commit 8c470e403935c3c20a34bb79b92f9084b73d47dc Author: Laurence Withers Date: Thu Nov 23 00:18:43 2006 +0000 Initial import from libStreamedXML-1.2.7 diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..d025740 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +obj +html diff --git a/COPYING b/COPYING new file mode 100644 index 0000000..d28d2c7 --- /dev/null +++ b/COPYING @@ -0,0 +1,278 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. diff --git a/README b/README new file mode 100644 index 0000000..f945cb8 --- /dev/null +++ b/README @@ -0,0 +1,14 @@ +libCStreamedXML http://www.lwithers.me.uk/projects/libCStreamedXML/ +======================================================================== +(c)2006, Laurence Withers, . +Released under the GNU GPLv2. See file COPYING or +http://www.gnu.org/copyleft/gpl.html for details. + +Really Quick Instructions +------------------------- + +To build: ./make.sh +To install: ./make.sh install + (you might want to set PREFIX, by default it's /usr/local) + +This library has no dependencies other than the C library. diff --git a/libCStreamedXML.kdevelop b/libCStreamedXML.kdevelop new file mode 100644 index 0000000..2ddbc5e --- /dev/null +++ b/libCStreamedXML.kdevelop @@ -0,0 +1,168 @@ + + + + Laurence Withers + l@lwithers.me.uk + $VERSION$ + KDevCustomProject + C++ + + . + false + + + + + + /bin/true + executable + / + + false + true + + + + make + + + + false + 1 + 0 + false + ./make.sh + default + + default + + + + + + + + + + + + + + + + + true + false + false + + + false + true + 10 + + + + + ada + ada_bugs_gcc + bash + bash_bugs + clanlib + fortran_bugs_gcc + gnome1 + gnustep + gtk + gtk_bugs + haskell + haskell_bugs_ghc + java_bugs_gcc + java_bugs_sun + kde2book + opengl + pascal_bugs_fp + php + php_bugs + perl + perl_bugs + python + python_bugs + qt-kdev3 + ruby + ruby_bugs + sdl + sw + w3c-dom-level2-html + w3c-svg + w3c-uaag10 + wxwidgets_bugs + + + Guide to the Qt Translation Tools + Qt Assistant Manual + Qt Designer Manual + Qt Reference Documentation + qmake User Guide + + + KDE Libraries (Doxygen) + + + + + + + + + + + + .h + .cpp + + + + + true + true + true + false + true + true + true + 1 + 1 + 250 + + + + set + m_,_ + theValue + true + true + + + + + + + + + + + + + false + false + + + *.o,*.lo,CVS + false + false + + + + + + + diff --git a/libCStreamedXML.kdevelop.filelist b/libCStreamedXML.kdevelop.filelist new file mode 100644 index 0000000..81bce2d --- /dev/null +++ b/libCStreamedXML.kdevelop.filelist @@ -0,0 +1,4 @@ +# KDevelop Custom Project File List +src/lib/BottomHeader.h +src/lib/TopHeader.h +src/lib/TopSource.cpp diff --git a/make.sh b/make.sh new file mode 100755 index 0000000..b1687fc --- /dev/null +++ b/make.sh @@ -0,0 +1,292 @@ +#!/bin/bash +# libCStreamedXML/make.sh +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + + +# This file is the script used to build libCStreamedXML. There are some +# options that can be edited; these are set below (or you can pass them +# in as variables). +[ -z "${CC}" ] && CC="gcc" +[ -z "${CXX}" ] && CXX="g++" +[ -z "${CFLAGS}" ] && CFLAGS="-g -O2 -W -Wall" +[ -z "${PREFIX}" ] && PREFIX="/usr/local" +[ -z "${LIBDIR}" ] && LIBDIR="${PREFIX}/lib" +[ -z "${BINDIR}" ] && BINDIR="${PREFIX}/bin" +[ -z "${INCLUDEDIR}" ] && INCLUDEDIR="${PREFIX}/include" +[ -z "${DOCSDIR}" ] && DOCSDIR="${PREFIX}/share/doc/libCStreamedXML" + +# for pkg-config +[ -z "${PKGCONFDIR}" ] && PKGCONFDIR="${LIBDIR}/pkgconfig" +[ -z "${FINALLIBDIR}" ] && FINALLIBDIR="${LIBDIR}" +[ -z "${FINALINCLUDEDIR}" ] && FINALINCLUDEDIR="${INCLUDEDIR}" + +# for SDCC-built firmware +[ -z "${HEXDIR}" ] && HEXDIR="${PREFIX}/share/firmware" +[ -z "${SDCC}" ] && SDCC="sdcc" + + + +# Get version information +source version || exit 1 +VERSION="${VERMAJOR}.${VERMINOR}.${VERMICRO}" +if [ ! -z "${VEREXTRA}" ] +then + VERSION="${VERSION}-${VEREXTRA}" +fi + + + +# Get standard functions +[ -z "${VERBOSE}" ] && VERBOSE="0" +source scripts/functions.sh || exit 1 + + +# List of directories which will be emptied by clean. +OUTPUT_DIRS="obj html" + + + +# This function makes a monolithic file out of several source files. Its +# first argument is the name of the output file, and the second is the +# format of monolithic file to create (for example, "C" will cause the +# inclusion of "#line" directives at the top of each included file). +# +# It also examines the following variables: +# MONOLITHIC_TESTS if any file mentioned in this list is newer +# than the output file, then we recreate it +# MONOLITHIC_SOURCE a list (in order) of the source files +# +# Recognised formats are: +# none no special processing happens before each file +# C #line directives are inserted before each file +# and VERSION, VERMAJOR etc. are #defined +# Ch Like C, but for header files (no VERSION #defines) +# +make_monolithic() { + if [ $# -ne 2 ] + then + print_failure "make_monolithic() called with wrong number of arguments" + print_failure "(expecting 2, got $#)" + return 1 + fi + + MONOLITHIC_OUT=$1 + + # extract options + HASHLINE=0 + VERDEFINE=0 + if [ "$2" == "C" ] + then + HASHLINE=1 + VERDEFINE=1 + elif [ "$2" == "Ch" ] + then + HASHLINE=1 + elif [ "$2" == "none" ] + then + HASHLINE=0 # dummy command + else + print_failure "make_monolithic() called with unknown format $2" + return 1 + fi + + echo " Building monolithic file '${MONOLITHIC_OUT}'..." + + MODIFIED=0 + for FILE in ${MONOLITHIC_TESTS} ${MONOLITHIC_SOURCE} + do + if [ ! -e "${FILE}" ] + then + print_failure "'${FILE}' does not exist" + return 1 + fi + + if [ "${FILE}" -nt ${MONOLITHIC_OUT} ] + then + MODIFIED=1 + break + fi + done + + if [ ${MODIFIED} -ne 0 ] + then + do_cmd mkdir -p $(dirname ${MONOLITHIC_OUT}) + do_cmd rm -f ${MONOLITHIC_OUT} || exit 1 + + if [ ${VERDEFINE} -ne 0 ] + then + do_cmd_redir ${MONOLITHIC_OUT} echo "#define VERSION \"${VERSION}\"" || return 1 + do_cmd_redir ${MONOLITHIC_OUT} echo "#define VERMAJOR ${VERMAJOR}" || return 1 + do_cmd_redir ${MONOLITHIC_OUT} echo "#define VERMINOR ${VERMINOR}" || return 1 + do_cmd_redir ${MONOLITHIC_OUT} echo "#define VERMICRO ${VERMICRO}" || return 1 + do_cmd_redir ${MONOLITHIC_OUT} echo "#define VEREXTRA \"${VEREXTRA}\"" || return 1 + fi + + for FILE in ${MONOLITHIC_SOURCE} + do + if [ ${HASHLINE} -ne 0 ] + then + do_cmd_redir ${MONOLITHIC_OUT} echo "#line 1 \"${FILE}\"" || return 1 + fi + do_cmd_redir ${MONOLITHIC_OUT} cat "${FILE}" || return 1 + done + print_success "Done" + else + print_success "Up to date" + fi +} + + + +# This will build a directory tree, if required, with mode 0755. The +# argument is the directory to build. +build_dir_tree() { + # sanity check + if [ $# -ne 1 ] + then + print_failure "build_dir_tree() called with wrong number of arguments" + print_failure "(expecting 1, got $#)" + return 1 + fi + + local DIR="$1" + + # if the directory already exists, return success + [ -d "${DIR}" ] && return 0 + + # if something with this name already exists, but not a directory, + # then fail + if [ -e "${DIR}" ] + then + print_failure "Failed to create directory '${DIR}'" + return 1 + fi + + # build the directory, but if it fails, recurse a level (and handle + # the case where recursion fails) + mkdir "${DIR}" >& /dev/null + if [ $? -ne 0 ] + then + build_dir_tree $(dirname "${DIR}") || return 1 + mkdir "${DIR}" + if [ $? -ne 0 ] + then + print_failure "Failed to create directory '${DIR}'" + return 1 + fi + fi + + # set permissions on newly-created dir and return + chmod 0755 "${DIR}" + return 0 +} + + + +# This will install a file. The first parameter is the source, and the +# second is the destination. The third is the octal mode. +install_file() { + # figure out if $2 is a directory or not + DEST_FILE="$2" + [ -d "$2" ] && DEST_FILE="$2/$(basename $1)" + + echo " Installing: '$1' -> '$2'" + do_cmd cp -fP "$1" "${DEST_FILE}" || return 1 + do_cmd chmod "$3" "${DEST_FILE}" || return 1 + + return 0 +} + + + +# This will install a header file. It is basically similar to +# install_file(), only we strip out the #line directives. +install_header() { + DEST_FILE="$2" + [ -d "$2" ] && DEST_FILE="$2/$(basename $1)" + + echo " Installing header: '$1' -> '$2'" + do_cmd rm -f ${DEST_FILE} || exit 1 + do_cmd_redir ${DEST_FILE} sed -e "s,^#line.*,," $1 || exit 1 + do_cmd chmod "$3" "${DEST_FILE}" || return 1 + + return 0 +} + + + +# This installs a symlink. The first argument is the symlink's name; the +# second the symlink's source filename, and the third is the directory +# in which to create the symlink. +install_symlink() { + echo " Installing symlink: '$3/$2' -> '$1'" + + ( do_cmd cd $3; ln -sf $2 $1 ) || return 1 + + return 0 +} + + + +build_target() { + ITEMS="src/$1/build.default" + if [ ! -e "${ITEMS}" ] + then + ITEMS="$(find src -type f -name build.$1)" + fi + + if [ -z "${ITEMS}" ] + then + print_failure "Unrecognised target '$1'" + return 1 + fi + + for item in ${ITEMS} + do + do_cmd source ${item} || exit 1 + done + return 0 +} + + + +######################################################################## +# Main script +######################################################################## + +if [ $# -eq 0 ] +then + targets="default" +else + targets="$@" +fi + +for func in ${targets} +do + case ${func} in + clean) + echo "Cleaning..." + rm -rf ${OUTPUT_DIRS} + print_success "Done" + ;; + + # bad Kdevelop! bad! + -j1) + ;; + -k) + ;; + + *) + build_target ${func} || exit 1 + ;; + esac +done + +exit 0 + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/run-test.sh b/run-test.sh new file mode 100755 index 0000000..db0a06b --- /dev/null +++ b/run-test.sh @@ -0,0 +1,54 @@ +#!/bin/bash +# libCStreamedXML/test.sh +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + +# Running this script on its own will display a summary of all the +# available tests; running it with arguments runs the relevant test. + + + +# This runs a test, setting the correct library path. +run_test() { + EXE=obj/tests/$1 + shift + if [ ! -x ${EXE} ] + then + echo "No such test '${EXE}'" + return 1 + fi + + LD_LIBRARY_PATH="obj" ${EXE} "$@" || return 1 + return 0 +} + + + +# This prints summary output from each test app. +print_tests() { + echo "Available tests" + echo "---------------------------------------------------------------------" + for EXE in obj/tests/* + do + [ -x ${EXE} ] || continue + NAME=$(echo ${EXE} | sed 's,obj/tests/,,') + echo -ne "${NAME}\t" + LD_LIBRARY_PATH="obj" ${EXE} --print-summary + done +} + + +# Main script +if [ $# -eq 0 ] +then + print_tests + exit 0 +fi + +run_test $* + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/scripts/.gitignore b/scripts/.gitignore new file mode 100644 index 0000000..a540f48 --- /dev/null +++ b/scripts/.gitignore @@ -0,0 +1,12 @@ +build.c++.app +build.c++.lib +build.c++.qtapp +build.c++.tests +build.c.app +build.c.lib +build.c.tests +build.doxygen.docs +build.none.files +build.sdcc.firmware +module-create.sh +release.sh diff --git a/scripts/functions.sh b/scripts/functions.sh new file mode 100755 index 0000000..d02fffe --- /dev/null +++ b/scripts/functions.sh @@ -0,0 +1,68 @@ +#!/bin/bash +# libCStreamedXML/scripts/functions.sh +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + +# Common functions + + + +# Print a success message +print_success() { + if [ -z "${TERM}" -o "${TERM}" == "dumb" ] + then + echo -n " - " + else + (echo -n -e " \E[32m* "; tput sgr0) + fi + echo $* +} + + + +# Print a failure message +print_failure() { + if [ -z "${TERM}" -o "${TERM}" == "dumb" ] + then + echo -n " *** " + else + (echo -n -e " \E[31m*** "; tput sgr0) + fi + echo $* +} + + + +# This function carries out a command, but reports its failure if +# necessary. +do_cmd() { + [ "${VERBOSE}" != "0" ] && echo "$@" + "$@" + if [ $? -ne 0 ] + then + print_failure "'$@' failed." + return 1 + fi +} + + + +# This function carries out a command, but reports its failure if +# necessary. +do_cmd_redir() { + DEST=$1 + shift + [ "${VERBOSE}" != "0" ] && echo "$@ >> ${DEST}" + "$@" >> ${DEST} + if [ $? -ne 0 ] + then + print_failure "'$@' failed." + return 1 + fi +} + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/docs/.params b/src/docs/.params new file mode 100644 index 0000000..efd9ae0 --- /dev/null +++ b/src/docs/.params @@ -0,0 +1 @@ +doxygen docs docs diff --git a/src/docs/Doxyfile.in b/src/docs/Doxyfile.in new file mode 100644 index 0000000..59aa2c8 --- /dev/null +++ b/src/docs/Doxyfile.in @@ -0,0 +1,146 @@ +# libCStreamedXML/src/docs/Doxyfile.in +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + +PROJECT_NAME = libCStreamedXML +OUTPUT_DIRECTORY = +CREATE_SUBDIRS = NO +OUTPUT_LANGUAGE = English +USE_WINDOWS_ENCODING = NO +BRIEF_MEMBER_DESC = YES +REPEAT_BRIEF = YES +ABBREVIATE_BRIEF = +ALWAYS_DETAILED_SEC = NO +INLINE_INHERITED_MEMB = YES +FULL_PATH_NAMES = NO +STRIP_FROM_PATH = +STRIP_FROM_INC_PATH = +SHORT_NAMES = NO +JAVADOC_AUTOBRIEF = NO +MULTILINE_CPP_IS_BRIEF = YES +DETAILS_AT_TOP = YES +INHERIT_DOCS = YES +DISTRIBUTE_GROUP_DOC = NO +TAB_SIZE = 4 +ALIASES = +OPTIMIZE_OUTPUT_FOR_C = NO +OPTIMIZE_OUTPUT_JAVA = NO +SUBGROUPING = YES +EXTRACT_ALL = NO +EXTRACT_PRIVATE = NO +EXTRACT_STATIC = NO +EXTRACT_LOCAL_CLASSES = NO +EXTRACT_LOCAL_METHODS = NO +HIDE_UNDOC_MEMBERS = NO +HIDE_UNDOC_CLASSES = NO +HIDE_FRIEND_COMPOUNDS = YES +HIDE_IN_BODY_DOCS = NO +INTERNAL_DOCS = NO +CASE_SENSE_NAMES = YES +HIDE_SCOPE_NAMES = NO +SHOW_INCLUDE_FILES = NO +INLINE_INFO = YES +SORT_MEMBER_DOCS = YES +SORT_BRIEF_DOCS = NO +SORT_BY_SCOPE_NAME = NO +GENERATE_TODOLIST = YES +GENERATE_TESTLIST = YES +GENERATE_BUGLIST = YES +GENERATE_DEPRECATEDLIST= YES +ENABLED_SECTIONS = +MAX_INITIALIZER_LINES = 30 +SHOW_USED_FILES = NO +SHOW_DIRECTORIES = NO +FILE_VERSION_FILTER = +QUIET = YES +WARNINGS = YES +WARN_IF_UNDOCUMENTED = YES +WARN_IF_DOC_ERROR = YES +WARN_NO_PARAMDOC = YES +WARN_FORMAT = "$file:$line: $text" +WARN_LOGFILE = +FILE_PATTERNS = +RECURSIVE = NO +EXCLUDE = +EXCLUDE_SYMLINKS = NO +EXCLUDE_PATTERNS = +EXAMPLE_PATH = +EXAMPLE_PATTERNS = +EXAMPLE_RECURSIVE = NO +IMAGE_PATH = src/docs +INPUT_FILTER = +FILTER_PATTERNS = +FILTER_SOURCE_FILES = NO +SOURCE_BROWSER = NO +INLINE_SOURCES = NO +STRIP_CODE_COMMENTS = YES +REFERENCED_BY_RELATION = YES +REFERENCES_RELATION = YES +VERBATIM_HEADERS = NO +ALPHABETICAL_INDEX = YES +COLS_IN_ALPHA_INDEX = 5 +IGNORE_PREFIX = +GENERATE_HTML = YES +HTML_OUTPUT = html +HTML_FILE_EXTENSION = .html +HTML_HEADER = +HTML_FOOTER = +HTML_STYLESHEET = +HTML_ALIGN_MEMBERS = YES +GENERATE_HTMLHELP = NO +CHM_FILE = +HHC_LOCATION = +GENERATE_CHI = NO +BINARY_TOC = NO +TOC_EXPAND = NO +DISABLE_INDEX = NO +ENUM_VALUES_PER_LINE = 4 +GENERATE_TREEVIEW = NO +TREEVIEW_WIDTH = 250 +GENERATE_LATEX = NO +GENERATE_RTF = NO +GENERATE_MAN = NO +GENERATE_XML = NO +GENERATE_AUTOGEN_DEF = NO +GENERATE_PERLMOD = NO +ENABLE_PREPROCESSING = YES +MACRO_EXPANSION = NO +EXPAND_ONLY_PREDEF = NO +SEARCH_INCLUDES = YES +INCLUDE_PATH = +INCLUDE_FILE_PATTERNS = +PREDEFINED = DOXYGEN +EXPAND_AS_DEFINED = +SKIP_FUNCTION_MACROS = YES +TAGFILES = +GENERATE_TAGFILE = +ALLEXTERNALS = NO +EXTERNAL_GROUPS = YES +PERL_PATH = /usr/bin/perl +CLASS_DIAGRAMS = YES +HIDE_UNDOC_RELATIONS = YES +HAVE_DOT = YES +CLASS_GRAPH = YES +COLLABORATION_GRAPH = YES +GROUP_GRAPHS = NO +UML_LOOK = NO +TEMPLATE_RELATIONS = NO +INCLUDE_GRAPH = NO +INCLUDED_BY_GRAPH = NO +CALL_GRAPH = NO +GRAPHICAL_HIERARCHY = YES +DIRECTORY_GRAPH = NO +DOT_IMAGE_FORMAT = png +DOT_PATH = +DOTFILE_DIRS = +MAX_DOT_GRAPH_WIDTH = 1024 +MAX_DOT_GRAPH_HEIGHT = 1024 +MAX_DOT_GRAPH_DEPTH = 0 +DOT_TRANSPARENT = YES +DOT_MULTI_TARGETS = YES +GENERATE_LEGEND = YES +DOT_CLEANUP = YES +SEARCHENGINE = NO diff --git a/src/docs/MainPage.dox b/src/docs/MainPage.dox new file mode 100644 index 0000000..b022470 --- /dev/null +++ b/src/docs/MainPage.dox @@ -0,0 +1,20 @@ +/* libCStreamedXML/src/docs/MainPage.dox + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +/*! \mainpage + +libCStreamedXML is a C implementation of a + +Streamed XML processor. It is written using an efficient +state-machine. It is an ASCII-only Streamed XML processor. + +*/ + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/docs/build.default b/src/docs/build.default new file mode 100644 index 0000000..ca22639 --- /dev/null +++ b/src/docs/build.default @@ -0,0 +1 @@ +source src/docs/build.docs diff --git a/src/docs/build.docs b/src/docs/build.docs new file mode 100644 index 0000000..653c323 --- /dev/null +++ b/src/docs/build.docs @@ -0,0 +1,43 @@ +# These are external variables, and shouldn't clash with anything else +# docs_BUILT +# + +MONOLITHIC_DOC="${MONOLITHIC_DOC} $(echo src/docs/*.dox)" +build_target monolithic + +if [ -z ${docs_BUILT} ] +then + echo "Building documentation with Doxygen..." + + DOXYFILE=obj/Doxyfile.docs + + if [ ! -e ${DOXYFILE} ] + then + do_cmd cp src/docs/Doxyfile.in ${DOXYFILE} || return 1 + echo "INPUT = ${MONOLITHIC_DOC}" >> ${DOXYFILE} + echo "PROJECT_NUMBER = ${VERSION}" >> ${DOXYFILE} + fi + + MODIFIED=0 + for file in ${MONOLITHIC_DOC} + do + if [ ${file} -nt html/index.html ] + then + MODIFIED=1 + break + fi + done + + if [ ${MODIFIED} -ne 0 ] + then + do_cmd doxygen ${DOXYFILE} || return 1 + print_success "Documentation built" + else + print_success "Documentation is up to date" + fi + + docs_BUILT=1 +fi + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/docs/build.install b/src/docs/build.install new file mode 100644 index 0000000..016c75c --- /dev/null +++ b/src/docs/build.install @@ -0,0 +1 @@ +source src/docs/build.install-docs diff --git a/src/docs/build.install-docs b/src/docs/build.install-docs new file mode 100644 index 0000000..66167d3 --- /dev/null +++ b/src/docs/build.install-docs @@ -0,0 +1,21 @@ +build_target docs + +# create documentation directories +echo "Installing documentation into ${DOCSDIR}" +build_dir_tree "${DOCSDIR}/html" || return 1 + +# copy across the Doxygen-generated documentation +for file in html/* +do + install_file ${file} ${DOCSDIR}/html 0644 || return 1 +done + +# copy across the generic files +for file in COPYING README +do + install_file ${file} ${DOCSDIR} 0644 || return 1 +done + +print_success "Documentation installed" +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/libCStreamedXML/.params b/src/libCStreamedXML/.params new file mode 100644 index 0000000..eca3504 --- /dev/null +++ b/src/libCStreamedXML/.params @@ -0,0 +1 @@ +c lib libCStreamedXML StreamedXML.h diff --git a/src/libCStreamedXML/BottomHeader.h b/src/libCStreamedXML/BottomHeader.h new file mode 100644 index 0000000..3034856 --- /dev/null +++ b/src/libCStreamedXML/BottomHeader.h @@ -0,0 +1,14 @@ +/* libCStreamedXML/src/libCStreamedXML/BottomHeader.h + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +#endif +/*!@}*/ + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/TopHeader.h b/src/libCStreamedXML/TopHeader.h new file mode 100644 index 0000000..729d936 --- /dev/null +++ b/src/libCStreamedXML/TopHeader.h @@ -0,0 +1,32 @@ +/* libCStreamedXML/src/libCStreamedXML/TopHeader.h + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +#ifndef HEADER_libCStreamedXML +#define HEADER_libCStreamedXML + +// standard includes, or includes needed for type declarations +#include + +/*! \defgroup libCStreamedXML libCStreamedXML interface. + +libCStreamedXML is a C library for parsing Streamed XML data. It is somewhat simpler than the C++ +library (it only parses ASCII data, not Unicode data). In future, the API could be extended to +use only fixed-size buffers, and not to call malloc() at all. This would be advantageous for small +embedded systems (e.g. PICs). + +To parse Streamed XML, you must first create a parser context object with csxml_newParser(). Then +you set up the returned object by changing options and callback functions. Once set up correctly, +pass in data using the csxml_feedChar() and csxml_feedData() functions. Finally, free the parser +object with csxml_freeParser(). + +*/ +/*!@{*/ + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/TopSource.c b/src/libCStreamedXML/TopSource.c new file mode 100644 index 0000000..b77394e --- /dev/null +++ b/src/libCStreamedXML/TopSource.c @@ -0,0 +1,20 @@ +/* libCStreamedXML/src/libCStreamedXML/TopSource.c + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +#include "StreamedXML.h" + +// Below are all the includes used throughout the library. +#include +#include +#include + +//#define DEBUG_STATE_MACHINE + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/buffer.c b/src/libCStreamedXML/buffer.c new file mode 100644 index 0000000..10cab8a --- /dev/null +++ b/src/libCStreamedXML/buffer.c @@ -0,0 +1,100 @@ +/* libCStreamedXML/src/libCStreamedXML/buffer.c + * + * (c)2006, Laurence Withers. Released under the GNU GPL. See file + * COPYING for more information / terms of license. +*/ + +static int do_realloc(struct csxml* ctx, struct csxml_buf* buf) +{ + char* n = realloc(buf->data, buf->size << 1); + if(!n) { + ctx->outOfMemory(ctx, buf->size << 1); + return -1; + } + + buf->size <<= 1; + buf->data = n; + return 0; +} + +static int buffer_copy(struct csxml* ctx, struct csxml_buf* dest, const struct csxml_buf* src) +{ + while(dest->size <= src->len) if(do_realloc(ctx, dest)) return -1; + strcpy(dest->data, src->data); + dest->len = src->len; + return 0; +} + +static int buffer_strcat(struct csxml* ctx, struct csxml_buf* dest, const char* src) +{ + size_t req = strlen(src) + dest->len; + while(req >= dest->size) if(do_realloc(ctx, dest)) return -1; + strcat(dest->data, src); + return 0; +} + +static int buffer_init(struct csxml* ctx, struct csxml_buf* buf) +{ + memset(buf, 0, sizeof(buf)); + buf->size = 256; + buf->data = malloc(buf->size); + if(!buf->data) { + ctx->outOfMemory(ctx, buf->size); + return -1; + } + return 0; +} + +static void buffer_free(struct csxml_buf* buf) +{ + free(buf->data); + memset(buf, 0, sizeof(struct csxml_buf)); +} + +static int do_realloc2(struct csxml* ctx, struct csxml_list* list) +{ + size_t i, newlen = list->size ? (list->size << 1) : 4; + struct csxml_buf* n = realloc(list->data, newlen * sizeof(struct csxml_buf)); + if(!n) { + ctx->outOfMemory(ctx, newlen * sizeof(struct csxml_buf)); + return -1; + } + + memset(n + list->size * sizeof(struct csxml_buf), 0, newlen * sizeof(struct csxml_buf)); + for(i = 0; i < newlen; ++i) { + if(buffer_init(ctx, n + list->size + i)) return -1; + } + + list->size = newlen; + list->data = n; + return 0; +} + +static int list_push(struct csxml* ctx, struct csxml_list* list, struct csxml_buf* buf) +{ + if((list->size == list->len) && do_realloc2(ctx, list)) return -1; + if(buffer_copy(ctx, list->data + list->len, buf)) return -1; + ++list->len; + return 0; +} + +static struct csxml_buf* list_pop(struct csxml_list* list) +{ + return list->data + --list->len; +} + +static void list_free(struct csxml_list* list) +{ + size_t i; + + for(i = 0; i < list->size; ++i) buffer_free(list->data + i); + free(list->data); + memset(list, 0, sizeof(struct csxml_list)); +} + + + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/build.default b/src/libCStreamedXML/build.default new file mode 100644 index 0000000..a24840e --- /dev/null +++ b/src/libCStreamedXML/build.default @@ -0,0 +1 @@ +source src/libCStreamedXML/build.lib diff --git a/src/libCStreamedXML/build.install b/src/libCStreamedXML/build.install new file mode 100644 index 0000000..a8df5b5 --- /dev/null +++ b/src/libCStreamedXML/build.install @@ -0,0 +1 @@ +source src/libCStreamedXML/build.install-lib diff --git a/src/libCStreamedXML/build.install-lib b/src/libCStreamedXML/build.install-lib new file mode 100644 index 0000000..beec81b --- /dev/null +++ b/src/libCStreamedXML/build.install-lib @@ -0,0 +1,36 @@ +build_target libCStreamedXML + +# make paths (this is for Gentoo in particular) +build_dir_tree "${LIBDIR}" || return 1 +build_dir_tree "${PKGCONFDIR}" || return 1 +build_dir_tree "${INCLUDEDIR}" || return 1 + +# install library +echo "Installing libraries into '${LIBDIR}'" +install_file ${libCStreamedXML} ${LIBDIR} 0755 || return 1 +BASE="${libCStreamedXML_BASE}.so" +MAJOR="${BASE}.${SOMAJOR}" +MINOR="${MAJOR}.${SOMINOR}" +MICRO="${MINOR}.${SOMICRO}" +install_symlink "${MINOR}" "${MICRO}" "${LIBDIR}" +install_symlink "${MAJOR}" "${MINOR}" "${LIBDIR}" +install_symlink "${BASE}" "${MAJOR}" "${LIBDIR}" + +# install header +echo "Installing header file '${libCStreamedXML_HEADER}' into ${INCLUDEDIR}" +install_header ${libCStreamedXML_HEADER} ${INCLUDEDIR} 0644 || return 1 + +# install pkgconfig file +echo "Installing package config file into ${PKGCONFDIR}" +PKGCONFFILE=${PKGCONFDIR}/libCStreamedXML.pc +do_cmd rm -f ${PKGCONFFILE} +do_cmd_redir ${PKGCONFFILE} sed \ + -e "s,@VERSION@,${VERSION}," \ + -e "s,@LIBDIR@,${FINALLIBDIR}," \ + -e "s,@INCLUDEDIR@,${FINALINCLUDEDIR}," \ + src/libCStreamedXML/pkgconf.in +do_cmd chmod 0644 ${PKGCONFFILE} +print_success "Done" + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/libCStreamedXML/build.lib b/src/libCStreamedXML/build.lib new file mode 100644 index 0000000..8bcd6a5 --- /dev/null +++ b/src/libCStreamedXML/build.lib @@ -0,0 +1,51 @@ +# These are external variables, and shouldn't clash with anything else +# libCStreamedXML +# libCStreamedXML_BUILT +# libCStreamedXML_HEADER +# libCStreamedXML_BASE + +if [ -z ${libCStreamedXML_BUILT} ] +then + libCStreamedXML_BASE=libCStreamedXML + source src/libCStreamedXML/soversion + + libCStreamedXML="obj/${libCStreamedXML_BASE}.so.${SOMAJOR}.${SOMINOR}.${SOMICRO}" + SO_EXTRA="-lc" + + echo "Building library ${libCStreamedXML}..." + + do_cmd source src/libCStreamedXML/build.monolithic || return 1 + + MODIFIED=0 + for test in ${MONOLITHIC_TESTS} ${HDR} ${SRC} + do + if [ ${test} -nt ${libCStreamedXML} ] + then + MODIFIED=1 + break + fi + done + + if [ ${MODIFIED} -ne 0 ] + then + echo " Compiling" + + SONAME="${libCStreamedXML_BASE}.so.${SOMAJOR}.${SOMINOR}" + do_cmd ${CC} ${CFLAGS} -Iobj -shared -fpic -o "${libCStreamedXML}" \ + -Wl,-soname,${SONAME} \ + ${SRC} ${SO_EXTRA} || return 1 + + # make tests work + do_cmd ln -sf $(basename ${libCStreamedXML}) obj/${SONAME} || return 1 + + print_success "Library built" + else + print_success "Library up to date" + fi + + libCStreamedXML_BUILT=1 + libCStreamedXML_HEADER=${HDR} + +fi +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/libCStreamedXML/build.monolithic b/src/libCStreamedXML/build.monolithic new file mode 100644 index 0000000..733082a --- /dev/null +++ b/src/libCStreamedXML/build.monolithic @@ -0,0 +1,21 @@ +# These are external variables, and shouldn't clash with anything else +# libCStreamedXML_MONOLITHIC + +SRC="obj/libCStreamedXML.c" +HDR="obj/StreamedXML.h" + +MONOLITHIC_TESTS="src/libCStreamedXML/build.lib src/libCStreamedXML/build.monolithic" + +if [ -z "${libCStreamedXML_MONOLITHIC}" ] +then + MONOLITHIC_SOURCE="$(echo src/libCStreamedXML/{TopHeader,types,functions,BottomHeader}.h)" + make_monolithic ${HDR} Ch || return 1 + + MONOLITHIC_SOURCE="$(echo src/libCStreamedXML/{TopSource,buffer,defaults,parser}.c)" + make_monolithic ${SRC} C || return 1 + + libCStreamedXML_MONOLITHIC=1 + MONOLITHIC_DOC="${MONOLITHIC_DOC} ${HDR}" +fi +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/libCStreamedXML/defaults.c b/src/libCStreamedXML/defaults.c new file mode 100644 index 0000000..a02e2f1 --- /dev/null +++ b/src/libCStreamedXML/defaults.c @@ -0,0 +1,79 @@ +/* libCStreamedXML/src/libCStreamedXML/defaults.c + * + * (c)2006, Laurence Withers. Released under the GNU GPL. See file + * COPYING for more information / terms of license. +*/ + +static void default_notWellFormed(const struct csxml* ctx, const char* reason) +{ + fprintf(stderr, "Streamed XML is not well formed.\n Line : %d\n Col : %d\n Reason: %s\n", + ctx->line + 1, ctx->col + 1, reason); +} + + + +static void default_outOfMemory(const struct csxml* ctx, size_t amount) +{ + (void)ctx; + fprintf(stderr, "Streamed XML parser: out of memory allocating %lu bytes\n", (unsigned long)amount); +} + + + +static void default_unknownEntity(const struct csxml* ctx, const char* ent) +{ + fprintf(stderr, "Unknown entity referenced in Streamed XML.\n Line: %d\n Col : %d\n Name: %s\n", + ctx->line + 1, ctx->col + 1, ent); +} + + + +static int default_discard(const struct csxml* ctx, const char* x) +{ + (void)ctx; + (void)x; + return 0; +} + + + +static int default_cdata(const struct csxml* ctx, const char* data) +{ + return ctx->content(ctx, data); +} + + + +static int default_discardPI(const struct csxml* ctx, const char* target, const char* data) +{ + (void)ctx; + (void)target; + (void)data; + return 0; +} + + + +static int default_discardElem(const struct csxml* ctx, const char* elemName, int numAttrs) +{ + (void)ctx; + (void)elemName; + (void)numAttrs; + return 0; +} + + + +static const char* default_discardEnt(const struct csxml* ctx, const char* ent) +{ + (void)ctx; + (void)ent; + return 0; +} + + + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/functions.h b/src/libCStreamedXML/functions.h new file mode 100644 index 0000000..9075ba9 --- /dev/null +++ b/src/libCStreamedXML/functions.h @@ -0,0 +1,102 @@ +/* libCStreamedXML/src/libCStreamedXML/types.h + * + * (c)2006, Laurence Withers. Released under the GNU GPL. See file + * COPYING for more information / terms of license. +*/ + + + +/*! \brief Allocate and set up a new parser object. + +\retval 0 on error (see \a errno). +\returns Pointer to newly-allocated parser object. + +Call this function to obtain a parser context object. The object is initially populated with +sensible defaults (\a expandEntities is 1, the error callback functions print messages to stderr, +the data callback functions discard the data, etc.). + +*/ +struct csxml* csxml_newParser(); + + + +/*! \brief Free an existing parser object. + +\param ctx The object to free (may be 0). + +Frees a parser object and all of its associated data structures (strings, lists, etc.). + +*/ +void csxml_freeParser(struct csxml* ctx); + + + +/*! \brief Parse a character. + +\param ctx Parser context. +\param ch Character to parse. +\retval 0 on success. +\retval -1 on XML error. +\retval (non-0) if any callback function signals an error. + +This function parses a single character. It will generate callbacks as appropriate. If one of the +callback functions returns a non-zero value, that value is returned from this function and the +object is put into an error state. If the streamed XML is not well formed, or some other parsing +error occurs, -1 will be returned and the object will be put into an error state. + +Once in an error state, the function will simply discard data passed to it and return 0. However, +a lower-level parser is still running and is capable of matching stream restart markers, allowing +the parser to be reset. + +*/ +int csxml_feedChar(struct csxml* ctx, char ch); + + + +/*! \brief Look up an entity. + +\param ctx Parser context. +\param ent Entity name. +\retval 0 on error. +\returns Pointer to null-terminated string of expanded entity text. + +This function is called to dereference entities. It handles the standard entities itself, and chains +on to the entityRef callback of the parser if needed. If the entity is not found, it calls the +unknownEntity callback and returns 0. + +*/ +const char* csxml_entityRef(struct csxml* ctx, const char* ent); + + + +/*! \brief Reset parser. + +\param ctx Parser context. + +This function will reset the parser into its initial state, as though no data had yet been +encountered. This is called after stream restart markers for example. + +*/ +void csxml_reset(struct csxml* ctx); + + + + +/*! \brief Parse a block of data. + +\param ctx Parser context. +\param data Pointer to block of data. +\param amt Number of bytes to parse. + +This function will parse each character in the block of data. If an error is encountered, the usual +process (callback, error state) is followed, but this function will continue to feed in data. The +idea is that you continue to feed in data from your data source, which might have a restart marker +(at which point the parsing will once again continue). + +*/ +void csxml_feedData(struct csxml* ctx, const char* data, size_t amt); + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/parser.c b/src/libCStreamedXML/parser.c new file mode 100644 index 0000000..7efea85 --- /dev/null +++ b/src/libCStreamedXML/parser.c @@ -0,0 +1,693 @@ +/* libCStreamedXML/src/libCStreamedXML/parser.c + * + * (c)2006, Laurence Withers. Released under the GNU GPL. See file + * COPYING for more information / terms of license. +*/ + +//#define DEBUG_STATE_MACHINE + +#ifdef DEBUG_STATE_MACHINE +#include +#endif + +#include +#include +#include + + + +enum csxml_State { + StateNone, // at element or stream level + StateRestartMarker, // after ', '?' + ClassOther, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // '@', 'A'--'C' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'D'--'G' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'H'--'K' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'L'--'O' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'P'--'S' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'T'--'W' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassOther, // 'X'--'Z', '[' + ClassOther, ClassOther, ClassOther, ClassNameStartChar, // '\\', ']', '^', '_' + ClassOther, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // '`', 'a'--'c' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'd'--'g' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'h'--'k' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'l'--'o' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 'p'--'s' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, // 't'--'w' + ClassNameStartChar, ClassNameStartChar, ClassNameStartChar, ClassOther, // 'x'--'z', '{' + ClassOther, ClassOther, ClassOther, ClassInvalid // '|', '}', '~', control 7F +}; + + + +int csxml_feedChar(struct csxml* ctx, char ch) +{ + enum TokenClass c; + int try; + +#ifdef DEBUG_STATE_MACHINE + printf("%p: Character '%c' (%02X), state %d, buffer %s\n", ctx, ch, ch, ctx->state, ctx->buffer.data); +#endif + +#define ERROR(_reason) do { \ + ctx->state = StateError; \ + ctx->notWellFormed(ctx, _reason); \ + return -1; \ +}while(0) + +#define APPEND_CH(_whichbuf, _ch) do { \ + ctx-> _whichbuf .data[ctx-> _whichbuf .len++] = _ch; \ + if((ctx-> _whichbuf .len == ctx-> _whichbuf .size) && \ + do_realloc(ctx, &ctx-> _whichbuf)) return -1; \ + ctx-> _whichbuf .data[ctx-> _whichbuf .len] = 0; \ +}while(0) + +#define CLEAR_BUFFER(_whichbuf) do { \ + ctx-> _whichbuf .data[0] = 0; \ + ctx-> _whichbuf .len = 0; \ +}while(0) + +#define TRY(_x) do { \ + try = (_x); \ + if(try) { \ + ctx->state = StateError; \ + return try; \ + } \ +}while(0) + + if(ch == xmlRestartMarker[ctx->restartCount]) { + if(++ctx->restartCount == 11) { + ctx->state = StateRestartMarker; + csxml_reset(ctx); + return 0; + } + } else { + ctx->restartCount = 0; + } + + if(ch & ~0x7F) c = ClassInvalid; + else c = token_classes[(int)ch]; + + if(ch == '\r') { + ctx->skipNextNewline = 1; + ch = '\n'; + ++ctx->line; + ctx->col = 0; + } else if(ch == '\n') { + if(ctx->skipNextNewline) return 0; + ++ctx->line; + ctx->col = 0; + } else { + ctx->skipNextNewline = 0; + } + + if(c == ClassInvalid) ERROR("Restricted character encountered."); + + // deal with char appropriately, according to state + switch(ctx->state) { + case StateError: + return 0; + + case StateNone: + switch(c) { + case ClassWhitespace: + APPEND_CH(buffer, ch); + break; + + case ClassOpenTag: + ctx->state = StateOpen; + if(ctx->buffer.len) TRY(ctx->whiteSpace(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + break; + + case ClassEntity: + if(ctx->expandEntities) { + if(!ctx->elementDepth) ERROR("Entities cannot appear at stream level."); + if(ctx->buffer.len) TRY(ctx->whiteSpace(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + ctx->parsingAttr = 0; + ctx->state = StateEntity; + break; + } + + // fall through + default: + if(!ctx->elementDepth) ERROR("Content cannot appear at stream level."); + ctx->state = StateData; + if(ctx->buffer.len) TRY(ctx->whiteSpace(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + APPEND_CH(buffer, ch); + break; + } + break; + + case StateData: + switch(c) { + case ClassOpenTag: + ctx->state = StateOpen; + TRY(ctx->content(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + break; + + case ClassEntity: + ctx->parsingAttr = 0; + ctx->state = StateEntity; + break; + + default: + APPEND_CH(buffer, ch); + break; + } + break; + + case StateCDATA: + if(ch == ']') ctx->state = StateCDATA1; + else APPEND_CH(buffer, ch); + break; + + case StateCDATA1: + if(ch == ']') ctx->state = StateCDATA2; + else { + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ch); + ctx->state = StateCDATA; + } + break; + + case StateCDATA2: + if(ch == '>') { + ctx->state = StateNone; + TRY(ctx->cdata(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + } else if(ch == ']') { + APPEND_CH(buffer, ']'); + } else { + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ch); + ctx->state = StateCDATA; + } + break; + + case StateRestartMarker: + if(ch == ']') ctx->state = StateRestartMarker1; + else APPEND_CH(buffer, ch); + break; + + case StateRestartMarker1: + if(ch == ']') ctx->state = StateRestartMarker2; + else { + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ch); + ctx->state = StateRestartMarker; + } + break; + + case StateRestartMarker2: + if(ch == '>') { + TRY(ctx->streamRestart(ctx, ctx->buffer.data)); + csxml_reset(ctx); + + } else if(ch == ']') { + APPEND_CH(buffer, ']'); + + } else { + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ']'); + APPEND_CH(buffer, ch); + ctx->state = StateRestartMarker; + } + break; + + case StateOpen: + switch(c) { + case ClassNameStartChar: + ctx->state = StateElemName; + ctx->elemAttrNames.len = 0; + ctx->elemAttrVals.len = 0; + CLEAR_BUFFER(elemName); + APPEND_CH(elemName, ch); + break; + + default: + if(ch == '!') ctx->state = StateOpenBang; + else if(ch == '?') { + ctx->state = StatePI; + CLEAR_BUFFER(buffer2); + } else if(ch == '/') { + if(!ctx->elementDepth) ERROR("Encountered a close tag at stream level."); + ctx->state = StateClose; + } else ERROR("Invalid start character for element."); + break; + } + break; + + case StatePI: + if(ch == '?') ctx->state = StatePI2; + else if(c == ClassWhitespace) { + ctx->state = StatePIData; + CLEAR_BUFFER(buffer); + } else APPEND_CH(buffer2, ch); + break; + + case StatePI2: + if(ch != '>') ERROR("Invalid target for PI"); + else { + ctx->state = StateNone; + TRY(ctx->PI(ctx, ctx->buffer2.data, 0)); + } + break; + + case StatePIData: + if(ch == '?') ctx->state = StatePI3; + else APPEND_CH(buffer, ch); + break; + + case StatePI3: + if(ch == '>') { + ctx->state = StateNone; + TRY(ctx->PI(ctx, ctx->buffer2.data, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + } else if(ch == '?') { + APPEND_CH(buffer, '?'); + } else { + APPEND_CH(buffer, '?'); + APPEND_CH(buffer, ch); + ctx->state = StatePIData; + } + break; + + case StateOpenBang: + if(ch == '[') { + // restart markers handled by lower layer + ctx->state = StateOpenCdataMarker; + ctx->xmlCount = 3; + if(!ctx->elementDepth) ERROR("CDATA sections not valid at stream level."); + } else if(ch == '-') ctx->state = StateOpenComment; + else ERROR("Invalid special tag."); + break; + + case StateOpenCdataMarker: + if(ch != xmlCdataMarker[ctx->xmlCount]) ERROR("Invalid marked section."); + if(!xmlCdataMarker[++ctx->xmlCount]) ctx->state = StateCDATA; + break; + + case StateOpenComment: + if(ch != '-') ERROR("Invalid special tag."); + ctx->state = StateComment; + CLEAR_BUFFER(buffer); + break; + + case StateComment: + if(ch == '-') ctx->state = StateComment2; + else APPEND_CH(buffer, ch); + break; + + case StateComment2: + if(ch == '-') ctx->state = StateComment3; + else { + APPEND_CH(buffer, '-'); + APPEND_CH(buffer, ch); + ctx->state = StateComment; + } + break; + + case StateComment3: + if(ch != '>') ERROR("`--' not valid in comments"); + ctx->state = StateNone; + TRY(ctx->comment(ctx, ctx->buffer.data)); + CLEAR_BUFFER(buffer); + break; + + case StateElemName: + switch(c) { + case ClassWhitespace: + ctx->state = StateElemTag; + CLEAR_BUFFER(buffer); + break; + + case ClassNameStartChar: + case ClassNameChar: + APPEND_CH(elemName, ch); + break; + + default: + switch(ch) { + case L'>': + CLEAR_BUFFER(buffer); + TRY(list_push(ctx, &ctx->elemStack, &ctx->elemName)); + ctx->state = StateNone; + TRY(ctx->element(ctx, ctx->elemName.data, 0)); + ++ctx->elementDepth; + break; + + case L'/': + ctx->state = StateNeedClose; + break; + + default: + ERROR("Invalid character in tag name."); + } + } + break; + + case StateElemTag: + switch(c) { + case ClassWhitespace: + break; + + case ClassNameStartChar: + ctx->state = StateElemAttrName; + CLEAR_BUFFER(buffer); + APPEND_CH(buffer, ch); + break; + + default: + switch(ch) { + case '>': + TRY(list_push(ctx, &ctx->elemStack, &ctx->elemName)); + ctx->state = StateNone; + TRY(ctx->element(ctx, ctx->elemName.data, ctx->elemAttrNames.len)); + ++ctx->elementDepth; + break; + + case '/': + ctx->state = StateNeedClose; + break; + + default: + ERROR("Invalid character in tag."); + } + } + break; + + case StateElemAttrName: + switch(c) { + case ClassNameStartChar: + case ClassNameChar: + APPEND_CH(buffer, ch); + break; + + default: + if(ch != '=') ERROR("Invalid character in attribute name."); + TRY(list_push(ctx, &ctx->elemAttrNames, &ctx->buffer)); + CLEAR_BUFFER(buffer); + ctx->state = StateElemAttrEq; + break; + } + break; + + case StateElemAttrEq: + if(ch == '\'') ctx->singleQuote = 1; + else if(ch == '"') ctx->singleQuote = 0; + else ERROR("Invalid character in attribute."); + ctx->state = StateElemAttrVal; + break; + + case StateElemAttrVal: + if((ctx->singleQuote && ch == '\'') || (!ctx->singleQuote && ch == '"')) { + TRY(list_push(ctx, &ctx->elemAttrVals, &ctx->buffer)); + ctx->state = StateElemAttrDone; + } else if(ctx->expandEntities && ch == L'&') { + ctx->parsingAttr = 1; + ctx->state = StateEntity; + } else APPEND_CH(buffer, ch); + break; + + case StateElemAttrDone: + switch(c) { + case ClassWhitespace: + ctx->state = StateElemTag; + break; + + default: + if(ch == '/') { + ctx->state = StateNeedClose; + } else if(ch == '>') { + ctx->state = StateNone; + CLEAR_BUFFER(buffer); + TRY(ctx->element(ctx, ctx->elemName.data, ctx->elemAttrVals.len)); + TRY(list_push(ctx, &ctx->elemStack, &ctx->elemName)); + ++ctx->elementDepth; + } else ERROR("Invalid character after attribute."); + break; + } + break; + + case StateNeedClose: + if(ch != '>') ERROR("Stray `/' in open tag."); + ctx->state = StateNone; + CLEAR_BUFFER(buffer); + TRY(ctx->element(ctx, ctx->elemName.data, ctx->elemAttrVals.len)); + TRY(ctx->closeTag(ctx, ctx->elemName.data)); + break; + + case StateClose: + if(c != ClassNameStartChar) ERROR("Invalid character in close tag name."); + APPEND_CH(buffer, ch); + ctx->state = StateClosing; + break; + + case StateClosing: + switch(c) { + case ClassNameStartChar: + case ClassNameChar: + APPEND_CH(buffer, ch); + break; + + case ClassWhitespace: + ctx->state = StateNeedClose2; + break; + + default: + if(ch != '>') ERROR("Invalid character in close tag name."); + TRY(buffer_copy(ctx, &ctx->elemName, list_pop(&ctx->elemStack))); + if(strcmp(ctx->elemName.data, ctx->buffer.data)) ERROR("Mismatched close tag."); + ctx->state = StateNone; + CLEAR_BUFFER(buffer); + TRY(ctx->closeTag(ctx, ctx->elemName.data)); + --ctx->elementDepth; + } + break; + + case StateNeedClose2: + if(c == ClassWhitespace) break; + if(ch != '>') ERROR("Invalid data in close tag."); + TRY(buffer_copy(ctx, &ctx->elemName, list_pop(&ctx->elemStack))); + if(strcmp(ctx->elemName.data, ctx->buffer.data)) ERROR("Mismatched close tag."); + ctx->state = StateNone; + CLEAR_BUFFER(buffer); + TRY(ctx->closeTag(ctx, ctx->elemName.data)); + --ctx->elementDepth; + break; + + case StateEntity: + if(ch == '#') { + ctx->state = StateCharEntity; + ctx->entityChar = 0; + } else if(c == ClassNameStartChar) { + CLEAR_BUFFER(buffer2); + APPEND_CH(buffer2, ch); + ctx->state = StateEntityName; + } else ERROR("Invalid entity name."); + break; + + case StateCharEntity: + if(ch == ';') { + APPEND_CH(buffer, ctx->entityChar); + ctx->state = ctx->parsingAttr ? StateElemAttrVal : StateData; + break; + + } else if(ch >= '0' && ch <= '9') { + ctx->entityChar *= 10; + ctx->entityChar += (ch - '0'); + if(!ctx->entityChar || ctx->entityChar > 126) ERROR("Character code out of range in character entity."); + } else ERROR("Invalid character in character entity."); + break; + + case StateEntityName: + if(ch == ';') { + const char* e = csxml_entityRef(ctx, ctx->buffer2.data); + TRY(!e || buffer_strcat(ctx, &ctx->buffer, e)); + ctx->state = ctx->parsingAttr ? StateElemAttrVal : StateData; + break; + } + if(c != ClassNameChar && c != ClassNameStartChar) ERROR("Invalid entity name."); + APPEND_CH(buffer2, ch); + break; + } + ++ctx->col; + return 0; +} + + + +const char* csxml_entityRef(struct csxml* ctx, const char* ent) +{ + const char* q = 0; + + if(!strcmp(ent, "quot")) return "\""; + if(!strcmp(ent, "amp")) return "&"; + if(!strcmp(ent, "apos")) return "'"; + if(!strcmp(ent, "lt")) return "<"; + if(!strcmp(ent, "gt")) return ">"; + + q = ctx->entityRef(ctx, ent); + if(!q) { + ctx->state = StateError; + ctx->unknownEntity(ctx, ent); + return 0; + } + + return q; +} + + + +void csxml_reset(struct csxml* ctx) +{ + CLEAR_BUFFER(buffer); + CLEAR_BUFFER(buffer2); + CLEAR_BUFFER(elemName); + ctx->state = StateNone; + ctx->xmlCount = 0; + ctx->elementDepth = 0; + ctx->restartCount = 0; + ctx->skipNextNewline = 0; + ctx->parsingAttr = 0; + ctx->line = 0; + ctx->col = 0; + ctx->elemStack.len = 0; + ctx->elemAttrNames.len = 0; + ctx->elemAttrVals.len = 0; +} + + + +#undef ERROR +#undef APPEND_CH +#undef CLEAR_BUFFER + + + +void csxml_freeParser(struct csxml* ctx) +{ + if(!ctx) return; + buffer_free(&ctx->buffer); + buffer_free(&ctx->buffer2); + buffer_free(&ctx->elemName); + list_free(&ctx->elemStack); + list_free(&ctx->elemAttrNames); + list_free(&ctx->elemAttrVals); +} + + + +struct csxml* csxml_newParser() +{ + struct csxml* ctx = 0; + + ctx = malloc(sizeof(struct csxml)); + if(!ctx) return 0; + memset(ctx, 0, sizeof(struct csxml)); + + if(buffer_init(ctx, &ctx->buffer) || buffer_init(ctx, &ctx->buffer2) || buffer_init(ctx, &ctx->elemName)) { + csxml_freeParser(ctx); + return 0; + } + + ctx->expandEntities = 1; + + ctx->notWellFormed = default_notWellFormed; + ctx->outOfMemory = default_outOfMemory; + ctx->unknownEntity = default_unknownEntity; + ctx->whiteSpace = default_discard; + ctx->content = default_discard; + ctx->cdata = default_cdata; + ctx->streamRestart = default_discard; + ctx->PI = default_discardPI; + ctx->comment = default_discard; + ctx->element = default_discardElem; + ctx->closeTag = default_discard; + ctx->entityRef = default_discardEnt; + + return ctx; +} + + + +void csxml_feedData(struct csxml* ctx, const char* data, size_t amt) +{ + while(amt--) csxml_feedChar(ctx, *data++); +} + + + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/libCStreamedXML/pkgconf.in b/src/libCStreamedXML/pkgconf.in new file mode 100644 index 0000000..0b5ddf5 --- /dev/null +++ b/src/libCStreamedXML/pkgconf.in @@ -0,0 +1,21 @@ +# libCStreamedXML/src/lib/libCStreamedXML/pkgconf.in +# +# Metadata file for pkg-config +# ( http://www.freedesktop.org/software/pkgconfig/ ) +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + +# Name, description +Name: libCStreamedXML +Description: C library for parsing Streamed XML +Version: @VERSION@ + +# Requirements +Requires: + +# Compilation information +Libs: -L@LIBDIR@ -lCStreamedXML +Cflags: -I@INCLUDEDIR@ diff --git a/src/libCStreamedXML/soversion b/src/libCStreamedXML/soversion new file mode 100644 index 0000000..d840856 --- /dev/null +++ b/src/libCStreamedXML/soversion @@ -0,0 +1,17 @@ +# libCStreamedXML/src/libCStreamedXML/soversion +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + + + +# SOMAJOR and SOMINOR are included in the library's soname. They need to +# be bumped on a binary-incompatible release. They are both single +# integers. +SOMAJOR=0 +SOMINOR=0 + +# SOMICRO is bumped every time there is a binary-compatible release. +SOMICRO=5 diff --git a/src/libCStreamedXML/types.h b/src/libCStreamedXML/types.h new file mode 100644 index 0000000..16a6ced --- /dev/null +++ b/src/libCStreamedXML/types.h @@ -0,0 +1,322 @@ +/* libCStreamedXML/src/libCStreamedXML/types.h + * + * (c)2006, Laurence Withers. Released under the GNU GPL. See file + * COPYING for more information / terms of license. +*/ + + + +/*! \brief String buffer. + +This type implements a simple string buffer. The string should be kept null-terminated. The \a data +pointer is reallocated as necessary (i.e. when \a len becomes equal to \a size). \a len is the +string length (excluding terminating null) and \a size is the size of the allocated buffer. It is +never valid for \a data or \a size to be 0. + +*/ +struct csxml_buf { + /// Pointer to string (null terminated). + char* data; + + /// Length of string (excluding null). + size_t len; + + /// Size of allocated buffer. + size_t size; +}; + + + +/*! \brief String list. + +This type implements a dynamic array of strings (using the struct csxml_buf type). The \a data +pointer is reallocated as necessary (i.e. when \a len becomes equal to \a size). \a len is the +number of valid elements in the array and \a size is the size of the allocated buffer. It is valid +for \a data and \a size to be zero. + +*/ +struct csxml_list { + /// Array of buffers (all allocated elements are valid and initialised). + struct csxml_buf* data; + + /// Number of elements in use. + size_t len; + + /// Number of allocated elements. + size_t size; +}; + + + +/*! \brief Streamed XML parser context. + +This structure contains all the details of a Streamed XML parsing operation. Most fields are +internal to the parser and should not be touched; those are briefly documented here. You may want to +change the \a expandEntities option, examine the \a line and \a col variables, and change the +callback functions. + +Those members marked Internal: are subject to change (either in semantics, type or existence). + +*/ +struct csxml { + /// Option: change "&lt;" to "<", etc. if non-zero (the default). Change to 0 to leave + /// entities inline. + int expandEntities; + + /// Current line (from 0, starts from last restart marker). + int line; + /// Current column (from 0, starts from last restart marker). + int col; + + /// List of attribute names for current element. + struct csxml_list elemAttrNames; + /// List of attribute values for current element. + struct csxml_list elemAttrVals; + + /// User data. + void* user; + + + /*! \brief Error callback: Streamed XML is not well formed. + + \param ctx Parsing context. + \param reason Human-readable description of error. + + This function is called whenever badly-formed Streamed XML is encountered (e.g. if content is + encountered at stream-level). + + The default implementation prints a formatted message to \a stderr. + + */ + void (*notWellFormed)(const struct csxml* ctx, const char* reason); + + + + /*! \brief Error callback: out of memory. + + \param ctx Parsing context. + \param amount Number of bytes we tried to allocate. + + This function is called whenever a dynamic string resizing operation (or similar) fails. It is + called with the number of bytes the library attempted to allocate. + + The default implementation prints a formatted message to \a stderr. + + \todo When parsing extremely long content sections, we could just call the content() callback + when memory is low rather than failing altogether. + + */ + void (*outOfMemory)(const struct csxml* ctx, size_t amount); + + + + /*! \brief Error callback: reference to unknown entity. + + \param ctx Parsing context. + \param ent Name of the referenced entity. + + If an entity is referenced by name (e.g. "&myEntity;" is encountered) but the lookup in the + default entity list and through the entityRef() callback fails to resolve the content, this + function is called. + + The default implementation prints a formatted message to \a stderr. + + */ + void (*unknownEntity)(const struct csxml* ctx, const char* ent); + + + + /*! \brief Callback: whitespace. + + \param ctx Parsing context. + \param ws Pointer to string of whitespace. + \returns Zero on success, non-zero on error. + + This function is called whenever a block of whitespace is encountered at stream level or + immediately after some structural element (i.e. on leading whitespace within elements). It is + generally safe to discard it, unless you need to reproduce the file verbatim. Once content is + encountered within an element, any further whitespace will be reported through the content() + callback, up to the next structural element. + + The default implementation discards the data. + + */ + int (*whiteSpace)(const struct csxml* ctx, const char* ws); + + + + /*! \brief Callback: content. + + \param ctx Parsing context. + \param content Pointer to string of cdata. + \returns Zero on success, non-zero on error. + + This function is called whenever textual content (cdata) is encountered inside an element. It + may be called multiple times simultaneously, in which case the data from each call should be + concatenated. If \a expandEntities is non-zero, then this function will also be called with the + expanded text from any entities encountered, rather than the entities themselves. + + The default implementation discards the data. + + */ + int (*content)(const struct csxml* ctx, const char* content); + + + + /*! \brief Callback: cdata block. + + \param ctx Parsing context. + \param cdata Pointer to string of cdata. + \returns Zero on success, non-zero on error. + + This function is called for all data inside a CDATA marked section. It is useful to + differentiate between cdata encoded in this manner and normal cdata if you are trying to + reproduce the orginal file verbatim. + + The default implementation calls content() with the same data. + + */ + int (*cdata)(const struct csxml* ctx, const char* cdata); + + + + /*! \brief Callback: stream restart marker. + + \param ctx Parsing context. + \param marker Pointer to marker string. + \returns Zero on success, non-zero on error. + + Whenever a stream restart marker is encountered, this function is called with the data found + inside the marker. + + The default implementation ignores the data (but note that the parser state is always reset, + regardless of what the callback does). + + */ + int (*streamRestart)(const struct csxml* ctx, const char* marker); + + + + /*! \brief Callback: processing instruction. + + \param ctx Parsing context. + \param target PI target. + \param data PI data (may be 0). + \returns Zero on success, non-zero on error. + + This callback is used to report processing instructions (PIs). If the PI has no data, then the + \a data variable can be set to 0. + + The default implementation ignores the data. + + */ + int (*PI)(const struct csxml* ctx, const char* target, const char* data); + + + + /*! \brief Callback: comment. + + \param ctx Parsing context. + \param comment Pointer to comment string data. + \returns Zero on success, non-zero on error. + + This callback is used to report comments. It is only useful if you wish to reproduce the source + file verbatim (for instance, you want to alter some data in a file but preserve user comments). + + The default implementation ignores the data. + + */ + int (*comment)(const struct csxml* ctx, const char* comment); + + + + /*! \brief Callback: element. + + \param ctx Parsing context. + \param elemName Pointer to element name string. + \param numAttrs Number of attributes. + \returns Zero on success, non-zero on error. + + This callback is used whenever an element open tag is encountered. To parse attributes, use the + numAttrs variable to determine how many there are, and then access them with: + + 
        // get attribute name
+        const char* elemName = ctx->elemAttrNames.data[i].data;
+
+        // get attribute value
+        const char* elemValue = ctx->elemAttrVals.data[i].data;
+ + In the case of an empty element, the closeTag() callback will be called immediately afterwards. + + The default implemenation ignores the data. + + */ + int (*element)(const struct csxml* ctx, const char* elemName, int numAttrs); + + + + /*! \brief Callback: close tag. + + \param ctx Parsing context. + \param elemName Element name. + \returns Zero on success, non-zero on error. + + This function is called whenever an element close tag is encountered. The element name will + always match the open tag element name (if not, the Streamed XML is not well formed, and an + error will be signalled before this callback is triggered). + + The default implementation ignores the data. + + */ + int (*closeTag)(const struct csxml* ctx, const char* elemName); + + + + /*! \brief Callback: entity reference. + + \param ctx Parsing context. + \param ent Entity name. + \retval 0 if the entity name does not match any known entity. + \returns Pointer to null-terminated string data for expanding entity. + + This function is called whenever \a expandEntities is true and an entity is encountered in cdata + or an attribute value. It is only called if the entity does not match one of the five built-in + defaults. You only need to provide an implementation if you know about some additional entities. + + The default implementation returns 0 ("no such entity"). + + */ + const char* (*entityRef)(const struct csxml* ctx, const char* ent); + + + + /// Internal: string buffer. + struct csxml_buf buffer; + /// Internal: string buffer. + struct csxml_buf buffer2; + /// Internal: string buffer. + struct csxml_buf elemName; + /// Internal: stack of element names, used to match open/close tags. + struct csxml_list elemStack; + /// Internal: state machine state. + int state; + /// Internal: for matching strings. + int xmlCount; + /// Internal: depth in element tree (0 = stream level). + int elementDepth; + /// Internal: for matching against restart marker string. + int restartCount; + /// Internal: for stripping windows line endings. + int skipNextNewline; + /// Internal: flag to check if we are currently parsing an attribute while expanding an entity. + int parsingAttr; + /// Internal: flag to record if current attribute was quoted with ' or " char. + int singleQuote; + /// Internal: used to expand character entities. + int entityChar; +}; + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/tests/.params b/src/tests/.params new file mode 100644 index 0000000..7be9ebb --- /dev/null +++ b/src/tests/.params @@ -0,0 +1 @@ +c tests tests libCStreamedXML diff --git a/src/tests/build.default b/src/tests/build.default new file mode 100644 index 0000000..2d979e2 --- /dev/null +++ b/src/tests/build.default @@ -0,0 +1,3 @@ +source src/tests/build.tests +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/tests/build.tests b/src/tests/build.tests new file mode 100644 index 0000000..1a098ed --- /dev/null +++ b/src/tests/build.tests @@ -0,0 +1,43 @@ +# These are external variables, and shouldn't clash with anything else +# tests_BUILT +# + +build_target libCStreamedXML || return 1 + +if [ -z ${tests_BUILT} ] +then + LIBS="${libCStreamedXML} " + EXTRAS="" + + echo "Building test programs..." + do_cmd mkdir -p obj/tests || return 1 + + for SRC in src/tests/*.c + do + TEST="obj/tests/$(basename ${SRC} | sed -e 's,.c$,,')" + MODIFIED=0 + for file in ${LIBS} ${SRC} src/tests/build.tests + do + if [ ${file} -nt ${TEST} ] + then + MODIFIED=1 + break + fi + done + + if [ ${MODIFIED} -ne 0 ] + then + do_cmd ${CC} -Iobj ${CFLAGS} -o ${TEST} ${SRC} ${LIBS} ${EXTRAS} || return 1 + print_success "Built ${TEST}" + else + print_success "${TEST} is up to date" + fi + done + + print_success "All tests built" + + tests_BUILT=1 +fi + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4 diff --git a/src/tests/callback.c b/src/tests/callback.c new file mode 100644 index 0000000..132f1cc --- /dev/null +++ b/src/tests/callback.c @@ -0,0 +1,137 @@ +/* libCStreamedXML/src/tests/callback.c + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +#include "StreamedXML.h" + +#include +#include + + + +int echo_whiteSpace(const struct csxml* ctx, const char* ws) +{ + (void)ctx; + printf("Whitespace: ``%s''\n", ws); + return 0; +} + +int echo_content(const struct csxml* ctx, const char* data) +{ + (void)ctx; + printf("Content: ``%s''\n", data); + return 0; +} + +int echo_cdata(const struct csxml* ctx, const char* data) +{ + (void)ctx; + printf("CDATA: ``%s''\n", data); + return 0; +} + +int echo_streamRestart(const struct csxml* ctx, const char* data) +{ + (void)ctx; + printf("Stream restart marker: ``%s''\n", data); + return 0; +} + +int echo_PI(const struct csxml* ctx, const char* target, const char* data) +{ + (void)ctx; + printf("PI: target ``%s'', data ", target); + if(data) printf("``%s''\n", data); + else printf("not specified\n"); + return 0; +} + +int echo_comment(const struct csxml* ctx, const char* data) +{ + (void)ctx; + printf("Comment: ``%s''\n", data); + return 0; +} + +int echo_element(const struct csxml* ctx, const char* elemName, int numAttrs) +{ + int i; + + printf("Open tag: <%s> (%d attributes)\n", elemName, numAttrs); + for(i = 0; i < numAttrs; ++i) printf(" %s='%s'\n", ctx->elemAttrNames.data[i].data, ctx->elemAttrVals.data[i].data); + return 0; +} + +int echo_closeTag(const struct csxml* ctx, const char* elemName) +{ + (void)ctx; + printf("Close tag: \n", elemName); + return 0; +} + +const char* echo_entityRef(const struct csxml* ctx, const char* ent) +{ + (void)ctx; + printf("Entity reference: ``%s''\n", ent); + return 0; +} + + + +int main(int argc, char* argv[]) +{ + FILE* fp = 0; + char buf[1024]; + size_t amt; + struct csxml* ctx = 0; + + if(argc == 2 && !strcmp(argv[1], "--print-summary")) { + printf("Tests the callback functions.\n"); + return 0; + } + + if(argc != 2) { + fprintf(stderr, "Expecting filename.\n"); + return 1; + } + + fp = fopen(argv[1], "r"); + if(!fp) { + fprintf(stderr, "Error opening '%s' for input.\n", argv[1]); + return 1; + } + + ctx = csxml_newParser(); + if(!ctx) { + fprintf(stderr, "Couldn't allocate a new parser.\n"); + return 1; + } + + ctx->whiteSpace = echo_whiteSpace; + ctx->content = echo_content; + ctx->cdata = echo_cdata; + ctx->streamRestart = echo_streamRestart; + ctx->PI = echo_PI; + ctx->comment = echo_comment; + ctx->element = echo_element; + ctx->closeTag = echo_closeTag; + ctx->entityRef = echo_entityRef; + + while(!feof(fp)) { + amt = fread(buf, 1, sizeof(buf), fp); + csxml_feedData(ctx, buf, amt); + } + + csxml_freeParser(ctx); + fclose(fp); + + return 0; +} + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/src/tests/template b/src/tests/template new file mode 100644 index 0000000..c02cdfb --- /dev/null +++ b/src/tests/template @@ -0,0 +1,35 @@ +/* libCStreamedXML/src/tests/???.c + * + * (c)2006, Laurence Withers, . + * Released under the GNU GPLv2. See file COPYING or + * http://www.gnu.org/copyleft/gpl.html for details. +*/ + +#include "StreamedXML.h" + +#include + + + +int main(int argc, char* argv[]) +{ + if(argc == 2 && !strcmp(argv[1], "--print-summary")) { + printf("One line summary.\n"); + return 0; + } + + if(argc == 1) { + // empty argument list + } + + int ret = 0; + + // TODO + + return ret; +} + +/* options for text editors +kate: replace-trailing-space-save true; space-indent true; tab-width 4; +vim: expandtab:ts=4:sw=4 +*/ diff --git a/version b/version new file mode 100644 index 0000000..fa2327d --- /dev/null +++ b/version @@ -0,0 +1,19 @@ +# libCStreamedXML/version +# +# (c)2006, Laurence Withers, . +# Released under the GNU GPLv2. See file COPYING or +# http://www.gnu.org/copyleft/gpl.html for details. +# + + + +# VERSION contains the full version number of the library, which is +# expected to be in 'major.minor.micro' format. It can optionally be +# suffixed with a string. +VERMAJOR=1 +VERMINOR=2 +VERMICRO=8 +VEREXTRA="" + +# kate: replace-trailing-space-save true; space-indent true; tab-width 4; +# vim: expandtab:ts=4:sw=4