobDest" stores the source node array index (relative + * to array dtd->scaffold) in field "numchildren". + * + * - The slower one, pointer dest, looks at the value stored in the + * "numchildren" field (which actually holds a source node array index + * at that time) and puts the real data from dtd->scaffold in. + * + * - Before the loop starts, jobDest writes source array index 0 + * (where the root node is located) so that dest will have something to do + * when it starts operation. + * + * - Whenever nodes with children are encountered, jobDest appends + * them as new jobs, in order. As a result, tree node siblings are + * adjacent in the resulting array, for example: + * + * [0] root, has two children + * [1] first child of 0, has three children + * [3] first child of 1, does not have children + * [4] second child of 1, does not have children + * [5] third child of 1, does not have children + * [2] second child of 0, does not have children + * + * Or (the same data) presented in flat array view: + * + * [0] root, has two children + * + * [1] first child of 0, has three children + * [2] second child of 0, does not have children + * + * [3] first child of 1, does not have children + * [4] second child of 1, does not have children + * [5] third child of 1, does not have children + * + * - The algorithm repeats until all target array indices have been processed. + */ + XML_Content *dest = ret; /* tree node writing location, moves upwards */ + XML_Content *const destLimit = &ret[dtd->scaffCount]; + XML_Content *jobDest = ret; /* next free writing location in target array */ + str = (XML_Char *)&ret[dtd->scaffCount]; + + /* Add the starting job, the root node (index 0) of the source tree */ + (jobDest++)->numchildren = 0; + + for (; dest < destLimit; dest++) { + /* Retrieve source tree array index from job storage */ + const int src_node = (int)dest->numchildren; + + /* Convert item */ + dest->type = dtd->scaffold[src_node].type; + dest->quant = dtd->scaffold[src_node].quant; + if (dest->type == XML_CTYPE_NAME) { + const XML_Char *src; + dest->name = str; + src = dtd->scaffold[src_node].name; + for (;;) { + *str++ = *src; + if (! *src) + break; + src++; + } + dest->numchildren = 0; + dest->children = NULL; + } else { + unsigned int i; + int cn; + dest->name = NULL; + dest->numchildren = dtd->scaffold[src_node].childcnt; + dest->children = jobDest; + + /* Append scaffold indices of children to array */ + for (i = 0, cn = dtd->scaffold[src_node].firstchild; + i < dest->numchildren; i++, cn = dtd->scaffold[cn].nextsib) + (jobDest++)->numchildren = (unsigned int)cn; + } + } - build_node(parser, 0, ret, &cpos, &str); return ret; } @@ -6894,7 +8063,7 @@ getElementType(XML_Parser parser, const ENCODING *enc, const char *ptr, static XML_Char * copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) { - int charsRequired = 0; + size_t charsRequired = 0; XML_Char *result; /* First determine how long the string is */ @@ -6912,3 +8081,761 @@ copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) { memcpy(result, s, charsRequired * sizeof(XML_Char)); return result; } + +#if XML_GE == 1 + +static float +accountingGetCurrentAmplification(XML_Parser rootParser) { + // 1.........1.........12 => 22 + const size_t lenOfShortestInclude = sizeof("<!ENTITY a SYSTEM 'b'>") - 1; + const XmlBigCount countBytesOutput + = rootParser->m_accounting.countBytesDirect + + rootParser->m_accounting.countBytesIndirect; + const float amplificationFactor + = rootParser->m_accounting.countBytesDirect + ? (countBytesOutput + / (float)(rootParser->m_accounting.countBytesDirect)) + : ((lenOfShortestInclude + + rootParser->m_accounting.countBytesIndirect) + / (float)lenOfShortestInclude); + assert(! rootParser->m_parentParser); + return amplificationFactor; +} + +static void +accountingReportStats(XML_Parser originParser, const char *epilog) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + if (rootParser->m_accounting.debugLevel == 0u) { + return; + } + + const float amplificationFactor + = accountingGetCurrentAmplification(rootParser); + fprintf(stderr, + "expat: Accounting(%p): Direct " EXPAT_FMT_ULL( + "10") ", indirect " EXPAT_FMT_ULL("10") ", amplification %8.2f%s", + (void *)rootParser, rootParser->m_accounting.countBytesDirect, + rootParser->m_accounting.countBytesIndirect, + (double)amplificationFactor, epilog); +} + +static void +accountingOnAbort(XML_Parser originParser) { + accountingReportStats(originParser, " ABORTING\n"); +} + +static void +accountingReportDiff(XML_Parser rootParser, + unsigned int levelsAwayFromRootParser, const char *before, + const char *after, ptrdiff_t bytesMore, int source_line, + enum XML_Account account) { + assert(! rootParser->m_parentParser); + + fprintf(stderr, + " (+" EXPAT_FMT_PTRDIFF_T("6") " bytes %s|%u, xmlparse.c:%d) %*s\"", + bytesMore, (account == XML_ACCOUNT_DIRECT) ? "DIR" : "EXP", + levelsAwayFromRootParser, source_line, 10, ""); + + const char ellipis[] = "[..]"; + const size_t ellipsisLength = sizeof(ellipis) /* because compile-time */ - 1; + const unsigned int contextLength = 10; + + /* Note: Performance is of no concern here */ + const char *walker = before; + if ((rootParser->m_accounting.debugLevel >= 3u) + || (after - before) + <= (ptrdiff_t)(contextLength + ellipsisLength + contextLength)) { + for (; walker < after; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + } else { + for (; walker < before + contextLength; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + fprintf(stderr, ellipis); + walker = after - contextLength; + for (; walker < after; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + } + fprintf(stderr, "\"\n"); +} + +static XML_Bool +accountingDiffTolerated(XML_Parser originParser, int tok, const char *before, + const char *after, int source_line, + enum XML_Account account) { + /* Note: We need to check the token type *first* to be sure that + * we can even access variable <after>, safely. + * E.g. for XML_TOK_NONE <after> may hold an invalid pointer. */ + switch (tok) { + case XML_TOK_INVALID: + case XML_TOK_PARTIAL: + case XML_TOK_PARTIAL_CHAR: + case XML_TOK_NONE: + return XML_TRUE; + } + + if (account == XML_ACCOUNT_NONE) + return XML_TRUE; /* because these bytes have been accounted for, already */ + + unsigned int levelsAwayFromRootParser; + const XML_Parser rootParser + = getRootParserOf(originParser, &levelsAwayFromRootParser); + assert(! rootParser->m_parentParser); + + const int isDirect + = (account == XML_ACCOUNT_DIRECT) && (originParser == rootParser); + const ptrdiff_t bytesMore = after - before; + + XmlBigCount *const additionTarget + = isDirect ? &rootParser->m_accounting.countBytesDirect + : &rootParser->m_accounting.countBytesIndirect; + + /* Detect and avoid integer overflow */ + if (*additionTarget > (XmlBigCount)(-1) - (XmlBigCount)bytesMore) + return XML_FALSE; + *additionTarget += bytesMore; + + const XmlBigCount countBytesOutput + = rootParser->m_accounting.countBytesDirect + + rootParser->m_accounting.countBytesIndirect; + const float amplificationFactor + = accountingGetCurrentAmplification(rootParser); + const XML_Bool tolerated + = (countBytesOutput < rootParser->m_accounting.activationThresholdBytes) + || (amplificationFactor + <= rootParser->m_accounting.maximumAmplificationFactor); + + if (rootParser->m_accounting.debugLevel >= 2u) { + accountingReportStats(rootParser, ""); + accountingReportDiff(rootParser, levelsAwayFromRootParser, before, after, + bytesMore, source_line, account); + } + + return tolerated; +} + +unsigned long long +testingAccountingGetCountBytesDirect(XML_Parser parser) { + if (! parser) + return 0; + return parser->m_accounting.countBytesDirect; +} + +unsigned long long +testingAccountingGetCountBytesIndirect(XML_Parser parser) { + if (! parser) + return 0; + return parser->m_accounting.countBytesIndirect; +} + +static void +entityTrackingReportStats(XML_Parser rootParser, ENTITY *entity, + const char *action, int sourceLine) { + assert(! rootParser->m_parentParser); + if (rootParser->m_entity_stats.debugLevel == 0u) + return; + +# if defined(XML_UNICODE) + const char *const entityName = "[..]"; +# else + const char *const entityName = entity->name; +# endif + + fprintf( + stderr, + "expat: Entities(%p): Count %9u, depth %2u/%2u %*s%s%s; %s length %d (xmlparse.c:%d)\n", + (void *)rootParser, rootParser->m_entity_stats.countEverOpened, + rootParser->m_entity_stats.currentDepth, + rootParser->m_entity_stats.maximumDepthSeen, + ((int)rootParser->m_entity_stats.currentDepth - 1) * 2, "", + entity->is_param ? "%" : "&", entityName, action, entity->textLen, + sourceLine); +} + +static void +entityTrackingOnOpen(XML_Parser originParser, ENTITY *entity, int sourceLine) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + rootParser->m_entity_stats.countEverOpened++; + rootParser->m_entity_stats.currentDepth++; + if (rootParser->m_entity_stats.currentDepth + > rootParser->m_entity_stats.maximumDepthSeen) { + rootParser->m_entity_stats.maximumDepthSeen++; + } + + entityTrackingReportStats(rootParser, entity, "OPEN ", sourceLine); +} + +static void +entityTrackingOnClose(XML_Parser originParser, ENTITY *entity, int sourceLine) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + entityTrackingReportStats(rootParser, entity, "CLOSE", sourceLine); + rootParser->m_entity_stats.currentDepth--; +} + +static XML_Parser +getRootParserOf(XML_Parser parser, unsigned int *outLevelDiff) { + XML_Parser rootParser = parser; + unsigned int stepsTakenUpwards = 0; + while (rootParser->m_parentParser) { + rootParser = rootParser->m_parentParser; + stepsTakenUpwards++; + } + assert(! rootParser->m_parentParser); + if (outLevelDiff != NULL) { + *outLevelDiff = stepsTakenUpwards; + } + return rootParser; +} + +const char * +unsignedCharToPrintable(unsigned char c) { + switch (c) { + case 0: + return "\\0"; + case 1: + return "\\x1"; + case 2: + return "\\x2"; + case 3: + return "\\x3"; + case 4: + return "\\x4"; + case 5: + return "\\x5"; + case 6: + return "\\x6"; + case 7: + return "\\x7"; + case 8: + return "\\x8"; + case 9: + return "\\t"; + case 10: + return "\\n"; + case 11: + return "\\xB"; + case 12: + return "\\xC"; + case 13: + return "\\r"; + case 14: + return "\\xE"; + case 15: + return "\\xF"; + case 16: + return "\\x10"; + case 17: + return "\\x11"; + case 18: + return "\\x12"; + case 19: + return "\\x13"; + case 20: + return "\\x14"; + case 21: + return "\\x15"; + case 22: + return "\\x16"; + case 23: + return "\\x17"; + case 24: + return "\\x18"; + case 25: + return "\\x19"; + case 26: + return "\\x1A"; + case 27: + return "\\x1B"; + case 28: + return "\\x1C"; + case 29: + return "\\x1D"; + case 30: + return "\\x1E"; + case 31: + return "\\x1F"; + case 32: + return " "; + case 33: + return "!"; + case 34: + return "\\\""; + case 35: + return "#"; + case 36: + return "$"; + case 37: + return "%"; + case 38: + return "&"; + case 39: + return "'"; + case 40: + return "("; + case 41: + return ")"; + case 42: + return "*"; + case 43: + return "+"; + case 44: + return ","; + case 45: + return "-"; + case 46: + return "."; + case 47: + return "/"; + case 48: + return "0"; + case 49: + return "1"; + case 50: + return "2"; + case 51: + return "3"; + case 52: + return "4"; + case 53: + return "5"; + case 54: + return "6"; + case 55: + return "7"; + case 56: + return "8"; + case 57: + return "9"; + case 58: + return ":"; + case 59: + return ";"; + case 60: + return "<"; + case 61: + return "="; + case 62: + return ">"; + case 63: + return "?"; + case 64: + return "@"; + case 65: + return "A"; + case 66: + return "B"; + case 67: + return "C"; + case 68: + return "D"; + case 69: + return "E"; + case 70: + return "F"; + case 71: + return "G"; + case 72: + return "H"; + case 73: + return "I"; + case 74: + return "J"; + case 75: + return "K"; + case 76: + return "L"; + case 77: + return "M"; + case 78: + return "N"; + case 79: + return "O"; + case 80: + return "P"; + case 81: + return "Q"; + case 82: + return "R"; + case 83: + return "S"; + case 84: + return "T"; + case 85: + return "U"; + case 86: + return "V"; + case 87: + return "W"; + case 88: + return "X"; + case 89: + return "Y"; + case 90: + return "Z"; + case 91: + return "["; + case 92: + return "\\\\"; + case 93: + return "]"; + case 94: + return "^"; + case 95: + return "_"; + case 96: + return "`"; + case 97: + return "a"; + case 98: + return "b"; + case 99: + return "c"; + case 100: + return "d"; + case 101: + return "e"; + case 102: + return "f"; + case 103: + return "g"; + case 104: + return "h"; + case 105: + return "i"; + case 106: + return "j"; + case 107: + return "k"; + case 108: + return "l"; + case 109: + return "m"; + case 110: + return "n"; + case 111: + return "o"; + case 112: + return "p"; + case 113: + return "q"; + case 114: + return "r"; + case 115: + return "s"; + case 116: + return "t"; + case 117: + return "u"; + case 118: + return "v"; + case 119: + return "w"; + case 120: + return "x"; + case 121: + return "y"; + case 122: + return "z"; + case 123: + return "{"; + case 124: + return "|"; + case 125: + return "}"; + case 126: + return "~"; + case 127: + return "\\x7F"; + case 128: + return "\\x80"; + case 129: + return "\\x81"; + case 130: + return "\\x82"; + case 131: + return "\\x83"; + case 132: + return "\\x84"; + case 133: + return "\\x85"; + case 134: + return "\\x86"; + case 135: + return "\\x87"; + case 136: + return "\\x88"; + case 137: + return "\\x89"; + case 138: + return "\\x8A"; + case 139: + return "\\x8B"; + case 140: + return "\\x8C"; + case 141: + return "\\x8D"; + case 142: + return "\\x8E"; + case 143: + return "\\x8F"; + case 144: + return "\\x90"; + case 145: + return "\\x91"; + case 146: + return "\\x92"; + case 147: + return "\\x93"; + case 148: + return "\\x94"; + case 149: + return "\\x95"; + case 150: + return "\\x96"; + case 151: + return "\\x97"; + case 152: + return "\\x98"; + case 153: + return "\\x99"; + case 154: + return "\\x9A"; + case 155: + return "\\x9B"; + case 156: + return "\\x9C"; + case 157: + return "\\x9D"; + case 158: + return "\\x9E"; + case 159: + return "\\x9F"; + case 160: + return "\\xA0"; + case 161: + return "\\xA1"; + case 162: + return "\\xA2"; + case 163: + return "\\xA3"; + case 164: + return "\\xA4"; + case 165: + return "\\xA5"; + case 166: + return "\\xA6"; + case 167: + return "\\xA7"; + case 168: + return "\\xA8"; + case 169: + return "\\xA9"; + case 170: + return "\\xAA"; + case 171: + return "\\xAB"; + case 172: + return "\\xAC"; + case 173: + return "\\xAD"; + case 174: + return "\\xAE"; + case 175: + return "\\xAF"; + case 176: + return "\\xB0"; + case 177: + return "\\xB1"; + case 178: + return "\\xB2"; + case 179: + return "\\xB3"; + case 180: + return "\\xB4"; + case 181: + return "\\xB5"; + case 182: + return "\\xB6"; + case 183: + return "\\xB7"; + case 184: + return "\\xB8"; + case 185: + return "\\xB9"; + case 186: + return "\\xBA"; + case 187: + return "\\xBB"; + case 188: + return "\\xBC"; + case 189: + return "\\xBD"; + case 190: + return "\\xBE"; + case 191: + return "\\xBF"; + case 192: + return "\\xC0"; + case 193: + return "\\xC1"; + case 194: + return "\\xC2"; + case 195: + return "\\xC3"; + case 196: + return "\\xC4"; + case 197: + return "\\xC5"; + case 198: + return "\\xC6"; + case 199: + return "\\xC7"; + case 200: + return "\\xC8"; + case 201: + return "\\xC9"; + case 202: + return "\\xCA"; + case 203: + return "\\xCB"; + case 204: + return "\\xCC"; + case 205: + return "\\xCD"; + case 206: + return "\\xCE"; + case 207: + return "\\xCF"; + case 208: + return "\\xD0"; + case 209: + return "\\xD1"; + case 210: + return "\\xD2"; + case 211: + return "\\xD3"; + case 212: + return "\\xD4"; + case 213: + return "\\xD5"; + case 214: + return "\\xD6"; + case 215: + return "\\xD7"; + case 216: + return "\\xD8"; + case 217: + return "\\xD9"; + case 218: + return "\\xDA"; + case 219: + return "\\xDB"; + case 220: + return "\\xDC"; + case 221: + return "\\xDD"; + case 222: + return "\\xDE"; + case 223: + return "\\xDF"; + case 224: + return "\\xE0"; + case 225: + return "\\xE1"; + case 226: + return "\\xE2"; + case 227: + return "\\xE3"; + case 228: + return "\\xE4"; + case 229: + return "\\xE5"; + case 230: + return "\\xE6"; + case 231: + return "\\xE7"; + case 232: + return "\\xE8"; + case 233: + return "\\xE9"; + case 234: + return "\\xEA"; + case 235: + return "\\xEB"; + case 236: + return "\\xEC"; + case 237: + return "\\xED"; + case 238: + return "\\xEE"; + case 239: + return "\\xEF"; + case 240: + return "\\xF0"; + case 241: + return "\\xF1"; + case 242: + return "\\xF2"; + case 243: + return "\\xF3"; + case 244: + return "\\xF4"; + case 245: + return "\\xF5"; + case 246: + return "\\xF6"; + case 247: + return "\\xF7"; + case 248: + return "\\xF8"; + case 249: + return "\\xF9"; + case 250: + return "\\xFA"; + case 251: + return "\\xFB"; + case 252: + return "\\xFC"; + case 253: + return "\\xFD"; + case 254: + return "\\xFE"; + case 255: + return "\\xFF"; + // LCOV_EXCL_START + default: + assert(0); /* never gets here */ + return "dead code"; + } + assert(0); /* never gets here */ + // LCOV_EXCL_STOP +} + +#endif /* XML_GE == 1 */ + +static unsigned long +getDebugLevel(const char *variableName, unsigned long defaultDebugLevel) { + const char *const valueOrNull = getenv(variableName); + if (valueOrNull == NULL) { + return defaultDebugLevel; + } + const char *const value = valueOrNull; + + errno = 0; + char *afterValue = NULL; + unsigned long debugLevel = strtoul(value, &afterValue, 10); + if ((errno != 0) || (afterValue == value) || (afterValue[0] != '\0')) { + errno = 0; + return defaultDebugLevel; + } + + return debugLevel; +} diff --git a/3rdparty/expat/lib/xmlrole.c b/3rdparty/expat/lib/xmlrole.c index 3b676a415d8..2c48bf40867 100644 --- a/3rdparty/expat/lib/xmlrole.c +++ b/3rdparty/expat/lib/xmlrole.c @@ -7,7 +7,15 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016-2023 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2021 Donghee Na <donghee.na@python.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -30,15 +38,13 @@ USE OR OTHER DEALINGS IN THE SOFTWARE. */ +#include "expat_config.h" + #include <stddef.h> #ifdef _WIN32 # include "winconfig.h" -#else -# ifdef HAVE_EXPAT_CONFIG_H -# include <expat_config.h> -# endif -#endif /* ndef _WIN32 */ +#endif #include "expat_external.h" #include "internal.h" diff --git a/3rdparty/expat/lib/xmlrole.h b/3rdparty/expat/lib/xmlrole.h index 036aba64fd2..a7904274c91 100644 --- a/3rdparty/expat/lib/xmlrole.h +++ b/3rdparty/expat/lib/xmlrole.h @@ -7,7 +7,10 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017-2024 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -124,9 +127,9 @@ typedef struct prolog_state { #endif /* XML_DTD */ } PROLOG_STATE; -void XmlPrologStateInit(PROLOG_STATE *); +void XmlPrologStateInit(PROLOG_STATE *state); #ifdef XML_DTD -void XmlPrologStateInitExternalEntity(PROLOG_STATE *); +void XmlPrologStateInitExternalEntity(PROLOG_STATE *state); #endif /* XML_DTD */ #define XmlTokenRole(state, tok, ptr, end, enc) \ diff --git a/3rdparty/expat/lib/xmltok.c b/3rdparty/expat/lib/xmltok.c index c4f9897f7dc..29a66d72cee 100644 --- a/3rdparty/expat/lib/xmltok.c +++ b/3rdparty/expat/lib/xmltok.c @@ -7,7 +7,23 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2001-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016-2024 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Pascal Cuoq <cuoq@trust-in-soft.com> + Copyright (c) 2016 Don Lewis <truckman@apache.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2017 Alexander Bluhm <alexander.bluhm@gmx.net> + Copyright (c) 2017 Benbuck Nason <bnason@netflix.com> + Copyright (c) 2017 José Gutiérrez de la Concha <jose@zeroc.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2021 Donghee Na <donghee.na@python.org> + Copyright (c) 2022 Martin Ettl <ettl.martin78@googlemail.com> + Copyright (c) 2022 Sean McBride <sean@rogue-research.com> + Copyright (c) 2023 Hanno Böck <hanno@gentoo.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -30,25 +46,15 @@ USE OR OTHER DEALINGS IN THE SOFTWARE. */ +#include "expat_config.h" + #include <stddef.h> #include <string.h> /* memcpy */ - -#if defined(_MSC_VER) && (_MSC_VER <= 1700) -/* for vs2012/11.0/1700 and earlier Visual Studio compilers */ -# define bool int -# define false 0 -# define true 1 -#else -# include <stdbool.h> -#endif +#include <stdbool.h> #ifdef _WIN32 # include "winconfig.h" -#else -# ifdef HAVE_EXPAT_CONFIG_H -# include <expat_config.h> -# endif -#endif /* ndef _WIN32 */ +#endif #include "expat_external.h" #include "internal.h" @@ -72,7 +78,7 @@ #define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) #define UCS2_GET_NAMING(pages, hi, lo) \ - (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo)&0x1F))) + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo) & 0x1F))) /* A 2 byte UTF-8 representation splits the characters 11 bits between the bottom 5 and 6 bits of the bytes. We need 8 bits to index into @@ -95,13 +101,8 @@ + ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \ & (1u << (((byte)[2]) & 0x1F))) -#define UTF8_GET_NAMING(pages, p, n) \ - ((n) == 2 \ - ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ - : ((n) == 3 ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) : 0)) - /* Detection of invalid UTF-8 sequences is based on Table 3.1B - of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ + of Unicode 3.2: https://www.unicode.org/unicode/reports/tr28/ with the additional restriction of not allowing the Unicode code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE). Implementation details: @@ -226,7 +227,7 @@ struct normal_encoding { /* isNmstrt2 */ NULL, /* isNmstrt3 */ NULL, /* isNmstrt4 */ NULL, \ /* isInvalid2 */ NULL, /* isInvalid3 */ NULL, /* isInvalid4 */ NULL -static int FASTCALL checkCharRefNumber(int); +static int FASTCALL checkCharRefNumber(int result); #include "xmltok_impl.h" #include "ascii.h" @@ -244,7 +245,7 @@ static int FASTCALL checkCharRefNumber(int); #endif #define SB_BYTE_TYPE(enc, p) \ - (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) + (((const struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) #ifdef XML_MIN_SIZE static int PTRFASTCALL @@ -269,8 +270,14 @@ sb_byteToAscii(const ENCODING *enc, const char *p) { #define IS_NAME_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isName##n(enc, p)) #define IS_NMSTRT_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isNmstrt##n(enc, p)) -#define IS_INVALID_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) +#ifdef XML_MIN_SIZE +# define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n \ + && AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) +#else +# define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) +#endif #ifdef XML_MIN_SIZE # define IS_NAME_CHAR_MINBPC(enc, p) \ @@ -292,7 +299,7 @@ sb_charMatches(const ENCODING *enc, const char *p, int c) { } #else /* 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 @@ -402,7 +409,7 @@ utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, unsigned short *to = *toP; const char *from = *fromP; while (from < fromLim && to < toLim) { - switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) { + switch (SB_BYTE_TYPE(enc, from)) { case BT_LEAD2: if (fromLim - from < 2) { res = XML_CONVERT_INPUT_INCOMPLETE; @@ -710,33 +717,28 @@ unicode_byte_type(char hi, char lo) { return res; \ } -#define SET2(ptr, ch) (((ptr)[0] = ((ch)&0xff)), ((ptr)[1] = ((ch) >> 8))) #define GET_LO(ptr) ((unsigned char)(ptr)[0]) #define GET_HI(ptr) ((unsigned char)(ptr)[1]) DEFINE_UTF16_TO_UTF8(little2_) DEFINE_UTF16_TO_UTF16(little2_) -#undef SET2 #undef GET_LO #undef GET_HI -#define SET2(ptr, ch) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch)&0xFF))) #define GET_LO(ptr) ((unsigned char)(ptr)[1]) #define GET_HI(ptr) ((unsigned char)(ptr)[0]) DEFINE_UTF16_TO_UTF8(big2_) DEFINE_UTF16_TO_UTF16(big2_) -#undef SET2 #undef GET_LO #undef GET_HI #define LITTLE2_BYTE_TYPE(enc, p) \ - ((p)[1] == 0 ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ - : unicode_byte_type((p)[1], (p)[0])) + ((p)[1] == 0 ? SB_BYTE_TYPE(enc, p) : unicode_byte_type((p)[1], (p)[0])) #define LITTLE2_BYTE_TO_ASCII(p) ((p)[1] == 0 ? (p)[0] : -1) -#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == (c)) #define LITTLE2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) #define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) \ @@ -867,11 +869,9 @@ static const struct normal_encoding internal_little2_encoding #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])) + ((p)[0] == 0 ? SB_BYTE_TYPE(enc, p + 1) : unicode_byte_type((p)[0], (p)[1])) #define BIG2_BYTE_TO_ASCII(p) ((p)[0] == 0 ? (p)[1] : -1) -#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == (c)) #define BIG2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) #define BIG2_IS_NMSTRT_CHAR_MINBPC(p) \ diff --git a/3rdparty/expat/lib/xmltok.h b/3rdparty/expat/lib/xmltok.h index 2adbf5307be..c51fce1ec15 100644 --- a/3rdparty/expat/lib/xmltok.h +++ b/3rdparty/expat/lib/xmltok.h @@ -7,7 +7,11 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2005 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2024 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -285,7 +289,8 @@ int XmlParseXmlDecl(int isGeneralTextEntity, const ENCODING *enc, const char **encodingNamePtr, const ENCODING **namedEncodingPtr, int *standalonePtr); -int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); +int XmlInitEncoding(INIT_ENCODING *p, const ENCODING **encPtr, + const char *name); const ENCODING *XmlGetUtf8InternalEncoding(void); const ENCODING *XmlGetUtf16InternalEncoding(void); int FASTCALL XmlUtf8Encode(int charNumber, char *buf); @@ -303,7 +308,8 @@ int XmlParseXmlDeclNS(int isGeneralTextEntity, const ENCODING *enc, const char **encodingNamePtr, const ENCODING **namedEncodingPtr, int *standalonePtr); -int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); +int XmlInitEncodingNS(INIT_ENCODING *p, const ENCODING **encPtr, + const char *name); const ENCODING *XmlGetUtf8InternalEncodingNS(void); const ENCODING *XmlGetUtf16InternalEncodingNS(void); ENCODING *XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, diff --git a/3rdparty/expat/lib/xmltok_impl.c b/3rdparty/expat/lib/xmltok_impl.c index 06d5c90851f..239a2d06c45 100644 --- a/3rdparty/expat/lib/xmltok_impl.c +++ b/3rdparty/expat/lib/xmltok_impl.c @@ -1,4 +1,4 @@ -/* This file is included! +/* This file is included (from xmltok.c, 1-3 times depending on XML_MIN_SIZE)! __ __ _ ___\ \/ /_ __ __ _| |_ / _ \\ /| '_ \ / _` | __| @@ -7,7 +7,16 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2022 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2018 Benjamin Peterson <benjamin@python.org> + Copyright (c) 2018 Anton Maklakov <antmak.pub@gmail.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2020 Boris Kolpackov <boris@codesynthesis.com> + Copyright (c) 2022 Martin Ettl <ettl.martin78@googlemail.com> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -32,7 +41,7 @@ #ifdef XML_TOK_IMPL_C -# ifndef IS_INVALID_CHAR +# ifndef IS_INVALID_CHAR // i.e. for UTF-16 and XML_MIN_SIZE not defined # define IS_INVALID_CHAR(enc, ptr, n) (0) # endif @@ -61,7 +70,7 @@ case BT_LEAD##n: \ if (end - ptr < n) \ return XML_TOK_PARTIAL_CHAR; \ - if (! IS_NAME_CHAR(enc, ptr, n)) { \ + if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NAME_CHAR(enc, ptr, n)) { \ *nextTokPtr = ptr; \ return XML_TOK_INVALID; \ } \ @@ -88,9 +97,9 @@ # define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ case BT_LEAD##n: \ - if (end - ptr < n) \ + if ((end) - (ptr) < (n)) \ return XML_TOK_PARTIAL_CHAR; \ - if (! IS_NMSTRT_CHAR(enc, ptr, n)) { \ + if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NMSTRT_CHAR(enc, ptr, n)) { \ *nextTokPtr = ptr; \ return XML_TOK_INVALID; \ } \ @@ -116,7 +125,8 @@ # define PREFIX(ident) ident # endif -# define HAS_CHARS(enc, ptr, end, count) (end - ptr >= count * MINBPC(enc)) +# define HAS_CHARS(enc, ptr, end, count) \ + ((end) - (ptr) >= ((count) * MINBPC(enc))) # define HAS_CHAR(enc, ptr, end) HAS_CHARS(enc, ptr, end, 1) @@ -1134,6 +1144,10 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, case BT_LEAD##n: \ if (end - ptr < n) \ return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ ptr += n; \ tok = XML_TOK_NAME; \ @@ -1262,7 +1276,7 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end, switch (BYTE_TYPE(enc, ptr)) { # define LEAD_CASE(n) \ case BT_LEAD##n: \ - ptr += n; \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ break; LEAD_CASE(2) LEAD_CASE(3) @@ -1331,7 +1345,7 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end, switch (BYTE_TYPE(enc, ptr)) { # define LEAD_CASE(n) \ case BT_LEAD##n: \ - ptr += n; \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ break; LEAD_CASE(2) LEAD_CASE(3) @@ -1510,7 +1524,7 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, int attsMax, state = inName; \ } # define LEAD_CASE(n) \ - case BT_LEAD##n: \ + case BT_LEAD##n: /* NOTE: The encoding has already been validated. */ \ START_NAME ptr += (n - MINBPC(enc)); \ break; LEAD_CASE(2) @@ -1722,7 +1736,7 @@ PREFIX(nameLength)(const ENCODING *enc, const char *ptr) { switch (BYTE_TYPE(enc, ptr)) { # define LEAD_CASE(n) \ case BT_LEAD##n: \ - ptr += n; \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ break; LEAD_CASE(2) LEAD_CASE(3) @@ -1767,7 +1781,7 @@ PREFIX(updatePosition)(const ENCODING *enc, const char *ptr, const char *end, switch (BYTE_TYPE(enc, ptr)) { # define LEAD_CASE(n) \ case BT_LEAD##n: \ - ptr += n; \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ pos->columnNumber++; \ break; LEAD_CASE(2) diff --git a/3rdparty/expat/lib/xmltok_impl.h b/3rdparty/expat/lib/xmltok_impl.h index e925dbc7e2c..3469c4ae138 100644 --- a/3rdparty/expat/lib/xmltok_impl.h +++ b/3rdparty/expat/lib/xmltok_impl.h @@ -7,7 +7,8 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2017-2019 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -44,7 +45,7 @@ enum { BT_LF, /* line feed = "\n" */ BT_GT, /* greater than = ">" */ BT_QUOT, /* quotation character = "\"" */ - BT_APOS, /* aposthrophe = "'" */ + BT_APOS, /* apostrophe = "'" */ BT_EQUALS, /* equal sign = "=" */ BT_QUEST, /* question mark = "?" */ BT_EXCL, /* exclamation mark = "!" */ diff --git a/3rdparty/expat/lib/xmltok_ns.c b/3rdparty/expat/lib/xmltok_ns.c index 919c74e9f97..fbdd3e3c7b7 100644 --- a/3rdparty/expat/lib/xmltok_ns.c +++ b/3rdparty/expat/lib/xmltok_ns.c @@ -7,7 +7,11 @@ |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd - Copyright (c) 2000-2017 Expat development team + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017-2021 Sebastian Pipping <sebastian@pipping.org> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining @@ -89,7 +93,7 @@ NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, static const ENCODING * NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) { # define ENCODING_MAX 128 - char buf[ENCODING_MAX]; + char buf[ENCODING_MAX] = ""; char *p = buf; int i; XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1); |