diff options
author | Daniel Baumann <daniel@debian.org> | 2024-11-21 15:51:37 +0100 |
---|---|---|
committer | Daniel Baumann <daniel@debian.org> | 2024-11-21 15:51:37 +0100 |
commit | ebb64aabedd789b5affbf30f03e43fcf3a0561f4 (patch) | |
tree | ec4dd9937434be85039f900efcc48c75c182d81d /src | |
parent | Initial commit. (diff) | |
download | packetq-upstream.tar.xz packetq-upstream.zip |
Adding upstream version 1.7.3+dfsg.upstream/1.7.3+dfsgupstream
Signed-off-by: Daniel Baumann <daniel@debian.org>
Diffstat (limited to '')
49 files changed, 13467 insertions, 0 deletions
diff --git a/src/Makefile.am b/src/Makefile.am new file mode 100644 index 0000000..4f70623 --- /dev/null +++ b/src/Makefile.am @@ -0,0 +1,47 @@ +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +CLEANFILES = *.gcda *.gcno *.gcov + +SUBDIRS = test + +AM_CXXFLAGS = -I$(srcdir) \ + -I$(srcdir)/Murmur \ + -I$(top_srcdir) \ + $(libmaxminddb_CFLAGS) + +bin_PROGRAMS = packetq + +packetq_SOURCES = dns.cpp dns.h icmp.cpp icmp.h output.h packet_handler.cpp \ + packet_handler.h packetq.cpp packetq.h pcap.cpp pcap.h reader.cpp \ + reader.h refcountstring.h segzip.h server.cpp server.h sql.cpp sql.h \ + tcp.cpp tcp.h variant.h +packetq_LDADD = $(libmaxminddb_LIBS) + +dist_packetq_SOURCES = Murmur/MurmurHash3.cpp Murmur/MurmurHash3.h + +EXTRA_DIST = regression-test.sh + +if ENABLE_GCOV +gcov-local: + for src in $(packetq_SOURCES) $(dist_packetq_SOURCES); do \ + gcov -l -r -s "$(srcdir)" "$$src"; \ + done +endif diff --git a/src/Makefile.in b/src/Makefile.in new file mode 100644 index 0000000..7e67255 --- /dev/null +++ b/src/Makefile.in @@ -0,0 +1,837 @@ +# Makefile.in generated by automake 1.16.5 from Makefile.am. +# @configure_input@ + +# Copyright (C) 1994-2021 Free Software Foundation, Inc. + +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ + +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +VPATH = @srcdir@ +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} +am__make_running_with_option = \ + case $${target_option-} in \ + ?) ;; \ + *) echo "am__make_running_with_option: internal error: invalid" \ + "target option '$${target_option-}' specified" >&2; \ + exit 1;; \ + esac; \ + has_opt=no; \ + sane_makeflags=$$MAKEFLAGS; \ + if $(am__is_gnu_make); then \ + sane_makeflags=$$MFLAGS; \ + else \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + bs=\\; \ + sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \ + | sed "s/$$bs$$bs[$$bs $$bs ]*//g"`;; \ + esac; \ + fi; \ + skip_next=no; \ + strip_trailopt () \ + { \ + flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \ + }; \ + for flg in $$sane_makeflags; do \ + test $$skip_next = yes && { skip_next=no; continue; }; \ + case $$flg in \ + *=*|--*) continue;; \ + -*I) strip_trailopt 'I'; skip_next=yes;; \ + -*I?*) strip_trailopt 'I';; \ + -*O) strip_trailopt 'O'; skip_next=yes;; \ + -*O?*) strip_trailopt 'O';; \ + -*l) strip_trailopt 'l'; skip_next=yes;; \ + -*l?*) strip_trailopt 'l';; \ + -[dEDm]) skip_next=yes;; \ + -[JT]) skip_next=yes;; \ + esac; \ + case $$flg in \ + *$$target_option*) has_opt=yes; break;; \ + esac; \ + done; \ + test $$has_opt = yes +am__make_dryrun = (target_option=n; $(am__make_running_with_option)) +am__make_keepgoing = (target_option=k; $(am__make_running_with_option)) +pkgdatadir = $(datadir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkglibexecdir = $(libexecdir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +bin_PROGRAMS = packetq$(EXEEXT) +subdir = src +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/m4/ax_cflags_warn_all.m4 \ + $(top_srcdir)/m4/ax_compiler_vendor.m4 \ + $(top_srcdir)/m4/ax_prepend_flag.m4 \ + $(top_srcdir)/m4/ax_require_defined.m4 \ + $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) +mkinstalldirs = $(install_sh) -d +CONFIG_HEADER = config.h +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +am__installdirs = "$(DESTDIR)$(bindir)" +PROGRAMS = $(bin_PROGRAMS) +am_packetq_OBJECTS = dns.$(OBJEXT) icmp.$(OBJEXT) \ + packet_handler.$(OBJEXT) packetq.$(OBJEXT) pcap.$(OBJEXT) \ + reader.$(OBJEXT) server.$(OBJEXT) sql.$(OBJEXT) tcp.$(OBJEXT) +am__dirstamp = $(am__leading_dot)dirstamp +dist_packetq_OBJECTS = Murmur/MurmurHash3.$(OBJEXT) +packetq_OBJECTS = $(am_packetq_OBJECTS) $(dist_packetq_OBJECTS) +am__DEPENDENCIES_1 = +packetq_DEPENDENCIES = $(am__DEPENDENCIES_1) +AM_V_P = $(am__v_P_@AM_V@) +am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) +am__v_P_0 = false +am__v_P_1 = : +AM_V_GEN = $(am__v_GEN_@AM_V@) +am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@) +am__v_GEN_0 = @echo " GEN " $@; +am__v_GEN_1 = +AM_V_at = $(am__v_at_@AM_V@) +am__v_at_ = $(am__v_at_@AM_DEFAULT_V@) +am__v_at_0 = @ +am__v_at_1 = +DEFAULT_INCLUDES = -I.@am__isrc@ +depcomp = $(SHELL) $(top_srcdir)/depcomp +am__maybe_remake_depfiles = depfiles +am__depfiles_remade = ./$(DEPDIR)/dns.Po ./$(DEPDIR)/icmp.Po \ + ./$(DEPDIR)/packet_handler.Po ./$(DEPDIR)/packetq.Po \ + ./$(DEPDIR)/pcap.Po ./$(DEPDIR)/reader.Po \ + ./$(DEPDIR)/server.Po ./$(DEPDIR)/sql.Po ./$(DEPDIR)/tcp.Po \ + Murmur/$(DEPDIR)/MurmurHash3.Po +am__mv = mv -f +CXXCOMPILE = $(CXX) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \ + $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CXXFLAGS) $(CXXFLAGS) +AM_V_CXX = $(am__v_CXX_@AM_V@) +am__v_CXX_ = $(am__v_CXX_@AM_DEFAULT_V@) +am__v_CXX_0 = @echo " CXX " $@; +am__v_CXX_1 = +CXXLD = $(CXX) +CXXLINK = $(CXXLD) $(AM_CXXFLAGS) $(CXXFLAGS) $(AM_LDFLAGS) $(LDFLAGS) \ + -o $@ +AM_V_CXXLD = $(am__v_CXXLD_@AM_V@) +am__v_CXXLD_ = $(am__v_CXXLD_@AM_DEFAULT_V@) +am__v_CXXLD_0 = @echo " CXXLD " $@; +am__v_CXXLD_1 = +COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ + $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +AM_V_CC = $(am__v_CC_@AM_V@) +am__v_CC_ = $(am__v_CC_@AM_DEFAULT_V@) +am__v_CC_0 = @echo " CC " $@; +am__v_CC_1 = +CCLD = $(CC) +LINK = $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o $@ +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 = $(packetq_SOURCES) $(dist_packetq_SOURCES) +DIST_SOURCES = $(packetq_SOURCES) $(dist_packetq_SOURCES) +RECURSIVE_TARGETS = all-recursive check-recursive cscopelist-recursive \ + ctags-recursive dvi-recursive html-recursive info-recursive \ + install-data-recursive install-dvi-recursive \ + install-exec-recursive install-html-recursive \ + install-info-recursive install-pdf-recursive \ + install-ps-recursive install-recursive installcheck-recursive \ + installdirs-recursive pdf-recursive ps-recursive \ + tags-recursive uninstall-recursive +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac +RECURSIVE_CLEAN_TARGETS = mostlyclean-recursive clean-recursive \ + distclean-recursive maintainer-clean-recursive +am__recursive_targets = \ + $(RECURSIVE_TARGETS) \ + $(RECURSIVE_CLEAN_TARGETS) \ + $(am__extra_recursive_targets) +AM_RECURSIVE_TARGETS = $(am__recursive_targets:-recursive=) TAGS CTAGS \ + distdir distdir-am +am__extra_recursive_targets = gcov-recursive +am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) \ + config.h.in +# Read a list of newline-separated strings from the standard input, +# and print each of them once, without duplicates. Input order is +# *not* preserved. +am__uniquify_input = $(AWK) '\ + BEGIN { nonempty = 0; } \ + { items[$$0] = 1; nonempty = 1; } \ + END { if (nonempty) { for (i in items) print i; }; } \ +' +# Make sure the list of sources is unique. This is necessary because, +# e.g., the same source file might be shared among _SOURCES variables +# for different programs/libraries. +am__define_uniq_tagged_files = \ + list='$(am__tagged_files)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | $(am__uniquify_input)` +DIST_SUBDIRS = $(SUBDIRS) +am__DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/config.h.in \ + $(top_srcdir)/depcomp +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +am__relativize = \ + dir0=`pwd`; \ + sed_first='s,^\([^/]*\)/.*$$,\1,'; \ + sed_rest='s,^[^/]*/*,,'; \ + sed_last='s,^.*/\([^/]*\)$$,\1,'; \ + sed_butlast='s,/*[^/]*$$,,'; \ + while test -n "$$dir1"; do \ + first=`echo "$$dir1" | sed -e "$$sed_first"`; \ + if test "$$first" != "."; then \ + if test "$$first" = ".."; then \ + dir2=`echo "$$dir0" | sed -e "$$sed_last"`/"$$dir2"; \ + dir0=`echo "$$dir0" | sed -e "$$sed_butlast"`; \ + else \ + first2=`echo "$$dir2" | sed -e "$$sed_first"`; \ + if test "$$first2" = "$$first"; then \ + dir2=`echo "$$dir2" | sed -e "$$sed_rest"`; \ + else \ + dir2="../$$dir2"; \ + fi; \ + dir0="$$dir0"/"$$first"; \ + fi; \ + fi; \ + dir1=`echo "$$dir1" | sed -e "$$sed_rest"`; \ + done; \ + reldir="$$dir2" +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ +CFLAGS = @CFLAGS@ +CPPFLAGS = @CPPFLAGS@ +CSCOPE = @CSCOPE@ +CTAGS = @CTAGS@ +CXX = @CXX@ +CXXDEPMODE = @CXXDEPMODE@ +CXXFLAGS = @CXXFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +ETAGS = @ETAGS@ +EXEEXT = @EXEEXT@ +GREP = @GREP@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LTLIBOBJS = @LTLIBOBJS@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +OBJEXT = @OBJEXT@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_URL = @PACKAGE_URL@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PKG_CONFIG = @PKG_CONFIG@ +PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@ +PKG_CONFIG_PATH = @PKG_CONFIG_PATH@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +VERSION = @VERSION@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +ac_ct_CXX = @ac_ct_CXX@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_vendor = @build_vendor@ +builddir = @builddir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +libmaxminddb_CFLAGS = @libmaxminddb_CFLAGS@ +libmaxminddb_LIBS = @libmaxminddb_LIBS@ +localedir = @localedir@ +localstatedir = @localstatedir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +runstatedir = @runstatedir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_build_prefix = @top_build_prefix@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +CLEANFILES = *.gcda *.gcno *.gcov +SUBDIRS = test +AM_CXXFLAGS = -I$(srcdir) \ + -I$(srcdir)/Murmur \ + -I$(top_srcdir) \ + $(libmaxminddb_CFLAGS) + +packetq_SOURCES = dns.cpp dns.h icmp.cpp icmp.h output.h packet_handler.cpp \ + packet_handler.h packetq.cpp packetq.h pcap.cpp pcap.h reader.cpp \ + reader.h refcountstring.h segzip.h server.cpp server.h sql.cpp sql.h \ + tcp.cpp tcp.h variant.h + +packetq_LDADD = $(libmaxminddb_LIBS) +dist_packetq_SOURCES = Murmur/MurmurHash3.cpp Murmur/MurmurHash3.h +EXTRA_DIST = regression-test.sh +all: config.h + $(MAKE) $(AM_MAKEFLAGS) all-recursive + +.SUFFIXES: +.SUFFIXES: .cpp .o .obj +$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \ + && { if test -f $@; then exit 0; else break; fi; }; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign src/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --foreign src/Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__maybe_remake_depfiles)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__maybe_remake_depfiles);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): + +config.h: stamp-h1 + @test -f $@ || rm -f stamp-h1 + @test -f $@ || $(MAKE) $(AM_MAKEFLAGS) stamp-h1 + +stamp-h1: $(srcdir)/config.h.in $(top_builddir)/config.status + @rm -f stamp-h1 + cd $(top_builddir) && $(SHELL) ./config.status src/config.h +$(srcdir)/config.h.in: $(am__configure_deps) + ($(am__cd) $(top_srcdir) && $(AUTOHEADER)) + rm -f stamp-h1 + touch $@ + +distclean-hdr: + -rm -f config.h stamp-h1 +install-binPROGRAMS: $(bin_PROGRAMS) + @$(NORMAL_INSTALL) + @list='$(bin_PROGRAMS)'; test -n "$(bindir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(bindir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(bindir)" || exit 1; \ + fi; \ + for p in $$list; do echo "$$p $$p"; done | \ + sed 's/$(EXEEXT)$$//' | \ + while read p p1; do if test -f $$p \ + ; then echo "$$p"; echo "$$p"; else :; fi; \ + done | \ + sed -e 'p;s,.*/,,;n;h' \ + -e 's|.*|.|' \ + -e 'p;x;s,.*/,,;s/$(EXEEXT)$$//;$(transform);s/$$/$(EXEEXT)/' | \ + sed 'N;N;N;s,\n, ,g' | \ + $(AWK) 'BEGIN { files["."] = ""; dirs["."] = 1 } \ + { d=$$3; if (dirs[d] != 1) { print "d", d; dirs[d] = 1 } \ + if ($$2 == $$4) files[d] = files[d] " " $$1; \ + else { print "f", $$3 "/" $$4, $$1; } } \ + END { for (d in files) print "f", d, files[d] }' | \ + while read type dir files; do \ + if test "$$dir" = .; then dir=; else dir=/$$dir; fi; \ + test -z "$$files" || { \ + echo " $(INSTALL_PROGRAM_ENV) $(INSTALL_PROGRAM) $$files '$(DESTDIR)$(bindir)$$dir'"; \ + $(INSTALL_PROGRAM_ENV) $(INSTALL_PROGRAM) $$files "$(DESTDIR)$(bindir)$$dir" || exit $$?; \ + } \ + ; done + +uninstall-binPROGRAMS: + @$(NORMAL_UNINSTALL) + @list='$(bin_PROGRAMS)'; test -n "$(bindir)" || list=; \ + files=`for p in $$list; do echo "$$p"; done | \ + sed -e 'h;s,^.*/,,;s/$(EXEEXT)$$//;$(transform)' \ + -e 's/$$/$(EXEEXT)/' \ + `; \ + test -n "$$list" || exit 0; \ + echo " ( cd '$(DESTDIR)$(bindir)' && rm -f" $$files ")"; \ + cd "$(DESTDIR)$(bindir)" && rm -f $$files + +clean-binPROGRAMS: + -test -z "$(bin_PROGRAMS)" || rm -f $(bin_PROGRAMS) +Murmur/$(am__dirstamp): + @$(MKDIR_P) Murmur + @: > Murmur/$(am__dirstamp) +Murmur/$(DEPDIR)/$(am__dirstamp): + @$(MKDIR_P) Murmur/$(DEPDIR) + @: > Murmur/$(DEPDIR)/$(am__dirstamp) +Murmur/MurmurHash3.$(OBJEXT): Murmur/$(am__dirstamp) \ + Murmur/$(DEPDIR)/$(am__dirstamp) + +packetq$(EXEEXT): $(packetq_OBJECTS) $(packetq_DEPENDENCIES) $(EXTRA_packetq_DEPENDENCIES) + @rm -f packetq$(EXEEXT) + $(AM_V_CXXLD)$(CXXLINK) $(packetq_OBJECTS) $(packetq_LDADD) $(LIBS) + +mostlyclean-compile: + -rm -f *.$(OBJEXT) + -rm -f Murmur/*.$(OBJEXT) + +distclean-compile: + -rm -f *.tab.c + +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/dns.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/icmp.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/packet_handler.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/packetq.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pcap.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/reader.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/server.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/sql.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/tcp.Po@am__quote@ # am--include-marker +@AMDEP_TRUE@@am__include@ @am__quote@Murmur/$(DEPDIR)/MurmurHash3.Po@am__quote@ # am--include-marker + +$(am__depfiles_remade): + @$(MKDIR_P) $(@D) + @echo '# dummy' >$@-t && $(am__mv) $@-t $@ + +am--depfiles: $(am__depfiles_remade) + +.cpp.o: +@am__fastdepCXX_TRUE@ $(AM_V_CXX)depbase=`echo $@ | sed 's|[^/]*$$|$(DEPDIR)/&|;s|\.o$$||'`;\ +@am__fastdepCXX_TRUE@ $(CXXCOMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ $< &&\ +@am__fastdepCXX_TRUE@ $(am__mv) $$depbase.Tpo $$depbase.Po +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ $(AM_V_CXX)source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ DEPDIR=$(DEPDIR) $(CXXDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCXX_FALSE@ $(AM_V_CXX@am__nodep@)$(CXXCOMPILE) -c -o $@ $< + +.cpp.obj: +@am__fastdepCXX_TRUE@ $(AM_V_CXX)depbase=`echo $@ | sed 's|[^/]*$$|$(DEPDIR)/&|;s|\.obj$$||'`;\ +@am__fastdepCXX_TRUE@ $(CXXCOMPILE) -MT $@ -MD -MP -MF $$depbase.Tpo -c -o $@ `$(CYGPATH_W) '$<'` &&\ +@am__fastdepCXX_TRUE@ $(am__mv) $$depbase.Tpo $$depbase.Po +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ $(AM_V_CXX)source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCXX_FALSE@ DEPDIR=$(DEPDIR) $(CXXDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCXX_FALSE@ $(AM_V_CXX@am__nodep@)$(CXXCOMPILE) -c -o $@ `$(CYGPATH_W) '$<'` + +# This directory's subdirectories are mostly independent; you can cd +# into them and run 'make' without going through this Makefile. +# To change the values of 'make' variables: instead of editing Makefiles, +# (1) if the variable is set in 'config.status', edit 'config.status' +# (which will cause the Makefiles to be regenerated when you run 'make'); +# (2) otherwise, pass the desired values on the 'make' command line. +$(am__recursive_targets): + @fail=; \ + if $(am__make_keepgoing); then \ + failcom='fail=yes'; \ + else \ + failcom='exit 1'; \ + fi; \ + dot_seen=no; \ + target=`echo $@ | sed s/-recursive//`; \ + case "$@" in \ + distclean-* | maintainer-clean-*) list='$(DIST_SUBDIRS)' ;; \ + *) list='$(SUBDIRS)' ;; \ + esac; \ + for subdir in $$list; do \ + echo "Making $$target in $$subdir"; \ + if test "$$subdir" = "."; then \ + dot_seen=yes; \ + local_target="$$target-am"; \ + else \ + local_target="$$target"; \ + fi; \ + ($(am__cd) $$subdir && $(MAKE) $(AM_MAKEFLAGS) $$local_target) \ + || eval $$failcom; \ + done; \ + if test "$$dot_seen" = "no"; then \ + $(MAKE) $(AM_MAKEFLAGS) "$$target-am" || exit 1; \ + fi; test -z "$$fail" +gcov-local: + +ID: $(am__tagged_files) + $(am__define_uniq_tagged_files); mkid -fID $$unique +tags: tags-recursive +TAGS: tags + +tags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files) + set x; \ + here=`pwd`; \ + if ($(ETAGS) --etags-include --version) >/dev/null 2>&1; then \ + include_option=--etags-include; \ + empty_fix=.; \ + else \ + include_option=--include; \ + empty_fix=; \ + fi; \ + list='$(SUBDIRS)'; for subdir in $$list; do \ + if test "$$subdir" = .; then :; else \ + test ! -f $$subdir/TAGS || \ + set "$$@" "$$include_option=$$here/$$subdir/TAGS"; \ + fi; \ + done; \ + $(am__define_uniq_tagged_files); \ + shift; \ + if test -z "$(ETAGS_ARGS)$$*$$unique"; then :; else \ + test -n "$$unique" || unique=$$empty_fix; \ + if test $$# -gt 0; then \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + "$$@" $$unique; \ + else \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + $$unique; \ + fi; \ + fi +ctags: ctags-recursive + +CTAGS: ctags +ctags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files) + $(am__define_uniq_tagged_files); \ + test -z "$(CTAGS_ARGS)$$unique" \ + || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \ + $$unique + +GTAGS: + here=`$(am__cd) $(top_builddir) && pwd` \ + && $(am__cd) $(top_srcdir) \ + && gtags -i $(GTAGS_ARGS) "$$here" +cscopelist: cscopelist-recursive + +cscopelist-am: $(am__tagged_files) + list='$(am__tagged_files)'; \ + case "$(srcdir)" in \ + [\\/]* | ?:[\\/]*) sdir="$(srcdir)" ;; \ + *) sdir=$(subdir)/$(srcdir) ;; \ + esac; \ + for i in $$list; do \ + if test -f "$$i"; then \ + echo "$(subdir)/$$i"; \ + else \ + echo "$$sdir/$$i"; \ + fi; \ + done >> $(top_builddir)/cscope.files + +distclean-tags: + -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags +distdir: $(BUILT_SOURCES) + $(MAKE) $(AM_MAKEFLAGS) distdir-am + +distdir-am: $(DISTFILES) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d "$(distdir)/$$file"; then \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -fpR $(srcdir)/$$file "$(distdir)$$dir" || exit 1; \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + cp -fpR $$d/$$file "$(distdir)$$dir" || exit 1; \ + else \ + test -f "$(distdir)/$$file" \ + || cp -p $$d/$$file "$(distdir)/$$file" \ + || exit 1; \ + fi; \ + done + @list='$(DIST_SUBDIRS)'; for subdir in $$list; do \ + if test "$$subdir" = .; then :; else \ + $(am__make_dryrun) \ + || test -d "$(distdir)/$$subdir" \ + || $(MKDIR_P) "$(distdir)/$$subdir" \ + || exit 1; \ + dir1=$$subdir; dir2="$(distdir)/$$subdir"; \ + $(am__relativize); \ + new_distdir=$$reldir; \ + dir1=$$subdir; dir2="$(top_distdir)"; \ + $(am__relativize); \ + new_top_distdir=$$reldir; \ + echo " (cd $$subdir && $(MAKE) $(AM_MAKEFLAGS) top_distdir="$$new_top_distdir" distdir="$$new_distdir" \\"; \ + echo " am__remove_distdir=: am__skip_length_check=: am__skip_mode_fix=: distdir)"; \ + ($(am__cd) $$subdir && \ + $(MAKE) $(AM_MAKEFLAGS) \ + top_distdir="$$new_top_distdir" \ + distdir="$$new_distdir" \ + am__remove_distdir=: \ + am__skip_length_check=: \ + am__skip_mode_fix=: \ + distdir) \ + || exit 1; \ + fi; \ + done +check-am: all-am +check: check-recursive +all-am: Makefile $(PROGRAMS) config.h +installdirs: installdirs-recursive +installdirs-am: + for dir in "$(DESTDIR)$(bindir)"; do \ + test -z "$$dir" || $(MKDIR_P) "$$dir"; \ + done +install: install-recursive +install-exec: install-exec-recursive +install-data: install-data-recursive +uninstall: uninstall-recursive + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-recursive +install-strip: + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi +mostlyclean-generic: + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + -rm -f Murmur/$(DEPDIR)/$(am__dirstamp) + -rm -f Murmur/$(am__dirstamp) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +@ENABLE_GCOV_FALSE@gcov-local: +clean: clean-recursive + +clean-am: clean-binPROGRAMS clean-generic mostlyclean-am + +distclean: distclean-recursive + -rm -f ./$(DEPDIR)/dns.Po + -rm -f ./$(DEPDIR)/icmp.Po + -rm -f ./$(DEPDIR)/packet_handler.Po + -rm -f ./$(DEPDIR)/packetq.Po + -rm -f ./$(DEPDIR)/pcap.Po + -rm -f ./$(DEPDIR)/reader.Po + -rm -f ./$(DEPDIR)/server.Po + -rm -f ./$(DEPDIR)/sql.Po + -rm -f ./$(DEPDIR)/tcp.Po + -rm -f Murmur/$(DEPDIR)/MurmurHash3.Po + -rm -f Makefile +distclean-am: clean-am distclean-compile distclean-generic \ + distclean-hdr distclean-tags + +dvi: dvi-recursive + +dvi-am: + +gcov: gcov-recursive + +gcov-am: gcov-local + +html: html-recursive + +html-am: + +info: info-recursive + +info-am: + +install-data-am: + +install-dvi: install-dvi-recursive + +install-dvi-am: + +install-exec-am: install-binPROGRAMS + +install-html: install-html-recursive + +install-html-am: + +install-info: install-info-recursive + +install-info-am: + +install-man: + +install-pdf: install-pdf-recursive + +install-pdf-am: + +install-ps: install-ps-recursive + +install-ps-am: + +installcheck-am: + +maintainer-clean: maintainer-clean-recursive + -rm -f ./$(DEPDIR)/dns.Po + -rm -f ./$(DEPDIR)/icmp.Po + -rm -f ./$(DEPDIR)/packet_handler.Po + -rm -f ./$(DEPDIR)/packetq.Po + -rm -f ./$(DEPDIR)/pcap.Po + -rm -f ./$(DEPDIR)/reader.Po + -rm -f ./$(DEPDIR)/server.Po + -rm -f ./$(DEPDIR)/sql.Po + -rm -f ./$(DEPDIR)/tcp.Po + -rm -f Murmur/$(DEPDIR)/MurmurHash3.Po + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-recursive + +mostlyclean-am: mostlyclean-compile mostlyclean-generic + +pdf: pdf-recursive + +pdf-am: + +ps: ps-recursive + +ps-am: + +uninstall-am: uninstall-binPROGRAMS + +.MAKE: $(am__recursive_targets) all install-am install-strip + +.PHONY: $(am__recursive_targets) CTAGS GTAGS TAGS all all-am \ + am--depfiles check check-am clean clean-binPROGRAMS \ + clean-generic cscopelist-am ctags ctags-am distclean \ + distclean-compile distclean-generic distclean-hdr \ + distclean-tags distdir dvi dvi-am gcov-am gcov-local html \ + html-am info info-am install install-am install-binPROGRAMS \ + install-data install-data-am install-dvi install-dvi-am \ + install-exec install-exec-am install-html install-html-am \ + install-info install-info-am install-man install-pdf \ + install-pdf-am install-ps install-ps-am install-strip \ + installcheck installcheck-am installdirs installdirs-am \ + maintainer-clean maintainer-clean-generic mostlyclean \ + mostlyclean-compile mostlyclean-generic pdf pdf-am ps ps-am \ + tags tags-am uninstall uninstall-am uninstall-binPROGRAMS + +.PRECIOUS: Makefile + + +@ENABLE_GCOV_TRUE@gcov-local: +@ENABLE_GCOV_TRUE@ for src in $(packetq_SOURCES) $(dist_packetq_SOURCES); do \ +@ENABLE_GCOV_TRUE@ gcov -l -r -s "$(srcdir)" "$$src"; \ +@ENABLE_GCOV_TRUE@ done + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/src/Murmur/MurmurHash3.cpp b/src/Murmur/MurmurHash3.cpp new file mode 100644 index 0000000..aa7982d --- /dev/null +++ b/src/Murmur/MurmurHash3.cpp @@ -0,0 +1,335 @@ +//----------------------------------------------------------------------------- +// MurmurHash3 was written by Austin Appleby, and is placed in the public +// domain. The author hereby disclaims copyright to this source code. + +// Note - The x86 and x64 versions do _not_ produce the same results, as the +// algorithms are optimized for their respective platforms. You can still +// compile and run any of them on any platform, but your performance with the +// non-native version will be less than optimal. + +#include "MurmurHash3.h" + +//----------------------------------------------------------------------------- +// Platform-specific functions and macros + +// Microsoft Visual Studio + +#if defined(_MSC_VER) + +#define FORCE_INLINE __forceinline + +#include <stdlib.h> + +#define ROTL32(x,y) _rotl(x,y) +#define ROTL64(x,y) _rotl64(x,y) + +#define BIG_CONSTANT(x) (x) + +// Other compilers + +#else // defined(_MSC_VER) + +#define FORCE_INLINE inline __attribute__((always_inline)) + +inline uint32_t rotl32 ( uint32_t x, int8_t r ) +{ + return (x << r) | (x >> (32 - r)); +} + +inline uint64_t rotl64 ( uint64_t x, int8_t r ) +{ + return (x << r) | (x >> (64 - r)); +} + +#define ROTL32(x,y) rotl32(x,y) +#define ROTL64(x,y) rotl64(x,y) + +#define BIG_CONSTANT(x) (x##LLU) + +#endif // !defined(_MSC_VER) + +//----------------------------------------------------------------------------- +// Block read - if your platform needs to do endian-swapping or can only +// handle aligned reads, do the conversion here + +FORCE_INLINE uint32_t getblock32 ( const uint32_t * p, int i ) +{ + return p[i]; +} + +FORCE_INLINE uint64_t getblock64 ( const uint64_t * p, int i ) +{ + return p[i]; +} + +//----------------------------------------------------------------------------- +// Finalization mix - force all bits of a hash block to avalanche + +FORCE_INLINE uint32_t fmix32 ( uint32_t h ) +{ + h ^= h >> 16; + h *= 0x85ebca6b; + h ^= h >> 13; + h *= 0xc2b2ae35; + h ^= h >> 16; + + return h; +} + +//---------- + +FORCE_INLINE uint64_t fmix64 ( uint64_t k ) +{ + k ^= k >> 33; + k *= BIG_CONSTANT(0xff51afd7ed558ccd); + k ^= k >> 33; + k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53); + k ^= k >> 33; + + return k; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_32 ( const void * key, int len, + uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 4; + + uint32_t h1 = seed; + + const uint32_t c1 = 0xcc9e2d51; + const uint32_t c2 = 0x1b873593; + + //---------- + // body + + const uint32_t * blocks = (const uint32_t *)(data + nblocks*4); + + for(int i = -nblocks; i; i++) + { + uint32_t k1 = getblock32(blocks,i); + + k1 *= c1; + k1 = ROTL32(k1,15); + k1 *= c2; + + h1 ^= k1; + h1 = ROTL32(h1,13); + h1 = h1*5+0xe6546b64; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*4); + + uint32_t k1 = 0; + + switch(len & 3) + { + case 3: k1 ^= tail[2] << 16; + case 2: k1 ^= tail[1] << 8; + case 1: k1 ^= tail[0]; + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; + + h1 = fmix32(h1); + + *(uint32_t*)out = h1; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_128 ( const void * key, const int len, + uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 16; + + uint32_t h1 = seed; + uint32_t h2 = seed; + uint32_t h3 = seed; + uint32_t h4 = seed; + + const uint32_t c1 = 0x239b961b; + const uint32_t c2 = 0xab0e9789; + const uint32_t c3 = 0x38b34ae5; + const uint32_t c4 = 0xa1e38b93; + + //---------- + // body + + const uint32_t * blocks = (const uint32_t *)(data + nblocks*16); + + for(int i = -nblocks; i; i++) + { + uint32_t k1 = getblock32(blocks,i*4+0); + uint32_t k2 = getblock32(blocks,i*4+1); + uint32_t k3 = getblock32(blocks,i*4+2); + uint32_t k4 = getblock32(blocks,i*4+3); + + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + + h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b; + + k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2; + + h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747; + + k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3; + + h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35; + + k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4; + + h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*16); + + uint32_t k1 = 0; + uint32_t k2 = 0; + uint32_t k3 = 0; + uint32_t k4 = 0; + + switch(len & 15) + { + case 15: k4 ^= tail[14] << 16; + case 14: k4 ^= tail[13] << 8; + case 13: k4 ^= tail[12] << 0; + k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4; + + case 12: k3 ^= tail[11] << 24; + case 11: k3 ^= tail[10] << 16; + case 10: k3 ^= tail[ 9] << 8; + case 9: k3 ^= tail[ 8] << 0; + k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3; + + case 8: k2 ^= tail[ 7] << 24; + case 7: k2 ^= tail[ 6] << 16; + case 6: k2 ^= tail[ 5] << 8; + case 5: k2 ^= tail[ 4] << 0; + k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2; + + case 4: k1 ^= tail[ 3] << 24; + case 3: k1 ^= tail[ 2] << 16; + case 2: k1 ^= tail[ 1] << 8; + case 1: k1 ^= tail[ 0] << 0; + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len; + + h1 += h2; h1 += h3; h1 += h4; + h2 += h1; h3 += h1; h4 += h1; + + h1 = fmix32(h1); + h2 = fmix32(h2); + h3 = fmix32(h3); + h4 = fmix32(h4); + + h1 += h2; h1 += h3; h1 += h4; + h2 += h1; h3 += h1; h4 += h1; + + ((uint32_t*)out)[0] = h1; + ((uint32_t*)out)[1] = h2; + ((uint32_t*)out)[2] = h3; + ((uint32_t*)out)[3] = h4; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x64_128 ( const void * key, const int len, + const uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 16; + + uint64_t h1 = seed; + uint64_t h2 = seed; + + const uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5); + const uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f); + + //---------- + // body + + const uint64_t * blocks = (const uint64_t *)(data); + + for(int i = 0; i < nblocks; i++) + { + uint64_t k1 = getblock64(blocks,i*2+0); + uint64_t k2 = getblock64(blocks,i*2+1); + + k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1; + + h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729; + + k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2; + + h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*16); + + uint64_t k1 = 0; + uint64_t k2 = 0; + + switch(len & 15) + { + case 15: k2 ^= ((uint64_t)tail[14]) << 48; + case 14: k2 ^= ((uint64_t)tail[13]) << 40; + case 13: k2 ^= ((uint64_t)tail[12]) << 32; + case 12: k2 ^= ((uint64_t)tail[11]) << 24; + case 11: k2 ^= ((uint64_t)tail[10]) << 16; + case 10: k2 ^= ((uint64_t)tail[ 9]) << 8; + case 9: k2 ^= ((uint64_t)tail[ 8]) << 0; + k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2; + + case 8: k1 ^= ((uint64_t)tail[ 7]) << 56; + case 7: k1 ^= ((uint64_t)tail[ 6]) << 48; + case 6: k1 ^= ((uint64_t)tail[ 5]) << 40; + case 5: k1 ^= ((uint64_t)tail[ 4]) << 32; + case 4: k1 ^= ((uint64_t)tail[ 3]) << 24; + case 3: k1 ^= ((uint64_t)tail[ 2]) << 16; + case 2: k1 ^= ((uint64_t)tail[ 1]) << 8; + case 1: k1 ^= ((uint64_t)tail[ 0]) << 0; + k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; h2 ^= len; + + h1 += h2; + h2 += h1; + + h1 = fmix64(h1); + h2 = fmix64(h2); + + h1 += h2; + h2 += h1; + + ((uint64_t*)out)[0] = h1; + ((uint64_t*)out)[1] = h2; +} + +//----------------------------------------------------------------------------- + diff --git a/src/Murmur/MurmurHash3.h b/src/Murmur/MurmurHash3.h new file mode 100644 index 0000000..54e9d3f --- /dev/null +++ b/src/Murmur/MurmurHash3.h @@ -0,0 +1,37 @@ +//----------------------------------------------------------------------------- +// MurmurHash3 was written by Austin Appleby, and is placed in the public +// domain. The author hereby disclaims copyright to this source code. + +#ifndef _MURMURHASH3_H_ +#define _MURMURHASH3_H_ + +//----------------------------------------------------------------------------- +// Platform-specific functions and macros + +// Microsoft Visual Studio + +#if defined(_MSC_VER) + +typedef unsigned char uint8_t; +typedef unsigned long uint32_t; +typedef unsigned __int64 uint64_t; + +// Other compilers + +#else // defined(_MSC_VER) + +#include <stdint.h> + +#endif // !defined(_MSC_VER) + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_32 ( const void * key, int len, uint32_t seed, void * out ); + +void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out ); + +void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out ); + +//----------------------------------------------------------------------------- + +#endif // _MURMURHASH3_H_ diff --git a/src/config.h.in b/src/config.h.in new file mode 100644 index 0000000..8c828dd --- /dev/null +++ b/src/config.h.in @@ -0,0 +1,137 @@ +/* src/config.h.in. Generated from configure.ac by autoheader. */ + +/* Define to 1 if you have the <arpa/inet.h> header file. */ +#undef HAVE_ARPA_INET_H + +/* Define to 1 if you have the `bzero' function. */ +#undef HAVE_BZERO + +/* Define to 1 if you have the `dup2' function. */ +#undef HAVE_DUP2 + +/* Define to 1 if you have the <fcntl.h> header file. */ +#undef HAVE_FCNTL_H + +/* Define to 1 if you have the <inttypes.h> header file. */ +#undef HAVE_INTTYPES_H + +/* Define to 1 if you have libmaxminddb. */ +#undef HAVE_LIBMAXMINDDB + +/* Define to 1 if you have the `nsl' library (-lnsl). */ +#undef HAVE_LIBNSL + +/* Define to 1 if you have the `socket' library (-lsocket). */ +#undef HAVE_LIBSOCKET + +/* Define to 1 if you have the `z' library (-lz). */ +#undef HAVE_LIBZ + +/* Define to 1 if you have the <limits.h> header file. */ +#undef HAVE_LIMITS_H + +/* Define to 1 if you have the `mkdir' function. */ +#undef HAVE_MKDIR + +/* Define to 1 if you have the <netinet/in.h> header file. */ +#undef HAVE_NETINET_IN_H + +/* has net/ethernet.h header */ +#undef HAVE_NET_ETHERNET_H + +/* has net/ethertypes.h header */ +#undef HAVE_NET_ETHERTYPES_H + +/* Define to 1 if your system has a GNU libc compatible `realloc' function, + and to 0 otherwise. */ +#undef HAVE_REALLOC + +/* Define to 1 if you have the `regcomp' function. */ +#undef HAVE_REGCOMP + +/* Define to 1 if you have the <stdint.h> header file. */ +#undef HAVE_STDINT_H + +/* Define to 1 if you have the <stdio.h> header file. */ +#undef HAVE_STDIO_H + +/* Define to 1 if you have the <stdlib.h> header file. */ +#undef HAVE_STDLIB_H + +/* Define to 1 if you have the `strdup' function. */ +#undef HAVE_STRDUP + +/* Define to 1 if you have the `strerror' function. */ +#undef HAVE_STRERROR + +/* Define to 1 if you have the `strftime' function. */ +#undef HAVE_STRFTIME + +/* Define to 1 if you have the <strings.h> header file. */ +#undef HAVE_STRINGS_H + +/* Define to 1 if you have the <string.h> header file. */ +#undef HAVE_STRING_H + +/* Define to 1 if you have the `strtoul' function. */ +#undef HAVE_STRTOUL + +/* Define to 1 if you have the <syslog.h> header file. */ +#undef HAVE_SYSLOG_H + +/* Define to 1 if you have the <sys/socket.h> header file. */ +#undef HAVE_SYS_SOCKET_H + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#undef HAVE_SYS_STAT_H + +/* Define to 1 if you have the <sys/time.h> header file. */ +#undef HAVE_SYS_TIME_H + +/* Define to 1 if you have the <sys/types.h> header file. */ +#undef HAVE_SYS_TYPES_H + +/* Define to 1 if you have the <unistd.h> header file. */ +#undef HAVE_UNISTD_H + +/* Name of package */ +#undef PACKAGE + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the home page for this package. */ +#undef PACKAGE_URL + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + +/* Define to 1 if all of the C90 standard headers exist (not just the ones + required in a freestanding environment). This macro is provided for + backward compatibility; new code need not use it. */ +#undef STDC_HEADERS + +/* Define to 1 if you can safely include both <sys/time.h> and <time.h>. This + macro is obsolete. */ +#undef TIME_WITH_SYS_TIME + +/* Version number of package */ +#undef VERSION + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to rpl_realloc if the replacement function should be used. */ +#undef realloc + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +#undef size_t diff --git a/src/dns.cpp b/src/dns.cpp new file mode 100644 index 0000000..24ebca1 --- /dev/null +++ b/src/dns.cpp @@ -0,0 +1,456 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "dns.h" +#include "output.h" +#include "packet_handler.h" +#include "packetq.h" +#include "tcp.h" + +#include <cctype> +#include <stdio.h> +#include <stdlib.h> + +namespace packetq { + +char visible_char_map[256]; + +void fill_in_visible_char_map() +{ + for (int i = 0; i < 256; ++i) { + visible_char_map[i] = isgraph(i) ? i : '$'; + } +} + +void fill_in_visible_char_map_rfc1035() +{ + for (int i = 0; i < 256; ++i) { + if ((i >= 'a' && i <= 'z') + || (i >= 'A' && i <= 'Z') + || (i >= '0' && i <= '9') + || (i == '-' || i == '_')) { + visible_char_map[i] = i; + } else { // espaping needed + visible_char_map[i] = 0; + } + } +} + +Parse_dns::Parse_dns(bool escape_dnsnames) +{ + if (escape_dnsnames) { + fill_in_visible_char_map_rfc1035(); + } else { + fill_in_visible_char_map(); + } + + table_name = "dns"; + + add_packet_columns(); + add_lookup_tables(); +} + +void Parse_dns::add_packet_columns() +{ + m_ip_helper.add_packet_columns(*this); + + add_packet_column("qname", "", Coltype::_text, COLUMN_QNAME); + add_packet_column("aname", "", Coltype::_text, COLUMN_ANAME); + add_packet_column("msg_id", "", Coltype::_int, COLUMN_MSG_ID); + add_packet_column("msg_size", "", Coltype::_int, COLUMN_MSG_SIZE); + add_packet_column("opcode", "", Coltype::_int, COLUMN_OPCODE); + add_packet_column("rcode", "", Coltype::_int, COLUMN_RCODE); + add_packet_column("extended_rcode", "", Coltype::_int, COLUMN_EXTENDED_RCODE); + add_packet_column("edns_version", "", Coltype::_int, COLUMN_EDNS_VERSION); + add_packet_column("z", "", Coltype::_int, COLUMN_Z); + add_packet_column("udp_size", "", Coltype::_int, COLUMN_UDP_SIZE); + add_packet_column("qd_count", "", Coltype::_int, COLUMN_QD_COUNT); + add_packet_column("an_count", "", Coltype::_int, COLUMN_AN_COUNT); + add_packet_column("ns_count", "", Coltype::_int, COLUMN_NS_COUNT); + add_packet_column("ar_count", "", Coltype::_int, COLUMN_AR_COUNT); + add_packet_column("qtype", "", Coltype::_int, COLUMN_QTYPE); + add_packet_column("qclass", "", Coltype::_int, COLUMN_QCLASS); + add_packet_column("qlabels", "", Coltype::_int, COLUMN_QLABELS); + add_packet_column("atype", "", Coltype::_int, COLUMN_ATYPE); + add_packet_column("aclass", "", Coltype::_int, COLUMN_ACLASS); + add_packet_column("attl", "", Coltype::_int, COLUMN_ATTL); + add_packet_column("alabels", "", Coltype::_int, COLUMN_ALABELS); + add_packet_column("aa", "", Coltype::_bool, COLUMN_AA); + add_packet_column("tc", "", Coltype::_bool, COLUMN_TC); + add_packet_column("rd", "", Coltype::_bool, COLUMN_RD); + add_packet_column("cd", "", Coltype::_bool, COLUMN_CD); + add_packet_column("ra", "", Coltype::_bool, COLUMN_RA); + add_packet_column("ad", "", Coltype::_bool, COLUMN_AD); + add_packet_column("do", "", Coltype::_bool, COLUMN_DO); + add_packet_column("edns0", "", Coltype::_bool, COLUMN_EDNS0); + add_packet_column("qr", "", Coltype::_bool, COLUMN_QR); + + add_packet_column("edns0_ecs", "", Coltype::_bool, COLUMN_EDNS0_ECS); + add_packet_column("edns0_ecs_family", "", Coltype::_int, COLUMN_EDNS0_ECS_FAMILY); + add_packet_column("edns0_ecs_source", "", Coltype::_int, COLUMN_EDNS0_ECS_SOURCE); + add_packet_column("edns0_ecs_scope", "", Coltype::_int, COLUMN_EDNS0_ECS_SCOPE); + add_packet_column("edns0_ecs_address", "", Coltype::_text, COLUMN_EDNS0_ECS_ADDRESS); +} + +void Parse_dns::add_lookup_tables() +{ + g_db.add_lut("qtype", 1, "A"); + g_db.add_lut("qtype", 2, "NS"); + g_db.add_lut("qtype", 3, "MD"); + g_db.add_lut("qtype", 4, "MF"); + g_db.add_lut("qtype", 5, "CNAME"); + g_db.add_lut("qtype", 6, "SOA"); + g_db.add_lut("qtype", 7, "MB"); + g_db.add_lut("qtype", 8, "MG"); + g_db.add_lut("qtype", 9, "MR"); + g_db.add_lut("qtype", 10, "NULL"); + g_db.add_lut("qtype", 11, "WKS"); + g_db.add_lut("qtype", 12, "PTR"); + g_db.add_lut("qtype", 13, "HINFO"); + g_db.add_lut("qtype", 14, "MINFO"); + g_db.add_lut("qtype", 15, "MX"); + g_db.add_lut("qtype", 16, "TXT"); + g_db.add_lut("qtype", 17, "RP"); + g_db.add_lut("qtype", 18, "AFSDB"); + g_db.add_lut("qtype", 19, "X25"); + g_db.add_lut("qtype", 20, "ISDN"); + g_db.add_lut("qtype", 21, "RT"); + g_db.add_lut("qtype", 22, "NSAP"); + g_db.add_lut("qtype", 23, "NSAP-PTR"); + g_db.add_lut("qtype", 24, "SIG"); + g_db.add_lut("qtype", 25, "KEY"); + g_db.add_lut("qtype", 26, "PX"); + g_db.add_lut("qtype", 27, "GPOS"); + g_db.add_lut("qtype", 28, "AAAA"); + g_db.add_lut("qtype", 29, "LOC"); + g_db.add_lut("qtype", 30, "NXT"); + g_db.add_lut("qtype", 31, "EID"); + g_db.add_lut("qtype", 32, "NIMLOC"); + g_db.add_lut("qtype", 33, "SRV"); + g_db.add_lut("qtype", 34, "ATMA"); + g_db.add_lut("qtype", 35, "NAPTR"); + g_db.add_lut("qtype", 36, "KX"); + g_db.add_lut("qtype", 37, "CERT"); + g_db.add_lut("qtype", 38, "A6"); + g_db.add_lut("qtype", 39, "DNAME"); + g_db.add_lut("qtype", 40, "SINK"); + g_db.add_lut("qtype", 41, "OPT"); + g_db.add_lut("qtype", 42, "APL"); + g_db.add_lut("qtype", 43, "DS"); + g_db.add_lut("qtype", 44, "SSHFP"); + g_db.add_lut("qtype", 45, "IPSECKEY"); + g_db.add_lut("qtype", 46, "RRSIG"); + g_db.add_lut("qtype", 47, "NSEC"); + g_db.add_lut("qtype", 48, "DNSKEY"); + g_db.add_lut("qtype", 49, "DHCID"); + g_db.add_lut("qtype", 50, "NSEC3"); + g_db.add_lut("qtype", 51, "NSEC3PARAM"); + g_db.add_lut("qtype", 52, "TLSA"); + g_db.add_lut("qtype", 53, "SMIMEA"); + g_db.add_lut("qtype", 55, "HIP"); + g_db.add_lut("qtype", 56, "NINFO"); + g_db.add_lut("qtype", 57, "RKEY"); + g_db.add_lut("qtype", 58, "TALINK"); + g_db.add_lut("qtype", 59, "CDS"); + g_db.add_lut("qtype", 60, "CDNSKEY"); + g_db.add_lut("qtype", 61, "OPENPGPKEY"); + g_db.add_lut("qtype", 62, "CSYNC"); + g_db.add_lut("qtype", 63, "ZONEMD"); + g_db.add_lut("qtype", 64, "SVCB"); + g_db.add_lut("qtype", 65, "HTTPS"); + g_db.add_lut("qtype", 99, "SPF"); + g_db.add_lut("qtype", 100, "UINFO"); + g_db.add_lut("qtype", 101, "UID"); + g_db.add_lut("qtype", 102, "GID"); + g_db.add_lut("qtype", 103, "UNSPEC"); + g_db.add_lut("qtype", 104, "NID"); + g_db.add_lut("qtype", 105, "L32"); + g_db.add_lut("qtype", 106, "L64"); + g_db.add_lut("qtype", 107, "LP"); + g_db.add_lut("qtype", 108, "EUI48"); + g_db.add_lut("qtype", 109, "EUI64"); + g_db.add_lut("qtype", 249, "TKEY"); + g_db.add_lut("qtype", 250, "TSIG"); + g_db.add_lut("qtype", 251, "IXFR"); + g_db.add_lut("qtype", 252, "AXFR"); + g_db.add_lut("qtype", 253, "MAILB"); + g_db.add_lut("qtype", 254, "MAILA"); + g_db.add_lut("qtype", 255, "*"); + g_db.add_lut("qtype", 256, "URI"); + g_db.add_lut("qtype", 257, "CAA"); + g_db.add_lut("qtype", 258, "AVC"); + g_db.add_lut("qtype", 259, "DOA"); + g_db.add_lut("qtype", 260, "AMTRELAY"); + g_db.add_lut("qtype", 32768, "TA"); + g_db.add_lut("qtype", 32769, "DLV"); + + g_db.add_lut("rcode", 0, "NoError"); + g_db.add_lut("rcode", 1, "FormErr"); + g_db.add_lut("rcode", 2, "ServFail"); + g_db.add_lut("rcode", 3, "NXDomain"); + g_db.add_lut("rcode", 4, "NotImp"); + g_db.add_lut("rcode", 5, "Refused"); + g_db.add_lut("rcode", 6, "YXDomain"); + g_db.add_lut("rcode", 7, "YXRRSet"); + g_db.add_lut("rcode", 8, "NXRRSet"); + g_db.add_lut("rcode", 9, "NotAuth"); + g_db.add_lut("rcode", 10, "NotZone"); + g_db.add_lut("rcode", 16, "BADVERS"); + g_db.add_lut("rcode", 16, "BADSIG"); + g_db.add_lut("rcode", 17, "BADKEY"); + g_db.add_lut("rcode", 18, "BADTIME"); + g_db.add_lut("rcode", 19, "BADMODE"); + g_db.add_lut("rcode", 20, "BADNAME"); + g_db.add_lut("rcode", 21, "BADALG"); + g_db.add_lut("rcode", 22, "BADTRUNC"); +} + +void Parse_dns::on_table_created(Table* table, const std::vector<int>& columns) +{ + m_ip_helper.on_table_created(table, columns); + + acc_msg_id = table->get_accessor<int_column>("msg_id"); + acc_msg_size = table->get_accessor<int_column>("msg_size"); + acc_opcode = table->get_accessor<int_column>("opcode"); + acc_rcode = table->get_accessor<int_column>("rcode"); + acc_extended_rcode = table->get_accessor<int_column>("extended_rcode"); + acc_edns_version = table->get_accessor<int_column>("edns_version"); + acc_z = table->get_accessor<int_column>("z"); + acc_udp_size = table->get_accessor<int_column>("udp_size"); + acc_qd_count = table->get_accessor<int_column>("qd_count"); + acc_an_count = table->get_accessor<int_column>("an_count"); + acc_ns_count = table->get_accessor<int_column>("ns_count"); + acc_ar_count = table->get_accessor<int_column>("ar_count"); + acc_qtype = table->get_accessor<int_column>("qtype"); + acc_qclass = table->get_accessor<int_column>("qclass"); + acc_qlabels = table->get_accessor<int_column>("qlabels"); + acc_atype = table->get_accessor<int_column>("atype"); + acc_aclass = table->get_accessor<int_column>("aclass"); + acc_attl = table->get_accessor<int_column>("attl"); + acc_alabels = table->get_accessor<int_column>("alabels"); + + acc_qr = table->get_accessor<bool_column>("qr"); + acc_aa = table->get_accessor<bool_column>("aa"); + acc_tc = table->get_accessor<bool_column>("tc"); + acc_rd = table->get_accessor<bool_column>("rd"); + acc_cd = table->get_accessor<bool_column>("cd"); + acc_ra = table->get_accessor<bool_column>("ra"); + acc_ad = table->get_accessor<bool_column>("ad"); + acc_do = table->get_accessor<bool_column>("do"); + acc_edns0 = table->get_accessor<bool_column>("edns0"); + + acc_qname = table->get_accessor<text_column>("qname"); + acc_aname = table->get_accessor<text_column>("aname"); + + acc_edns0_ecs = table->get_accessor<bool_column>("edns0_ecs"); + acc_edns0_ecs_family = table->get_accessor<int_column>("edns0_ecs_family"); + acc_edns0_ecs_source = table->get_accessor<int_column>("edns0_ecs_source"); + acc_edns0_ecs_scope = table->get_accessor<int_column>("edns0_ecs_scope"); + acc_edns0_ecs_address = table->get_accessor<text_column>("edns0_ecs_address"); +} + +Packet::ParseResult Parse_dns::parse(Packet& packet, const std::vector<int>& columns, Row& destination_row, bool sample) +{ + if (not(packet.m_len >= 12 && (packet.m_ip_header.proto == IPPROTO_UDP || packet.m_ip_header.proto == IPPROTO_TCP))) + return Packet::ERROR; + + if (!sample) + return Packet::NOT_SAMPLED; + + unsigned char* ddata = packet.m_data; + int dlength = packet.m_len; + + if (packet.m_ip_header.proto == IPPROTO_TCP) { + int dns_size = (int(ddata[0]) << 8) | ddata[1]; + ddata += 2; + dlength -= 2; + if (dns_size != dlength) + return Packet::ERROR; + } + + DNSMessage message(ddata, dlength, packet.m_ip_header); + + DNSMessage::Header& header = message.m_header; + IP_header& ip_header = message.m_ip_header; + + if (message.m_error != 0) + return Packet::ERROR; + + if (!header.qr and header.qdcount == 0) + return Packet::ERROR; + + Row* r = &destination_row; + + m_ip_helper.assign(r, &ip_header, columns); + + for (auto i = columns.begin(), end = columns.end(); i != end; ++i) { + switch (*i) { + case COLUMN_MSG_ID: + acc_msg_id.value(r) = header.id; + break; + + case COLUMN_MSG_SIZE: + acc_msg_size.value(r) = message.m_length; + break; + + case COLUMN_QR: + acc_qr.value(r) = header.qr; + break; + + case COLUMN_AA: + acc_aa.value(r) = header.aa; + break; + + case COLUMN_TC: + acc_tc.value(r) = header.tc; + break; + + case COLUMN_RD: + acc_rd.value(r) = header.rd; + break; + + case COLUMN_CD: + acc_cd.value(r) = header.cd; + break; + + case COLUMN_RA: + acc_ra.value(r) = header.ra; + break; + + case COLUMN_AD: + acc_ad.value(r) = header.ad; + break; + + case COLUMN_OPCODE: + acc_opcode.value(r) = header.opcode; + break; + + case COLUMN_RCODE: + acc_rcode.value(r) = header.rcode; + break; + + case COLUMN_QD_COUNT: + acc_qd_count.value(r) = header.qdcount; + break; + + case COLUMN_AN_COUNT: + acc_an_count.value(r) = header.ancount; + break; + + case COLUMN_NS_COUNT: + acc_ns_count.value(r) = header.nscount; + break; + + case COLUMN_AR_COUNT: + acc_ar_count.value(r) = header.arcount; + break; + + case COLUMN_QTYPE: + acc_qtype.value(r) = message.m_questions[0].qtype; + break; + + case COLUMN_QCLASS: + acc_qclass.value(r) = message.m_questions[0].qclass; + break; + + case COLUMN_QLABELS: + acc_qlabels.value(r) = message.m_questions[0].qname.labels; + break; + + case COLUMN_QNAME: + acc_qname.value(r) = RefCountString::construct(message.m_questions[0].qname.fqdn); + break; + + case COLUMN_EDNS0: + acc_edns0.value(r) = message.m_edns0 ? 1 : 0; + break; + + case COLUMN_DO: + acc_do.value(r) = message.m_edns0 ? message.m_do : 0; + break; + + case COLUMN_EXTENDED_RCODE: + acc_extended_rcode.value(r) = message.m_edns0 ? message.m_extended_rcode : 0; + break; + + case COLUMN_EDNS_VERSION: + acc_edns_version.value(r) = message.m_edns0 ? message.m_edns_version : 0; + break; + + case COLUMN_Z: + acc_z.value(r) = message.m_edns0 ? message.m_z : 0; + break; + + case COLUMN_UDP_SIZE: + acc_udp_size.value(r) = message.m_edns0 ? message.m_udp_size : 0; + break; + + case COLUMN_ANAME: + acc_aname.value(r) = header.ancount ? RefCountString::construct(message.m_answer[0].name.fqdn) : RefCountString::construct(""); + break; + + case COLUMN_ATYPE: + acc_atype.value(r) = header.ancount ? message.m_answer[0].type : 0; + break; + + case COLUMN_ACLASS: + acc_aclass.value(r) = header.ancount ? message.m_answer[0].rr_class : 0; + break; + + case COLUMN_ATTL: + acc_attl.value(r) = header.ancount ? message.m_answer[0].ttl : 0; + break; + + case COLUMN_ALABELS: + acc_alabels.value(r) = header.ancount ? message.m_answer[0].name.labels : 0; + break; + + case COLUMN_EDNS0_ECS: + acc_edns0_ecs.value(r) = message.m_edns0_ecs ? 1 : 0; + break; + + case COLUMN_EDNS0_ECS_FAMILY: + acc_edns0_ecs_family.value(r) = message.m_edns0_ecs_family; + break; + + case COLUMN_EDNS0_ECS_SOURCE: + acc_edns0_ecs_source.value(r) = message.m_edns0_ecs_source; + break; + + case COLUMN_EDNS0_ECS_SCOPE: + acc_edns0_ecs_scope.value(r) = message.m_edns0_ecs_scope; + break; + + case COLUMN_EDNS0_ECS_ADDRESS: + if (message.m_edns0_ecs_addr_set && message.m_edns0_ecs_family == 1) + acc_edns0_ecs_address.value(r) = v4_addr2str(message.m_edns0_ecs_addr); + else if (message.m_edns0_ecs_addr_set && message.m_edns0_ecs_family == 2) + acc_edns0_ecs_address.value(r) = v6_addr2str(message.m_edns0_ecs_addr); + else + acc_edns0_ecs_address.value(r) = RefCountString::construct(""); + break; + } + } + + return Packet::OK; +} + +} // namespace packetq diff --git a/src/dns.h b/src/dns.h new file mode 100644 index 0000000..0afd281 --- /dev/null +++ b/src/dns.h @@ -0,0 +1,541 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_dns_h +#define __packetq_dns_h + +#include <assert.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "output.h" +#include "packet_handler.h" +#include "tcp.h" + +namespace packetq { + +extern char visible_char_map[256]; + +class DNSMessage { +public: + class Header { + public: + int id; + int z; + bool qr; + int opcode; + bool aa; + bool tc; + bool rd; + bool ra; + bool ad; + bool cd; + int rcode; + int qdcount; + int ancount; + int nscount; + int arcount; + Header() + : z(0) + { + id = 0; + qr = 0; + opcode = 0; + aa = 0; + tc = 0; + rd = 0; + ra = 0; + ad = 0; + cd = 0; + rcode = 0; + qdcount = 0; + ancount = 0; + nscount = 0; + arcount = 0; + } + void parse(DNSMessage& p) + { + /* + From rfc 2929 + 1 1 1 1 1 1 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + | ID | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + |QR| Opcode |AA|TC|RD|RA| Z|AD|CD| RCODE | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + | QDCOUNT/ZOCOUNT | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + | ANCOUNT/PRCOUNT | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + | NSCOUNT/UPCOUNT | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + | ARCOUNT | + +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+ + */ + + id = p.get_ushort(0); + qr = p.get_bit(2, 0); + opcode = p.get_bits(2, 1, 4); + aa = p.get_bit(2, 5); + tc = p.get_bit(2, 6); + rd = p.get_bit(2, 7); + ra = p.get_bit(2, 8); + ad = p.get_bit(2, 10); + cd = p.get_bit(2, 11); + rcode = p.get_bits(2, 12, 4); + qdcount = p.get_ushort(4); + ancount = p.get_ushort(6); + nscount = p.get_ushort(8); + arcount = p.get_ushort(10); + } + }; + + class Name { + public: + char fqdn[2048]; // escaping needs *4 the space + int labels; + + Name() + : fqdn { 0 } + , labels(0) + { + } + + void reset(void) + { + fqdn[0] = 0; + labels = 0; + } + }; + + class Question { + public: + Name qname; + int qtype; + int qclass; + + Question() + { + qtype = 0; + qclass = 0; + } + + int parse(DNSMessage& m, int offs) + { + offs = m.parse_dname(qname, offs); + qtype = m.get_ushort(offs); + offs += 2; + qclass = m.get_ushort(offs); + offs += 2; + return offs; + } + }; + + class RR { + public: + Name name; + int type; + int rr_class; + unsigned int ttl; + int rdlength; + int doffs; + + RR() + { + type = 0; + rr_class = 0; + ttl = 0; + rdlength = 0; + doffs = 0; + } + + int parse(DNSMessage& m, int offs) + { + offs = m.parse_dname(name, offs); + type = m.get_ushort(offs); + if (type == 41) { + m.m_opt_rr = this; + m.m_new_opt_rr = true; + } + offs += 2; + rr_class = m.get_ushort(offs); + offs += 2; + ttl = m.get_ushort(offs) << 16; + ttl |= m.get_ushort(offs + 2); + offs += 4; + rdlength = m.get_ushort(offs); + offs += 2; + doffs = offs; + offs += rdlength; + return offs; + } + }; + + IP_header& m_ip_header; + unsigned char* m_data; + int m_length; + Header m_header; + Question m_questions[2]; + RR m_answer[2]; + RR m_authority[2]; + RR m_additional[2]; + RR* m_opt_rr; + bool m_new_opt_rr; + int m_error; + bool m_edns0; + bool m_do; + int m_extended_rcode; + int m_edns_version; + int m_z; + int m_udp_size; + bool m_edns0_ecs; + int m_edns0_ecs_family; + int m_edns0_ecs_source; + int m_edns0_ecs_scope; + in6addr_t m_edns0_ecs_addr; + bool m_edns0_ecs_addr_set; + + DNSMessage(unsigned char* data, int len, IP_header& head) + : m_ip_header(head) + { + m_opt_rr = 0; + m_new_opt_rr = false; + m_error = 0; + m_data = data; + m_length = len; + m_edns0 = false; + m_do = false; + m_extended_rcode = 0; + m_edns_version = 0; + m_z = 0; + m_udp_size = 0; + m_edns0_ecs = false; + m_edns0_ecs_family = 0; + m_edns0_ecs_source = 0; + m_edns0_ecs_scope = 0; + m_edns0_ecs_addr_set = false; + + parse(); + } + int parse_dname(Name& name, int offs) + { + int p = 0; + int savedoffs = 0; + int n = get_ubyte(offs++); + char* out = &name.fqdn[0]; + if (n == 0) + out[p++] = '.'; + + while (n > 0) { + name.labels++; + while (n >= 192) { + if (savedoffs) { + out[p++] = 0; + return savedoffs; + } + savedoffs = offs + 1; + int n2 = get_ubyte(offs++); + int ptr = (n & 63) * 0x100 + n2; + offs = ptr; + n = get_ubyte(offs++); + } + + // if the string is too long restart and mess it up + // check if we can fit a fully escaped label + . and reserve for zeroing it later + if (p + (n * 4) + 1 > sizeof(name.fqdn) - 1) + p = 0; + + while (n-- > 0) { + const unsigned int byte = get_ubyte(offs++); + if (visible_char_map[byte]) { + out[p++] = visible_char_map[byte]; + } else { + out[p++] = '\\'; + out[p++] = '0' + byte / 100; + out[p++] = '0' + byte / 10 % 10; + out[p++] = '0' + byte % 10; + } + } + out[p++] = '.'; + n = get_ubyte(offs++); + } + if (savedoffs) + offs = savedoffs; + out[p++] = 0; + return offs; + } + void parse_opt_rr() + { + if (m_opt_rr) { + if (!m_edns0) { + m_edns0 = true; + unsigned long ttl = m_opt_rr->ttl; + m_do = (ttl >> 15) & 1; + m_extended_rcode = ttl >> 24; + m_edns_version = (ttl >> 16) & 0xff; + m_z = ttl & 0x7fff; + m_udp_size = m_opt_rr->rr_class; + } + if (((m_opt_rr->ttl >> 16) & 0xff) == 0 && m_opt_rr->rdlength > 0) { + // Parse this OPT RR that is EDNS0 + int rdlen = m_opt_rr->rdlength, + offs = m_opt_rr->doffs, + opcode = 0, + oplen = 0; + + while (rdlen > 3) { + // Minimum op code and length + opcode = get_ushort(offs); + oplen = get_ushort(offs + 2); + offs += 4; + rdlen -= 4; + + if (rdlen < oplen) + break; + + if (opcode == 8 && !m_edns0_ecs && oplen > 3) { + // ECS - Client Subnet - RFC7871 + m_edns0_ecs = true; + m_edns0_ecs_family = get_ushort(offs); + m_edns0_ecs_source = get_ubyte(offs + 2); + m_edns0_ecs_scope = get_ubyte(offs + 3); + + int addrlen = (m_edns0_ecs_source / 8) + (m_edns0_ecs_source % 8 ? 1 : 0); + int fill = 0; + + if (addrlen <= (oplen - 4)) { + switch (m_edns0_ecs_family) { + case 1: + fill = 4; + m_edns0_ecs_addr_set = true; + break; + case 2: + fill = 16; + m_edns0_ecs_addr_set = true; + break; + } + + int a = 0, b; + for (b = 15; fill && b > -1; fill--, b--) { + if (a < addrlen) { + m_edns0_ecs_addr.__in6_u.__u6_addr8[b] = get_ubyte(offs + 4 + a); + a++; + } else { + m_edns0_ecs_addr.__in6_u.__u6_addr8[b] = 0; + } + } + } + } + + rdlen -= oplen; + offs += oplen; + } + } + } + } + void parse() + { + m_header.parse(*this); + int offs = 12; + int q = 0; + int cnt = m_header.qdcount; + while (cnt-- > 0) { + offs = m_questions[q].parse(*this, offs); + if (offs > m_length) { + m_questions[q].qname.reset(); + m_error = offs; + return; + } + q = 1; // not ++ ignore further Q's + } + q = 0; + cnt = m_header.ancount; + while (cnt-- > 0) { + offs = m_answer[q].parse(*this, offs); + q = 1; // not ++ ignore further Q's + if (offs > m_length) { + m_error = offs; + return; + } + } + q = 0; + cnt = m_header.nscount; + while (cnt-- > 0) { + offs = m_authority[q].parse(*this, offs); + q = 1; // not ++ ignore further Q's + if (offs > m_length) { + m_error = offs; + return; + } + } + q = 0; + cnt = m_header.arcount; + while (cnt-- > 0) { + offs = m_additional[q].parse(*this, offs); + q = 1; // not ++ ignore further Q's + if (offs > m_length) { + m_error = offs; + return; + } + if (m_new_opt_rr) { + parse_opt_rr(); + m_new_opt_rr = false; + } + } + if (offs > m_length) + m_error = offs; + } + + unsigned int get_ubyte(int offs) + { + if (offs >= m_length) + return 0; + return int(m_data[offs]); + } + // returns 16 bit number at byte offset offs + unsigned int get_ushort(int offs) + { + if ((offs + 1) >= m_length) + return 0; + return (int(m_data[offs]) << 8) | int(m_data[offs + 1]); + } + uint32_t get_uint32(int offs) + { + if ((offs + 3) >= m_length) + return 0; + return (uint32_t(m_data[offs]) << 24) | (uint32_t(m_data[offs + 1]) << 16) | (uint32_t(m_data[offs + 2]) << 8) | uint32_t(m_data[offs + 3]); + } + bool get_bit(int offs, int bit) + { + if (offs >= m_length) + return 0; + return ((get_ushort(offs) << bit) & 0x8000) == 0x8000; + } + unsigned int get_bits(int offs, int bit, int bits) + { + if (offs >= m_length) + return 0; + return ((get_ushort(offs) << bit) & 0xffff) >> (16 - bits); + } +}; + +class Parse_dns : public Packet_handler { +public: + enum { + COLUMN_QNAME = IP_header_to_table::COLUMN_FRAGMENTS + 1, + COLUMN_ANAME, + COLUMN_MSG_ID, + COLUMN_MSG_SIZE, + COLUMN_OPCODE, + COLUMN_RCODE, + COLUMN_EXTENDED_RCODE, + COLUMN_EDNS_VERSION, + COLUMN_Z, + COLUMN_UDP_SIZE, + COLUMN_QD_COUNT, + COLUMN_AN_COUNT, + COLUMN_NS_COUNT, + COLUMN_AR_COUNT, + COLUMN_QTYPE, + COLUMN_QCLASS, + COLUMN_QLABELS, + COLUMN_ATYPE, + COLUMN_ACLASS, + COLUMN_ALABELS, + COLUMN_ATTL, + COLUMN_AA, + COLUMN_TC, + COLUMN_RD, + COLUMN_CD, + COLUMN_RA, + COLUMN_AD, + COLUMN_DO, + COLUMN_EDNS0, + COLUMN_QR, + COLUMN_EDNS0_ECS, + COLUMN_EDNS0_ECS_FAMILY, + COLUMN_EDNS0_ECS_SOURCE, + COLUMN_EDNS0_ECS_SCOPE, + COLUMN_EDNS0_ECS_ADDRESS, + }; + + Parse_dns(bool escape_dnsnames); + + virtual void on_table_created(Table* table, const std::vector<int>& columns); + virtual Packet::ParseResult parse(Packet& packet, const std::vector<int>& columns, Row& destination_row, bool sample); + + void add_packet_columns(); + void add_lookup_tables(); + +private: + Str_conv converter; + + IP_header_to_table m_ip_helper; + + Int_accessor acc_s; + Int_accessor acc_us; + Int_accessor acc_ether_type; + Int_accessor acc_protocol; + Int_accessor acc_src_port; + Int_accessor acc_msg_id; + Int_accessor acc_msg_size; + Int_accessor acc_opcode; + Int_accessor acc_rcode; + Int_accessor acc_extended_rcode; + Int_accessor acc_edns_version; + Int_accessor acc_z; + Int_accessor acc_udp_size; + Int_accessor acc_qd_count; + Int_accessor acc_an_count; + Int_accessor acc_ns_count; + Int_accessor acc_ar_count; + Int_accessor acc_qtype; + Int_accessor acc_qclass; + Int_accessor acc_qlabels; + Int_accessor acc_atype; + Int_accessor acc_aclass; + Int_accessor acc_attl; + Int_accessor acc_alabels; + Int_accessor acc_edns0_ecs_family; + Int_accessor acc_edns0_ecs_source; + Int_accessor acc_edns0_ecs_scope; + Bool_accessor acc_qr; + Bool_accessor acc_aa; + Bool_accessor acc_tc; + Bool_accessor acc_rd; + Bool_accessor acc_cd; + Bool_accessor acc_ra; + Bool_accessor acc_ad; + Bool_accessor acc_do; + Bool_accessor acc_edns0; + Bool_accessor acc_edns0_ecs; + Text_accessor acc_qname; + Text_accessor acc_aname; + Text_accessor acc_src_addr; + Text_accessor acc_dst_addr; + Text_accessor acc_edns0_ecs_address; +}; + +} // namespace packetq + +#endif // __packetq_dns_h diff --git a/src/icmp.cpp b/src/icmp.cpp new file mode 100644 index 0000000..108d66d --- /dev/null +++ b/src/icmp.cpp @@ -0,0 +1,238 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "icmp.h" +#include "output.h" +#include "packet_handler.h" +#include "packetq.h" +#include "tcp.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +namespace packetq { + +Parse_icmp::Parse_icmp() +{ + table_name = "icmp"; + + add_packet_columns(); + add_lookup_tables(); +} + +void Parse_icmp::add_packet_columns() +{ + m_ip_helper.add_packet_columns(*this); + + add_packet_column("type", "", Coltype::_int, COLUMN_TYPE); + add_packet_column("code", "", Coltype::_int, COLUMN_CODE); + add_packet_column("echo_identifier", "", Coltype::_int, COLUMN_ECHO_IDENTIFIER); + add_packet_column("echo_sequence", "", Coltype::_int, COLUMN_ECHO_SEQUENCE); + add_packet_column("du_protocol", "", Coltype::_int, COLUMN_DU_PROTOCOL); + add_packet_column("du_src_addr", "", Coltype::_text, COLUMN_DU_SRC_ADDR); + add_packet_column("du_dst_addr", "", Coltype::_text, COLUMN_DU_DST_ADDR); + add_packet_column("desc", "", Coltype::_text, COLUMN_DESC); +} + +void Parse_icmp::add_lookup_tables() +{ +} + +Packet::ParseResult Parse_icmp::parse(Packet& packet, const std::vector<int>& columns, Row& destination_row, bool sample) +{ + if (packet.m_ip_header.proto != IPPROTO_ICMP) + return Packet::ERROR; + if (packet.m_ip_header.ethertype != 2048) // we dont support ICMPv6 yet + return Packet::ERROR; + + if (!sample) + return Packet::NOT_SAMPLED; + + if (packet.m_len < 2) + return Packet::ERROR; + + Row* r = &destination_row; + + m_ip_helper.assign(r, &packet.m_ip_header, columns); + + unsigned char* raw = packet.m_data; + int type = raw[0]; + int code = raw[1]; + int identifier = 0, sequence = 0, protocol = 0; + RefCountString *src_addr = 0, *dst_addr = 0; + bool src_addr_used = false, dst_addr_used = false; + + switch (type) { + case 0: + if (packet.m_len < 8) + return Packet::ERROR; + identifier = get_short(&raw[4]); + sequence = get_short(&raw[6]); + break; + case 3: { + IP_header head; + if (packet.m_len < 8 + 20) + return Packet::ERROR; + head.decode(&raw[8], packet.m_ip_header.ethertype, 0); + protocol = head.proto; + src_addr = v4_addr2str(head.src_ip); + dst_addr = v4_addr2str(head.dst_ip); + } break; + case 8: + if (packet.m_len < 8) + return Packet::ERROR; + identifier = get_short(&raw[4]); + sequence = get_short(&raw[6]); + break; + } + + for (auto i = columns.begin(), end = columns.end(); i != end; ++i) { + switch (*i) { + case COLUMN_TYPE: + acc_type.value(r) = type; + break; + + case COLUMN_CODE: + acc_code.value(r) = code; + break; + + case COLUMN_ECHO_IDENTIFIER: + acc_echo_identifier.value(r) = identifier; + break; + + case COLUMN_ECHO_SEQUENCE: + acc_echo_sequence.value(r) = sequence; + break; + + case COLUMN_DU_PROTOCOL: + acc_du_protocol.value(r) = protocol; + break; + + case COLUMN_DU_SRC_ADDR: + acc_du_src_addr.value(r) = src_addr ? src_addr : RefCountString::construct(""); + src_addr_used = true; + break; + + case COLUMN_DU_DST_ADDR: + acc_du_dst_addr.value(r) = dst_addr ? dst_addr : RefCountString::construct(""); + dst_addr_used = true; + break; + + case COLUMN_DESC: + switch (type) { + case 0: + acc_desc.value(r) = RefCountString::construct("Echo Reply"); + break; + case 3: + switch (code) { + case 0: + acc_desc.value(r) = RefCountString::construct("Destination network unreachable"); + break; + case 1: + acc_desc.value(r) = RefCountString::construct("Destination host unreachable"); + break; + case 2: + acc_desc.value(r) = RefCountString::construct("Destination protocol unreachable"); + break; + case 3: + acc_desc.value(r) = RefCountString::construct("Destination port unreachable"); + break; + default: + acc_desc.value(r) = RefCountString::construct("Destination unreachable"); + break; + } + break; + case 4: + acc_desc.value(r) = RefCountString::construct("Source quench"); + break; + case 5: + acc_desc.value(r) = RefCountString::construct("Redirect Message"); + break; + case 6: + acc_desc.value(r) = RefCountString::construct("Alternate Host Address"); + break; + case 8: + acc_desc.value(r) = RefCountString::construct("Echo Request"); + break; + case 9: + acc_desc.value(r) = RefCountString::construct("Router Advertisement"); + break; + case 10: + acc_desc.value(r) = RefCountString::construct("Router Solicitation"); + break; + case 11: + acc_desc.value(r) = RefCountString::construct("Time Exceeded"); + break; + case 12: + acc_desc.value(r) = RefCountString::construct("Bad IP header"); + break; + case 13: + acc_desc.value(r) = RefCountString::construct("Timestamp"); + break; + case 14: + acc_desc.value(r) = RefCountString::construct("Timestamp Reply"); + break; + case 15: + acc_desc.value(r) = RefCountString::construct("Information Request"); + break; + case 16: + acc_desc.value(r) = RefCountString::construct("Information Reply"); + break; + case 17: + acc_desc.value(r) = RefCountString::construct("Address Mask Request"); + break; + case 18: + acc_desc.value(r) = RefCountString::construct("Address Mask Reply"); + break; + case 30: + acc_desc.value(r) = RefCountString::construct("Traceroute"); + break; + default: + acc_desc.value(r) = RefCountString::construct("UNKNOWN TYPE"); + } + break; + } + } + + if (src_addr && !src_addr_used) + src_addr->dec_refcount(); + if (dst_addr && !dst_addr_used) + dst_addr->dec_refcount(); + + return Packet::OK; +} + +void Parse_icmp::on_table_created(Table* table, const std::vector<int>& columns) +{ + m_ip_helper.on_table_created(table, columns); + + acc_type = table->get_accessor<int_column>("type"); + acc_code = table->get_accessor<int_column>("code"); + acc_echo_identifier = table->get_accessor<int_column>("echo_identifier"); + acc_echo_sequence = table->get_accessor<int_column>("echo_sequence"); + acc_du_protocol = table->get_accessor<int_column>("du_protocol"); + acc_du_src_addr = table->get_accessor<text_column>("du_src_addr"); + acc_du_dst_addr = table->get_accessor<text_column>("du_dst_addr"); + acc_desc = table->get_accessor<text_column>("desc"); +} + +} // namespace packetq diff --git a/src/icmp.h b/src/icmp.h new file mode 100644 index 0000000..0528849 --- /dev/null +++ b/src/icmp.h @@ -0,0 +1,76 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_icmp_h +#define __packetq_icmp_h + +#include <assert.h> +#include <cctype> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "output.h" +#include "packet_handler.h" +#include "sql.h" +#include "tcp.h" + +namespace packetq { + +class Parse_icmp : public Packet_handler { +public: + enum { + COLUMN_TYPE = IP_header_to_table::COLUMN_FRAGMENTS + 1, + COLUMN_CODE, + COLUMN_ECHO_IDENTIFIER, + COLUMN_ECHO_SEQUENCE, + COLUMN_DU_PROTOCOL, + COLUMN_DU_SRC_ADDR, + COLUMN_DU_DST_ADDR, + COLUMN_DESC + }; + + Parse_icmp(); + + virtual void on_table_created(Table* table, const std::vector<int>& columns); + virtual Packet::ParseResult parse(Packet& packet, const std::vector<int>& columns, Row& destination_row, bool sample); + + void add_packet_columns(); + void add_lookup_tables(); + +private: + Str_conv converter; + + IP_header_to_table m_ip_helper; + + Int_accessor acc_type; + Int_accessor acc_code; + Int_accessor acc_echo_identifier; + Int_accessor acc_echo_sequence; + Int_accessor acc_du_protocol; + Text_accessor acc_du_src_addr; + Text_accessor acc_du_dst_addr; + Text_accessor acc_desc; +}; + +} // namespace packetq + +#endif // __packetq_icmp_h diff --git a/src/output.h b/src/output.h new file mode 100644 index 0000000..ca526de --- /dev/null +++ b/src/output.h @@ -0,0 +1,415 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_output_h +#define __packetq_output_h + +#include <stdio.h> +#include <stdlib.h> + +namespace packetq { + +class Output { + char m_buffer[0x10000]; + char m_diglut[0x100][4]; + int m_len; + int m_tot; + +public: + Output() + { + for (int i = 0; i < 256; i++) + snprintf(m_diglut[i], 4, "%d", i); + + m_len = 0; + m_tot = 0; + } + ~Output() + { + // print(); + } + void reset() { m_len = 0; } + void print() + { + if (!m_len) + return; + fwrite(m_buffer, m_len, 1, stdout); + m_tot += m_len; + m_len = 0; + } + void flush() + { + print(); + fflush(stdout); + } + inline void add_q_string(const char* p) + { + m_buffer[m_len++] = '"'; + add_string_esc_json(p); + m_buffer[m_len++] = '"'; + } + inline void add_string_esc_json(const char* p) + { + static const char lut[] = "0123456789ABCDEF"; + if (m_len > sizeof(m_buffer) / 2) + print(); + char c; + while ((c = *p++)) { + if (c == '\\') { + m_buffer[m_len++] = '\\'; + c = '\\'; + } else if (c == '"') { + m_buffer[m_len++] = '\\'; + } else if (c < 0x20) { + m_buffer[m_len++] = '\\'; + m_buffer[m_len++] = 'u'; + m_buffer[m_len++] = '0'; + m_buffer[m_len++] = '0'; + m_buffer[m_len++] = lut[(c >> 4) & 0xf]; + m_buffer[m_len++] = lut[c & 0xf]; + continue; + } + m_buffer[m_len++] = c; + } + } + inline void add_string_esc_xml(const char* p) + { + if (m_len > sizeof(m_buffer) / 2) + print(); + char c; + while ((c = *p++) > 'A') { + m_buffer[m_len++] = c; + } + if (c == 0) + return; + p--; + while ((c = *p++)) { + if (c == '>') { + m_buffer[m_len++] = '&'; + add_string("gt"); + c = ';'; + } + if (c == '<') { + m_buffer[m_len++] = '&'; + add_string("lt"); + c = ';'; + } + if (c == '\'') { + m_buffer[m_len++] = '&'; + add_string("apos"); + c = ';'; + } + if (c == '"') { + m_buffer[m_len++] = '&'; + add_string("quot"); + c = ';'; + } + m_buffer[m_len++] = c; + if (c == '&') { + add_string("amp;"); + } + } + } + inline void check() + { + if (m_len > sizeof(m_buffer) / 2) + print(); + } + inline void add_string(const char* p) + { + check(); + char c; + while ((c = *p++)) { + m_buffer[m_len++] = c; + } + } + + inline void add_hex_ushort(unsigned short v) + { + static const char lut[] = "0123456789abcdef"; + if (v & 0xf000) { + m_buffer[m_len++] = lut[v >> 12]; + m_buffer[m_len++] = lut[(v >> 8) & 0xf]; + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + if (v & 0xf00) { + m_buffer[m_len++] = lut[(v >> 8) & 0xf]; + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + if (v & 0xf0) { + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + m_buffer[m_len++] = lut[v & 0xf]; + } + + inline void add_attr_ipv6(const char* name, unsigned char* addr) + { + check(); + add_string_q(name); + m_buffer[m_len++] = '='; + m_buffer[m_len++] = '"'; + + unsigned short digs[8]; + unsigned char* p = addr; + int longest_run = 0; + int longest_p = 9; + int cur_run = 0; + for (int i = 0; i < 8; i++) { + digs[i] = ((unsigned short)(p[0]) << 8) | (unsigned short)(p[1]); + if (digs[i] == 0) { + cur_run++; + if ((cur_run > 1) && (cur_run > longest_run)) { + longest_run = cur_run; + longest_p = i + 1 - cur_run; + } + } else + cur_run = 0; + + p += 2; + } + + for (int i = 0; i < 8; i++) { + if (i >= longest_p && i < longest_p + longest_run) { + if (i == longest_p) { + if (i == 0) + m_buffer[m_len++] = ':'; + m_buffer[m_len++] = ':'; + } + } else { + add_hex_ushort(digs[i]); + if (i != 7) + m_buffer[m_len++] = ':'; + } + } + + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = ' '; + } + + inline void add_attr_ipv4(const char* p, unsigned int i) + { + check(); + add_string_q(p); + m_buffer[m_len++] = '='; + m_buffer[m_len++] = '"'; + add_string_q(m_diglut[i & 255]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 8) & 255]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 16) & 255]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 24)]); + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = ' '; + } + + inline void add_attr_bool(const char* p, bool i) + { + if (!i) + return; + check(); + add_string_q(p); + m_buffer[m_len++] = '='; + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = i ? '1' : '0'; + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = ' '; + } + + inline void add_int(unsigned int i) + { + check(); + if (i < 256) { + add_string_q(m_diglut[i & 255]); + } else { + unsigned char d[64]; + + unsigned char* cd = d; + while (i > 0 && cd < (&d[0] + sizeof(d))) { + unsigned int n = i; + i = i / 100; + n = n - (i * 100); + *cd++ = n; + } + if (cd != d) { + unsigned char t = *--cd; + add_string_q(m_diglut[t]); + } + while (cd != d) { + unsigned char t = *--cd; + if (t >= 10) + add_string_q(m_diglut[t]); + else { + m_buffer[m_len++] = '0'; + m_buffer[m_len++] = '0' + t; + } + } + } + } + inline void add_attr_int(const char* p, unsigned int i) + { + check(); + if (i == 0) + return; + add_string_q(p); + m_buffer[m_len++] = '='; + m_buffer[m_len++] = '"'; + add_int(i); + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = ' '; + } + + inline void add_attr_str(const char* p, const char* t) + { + add_string(p); + m_buffer[m_len++] = '='; + m_buffer[m_len++] = '"'; + add_string_esc_json(t); + m_buffer[m_len++] = '"'; + m_buffer[m_len++] = ' '; + } + +private: + inline void add_string_q(const char* p) + { + char c; + while ((c = *p++)) { + m_buffer[m_len++] = c; + } + } +}; + +class Str_conv { + char m_buffer[0x10000]; + char m_diglut[0x100][4]; + int m_len; + int m_tot; + +public: + Str_conv() + { + for (int i = 0; i < 256; i++) + snprintf(m_diglut[i], 4, "%d", i); + + m_len = 0; + m_tot = 0; + } + ~Str_conv() + { + // print(); + } + const char* get() + { + m_buffer[m_len] = 0; + return m_buffer; + } + int get_len() { return m_len; } + void reset() { m_len = 0; } + inline void add_attr_ipv6(unsigned char* addr) + { + unsigned short digs[8]; + unsigned char* p = &addr[14]; + int longest_run = 0; + int longest_p = 9; + int cur_run = 0; + for (int i = 0; i < 8; i++) { + digs[i] = ((unsigned short)(p[1]) << 8) | (unsigned short)(p[0]); + if (digs[i] == 0) { + cur_run++; + if ((cur_run > 1) && (cur_run > longest_run)) { + longest_run = cur_run; + longest_p = i + 1 - cur_run; + } + } else + cur_run = 0; + + p -= 2; + } + + for (int i = 0; i < 8; i++) { + if (i >= longest_p && i < longest_p + longest_run) { + if (i == longest_p) { + if (i == 0) + m_buffer[m_len++] = ':'; + m_buffer[m_len++] = ':'; + } + } else { + add_hex_ushort(digs[i]); + if (i != 7) + m_buffer[m_len++] = ':'; + } + } + } + + inline void add_string_q(const char* p) + { + char c; + while ((c = *p++)) { + m_buffer[m_len++] = c; + } + } + + inline void add_attr_ipv4(unsigned int i) + { + add_string_q(m_diglut[(i >> 24)]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 16) & 255]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 8) & 255]); + m_buffer[m_len++] = '.'; + add_string_q(m_diglut[(i >> 0) & 255]); + } + inline void add_hex_ushort(unsigned short v) + { + static const char lut[] = "0123456789abcdef"; + if (v & 0xf000) { + m_buffer[m_len++] = lut[v >> 12]; + m_buffer[m_len++] = lut[(v >> 8) & 0xf]; + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + if (v & 0xf00) { + m_buffer[m_len++] = lut[(v >> 8) & 0xf]; + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + if (v & 0xf0) { + m_buffer[m_len++] = lut[(v >> 4) & 0xf]; + m_buffer[m_len++] = lut[v & 0xf]; + return; + } + m_buffer[m_len++] = lut[v & 0xf]; + } +}; + +extern Output g_output; + +} // namespace packetq + +#endif // __packetq_output_h diff --git a/src/packet_handler.cpp b/src/packet_handler.cpp new file mode 100644 index 0000000..df21e9f --- /dev/null +++ b/src/packet_handler.cpp @@ -0,0 +1,566 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "packet_handler.h" + +#include "dns.h" +#include "icmp.h" +#include "output.h" +#include "packetq.h" +#include "sql.h" +#include "tcp.h" + +#include <stdio.h> +#include <stdlib.h> + +namespace packetq { + +Payload g_payload; +Output g_output; +Str_conv converter; + +class Fragments { +private: + Fragments& operator=(const Fragments& other); + Fragments(Fragments&& other) noexcept; + Fragments const& operator=(Fragments&& other); + +public: + class Range { + public: + bool operator<(const Range& r) const + { + if (begin < r.begin) + return true; + return false; + } + Range(int s, int e1) + { + begin = s; + endp1 = e1; + } + int begin; + int endp1; + }; + Fragments(const Fragments& f) + { + // printf( "copy Fragments\n" ); + m_first = f.m_first; + m_complete = f.m_complete; + m_frags = f.m_frags; + } + Fragments() + { + m_complete = 0; + m_frags = 0; + } + ~Fragments() + { + // printf( "delete Fragments\n", m_first.offset ); + } + bool add(IP_header& head, unsigned char* data, int len) + { + if (head.offset == 0) + m_first = head; + if (head.offset + len > 0x10000 || len < 0) + return false; + m_frags++; + if (head.fragments == 0) + m_complete = head.offset + len; + bool complete = add_range(head.offset, head.offset + len); + memcpy((void*)&m_buffer[head.offset], data, len); + if (complete) { + m_complete = head.offset + len; + m_first.fragments = m_frags; + return true; + } + return false; + } + bool add_range(int start, int end) + { + + m_ranges.push_back(Range(start, end)); + m_ranges.sort(); + bool merged = true; + // this is algorithmically horrid (hope there wont be tonnes of fragments) + while (merged) { + merged = false; + auto it = m_ranges.begin(); + auto last = it; + if (last == m_ranges.end()) + break; + it++; + for (; it != m_ranges.end(); it++) { + if (last->endp1 == it->begin) { + merged = true; + last->endp1 = it->endp1; + m_ranges.erase(it); + break; + } + } + } + if (m_ranges.size() == 1 && m_ranges.begin()->endp1 == m_complete && m_ranges.begin()->begin == 0) + return true; + return false; + } + + std::list<Range> m_ranges; + int m_complete; + int m_frags; + IP_header m_first; + unsigned char m_buffer[0x10000]; +}; + +class Ident { +public: + bool operator<(const Ident& rhs) const + { + if (m_ident < rhs.m_ident) + return true; + if (m_ident > rhs.m_ident) + return false; + for (int i = 0; i < 4; i++) { + if (m_src_ip.__in6_u.__u6_addr32[i] < rhs.m_src_ip.__in6_u.__u6_addr32[i]) + return true; + if (m_src_ip.__in6_u.__u6_addr32[i] > rhs.m_src_ip.__in6_u.__u6_addr32[i]) + return false; + } + if (m_protocol < rhs.m_protocol) + return true; + if (m_protocol > rhs.m_protocol) + return false; + for (int i = 0; i < 4; i++) { + if (m_dst_ip.__in6_u.__u6_addr32[i] < rhs.m_dst_ip.__in6_u.__u6_addr32[i]) + return true; + if (m_dst_ip.__in6_u.__u6_addr32[i] > rhs.m_dst_ip.__in6_u.__u6_addr32[i]) + return false; + } + return false; + } + in6addr_t m_dst_ip; + in6addr_t m_src_ip; + int m_ident; + int m_protocol; +}; + +class FragmentHandler { +public: + void add_fragment(IP_header& head, unsigned char* data, int len, Packet& p) + { + Ident i; + i.m_src_ip = head.src_ip; + i.m_dst_ip = head.dst_ip; + i.m_protocol = head.proto; + i.m_ident = head.ident; + Fragments& frag = m_fragments[i]; + if (frag.add(head, data, len)) { + p.m_ip_header = frag.m_first; + p.parse_transport(frag.m_buffer, frag.m_complete); + m_fragments.erase(i); + } + } + std::map<Ident, Fragments> m_fragments; +}; + +FragmentHandler m_fraghandler; + +void IP_header::reset() +{ + memset(&src_ip, 0, sizeof(in6addr_t)); + memset(&dst_ip, 0, sizeof(in6addr_t)); + fragments = 0; + offset = 0; + ident = 0; + s = 0; + us = 0; + ethertype = 0; + src_port = 0; + dst_port = 0; + proto = 0; + ip_ttl = 0; + ip_version = 0; + id = 0; + length = 0; +} + +int IP_header::decode(unsigned char* data, int itype, int i_id) +{ + reset(); + ethertype = itype; + id = i_id; + int len = 0; + // ether frame done (ignored mac's) + // ip + + ip_version = data[0] >> 4; + proto = 0; + if (ip_version == 4) { + if (ethertype == 0) + ethertype = 0x800; + + int header_len = (data[0] & 0xf) * 4; + proto = data[9]; + ip_ttl = data[8]; + + src_ip.__in6_u.__u6_addr32[3] = get_int(&data[12]); + dst_ip.__in6_u.__u6_addr32[3] = get_int(&data[16]); + + int totallen = get_short(&data[2]); + length = totallen - header_len; + int flags = get_short(&data[6]); + offset = (flags & 0x1fff) << 3; + flags >>= 13; + if (flags & 1) + fragments = 1; + data += header_len; + len += header_len; + } else if (ip_version == 6) { + if (ethertype == 0) + ethertype = 0x86DD; + + proto = data[6]; + ip_ttl = data[7]; + + src_ip.__in6_u.__u6_addr32[3] = get_int(&data[8]); + src_ip.__in6_u.__u6_addr32[2] = get_int(&data[12]); + src_ip.__in6_u.__u6_addr32[1] = get_int(&data[16]); + src_ip.__in6_u.__u6_addr32[0] = get_int(&data[20]); + + dst_ip.__in6_u.__u6_addr32[3] = get_int(&data[24]); + dst_ip.__in6_u.__u6_addr32[2] = get_int(&data[28]); + dst_ip.__in6_u.__u6_addr32[1] = get_int(&data[32]); + dst_ip.__in6_u.__u6_addr32[0] = get_int(&data[36]); + + data += 40; + len += 40; + + // process next headers - NOTE: there are 6 not 4 + while (proto == 0 || proto == 43 || proto == 44 || proto == 60) { + if (proto == 44) { + offset = get_short(&data[2]) & 0xfff8; + fragments = get_short(&data[2]) & 1; + } + proto = data[0]; + int hdr_len = data[1] + 8; + data += hdr_len; + len += hdr_len; + } + } else { + return 0; + } + + return len; +} + +std::vector<Packet_handler*> packet_handlers; + +Packet::ParseResult Packet::parse(Packet_handler* handler, const std::vector<int>& columns, Row& destination_row, bool sample) +{ + bool base_layers_parsed; + if (m_link_layer_type == 1) + base_layers_parsed = parse_ethernet(); + else if (m_link_layer_type == 113) + base_layers_parsed = parse_sll(); + else + base_layers_parsed = parse_ip(m_data, m_len, 0); + + if (!base_layers_parsed) + return ERROR; + + // do the application layer + return handler->parse(*this, columns, destination_row, sample); +} + +bool Packet::parse_ethernet() +{ + unsigned char* data = m_data; + int len = m_len; + if (len < 14) + return false; // check for etherframe size + + int ethertype = data[13] | (data[12] << 8); + if (ethertype == 0x8100) { + if (len < 18) + return false; // check for etherframe size + VLAN tag + ethertype = data[17] | (data[16] << 8); + data += 18; + len -= 18; + } else { + data += 14; + len -= 14; + } + + return parse_ip(data, len, ethertype); +} + +bool Packet::parse_sll() +{ + unsigned char* data = m_data; + int len = m_len; + if (len < 16) + return false; // check for LINUX_SLL size + + int ethertype = data[15] | (data[14] << 8); + if (ethertype == 0x8100) { + if (len < 20) + return false; // check for etherframe size + VLAN tag + ethertype = data[19] | (data[18] << 8); + data += 20; + len -= 20; + } else { + data += 16; + len -= 16; + } + + return parse_ip(data, len, ethertype); +} + +bool Packet::parse_ip(unsigned char* data, int len, int ethertype) +{ + if (len < 5 * 4) + return false; // check for etherframe size + ipv4 header + + int consumed = m_ip_header.decode(data, ethertype, m_id); + m_ip_header.s = m_s; + m_ip_header.us = m_us; + data += consumed; + len -= consumed; + if (m_ip_header.fragments > 0 || m_ip_header.offset > 0) { + m_fraghandler.add_fragment(m_ip_header, data, len, *this); + return false; + } + + return parse_transport(data, len); +} + +bool Packet::parse_transport(unsigned char* data, int len) +{ + // tcp/udp + if (m_ip_header.proto == IPPROTO_TCP) { + if (len < 14) + return false; + + m_ip_header.src_port = get_short(data); + m_ip_header.dst_port = get_short(&data[2]); + + int seq = get_int(&data[4]); + int ack = get_int(&data[8]); + + int dataoffs = 4 * (data[12] >> 4); + + unsigned char bits = data[13]; + char syn = (bits >> 1) & 1; + char fin = (bits >> 0) & 1; + char rst = (bits >> 2) & 1; + + // get the assembled TCP packet and remove the individual segments. + data += dataoffs; + len -= dataoffs; + if (len < 0) { + fprintf(stderr, "Warning: Found TCP packet with bad length\n"); + return false; + } + + unsigned int rest = len; + data = assemble_tcp(g_payload, &m_ip_header.src_ip, &m_ip_header.dst_ip, m_ip_header.src_port, m_ip_header.dst_port, &rest, seq, data, rest, syn, fin, rst, ack); + len = rest; + } else if (m_ip_header.proto == IPPROTO_UDP) { + if (len < 4) + return false; + + m_ip_header.src_port = get_short(data); + m_ip_header.dst_port = get_short(&data[2]); + + data += 8; + len -= 8; + + if (len < 0) { + fprintf(stderr, "Warning: Found UDP packet with bad length\n"); + return false; + } + } + + if (data) { + m_data = data; + m_len = len; + return true; + } + + return false; +} + +Table* Packet_handler::create_table(const std::vector<int>& columns) +{ + Table* table = g_db.create_table(table_name); + + for (auto i = packet_columns.begin(); i != packet_columns.end(); ++i) + if (std::find(columns.begin(), columns.end(), i->id) != columns.end()) + table->add_column(i->name, i->type, i->id); + + on_table_created(table, columns); + + return table; +} + +void Packet_handler::add_packet_column(const char* name, const char* description, Coltype::Type type, int id) +{ + Packet_column c; + c.name = name; + c.description = description; + c.id = id; + c.type = type; + packet_columns.push_back(c); +} + +void init_packet_handlers(bool escape_dnsnames) +{ + packet_handlers.push_back(new Parse_dns(escape_dnsnames)); + packet_handlers.push_back(new Parse_icmp()); +} + +void destroy_packet_handlers() +{ + for (auto i = packet_handlers.begin(); i != packet_handlers.end(); ++i) + delete *i; + packet_handlers.clear(); +} + +Packet_handler* get_packet_handler(std::string table_name) +{ + for (auto i = packet_handlers.begin(); i != packet_handlers.end(); ++i) { + if (table_name == (*i)->table_name) + return *i; + } + + return 0; +} + +void IP_header_to_table::add_packet_columns(Packet_handler& packet_handler) +{ + packet_handler.add_packet_column("id", "ID", Coltype::_int, COLUMN_ID); + packet_handler.add_packet_column("s", "Seconds", Coltype::_int, COLUMN_S); + packet_handler.add_packet_column("us", "Milliseconds", Coltype::_int, COLUMN_US); + packet_handler.add_packet_column("ether_type", "", Coltype::_int, COLUMN_ETHER_TYPE); + packet_handler.add_packet_column("src_port", "", Coltype::_int, COLUMN_SRC_PORT); // this is really tcp/udp but accidents do happen + packet_handler.add_packet_column("dst_port", "", Coltype::_int, COLUMN_DST_PORT); + packet_handler.add_packet_column("src_addr", "", Coltype::_text, COLUMN_SRC_ADDR); + packet_handler.add_packet_column("dst_addr", "", Coltype::_text, COLUMN_DST_ADDR); + packet_handler.add_packet_column("protocol", "", Coltype::_int, COLUMN_PROTOCOL); + packet_handler.add_packet_column("ip_ttl", "", Coltype::_int, COLUMN_IP_TTL); + packet_handler.add_packet_column("ip_version", "", Coltype::_int, COLUMN_IP_VERSION); + packet_handler.add_packet_column("fragments", "", Coltype::_int, COLUMN_FRAGMENTS); +} + +void IP_header_to_table::on_table_created(Table* table, const std::vector<int>& columns) +{ + acc_src_addr = table->get_accessor<text_column>("src_addr"); + acc_dst_addr = table->get_accessor<text_column>("dst_addr"); + acc_ether_type = table->get_accessor<int_column>("ether_type"); + acc_protocol = table->get_accessor<int_column>("protocol"); + acc_ip_ttl = table->get_accessor<int_column>("ip_ttl"); + acc_ip_version = table->get_accessor<int_column>("ip_version"); + acc_src_port = table->get_accessor<int_column>("src_port"); + acc_dst_port = table->get_accessor<int_column>("dst_port"); + acc_s = table->get_accessor<int_column>("s"); + acc_us = table->get_accessor<int_column>("us"); + acc_id = table->get_accessor<int_column>("id"); + acc_fragments = table->get_accessor<int_column>("fragments"); +} + +void IP_header_to_table::assign(Row* row, IP_header* head, const std::vector<int>& columns) +{ + if (!head) + return; + + for (auto i = columns.begin(), end = columns.end(); i != end; ++i) { + switch (*i) { + case COLUMN_ID: + acc_id.value(row) = head->id; + break; + + case COLUMN_S: + acc_s.value(row) = head->s; + break; + + case COLUMN_US: + acc_us.value(row) = head->us; + break; + + case COLUMN_ETHER_TYPE: + acc_ether_type.value(row) = head->ethertype; + break; + + case COLUMN_PROTOCOL: + acc_protocol.value(row) = head->proto; + break; + + case COLUMN_IP_TTL: + acc_ip_ttl.value(row) = head->ip_ttl; + break; + + case COLUMN_IP_VERSION: + acc_ip_version.value(row) = head->ip_version; + break; + + case COLUMN_SRC_PORT: + acc_src_port.value(row) = head->src_port; + break; + + case COLUMN_DST_PORT: + acc_dst_port.value(row) = head->dst_port; + break; + + case COLUMN_FRAGMENTS: + acc_fragments.value(row) = head->fragments; + break; + + case COLUMN_SRC_ADDR: + if (head->ethertype == 2048) + acc_src_addr.value(row) = v4_addr2str(head->src_ip); + else + acc_src_addr.value(row) = v6_addr2str(head->src_ip); + break; + + case COLUMN_DST_ADDR: + if (head->ethertype == 2048) + acc_dst_addr.value(row) = v4_addr2str(head->dst_ip); + else + acc_dst_addr.value(row) = v6_addr2str(head->dst_ip); + break; + } + } +} + +RefCountString* v4_addr2str(in6addr_t& addr) +{ + converter.reset(); + converter.add_attr_ipv4(addr.__in6_u.__u6_addr32[3]); + return RefCountString::construct(converter.get()); +} + +RefCountString* v6_addr2str(in6addr_t& addr) +{ + converter.reset(); + converter.add_attr_ipv6(&addr.__in6_u.__u6_addr8[0]); + return RefCountString::construct(converter.get()); +} + +} // namespace packetq diff --git a/src/packet_handler.h b/src/packet_handler.h new file mode 100644 index 0000000..7e966d4 --- /dev/null +++ b/src/packet_handler.h @@ -0,0 +1,226 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_packet_handler_h +#define __packetq_packet_handler_h + +#include <assert.h> +#include <cctype> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <string> +#include <vector> + +#include "sql.h" +#include "tcp.h" + +namespace packetq { + +class Table; +class Row; + +inline int get_int_h(unsigned char* data) +{ + return data[0] | (data[1] << 8) | (data[2] << 16) | (data[3] << 24); +} + +inline int get_short_h(unsigned char* data) +{ + return data[0] | (data[1] << 8); +} + +inline int get_int(unsigned char* data) +{ + return data[3] | (data[2] << 8) | (data[1] << 16) | (data[0] << 24); +} + +inline int get_short(unsigned char* data) +{ + return data[1] | (data[0] << 8); +} + +RefCountString* v4_addr2str(in6addr_t& addr); +RefCountString* v6_addr2str(in6addr_t& addr); + +class Payload { +public: + char m_p[0x10000]; + int m_size; + Payload() + { + m_size = sizeof(m_p); + } + inline char* alloc(int size) + { + if (size > m_size) + return 0; + return m_p; + } +}; + +class IP_header { +public: + IP_header() + : s(0) + , us(0) + , ethertype(0) + , src_port(0) + , dst_port(0) + , proto(0) + , ip_ttl(0) + , ip_version(0) + , id(0) + , length(0) + , fragments(0) + , ident(0) + , offset(0) + { + memset(&src_ip, 0, sizeof(src_ip)); + memset(&dst_ip, 0, sizeof(dst_ip)); + } + + void reset(); + int decode(unsigned char* data, int ether_type, int id); + unsigned int s; + unsigned int us; + unsigned short ethertype; + in6addr_t src_ip; + in6addr_t dst_ip; + unsigned short src_port; + unsigned short dst_port; + unsigned short proto; + unsigned short ip_ttl; + unsigned short ip_version; + unsigned int id; + unsigned int length; + unsigned int fragments; + unsigned int ident; + unsigned int offset; +}; + +class Packet_handler; + +class IP_header_to_table { +public: + enum { + COLUMN_ID, + COLUMN_S, + COLUMN_US, + COLUMN_ETHER_TYPE, + COLUMN_PROTOCOL, + COLUMN_IP_TTL, + COLUMN_IP_VERSION, + COLUMN_SRC_PORT, + COLUMN_DST_PORT, + COLUMN_SRC_ADDR, + COLUMN_DST_ADDR, + COLUMN_FRAGMENTS + }; + + void add_packet_columns(Packet_handler& packet_handler); + void on_table_created(Table* table, const std::vector<int>& columns); + void assign(Row* row, IP_header* head, const std::vector<int>& columns); + +private: + Int_accessor acc_id; + Int_accessor acc_s; + Int_accessor acc_us; + Int_accessor acc_ether_type; + Int_accessor acc_protocol; + Int_accessor acc_ip_ttl; + Int_accessor acc_ip_version; + Int_accessor acc_src_port; + Int_accessor acc_dst_port; + Int_accessor acc_fragments; + Text_accessor acc_src_addr; + Text_accessor acc_dst_addr; +}; + +class Packet { +public: + enum ParseResult { + ERROR, + OK, + NOT_SAMPLED + }; + + Packet(unsigned char* data, int len, int s, int us, int id, int link_layer_type) + { + m_s = s; + m_us = us; + m_data = data; + m_len = len; + m_id = id; + m_link_layer_type = link_layer_type; + } + + ParseResult parse(Packet_handler* handler, const std::vector<int>& columns, Row& destination_row, bool sample); + bool parse_ethernet(); + bool parse_sll(); + bool parse_ip(unsigned char* data, int len, int ether_type); + bool parse_transport(unsigned char* data, int len); + + IP_header m_ip_header; + unsigned char* m_data; + int m_len; + int m_s; + int m_us; + int m_id; + int m_link_layer_type; +}; + +struct Packet_column { + const char* name; + const char* description; + int id; + Coltype::Type type; +}; + +class Packet_handler { +public: + Packet_handler() + : table_name(0) + { + } + virtual ~Packet_handler() + { + } + + Table* create_table(const std::vector<int>& columns); + + // for actual packet handlers to fill in + virtual void on_table_created(Table* table, const std::vector<int>& columns) = 0; + virtual Packet::ParseResult parse(Packet& packet, const std::vector<int>& columns, Row& destination_row, bool sample) = 0; + + const char* table_name; + std::vector<Packet_column> packet_columns; + + void add_packet_column(const char* name, const char* description, Coltype::Type type, int id); +}; + +void init_packet_handlers(bool escape_dnsnames); +void destroy_packet_handlers(); +Packet_handler* get_packet_handler(std::string table_name); + +} // namespace packetq + +#endif // __packetq_packet_handler_h diff --git a/src/packetq.cpp b/src/packetq.cpp new file mode 100644 index 0000000..3a56fd5 --- /dev/null +++ b/src/packetq.cpp @@ -0,0 +1,346 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "config.h" + +#include "packet_handler.h" +#include "packetq.h" +#include "pcap.h" +#include "reader.h" +#include "server.h" +#include "sql.h" + +#include <algorithm> +#include <list> +#include <stack> +#include <stdexcept> +#include <stdio.h> +#include <stdlib.h> +#include <string> +#ifndef WIN32 +#include <getopt.h> +#include <signal.h> +#endif + +#define NUM_QUERIES 32 + +namespace packetq { + +static void usage(char* argv0, bool longversion) +{ + if (!longversion) { + fprintf(stdout, + "usage: %s [-vhjctxd] [-s stmt] [-l pkts] [-p port] [-w dir] [-r dir] [-m num] <pcapfile ...>\n", + argv0); + return; + } + + fprintf(stdout, + "usage: %s [options] pcapfile(s)...\n" + /* -o description .*/ + " --select statements |\n" + " -s statement Set the SQL statement, can be given multiple times.\n" + " --limit packets |\n" + " -l packets Set maximum number of packets to process, from all\n" + " files and not per file.\n" + " --version | -v Display version and exit.\n" + " --help | -h Display this help.\n" + "\n" + "Output:\n" + " --json | -j JSON (default)\n" + " --csv | -c CSV\n" + " --table | -t Text table\n" + " --xml | -x XML\n" + " --rfc1035 Output DNS names escaped using RFC1035 format:\n" + " All characters outsize [a-zA-Z0-9_-] are escaped\n" + " like \\012. (Octet value in decimal.)\n" + "\n" + "Web Server:\n" + " --daemon | -d Run web server in daemon mode.\n" + " --port number |\n" + " -p number Set the port number to listen on.\n" + " --webroot dir |\n" + " -w dir Set the root directory for the web content.\n" + " --pcaproot dir |\n" + " -r dir Set the root for the PCAP files to make available.\n" + " --maxconn number |\n" + " -m number Set the maximum number of concurrent connections.\n" + "\n" + "example> packetq --csv -s \"select count(*) as mycount, protocol from dns group by protocol;\" myfile.pcap\n" + "\n" + "Packet fields (available in all tables):\n" + " id, s, us, ether_type, src_addr, src_port, dst_addr, dst_port, protocol,\n" + " ip_ttl, ip_version, fragments\n" + "\"dns\" table fields:\n" + " qname, aname, msg_id, msg_size, opcode, rcode, extended_rcode,\n" + " edns_version, z, udp_size, qd_count, an_count, ns_count, ar_count,\n" + " qtype, qclass, atype, aclass, attl, aa, tc, rd, cd, ra, ad, do, edns0, qr,\n" + " edns0_ecs, edns0_ecs_family, edns0_ecs_source, edns0_ecs_scope,\n" + " edns0_ecs_address\n" + "\"icmp\" table fields:\n" + " type, code, echo_identifier, echo_sequence, du_protocol, du_src_addr,\n" + " du_dst_addr, desc\n", + argv0); +} + +#ifdef WIN32 +// windows support is merely for development purposes atm +#define PACKAGE_STRING "packetq" +struct option { + char* s; + int args; + int b; + char c; +}; + +char* optarg = 0; +int optind = 1; + +int getopt_long(int argc, char* argv[], const char* str, option* opt, int* option_index) +{ + while (optind < argc) { + if (argv[optind][0] != '-') + return -1; + if (argv[optind][1] != '-') { + int i = 0; + while (opt[i].s != NULL) { + if (opt[i].c == argv[optind][1]) { + optarg = argv[optind + opt[i].args]; + optind += 1 + opt[i].args; + return opt[i].c; + } + i++; + } + } + optind++; + } + return -1; +} + +#endif + +void sigproc(int sig) +{ + // ignore sig pipe + signal(SIGPIPE, sigproc); +} + +PacketQ* g_app = new PacketQ(); + +} // namespace packetq + +using namespace packetq; + +// The main funtion +int main(int argc, char* argv[]) +{ + signal(SIGPIPE, sigproc); + int port = 0; + int limit = 0; + int max_conn = 7; + bool daemon = false; + + std::string webroot = "", pcaproot = ""; + std::string queries[NUM_QUERIES] = { + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + }; + int qcount = 0; + + while (1) { + int option_index; + struct option long_options[] = { + { "select", 1, 0, 's' }, + { "limit", 1, 0, 'l' }, + { "maxconn", 1, 0, 'm' }, + { "webroot", 1, 0, 'w' }, + { "pcaproot", 1, 0, 'r' }, + { "port", 1, 0, 'p' }, + { "daemon", 0, 0, 'd' }, + { "csv", 0, 0, 'c' }, + { "json", 0, 0, 'j' }, + { "table", 0, 0, 't' }, + { "xml", 0, 0, 'x' }, + { "rfc1035", 0, 0, 10000 }, + { "help", 0, 0, 'h' }, + { "version", 0, 0, 'v' }, + { NULL, 0, 0, 0 } + }; + + int c = getopt_long(argc, argv, "w:r:s:l:p:hHdvcxtjm:", long_options, &option_index); + if (c == -1) + break; + + switch (c) { + case 'v': + fprintf(stdout, "%s\n", PACKAGE_STRING); + exit(0); + case 's': + if (qcount < NUM_QUERIES) { + queries[qcount++] = optarg; + } else { + fprintf(stderr, "Warning: can't handle more than %d separate query strings; discarding '%s'\n", NUM_QUERIES, optarg); + } + break; + case 'c': + g_app->set_output(PacketQ::csv); + break; + case 't': + g_app->set_output(PacketQ::csv_format); + break; + case 'x': + g_app->set_output(PacketQ::xml); + break; + case 'j': + g_app->set_output(PacketQ::json); + break; + case 'd': + daemon = true; + break; + case 'w': + webroot = optarg; + break; + case 'r': + pcaproot = optarg; + break; + case 'm': + max_conn = atoi(optarg) + 1; + if (max_conn < 2) + max_conn = 2; + break; + case 'l': + limit = atoi(optarg); + break; + case 'p': + port = atoi(optarg); + break; + case 10000: // rfc1035 + g_app->set_escape(true); + break; + default: + fprintf(stderr, "Unknown option: %c\n", c); + usage(argv[0], false); + return 1; + case 'h': + usage(argv[0], true); + return 1; + } + } + init_packet_handlers(g_app->get_escape()); // set up tables + g_app->set_limit(limit); + if (port > 0) { + start_server(port, daemon, pcaproot, webroot, max_conn); + } + + if (optind >= argc) { + fprintf(stderr, "Missing input uri\n"); + usage(argv[0], false); + return 1; + } + + std::vector<std::string> in_files; + + while (optind < argc) { + in_files.push_back(argv[optind]); + optind++; + } + + Reader reader(in_files, g_app->get_limit()); + + if (g_app->get_output() == PacketQ::json) { + printf("[\n"); + } + for (int i = 0; i < qcount; i++) { + char tablename[32]; + snprintf(tablename, 32, "result-%d", i); + try { + Query query(tablename, queries[i].c_str()); + query.parse(); + query.execute(reader); + Table* result = query.m_result; + + switch (g_app->get_output()) { + case (PacketQ::csv_format): + if (result) + result->csv(true); + break; + case (PacketQ::csv): + if (result) + result->csv(); + break; + case (PacketQ::xml): + if (result) + result->xml(); + break; + case (PacketQ::json): + if (result) + result->json(i < (qcount - 1)); + break; + } + } catch (Error& e) { + printf("Error: %s\n", e.m_err.c_str()); + fflush(stdout); + exit(1); + } catch (...) { + printf("Error: an unknown error has occured !\n"); + fflush(stdout); + } + } + if (g_app->get_output() == PacketQ::json) { + printf("]\n"); + } + + delete g_app; + + destroy_packet_handlers(); + + return 0; +} diff --git a/src/packetq.h b/src/packetq.h new file mode 100644 index 0000000..8ee9841 --- /dev/null +++ b/src/packetq.h @@ -0,0 +1,70 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_packetq_h +#define __packetq_packetq_h + +#include "sql.h" + +namespace packetq { + +// App class +class PacketQ { +public: + enum OutputOpts { + json, + csv, + csv_format, + xml + }; + PacketQ() + { + m_escape = false; + m_limit = 0; + m_output = json; + } + void set_escape(bool escape) + { + m_escape = escape; + } + void set_limit(int limit) + { + m_limit = limit; + } + void set_output(OutputOpts opt) + { + m_output = opt; + } + int get_escape() { return m_escape; } + OutputOpts get_output() { return m_output; } + int get_limit() { return m_limit; } + +private: + bool m_escape; + int m_limit; + OutputOpts m_output; +}; + +extern PacketQ* g_app; + +} // namespace packetq + +#endif // __packetq_packetq_h diff --git a/src/pcap.cpp b/src/pcap.cpp new file mode 100644 index 0000000..0a39487 --- /dev/null +++ b/src/pcap.cpp @@ -0,0 +1,91 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "pcap.h" + +#include <stdio.h> +#include <stdlib.h> + +namespace packetq { + +bool Pcap_file::get_header() +{ + // establish: byte order and file format + int res = get_int32(); + if (res != 0xa1b2c3d4) { + res = flip32(res); + if (res != 0xa1b2c3d4) { + if (!m_gzipped) { + set_gzipped(); + return get_header(); + } + return false; + } + m_reverse_order = true; + } + // establish version + int major_version = get_int16(); + int minor_version = get_int16(); + if (major_version != 2 || minor_version != 4) { + printf("maj:%d min:%d\n", major_version, minor_version); + return false; + } + // check for 0 timezone offset and accuracy + if (!(get_int32() == 0)) { + printf("timezone offset != 0"); + return false; + } + if (!(get_int32() == 0)) { + printf("timezone offset != 0"); + return false; + } + + m_snapshot_length = get_int32(); + // check for ethernet packets + m_link_layer_type = get_int32(); + if (m_link_layer_type != 1 && m_link_layer_type != 101 && m_link_layer_type != 113) { + fprintf(stderr, "PCAP file unsupported linklayer (%d)\n", m_link_layer_type); + return false; + } + return true; +} + +unsigned char* Pcap_file::get_packet(int& len, int& s, int& us) +{ + s = 0; + us = 0; + len = 0; + s = get_int32(); + us = get_int32(); + len = get_int32(); + + // skip past reallen + get_int32(); + + if (get_eof() || len < 0) + return 0; + + unsigned char* buf = get_bytes(len); + + return buf; +} + +} // namespace packetq diff --git a/src/pcap.h b/src/pcap.h new file mode 100644 index 0000000..26bef6a --- /dev/null +++ b/src/pcap.h @@ -0,0 +1,209 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_pcap_h +#define __packetq_pcap_h + +#include <stdio.h> +#include <stdlib.h> +#include <zlib.h> + +#include "segzip.h" +#include "sql.h" + +namespace packetq { + +class Pcap_file { +private: + Pcap_file& operator=(const Pcap_file& other); + Pcap_file(Pcap_file&& other) noexcept; + Pcap_file const& operator=(Pcap_file&& other); + +public: + static const bool TAKE_OVER_FP = true; + + Pcap_file(FILE* fp, bool take_over_fp = false) + { + m_fp_owned = take_over_fp; + m_fp = fp; + m_reverse_order = false; + m_packetbuffer = 0; + m_packetbuffer_len = 0; + m_eof = false; + m_snapshot_length = 0; + m_link_layer_type = 0; + m_gzipped = false; + } + ~Pcap_file() + { + if (m_packetbuffer) + delete[] m_packetbuffer; + if (m_fp_owned) + fclose(m_fp); + } + + bool get_header(); + + unsigned char* get_packet(int& len, int& s, int& us); + + int get_int32() + { + int res = 0; + get_bytes((unsigned char*)&res, 4); + if (m_reverse_order) { + return flip32(res); + } + return res; + } + int get_int16() + { + short res = 0; + get_bytes((unsigned char*)&res, 2); + if (m_reverse_order) { + return flip16(res); + } + return res; + } + unsigned char* get_bytes(int count) + { + Buffer& buf = m_gzipped ? m_zipbuffer : m_filebuffer; + if (count < buf.m_buffer_len - buf.m_buffer_pos) { + unsigned char* ptr = &buf.m_buffer[buf.m_buffer_pos]; + buf.m_buffer_pos += count; + return ptr; + } + + unsigned char* bufp = get_pbuffer(count + 400); + int r = get_bytes(bufp, count); + + if (r == count) + return bufp; + return 0; + } + int get_bytes(unsigned char* dst, int count) + { + Buffer& buf = m_gzipped ? m_zipbuffer : m_filebuffer; + if (count == 0) + return 0; + + int bytes = 0; + while (count > 0) { + if (buf.m_buffer_len == buf.m_buffer_pos) { + buffread(); + if (buf.m_buffer_len == 0) { + m_eof = true; + return bytes; + } + } + int n = (buf.m_buffer_len - buf.m_buffer_pos) > count ? count : buf.m_buffer_len - buf.m_buffer_pos; + for (int i = 0; i < n; i++) { + *dst++ = buf.m_buffer[buf.m_buffer_pos++]; + } + bytes += n; + count -= n; + } + return bytes; + } + void buffread() + { + if (!m_fp) + throw Error("No file"); + + Buffer& buf = m_filebuffer; + if (buf.m_buffer_len == buf.m_buffer_pos) { + buf.m_buffer_len = (int)fread(buf.m_buffer, 1, buf.m_nextread, m_fp); + buf.m_buffer_pos = 0; + buf.m_nextread = sizeof(buf.m_buffer); + } + if (m_gzipped) { + if (m_zip.m_error || buf.m_buffer_len == buf.m_buffer_pos) { + m_zipbuffer.m_buffer_pos = m_zipbuffer.m_buffer_len = 0; + return; + } + if (m_zipbuffer.m_buffer_len == m_zipbuffer.m_buffer_pos) + m_zip.inflate(m_filebuffer, m_zipbuffer); + } + } + void set_gzipped() + { + m_gzipped = true; + m_filebuffer.m_buffer_pos = 0; + } + int flip16(unsigned short i) + { + unsigned int r = i & 0xff; + r <<= 8; + i >>= 8; + r |= i & 0xff; + return int(r); + } + int flip32(unsigned int i) + { + unsigned int r = i & 0xff; + r <<= 8; + i >>= 8; + r |= i & 0xff; + r <<= 8; + i >>= 8; + r |= i & 0xff; + r <<= 8; + i >>= 8; + r |= i & 0xff; + return int(r); + } + + unsigned char* get_pbuffer(int len) + { + if (!m_packetbuffer || len >= m_packetbuffer_len) { + if (m_packetbuffer) { + delete[] m_packetbuffer; + m_packetbuffer = 0; + } + m_packetbuffer_len = len + 4096; + m_packetbuffer = new (std::nothrow) unsigned char[m_packetbuffer_len]; + if (!m_packetbuffer) + m_packetbuffer_len = 0; + } + return m_packetbuffer; + } + bool get_eof() { return m_eof; } + int get_link_layer_type() { return m_link_layer_type; } + +private: + int m_snapshot_length; + int m_link_layer_type; + bool m_reverse_order; + bool m_eof; + bool m_gzipped; + FILE* m_fp; + bool m_fp_owned; + + unsigned char* m_packetbuffer; + int m_packetbuffer_len; + + Buffer m_filebuffer; + Buffer m_zipbuffer; + Zip m_zip; +}; + +} // namespace packetq + +#endif // __packetq_pcap_h diff --git a/src/reader.cpp b/src/reader.cpp new file mode 100644 index 0000000..dae5376 --- /dev/null +++ b/src/reader.cpp @@ -0,0 +1,84 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "reader.h" +#include "packet_handler.h" + +namespace packetq { + +void Reader::seek_to_start() +{ + currently_reading = filenames.begin(); + pcap.reset(); + packets_read = 0; +} + +bool Reader::done() +{ + return (!pcap && currently_reading == filenames.end()) || (max_packets > 0 && packets_read >= max_packets); +} + +bool Reader::read_next(Packet_handler* handler, const std::vector<int>& columns, Row& destination_row, int skip_packets) +{ + bool filled_in_row = false; + + while (!filled_in_row and !done()) { + // try opening pcap file + if (!pcap && currently_reading != filenames.end()) { + FILE* fp = fopen(currently_reading->c_str(), "rb"); + if (fp) { + pcap.reset(new Pcap_file(fp, Pcap_file::TAKE_OVER_FP)); + + if (!pcap->get_header()) + pcap.reset(); + } + + if (!pcap) + ++currently_reading; + } + + // try reading a row + if (pcap) { + int len, s, us; + unsigned char* data = pcap->get_packet(len, s, us); + bool read_success = len && data; + ++packets_read; // we count all packets + if (read_success) { + Packet packet(data, len, s, us, packets_read, pcap->get_link_layer_type()); + Packet::ParseResult res = packet.parse(handler, columns, destination_row, skip_packets == 0); + + if (res == Packet::NOT_SAMPLED) + --skip_packets; + + filled_in_row = res == Packet::OK; + } else { + // last row in file + pcap.reset(); + if (currently_reading != filenames.end()) + ++currently_reading; + } + } + } + + return filled_in_row; +} + +} // namespace packetq diff --git a/src/reader.h b/src/reader.h new file mode 100644 index 0000000..fb65833 --- /dev/null +++ b/src/reader.h @@ -0,0 +1,62 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_reader_h +#define __packetq_reader_h + +#include <memory> +#include <stdio.h> +#include <vector> + +#include "pcap.h" +#include "sql.h" + +namespace packetq { + +class Packet_handler; + +// reading packet rows out of a list of files +class Reader { +public: + Reader(std::vector<std::string> filenames, int max_packets) + : packets_read(0) + { + this->filenames = filenames; + this->currently_reading = filenames.end(); + this->max_packets = max_packets; + } + + void seek_to_start(); + + bool done(); + bool read_next(Packet_handler* handler, const std::vector<int>& columns, Row& destination_row, int skip_packets); + +private: + std::vector<std::string>::iterator currently_reading; + + std::vector<std::string> filenames; + int max_packets, packets_read; + std::unique_ptr<Pcap_file> pcap; +}; + +} // namespace packetq + +#endif // __packetq_reader_h diff --git a/src/refcountstring.h b/src/refcountstring.h new file mode 100644 index 0000000..f91a4a0 --- /dev/null +++ b/src/refcountstring.h @@ -0,0 +1,122 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_refcountstring_h +#define __packetq_refcountstring_h + +#include <cstdlib> +#include <cstring> + +// A simple reference-counted C string, intended to be used through a pointer +// as RefCountString * with manual management of the reference count in order +// to stay a POD (for use in unions). For the same reason, constructors are +// static. The wrapper RefCountStringHandle can be used where automatic +// reference handling is possible. +struct RefCountString { + // data + int count; + char data[]; + + // implementation + void inc_refcount() + { + count += 1; + } + + void dec_refcount() + { + count -= 1; + if (count == 0) + std::free(this); + } + + static RefCountString* allocate(int data_length) + { + void* chunk = std::calloc(1, sizeof(RefCountString) + data_length); + if (!chunk) + throw std::bad_alloc(); + + RefCountString* new_str = static_cast<RefCountString*>(chunk); + new_str->count = 1; + return new_str; + } + + static RefCountString* construct(const char* c_string) + { + std::size_t length = std::strlen(c_string); + RefCountString* str = RefCountString::allocate(length + 1); + std::memcpy(str->data, c_string, length + 1); + return str; + } + + static RefCountString* construct(const char* data, int from, int to) + { + int length = to - from; + if (length < 0) + length = 0; + RefCountString* str = RefCountString::allocate(length + 1); + std::memcpy(str->data, data + from, length); + str->data[length - 1 + 1] = '\0'; + return str; + } +}; + +class RefCountStringHandle { +private: + RefCountStringHandle& operator=(const RefCountStringHandle& other); + RefCountStringHandle(RefCountStringHandle&& other) noexcept; + RefCountStringHandle const& operator=(RefCountStringHandle&& other); + +public: + RefCountStringHandle() + { + value = 0; + } + + RefCountStringHandle(RefCountString* str) + { + value = str; + } + + ~RefCountStringHandle() + { + if (value) + value->dec_refcount(); + } + + RefCountString* operator*() + { + return value; + } + + void set(RefCountString* str) + { + if (value != str) { + if (value) + value->dec_refcount(); + value = str; + } + } + + RefCountString* value; +}; + +#endif // __packetq_refcountstring_h diff --git a/src/regression-test.sh b/src/regression-test.sh new file mode 100755 index 0000000..9d25736 --- /dev/null +++ b/src/regression-test.sh @@ -0,0 +1,92 @@ +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +set -e + +# Simple regression-testing tool that exercises all operators of the +# SQL evaluator and outputs the results. +# +# Usage: regression-test.sh pcap-dump-file +# +# If the script finds a binary called packetq-before, it will execute +# the query on that too and compare the results with diff. So copy the +# packetq binary to packetq-before before you make a change to see the +# effect on the output. + +#set -e +DIR=/tmp/test/packetq +mkdir -p $DIR +typeset -i test +test=0 +cd $(dirname $0) +for SQL in \ + "select qname as CertainQnames, qtype as Qtype, count(1) as count from dns where (qname='localhost' or qname like '%.root-servers.net') and qr==0 group by CertainQnames,Qtype order by count desc ;" \ + 'select qtype as Qtype, qname as Qname, count(1) as count from dns where qclass==3 and qr==0 group by Qtype,Qname order by count desc ;' \ + 'select rcode as Rcode, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==1 group by Rcode,ClientAddr order by count desc limit 50;' \ + "select 'ALL' as All, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by All,ClientSubnet order by count,ClientSubnet desc limit 200;;" \ + "select 'ALL' as All, subnet(src_addr,24,96) as ClientSubnet, count(1) as count from dns where qr==0 group by All,ClientSubnet order by count desc,ClientSubnet limit 200;;" \ + "select if(rsplit(qname,1)='de','ok','non-auth-tld') as Class, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by Class,ClientSubnet order by count,ClientSubnet,Class desc limit 200;;" \ + "select if(qr==1,'sent','recv') as Direction, if(protocol==6,'tcp',if(protocol==17,'udp',if(protocol==1,'icmp',if(protocol==58,'ipv6-icmp',protocol)))) as IPProto, count(1) as count from dns group by Direction,IPProto order by count,Direction desc ;" \ + "select if(ether_type==34525,'IPv6','IPv4') as IPVersion, qtype as Qtype, count(1) as count from dns where qr==0 group by IPVersion,Qtype order by count desc ;" \ + "select 'ALL' as All, do, edns0, edns_version, extended_rcode, z, if(do==1,'set','clr') as D0, count(1) as count from dns where qr==0 group by All,do,D0,edns0,edns_version,extended_rcode,z order by count desc ;" \ + "select 'ALL' as All, if(edns0,edns_version,'none') as EDNSVersion, count(1) as count from dns where qr==0 group by All,EDNSVersion order by count desc ;" \ + "select 'ALL' as All, if(qname like 'xn--%','idn','normal') as IDNQname, count(1) as count from dns where qr==0 group by All,IDNQname order by count desc ;" \ + "select 'ALL' as All, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qname like 'xn--%') group by All,TLD order by count,TLD desc ;" \ + "select 'ALL' as All, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==0 and (qtype=28 or qtype=38) and (qname like '%.root-servers.net') group by All,ClientAddr order by count desc limit 50;;" \ + "select 'ALL' as All, opcode as Opcode, count(1) as count from dns where qr==0 group by All,Opcode order by count desc ;" \ + "select 'ALL' as All, qtype as Qtype, count(1) as count from dns where qr==0 group by All,Qtype order by count desc ;" \ + 'select qtype as Qtype, len(qname) as QnameLen, count(1) as count from dns where qr==0 group by Qtype,QnameLen order by count,QnameLen,Qtype desc ;' \ + 'select qtype as Qtype, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qtype=1 or qtype=2 or qtype=5 or qtype=6 or qtype=12 or qtype=15 or qtype=28 or qtype=38 or qtype=255) group by Qtype,TLD order by count,TLD,Qtype desc limit 200;;' \ + "select 'ALL' as All, rcode as Rcode, count(1) as count from dns where qr==1 group by All,Rcode order by count desc ;" \ + 'select rcode as Rcode, msg_size as ReplyLen, count(1) as count from dns where qr==1 group by Rcode,ReplyLen order by count desc ;' \ + "select 'ALL' as All, rd as RD, count(1) as count from dns where qr==0 group by All,RD order by count desc ;" \ + "select if(protocol==6,'tcp',if(protocol==17,'udp',protocol)) as Transport, qtype as Qtype, count(1) as count from dns where qr==0 group by Transport,Qtype order by Transport,Qtype,count desc ;" \ + "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, dst_addr, lower_src, integer, float" \ + "select name( 'qtype' , qtype ) as qt, count(*) as count from dns group by qtype order by count desc;"\ + "select count(*) as count, lower(rsplit(qname,1)) as tld, istld(tld) as flag from dns group by tld order by count desc limit 50;" \ + ; +do + test=$test+1 + new=$(./packetq --version | tr " " "_") + echo "" + if [ ${#SQL} -gt 200 ]; then ellipsis="..."; else ellipsis=""; fi + echo "Test $test: '${SQL:0:200}$ellipsis'" + t_new=$(/usr/bin/time -f "%e" ./packetq --tlds /usr/share/packetq/tlds -s "$SQL" $1 2>&1 > $DIR/$new.test$test.result) + e_new=$? + echo " Comparing $new against available binaries:" + for prev in $(ls ../../packetq*/src/packetq); do + old=$($prev --version | cut -d " " -f 2) + ver=$(printf "%-20s" $old) + bin=$(printf "%-48s" $prev) + t_old=$(/usr/bin/time -f "%e" $prev -s "$SQL" $1 2>&1 > $DIR/$old.test$test.result) + e_old=$? + if [ $e_new = 0 -a $e_old = 0 -a "$t_old" != "0.00" ]; then + echo -e " $bin $ver: $t_old --> $t_new ($(python -c "print '%5.2f %d%%' % ($t_new - $t_old, ($t_new-$t_old)*100/$t_old)"))" + else + echo -e " $bin $ver: $t_old --> $t_new ($ver Failed)" + fi + diff -u $DIR/$old.test$test.result $DIR/$new.test$test.result > $DIR/$new.test$test.diff + if [ $? = 0 ]; then + #echo "Test $test: No changes in output" + true + else + head -n 20 $DIR/$new.test$test.diff + fi + done +done diff --git a/src/segzip.h b/src/segzip.h new file mode 100644 index 0000000..14b28e4 --- /dev/null +++ b/src/segzip.h @@ -0,0 +1,121 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_segzip_h +#define __packetq_segzip_h + +#include <stdio.h> +#include <stdlib.h> +#include <zlib.h> + +namespace packetq { + +class Buffer { +public: + Buffer() + { + m_buffer_len = 0; + m_buffer_pos = 0; + m_nextread = 1024; + } + int size() { return sizeof(m_buffer); } + unsigned char m_buffer[0x40000]; + int m_nextread; + int m_buffer_len; + int m_buffer_pos; +}; + +class Zip { +private: + Zip& operator=(const Zip& other); + Zip(Zip&& other) noexcept; + Zip const& operator=(Zip&& other); + +public: + Zip() + : m_stream() + { + m_init = true; + m_error = false; + m_run_end = false; + m_stream.next_out = 0; + m_stream.avail_out = 0; + } + ~Zip() + { + if (m_run_end) + ::inflateEnd(&m_stream); + } + bool inflate(Buffer& in, Buffer& out) + { + if (m_error) { + in.m_buffer_pos = in.m_buffer_len; + out.m_buffer_len = 0; + return false; + } + out.m_buffer_pos = 0; + out.m_buffer_len = sizeof(out.m_buffer); + m_stream.next_out = &out.m_buffer[out.m_buffer_pos]; + m_stream.avail_out = out.m_buffer_len - out.m_buffer_pos; + if (m_init) { + m_stream.next_in = 0; + m_stream.avail_in = 0; + m_stream.zalloc = 0; + m_stream.zfree = 0; + m_stream.opaque = 0; + m_init = false; + if (inflateInit2(&m_stream, 15 + 32) != Z_OK) { + m_error = true; + out.m_buffer_len = 0; + in.m_buffer_pos = in.m_buffer_len; + return false; + } + } + m_stream.next_in = &in.m_buffer[in.m_buffer_pos]; + m_stream.avail_in = in.m_buffer_len - in.m_buffer_pos; + + int ret = ::inflate(&m_stream, Z_NO_FLUSH); + + if (ret != Z_OK) + ::inflateEnd(&m_stream); + else + m_run_end = true; + if (ret != Z_OK && ret != Z_STREAM_END) { + m_error = true; + out.m_buffer_len = 0; + in.m_buffer_pos = in.m_buffer_len = 0; + return false; + } + + in.m_buffer_pos = in.m_buffer_len - m_stream.avail_in; + out.m_buffer_len = sizeof(out.m_buffer) - m_stream.avail_out; + out.m_buffer_pos = 0; + return true; + } + bool m_init; + bool m_run_end; + bool m_error; + z_stream m_stream; +}; + +} // namespace packetq + +#endif // __packetq_segzip_h diff --git a/src/server.cpp b/src/server.cpp new file mode 100644 index 0000000..96e14d3 --- /dev/null +++ b/src/server.cpp @@ -0,0 +1,1183 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "packetq.h" +#include "pcap.h" +#include "reader.h" + +#include <arpa/inet.h> +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <getopt.h> +#include <list> +#include <map> +#include <netdb.h> +#include <netinet/in.h> +#include <poll.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <string> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <syslog.h> +#include <time.h> +#include <unistd.h> + +#define MAXHOSTNAME 256 + +namespace packetq { +namespace httpd { + class Socket; + class Server; + + static char redirect[] = "HTTP/1.1 307 Temporary Redirect\r\n" + "Location: /\r\n" + "Connection: close\r\n" + "Content-Type: text/html\r\n" + "\r\n<html><head><title>moved</title></head><body><h1>moved</h1>this page has moved to /</body></html>"; + + static char header[] = "HTTP/1.1 200 OK\r\n" + "Server: PacketQ builtin\r\n" + "Connection: close\r\n" + "Access-Control-Allow-Origin: *\r\n" + "Content-Type: %s\r\n" + "\r\n"; + + static Server* g_server = 0; + + class SocketPool { + public: + SocketPool() + { + m_free = 0; + for (int i = 0; i < FD_SETSIZE; i++) { + m_sockets[i] = 0; + } + m_socket_count = 0; + } + int add(Socket* s) + { + if (m_free < FD_SETSIZE) + m_sockets[m_free] = s; + else + return -1; + int idx = m_free; + while (m_free < FD_SETSIZE && m_sockets[m_free]) + m_free++; + m_socket_count++; + return idx; + } + void remove(int s) + { + m_sockets[s] = 0; + if (s < m_free) + m_free = s; + m_socket_count--; + } + + int get_sockets() { return m_socket_count; } + void select(); + + fd_set m_readset; + fd_set m_writeset; + int m_free; + int m_socket_count; + Socket* m_sockets[FD_SETSIZE]; + }; + + SocketPool g_pool; + + class Stream { + public: + class Buffer { + private: + Buffer& operator=(const Buffer& other); + Buffer const& operator=(Buffer&& other); + + public: + Buffer(const unsigned char* buf, int len) + { + m_buf = new unsigned char[len]; + memcpy(m_buf, buf, len); + m_len = len; + m_pos = 0; + } + Buffer(Buffer&& other) noexcept + { + m_buf = other.m_buf; + m_len = other.m_len; + m_pos = other.m_pos; + other.m_buf = 0; + other.m_len = 0; + other.m_pos = 0; + } + ~Buffer() + { + m_len = 0; + delete[] m_buf; + } + unsigned char* m_buf; + int m_len; + int m_pos; + }; + Stream() + { + m_len = 0; + } + void push_front(unsigned char* data, int len) + { + m_stream.push_front(Buffer(data, len)); + m_len += len; + } + void write(unsigned char* data, int len) + { + m_stream.push_back(Buffer(data, len)); + m_len += len; + } + int read(unsigned char* data, int maxlen) + { + int p = 0; + while (p < maxlen && m_len > 0) { + Buffer& buf = m_stream.front(); + int l = maxlen - p; + if (l > buf.m_len - buf.m_pos) + l = buf.m_len - buf.m_pos; + for (int i = 0; i < l; i++) { + data[p++] = buf.m_buf[buf.m_pos++]; + } + m_len -= l; + if (l == 0) { + m_stream.pop_front(); + } + } + return p; + } + int len() + { + return m_len; + } + int get() + { + unsigned char c = '@'; + int r = read(&c, 1); + if (r == 0) + return -1; + return c; + } + + private: + int m_len; + std::list<Stream::Buffer> m_stream; + }; + + class Socket { + private: + Socket& operator=(const Socket& other); + Socket(Socket&& other) noexcept; + Socket const& operator=(Socket&& other); + + public: + Socket(int s, bool serv) + : m_want_write(false) + { + int flags; + + // Add non-blocking flag + if ((flags = fcntl(s, F_GETFL)) == -1) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_GETFL) failed: %d\n", s, errno); + exit(-1); + } + if (fcntl(s, F_SETFL, flags | O_NONBLOCK)) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_SETFL, 0x%x) failed: %d\n", s, errno, flags | O_NONBLOCK); + exit(-1); + } + + m_bytes_written = 0; + m_bytes_read = 0; + m_serv = serv; + m_socket = s; + m_sidx = g_pool.add(this); + m_close_when_empty = false; + m_file = 0; + } + virtual ~Socket() + { + g_pool.remove(m_sidx); + close(m_socket); + } + void process(bool read) + { + // m_serv means this is a listening socket + if (m_serv) + return; + if (!read) { + on_write(); + unsigned char ptr[4096]; + int len; + + while ((len = m_write.read(ptr, sizeof(ptr)))) { + int res = write(m_socket, ptr, len); +#if EAGAIN != EWOULDBLOCK + if (res == -1 && (errno == EAGAIN || errno == EWOULDBLOCK)) { +#else + if (res == -1 && (errno == EAGAIN)) { +#endif + m_write.push_front(ptr, len); + set_want_write(); + return; + } + if (res < 0) { + delete this; + return; + } + m_bytes_written += res; + if (res < len) { + m_write.push_front(&ptr[res], len - res); + set_want_write(); + return; + } + } + if (m_close_when_empty) { + shutdown(m_socket, SHUT_WR); + // fflush(m_socket); + delete this; + } + } + if (read) { + int avail = read_sock(); + + if (avail) + on_read(); + } + } + virtual void file_write() + { + } + virtual void file_read() + { + } + void set_delete() + { + m_close_when_empty = true; + m_want_write = false; + } + virtual void on_write() + { + } + virtual void on_read() + { + } + int read_sock() + { + unsigned char buf[2000]; + int len = 0; + if ((len = recv(m_socket, buf, sizeof(buf) - 1, 0)) > 0) { + m_bytes_read += len; + buf[len] = 0; + m_read.write(buf, len); + } + if (len < 0) { + delete this; + return 0; + } + return len; + } + bool failed() + { + return m_sidx == -1; + } + bool has_data() + { + return m_want_write || m_write.len() > 0; + } + void set_want_write(bool set = true) + { + m_want_write = set; + } + + int m_bytes_written; + int m_bytes_read; + int m_socket; + int m_file; + int m_sidx; + bool m_serv; + bool m_want_write; + bool m_close_when_empty; + char m_buffer[4096]; + + Stream m_read, m_write; + }; + + void SocketPool::select() + { + FD_ZERO(&m_readset); + FD_ZERO(&m_writeset); + int max = 0; + for (int i = 0; i < FD_SETSIZE; i++) { + if (m_sockets[i]) { + if (max < m_sockets[i]->m_socket) + max = m_sockets[i]->m_socket; + FD_SET(m_sockets[i]->m_socket, &m_readset); + if (m_sockets[i]->has_data()) + FD_SET(m_sockets[i]->m_socket, &m_writeset); + if (max < m_sockets[i]->m_file) + max = m_sockets[i]->m_file; + FD_SET(m_sockets[i]->m_file, &m_readset); + } + } + timeval timeout; + timeout.tv_sec = 30; + timeout.tv_usec = 0; + + int sel = ::select(max + 1, &m_readset, &m_writeset, 0, &timeout); + if (sel < 0) { + syslog(LOG_ERR | LOG_USER, "sel -1 errno = %d %s max:%d", errno, strerror(errno), max); + exit(-1); + } + if (sel) { + for (int i = 0; i < FD_SETSIZE; i++) { + if (m_sockets[i] && m_sockets[i]->m_file) { + if (FD_ISSET(m_sockets[i]->m_file, &m_readset)) { + m_sockets[i]->file_read(); + } + if (m_sockets[i] && FD_ISSET(m_sockets[i]->m_file, &m_writeset)) { + m_sockets[i]->file_write(); + } + } + if (m_sockets[i] && FD_ISSET(m_sockets[i]->m_socket, &m_readset)) { + m_sockets[i]->process(true); + } + if (m_sockets[i] && FD_ISSET(m_sockets[i]->m_socket, &m_writeset)) { + m_sockets[i]->process(false); + } + } + } + } + + class Server { + public: + Socket m_socket; + + Server(int port, const std::string& pcaproot, const std::string& webroot) + : m_socket(establish(port), true) + , m_pcaproot(pcaproot) + , m_webroot(webroot) + { + if (m_socket.m_socket < 0) { + if (m_socket.m_socket == EADDRINUSE) + syslog(LOG_ERR | LOG_USER, "Fail EADDRINUSE (%d)\n", m_socket.m_socket); + else + syslog(LOG_ERR | LOG_USER, "Fail %d port:%d\n", m_socket.m_socket, port); + exit(-1); + } + } + + ~Server() + { + } + + int get_connection() + { + int s = m_socket.m_socket; + int t; /* socket of connection */ + if ((t = accept(s, NULL, NULL)) < 0) /* accept connection if there is one */ + return (-1); + + return (t); + } + + int establish(unsigned short portnum) + { + int s, res; + sockaddr_in sa; + memset(&sa, 0, sizeof(struct sockaddr_in)); + + sa.sin_family = AF_INET; + sa.sin_addr.s_addr = htonl(INADDR_ANY); + + sa.sin_port = htons(portnum); + + if ((s = socket(AF_INET, SOCK_STREAM, 0)) < 0) + return (-2); + int on = 1; + + res = setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)); + + if ((res = bind(s, (const sockaddr*)&sa, sizeof(struct sockaddr_in))) < 0) { + close(s); + return (res); /* bind address to socket */ + } + + // Add non-blocking flag + int flags; + if ((flags = fcntl(s, F_GETFL)) == -1) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_GETFL) failed: %d\n", s, errno); + exit(-1); + } + if (fcntl(s, F_SETFL, flags | O_NONBLOCK)) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_SETFL, 0x%x) failed: %d\n", s, errno, flags | O_NONBLOCK); + exit(-1); + } + + listen(s, 511); /* max # of queued connects */ + return (s); + } + + std::string m_pcaproot; + std::string m_webroot; + }; + + class Url { + public: + Url(const char* url) + : m_full(url) + { + int i = 0; + for (; i < m_full.length();) { + char c = m_full.c_str()[i]; + if (c == '?') { + i++; + break; + } + m_path += c; + i++; + } + m_path = decode(m_path); + if (m_path == "") + m_path = "/"; + decode_params(m_full.substr(i).c_str()); + } + void decode_params(const char* params) + { + if (!params) + return; + std::string str = params; + for (int i = 0; i < str.length();) { + std::string param = "", value = ""; + for (; i < str.length();) { + char c = str.c_str()[i]; + if (c == '=' || c == '&') { + i++; + break; + } + param += c; + i++; + } + for (; i < str.length();) { + char c = str.c_str()[i]; + if (c == '&') { + i++; + break; + } + value += c; + i++; + } + add_param(decode(param), decode(value)); + } + } + const char* get_param(const char* param) + { + auto it = m_params.find(std::string(param)); + if (it == m_params.end()) + return 0; + return it->second.c_str(); + } + void add_param(std::string key, std::string val) + { + auto it = m_params.find(key); + if (it == m_params.end()) { + m_params[key] = val; + m_counts[key] = 1; + return; + } + char cnt[100]; + int n = m_counts[key]; + m_counts[key] = n + 1; + + snprintf(cnt, sizeof(cnt) - 1, "%d", n); + cnt[99] = 0; + std::string keyn = key; + keyn += cnt; + m_params[keyn] = val; + } + + std::string decode(std::string str) + { + std::string dst; + int percent_state = 0; + int code = 0; + for (int i = 0; i < str.length(); i++) { + char c = str.c_str()[i]; + if (percent_state) { + int n = 0; + if (c >= '0' && c <= '9') + n = c - '0'; + if (c >= 'a' && c <= 'f') + n = c - 'a' + 10; + if (c >= 'A' && c <= 'F') + n = c - 'A' + 10; + code = (code << 4) | n; + percent_state--; + if (!percent_state) { + dst += char(code); + code = 0; + } + } else { + if (c == '%') { + percent_state = 2; + } else + dst += c; + } + } + return dst; + } + + std::string get_full() + { + return m_full; + } + std::string get_path() + { + return m_path; + } + + std::string m_full; + std::string m_path; + std::map<std::string, std::string> m_params; + std::map<std::string, int> m_counts; + }; + + class Page { + public: + Page(const char* url, const char* body) + : m_url(url) + { + m_url.decode_params(body); + } + + void process() + { + + if (m_url.get_path().compare("/query") == 0) { + if (!m_url.get_param("file")) { + printf(header, "text/plain"); + printf("no file selected\n"); + return; + } + + printf(header, "text/plain"); + if (m_url.get_param("sql")) + query(m_url.get_param("sql")); + else + printf("no query defined \n"); + } else if (m_url.get_path().substr(0, 8).compare("/resolve") == 0) { + resolve(); + } else if (m_url.get_path().substr(0, 5).compare("/list") == 0) { + serve_dir(); + } else { + serve_static(); + } + + delete g_app; + } + static std::string join_path(const std::string& a, const std::string& b) + { + if (b.find("..") != std::string::npos) + return a; + if (a.length() == 0) + return b; + if (b.length() == 0) + return a; + if (a[a.length() - 1] != '/' && b[0] != '/') + return a + std::string("/") + b; + return a + b; + } + const char* get_mimetype(const std::string& file) + { + int p = file.find_last_of('.'); + if (p == std::string::npos || p + 1 >= file.length()) + return 0; + std::string suff = file.substr(p + 1); + if (suff.compare("js") == 0) + return "application/x-javascript"; + if (suff.compare("jpg") == 0) + return "image/jpeg"; + if (suff.compare("html") == 0) + return "text/html"; + if (suff.compare("htm") == 0) + return "text/html"; + if (suff.compare("txt") == 0) + return "text/plain"; + if (suff.compare("png") == 0) + return "image/png"; + if (suff.compare("gif") == 0) + return "image/gif"; + if (suff.compare("ico") == 0) + return "image/x-icon"; + if (suff.compare("json") == 0) + return "application/json"; + if (suff.compare("css") == 0) + return "text/css"; + + return 0; + } + bool serve_file(const std::string& file) + { + const char* mimetype = get_mimetype(file); + + if (mimetype) { + FILE* fp = fopen(file.c_str(), "rb"); + if (fp) { + printf(header, mimetype); + char buffer[8192]; + int len; + while ((len = fread(buffer, 1, 200, fp)) > 0) { + fwrite(buffer, 1, len, stdout); + } + fclose(fp); + return true; + } + } + return false; + } + void serve_static() + { + if (g_server->m_webroot == "") { + printf(header, "text/html"); + printf("<h2>This server is not configured to serve static pages</h2>"); + printf("Start using the -w option to set a html directory"); + return; + } + std::string file = join_path(g_server->m_webroot, m_url.get_path()); + + if (serve_file(file)) + return; + if (serve_file(join_path(file, "index.html"))) + return; + + if (m_url.get_path().compare("/") != 0) { + printf("%s", redirect); + return; + } + + printf(header, "text/html"); + printf("<h2>It works !</h2><br>\n"); + printf("%s", "<a href=\"/query?file=sample.pcap&sql=select%20qr,qname,protocol%20from%20dns%20limit%2018;\">Test query</a><br/>\n"); + printf("%s", "<a href=\"/list\">list available files</a><br/>\n"); + } + + void resolve() + { + const char* ip = m_url.get_param("ip"); + const char* name = m_url.get_param("name"); + + if (ip) { + + printf(header, "application/json"); + + printf("["); + + struct addrinfo* result; + struct addrinfo* res; + int error; + + error = getaddrinfo(ip, NULL, NULL, &result); + if (error == 0) { + for (res = result; res != NULL; res = res->ai_next) { + char hostname[NI_MAXHOST] = ""; + + error = getnameinfo(res->ai_addr, res->ai_addrlen, hostname, NI_MAXHOST, NULL, 0, 0); + if (error != 0) { + continue; + } + if (*hostname != '\0') { + printf("\"%s\"", hostname); + break; + } + } + freeaddrinfo(result); + } + printf("]\n"); + } else if (name) { + char tmp[100]; + printf(header, "application/json"); + + printf("["); + + struct addrinfo* result; + struct addrinfo* res; + int error; + + error = getaddrinfo(name, NULL, NULL, &result); + char empty[] = "", line[] = ",\n"; + char* sep = empty; + if (error == 0) { + for (res = result; res != NULL; res = res->ai_next) { + void* ptr = &((struct sockaddr_in*)res->ai_addr)->sin_addr; + if (res->ai_family == AF_INET6) + ptr = &((struct sockaddr_in6*)res->ai_addr)->sin6_addr; + tmp[0] = 0; + inet_ntop(res->ai_family, ptr, tmp, sizeof(tmp)); + printf("%s\"%s\"", sep, tmp); + sep = line; + } + freeaddrinfo(result); + } + printf("]\n"); + } else + printf("[]\n"); + } + + void serve_dir() + { + if (g_server->m_pcaproot == "") { + printf(header, "text/html"); + printf("<h2>This server is not configured to list pcapfiles</h2>"); + printf("Start using the -r option to set a pcap directory"); + return; + } + std::string directory = join_path(g_server->m_pcaproot, m_url.get_path().substr(5)); + + DIR* dir = opendir(directory.c_str()); + if (!dir) { + printf("%s", redirect); + return; + } + + printf(header, "application/json"); + + printf("[\n"); + struct dirent* d; + struct stat statbuf; + + char comma = ' '; + + while ((d = readdir(dir)) != 0) { + std::string subject = join_path(directory, d->d_name); + int fd = open(subject.c_str(), O_RDONLY); + + if (fd < 0) + continue; + if (fstat(fd, &statbuf) == -1) { + close(fd); + continue; + } + if (S_ISDIR(statbuf.st_mode)) { + if ((strcmp(d->d_name, ".") != 0) && (strcmp(d->d_name, "..") != 0)) { + printf(" %c{\n \"data\" : \"%s\",\n \"attr\" : { \"id\": \"%s\" },\n \"children\" : [], \"state\" : \"closed\" }\n", + comma, d->d_name, join_path(m_url.get_path(), d->d_name).substr(5).c_str()); + comma = ','; + } + } else { + bool found = false; + FILE* fp = fdopen(fd, "rb"); + if (fp) { + Pcap_file pfile(fp); + if (pfile.get_header()) { + unsigned char* data = 0; + int s = 0, us, len; + data = pfile.get_packet(len, s, us); + if (data) { + printf(" %c{\n \"data\" : \"%s\",\n \"attr\" : { \"id\" : \"%s\", \"size\": %d, \"time\": %d,\"type\": \"pcap\" },\n \"children\" : [] }\n", + comma, d->d_name, join_path(m_url.get_path(), d->d_name).substr(5).c_str(), int(statbuf.st_size), s); + comma = ','; + found = true; + } + } + fclose(fp); + } + if (!found) { + std::string str = subject; + transform(str.begin(), str.end(), str.begin(), tolower); + if (str.rfind(".json") == str.length() - 5) { + printf(" %c{\n \"data\" : \"%s\",\n \"attr\" : { \"id\" : \"%s\", \"size\": %d, \"type\": \"json\" },\n \"children\" : [] }\n", + comma, d->d_name, join_path(m_url.get_path(), d->d_name).substr(5).c_str(), int(statbuf.st_size)); + comma = ','; + } + } + } + close(fd); + } + + printf("]\n"); + + closedir(dir); + } + + void query(const char* sql) + { + Query query("result", sql); + + query.parse(); + + std::vector<std::string> in_files; + + int i = 0; + while (true) { + char param[50] = "file"; + + std::string par = "file"; + if (i > 0) { + snprintf(param, sizeof(param) - 1, "file%d", i); + param[49] = 0; + } + i++; + const char* f = m_url.get_param(param); + if (!f) + break; + std::string file = join_path(g_server->m_pcaproot, f); + in_files.push_back(file); + } + + Reader reader(in_files, g_app->get_limit()); + + query.execute(reader); + query.m_result->json(false); + } + Url m_url; + }; + + class Http_socket : public Socket { + private: + Http_socket& operator=(const Http_socket& other); + Http_socket(Http_socket&& other) noexcept; + Http_socket const& operator=(Http_socket&& other); + + public: + enum State { + get_post, + header, + body, + error, + wait_child, + done + }; + Http_socket(int socket) + : Socket(socket, false) + , m_http_version(0) + , m_emptyline(0) + { + m_state = get_post; + m_nextc = -1; + m_cr = false; + m_line = ""; + m_url = ""; + m_child_fd = 0; + m_child_pid = 0; + m_child_read = 0; + m_body_cnt = -1; + m_content_len = 0; + } + ~Http_socket() + { + if (m_child_pid) { + kill(m_child_pid, SIGHUP); + int status; + waitpid(m_child_pid, &status, 0); + } + if (m_child_fd) + close(m_child_fd); + m_file = 0; + } + inline void print(const char* fmt, ...) + { + char string[4096]; + va_list ap; + + va_start(ap, fmt); + vsnprintf(string, sizeof(string), fmt, ap); + va_end(ap); + + m_write.write((unsigned char*)string, strlen(string)); + } + + int peek() + { + if (m_nextc >= 0) + return m_nextc; + m_nextc = m_read.get(); + return m_nextc; + } + int getc() + { + int c = peek(); + m_nextc = -1; + return c; + } + + void on_read() + { + while (true) { + int c = peek(); + if (c == -1) + return; + if (m_body_cnt >= 0) { + c = getc(); + if (!(m_body_cnt == 0 && c == 10)) { + m_line += char(c); + m_content_len--; + } + m_body_cnt++; + if (m_content_len == 0) + parseline(); + continue; + } + c = getc(); + if (c != 13 && c != 10) { + m_line += char(c); + m_cr = false; + } else { + bool cr = m_cr; + m_cr = false; + if (c == 10 && cr) { + continue; + } + if (c == 13) + m_cr = true; + parseline(); + } + } + } + virtual void file_read() + { + set_want_write(); + } + virtual void file_write() + { + } + void on_write() + { + set_want_write(false); + if (m_state == wait_child) { + unsigned char buffer[4096]; + int status; + bool done = true; + if (0 == waitpid(m_child_pid, &status, WNOHANG)) { + done = false; + } + if (m_child_fd) { + // Add non-blocking flag + int flags; + if ((flags = fcntl(m_child_fd, F_GETFL)) == -1) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_GETFL) failed: %d\n", m_child_fd, errno); + exit(-1); + } + if (fcntl(m_child_fd, F_SETFL, flags | O_NONBLOCK)) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_SETFL, 0x%x) failed: %d\n", m_child_fd, errno, flags | O_NONBLOCK); + exit(-1); + } + + size_t res; + pollfd pfd; + pfd.fd = m_child_fd; + pfd.events = POLLIN; + pfd.revents = 0; + if (1 == poll(&pfd, 1, 0) && (pfd.revents & POLLIN) != 0) { + if ((res = read(m_child_fd, buffer, (int)sizeof(buffer))) > 0) { + done = false; + m_child_read += res; + m_write.write(buffer, res); + } + } + } + if (done) { + m_child_pid = 0; + if (m_child_fd) { + close(m_child_fd); + m_child_fd = 0; + m_file = 0; + } + set_delete(); + } + } + } + void parseline() + { + switch (m_state) { + case (get_post): { + m_state = error; + syslog(LOG_INFO | LOG_USER, "%s\n", m_line.c_str()); + int p = 0; + if (m_line.find("GET ") != -1) { + if ((p = m_line.find(" HTTP/1.1")) != -1) { + m_http_version = 1; + } else if ((p = m_line.find(" HTTP/1.0")) != -1) { + m_http_version = 0; + } else { + return; + } + m_url = m_line.substr(4, p - 4); + m_state = header; + } else if (m_line.find("POST ") != -1) { + if ((p = m_line.find(" HTTP/1.1")) != -1) { + m_http_version = 1; + } else if ((p = m_line.find(" HTTP/1.0")) != -1) { + m_http_version = 0; + } else { + return; + } + m_url = m_line.substr(5, p - 5); + m_state = header; + } + } break; + case (header): + if (m_line.length() == 0) { + m_body_cnt = 0; + m_state = body; + } else { + int colon = m_line.find(": "); + std::string key = m_line.substr(0, colon); + std::string val = m_line.substr(colon + 2); + if (key == "Content-Length") { + if (val.length() > 0) + m_content_len = atoi(val.c_str()); + } + } + break; + case (body): + m_body = m_line; + header_done(); + break; + default: + printf("error line: %s !\n", m_line.c_str()); + break; + } + m_line = ""; + } + void header_done() + { + fflush(stdout); // required before fork or any unflushed output will go to the client + int fd[2]; + if (pipe(fd) < 0) + return; + + // Add non-blocking flag + int flags; + if ((flags = fcntl(fd[0], F_GETFL)) == -1) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_GETFL) failed: %d\n", fd[0], errno); + exit(-1); + } + if (fcntl(fd[0], F_SETFL, flags | O_NONBLOCK)) { + syslog(LOG_ERR | LOG_USER, "fcntl(%d, F_SETFL, 0x%x) failed: %d\n", fd[0], errno, flags | O_NONBLOCK); + exit(-1); + } + + m_child_pid = fork(); + if (m_child_pid < 0) { + print("Internal error"); + set_delete(); + return; + } + if (m_child_pid == 0) { + ////////// child code ///////// + dup2(fd[1], fileno(stdout)); + dup2(fd[1], fileno(stderr)); + close(fd[1]); + + Page page(m_url.c_str(), m_body.c_str()); + page.process(); + fflush(stdout); + exit(0); + ///////////// child exit() /////////////// + } else { + close(fd[1]); + m_child_fd = fd[0]; + m_file = m_child_fd; + m_state = wait_child; + } + set_want_write(); + } + State m_state; + bool m_cr; + int m_body_cnt; + int m_content_len; + int m_nextc; + int m_child_pid; + int m_child_fd; + + int m_child_read; + + int m_http_version; // 0 = HTTP/1.0 1 = HTTP/1.1 + + int m_emptyline; + std::string m_line; + std::string m_url; + std::string m_body; + }; + +} // namespace httpd + +using namespace httpd; + +void start_server(int port, bool fork_me, const std::string& pcaproot, const std::string& webroot, int max_conn) +{ + pid_t pid, sid; + bool fg = !fork_me; + + printf("listening on port %d\n", port); + + if (!fg) { + pid = fork(); + + if (pid < 0) { + exit(EXIT_FAILURE); + } else if (pid > 0) { + exit(EXIT_SUCCESS); + } + + sid = setsid(); + + if (sid < 0) { + exit(EXIT_FAILURE); + } + } + openlog("packetq", LOG_PID, LOG_USER); + + httpd::Server server(port, pcaproot, webroot); + g_server = &server; + + while (true) { + httpd::g_pool.select(); + int cnt = g_pool.get_sockets(); + if (cnt < max_conn) { + int c = server.get_connection(); + if (c > -1) { + Http_socket* s = new (std::nothrow) Http_socket(c); + if (s && s->failed()) { + syslog(LOG_ERR | LOG_USER, "failed to create socket"); + delete s; + } + } + } + usleep(1000); + } + // loop will never break + // g_server = 0; + // syslog(LOG_INFO | LOG_USER, "exiting"); + // exit(EXIT_SUCCESS); +} + +} // namespace packetq diff --git a/src/server.h b/src/server.h new file mode 100644 index 0000000..ed14fee --- /dev/null +++ b/src/server.h @@ -0,0 +1,31 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_server_h +#define __packetq_server_h + +namespace packetq { + +void start_server(int port, bool fork, const std::string& pcaproot, const std::string& webroot, int max_conn); + +} // namespace packetq + +#endif // __packetq_server_h diff --git a/src/sql.cpp b/src/sql.cpp new file mode 100644 index 0000000..94ad7ed --- /dev/null +++ b/src/sql.cpp @@ -0,0 +1,2696 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "config.h" + +#include "sql.h" +#include "output.h" +#include "packet_handler.h" +#include "packetq.h" +#include "reader.h" + +#include <unordered_map> +#include <utility> +#include <vector> +#ifdef WIN32 +#include <windows.h> +#endif +#ifdef HAVE_LIBMAXMINDDB +#include <maxminddb.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +static MMDB_s* __cc_mmdb = 0; +static MMDB_s* __asn_mmdb = 0; +#endif + +namespace packetq { + +bool verbose = false; + +int g_allocs = 0; + +Column* Table::add_column(const char* name, const char* type, int id, bool hidden) +{ + if (!type) + return add_column(name, Coltype::_text, id, hidden); + else if (strcmp(type, "bool") == 0) + return add_column(name, Coltype::_bool, id, hidden); + else if (strcmp(type, "int") == 0) + return add_column(name, Coltype::_int, id, hidden); + else if (strcmp(type, "float") == 0) + return add_column(name, Coltype::_float, id, hidden); + else + return add_column(name, Coltype::_text, id, hidden); +} + +Column* Table::add_column(const char* name, Coltype::Type type, int id, bool hidden) +{ + Column* col = new Column(name, type, id, hidden); + col->m_offset = Table::align(m_curpos, col->m_def.m_align); + m_curpos = col->m_offset + col->m_def.m_size; + if (type == Coltype::_text) + m_text_column_offsets.push_back(col->m_offset); + m_cols.push_back(col); + return col; +} + +void Table::delete_row(Row* row) +{ + row->decref_text_columns(m_text_column_offsets); + m_row_allocator->deallocate(row); +} + +Row* Table::create_row() +{ + if (!m_row_allocator) { + m_rsize = sizeof(Row) - ROW_DUMMY_SIZE; // exclude the dummy + m_dsize = m_curpos; + m_row_allocator = new Allocator<Row>(m_rsize + m_dsize, 10000); + } + + Row* r = m_row_allocator->allocate(); + r->zero_text_columns(m_text_column_offsets); + return r; +} + +void Table::add_row(Row* row) +{ + m_rows.push_back(row); +} + +int g_comp = 0; + +void Ordering_terms::compile(const std::vector<Table*>& tables, const std::vector<int>& search_order, Query& q) +{ + for (auto it = m_terms.begin(); it != m_terms.end(); it++) { + OP* op = it->m_op; + it->m_op = op->compile(tables, search_order, q); + } +} + +class Sorter { +public: + Sorter(Ordering_terms& order) + : m_order(order) + { + } + bool operator()(Row* ia, Row* ib) + { + // this works under the assumption that the ordering terms have + // been compiled with only one table so the row index i is 0 + Row** ia_rows = &ia; + Row** ib_rows = &ib; + + for (auto it = m_order.m_terms.begin(); it != m_order.m_terms.end(); it++) { + g_comp++; + + OP* op = it->m_op; + op->evaluate(it->m_asc ? ia_rows : ib_rows, m_a); + op->evaluate(it->m_asc ? ib_rows : ia_rows, m_b); + int res = m_a.cmp(m_b); + if (res < 0) + return true; + if (res > 0) + return false; + } + return false; + } + bool eq(Row* ia, Row* ib) + { + Row** ia_rows = &ia; + Row** ib_rows = &ib; + + for (auto it = m_order.m_terms.begin(); it != m_order.m_terms.end(); it++) { + g_comp++; + + OP* op = it->m_op; + op->evaluate(it->m_asc ? ia_rows : ib_rows, m_a); + op->evaluate(it->m_asc ? ib_rows : ia_rows, m_b); + int res = m_a.cmp(m_b); + if (res != 0) + return false; + } + return true; + } + int cmp(Row* ia, Row* ib) + { + Row** ia_rows = &ia; + Row** ib_rows = &ib; + + for (auto it = m_order.m_terms.begin(); it != m_order.m_terms.end(); it++) { + g_comp++; + + OP* op = it->m_op; + op->evaluate(it->m_asc ? ia_rows : ib_rows, m_a); + op->evaluate(it->m_asc ? ib_rows : ia_rows, m_b); + int res = m_a.cmp(m_b); + if (res != 0) + return res; + } + return 0; + } + Ordering_terms& m_order; + Variant m_a, m_b; +}; + +struct Stki { + int s; + int l; + int b; +}; + +struct Spkt { + Variant cache; + int row; +}; + +class Per_sort { +public: + struct Tlink { + Tlink() + : m_next(0) + , row(0) + , m_eq(0) + { + } + + Tlink* get_eq() { return m_eq; } + void reset() + { + m_next = 0; + row = 0; + m_eq = 0; + } + void add_eq(Tlink* o) + { + if (!o->m_eq) { + // add single + if (!m_eq) { + // as first + m_eq = o; + o->m_eq_last = o; + return; + } + // to list + m_eq->m_eq_last->m_eq = o; + m_eq->m_eq_last = o; + return; + } else { + // add list + if (!m_eq) { + // as first + m_eq = o; + o->m_eq_last = o->m_eq->m_eq_last; + return; + } + // to list + m_eq->m_eq_last->m_eq = o; + m_eq->m_eq_last = o->m_eq->m_eq_last; + } + } + union { + Tlink* m_next; + Tlink* m_eq_last; + }; + Row* row; + Variant cache; + + private: + Tlink* m_eq; + }; + struct List { + public: + void reset() + { + m_size = 0; + m_fl[0] = 0; + m_fl[1] = 0; + } + int m_size; + Tlink* m_fl[2]; + }; + Per_sort(Table& table, Ordering_terms& order) + : m_sorter(order) + , m_table(table) + { + m_escalate_sort = order.m_terms.size() > 1; + m_asc = order.m_terms.begin()->m_asc ? 1 : -1; + m_op = order.m_terms.begin()->m_op; + memset(m_groups, 0, sizeof(m_groups)); + m_current.reset(); + } + inline bool add_to_list(List& list, Tlink* t) + { + if (list.m_fl[0] == 0) { + list.m_fl[0] = list.m_fl[1] = t; + list.m_size = 1; + return true; + } + list.m_fl[1]->m_next = t; + list.m_fl[1] = t; + list.m_size++; + return true; + } + inline bool insert_into_list(List& list, Tlink* t) + { + if (list.m_fl[0] == 0) { + list.m_fl[0] = list.m_fl[1] = t; + list.m_size = 1; + return true; + } + int cmp0 = cmp(t, list.m_fl[0]); + if (cmp0 == 0) { + list.m_fl[0]->add_eq(t); + return true; + } + if (cmp0 < 0) { + t->m_next = list.m_fl[0]; + list.m_fl[0] = t; + list.m_size++; + return true; + } + int cmp1 = cmp(t, list.m_fl[1]); + if (cmp1 == 0) { + list.m_fl[1]->add_eq(t); + return true; + } + if (cmp1 > 0) { + list.m_fl[1]->m_next = t; + list.m_fl[1] = t; + list.m_size++; + return true; + } + return false; + } + int cmp(Tlink* a, Tlink* b) + { + int cmp = a->cache.cmp(b->cache) * m_asc; + if (cmp != 0 || !m_escalate_sort) + return cmp; + return m_sorter.cmp(a->row, b->row); + } + inline void add(Tlink* t) + { + if (!insert_into_list(m_current, t)) { + insert_list(m_current); + m_current.reset(); + insert_into_list(m_current, t); + } + } + inline void insert_list(List& l) + { + unsigned int size = l.m_size; + int offs = 0; + size >>= 1; + while (size != 0) { + offs++; + size >>= 1; + } + if (m_groups[offs].m_size != 0) { + List m = merge(m_groups[offs], l); + m_groups[offs].reset(); + insert_list(m); + } else + m_groups[offs] = l; + } + List merge(List& l1, List& l2) + { + List r; + r.reset(); + Tlink* a = l1.m_fl[0]; + Tlink* b = l2.m_fl[0]; + if (!a) + return l2; + if (!b) + return l1; + + int size = l1.m_size + l2.m_size; + + while (a && b) { + int c = cmp(a, b); + if (c == 0) { + Tlink* a2 = a; + Tlink* b2 = b; + a = a->m_next; + b = b->m_next; + a2->m_next = 0; + b2->m_next = 0; + a2->add_eq(b2); + add_to_list(r, a2); + size--; + } else if (c < 0) { + Tlink* a2 = a; + a = a->m_next; + a2->m_next = 0; + add_to_list(r, a2); + } else { + Tlink* b2 = b; + b = b->m_next; + b2->m_next = 0; + add_to_list(r, b2); + } + } + if (a) { + r.m_fl[1]->m_next = a; + r.m_fl[1] = l1.m_fl[1]; + } + if (b) { + r.m_fl[1]->m_next = b; + r.m_fl[1] = l2.m_fl[1]; + } + + l1.reset(); + l2.reset(); + r.m_size = size; + return r; + } + + void sort() + { + int table_size = (int)m_table.m_rows.size(); + if (table_size <= 1) + return; + auto it = m_table.m_rows.begin(); + Tlink* links = new Tlink[table_size]; + + int i; + for (i = 0; i < table_size; i++) { + Tlink& r = links[i]; + r.reset(); + r.row = *it; + // &row works under the assumption that m_op has been compiled with + // this table only so row index is 0 + m_op->evaluate(&r.row, r.cache); + it++; + add(&r); + } + if (m_current.m_size) + insert_list(m_current); + List result; + result.reset(); + for (i = 0; i < sizeof(m_groups) / sizeof(List); i++) { + if (m_groups[i].m_size > 0) { + result = merge(result, m_groups[i]); + m_groups[i].reset(); + } + } + Tlink* p = result.m_fl[0]; + it = m_table.m_rows.begin(); + while (p) { + *it++ = p->row; + Tlink* e = p->get_eq(); + while (e) { + *it++ = e->row; + e = e->get_eq(); + } + p = p->m_next; + }; + + delete[] links; + } + + OP* m_op; + Sorter m_sorter; + bool m_escalate_sort; + int m_asc; + Table& m_table; + List m_groups[32]; + List m_current; +}; + +void Table::per_sort(Ordering_terms& order) +{ + Per_sort sort(*this, order); + + sort.sort(); + + return; +} + +void Table::merge_sort(Ordering_terms& order) +{ + Sorter sorter(order); + + bool escalate_sort = order.m_terms.size() > 1; + int asc = order.m_terms.begin()->m_asc ? 1 : -1; + OP* op = order.m_terms.begin()->m_op; + + int table_size = (int)m_rows.size(); + if (table_size <= 1) + return; + Row** row_ptrs = new Row*[table_size]; + Spkt* spktpool = new Spkt[table_size * 2]; + Spkt* rows[2]; + rows[0] = spktpool; + rows[1] = &spktpool[table_size]; + auto it = m_rows.begin(); + + int i = 0; + Spkt* r = rows[0]; + for (i = 0; i < table_size; i += 2) { + + row_ptrs[i] = *it++; + r[i].row = i; + // &row works under the assumption that m_op has been compiled with + // this table only so row index is 0 + op->evaluate(&row_ptrs[r[i].row], r[i].cache); + if (i + 1 < table_size) { + row_ptrs[i + 1] = *it++; + r[i + 1].row = i + 1; + op->evaluate(&row_ptrs[r[i + 1].row], r[i + 1].cache); + } + } + int swap = 0; + + Stki stack[64]; + Stki* sp = stack; + sp->s = 0; + sp->l = 2; + sp->b = 1; + rows[1][0] = rows[0][1]; + rows[1][1] = rows[0][0]; + + sp--; + + int npos = 0; + while (true) { + int start, len; + if (sp > stack && sp->l == sp[-1].l) { + // two equal size -> merge + + len = sp->l <<= 1; + start = sp[-1].s; + swap = sp[-1].b; + sp--; + sp--; + } else { + start = npos; + npos += 2; + swap = 0; + len = 2; + } + + int cnt = start + len > table_size ? table_size - start : len; + Spkt* s = rows[swap]; + Spkt* d = rows[1 - swap]; + if (cnt > 0) { + int p1 = start; + int p2 = start + (len >> 1); + int l1 = len >> 1; + int l2 = l1; + if (p1 + l1 > table_size) + l1 = table_size - p1; + if (p2 + l2 > table_size) + l2 = table_size - p2; + + i = start; + while (cnt-- > 0) { + if (l1 <= 0) { + d[i++] = s[p2++]; + } else if (l2 <= 0) { + d[i++] = s[p1++]; + } else { + int cmp = s[p1].cache.cmp(s[p2].cache) * asc; + if (cmp < 0 || (cmp == 0 && escalate_sort && sorter(row_ptrs[s[p1].row], row_ptrs[s[p2].row]))) { + l1--; + d[i++] = s[p1++]; + } else { + l2--; + d[i++] = s[p2++]; + } + } + } + } + ++sp; + sp->l = len; + sp->s = start; + sp->b = 1 - swap; + if (len > table_size) { + for (it = m_rows.begin(); it != m_rows.end(); it++) { + *it = row_ptrs[(d++)->row]; + } + + break; + } + } + delete[] row_ptrs; + delete[] spktpool; + return; +} + +void Table::limit(int limit, int offset) +{ + int count = 0; + auto e = m_rows.end(); + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + if (e != m_rows.end()) { + delete_row(*e); + m_rows.erase(e); + e = m_rows.end(); + } + + int l = count++; + if (l < offset || l >= offset + limit) { + e = it; + } + } + if (e != m_rows.end()) { + delete_row(*e); + m_rows.erase(e); + } +} + +void printrep(int n, char c) +{ + if (n >= 3000) + return; + char buf[3000]; + int i; + for (i = 0; i < n; i++) + buf[i] = c; + buf[i] = 0; + printf("%s", buf); +} + +void Table::xml() +{ + g_output.reset(); + int cols = (int)m_cols.size(); + + g_output.add_string("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"); + g_output.add_string("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"); + g_output.add_string("<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" lang=\"en\">\n<head>\n <title>"); + g_output.add_string(m_name.c_str()); + g_output.add_string("</title>\n"); + g_output.add_string("<style type=\"text/css\">\n"); + g_output.add_string(" th.int { color: #0F0C00; }\n"); + g_output.add_string(" th.float { color: #0F0900; }\n"); + g_output.add_string(" th.text { color: #0F0600; }\n"); + g_output.add_string(" th.bool { color: #0C0900; }\n"); + g_output.add_string("</style>\n"); + g_output.add_string("</head>\n"); + g_output.add_string("<body>\n"); + g_output.add_string("<table>\n"); + + g_output.add_string("<tr>"); + + for (int i = 0; i < cols; i++) { + if (m_cols[i]->m_hidden) + continue; + + const char* t = ""; + switch (m_cols[i]->m_type) { + case (Coltype::_float): + t = "float"; + break; + case (Coltype::_int): + t = "int"; + break; + case (Coltype::_text): + t = "text"; + break; + case (Coltype::_bool): + t = "bool"; + break; + } + g_output.add_string("<th class=\""); + g_output.add_string(t); + g_output.add_string("\">"); + g_output.add_string(m_cols[i]->m_name.c_str()); + g_output.add_string("</th>"); + } + g_output.add_string("</tr>\n"); + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + g_output.add_string("<tr>"); + Row* r = *it; + + Variant v; + for (int i = 0; i < cols; i++) { + Column* c = m_cols[i]; + + if (c->m_hidden) + continue; + + int offset = c->m_offset; + + static const int bufsize = 100; + char buf[bufsize]; + + g_output.add_string("<td>"); + switch (c->m_type) { + case Coltype::_bool: + g_output.add_string(r->access_column<bool_column>(offset) ? "1" : "0"); + break; + case Coltype::_int: + snprintf(buf, bufsize, "%i", r->access_column<int_column>(offset)); + g_output.add_string(buf); + break; + case Coltype::_float: + snprintf(buf, bufsize, "%g", r->access_column<float_column>(offset)); + g_output.add_string(buf); + break; + case Coltype::_text: + g_output.add_string(r->access_column<text_column>(offset)->data); + break; + } + g_output.add_string("</td> "); + } + + g_output.add_string("</tr>\n"); + } + g_output.add_string("</table>\n"); + g_output.add_string("</body>\n"); + g_output.add_string("</html>\n"); + g_output.print(); +} + +void Table::json(bool trailing_comma) +{ + g_output.reset(); + int cols = (int)m_cols.size(); + + g_output.add_string(" {\n "); + + g_output.add_q_string("table_name"); + g_output.add_string(": "); + g_output.add_q_string(m_name.c_str()); + g_output.add_string(",\n "); + + g_output.add_q_string("query"); + g_output.add_string(": "); + g_output.add_q_string(m_qstring.c_str()); + g_output.add_string(",\n "); + + g_output.add_q_string("head"); + g_output.add_string(": ["); + + bool append_comma = false; + for (int i = 0; i < cols; i++) { + if (m_cols[i]->m_hidden) + continue; + + if (append_comma) + g_output.add_string(",\n"); + else + g_output.add_string("\n"); + append_comma = true; + g_output.add_string(" { "); + g_output.add_q_string("name"); + g_output.add_string(": "); + g_output.add_q_string(m_cols[i]->m_name.c_str()); + g_output.add_string(","); + g_output.add_q_string("type"); + g_output.add_string(": "); + const char* t = ""; + switch (m_cols[i]->m_type) { + case (Coltype::_float): + t = "float"; + break; + case (Coltype::_int): + t = "int"; + break; + case (Coltype::_text): + t = "text"; + break; + case (Coltype::_bool): + t = "bool"; + break; + } + g_output.add_q_string(t); + g_output.add_string(" }"); + } + g_output.add_string("\n ],\n "); + g_output.add_q_string("data"); + g_output.add_string(": ["); + bool outer_comma = false; + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + if (outer_comma) + g_output.add_string(",\n ["); + else + g_output.add_string("\n ["); + outer_comma = true; + bool comma = false; + Row* r = *it; + + for (int i = 0; i < cols; i++) { + Column* c = m_cols[i]; + + if (c->m_hidden) + continue; + + if (comma) + g_output.add_string(","); + + comma = true; + + int offset = c->m_offset; + static const int bufsize = 100; + char buf[bufsize]; + + switch (c->m_type) { + case Coltype::_bool: + g_output.add_string(r->access_column<bool_column>(offset) ? "1" : "0"); + break; + case Coltype::_int: + snprintf(buf, bufsize, "%i", r->access_column<int_column>(offset)); + g_output.add_string(buf); + break; + case Coltype::_float: + snprintf(buf, bufsize, "%g", r->access_column<float_column>(offset)); + g_output.add_string(buf); + break; + case Coltype::_text: + g_output.add_q_string(r->access_column<text_column>(offset)->data); + break; + } + } + + g_output.add_string("]"); + } + g_output.add_string("\n ]\n"); + if (trailing_comma) { + g_output.add_string(" },\n"); + } else { + g_output.add_string(" }\n"); + } + g_output.print(); +} + +std::string csv_qoute_string(const std::string& s) +{ + std::string r = "\""; + int len = s.length(); + for (int i = 0; i < len; i++) { + if (s[i] == '"') { + r += '"'; + } + r += s[i]; + } + r += '"'; + return r; +} + +void Table::csv(bool format) +{ + int cols = (int)m_cols.size(); + std::vector<int> col_len(cols); + + for (int i = 0; i < cols; i++) + col_len[i] = 0; + int max = 0; + char* tmp = 0; + if (format) { + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + Row* r = *it; + + for (int i = 0; i < cols; i++) { + Column* c = m_cols[i]; + + if (c->m_hidden) + continue; + + int len = 0; + + int offset = c->m_offset; + static const int bufsize = 100; + char buf[bufsize]; + + switch (c->m_type) { + case Coltype::_bool: + len = 1; + break; + case Coltype::_int: + snprintf(buf, bufsize, "%i", r->access_column<int_column>(offset)); + len = strlen(buf); + break; + case Coltype::_float: + snprintf(buf, bufsize, "%g", r->access_column<float_column>(offset)); + len = strlen(buf); + break; + case Coltype::_text: + len = csv_qoute_string(r->access_column<text_column>(offset)->data).length(); + break; + } + len++; + if (len > col_len[i]) + col_len[i] = len; + if (len > max) + max = len; + } + } + for (int i = 0; i < cols; i++) { + if (m_cols[i]->m_hidden) + continue; + + int l = csv_qoute_string(m_cols[i]->m_name).length(); + l++; + if (l > col_len[i]) + col_len[i] = l; + if (l > max) + max = l; + } + + tmp = new char[max + 1]; + for (int i = 0; i < max; i++) + tmp[i] = 32; + tmp[max] = 0; + } + + for (int i = 0; i < cols; i++) { + if (m_cols[i]->m_hidden) + continue; + + printf("%s", csv_qoute_string(m_cols[i]->m_name).c_str()); + if (i < cols - 1) { + size_t pos = csv_qoute_string(m_cols[i]->m_name).length() + max - col_len[i] + 1; + if (format && pos < max) { + printf("%s,", &tmp[pos]); + } else { + printf(","); + } + } + } + printf("\n"); + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + Row* r = *it; + + for (int i = 0; i < cols; i++) { + Column* c = m_cols[i]; + + if (c->m_hidden) + continue; + + int offset = c->m_offset; + static const int bufsize = 100; + char buf[bufsize]; + + std::string out; + + switch (c->m_type) { + case Coltype::_bool: + out = r->access_column<bool_column>(offset) ? "1" : "0"; + break; + case Coltype::_int: + snprintf(buf, bufsize, "%i", r->access_column<int_column>(offset)); + out = buf; + break; + case Coltype::_float: + snprintf(buf, bufsize, "%g", r->access_column<float_column>(offset)); + out = buf; + break; + case Coltype::_text: + out = csv_qoute_string(r->access_column<text_column>(offset)->data); + break; + } + + fputs(out.c_str(), stdout); + if (i < cols - 1) { + if (format) { + printf("%s,", &tmp[out.length() + max - col_len[i] + 1]); + } else { + printf(","); + } + } + } + + printf("\n"); + } + delete[] tmp; +} + +void Table::dump() +{ + int cols = (int)m_cols.size(); + int width = 25; + char fmti[40]; + snprintf(fmti, sizeof(fmti) - 1, "%%%dd |", width); + fmti[39] = 0; + char fmtd[40]; + snprintf(fmtd, sizeof(fmtd) - 1, "%%%dg |", width); + fmtd[39] = 0; + char fmts[40]; + snprintf(fmts, sizeof(fmts) - 1, "%%%ds |", width); + fmts[39] = 0; + + printf("Table::dump() table:%s cols:%d\n", m_name.c_str(), cols); + printrep((width + 2) * cols + 1, '-'); + printf("\n"); + printf("|"); + for (int i = 0; i < cols; i++) + printf(fmti, m_cols[i]->m_type); + printf("\n"); + printf("|"); + for (int i = 0; i < cols; i++) + printf(fmts, m_cols[i]->m_name.c_str()); + printf("\n"); + printrep((width + 2) * cols + 1, '*'); + printf("\n"); + for (auto it = m_rows.begin(); it != m_rows.end(); it++) { + printf("|"); + Row* r = *it; + + for (int i = 0; i < cols; i++) { + Column* c = m_cols[i]; + int offset = c->m_offset; + + switch (c->m_type) { + case Coltype::_bool: + printf(fmts, r->access_column<bool_column>(offset) ? "1" : "0"); + break; + case Coltype::_int: + printf(fmti, r->access_column<int_column>(offset)); + break; + case Coltype::_float: + printf(fmtd, r->access_column<float_column>(offset)); + break; + case Coltype::_text: + printf(fmts, r->access_column<text_column>(offset)); + break; + } + } + + printf("\n"); + } + printrep((width + 2) * cols + 1, '-'); + printf("\n"); +} + +class Parser { +private: + Token::Type m_last; + +public: + std::list<Token> m_tokens; + typedef std::list<Token>::iterator Lit; + + Parser() + { + m_last = Token::_invalid; + } + + void push(Token::Type type, const char* string) + { + if (!(type == Token::_semicolon && m_last == Token::_semicolon)) + m_tokens.push_back(Token(type, string)); + m_last = type; + } + + void dump() + { + for (auto it = m_tokens.begin(); it != m_tokens.end(); it++) { + printf("Type %d: %s\n", it->get_type(), it->get_token()); + } + } + + bool analyze(Query& q) + { + auto it = m_tokens.begin(); + bool ok = true; + while (ok) { + ok = false; + if (get_sample_stmt(q, it)) + ok = true; + + if (get_select_stmt(q, it)) + ok = true; + } + + return true; + } + + bool get_sample_stmt(Query& q, Lit& i_iter) + { + Lit it = i_iter; + if (!is(it, Token::_label, "sample")) + return false; + it++; + if (!is(it, Token::_number)) + return false; + int sample = atoi(it->get_token()); + it++; + if (!is(it, Token::_semicolon)) + return false; + + it++; + q.m_sample = sample; + i_iter = it; + return true; + } + + bool get_select_stmt(Query& q, Lit& i_iter) + { + Lit it = i_iter; + if (!get_select_core(q, it)) { + return false; + } + + get_from(q, it); + get_where(q, it); + get_group_by(q, it); + get_order_by(q, it); + get_limit(q, it); + get_as(q, it); + if (!is(it, Token::_semicolon)) { + throw Error("Expected ';' but found '%s' !", it->get_token()); + } + it++; + i_iter = it; + return true; + } + + bool is(Lit& it, Token::Type type, const char* str = 0) + { + if (!str) + return (it->get_type() == type); + + return (it->get_type() == type && cmpi(it->get_token(), str)); + } + + OP* get_result_column(std::list<Token>::iterator& it) + { + OP* res = 0; + Lit save = it; + if (is(it, Token::_op, "*")) { + it++; + return new OP(Token(Token::_column, "*")); + } + if (it->get_type() == Token::_label) { + std::string table = it->get_token(); + it++; + if (is(it, Token::_op, ".")) { + it++; + if (is(it, Token::_op, "*")) { + it++; + std::string c = table + ".*"; + return new OP(Token(Token::_column, c.c_str())); + } + it = save; + return 0; + } + } + it = save; + if ((res = get_expr(it, 0))) { + save = it; + + if (is(it, Token::_label, "as")) { + it++; + if (is(it, Token::_label)) { + res->m_name = it->get_token(); + it++; + } else + it = save; + } + } + return res; + + // check for valid table + } + + bool get_select_core(Query& q, Lit& it) + { + Lit save = it; + if (!is(it, Token::_label, "select")) + return false; + it++; + bool again = true; + bool success = true; + while (again) { + OP* op; + if ((op = get_result_column(it))) { + q.m_select.push_back(op); + } else { + success = false; + break; + } + + if (is(it, Token::_op, ",")) + it++; + else + again = false; + } + if (success) + return true; + + it = save; + return false; + } + + bool get_ordering_terms(Ordering_terms& ordering, std::list<Token>::iterator& it) + { + OP* op; + while ((op = get_expr(it, 0))) { + bool asc = true; + if (it->get_type() == Token::_label) { + if (cmpi(it->get_token(), "asc")) { + // default + } else if (cmpi(it->get_token(), "desc")) { + asc = false; + } else if (cmpi(it->get_token(), "collate")) { + throw Error("unhandled option:collate"); + } else { + ordering.m_terms.push_back(Ordering_terms::OP_dir(op, asc)); + break; + } + + it++; + } + + ordering.m_terms.push_back(Ordering_terms::OP_dir(op, asc)); + + if (!is(it, Token::_op, ",")) + break; + it++; + } + return true; + } + bool get_group_by(Query& q, Lit& it) + { + if (!is(it, Token::_label, "group")) { + return true; + } + it++; + if (!is(it, Token::_label, "by")) + return false; + it++; + bool res = get_ordering_terms(q.m_group_by, it); + get_having(q, it); + return res; + } + bool get_as(Query& q, Lit& it) + { + if (!is(it, Token::_label, "as")) { + return true; + } + it++; + if (!is(it, Token::_label)) + return false; + q.m_result->m_name = it->get_token(); + it++; + return true; + } + + bool get_order_by(Query& q, Lit& it) + { + if (!is(it, Token::_label, "order")) { + return true; + } + it++; + if (!is(it, Token::_label, "by")) + return false; + it++; + return get_ordering_terms(q.m_order_by, it); + } + + bool get_limit(Query& q, Lit& it) + { + Lit save = it; + if (!is(it, Token::_label, "limit")) { + return true; + } + it++; + if (!is(it, Token::_number)) { + it = save; + throw Error("non numeric operand to limit"); + } + q.m_limit = atoi(it->get_token()); + it++; + save = it; + + if (!is(it, Token::_label, "offset")) { + return true; + } + it++; + if (!is(it, Token::_number)) { + it = save; + throw Error("non numeric operand to offset"); + } + q.m_offset = atoi(it->get_token()); + it++; + return true; + } + + bool get_having(Query& q, Lit& it) + { + Lit save = it; + if (!is(it, Token::_label, "having")) + return true; + it++; + OP* res = 0; + if ((res = get_expr(it, 0))) { + q.m_having = res; + return true; + } + it = save; + return false; + } + + bool get_where(Query& q, Lit& it) + { + Lit save = it; + if (!is(it, Token::_label, "where")) + return true; + it++; + OP* res = 0; + if ((res = get_expr(it, 0))) { + q.m_where = res; + return true; + } + it = save; + return false; + } + + bool get_from(Query& q, Lit& it) + { + if (!is(it, Token::_label, "from")) + return false; + it++; + if (it->get_type() == Token::_label) { + const char* name = it->get_token(); + if (get_packet_handler(name)) { + q.m_from_name = name; + it++; + return true; + } else + throw Error("Error in from statement, table '%s' not found", name); + } + throw Error("Error in from statement"); + } + + int get_stack_precedence(std::stack<OP*>& operator_stack) + { + int pre = 0; + if (!operator_stack.empty()) + pre = operator_stack.top()->m_precedence; + return pre; + } + + // using The shunting yard algorithm + OP* get_expr(Lit& it, int rec) + { + std::stack<OP*> operator_stack; + std::stack<OP*> operand_stack; + bool success = true; + bool expect_expr = true; + while (success) { + success = false; + Lit save = it; + Lit next = it; + next++; + + // match literal + if (expect_expr && is_literal(it)) { + OP* op = new OP(*it); + it++; + operand_stack.push(op); + success = true; + expect_expr = false; + continue; + } + // match literal + if (expect_expr && is_unary_op(it)) { + OP* op = new OP(*it); + op->set_type(Token::_uop); + it++; + if (!(op->m_right = get_expr(it, rec + 1))) + throw Error("Got unary '%s' but could not parse following expression", op->get_token()); + + operand_stack.push(op); + success = true; + expect_expr = false; + continue; + } + // match function-name ( + if (expect_expr && is(it, Token::_label) && is(next, Token::_paren, "(")) { + OP* func = new OP(*it); + func->set_type(Token::_function); + it++; + it++; + if (is(it, Token::_op, "*")) { + it->set_type(Token::_number); + it->set_token("1"); + } + func->m_param[0] = get_expr(it, rec + 1); + if (!func->m_param[0]) + throw Error("Missing operand to function"); + operand_stack.push(func); + int n = 1; + while (n < OP::max_param() && is(it, Token::_op, ",")) { + + it++; + func->m_param[n++] = get_expr(it, rec + 1); + } + if (!is(it, Token::_paren, ")")) + throw Error("Expected ) after %s", func->get_token()); + it++; + expect_expr = false; + success = true; + continue; + } + // match [[databasename .] table-name . ] column name + if (expect_expr && is(it, Token::_label)) { + OP* op = new OP(*it); + it++; + success = true; + op->set_type(Token::_column); + operand_stack.push(op); + expect_expr = false; + continue; + } + // match ( expr ) + if (!expect_expr && is(it, Token::_paren, ",")) { + break; + } + if (!expect_expr && is(it, Token::_paren, ")")) { + break; + } + if (expect_expr && is(it, Token::_paren, "(")) { + it++; + OP* op = 0; + if ((op = get_expr(it, rec + 1))) { + if (is(it, Token::_paren, ")")) { + it++; + operand_stack.push(op); + expect_expr = false; + success = true; + continue; + } + throw Error("Error in expression no )"); + } + it = save; + throw Error("Error in expression"); + } + // bin op + if (!expect_expr && is(it, Token::_op, "is") && is(next, Token::_op, "not")) { + it++; + it->set_token("is not"); + } + // bin op + if (!expect_expr && is(it, Token::_op, "not") && is(next, Token::_op, "like")) { + it++; + it->set_token("not like"); + } + if (!expect_expr && is(it, Token::_op) && OP::is_binary(it->get_token())) { + OP* bop = new OP(*it); + while (bop->m_precedence <= get_stack_precedence(operator_stack)) { + + OP* stack_op = operator_stack.top(); + operator_stack.pop(); + if (operand_stack.size() >= 2) { + + OP* stk1 = operand_stack.top(); + stack_op->m_right = stk1; + operand_stack.pop(); + OP* stk2 = operand_stack.top(); + stack_op->m_left = stk2; + operand_stack.pop(); + operand_stack.push(stack_op); + } + } + + operator_stack.push(bop); + it++; + success = true; + expect_expr = true; + continue; + } + } + while (!operator_stack.empty()) { + OP* bop = operator_stack.top(); + operator_stack.pop(); + if (bop) { + if (operand_stack.size() >= 2) { + OP* stk = operand_stack.top(); + bop->m_right = stk; + operand_stack.pop(); + OP* stk2 = operand_stack.top(); + bop->m_left = stk2; + operand_stack.pop(); + operand_stack.push(bop); + } + } + } + if (operand_stack.size() == 0) + return 0; + return operand_stack.top(); + } + + bool is_unary_op(Lit& it) + { + if (is(it, Token::_op, "-")) + return true; + if (is(it, Token::_op, "+")) + return true; + if (is(it, Token::_op, "~")) + return true; + if (is(it, Token::_op, "not")) + return true; + return false; + } + bool is_literal(Lit& it) + { + if (it->get_type() == Token::_number || it->get_type() == Token::_string) + return true; + if (it->get_type() == Token::_label && cmpi(it->get_token(), "null")) + return true; + return false; + } +}; + +class Lexer { +public: + Lexer(Parser& p) + : m_parser(p) + , num_state(_nan) + { + } + + Parser& m_parser; + + enum State { + _unknown, + _white, + _label, + _number, + _op, + _paren, + _string + }; + bool is_white(const char c) { return (c == ' ' || c == 9 || c == 10 || c == 13); } + bool is_char(const char c) { return ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')); } + bool is_num(const char c) { return ((c >= '0' && c <= '9')); } + bool is_op(const char c) { return (c == '*' || c == ',' || c == '=' || c == '<' || c == '>' || c == '/' || c == '|' || c == '%' || c == '+' || c == '-' || c == '&' || c == '~' || c == '!'); } + bool is_paren(const char c) { return (c == '(' || c == ')'); } + bool is_termination(const char c) { return (c == 0 || c == ';'); } + bool is_quote(const char c) { return (c == '\''); } + bool is_label_start(const char c) { return (is_char(c)); } + bool is_label_part(const char c) { return (is_num(c) || is_char(c) || c == '_'); } + + bool lex(const char* i_str) + { + const char* p = i_str; + State state = _white; + const char* strstart = 0; + bool is_escaped = false; + std::string str = ""; + + while (true) { + switch (state) { + case (_unknown): { + if (is_white(*p)) + state = _white; + else if (is_label_start(*p)) + state = _label; + else if (is_num(*p) || (*p == '.' && is_num(p[1]))) + state = _number; + else if (is_quote(*p)) + state = _string; + else if (is_paren(*p)) + state = _paren; + else if (is_op(*p)) + state = _op; + else if (is_termination(*p)) { + m_parser.push(Token::_semicolon, ";"); + if (*p++ == 0) { + m_parser.push(Token::_end, "END"); + return true; + } + } else { + m_parser.push(Token::_end, "END"); + printf("Unknown char %c (%d) at %d! in statement %s\n", *p, *p, int(p - i_str), i_str); + return false; + } + } break; + case (_white): { + if (is_white(*p)) + p++; + else { + state = _unknown; + } + } break; + case (_string): { + if ((!is_escaped) && is_quote(*p)) { + if (!strstart) { + strstart = p; + str = ""; + } else { + m_parser.push(Token::_string, str.c_str()); + + str = ""; + strstart = 0; + state = _unknown; + is_escaped = false; + } + p++; + } else { + if (is_escaped) { + if (!is_quote(*p)) + str += '\\'; + is_escaped = false; + } + + if (*p == 0) { + printf("Unexpected end of string in statement %s\n", strstart); + m_parser.push(Token::_end, "END"); + return false; + } + if (*p == '\\') + is_escaped = true; + else + str += (*p); + p++; + } + + } break; + case (_number): { + if (parse_num(*p)) { + if (!strstart) + strstart = p; + p++; + } else { + if (!strstart) + throw Error("Numeric problem"); + std::string label = strstart; + label = label.substr(0, p - strstart); + m_parser.push(Token::_number, label.c_str()); + + strstart = 0; + state = _unknown; + } + } break; + case (_label): { + if (!strstart) { + strstart = p++; + } else if (is_label_part(*p)) { + p++; + } else { + std::string label = strstart; + label = label.substr(0, p - strstart); + + Token::Type type = Token::_label; + if (cmpi(label, "is")) + type = Token::_op; + if (cmpi(label, "not")) + type = Token::_op; + if (cmpi(label, "in")) + type = Token::_op; + if (cmpi(label, "like")) + type = Token::_op; + if (cmpi(label, "glob")) + type = Token::_op; + if (cmpi(label, "match")) + type = Token::_op; + if (cmpi(label, "regexp")) + type = Token::_op; + if (cmpi(label, "and")) + type = Token::_op; + if (cmpi(label, "or")) + type = Token::_op; + + m_parser.push(type, label.c_str()); + + strstart = 0; + state = _unknown; + } + + } break; + case (_paren): { + std::string s; + s = *p; + m_parser.push(Token::_paren, s.c_str()); + p++; + state = _unknown; + } break; + case (_op): { + std::string s; + s = *p; + char n = p[1]; + switch (*p) { + case ('|'): + if (n == '|') { + p++; + s += *p; + } + break; + case ('>'): + if (n == '=') { + p++; + s += *p; + } + if (n == '>') { + p++; + s += *p; + } + break; + case ('<'): + if (n == '<') { + p++; + s += *p; + } + if (n == '=') { + p++; + s += *p; + } + if (n == '>') { + p++; + s += *p; + } + break; + case ('='): + if (n == '=') { + p++; + s += *p; + } + break; + case ('!'): + if (n == '=') { + p++; + s += *p; + } + break; + } + m_parser.push(Token::_op, s.c_str()); + p++; + state = _unknown; + } break; + default: + printf("Missing impl char %c at %d! in statement %s\n", *p, int(p - i_str), i_str); + m_parser.push(Token::_end, "END"); + return false; + } + } + } + bool parse_num(const char p) + { + switch (num_state) { + case (_nan): + num_state = _int; + if (p == '.') + num_state = _dot; + break; + case (_int): + if (p == '.') + num_state = _dot; + else if (!is_num(p)) { + num_state = _nan; + return false; + } + break; + case (_dot): + if (p == 'E' || p == 'e') + num_state = _e; + else if (!is_num(p)) { + num_state = _nan; + return false; + } + break; + case (_dec): + if (p == 'E' || p == 'e') + num_state = _e; + else if (!is_num(p)) { + num_state = _nan; + return false; + } + break; + case (_e): + if (p == '+' || p == '-') + num_state = _sign; + else if (is_num(p)) + num_state = _exp; + else { + throw Error("expected number digit after E"); + } + break; + case (_sign): + if (!is_num(p)) + throw Error("expected number digit after E"); + num_state = _exp; + break; + case (_exp): + if (!is_num(p)) { + num_state = _nan; + return false; + } + break; + } + return true; + } + enum Num_state { + _nan, + _int, + _dot, + _dec, + _e, + _sign, + _exp, + }; + + Num_state num_state; +}; + +void Query::parse() +{ + Parser p; + Lexer l(p); + l.lex(m_sql.c_str()); + // p.dump(); + if (!p.analyze(*this)) + throw Error("error parsing select statement"); +} + +// return column and index in tables, or 0 for column if column isn't found +std::pair<Column*, int> lookup_column_in_tables(const std::vector<Table*>& tables, + const std::vector<int>& search_order, + const char* name) +{ + if (strcmp(name, "*") == 0) + return std::pair<Column*, int>((Column*)0, 0); + + for (auto i = search_order.begin(); i != search_order.end(); ++i) { + Table* table = tables[*i]; + int col_index = table->get_col_index(name); + if (col_index >= 0) + return std::pair<Column*, int>(table->m_cols[col_index], *i); + } + + return std::pair<Column*, int>((Column*)0, 0); +} + +OP* OP::compile(const std::vector<Table*>& tables, const std::vector<int>& search_order, Query& q) +{ + OP* ret = 0; + for (int i = 0; i < max_param(); i++) { + if (m_param[i]) { + m_param[i] = m_param[i]->compile(tables, search_order, q); + if (m_param[i]->m_has_aggregate_function) + m_has_aggregate_function = true; + } + } + + if (m_left) { + m_left = m_left->compile(tables, search_order, q); + if (m_left->m_has_aggregate_function) + m_has_aggregate_function = true; + } + + if (m_right) { + m_right = m_right->compile(tables, search_order, q); + if (m_right->m_has_aggregate_function) + m_has_aggregate_function = true; + } + + // default to destination row + m_row_index = tables.size() - 1; + + if (get_type() == _column) { + auto lookup = lookup_column_in_tables(tables, search_order, get_token()); + Column* column = lookup.first; + m_row_index = lookup.second; + + if (!column) + throw Error("Column '%s' not found", get_token()); + + int offset = column->m_offset; + + m_t = column->m_type; + + switch (m_t) { + case Coltype::_int: + ret = new Column_access_int(*this, offset); + break; + case Coltype::_bool: + ret = new Column_access_bool(*this, offset); + break; + case Coltype::_float: + ret = new Column_access_float(*this, offset); + break; + case Coltype::_text: + ret = new Column_access_text(*this, offset); + break; + } + } else if (get_type() == _number) { + const char* p = get_token(); + bool integer = true; + while (*p != 0) { + if (*p < '0' || *p > '9') + integer = false; + p++; + } + if (integer) { + m_t = Coltype::_int; + ret = new Static_int(*this); + } else { + m_t = Coltype::_float; + ret = new Static_float(*this); + } + } else if (get_type() == _string) { + m_t = Coltype::_text; + ret = new Static_text(*this); + } else if ((get_type() == _function) && m_param[0]) { + Table* dest_table = tables[m_row_index]; + + m_t = Coltype::_int; + if (cmpi(get_token(), "if") && m_param[1] && m_param[2]) { + m_t = m_param[1]->m_t; + if (m_param[2]->m_t > m_t) + m_t = m_param[2]->m_t; + ret = new If_func(*this); + } else if (cmpi(get_token(), "name") && m_param[1]) { + m_t = Coltype::_text; + ret = new Name_func(*this); + } else if (cmpi(get_token(), "trim")) { + m_t = Coltype::_text; + ret = new Trim_func(*this); + } else if (cmpi(get_token(), "rsplit") && m_param[1]) { + m_t = Coltype::_text; + ret = new Rsplit_func(*this); + } else if (cmpi(get_token(), "netmask")) { + m_t = Coltype::_text; + ret = new Netmask_func(*this); + } else if (cmpi(get_token(), "cc")) { + m_t = Coltype::_text; + ret = new Cc_func(*this); + } else if (cmpi(get_token(), "asn")) { + m_t = Coltype::_int; + ret = new Asn_func(*this); + } else if (cmpi(get_token(), "count")) { + m_t = Coltype::_int; + ret = new Count_func(*this, dest_table); + } else if (m_param[0]->ret_type() == Coltype::_float && cmpi(get_token(), "min")) { + m_t = Coltype::_float; + ret = new Min_func_float(*this, dest_table); + } else if (m_param[0]->ret_type() == Coltype::_float && cmpi(get_token(), "max")) { + m_t = Coltype::_float; + ret = new Max_func_float(*this, dest_table); + } else if (m_param[0]->ret_type() == Coltype::_float && cmpi(get_token(), "sum")) { + m_t = Coltype::_float; + ret = new Sum_func_float(*this, dest_table); + } else if (cmpi(get_token(), "min")) { + m_t = Coltype::_int; + ret = new Min_func_int(*this, dest_table); + } else if (cmpi(get_token(), "max")) { + m_t = Coltype::_int; + ret = new Max_func_int(*this, dest_table); + } else if (cmpi(get_token(), "sum")) { + m_t = Coltype::_int; + ret = new Sum_func_int(*this, dest_table); + } else if (cmpi(get_token(), "lower")) { + m_t = Coltype::_text; + ret = new Lower_func(*this); + } else if (cmpi(get_token(), "len")) { + m_t = Coltype::_int; + ret = new Len_func(*this); + } else if (cmpi(get_token(), "truncate")) { + m_t = Coltype::_int; + ret = new Truncate_func(*this); + } else if (cmpi(get_token(), "stdev")) { + m_t = Coltype::_float; + ret = new Stdev_func(*this, dest_table); + } else if (cmpi(get_token(), "avg")) { + m_t = Coltype::_float; + ret = new Avg_func(*this, dest_table); + } + } else if ((get_type() == _op) && m_left && m_right) { + if (cmpi(get_token(), "||")) { + m_t = Coltype::_text; + ret = new Bin_op_concatenate(*this); + } else if (cmpi(get_token(), "*")) { + if (m_left->ret_type() == Coltype::_float || m_right->ret_type() == Coltype::_float) { + m_t = Coltype::_float; + ret = new Bin_op_mul_float(*this); + } else { + m_t = Coltype::_int; + ret = new Bin_op_mul(*this); + } + } else if (cmpi(get_token(), "/")) { + m_t = Coltype::_float; + ret = new Bin_op_div(*this); + } else if (cmpi(get_token(), "%")) { + m_t = Coltype::_float; + ret = new Bin_op_modulo(*this); + } else if (cmpi(get_token(), "+")) { + if (m_left->ret_type() == Coltype::_float || m_right->ret_type() == Coltype::_float) { + m_t = Coltype::_float; + ret = new Bin_op_add_float(*this); + } else { + m_t = Coltype::_int; + ret = new Bin_op_add(*this); + } + } else if (cmpi(get_token(), "-")) { + if (m_left->ret_type() == Coltype::_float || m_right->ret_type() == Coltype::_float) { + m_t = Coltype::_float; + ret = new Bin_op_sub_float(*this); + } else { + m_t = Coltype::_int; + ret = new Bin_op_sub(*this); + } + } else if (cmpi(get_token(), "<<")) { + m_t = Coltype::_int; + ret = new Bin_op_arithmetic_shift_left(*this); + } else if (cmpi(get_token(), ">>")) { + m_t = Coltype::_int; + ret = new Bin_op_arithmetic_shift_right(*this); + } else if (cmpi(get_token(), "&")) { + m_t = Coltype::_int; + ret = new Bin_op_bitwise_and(*this); + } else if (cmpi(get_token(), "|")) { + m_t = Coltype::_int; + ret = new Bin_op_bitwise_or(*this); + } else if (cmpi(get_token(), "<")) { + m_t = Coltype::_bool; + ret = new Bin_op_lt(*this); + } else if (cmpi(get_token(), "<=")) { + m_t = Coltype::_bool; + ret = new Bin_op_lteq(*this); + } else if (cmpi(get_token(), ">")) { + m_t = Coltype::_bool; + ret = new Bin_op_gt(*this); + } else if (cmpi(get_token(), ">=")) { + m_t = Coltype::_bool; + ret = new Bin_op_gteq(*this); + } else if (cmpi(get_token(), "=")) { + m_t = Coltype::_bool; + ret = new Bin_op_eq(*this); + } else if (cmpi(get_token(), "==")) { + m_t = Coltype::_bool; + ret = new Bin_op_eq(*this); + } else if (cmpi(get_token(), "like")) { + m_t = Coltype::_bool; + ret = new Bin_op_like(*this); + } else if (cmpi(get_token(), "not like")) { + m_t = Coltype::_bool; + ret = new Bin_op_not_like(*this); + } else if (cmpi(get_token(), "!=")) { + m_t = Coltype::_bool; + ret = new Bin_op_not_eq(*this); + } else if (cmpi(get_token(), "<>")) { + m_t = Coltype::_bool; + ret = new Bin_op_not_eq(*this); + } else if (cmpi(get_token(), "is")) { + m_t = Coltype::_bool; + ret = new Bin_op_eq(*this); + } else if (cmpi(get_token(), "is not")) { + m_t = Coltype::_bool; + ret = new Bin_op_not_eq(*this); + } else if (cmpi(get_token(), "and")) { + m_t = Coltype::_bool; + ret = new Bin_op_and(*this); + } else if (cmpi(get_token(), "or")) { + m_t = Coltype::_bool; + ret = new Bin_op_or(*this); + } + } else if ((get_type() == _uop) && m_right) { + if (cmpi(get_token(), "not")) { + m_t = Coltype::_bool; + ret = new Un_op_not(*this); + } else if (cmpi(get_token(), "+")) { + ret = m_right; + } else if (cmpi(get_token(), "-")) { + if (m_right->ret_type() == Coltype::_float) { + m_t = Coltype::_float; + ret = new Un_op_neg_float(*this); + } else { + m_t = Coltype::_int; + ret = new Un_op_neg(*this); + } + } else if (cmpi(get_token(), "~")) { + m_t = Coltype::_int; + ret = new Un_op_ones_complement(*this); + } + } + clear_ptr(); + if (!ret) + throw Error("Unknown operator error '%s' !", get_token()); + + delete this; + + return ret; +} + +void OP::evaluate_aggregate_operands(Row** rows) +{ + if (m_left) + m_left->evaluate_aggregate_operands(rows); + if (m_right) + m_right->evaluate_aggregate_operands(rows); + for (int i = 0; i < max_param(); ++i) + if (m_param[i]) + m_param[i]->evaluate_aggregate_operands(rows); +} + +void OP::combine_aggregate(Row* base_row, Row* other_row) +{ + if (m_left) + m_left->combine_aggregate(base_row, other_row); + if (m_right) + m_right->combine_aggregate(base_row, other_row); + for (int i = 0; i < max_param(); ++i) + if (m_param[i]) + m_param[i]->combine_aggregate(base_row, other_row); +} + +// return any column access ops found in given list of op trees - they don't +// have to be compiled beforehand; duplicate column tokens are skipped +std::vector<OP*> find_unique_column_ops(std::vector<OP*> ops) +{ + std::vector<OP*> res; + + while (!ops.empty()) { + OP* op = ops.back(); + ops.pop_back(); + + if (op->m_left) + ops.push_back(op->m_left); + if (op->m_right) + ops.push_back(op->m_right); + for (int i = 0; i < op->max_param(); ++i) + if (op->m_param[i]) + ops.push_back(op->m_param[i]); + + if (op->get_type() == Token::_column) { + bool found = false; + + for (auto i = res.begin(); i != res.end(); ++i) { + if (cmpii((*i)->get_token(), op->get_token())) { + found = true; + break; + } + } + + if (!found) + res.push_back(op); + } + } + + return res; +} + +void Query::replace_star_column_with_all_columns() +{ + bool found_star = false; + for (auto i = m_select.begin(); i != m_select.end(); ++i) { + if (strcmp((*i)->get_token(), "*") == 0) { + found_star = true; + break; + } + } + + if (found_star) { + for (auto i = m_select.begin(); i != m_select.end(); ++i) + delete *i; + m_select.clear(); + + if (!m_from_name.empty()) { + Packet_handler* handler = get_packet_handler(m_from_name); + + for (auto i = handler->packet_columns.begin(); i != handler->packet_columns.end(); ++i) + m_select.push_back(new OP(Token(Token::_column, i->name))); + } + } +} + +void Query::process_from() +{ + replace_star_column_with_all_columns(); + + if (m_from_name.empty()) + return; + + std::vector<OP*> all_ops; + all_ops.insert(all_ops.end(), m_select.begin(), m_select.end()); + if (m_where) + all_ops.push_back(m_where); + // skip m_having, it can't access source columns + for (auto i = m_order_by.m_terms.begin(); i != m_order_by.m_terms.end(); ++i) + all_ops.push_back(i->m_op); + for (auto i = m_group_by.m_terms.begin(); i != m_group_by.m_terms.end(); ++i) + all_ops.push_back(i->m_op); + + auto used_columns = find_unique_column_ops(all_ops); + + // add from table with used columns + Packet_handler* handler = get_packet_handler(m_from_name); + for (auto j = handler->packet_columns.begin(); j != handler->packet_columns.end(); ++j) + for (auto i = used_columns.begin(); i != used_columns.end(); ++i) + if (cmpii(j->name, (*i)->get_token())) + m_used_from_column_ids.push_back(j->id); + + m_from = handler->create_table(m_used_from_column_ids); +} + +void Query::process_select(Row** rows, Row* dest, GenericAccessor* dest_accessors) +{ + for (unsigned int i = 0, size = m_select.size(); i < size; ++i) { + OP* op = m_select[i]; + if (!op) + continue; + + if (op->m_has_aggregate_function) { + // defer evaluating aggregate functions, just eval their operands + op->evaluate_aggregate_operands(rows); + } else { + Variant v; + op->evaluate(rows, v); + dest_accessors[i].set(dest, v); + } + } +} + +void Query::combine_aggregates_in_select(Row* base_row, Row* other_row) +{ + for (unsigned int i = 0; i < m_select.size(); ++i) { + OP* op = m_select[i]; + if (op && op->m_has_aggregate_function) + op->combine_aggregate(base_row, other_row); + } +} + +void Query::process_aggregates_in_select(Row** rows, Row* dest, GenericAccessor dest_accessors[]) +{ + for (unsigned int i = 0; i < m_select.size(); ++i) { + OP* op = m_select[i]; + if (op && op->m_has_aggregate_function) { + Variant v; + op->evaluate(rows, v); + dest_accessors[i].set(dest, v); + } + } +} + +bool Query::process_where(Row** rows) +{ + if (!m_where) + return true; + + Variant v; + m_where->evaluate(rows, v); + return v.get_bool(); +} + +bool Query::process_having(Row** rows) +{ + if (!m_having) + return true; + + Variant v; + m_having->evaluate(rows, v); + return v.get_bool(); +} + +std::vector<Variant> process_group_by_key(Ordering_terms& group_by, Row** rows) +{ + int size = group_by.m_terms.size(); + + std::vector<Variant> res(size); + + for (int i = 0; i < size; ++i) + group_by.m_terms[i].m_op->evaluate(rows, res[i]); + + return res; +} + +bool Query::has_aggregate_functions() +{ + // this assumes the ops have been compiled + for (auto it = m_select.begin(); it != m_select.end(); it++) + if ((*it)->m_has_aggregate_function) + return true; + + return false; +} + +void Query::execute(Reader& reader) +{ + std::vector<Table*> tables; + std::vector<int> search_results_last, search_results_first, search_results_only; + + // set up tables + process_from(); + + if (m_from) + tables.push_back(m_from); + tables.push_back(m_result); + + for (int i = 0; i < int(tables.size()); ++i) + search_results_last.push_back(i); + for (int i = int(tables.size()) - 1; i >= 0; --i) + search_results_first.push_back(i); + + search_results_only.push_back(tables.size() - 1); + + std::vector<Row*> row_ptrs(tables.size()); + Row** rows = &row_ptrs[0]; + + std::vector<GenericAccessor> result_accessors_vector; + + // compile + for (auto i = m_select.begin(); i != m_select.end(); ++i) { + *i = (*i)->compile(tables, search_results_last, *this); + Column* col = m_result->add_column((*i)->get_name(), (*i)->ret_type()); + GenericAccessor a; + a.m_offset = col->m_offset; + a.m_type = col->m_type; + result_accessors_vector.push_back(a); + } + + if (m_where) + m_where = m_where->compile(tables, search_results_last, *this); + + if (m_having) + m_having = m_having->compile(tables, search_results_only, *this); + + if (m_group_by.exist()) + m_group_by.compile(tables, search_results_last, *this); + + if (m_order_by.exist()) { + // copy any missing columns to result table as hidden so we can + // order by them + std::vector<OP*> ops; + for (auto i = m_order_by.m_terms.begin(); i != m_order_by.m_terms.end(); ++i) + ops.push_back(i->m_op); + + std::vector<OP*> column_ops = find_unique_column_ops(ops); + + for (auto i = column_ops.begin(); i != column_ops.end(); ++i) { + const char* name = (*i)->get_token(); + auto lookup = lookup_column_in_tables(tables, search_results_first, name); + if (lookup.first and lookup.second < int(tables.size()) - 1) { + // found, but not in result table + OP* copying_op = new OP(**i); + copying_op = copying_op->compile(tables, search_results_last, *this); + m_select.push_back(copying_op); + Column* col = m_result->add_column(copying_op->get_name(), copying_op->ret_type(), -1, Column::HIDDEN); + GenericAccessor a; + a.m_offset = col->m_offset; + a.m_type = col->m_type; + result_accessors_vector.push_back(a); + } + } + + // we only provide access to result table for "order by"; in order + // to make the sort thing work correctly the result table currently + // has to be at index 0 + std::vector<Table*> tables_result_only = { m_result }; + std::vector<int> tables_result_only_search = { 0 }; + m_order_by.compile(tables_result_only, tables_result_only_search, *this); + } + + // execute + GenericAccessor* result_accessors = &result_accessors_vector[0]; + bool aggregate_functions = has_aggregate_functions(); + + int count = 0; + bool limiter = !m_order_by.exist() && !m_group_by.exist() && !aggregate_functions && m_limit >= 0; + + if (m_from) { + bool first_row = true; + Packet_handler* handler = get_packet_handler(m_from_name); + + reader.seek_to_start(); + + const int src_i = 0, dest_i = tables.size() - 1; + + rows[src_i] = m_from->create_row(); + + if (m_group_by.exist() || aggregate_functions) { + std::unordered_map<std::vector<Variant>, Row*> groups; + + rows[dest_i] = 0; + while (reader.read_next(handler, m_used_from_column_ids, *rows[src_i], first_row or m_sample == 0 ? 0 : m_sample - 1)) { + // fill in groups + if (rows[dest_i]) + rows[dest_i]->reset_text_columns(m_result->m_text_column_offsets); + else + rows[dest_i] = m_result->create_row(); + + process_select(rows, rows[dest_i], result_accessors); + if (process_where(rows)) { + auto key = process_group_by_key(m_group_by, rows); + Row*& entry = groups[key]; + if (entry) { + combine_aggregates_in_select(entry, rows[dest_i]); + } else { + entry = rows[dest_i]; + rows[dest_i] = 0; + } + } + + first_row = false; + rows[src_i]->reset_text_columns(m_from->m_text_column_offsets); + } + if (rows[dest_i]) + m_result->delete_row(rows[dest_i]); + + // put groups into result + for (auto i = groups.begin(); i != groups.end(); ++i) { + rows[dest_i] = i->second; + // propagate the aggregate results through the evaluation tree + process_aggregates_in_select(rows, rows[dest_i], result_accessors); + if (process_having(rows)) + m_result->add_row(rows[dest_i]); + else + m_result->delete_row(rows[dest_i]); + } + } else { + rows[dest_i] = m_result->create_row(); + while (reader.read_next(handler, m_used_from_column_ids, *rows[src_i], first_row or m_sample == 0 ? 0 : m_sample - 1)) { + // fill in result + process_select(rows, rows[dest_i], result_accessors); + if (process_where(rows)) { + bool commit = true; + if (limiter) { + int l = count++; + if (m_offset > 0) + l -= m_offset; + if (m_limit >= 0 && l >= m_limit) + break; + + if (l < 0) + commit = false; + } + + if (commit) { + m_result->add_row(rows[dest_i]); + rows[dest_i] = m_result->create_row(); + } + } + + first_row = false; + rows[src_i]->reset_text_columns(m_from->m_text_column_offsets); + } + m_result->delete_row(rows[dest_i]); + } + + m_from->delete_row(rows[src_i]); + } else { + const int dest_i = tables.size() - 1; + rows[dest_i] = m_result->create_row(); + process_select(rows, rows[dest_i], result_accessors); + if (process_where(rows)) + m_result->add_row(rows[dest_i]); + else + m_result->delete_row(rows[dest_i]); + } + + if (m_order_by.exist()) + m_result->per_sort(m_order_by); + + if (m_limit >= 0 && !limiter) + m_result->limit(m_limit, m_offset); +} + +DB::DB() +{ + Column::init_defs(); +} + +DB::~DB() +{ +} + +bool DB::query(const char* q) +{ + return false; +} + +Table* DB::get_table(const char* i_name) +{ + std::string name = lower(i_name); + Table* t = 0; + auto it = m_tables.find(name); + if (it != m_tables.end()) + t = it->second; + + return t; +} +Table* DB::create_or_use_table(const char* i_name) +{ + std::string name = lower(i_name); + Table* t = get_table(name.c_str()); + if (!t) + t = create_table(name.c_str()); + + return t; +} +Table* DB::create_table(const char* i_name) +{ + std::string name = lower(i_name); + Table* t = new Table(name.c_str()); + m_tables[std::string(name.c_str())] = t; + + return t; +} +Column::Column(const char* name, Coltype::Type type, int id, bool hidden) + : m_name(name) + , m_type(type) + , m_def(Column::m_coldefs[type]) + , m_id(id) + , m_offset(0) +{ + m_hidden = hidden; +} + +void Trim_func::evaluate(Row** rows, Variant& v) +{ + Variant str; + m_param[0]->evaluate(rows, str); + RefCountStringHandle str_handle(str.get_text()); + const char* s = (*str_handle)->data; + + const char* t; + RefCountStringHandle trim_handle; + if (m_param[1]) { + Variant trim; + m_param[1]->evaluate(rows, trim); + trim_handle.set(trim.get_text()); + t = (*trim_handle)->data; + } else + t = " "; + + int l = strlen(t); + if (l <= 0) { + v = *str_handle; + return; + } + + int slen = strlen(s); + int start = 0, end = slen; + + // left trim + while (end - start >= l && memcmp(s + start, t, l) == 0) + start += l; + + // right trim + while (end - start >= l && memcmp(s + end - l, t, l) == 0) + end -= l; + + if (start == 0 && end == slen) + v = *str_handle; + else { + RefCountStringHandle res(RefCountString::construct(s, start, end)); + v = *res; + } +} + +Cc_func::Cc_func(const OP& op) + : OP(op) +{ +#ifdef HAVE_LIBMAXMINDDB + if (__cc_mmdb) { + return; + } + + std::string db; + char* env = getenv("PACKETQ_MAXMIND_CC_DB"); + if (env) { + db = env; + } + + if (db.empty()) { + std::list<std::string> paths = { + "/var/lib/GeoIP", "/usr/share/GeoIP", "/usr/local/share/GeoIP" + }; + + if ((env = getenv("PACKETQ_MAXMIND_PATH"))) { + paths.push_front(std::string(env)); + } + + auto i = paths.begin(); + for (; i != paths.end(); i++) { + db = (*i) + "/GeoLite2-Country.mmdb"; + struct stat s; + if (!stat(db.c_str(), &s)) { + break; + } + } + if (i == paths.end()) { + return; + } + } + + MMDB_s* mmdb = new (std::nothrow) MMDB_s; + if (!mmdb) { + return; + } + + int ret = MMDB_open(db.c_str(), 0, mmdb); + if (ret != MMDB_SUCCESS) { + fprintf(stderr, "Warning: cannot open MaxMind CC database \"%s\": %s\n", db.c_str(), MMDB_strerror(ret)); + delete mmdb; + return; + } + + __cc_mmdb = mmdb; +#endif +} + +void Cc_func::evaluate(Row** rows, Variant& v) +{ +#ifdef HAVE_LIBMAXMINDDB + if (!__cc_mmdb) { + RefCountStringHandle res(RefCountString::construct("")); + v = *res; + return; + } + + Variant str; + m_param[0]->evaluate(rows, str); + RefCountStringHandle str_handle(str.get_text()); + + int gai_error, ret; + + MMDB_lookup_result_s mmdb_result = MMDB_lookup_string(__cc_mmdb, (*str_handle)->data, &gai_error, &ret); + + if (gai_error || ret != MMDB_SUCCESS || !mmdb_result.found_entry) { + RefCountStringHandle res(RefCountString::construct("")); + v = *res; + return; + } + + MMDB_entry_data_s entry_data; + ret = MMDB_get_value(&mmdb_result.entry, &entry_data, "country", "iso_code", NULL); + + if (ret != MMDB_SUCCESS || !entry_data.has_data || entry_data.type != MMDB_DATA_TYPE_UTF8_STRING) { + RefCountStringHandle res(RefCountString::construct("")); + v = *res; + return; + } + + RefCountStringHandle res(RefCountString::construct(entry_data.utf8_string, 0, entry_data.data_size)); + v = *res; +#else + RefCountStringHandle res(RefCountString::construct("")); + v = *res; +#endif +} + +Asn_func::Asn_func(const OP& op) + : OP(op) +{ +#ifdef HAVE_LIBMAXMINDDB + if (__asn_mmdb) { + return; + } + + std::string db; + char* env = getenv("PACKETQ_MAXMIND_ASN_DB"); + if (env) { + db = env; + } + + if (db.empty()) { + std::list<std::string> paths = { + "/var/lib/GeoIP", "/usr/share/GeoIP", "/usr/local/share/GeoIP" + }; + + if ((env = getenv("PACKETQ_MAXMIND_PATH"))) { + paths.push_front(std::string(env)); + } + + auto i = paths.begin(); + for (; i != paths.end(); i++) { + db = (*i) + "/GeoLite2-ASN.mmdb"; + struct stat s; + if (!stat(db.c_str(), &s)) { + break; + } + } + if (i == paths.end()) { + return; + } + } + + MMDB_s* mmdb = new (std::nothrow) MMDB_s; + if (!mmdb) { + return; + } + + int ret = MMDB_open(db.c_str(), 0, mmdb); + if (ret != MMDB_SUCCESS) { + fprintf(stderr, "Warning: cannot open MaxMind ASN database \"%s\": %s\n", db.c_str(), MMDB_strerror(ret)); + delete mmdb; + return; + } + + __asn_mmdb = mmdb; +#endif +} + +void Asn_func::evaluate(Row** rows, Variant& v) +{ +#ifdef HAVE_LIBMAXMINDDB + if (!__asn_mmdb) { + v = -1; + return; + } + + Variant str; + m_param[0]->evaluate(rows, str); + RefCountStringHandle str_handle(str.get_text()); + + int gai_error, ret; + + MMDB_lookup_result_s mmdb_result = MMDB_lookup_string(__asn_mmdb, (*str_handle)->data, &gai_error, &ret); + + if (gai_error || ret != MMDB_SUCCESS || !mmdb_result.found_entry) { + v = -1; + return; + } + + MMDB_entry_data_s entry_data; + ret = MMDB_get_value(&mmdb_result.entry, &entry_data, "autonomous_system_number", NULL); + + if (ret != MMDB_SUCCESS || !entry_data.has_data || entry_data.type != MMDB_DATA_TYPE_UINT32) { + v = -1; + return; + } + + v = (int_column)entry_data.uint32; +#else + v = -1; +#endif +} + +DB g_db; + +Coldef Column::m_coldefs[COLTYPE_MAX]; + +} // namespace packetq diff --git a/src/sql.h b/src/sql.h new file mode 100644 index 0000000..0c68e5f --- /dev/null +++ b/src/sql.h @@ -0,0 +1,1938 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_sql_h +#define __packetq_sql_h + +#include <algorithm> +#include <functional> +#include <list> +#include <map> +#include <math.h> +#include <regex.h> +#include <set> +#include <stack> +#include <stdarg.h> +#include <stdexcept> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <string> +#include <sys/types.h> +#include <vector> +#include <arpa/inet.h> +#include <netinet/in.h> +#ifndef s6_addr32 // For *BSD +#define s6_addr32 __u6_addr.__u6_addr32 +#endif +#include <sys/socket.h> + +#include "refcountstring.h" +#include "variant.h" + +#ifdef WIN32 +#define snprintf _snprintf +#endif + +#define RE_LEN 64 + +namespace packetq { + +extern int g_allocs; +static const int max_func_param = 4; +extern bool verbose; + +inline void vlog(const char* fmt, ...) +{ + if (!verbose) + return; + + char string[1024]; + va_list ap; + + va_start(ap, fmt); + vsnprintf(string, sizeof(string), fmt, ap); + va_end(ap); + + fprintf(stderr, "%s", string); +} + +class Error { +public: + Error(const char* fmt, ...) + { + char string[1024]; + va_list ap; + + va_start(ap, fmt); + vsnprintf(string, sizeof(string), fmt, ap); + va_end(ap); + + m_err = string; + } + std::string m_err; +}; + +class Query; +class Table; +class Parser; +class Row; +class Ordering_terms; + +inline std::string lower(const char* s) +{ + std::string str = s; + transform(str.begin(), str.end(), str.begin(), tolower); + return str; +} + +inline bool cmpi(const std::string& i_a, const char* b) +{ + std::string str = i_a; + transform(str.begin(), str.end(), str.begin(), tolower); + return (str.compare(b) == 0); +} + +inline bool cmpii(const std::string& i_a, const char* b) +{ + std::string stra = i_a; + transform(stra.begin(), stra.end(), stra.begin(), tolower); + std::string strb = b; + transform(strb.begin(), strb.end(), strb.begin(), tolower); + return (stra.compare(strb) == 0); +} + +inline const char* ind(int in) +{ + static const char spc[] = " "; + if (in < 0) + in = 0; + if (in > sizeof(spc) - 2) + in = sizeof(spc) - 2; + return &spc[sizeof(spc) - 1 - in]; +} + +class DB { +private: + class Item { + public: + std::string m_function; + int m_key; + bool operator<(const Item& r) const + { + if (m_key < r.m_key) + return true; + if (m_key > r.m_key) + return false; + if (m_function < r.m_function) + return true; + return false; + } + }; + +public: + DB(); + ~DB(); + + bool query(const char* q); + + Table* create_table(const char* name); + Table* create_or_use_table(const char* name); + Table* get_table(const char* name); + void add_lut(const char* table, int key, const char* value) + { + Item i; + i.m_function = table; + i.m_key = key; + m_lut[i] = value; + } + + RefCountString* get_value(const char* table, int key) + { + Item i; + i.m_function = table; + i.m_key = key; + auto it = m_lut.find(i); + if (it != m_lut.end()) + return RefCountString::construct(it->second.c_str()); + + return 0; + } + +private: + std::map<std::string, Table*> m_tables; + std::map<Item, std::string> m_lut; +}; + +extern DB g_db; + +class Coldef { +public: + int m_size; + int m_align; +}; + +template <typename T> +class Allocator { +private: + Allocator& operator=(const Allocator& other); + Allocator(Allocator&& other) noexcept; + Allocator const& operator=(Allocator&& other); + +public: + Allocator(int size, int buffersize) + : m_buffersize(buffersize) + , m_size(size) + { + add_buffer(); + } + ~Allocator() + { + auto it = m_buffers.begin(); + while (it != m_buffers.end()) { + delete *it; + m_buffers.erase(it); + it = m_buffers.begin(); + } + } + + void add_buffer() + { + m_curr_buffer = new _Buffer(*this); + m_buffers.push_back(m_curr_buffer); + } + T* allocate() + { + + T* obj = m_curr_buffer->allocate(); + if (!obj) { + for (auto it = m_buffers.begin(); + it != m_buffers.end(); + it++) { + if ((*it)->m_has_space) + obj = (*it)->allocate(); + if (obj) { + m_curr_buffer = *it; + break; + } + } + } + if (!obj) { + add_buffer(); + obj = m_curr_buffer->allocate(); + } + return obj; + } + void deallocate(T* item) + { + _Buffer** buffptr = (_Buffer**)item; + buffptr[-1]->deallocate(item); + } + +private: + class _Buffer { + private: + _Buffer& operator=(const _Buffer& other); + _Buffer(_Buffer&& other) noexcept; + _Buffer const& operator=(_Buffer&& other); + + public: + friend class Allocator; + _Buffer(Allocator& allocator) + : m_allocator(allocator) + { + m_has_space = true; + m_used = 0; + m_stride = (sizeof(_Buffer*) + m_allocator.m_size); + // align size of m_stride to that of a pointer + m_stride = ((m_stride / sizeof(void*)) + 1) * sizeof(void*); + m_memory = (char*)calloc(m_stride, m_allocator.m_buffersize); + } + ~_Buffer() + { + free(m_memory); + } + + T* allocate() + { + T* obj = 0; + if (m_free_list.size() > 0) { + obj = m_free_list.top(); + m_free_list.pop(); + } + if (!obj && m_used < m_allocator.m_buffersize) { + char* ptr = &m_memory[m_stride * m_used++]; + _Buffer** b = (_Buffer**)ptr; + *b = this; + obj = (T*)(&b[1]); + } + m_has_space = true; + if (!obj) + m_has_space = false; + return obj; + } + void deallocate(T* item) + { + m_has_space = true; + memset(item, 0, m_allocator.m_size); + m_free_list.push(item); + } + + bool m_has_space; + int m_stride; + std::stack<T*> m_free_list; + Allocator& m_allocator; + int m_used; + char* m_memory; + }; + + _Buffer* m_curr_buffer; + std::list<_Buffer*> m_buffers; + + int m_buffersize; + int m_size; +}; + +class Column { +public: + static const bool HIDDEN = true; + + static Coldef m_coldefs[COLTYPE_MAX]; + Column(const char* name, Coltype::Type type, int id, bool hidden); + // called at startup by DB + static void init_defs() + { + m_coldefs[Coltype::_bool].m_size = bool_size; + m_coldefs[Coltype::_bool].m_align = bool_align; + m_coldefs[Coltype::_int].m_size = int_size; + m_coldefs[Coltype::_int].m_align = int_align; + m_coldefs[Coltype::_float].m_size = float_size; + m_coldefs[Coltype::_float].m_align = float_align; + m_coldefs[Coltype::_text].m_size = text_size; + m_coldefs[Coltype::_text].m_align = text_align; + } + std::string m_name; + Coltype::Type m_type; + Coldef& m_def; + bool m_hidden; + int m_id; // numeric id used by packet parsers for speed + int m_offset; +}; + +// for accessing a field in a row +template <typename T> +class Accessor { +public: + Accessor() + : m_offset(0) + { + } + + T& value(Row* row); + + int m_offset; +}; + +typedef Accessor<bool_column> Bool_accessor; +typedef Accessor<int_column> Int_accessor; +typedef Accessor<float_column> Float_accessor; +typedef Accessor<text_column> Text_accessor; + +// for writing a variant to a field in a row +class GenericAccessor { +public: + void set(Row* row, const Variant& v); + + int m_offset; + Coltype::Type m_type; +}; + +class Table { +private: + Table& operator=(const Table& other); + Table(Table&& other) noexcept; + Table const& operator=(Table&& other); + +public: + Table(const char* name = 0, const char* query = 0) + : m_rsize(0) + , m_dsize(0) + { + m_row_allocator = 0; + m_name = name ? name : "result"; + m_qstring = query ? query : ""; + m_curpos = 0; + } + ~Table() + { + for (auto i = m_rows.begin(), end = m_rows.end(); i != end; ++i) + delete_row(*i); + for (auto i = m_cols.begin(), end = m_cols.end(); i != end; ++i) + delete *i; + delete m_row_allocator; + } + static int align(int pos, int align) + { + int res = pos; + int rem = pos % align; + if (rem) + res = pos + align - rem; + return res; + } + int get_col_index(const char* col) + { + int i = 0; + for (auto it = m_cols.begin(); it != m_cols.end(); it++) { + if (cmpii(m_cols[i]->m_name, col)) + return i; + i++; + } + return -1; + } + int get_column_id(const char* col) + { + for (auto i = m_cols.begin(); i != m_cols.end(); ++i) { + if (cmpii((*i)->m_name, col)) + return (*i)->m_id; + } + return -1; + } + + template <typename T> + Accessor<T> get_accessor(const char* col) + { + Accessor<T> res; + res.m_offset = -1; + + int i = get_col_index(col); + if (i >= 0) + res.m_offset = m_cols[i]->m_offset; + + return res; + } + + void dump(); + void json(bool trailing_comma); + void csv(bool format = false); + void xml(); + + Column* add_column(const char* name, Coltype::Type type, int id = -1, bool hidden = false); + Column* add_column(const char* name, const char* type, int id = -1, bool hidden = false); + void merge_sort(Ordering_terms& order); + void per_sort(Ordering_terms& order); + Row* create_row(); + void delete_row(Row* row); + void add_row(Row* row); + void limit(int limit, int offset = 0); + + std::vector<Column*> m_cols; + std::list<Row*> m_rows; + int m_curpos; + std::string m_name; + std::string m_qstring; + Allocator<Row>* m_row_allocator; + int m_rsize; + int m_dsize; + std::vector<int> m_text_column_offsets; +}; + +#define ROW_DUMMY_SIZE sizeof(void*) + +class Row { +public: + void zero_text_columns(const std::vector<int>& text_column_offsets) + { + for (auto i = text_column_offsets.begin(), end = text_column_offsets.end(); i != end; ++i) + access_column<text_column>(*i) = 0; + } + + void decref_text_columns(const std::vector<int>& text_column_offsets) + { + for (auto i = text_column_offsets.begin(), end = text_column_offsets.end(); i != end; ++i) { + text_column& t = access_column<text_column>(*i); + if (t) + t->dec_refcount(); + } + } + + void reset_text_columns(const std::vector<int>& text_column_offsets) + { + for (auto i = text_column_offsets.begin(), end = text_column_offsets.end(); i != end; ++i) { + text_column& t = access_column<text_column>(*i); + if (t) { + t->dec_refcount(); + t = 0; + } + } + } + + template <typename T> + T& access_column(int offset) + { + void* ptr = m_data + offset; + return *reinterpret_cast<T*>(ptr); + } + + char m_data[ROW_DUMMY_SIZE]; // dummy +}; + +template <typename T> +inline T& Accessor<T>::value(Row* row) +{ + return row->access_column<T>(m_offset); +} + +inline void GenericAccessor::set(Row* row, const Variant& v) +{ + switch (m_type) { + case Coltype::_bool: + row->access_column<bool_column>(m_offset) = v.get_bool(); + break; + + case Coltype::_int: + row->access_column<int_column>(m_offset) = v.get_int(); + break; + + case Coltype::_float: + row->access_column<float_column>(m_offset) = v.get_float(); + break; + + case Coltype::_text: + // reference count on string has already been incremented by get_text() + // so we can assign the pointer directly + row->access_column<text_column>(m_offset) = v.get_text(); + break; + } +} + +class Token { +public: + enum Type { + _invalid = 0, + _label = 1, + _number = 2, + _op = 3, + _uop = 4, + _string = 5, + _column = 6, + _paren = 7, + _function = 8, + _semicolon = 9, + _end = 10 + }; + + Token(const Type type, const char* token) + { + m_type = type; + m_token = token; + } + const char* get_token() const + { + return m_token.c_str(); + } + void set_token(const char* istr) + { + m_token = istr; + } + Type get_type() const + { + return m_type; + } + void set_type(const Type type) + { + m_type = type; + } + +private: + Type m_type; + std::string m_token; +}; + +class OP : public Token { +private: + OP& operator=(const OP& other); + OP(OP&& other) + noexcept; + OP const& operator=(OP&& other); + +public: + static int is_binary(const char* str) + { + const char* bin_ops[] = { "||", "*", "/", "%", "+", "-", "<<", ">>", "&", "|", "<", "<=", ">", ">=", "=", "==", "!=", "<>", "is", "is not", "in", "like", "not like", "or", "and" }; + int pre_ops[] = { 8, 7, 7, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 1 }; + int len = sizeof(bin_ops) / sizeof(const char*); + int idx = len - 1; + while (idx >= 0) { + if (cmpi(std::string(str), bin_ops[idx])) { + return pre_ops[idx]; + } + idx--; + } + return 0; + } + + OP(const OP& op) + : Token(op.get_type(), op.get_token()) + { + for (int i = 0; i < max_param(); i++) { + m_param[i] = op.m_param[i]; + } + m_left = op.m_left; + m_right = op.m_right; + m_row_index = op.m_row_index; + m_t = op.m_t; + m_name = op.m_name; + m_has_aggregate_function = op.m_has_aggregate_function; + + precedence(); + } + OP(const Token& tok) + : Token(tok.get_type(), tok.get_token()) + { + for (int i = 0; i < max_param(); i++) { + m_param[i] = 0; + } + m_left = m_right = 0; + m_row_index = -1; + m_t = Coltype::_int; + m_name = ""; + m_has_aggregate_function = false; + + precedence(); + } + virtual ~OP() + { + for (int i = 0; i < max_param(); i++) + if (m_param[i]) + delete m_param[i]; + if (m_left) + delete m_left; + if (m_right) + delete m_right; + } + static int max_param() + { + return max_func_param; + } + void clear_ptr() + { + for (int i = 0; i < max_param(); i++) { + m_param[i] = 0; + } + m_left = m_right = 0; + } + void precedence() + { + m_precedence = is_binary(get_token()); + } + const char* get_name() + { + if (m_name.length() > 0) + return m_name.c_str(); + + m_name = ""; + if (m_left) { + m_name += "("; + m_name += m_left->get_name(); + } + m_name += get_token(); + if (m_right) { + if (!m_left) + m_name += "("; + m_name += m_right->get_name(); + m_name += ")"; + } + if (m_param[0]) { + m_name += "("; + for (int i = 0; i < max_param(); i++) + if (m_param[i]) { + if (i > 0) + m_name += ","; + m_name += m_param[i]->get_name(); + } + m_name += ")"; + } + return m_name.c_str(); + } + Coltype::Type ret_type() { return m_t; } + + // add a hidden column for storing intermediate results + template <typename T> + T add_intermediate_column(Table* table, std::string name_suffix, Coltype::Type type) + { + std::string name = std::string(get_name()) + name_suffix; + Column* column = table->add_column(name.c_str(), type, -1, Column::HIDDEN); + T res; + res.m_offset = column->m_offset; + return res; + } + + virtual void evaluate(Row** rows, Variant& v) { throw Error("evaluate() called on abstract OP class"); }; + virtual void evaluate_aggregate_operands(Row** rows); + virtual void combine_aggregate(Row* base_row, Row* other_row); + OP* compile(const std::vector<Table*>& tables, + const std::vector<int>& search_order, Query& q); + int m_row_index; + std::string m_name; + int m_precedence; + OP* m_param[max_func_param]; + OP* m_left; + OP* m_right; + Coltype::Type m_t; + bool m_has_aggregate_function; +}; + +////////////////// column accessors + +class Column_access_int : public OP { +public: + Column_access_int(const OP& op, int offset) + : OP(op) + { + m_accessor.m_offset = offset; + } + void evaluate(Row** rows, Variant& v) + { + v = m_accessor.value(rows[m_row_index]); + } + Int_accessor m_accessor; +}; + +class Column_access_bool : public OP { +public: + Column_access_bool(const OP& op, int offset) + : OP(op) + { + m_accessor.m_offset = offset; + } + void evaluate(Row** rows, Variant& v) + { + v = m_accessor.value(rows[m_row_index]); + } + Bool_accessor m_accessor; +}; + +class Column_access_float : public OP { +public: + Column_access_float(const OP& op, int offset) + : OP(op) + { + m_accessor.m_offset = offset; + } + void evaluate(Row** rows, Variant& v) + { + v = m_accessor.value(rows[m_row_index]); + } + Float_accessor m_accessor; +}; + +class Column_access_text : public OP { +public: + Column_access_text(const OP& op, int offset) + : OP(op) + { + m_accessor.m_offset = offset; + } + void evaluate(Row** rows, Variant& v) + { + v = m_accessor.value(rows[m_row_index]); + } + Text_accessor m_accessor; +}; + +///////////////// Static numbers + +class Static_int : public OP { +public: + Static_int(const OP& op) + : OP(op) + { + m_val = atoi(get_token()); + } + void evaluate(Row** rows, Variant& v) + { + v = m_val; + } + int m_val; +}; + +class Static_float : public OP { +public: + Static_float(const OP& op) + : OP(op) + { + m_val = atof(get_token()); + } + void evaluate(Row** rows, Variant& v) + { + v = m_val; + } + double m_val; +}; + +class Static_text : public OP { +public: + Static_text(const OP& op) + : OP(op) + { + m_val.set(RefCountString::construct(get_token())); + } + void evaluate(Row** rows, Variant& v) + { + v = *m_val; + } + RefCountStringHandle m_val; +}; + +///////////////// Functions + +class Netmask_func : public OP { +public: + Netmask_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant orig_ip; + m_param[0]->evaluate(rows, orig_ip); + + if (!valid_masks) + set_masks(rows); + + RefCountStringHandle src(orig_ip.get_text()); + RefCountStringHandle dest(RefCountString::allocate(INET6_ADDRSTRLEN + 1)); + + if (strchr((*src)->data, ':')) { + struct in6_addr a6; + if (inet_pton(AF_INET6, (*src)->data, &a6) == 1) { + a6.s6_addr32[0] &= v6_mask[0]; + a6.s6_addr32[1] &= v6_mask[1]; + a6.s6_addr32[2] &= v6_mask[2]; + a6.s6_addr32[3] &= v6_mask[3]; + if (inet_ntop(AF_INET6, &a6, (*dest)->data, INET6_ADDRSTRLEN)) { + v = *dest; + return; + } + } + } else { + struct in_addr a4; + if (inet_pton(AF_INET, (*src)->data, &a4) == 1) { + a4.s_addr &= v4_mask; + if (inet_ntop(AF_INET, &a4, (*dest)->data, INET6_ADDRSTRLEN)) { + v = *dest; + return; + } + } + } + + // Operation on non-IP address text + RefCountStringHandle empty(RefCountString::construct("")); + v = *empty; + } + +private: + void set_masks(Row** rows) + { + if (m_param[1]) { + Variant v4cidr; + m_param[1]->evaluate(rows, v4cidr); + int v4size = v4cidr.get_int(); + if (v4size > -1 && v4size < 33) { + v4_mask = htonl(0xffffffff << (32 - v4size)); + } + } + if (m_param[2]) { + Variant v6cidr; + m_param[2]->evaluate(rows, v6cidr); + int v6size = v6cidr.get_int(); + if (v6size > -1 && v6size < 129) { + for (int i = 0; i < 4; i++) { + if (v6size >= 32) { + v6_mask[i] = 0xffffffff; + v6size -= 32; + } else if (v6size) { + v6_mask[i] = htonl(0xffffffff << (32 - v6size)); + v6size = 0; + } else { + v6_mask[i] = 0; + } + } + } + } + valid_masks = true; + } + + uint32_t v4_mask = htonl(0xffffff00); + uint32_t v6_mask[4] = { 0xffffffff, htonl(0xffff0000), 0, 0 }; + bool valid_masks = false; +}; + +class Cc_func : public OP { +public: + Cc_func(const OP& op); + ~Cc_func() { } + void evaluate(Row** rows, Variant& v); +}; + +class Asn_func : public OP { +public: + Asn_func(const OP& op); + ~Asn_func() { } + void evaluate(Row** rows, Variant& v); +}; + +class Truncate_func : public OP { +public: + Truncate_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant val; + m_param[0]->evaluate(rows, val); + v = val.get_int(); + } +}; + +class Name_func : public OP { +public: + Name_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant str, num; + m_param[0]->evaluate(rows, str); + m_param[1]->evaluate(rows, num); + + int_column n = num.get_int(); + RefCountStringHandle lookup(str.get_text()); + RefCountStringHandle r(g_db.get_value((*lookup)->data, n)); + + if (!*r) + r.set(num.get_text()); + + v = *r; + } +}; + +class Lower_func : public OP { +public: + Lower_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant str; + m_param[0]->evaluate(rows, str); + RefCountStringHandle src(str.get_text()); + + int l = strlen((*src)->data); + int p = 0; + + RefCountStringHandle dest(RefCountString::allocate(l + 1)); + + while ((*src)->data[p]) { + char c = (*src)->data[p]; + if (c >= 'A' && c <= 'Z') { + c = c - 'A' + 'a'; + } + (*dest)->data[p] = c; + p++; + } + (*dest)->data[p] = 0; + + v = *dest; + } +}; + +class Rsplit_func : public OP { +public: + Rsplit_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + char sep = '.'; + Variant str, num; + m_param[0]->evaluate(rows, str); + m_param[1]->evaluate(rows, num); + + if (m_param[2]) { + Variant vsep; + m_param[2]->evaluate(rows, vsep); + RefCountStringHandle sep_text(vsep.get_text()); + const char* s = (*sep_text)->data; + if (s) + sep = s[0]; + } + + int n = num.get_int(); + RefCountStringHandle src(str.get_text()); + const char* s = (*src)->data; + int l = strlen(s); + if (!l) { + RefCountStringHandle res(RefCountString::construct("")); + v = *res; + return; + } + int p = l - 1; + int found = 0, end = l, start = 0; + if (n == 0) + end = p + 1; + while (p >= 0) { + char c = s[p]; + if (c == sep) { + found++; + if (found == n) + end = p; + if (found == n + 1) + start = p + 1; + } + p--; + } + if (found < n || start >= l) { + RefCountStringHandle res(RefCountString::construct("")); + v = *res; + return; + } + size_t buflen = start < end ? end - start + 1 : 1; + char buf[buflen]; + p = 0; + while (start < end) + buf[p++] = s[start++]; + buf[p] = 0; + + RefCountStringHandle res(RefCountString::construct(buf)); + v = *res; + } +}; + +class Len_func : public OP { +public: + Len_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant str; + m_param[0]->evaluate(rows, str); + RefCountStringHandle t(str.get_text()); + v = int(strlen((*t)->data)); + } +}; + +class Trim_func : public OP { +public: + Trim_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v); +}; + +class If_func : public OP { +public: + If_func(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant cond; + m_param[0]->evaluate(rows, cond); + if (cond.get_bool()) + m_param[1]->evaluate(rows, v); + else + m_param[2]->evaluate(rows, v); + } +}; + +// Aggregate functions, generally these store their calculations in hidden +// columns + +class Min_func_int : public OP { +public: + Min_func_int(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_min = add_intermediate_column<Int_accessor>(dest_table, ".min", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_min.value(rows[m_row_index]) = p.get_int(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + int_column n = acc_min.value(next_row); + if (n < acc_min.value(base_row)) + acc_min.value(base_row) = n; + } + void evaluate(Row** rows, Variant& v) + { + v = acc_min.value(rows[m_row_index]); + } + + Int_accessor acc_min; +}; + +class Min_func_float : public OP { +public: + Min_func_float(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_min = add_intermediate_column<Float_accessor>(dest_table, ".min", Coltype::_float); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_min.value(rows[m_row_index]) = p.get_float(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + float_column n = acc_min.value(next_row); + if (n < acc_min.value(base_row)) + acc_min.value(base_row) = n; + } + void evaluate(Row** rows, Variant& v) + { + v = acc_min.value(rows[m_row_index]); + } + + Float_accessor acc_min; +}; + +class Max_func_int : public OP { +public: + Max_func_int(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_max = add_intermediate_column<Int_accessor>(dest_table, ".max", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_max.value(rows[m_row_index]) = p.get_int(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + int_column n = acc_max.value(next_row); + if (n > acc_max.value(base_row)) + acc_max.value(base_row) = n; + } + void evaluate(Row** rows, Variant& v) + { + v = acc_max.value(rows[m_row_index]); + } + + Int_accessor acc_max; +}; + +class Max_func_float : public OP { +public: + Max_func_float(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_max = add_intermediate_column<Float_accessor>(dest_table, ".max", Coltype::_float); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_max.value(rows[m_row_index]) = p.get_float(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + float_column n = acc_max.value(next_row); + if (n > acc_max.value(base_row)) + acc_max.value(base_row) = n; + } + void evaluate(Row** rows, Variant& v) + { + v = acc_max.value(rows[m_row_index]); + } + + Float_accessor acc_max; +}; + +class Stdev_func : public OP { +public: + Stdev_func(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_sum = add_intermediate_column<Float_accessor>(dest_table, ".sum", Coltype::_float); + acc_sum_sq = add_intermediate_column<Float_accessor>(dest_table, ".sumsquared", Coltype::_float); + acc_count = add_intermediate_column<Int_accessor>(dest_table, ".count", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + float_column val = p.get_float(); + + acc_sum.value(rows[m_row_index]) = val; + acc_sum_sq.value(rows[m_row_index]) = val * val; + acc_count.value(rows[m_row_index]) = 1; + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + acc_sum.value(base_row) = acc_sum.value(base_row) + acc_sum.value(next_row); + acc_sum_sq.value(base_row) = acc_sum_sq.value(base_row) + acc_sum_sq.value(next_row); + acc_count.value(base_row) = acc_count.value(base_row) + acc_count.value(next_row); + } + void evaluate(Row** rows, Variant& v) + { + Row* row = rows[m_row_index]; + int c = acc_count.value(row); + if (c == 0) { + c = 1; + } + double mean = acc_sum.value(row) / c; + double variance = acc_sum_sq.value(row) / c - mean * mean; + + v = sqrt(variance); + } + + Float_accessor acc_sum, acc_sum_sq; + Int_accessor acc_count; +}; + +class Avg_func : public OP { +public: + Avg_func(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_sum = add_intermediate_column<Float_accessor>(dest_table, ".sum", Coltype::_float); + acc_count = add_intermediate_column<Int_accessor>(dest_table, ".count", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_sum.value(rows[m_row_index]) = p.get_float(); + acc_count.value(rows[m_row_index]) = 1; + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + acc_sum.value(base_row) = acc_sum.value(base_row) + acc_sum.value(next_row); + acc_count.value(base_row) = acc_count.value(base_row) + acc_count.value(next_row); + } + void evaluate(Row** rows, Variant& v) + { + v = acc_sum.value(rows[m_row_index]) / acc_count.value(rows[m_row_index]); + } + + Float_accessor acc_sum; + Int_accessor acc_count; +}; + +class Sum_func_int : public OP { +public: + Sum_func_int(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_sum = add_intermediate_column<Int_accessor>(dest_table, ".sum", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_sum.value(rows[m_row_index]) = p.get_int(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + acc_sum.value(base_row) = acc_sum.value(base_row) + acc_sum.value(next_row); + } + void evaluate(Row** rows, Variant& v) + { + v = acc_sum.value(rows[m_row_index]); + } + + Int_accessor acc_sum; +}; + +class Sum_func_float : public OP { +public: + Sum_func_float(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_sum = add_intermediate_column<Float_accessor>(dest_table, ".sum", Coltype::_float); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + Variant p; + m_param[0]->evaluate(rows, p); + acc_sum.value(rows[m_row_index]) = p.get_float(); + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + acc_sum.value(base_row) = acc_sum.value(base_row) + acc_sum.value(next_row); + } + void evaluate(Row** rows, Variant& v) + { + v = acc_sum.value(rows[m_row_index]); + } + + Float_accessor acc_sum; +}; + +class Count_func : public OP { +public: + Count_func(const OP& op, Table* dest_table) + : OP(op) + { + m_has_aggregate_function = true; + acc_count = add_intermediate_column<Int_accessor>(dest_table, ".count", Coltype::_int); + } + virtual void evaluate_aggregate_operands(Row** rows) + { + acc_count.value(rows[m_row_index]) = 1; + } + virtual void combine_aggregate(Row* base_row, Row* next_row) + { + acc_count.value(base_row) = acc_count.value(base_row) + acc_count.value(next_row); + } + void evaluate(Row** rows, Variant& v) + { + v = acc_count.value(rows[m_row_index]); + } + + Int_accessor acc_count; +}; + +//////////////// Binary ops + +class Bin_op_eq : public OP { +public: + Bin_op_eq(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = bool(lhs == rhs); + } +}; +class Bin_op_not_eq : public OP { +public: + Bin_op_not_eq(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = !bool(lhs == rhs); + } +}; +class Bin_op_or : public OP { +public: + Bin_op_or(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + m_left->evaluate(rows, v); + if (v.get_bool()) { + v = true; + return; + } + m_right->evaluate(rows, v); + v = v.get_bool(); + } +}; + +class Bin_op_and : public OP { +public: + Bin_op_and(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + m_left->evaluate(rows, v); + if (!v.get_bool()) { + v = false; + return; + } + m_right->evaluate(rows, v); + v = v.get_bool(); + } +}; +class Bin_op_lt : public OP { +public: + Bin_op_lt(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = bool(lhs < rhs); + } +}; +class Bin_op_gt : public OP { +public: + Bin_op_gt(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = bool(rhs < lhs); + } +}; +class Bin_op_lteq : public OP { +public: + Bin_op_lteq(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = !bool(rhs < lhs); + } +}; +class Bin_op_gteq : public OP { +public: + Bin_op_gteq(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = !bool(lhs < rhs); + } +}; +class Bin_op_add : public OP { +public: + Bin_op_add(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() + rhs.get_int(); + } +}; +class Bin_op_add_float : public OP { +public: + Bin_op_add_float(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_float() + rhs.get_float(); + } +}; +class Bin_op_sub : public OP { +public: + Bin_op_sub(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() - rhs.get_int(); + } +}; +class Bin_op_sub_float : public OP { +public: + Bin_op_sub_float(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_float() - rhs.get_float(); + } +}; + +class Bin_op_mul : public OP { +public: + Bin_op_mul(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() * rhs.get_int(); + } +}; +class Bin_op_mul_float : public OP { +public: + Bin_op_mul_float(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_float() * rhs.get_float(); + } +}; +class Bin_op_div : public OP { +public: + Bin_op_div(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_float() / rhs.get_float(); + } +}; +class Bin_op_modulo : public OP { +public: + Bin_op_modulo(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = fmod(lhs.get_float(), rhs.get_float()); + } +}; +class Bin_op_arithmetic_shift_left : public OP { +public: + Bin_op_arithmetic_shift_left(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() << rhs.get_int(); + } +}; +class Bin_op_arithmetic_shift_right : public OP { +public: + Bin_op_arithmetic_shift_right(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() >> rhs.get_int(); + } +}; +class Bin_op_bitwise_and : public OP { +public: + Bin_op_bitwise_and(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() & rhs.get_int(); + } +}; +class Bin_op_bitwise_or : public OP { +public: + Bin_op_bitwise_or(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + v = lhs.get_int() | rhs.get_int(); + } +}; +class Bin_op_concatenate : public OP { +public: + Bin_op_concatenate(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + RefCountStringHandle lhandle(lhs.get_text()), rhandle(rhs.get_text()); + + const char* lhs_str = (*lhandle)->data; + const char* rhs_str = (*rhandle)->data; + + int l = (int)strlen(lhs_str); + int r = (int)strlen(rhs_str); + + RefCountStringHandle res(RefCountString::allocate(l + r + 1)); + memcpy((*res)->data, lhs_str, l); + memcpy((*res)->data + l, rhs_str, r + 1); // copy the zero terminator + + v = *res; + } +}; +class Bin_op_like : public OP { +private: + Bin_op_like& operator=(const Bin_op_like& other); + Bin_op_like(Bin_op_like&& other) noexcept; + Bin_op_like const& operator=(Bin_op_like&& other); + + regex_t m_re; + char m_re_str[RE_LEN]; + bool m_compiled; + int m_err; + +public: + Bin_op_like(const OP& op) + : OP(op) + , m_re() + { + m_err = 0; + m_compiled = false; + } + void regex_from_like(const char* s, char* r, int l) + { + char* stop = r + l - 4; + if (r < stop) { + *r++ = '^'; + while (r < stop and *s) { + // printf("s: %s\n", s); + if (*s == '\\') { + s++; + if (*s) { + *r = *s; + } else { + s--; + } + } else if (*s == '.') { + *r++ = '\\'; + *r = '.'; + } else if (*s == '*') { + *r++ = '\\'; + *r = '*'; + } else if (*s == '%') { + *r++ = '.'; + *r = '*'; + } else if (*s == '_') { + *r = '.'; + } else { + *r = *s; + } + s++; + r++; + // printf("r: %s\n\n", start); + } + *r++ = '$'; + *r = '\0'; + } + // printf("r: %s\n\n", start); + // printf("Done\n\n"); + } + void evaluate(Row** rows, Variant& v) + { + Variant lhs, rhs; + m_left->evaluate(rows, lhs); + m_right->evaluate(rows, rhs); + RefCountStringHandle lhandle(lhs.get_text()), rhandle(rhs.get_text()); + const char* lstr = (*lhandle)->data; + const char* rstr = (*rhandle)->data; + if (!m_compiled) { + m_compiled = true; // Set this before we try; no need to try again if we fail + regex_from_like(rstr, m_re_str, RE_LEN); + m_err = regcomp(&m_re, m_re_str, REG_NOSUB); + if (m_err) { + char errstr[RE_LEN]; + regerror(m_err, &m_re, errstr, RE_LEN); + printf("Error compiling regex: %d: %s", m_err, errstr); + } + } + if (m_err) + v = false; + else + v = regexec(&m_re, lstr, 0, 0, 0) == 0; + } + ~Bin_op_like() + { + if (m_compiled) { + regfree(&m_re); + } + } +}; +class Bin_op_not_like : public Bin_op_like { +public: + Bin_op_not_like(const OP& op) + : Bin_op_like(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Bin_op_like::evaluate(rows, v); + v = !v.get_bool(); + } +}; +////////////////// unary ops + +class Un_op_not : public OP { +public: + Un_op_not(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant rhs; + m_right->evaluate(rows, rhs); + v = !rhs.get_bool(); + } +}; + +class Un_op_neg : public OP { +public: + Un_op_neg(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant rhs; + m_right->evaluate(rows, rhs); + v = -rhs.get_int(); + } +}; + +class Un_op_neg_float : public OP { +public: + Un_op_neg_float(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant rhs; + m_right->evaluate(rows, rhs); + v = -rhs.get_float(); + } +}; + +class Un_op_ones_complement : public OP { +public: + Un_op_ones_complement(const OP& op) + : OP(op) + { + } + void evaluate(Row** rows, Variant& v) + { + Variant rhs; + m_right->evaluate(rows, rhs); + v = ~rhs.get_int(); + } +}; + +class Ordering_terms { +private: + Ordering_terms& operator=(const Ordering_terms& other); + Ordering_terms(Ordering_terms&& other) noexcept; + Ordering_terms const& operator=(Ordering_terms&& other); + +public: + Ordering_terms() + { + m_terms.clear(); + } + ~Ordering_terms() + { + auto it = m_terms.begin(); + while (it != m_terms.end()) { + delete it->m_op; + it->m_op = 0; + it++; + } + } + class OP_dir { + public: + OP_dir(OP* op, bool asc) + { + m_op = op; + m_asc = asc; + } + OP* m_op; + bool m_asc; + }; + bool exist() + { + return !m_terms.empty(); + } + void compile(const std::vector<Table*>& tables, const std::vector<int>& search_order, Query& q); + + std::vector<OP_dir> m_terms; +}; + +class Reader; + +class Query { +private: + Query& operator=(const Query& other); + Query(Query&& other) noexcept; + Query const& operator=(Query&& other); + +public: + Query(const char* name, const char* query) + { + m_sample = 0; + m_where = 0; + m_having = 0; + m_from = 0; + m_limit = -1; + m_offset = 0; + m_result = new Table(name, query); + m_sql = query; + } + + ~Query() + { + if (m_from) + delete m_from; + if (m_result) + delete m_result; + if (m_where) + delete m_where; + if (m_having) + delete m_having; + for (auto i = m_select.begin(); i != m_select.end(); ++i) + delete *i; + } + + void parse(); + void execute(Reader& reader); + + std::vector<OP*> m_select; + OP* m_where; + OP* m_having; + Ordering_terms m_order_by; + Ordering_terms m_group_by; + + int m_limit; + int m_offset; + int m_sample; + + std::string m_from_name; + std::vector<int> m_used_from_column_ids; + + Table* m_from; + Table* m_result; + +private: + void replace_star_column_with_all_columns(); + + void process_from(); + void process_select(Row** rows, Row* dest, GenericAccessor dest_accessors[]); + void combine_aggregates_in_select(Row* base_row, Row* other_row); + void process_aggregates_in_select(Row** rows, Row* dest, GenericAccessor dest_accessors[]); + bool process_where(Row** rows); + bool process_having(Row** rows); + bool has_aggregate_functions(); + + std::string m_sql; +}; + +} // namespace packetq + +namespace std { + +// support for hashing std::vector<packetq::Variant> +template <> +struct hash<std::vector<packetq::Variant>> { + size_t operator()(const std::vector<packetq::Variant>& seq) const + { + // combination procedure from boost::hash_combine + std::size_t accumulator = 0; + for (auto i = seq.begin(), end = seq.end(); i != end; ++i) + accumulator ^= i->hash() + 0x9e3779b9 + (accumulator << 6) + (accumulator >> 2); + return accumulator; + } +}; + +} // namespace std + +#endif // __packetq_sql_h diff --git a/src/tcp.cpp b/src/tcp.cpp new file mode 100644 index 0000000..5787e84 --- /dev/null +++ b/src/tcp.cpp @@ -0,0 +1,268 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "tcp.h" +#include "packet_handler.h" + +#include <cstring> +#include <list> +#include <map> +#include <stdlib.h> + +namespace packetq { + +/// TCP Stream id class - serves as the key in the streams map +class Stream_id { +public: + /// constructor + Stream_id(in6addr_t& src_ip, + in6addr_t& dst_ip, + unsigned short src_port, + unsigned short dst_port) + { + m_src_ip = src_ip; + m_dst_ip = dst_ip; + m_src_port = src_port; + m_dst_port = dst_port; + } + + /// < comparison operator for the std::map + bool operator<(const Stream_id& rhs) const + { + return memcmp(this, &rhs, sizeof(*this)) < 0; + } + +private: + in6addr_t m_src_ip, m_dst_ip; + unsigned short m_src_port, m_dst_port; +}; + +/// TCP data segment container +/** Data_segment contains the data found in a single tcp packet + * Data_segment are inerted into a list in the Stream class + */ +class Data_segment { +private: + Data_segment& operator=(const Data_segment& other); + Data_segment(Data_segment&& other) noexcept; + Data_segment const& operator=(Data_segment&& other); + +public: + /// Constructor taking a memory block with packet content + Data_segment(unsigned char* data, unsigned int len) + { + m_datasize = len; + m_data = new unsigned char[m_datasize]; + for (unsigned int i = 0; i < m_datasize; i++) { + m_data[i] = data[i]; + } + } + Data_segment(const Data_segment& other) + { + m_datasize = other.m_datasize; + m_data = new unsigned char[m_datasize]; + for (unsigned int i = 0; i < m_datasize; i++) { + m_data[i] = other.m_data[i]; + } + } + /// Destructor + ~Data_segment() + { + delete[] m_data; + } + + /// size of the data + unsigned int m_datasize; + /// pointer to the data + unsigned char* m_data; +}; + +int g_count = 0; + +/// TCP Stream class +/** The Stream class has an Stream_id and a list of Data_segemnts that make up + * a tcp data stream. + * The Streams are organized into a global map ( g_tcp_streams ) indexed by a Stream_id + */ +class Stream { +public: + /// Constructor + Stream() + { + m_ser = g_count++; + m_content = false; + m_nseq = false; + m_seq = 0; + } + ~Stream() + { + m_segments.clear(); + } + /// add a datasegment to the stream + /** If the segment has the expected sequence number + * the segment will be added to the list + */ + void add(bool syn, unsigned int seq, Data_segment& s) + { + m_content = true; + if (!m_segments.size() || syn) + m_seq = seq; + + if (m_seq == seq) { + m_content = true; + if ((s.m_datasize > 0 && s.m_datasize <= 65535)) { + m_segments.push_back(s); + m_seq = seq + s.m_datasize; + } + } + } + /// checka if there's any content in the stream + bool has_content() + { + return m_content; + } + /// Erase (and free) all segments and reset state + void erase() + { + m_content = false; + m_nseq = false; + m_segments.clear(); + } + /// return the streams data size + int get_size() + { + int size = 0; + for (auto it = m_segments.begin(); + it != m_segments.end(); it++) { + size += it->m_datasize; + } + return size; + } + /// debug functionality to dump a streams content + void dump() + { + int start = 2; + for (auto it = m_segments.begin(); + it != m_segments.end(); it++) { + for (unsigned int i = start; i < it->m_datasize; i++) { + printf("%02x", it->m_data[i]); + } + start = 0; + } + printf("\n"); + } + /// returns the data in the stream + /** The returned data is located in a static buffer shared by all streams + * the data is valid until the next call to get_buffer() + */ + unsigned char* get_buffer() + { + int p = 0; + for (auto it = m_segments.begin(); + it != m_segments.end(); it++) { + for (unsigned int i = 0; i < it->m_datasize; i++) { + m_buffer[p++] = it->m_data[i]; + if (p >= 0xffff) + return m_buffer; + } + } + return m_buffer; + } + +private: + unsigned int m_seq; + int m_ser; + bool m_content; + bool m_nseq; + std::list<Data_segment> m_segments; + + static unsigned char m_buffer[0x10000]; +}; +unsigned char Stream::m_buffer[0x10000]; + +std::map<Stream_id, Stream> g_tcp_streams; + +/// assemble_tcp builds datastreams out of tcp packets +/** TCP packets are inserted into streams. When the streams are closed + * the contained data is returned as a pointer the data + * it is up to the caller to free() the memory returned. + */ +unsigned char* +assemble_tcp( + Payload& payload, + in6addr_t* src_ip, + in6addr_t* dst_ip, + unsigned short src_port, + unsigned short dst_port, + unsigned int* rest, + unsigned int seq, + unsigned char* data, + int len, + char syn, + char fin, + char rst, + char ack) +{ + Stream_id id(*src_ip, *dst_ip, src_port, dst_port); + Stream& str = g_tcp_streams[id]; + bool data_avail = false; + + if (!str.has_content()) { + Data_segment seg(data, len); + str.add(syn, seq, seg); + } else { + if (rst == 1) { + str.erase(); + } else if (syn == 1) { + str.erase(); + Data_segment seg(data, len); + str.add(syn, seq, seg); + } else { + Data_segment seg(data, len); + str.add(syn, seq, seg); + } + } + + data = 0; + if (str.has_content()) { + int size = str.get_size(); + if (size < 2) { + // need at least dnslen + return 0; + } + unsigned char* buffer = str.get_buffer(); + int dns_size = (int(buffer[0]) << 8) | buffer[1]; + + data_avail = (fin == 1) && (rst == 0); + if (data_avail || dns_size + 2 == size) { + *rest = size; + if (*rest > 0xffff) + *rest = 0xffff; + data = (unsigned char*)payload.alloc(*rest); + memcpy(data, buffer, *rest); + str.erase(); + g_tcp_streams.erase(id); + } + } + return data; +} + +} // namespace packetq diff --git a/src/tcp.h b/src/tcp.h new file mode 100644 index 0000000..48a2a2d --- /dev/null +++ b/src/tcp.h @@ -0,0 +1,62 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_tcp_h +#define __packetq_tcp_h + +#include <stdio.h> +#include <stdint.h> + +namespace packetq { + +struct _in6_addr { + union { + uint8_t __u6_addr8[16]; + uint16_t __u6_addr16[8]; + uint32_t __u6_addr32[4]; + } __in6_u; /* 128-bit IP6 address */ +}; + +typedef struct _in6_addr in6addr_t; + +class Payload; + +/** Assembles tcp packets into streams and returns data + when 'fin' has been recieved + */ +unsigned char* assemble_tcp( + Payload& payload, + in6addr_t* src_ip, + in6addr_t* dst_ip, + unsigned short src_port, + unsigned short dst_port, + unsigned int* rest, + unsigned int seq, + unsigned char* data, + int len, + char syn, + char fin, + char rst, + char ack); + +} // namespace packetq + +#endif // __packetq_tcp_h diff --git a/src/test/Makefile.am b/src/test/Makefile.am new file mode 100644 index 0000000..eb40c2c --- /dev/null +++ b/src/test/Makefile.am @@ -0,0 +1,32 @@ +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +CLEANFILES = test*.log test*.trs \ + test1.out test2.out test3.out test4.out test5.out test6.out test7.out \ + test8.out + +TESTS = test1.sh test2.sh test3.sh test4.sh test5.sh test6.sh test7.sh \ + test8.sh + +EXTRA_DIST = $(TESTS) \ + test1.gold test2.gold test3.gold test4.gold test5.gold test6.gold \ + test7.gold sql.txt test8.gold \ + dns.pcap dns6.pcap diff --git a/src/test/Makefile.in b/src/test/Makefile.in new file mode 100644 index 0000000..d4f26b2 --- /dev/null +++ b/src/test/Makefile.in @@ -0,0 +1,885 @@ +# Makefile.in generated by automake 1.16.5 from Makefile.am. +# @configure_input@ + +# 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, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ + +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. +VPATH = @srcdir@ +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} +am__make_running_with_option = \ + case $${target_option-} in \ + ?) ;; \ + *) echo "am__make_running_with_option: internal error: invalid" \ + "target option '$${target_option-}' specified" >&2; \ + exit 1;; \ + esac; \ + has_opt=no; \ + sane_makeflags=$$MAKEFLAGS; \ + if $(am__is_gnu_make); then \ + sane_makeflags=$$MFLAGS; \ + else \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + bs=\\; \ + sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \ + | sed "s/$$bs$$bs[$$bs $$bs ]*//g"`;; \ + esac; \ + fi; \ + skip_next=no; \ + strip_trailopt () \ + { \ + flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \ + }; \ + for flg in $$sane_makeflags; do \ + test $$skip_next = yes && { skip_next=no; continue; }; \ + case $$flg in \ + *=*|--*) continue;; \ + -*I) strip_trailopt 'I'; skip_next=yes;; \ + -*I?*) strip_trailopt 'I';; \ + -*O) strip_trailopt 'O'; skip_next=yes;; \ + -*O?*) strip_trailopt 'O';; \ + -*l) strip_trailopt 'l'; skip_next=yes;; \ + -*l?*) strip_trailopt 'l';; \ + -[dEDm]) skip_next=yes;; \ + -[JT]) skip_next=yes;; \ + esac; \ + case $$flg in \ + *$$target_option*) has_opt=yes; break;; \ + esac; \ + done; \ + test $$has_opt = yes +am__make_dryrun = (target_option=n; $(am__make_running_with_option)) +am__make_keepgoing = (target_option=k; $(am__make_running_with_option)) +pkgdatadir = $(datadir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkglibexecdir = $(libexecdir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +build_triplet = @build@ +host_triplet = @host@ +subdir = src/test +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/m4/ax_cflags_warn_all.m4 \ + $(top_srcdir)/m4/ax_compiler_vendor.m4 \ + $(top_srcdir)/m4/ax_prepend_flag.m4 \ + $(top_srcdir)/m4/ax_require_defined.m4 \ + $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) +mkinstalldirs = $(install_sh) -d +CONFIG_HEADER = $(top_builddir)/src/config.h +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +AM_V_P = $(am__v_P_@AM_V@) +am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) +am__v_P_0 = false +am__v_P_1 = : +AM_V_GEN = $(am__v_GEN_@AM_V@) +am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@) +am__v_GEN_0 = @echo " GEN " $@; +am__v_GEN_1 = +AM_V_at = $(am__v_at_@AM_V@) +am__v_at_ = $(am__v_at_@AM_DEFAULT_V@) +am__v_at_0 = @ +am__v_at_1 = +SOURCES = +DIST_SOURCES = +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac +am__extra_recursive_targets = gcov-recursive +am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +am__tty_colors_dummy = \ + mgn= red= grn= lgn= blu= brg= std=; \ + am__color_tests=no +am__tty_colors = { \ + $(am__tty_colors_dummy); \ + if test "X$(AM_COLOR_TESTS)" = Xno; then \ + am__color_tests=no; \ + elif test "X$(AM_COLOR_TESTS)" = Xalways; then \ + am__color_tests=yes; \ + elif test "X$$TERM" != Xdumb && { test -t 1; } 2>/dev/null; then \ + am__color_tests=yes; \ + fi; \ + if test $$am__color_tests = yes; then \ + red='[0;31m'; \ + grn='[0;32m'; \ + lgn='[1;32m'; \ + blu='[1;34m'; \ + mgn='[0;35m'; \ + brg='[1m'; \ + std='[m'; \ + fi; \ +} +am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; +am__vpath_adj = case $$p in \ + $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \ + *) f=$$p;; \ + esac; +am__strip_dir = f=`echo $$p | sed -e 's|^.*/||'`; +am__install_max = 40 +am__nobase_strip_setup = \ + srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*|]/\\\\&/g'` +am__nobase_strip = \ + for p in $$list; do echo "$$p"; done | sed -e "s|$$srcdirstrip/||" +am__nobase_list = $(am__nobase_strip_setup); \ + for p in $$list; do echo "$$p $$p"; done | \ + sed "s| $$srcdirstrip/| |;"' / .*\//!s/ .*/ ./; s,\( .*\)/[^/]*$$,\1,' | \ + $(AWK) 'BEGIN { files["."] = "" } { files[$$2] = files[$$2] " " $$1; \ + if (++n[$$2] == $(am__install_max)) \ + { print $$2, files[$$2]; n[$$2] = 0; files[$$2] = "" } } \ + END { for (dir in files) print dir, files[dir] }' +am__base_list = \ + sed '$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;s/\n/ /g' | \ + sed '$$!N;$$!N;$$!N;$$!N;s/\n/ /g' +am__uninstall_files_from_dir = { \ + test -z "$$files" \ + || { test ! -d "$$dir" && test ! -f "$$dir" && test ! -r "$$dir"; } \ + || { echo " ( cd '$$dir' && rm -f" $$files ")"; \ + $(am__cd) "$$dir" && rm -f $$files; }; \ + } +am__recheck_rx = ^[ ]*:recheck:[ ]* +am__global_test_result_rx = ^[ ]*:global-test-result:[ ]* +am__copy_in_global_log_rx = ^[ ]*:copy-in-global-log:[ ]* +# A command that, given a newline-separated list of test names on the +# standard input, print the name of the tests that are to be re-run +# upon "make recheck". +am__list_recheck_tests = $(AWK) '{ \ + recheck = 1; \ + while ((rc = (getline line < ($$0 ".trs"))) != 0) \ + { \ + if (rc < 0) \ + { \ + if ((getline line2 < ($$0 ".log")) < 0) \ + recheck = 0; \ + break; \ + } \ + else if (line ~ /$(am__recheck_rx)[nN][Oo]/) \ + { \ + recheck = 0; \ + break; \ + } \ + else if (line ~ /$(am__recheck_rx)[yY][eE][sS]/) \ + { \ + break; \ + } \ + }; \ + if (recheck) \ + print $$0; \ + close ($$0 ".trs"); \ + close ($$0 ".log"); \ +}' +# A command that, given a newline-separated list of test names on the +# standard input, create the global log from their .trs and .log files. +am__create_global_log = $(AWK) ' \ +function fatal(msg) \ +{ \ + print "fatal: making $@: " msg | "cat >&2"; \ + exit 1; \ +} \ +function rst_section(header) \ +{ \ + print header; \ + len = length(header); \ + for (i = 1; i <= len; i = i + 1) \ + printf "="; \ + printf "\n\n"; \ +} \ +{ \ + copy_in_global_log = 1; \ + global_test_result = "RUN"; \ + while ((rc = (getline line < ($$0 ".trs"))) != 0) \ + { \ + if (rc < 0) \ + fatal("failed to read from " $$0 ".trs"); \ + if (line ~ /$(am__global_test_result_rx)/) \ + { \ + sub("$(am__global_test_result_rx)", "", line); \ + sub("[ ]*$$", "", line); \ + global_test_result = line; \ + } \ + else if (line ~ /$(am__copy_in_global_log_rx)[nN][oO]/) \ + copy_in_global_log = 0; \ + }; \ + if (copy_in_global_log) \ + { \ + rst_section(global_test_result ": " $$0); \ + while ((rc = (getline line < ($$0 ".log"))) != 0) \ + { \ + if (rc < 0) \ + fatal("failed to read from " $$0 ".log"); \ + print line; \ + }; \ + printf "\n"; \ + }; \ + close ($$0 ".trs"); \ + close ($$0 ".log"); \ +}' +# Restructured Text title. +am__rst_title = { sed 's/.*/ & /;h;s/./=/g;p;x;s/ *$$//;p;g' && echo; } +# Solaris 10 'make', and several other traditional 'make' implementations, +# pass "-e" to $(SHELL), and POSIX 2008 even requires this. Work around it +# by disabling -e (using the XSI extension "set +e") if it's set. +am__sh_e_setup = case $$- in *e*) set +e;; esac +# Default flags passed to test drivers. +am__common_driver_flags = \ + --color-tests "$$am__color_tests" \ + --enable-hard-errors "$$am__enable_hard_errors" \ + --expect-failure "$$am__expect_failure" +# To be inserted before the command running the test. Creates the +# directory for the log if needed. Stores in $dir the directory +# containing $f, in $tst the test, in $log the log. Executes the +# developer- defined test setup AM_TESTS_ENVIRONMENT (if any), and +# passes TESTS_ENVIRONMENT. Set up options for the wrapper that +# will run the test scripts (or their associated LOG_COMPILER, if +# thy have one). +am__check_pre = \ +$(am__sh_e_setup); \ +$(am__vpath_adj_setup) $(am__vpath_adj) \ +$(am__tty_colors); \ +srcdir=$(srcdir); export srcdir; \ +case "$@" in \ + */*) am__odir=`echo "./$@" | sed 's|/[^/]*$$||'`;; \ + *) am__odir=.;; \ +esac; \ +test "x$$am__odir" = x"." || test -d "$$am__odir" \ + || $(MKDIR_P) "$$am__odir" || exit $$?; \ +if test -f "./$$f"; then dir=./; \ +elif test -f "$$f"; then dir=; \ +else dir="$(srcdir)/"; fi; \ +tst=$$dir$$f; log='$@'; \ +if test -n '$(DISABLE_HARD_ERRORS)'; then \ + am__enable_hard_errors=no; \ +else \ + am__enable_hard_errors=yes; \ +fi; \ +case " $(XFAIL_TESTS) " in \ + *[\ \ ]$$f[\ \ ]* | *[\ \ ]$$dir$$f[\ \ ]*) \ + am__expect_failure=yes;; \ + *) \ + am__expect_failure=no;; \ +esac; \ +$(AM_TESTS_ENVIRONMENT) $(TESTS_ENVIRONMENT) +# A shell command to get the names of the tests scripts with any registered +# extension removed (i.e., equivalently, the names of the test logs, with +# the '.log' extension removed). The result is saved in the shell variable +# '$bases'. This honors runtime overriding of TESTS and TEST_LOGS. Sadly, +# we cannot use something simpler, involving e.g., "$(TEST_LOGS:.log=)", +# since that might cause problem with VPATH rewrites for suffix-less tests. +# See also 'test-harness-vpath-rewrite.sh' and 'test-trs-basic.sh'. +am__set_TESTS_bases = \ + bases='$(TEST_LOGS)'; \ + bases=`for i in $$bases; do echo $$i; done | sed 's/\.log$$//'`; \ + bases=`echo $$bases` +AM_TESTSUITE_SUMMARY_HEADER = ' for $(PACKAGE_STRING)' +RECHECK_LOGS = $(TEST_LOGS) +AM_RECURSIVE_TARGETS = check recheck +TEST_SUITE_LOG = test-suite.log +TEST_EXTENSIONS = @EXEEXT@ .test +LOG_DRIVER = $(SHELL) $(top_srcdir)/test-driver +LOG_COMPILE = $(LOG_COMPILER) $(AM_LOG_FLAGS) $(LOG_FLAGS) +am__set_b = \ + case '$@' in \ + */*) \ + case '$*' in \ + */*) b='$*';; \ + *) b=`echo '$@' | sed 's/\.log$$//'`; \ + esac;; \ + *) \ + b='$*';; \ + esac +am__test_logs1 = $(TESTS:=.log) +am__test_logs2 = $(am__test_logs1:@EXEEXT@.log=.log) +TEST_LOGS = $(am__test_logs2:.test.log=.log) +TEST_LOG_DRIVER = $(SHELL) $(top_srcdir)/test-driver +TEST_LOG_COMPILE = $(TEST_LOG_COMPILER) $(AM_TEST_LOG_FLAGS) \ + $(TEST_LOG_FLAGS) +am__DIST_COMMON = $(srcdir)/Makefile.in $(top_srcdir)/test-driver +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ +CFLAGS = @CFLAGS@ +CPPFLAGS = @CPPFLAGS@ +CSCOPE = @CSCOPE@ +CTAGS = @CTAGS@ +CXX = @CXX@ +CXXDEPMODE = @CXXDEPMODE@ +CXXFLAGS = @CXXFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +ETAGS = @ETAGS@ +EXEEXT = @EXEEXT@ +GREP = @GREP@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LTLIBOBJS = @LTLIBOBJS@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +OBJEXT = @OBJEXT@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_URL = @PACKAGE_URL@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +PKG_CONFIG = @PKG_CONFIG@ +PKG_CONFIG_LIBDIR = @PKG_CONFIG_LIBDIR@ +PKG_CONFIG_PATH = @PKG_CONFIG_PATH@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +VERSION = @VERSION@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +ac_ct_CXX = @ac_ct_CXX@ +am__include = @am__include@ +am__leading_dot = @am__leading_dot@ +am__quote = @am__quote@ +am__tar = @am__tar@ +am__untar = @am__untar@ +bindir = @bindir@ +build = @build@ +build_alias = @build_alias@ +build_cpu = @build_cpu@ +build_os = @build_os@ +build_vendor = @build_vendor@ +builddir = @builddir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host = @host@ +host_alias = @host_alias@ +host_cpu = @host_cpu@ +host_os = @host_os@ +host_vendor = @host_vendor@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +libmaxminddb_CFLAGS = @libmaxminddb_CFLAGS@ +libmaxminddb_LIBS = @libmaxminddb_LIBS@ +localedir = @localedir@ +localstatedir = @localstatedir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +runstatedir = @runstatedir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_build_prefix = @top_build_prefix@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +CLEANFILES = test*.log test*.trs \ + test1.out test2.out test3.out test4.out test5.out test6.out test7.out \ + test8.out + +TESTS = test1.sh test2.sh test3.sh test4.sh test5.sh test6.sh test7.sh \ + test8.sh + +EXTRA_DIST = $(TESTS) \ + test1.gold test2.gold test3.gold test4.gold test5.gold test6.gold \ + test7.gold sql.txt test8.gold \ + dns.pcap dns6.pcap + +all: all-am + +.SUFFIXES: +.SUFFIXES: .log .test .test$(EXEEXT) .trs +$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \ + && { if test -f $@; then exit 0; else break; fi; }; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign src/test/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --foreign src/test/Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__maybe_remake_depfiles)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__maybe_remake_depfiles);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): +gcov-local: +tags TAGS: + +ctags CTAGS: + +cscope cscopelist: + + +# Recover from deleted '.trs' file; this should ensure that +# "rm -f foo.log; make foo.trs" re-run 'foo.test', and re-create +# both 'foo.log' and 'foo.trs'. Break the recipe in two subshells +# to avoid problems with "make -n". +.log.trs: + rm -f $< $@ + $(MAKE) $(AM_MAKEFLAGS) $< + +# Leading 'am--fnord' is there to ensure the list of targets does not +# expand to empty, as could happen e.g. with make check TESTS=''. +am--fnord $(TEST_LOGS) $(TEST_LOGS:.log=.trs): $(am__force_recheck) +am--force-recheck: + @: + +$(TEST_SUITE_LOG): $(TEST_LOGS) + @$(am__set_TESTS_bases); \ + am__f_ok () { test -f "$$1" && test -r "$$1"; }; \ + redo_bases=`for i in $$bases; do \ + am__f_ok $$i.trs && am__f_ok $$i.log || echo $$i; \ + done`; \ + if test -n "$$redo_bases"; then \ + redo_logs=`for i in $$redo_bases; do echo $$i.log; done`; \ + redo_results=`for i in $$redo_bases; do echo $$i.trs; done`; \ + if $(am__make_dryrun); then :; else \ + rm -f $$redo_logs && rm -f $$redo_results || exit 1; \ + fi; \ + fi; \ + if test -n "$$am__remaking_logs"; then \ + echo "fatal: making $(TEST_SUITE_LOG): possible infinite" \ + "recursion detected" >&2; \ + elif test -n "$$redo_logs"; then \ + am__remaking_logs=yes $(MAKE) $(AM_MAKEFLAGS) $$redo_logs; \ + fi; \ + if $(am__make_dryrun); then :; else \ + st=0; \ + errmsg="fatal: making $(TEST_SUITE_LOG): failed to create"; \ + for i in $$redo_bases; do \ + test -f $$i.trs && test -r $$i.trs \ + || { echo "$$errmsg $$i.trs" >&2; st=1; }; \ + test -f $$i.log && test -r $$i.log \ + || { echo "$$errmsg $$i.log" >&2; st=1; }; \ + done; \ + test $$st -eq 0 || exit 1; \ + fi + @$(am__sh_e_setup); $(am__tty_colors); $(am__set_TESTS_bases); \ + ws='[ ]'; \ + results=`for b in $$bases; do echo $$b.trs; done`; \ + test -n "$$results" || results=/dev/null; \ + all=` grep "^$$ws*:test-result:" $$results | wc -l`; \ + pass=` grep "^$$ws*:test-result:$$ws*PASS" $$results | wc -l`; \ + fail=` grep "^$$ws*:test-result:$$ws*FAIL" $$results | wc -l`; \ + skip=` grep "^$$ws*:test-result:$$ws*SKIP" $$results | wc -l`; \ + xfail=`grep "^$$ws*:test-result:$$ws*XFAIL" $$results | wc -l`; \ + xpass=`grep "^$$ws*:test-result:$$ws*XPASS" $$results | wc -l`; \ + error=`grep "^$$ws*:test-result:$$ws*ERROR" $$results | wc -l`; \ + if test `expr $$fail + $$xpass + $$error` -eq 0; then \ + success=true; \ + else \ + success=false; \ + fi; \ + br='==================='; br=$$br$$br$$br$$br; \ + result_count () \ + { \ + if test x"$$1" = x"--maybe-color"; then \ + maybe_colorize=yes; \ + elif test x"$$1" = x"--no-color"; then \ + maybe_colorize=no; \ + else \ + echo "$@: invalid 'result_count' usage" >&2; exit 4; \ + fi; \ + shift; \ + desc=$$1 count=$$2; \ + if test $$maybe_colorize = yes && test $$count -gt 0; then \ + color_start=$$3 color_end=$$std; \ + else \ + color_start= color_end=; \ + fi; \ + echo "$${color_start}# $$desc $$count$${color_end}"; \ + }; \ + create_testsuite_report () \ + { \ + result_count $$1 "TOTAL:" $$all "$$brg"; \ + result_count $$1 "PASS: " $$pass "$$grn"; \ + result_count $$1 "SKIP: " $$skip "$$blu"; \ + result_count $$1 "XFAIL:" $$xfail "$$lgn"; \ + result_count $$1 "FAIL: " $$fail "$$red"; \ + result_count $$1 "XPASS:" $$xpass "$$red"; \ + result_count $$1 "ERROR:" $$error "$$mgn"; \ + }; \ + { \ + echo "$(PACKAGE_STRING): $(subdir)/$(TEST_SUITE_LOG)" | \ + $(am__rst_title); \ + create_testsuite_report --no-color; \ + echo; \ + echo ".. contents:: :depth: 2"; \ + echo; \ + for b in $$bases; do echo $$b; done \ + | $(am__create_global_log); \ + } >$(TEST_SUITE_LOG).tmp || exit 1; \ + mv $(TEST_SUITE_LOG).tmp $(TEST_SUITE_LOG); \ + if $$success; then \ + col="$$grn"; \ + else \ + col="$$red"; \ + test x"$$VERBOSE" = x || cat $(TEST_SUITE_LOG); \ + fi; \ + echo "$${col}$$br$${std}"; \ + echo "$${col}Testsuite summary"$(AM_TESTSUITE_SUMMARY_HEADER)"$${std}"; \ + echo "$${col}$$br$${std}"; \ + create_testsuite_report --maybe-color; \ + echo "$$col$$br$$std"; \ + if $$success; then :; else \ + echo "$${col}See $(subdir)/$(TEST_SUITE_LOG)$${std}"; \ + if test -n "$(PACKAGE_BUGREPORT)"; then \ + echo "$${col}Please report to $(PACKAGE_BUGREPORT)$${std}"; \ + fi; \ + echo "$$col$$br$$std"; \ + fi; \ + $$success || exit 1 + +check-TESTS: + @list='$(RECHECK_LOGS)'; test -z "$$list" || rm -f $$list + @list='$(RECHECK_LOGS:.log=.trs)'; test -z "$$list" || rm -f $$list + @test -z "$(TEST_SUITE_LOG)" || rm -f $(TEST_SUITE_LOG) + @set +e; $(am__set_TESTS_bases); \ + log_list=`for i in $$bases; do echo $$i.log; done`; \ + trs_list=`for i in $$bases; do echo $$i.trs; done`; \ + log_list=`echo $$log_list`; trs_list=`echo $$trs_list`; \ + $(MAKE) $(AM_MAKEFLAGS) $(TEST_SUITE_LOG) TEST_LOGS="$$log_list"; \ + exit $$?; +recheck: all + @test -z "$(TEST_SUITE_LOG)" || rm -f $(TEST_SUITE_LOG) + @set +e; $(am__set_TESTS_bases); \ + bases=`for i in $$bases; do echo $$i; done \ + | $(am__list_recheck_tests)` || exit 1; \ + log_list=`for i in $$bases; do echo $$i.log; done`; \ + log_list=`echo $$log_list`; \ + $(MAKE) $(AM_MAKEFLAGS) $(TEST_SUITE_LOG) \ + am__force_recheck=am--force-recheck \ + TEST_LOGS="$$log_list"; \ + exit $$? +test1.sh.log: test1.sh + @p='test1.sh'; \ + b='test1.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test2.sh.log: test2.sh + @p='test2.sh'; \ + b='test2.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test3.sh.log: test3.sh + @p='test3.sh'; \ + b='test3.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test4.sh.log: test4.sh + @p='test4.sh'; \ + b='test4.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test5.sh.log: test5.sh + @p='test5.sh'; \ + b='test5.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test6.sh.log: test6.sh + @p='test6.sh'; \ + b='test6.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test7.sh.log: test7.sh + @p='test7.sh'; \ + b='test7.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +test8.sh.log: test8.sh + @p='test8.sh'; \ + b='test8.sh'; \ + $(am__check_pre) $(LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_LOG_DRIVER_FLAGS) $(LOG_DRIVER_FLAGS) -- $(LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +.test.log: + @p='$<'; \ + $(am__set_b); \ + $(am__check_pre) $(TEST_LOG_DRIVER) --test-name "$$f" \ + --log-file $$b.log --trs-file $$b.trs \ + $(am__common_driver_flags) $(AM_TEST_LOG_DRIVER_FLAGS) $(TEST_LOG_DRIVER_FLAGS) -- $(TEST_LOG_COMPILE) \ + "$$tst" $(AM_TESTS_FD_REDIRECT) +@am__EXEEXT_TRUE@.test$(EXEEXT).log: +@am__EXEEXT_TRUE@ @p='$<'; \ +@am__EXEEXT_TRUE@ $(am__set_b); \ +@am__EXEEXT_TRUE@ $(am__check_pre) $(TEST_LOG_DRIVER) --test-name "$$f" \ +@am__EXEEXT_TRUE@ --log-file $$b.log --trs-file $$b.trs \ +@am__EXEEXT_TRUE@ $(am__common_driver_flags) $(AM_TEST_LOG_DRIVER_FLAGS) $(TEST_LOG_DRIVER_FLAGS) -- $(TEST_LOG_COMPILE) \ +@am__EXEEXT_TRUE@ "$$tst" $(AM_TESTS_FD_REDIRECT) +distdir: $(BUILT_SOURCES) + $(MAKE) $(AM_MAKEFLAGS) distdir-am + +distdir-am: $(DISTFILES) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + topsrcdirstrip=`echo "$(top_srcdir)" | sed 's/[].[^$$\\*]/\\\\&/g'`; \ + list='$(DISTFILES)'; \ + dist_files=`for file in $$list; do echo $$file; done | \ + sed -e "s|^$$srcdirstrip/||;t" \ + -e "s|^$$topsrcdirstrip/|$(top_builddir)/|;t"`; \ + case $$dist_files in \ + */*) $(MKDIR_P) `echo "$$dist_files" | \ + sed '/\//!d;s|^|$(distdir)/|;s,/[^/]*$$,,' | \ + sort -u` ;; \ + esac; \ + for file in $$dist_files; do \ + if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \ + if test -d $$d/$$file; then \ + dir=`echo "/$$file" | sed -e 's,/[^/]*$$,,'`; \ + if test -d "$(distdir)/$$file"; then \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \ + cp -fpR $(srcdir)/$$file "$(distdir)$$dir" || exit 1; \ + find "$(distdir)/$$file" -type d ! -perm -700 -exec chmod u+rwx {} \;; \ + fi; \ + cp -fpR $$d/$$file "$(distdir)$$dir" || exit 1; \ + else \ + test -f "$(distdir)/$$file" \ + || cp -p $$d/$$file "$(distdir)/$$file" \ + || exit 1; \ + fi; \ + done +check-am: all-am + $(MAKE) $(AM_MAKEFLAGS) check-TESTS +check: check-am +all-am: Makefile +installdirs: +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi +mostlyclean-generic: + -test -z "$(TEST_LOGS)" || rm -f $(TEST_LOGS) + -test -z "$(TEST_LOGS:.log=.trs)" || rm -f $(TEST_LOGS:.log=.trs) + -test -z "$(TEST_SUITE_LOG)" || rm -f $(TEST_SUITE_LOG) + +clean-generic: + -test -z "$(CLEANFILES)" || rm -f $(CLEANFILES) + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." + -test -z "$(MAINTAINERCLEANFILES)" || rm -f $(MAINTAINERCLEANFILES) +clean: clean-am + +clean-am: clean-generic mostlyclean-am + +distclean: distclean-am + -rm -f Makefile +distclean-am: clean-am distclean-generic + +dvi: dvi-am + +dvi-am: + +gcov: gcov-am + +gcov-am: gcov-local + +html: html-am + +html-am: + +info: info-am + +info-am: + +install-data-am: + +install-dvi: install-dvi-am + +install-dvi-am: + +install-exec-am: + +install-html: install-html-am + +install-html-am: + +install-info: install-info-am + +install-info-am: + +install-man: + +install-pdf: install-pdf-am + +install-pdf-am: + +install-ps: install-ps-am + +install-ps-am: + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-generic + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: + +.MAKE: check-am install-am install-strip + +.PHONY: all all-am check check-TESTS check-am clean clean-generic \ + cscopelist-am ctags-am distclean distclean-generic distdir dvi \ + dvi-am gcov-am gcov-local html html-am info info-am install \ + install-am install-data install-data-am install-dvi \ + install-dvi-am install-exec install-exec-am install-html \ + install-html-am install-info install-info-am 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-generic pdf pdf-am ps ps-am recheck tags-am \ + uninstall uninstall-am + +.PRECIOUS: Makefile + + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/src/test/dns.pcap b/src/test/dns.pcap Binary files differnew file mode 100644 index 0000000..a0e585c --- /dev/null +++ b/src/test/dns.pcap diff --git a/src/test/dns6.pcap b/src/test/dns6.pcap Binary files differnew file mode 100644 index 0000000..5fa3af8 --- /dev/null +++ b/src/test/dns6.pcap diff --git a/src/test/sql.txt b/src/test/sql.txt new file mode 100644 index 0000000..b1d0bbb --- /dev/null +++ b/src/test/sql.txt @@ -0,0 +1,26 @@ +select qname as CertainQnames, qtype as Qtype, count(1) as count from dns where (qname='localhost' or qname like '%.root-servers.net') and qr==0 group by CertainQnames,Qtype order by count desc; +select qtype as Qtype, qname as Qname, count(1) as count from dns where qclass==3 and qr==0 group by Qtype,Qname order by count desc; +select rcode as Rcode, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==1 group by Rcode,ClientAddr order by count,Rcode,ClientAddr desc limit 50; +select 'ALL' as All, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by All,ClientSubnet order by count,ClientSubnet desc limit 200; +#select 'ALL' as All, subnet(src_addr,24,96) as ClientSubnet, count(1) as count from dns where qr==0 group by All,ClientSubnet order by count desc,ClientSubnet limit 200; +select if(rsplit(qname,1)='de','ok','non-auth-tld') as Class, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by Class,ClientSubnet order by count,ClientSubnet,Class desc limit 200; +select if(qr==1,'sent','recv') as Direction, if(protocol==6,'tcp',if(protocol==17,'udp',if(protocol==1,'icmp',if(protocol==58,'ipv6-icmp',protocol)))) as IPProto, count(1) as count from dns group by Direction,IPProto order by count,Direction,IPProto desc; +select if(ether_type==34525,'IPv6','IPv4') as IPVersion, qtype as Qtype, count(1) as count from dns where qr==0 group by IPVersion,Qtype order by count,IPVersion,Qtype desc; +select 'ALL' as All, do, edns0, edns_version, extended_rcode, z, if(do==1,'set','clr') as D0, count(1) as count from dns where qr==0 group by All,do,D0,edns0,edns_version,extended_rcode,z order by count desc; +select 'ALL' as All, if(edns0,edns_version,'none') as EDNSVersion, count(1) as count from dns where qr==0 group by All,EDNSVersion order by count desc; +select 'ALL' as All, if(qname like 'xn--%','idn','normal') as IDNQname, count(1) as count from dns where qr==0 group by All,IDNQname order by count desc; +select 'ALL' as All, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qname like 'xn--%') group by All,TLD order by count,TLD desc; +select 'ALL' as All, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==0 and (qtype=28 or qtype=38) and (qname like '%.root-servers.net') group by All,ClientAddr order by count desc limit 50; +select 'ALL' as All, opcode as Opcode, count(1) as count from dns where qr==0 group by All,Opcode order by count,Opcode desc; +select 'ALL' as All, qtype as Qtype, count(1) as count from dns where qr==0 group by All,Qtype order by count,Qtype desc; +select qtype as Qtype, len(qname) as QnameLen, count(1) as count from dns where qr==0 group by Qtype,QnameLen order by count,QnameLen,Qtype desc; +select qtype as Qtype, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qtype=1 or qtype=2 or qtype=5 or qtype=6 or qtype=12 or qtype=15 or qtype=28 or qtype=38 or qtype=255) group by Qtype,TLD order by count,TLD,Qtype desc limit 200; +select 'ALL' as All, rcode as Rcode, count(1) as count from dns where qr==1 group by All,Rcode order by count,Rcode desc; +select rcode as Rcode, msg_size as ReplyLen, count(1) as count from dns where qr==1 group by Rcode,ReplyLen order by count,Rcode,ReplyLen desc; +select 'ALL' as All, rd as RD, count(1) as count from dns where qr==0 group by All,RD order by count desc; +select if(protocol==6,'tcp',if(protocol==17,'udp',protocol)) as Transport, qtype as Qtype, count(1) as count from dns where qr==0 group by Transport,Qtype order by Transport,Qtype,count desc; +select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, dst_addr, lower_src, integer, float; +select name( 'qtype' , qtype ) as qt, count(*) as count from dns group by qtype order by count, qt desc; +#select count(*) as count, lower(rsplit(qname,1)) as tld, istld(tld) as flag from dns group by tld order by count desc limit 50; +select * from icmp; +select count(*) from icmp; diff --git a/src/test/test1.gold b/src/test/test1.gold new file mode 100644 index 0000000..d0b3203 --- /dev/null +++ b/src/test/test1.gold @@ -0,0 +1,145 @@ +[ + { + "table_name": "result-0", + "query": "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, lower_src, integer, float", + "head": [ + { "name": "s","type": "int" }, + { "name": "Dst_addr","type": "text" }, + { "name": "questiontype","type": "int" }, + { "name": "lower_src","type": "text" }, + { "name": "if((1and((((s<1)or(s<=1))or(s>1))or(s>=1))),t,f)","type": "text" }, + { "name": "trim(trim(((foofoo||rsplit(src_addr,1))||foofoo),foo),bar)","type": "text" }, + { "name": "count(1)","type": "int" }, + { "name": "len(src_addr)","type": "int" }, + { "name": "(sum((msg_size+-((((((1-(2%4))<<3)>>2)|3)&~(4)))))+1)","type": "int" }, + { "name": "min(msg_size)","type": "int" }, + { "name": "max(msg_size)","type": "int" }, + { "name": "integer","type": "int" }, + { "name": "float","type": "float" }, + { "name": "(sum(((src_port+1.0)-((2.0/1.5)*-(2.5))))+1.0)","type": "float" }, + { "name": "max((src_port+1.0))","type": "float" }, + { "name": "min((src_port+1.0))","type": "float" }, + { "name": "avg(src_port)","type": "float" }, + { "name": "stdev(src_port)","type": "float" }, + { "name": "name(rcode,0)","type": "text" } + ], + "data": [ + [1297433016,"212.247.204.2",12,"172.18.24.52","t","24",1,12,48,42,42,1,1.1,52271.3,52267,52267,52266,0,"NoError"], + [1297433016,"172.18.24.52",12,"212.247.204.2","t","204",1,13,125,119,119,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433026,"212.247.204.2",1,"172.18.24.52","t","24",1,12,36,30,30,1,1.1,54066.3,54062,54062,54061,0,"NoError"], + [1297433027,"172.18.24.52",1,"212.247.204.2","t","204",1,13,84,78,78,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433030,"212.247.204.2",1,"172.18.24.52","t","24",1,12,30,24,24,1,1.1,59489.3,59485,59485,59484,0,"NoError"], + [1297433030,"172.18.24.52",1,"212.247.204.2","t","204",1,13,46,40,40,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433038,"212.247.204.2",12,"172.18.24.52","t","24",1,12,50,44,44,1,1.1,49372.3,49368,49368,49367,0,"NoError"], + [1297433039,"172.18.24.52",12,"212.247.204.2","t","204",1,13,102,96,96,1,1.1,58.3333,54,54,53,0,"NoError"] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select netmask(src_addr), netmask(dst_addr, 8, 16) from dns", + "head": [ + { "name": "netmask(src_addr)","type": "text" }, + { "name": "netmask(dst_addr,8,16)","type": "text" } + ], + "data": [ + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"], + ["172.17.0.0","8.0.0.0"], + ["8.8.8.0","172.0.0.0"] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select netmask(src_addr), netmask(dst_addr, 8, 16) from dns", + "head": [ + { "name": "netmask(src_addr)","type": "text" }, + { "name": "netmask(dst_addr,8,16)","type": "text" } + ], + "data": [ + ["2a01:3f0::","2001::"], + ["2001:4860:4860::","2a01::"] + ] + } +] diff --git a/src/test/test1.sh b/src/test/test1.sh new file mode 100755 index 0000000..83e6779 --- /dev/null +++ b/src/test/test1.sh @@ -0,0 +1,27 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -j -s "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, lower_src, integer, float" "$srcdir/../../pcap/sample.pcap.gz" > test1.out + +../packetq -j -s "select netmask(src_addr), netmask(dst_addr, 8, 16) from dns" "$srcdir/dns.pcap" >>test1.out + +../packetq -j -s "select netmask(src_addr), netmask(dst_addr, 8, 16) from dns" "$srcdir/dns6.pcap" >>test1.out + +diff -uw "$srcdir/test1.gold" test1.out diff --git a/src/test/test2.gold b/src/test/test2.gold new file mode 100644 index 0000000..eff7e73 --- /dev/null +++ b/src/test/test2.gold @@ -0,0 +1,9 @@ +"s","Dst_addr","questiontype","lower_src","if((1and((((s<1)or(s<=1))or(s>1))or(s>=1))),t,f)","trim(trim(((foofoo||rsplit(src_addr,1))||foofoo),foo),bar)","count(1)","len(src_addr)","(sum((msg_size+-((((((1-(2%4))<<3)>>2)|3)&~(4)))))+1)","min(msg_size)","max(msg_size)","integer","float","(sum(((src_port+1.0)-((2.0/1.5)*-(2.5))))+1.0)","max((src_port+1.0))","min((src_port+1.0))","avg(src_port)","stdev(src_port)","name(rcode,0)" +1297433016,"212.247.204.2",12,"172.18.24.52","t","24",1,12,48,42,42,1,1.1,52271.3,52267,52267,52266,0,"NoError" +1297433016,"172.18.24.52",12,"212.247.204.2","t","204",1,13,125,119,119,1,1.1,58.3333,54,54,53,0,"NoError" +1297433026,"212.247.204.2",1,"172.18.24.52","t","24",1,12,36,30,30,1,1.1,54066.3,54062,54062,54061,0,"NoError" +1297433027,"172.18.24.52",1,"212.247.204.2","t","204",1,13,84,78,78,1,1.1,58.3333,54,54,53,0,"NoError" +1297433030,"212.247.204.2",1,"172.18.24.52","t","24",1,12,30,24,24,1,1.1,59489.3,59485,59485,59484,0,"NoError" +1297433030,"172.18.24.52",1,"212.247.204.2","t","204",1,13,46,40,40,1,1.1,58.3333,54,54,53,0,"NoError" +1297433038,"212.247.204.2",12,"172.18.24.52","t","24",1,12,50,44,44,1,1.1,49372.3,49368,49368,49367,0,"NoError" +1297433039,"172.18.24.52",12,"212.247.204.2","t","204",1,13,102,96,96,1,1.1,58.3333,54,54,53,0,"NoError" diff --git a/src/test/test2.sh b/src/test/test2.sh new file mode 100755 index 0000000..c443ec1 --- /dev/null +++ b/src/test/test2.sh @@ -0,0 +1,23 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -c -s "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, lower_src, integer, float" "$srcdir/../../pcap/sample.pcap.gz" > test2.out + +diff -uw "$srcdir/test2.gold" test2.out diff --git a/src/test/test3.gold b/src/test/test3.gold new file mode 100644 index 0000000..c605f71 --- /dev/null +++ b/src/test/test3.gold @@ -0,0 +1,9 @@ +"s" ,"Dst_addr" ,"questiontype","lower_src" ,"if((1and((((s<1)or(s<=1))or(s>1))or(s>=1))),t,f)","trim(trim(((foofoo||rsplit(src_addr,1))||foofoo),foo),bar)","count(1)","len(src_addr)","(sum((msg_size+-((((((1-(2%4))<<3)>>2)|3)&~(4)))))+1)","min(msg_size)","max(msg_size)","integer","float","(sum(((src_port+1.0)-((2.0/1.5)*-(2.5))))+1.0)","max((src_port+1.0))","min((src_port+1.0))","avg(src_port)","stdev(src_port)","name(rcode,0)" +1297433016,"212.247.204.2",12 ,"172.18.24.52" ,"t" ,"24" ,1 ,12 ,48 ,42 ,42 ,1 ,1.1 ,52271.3 ,52267 ,52267 ,52266 ,0 ,"NoError" +1297433016,"172.18.24.52" ,12 ,"212.247.204.2","t" ,"204" ,1 ,13 ,125 ,119 ,119 ,1 ,1.1 ,58.3333 ,54 ,54 ,53 ,0 ,"NoError" +1297433026,"212.247.204.2",1 ,"172.18.24.52" ,"t" ,"24" ,1 ,12 ,36 ,30 ,30 ,1 ,1.1 ,54066.3 ,54062 ,54062 ,54061 ,0 ,"NoError" +1297433027,"172.18.24.52" ,1 ,"212.247.204.2","t" ,"204" ,1 ,13 ,84 ,78 ,78 ,1 ,1.1 ,58.3333 ,54 ,54 ,53 ,0 ,"NoError" +1297433030,"212.247.204.2",1 ,"172.18.24.52" ,"t" ,"24" ,1 ,12 ,30 ,24 ,24 ,1 ,1.1 ,59489.3 ,59485 ,59485 ,59484 ,0 ,"NoError" +1297433030,"172.18.24.52" ,1 ,"212.247.204.2","t" ,"204" ,1 ,13 ,46 ,40 ,40 ,1 ,1.1 ,58.3333 ,54 ,54 ,53 ,0 ,"NoError" +1297433038,"212.247.204.2",12 ,"172.18.24.52" ,"t" ,"24" ,1 ,12 ,50 ,44 ,44 ,1 ,1.1 ,49372.3 ,49368 ,49368 ,49367 ,0 ,"NoError" +1297433039,"172.18.24.52" ,12 ,"212.247.204.2","t" ,"204" ,1 ,13 ,102 ,96 ,96 ,1 ,1.1 ,58.3333 ,54 ,54 ,53 ,0 ,"NoError" diff --git a/src/test/test3.sh b/src/test/test3.sh new file mode 100755 index 0000000..528845d --- /dev/null +++ b/src/test/test3.sh @@ -0,0 +1,23 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -t -s "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, lower_src, integer, float" "$srcdir/../../pcap/sample.pcap.gz" > test3.out + +diff -uw "$srcdir/test3.gold" test3.out diff --git a/src/test/test4.gold b/src/test/test4.gold new file mode 100644 index 0000000..18b1cfc --- /dev/null +++ b/src/test/test4.gold @@ -0,0 +1,26 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> +<head> + <title>result-0</title> +<style type="text/css"> + th.int { color: #0F0C00; } + th.float { color: #0F0900; } + th.text { color: #0F0600; } + th.bool { color: #0C0900; } +</style> +</head> +<body> +<table> +<tr><th class="int">s</th><th class="text">Dst_addr</th><th class="int">questiontype</th><th class="text">lower_src</th><th class="text">if((1and((((s<1)or(s<=1))or(s>1))or(s>=1))),t,f)</th><th class="text">trim(trim(((foofoo||rsplit(src_addr,1))||foofoo),foo),bar)</th><th class="int">count(1)</th><th class="int">len(src_addr)</th><th class="int">(sum((msg_size+-((((((1-(2%4))<<3)>>2)|3)&~(4)))))+1)</th><th class="int">min(msg_size)</th><th class="int">max(msg_size)</th><th class="int">integer</th><th class="float">float</th><th class="float">(sum(((src_port+1.0)-((2.0/1.5)*-(2.5))))+1.0)</th><th class="float">max((src_port+1.0))</th><th class="float">min((src_port+1.0))</th><th class="float">avg(src_port)</th><th class="float">stdev(src_port)</th><th class="text">name(rcode,0)</th></tr> +<tr><td>1297433016</td> <td>212.247.204.2</td> <td>12</td> <td>172.18.24.52</td> <td>t</td> <td>24</td> <td>1</td> <td>12</td> <td>48</td> <td>42</td> <td>42</td> <td>1</td> <td>1.1</td> <td>52271.3</td> <td>52267</td> <td>52267</td> <td>52266</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433016</td> <td>172.18.24.52</td> <td>12</td> <td>212.247.204.2</td> <td>t</td> <td>204</td> <td>1</td> <td>13</td> <td>125</td> <td>119</td> <td>119</td> <td>1</td> <td>1.1</td> <td>58.3333</td> <td>54</td> <td>54</td> <td>53</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433026</td> <td>212.247.204.2</td> <td>1</td> <td>172.18.24.52</td> <td>t</td> <td>24</td> <td>1</td> <td>12</td> <td>36</td> <td>30</td> <td>30</td> <td>1</td> <td>1.1</td> <td>54066.3</td> <td>54062</td> <td>54062</td> <td>54061</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433027</td> <td>172.18.24.52</td> <td>1</td> <td>212.247.204.2</td> <td>t</td> <td>204</td> <td>1</td> <td>13</td> <td>84</td> <td>78</td> <td>78</td> <td>1</td> <td>1.1</td> <td>58.3333</td> <td>54</td> <td>54</td> <td>53</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433030</td> <td>212.247.204.2</td> <td>1</td> <td>172.18.24.52</td> <td>t</td> <td>24</td> <td>1</td> <td>12</td> <td>30</td> <td>24</td> <td>24</td> <td>1</td> <td>1.1</td> <td>59489.3</td> <td>59485</td> <td>59485</td> <td>59484</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433030</td> <td>172.18.24.52</td> <td>1</td> <td>212.247.204.2</td> <td>t</td> <td>204</td> <td>1</td> <td>13</td> <td>46</td> <td>40</td> <td>40</td> <td>1</td> <td>1.1</td> <td>58.3333</td> <td>54</td> <td>54</td> <td>53</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433038</td> <td>212.247.204.2</td> <td>12</td> <td>172.18.24.52</td> <td>t</td> <td>24</td> <td>1</td> <td>12</td> <td>50</td> <td>44</td> <td>44</td> <td>1</td> <td>1.1</td> <td>49372.3</td> <td>49368</td> <td>49368</td> <td>49367</td> <td>0</td> <td>NoError</td> </tr> +<tr><td>1297433039</td> <td>172.18.24.52</td> <td>12</td> <td>212.247.204.2</td> <td>t</td> <td>204</td> <td>1</td> <td>13</td> <td>102</td> <td>96</td> <td>96</td> <td>1</td> <td>1.1</td> <td>58.3333</td> <td>54</td> <td>54</td> <td>53</td> <td>0</td> <td>NoError</td> </tr> +</table> +</body> +</html> diff --git a/src/test/test4.sh b/src/test/test4.sh new file mode 100755 index 0000000..0747e73 --- /dev/null +++ b/src/test/test4.sh @@ -0,0 +1,23 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -x -s "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, lower_src, integer, float" "$srcdir/../../pcap/sample.pcap.gz" > test4.out + +diff -uw "$srcdir/test4.gold" test4.out diff --git a/src/test/test5.gold b/src/test/test5.gold new file mode 100644 index 0000000..c1c4a82 --- /dev/null +++ b/src/test/test5.gold @@ -0,0 +1,387 @@ +[ + { + "table_name": "result-0", + "query": "select qname as CertainQnames, qtype as Qtype, count(1) as count from dns where (qname='localhost' or qname like '%.root-servers.net') and qr==0 group by CertainQnames,Qtype order by count desc;", + "head": [ + { "name": "CertainQnames","type": "text" }, + { "name": "Qtype","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ] + } +] +[ + { + "table_name": "result-0", + "query": "select qtype as Qtype, qname as Qname, count(1) as count from dns where qclass==3 and qr==0 group by Qtype,Qname order by count desc;", + "head": [ + { "name": "Qtype","type": "int" }, + { "name": "Qname","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ] + } +] +[ + { + "table_name": "result-0", + "query": "select rcode as Rcode, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==1 group by Rcode,ClientAddr order by count,Rcode,ClientAddr desc limit 50;", + "head": [ + { "name": "Rcode","type": "int" }, + { "name": "ClientAddr","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + [3,"172.18.24.52",1], + [0,"172.18.24.52",3] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by All,ClientSubnet order by count,ClientSubnet desc limit 200;", + "head": [ + { "name": "All","type": "text" }, + { "name": "ClientSubnet","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL","172.18.24.0",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select if(rsplit(qname,1)='de','ok','non-auth-tld') as Class, if(ether_type==34525,rsplit(src_addr,7,':')||':'||rsplit(src_addr,6,':')||':'||rsplit(src_addr,5,':')||':'||rsplit(src_addr,4,':')||':'||rsplit(src_addr,3,':')||'::',rsplit(src_addr,3)||'.'||rsplit(src_addr,2)||'.'||rsplit(src_addr,1)||'.0') as ClientSubnet, count(1) as count from dns where qr==0 group by Class,ClientSubnet order by count,ClientSubnet,Class desc limit 200;", + "head": [ + { "name": "Class","type": "text" }, + { "name": "ClientSubnet","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["non-auth-tld","172.18.24.0",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select if(qr==1,'sent','recv') as Direction, if(protocol==6,'tcp',if(protocol==17,'udp',if(protocol==1,'icmp',if(protocol==58,'ipv6-icmp',protocol)))) as IPProto, count(1) as count from dns group by Direction,IPProto order by count,Direction,IPProto desc;", + "head": [ + { "name": "Direction","type": "text" }, + { "name": "IPProto","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["recv","udp",4], + ["sent","udp",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select if(ether_type==34525,'IPv6','IPv4') as IPVersion, qtype as Qtype, count(1) as count from dns where qr==0 group by IPVersion,Qtype order by count,IPVersion,Qtype desc;", + "head": [ + { "name": "IPVersion","type": "text" }, + { "name": "Qtype","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ["IPv4",12,2], + ["IPv4",1,2] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, do, edns0, edns_version, extended_rcode, z, if(do==1,'set','clr') as D0, count(1) as count from dns where qr==0 group by All,do,D0,edns0,edns_version,extended_rcode,z order by count desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "do","type": "bool" }, + { "name": "edns0","type": "bool" }, + { "name": "edns_version","type": "int" }, + { "name": "extended_rcode","type": "int" }, + { "name": "z","type": "int" }, + { "name": "D0","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL",0,0,0,0,0,"clr",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, if(edns0,edns_version,'none') as EDNSVersion, count(1) as count from dns where qr==0 group by All,EDNSVersion order by count desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "EDNSVersion","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL","none",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, if(qname like 'xn--%','idn','normal') as IDNQname, count(1) as count from dns where qr==0 group by All,IDNQname order by count desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "IDNQname","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL","normal",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qname like 'xn--%') group by All,TLD order by count,TLD desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "TLD","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, if(qr==1,dst_addr,src_addr) as ClientAddr, count(1) as count from dns where qr==0 and (qtype=28 or qtype=38) and (qname like '%.root-servers.net') group by All,ClientAddr order by count desc limit 50;", + "head": [ + { "name": "All","type": "text" }, + { "name": "ClientAddr","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, opcode as Opcode, count(1) as count from dns where qr==0 group by All,Opcode order by count,Opcode desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "Opcode","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL",0,4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, qtype as Qtype, count(1) as count from dns where qr==0 group by All,Qtype order by count,Qtype desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "Qtype","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL",12,2], + ["ALL",1,2] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select qtype as Qtype, len(qname) as QnameLen, count(1) as count from dns where qr==0 group by Qtype,QnameLen order by count,QnameLen,Qtype desc;", + "head": [ + { "name": "Qtype","type": "int" }, + { "name": "QnameLen","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + [1,7,1], + [1,13,1], + [12,25,1], + [12,27,1] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select qtype as Qtype, lower(rsplit(qname,1)) as TLD, count(1) as count from dns where qr==0 and (qtype=1 or qtype=2 or qtype=5 or qtype=6 or qtype=12 or qtype=15 or qtype=28 or qtype=38 or qtype=255) group by Qtype,TLD order by count,TLD,Qtype desc limit 200;", + "head": [ + { "name": "Qtype","type": "int" }, + { "name": "TLD","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + [1,"org",1], + [1,"se",1], + [12,"arpa",2] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, rcode as Rcode, count(1) as count from dns where qr==1 group by All,Rcode order by count,Rcode desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "Rcode","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL",3,1], + ["ALL",0,3] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select rcode as Rcode, msg_size as ReplyLen, count(1) as count from dns where qr==1 group by Rcode,ReplyLen order by count,Rcode,ReplyLen desc;", + "head": [ + { "name": "Rcode","type": "int" }, + { "name": "ReplyLen","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + [0,96,1], + [0,78,1], + [0,40,1], + [3,119,1] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select 'ALL' as All, rd as RD, count(1) as count from dns where qr==0 group by All,RD order by count desc;", + "head": [ + { "name": "All","type": "text" }, + { "name": "RD","type": "bool" }, + { "name": "count","type": "int" } + ], + "data": [ + ["ALL",1,4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select if(protocol==6,'tcp',if(protocol==17,'udp',protocol)) as Transport, qtype as Qtype, count(1) as count from dns where qr==0 group by Transport,Qtype order by Transport,Qtype,count desc;", + "head": [ + { "name": "Transport","type": "text" }, + { "name": "Qtype","type": "int" }, + { "name": "count","type": "int" } + ], + "data": [ + ["udp",1,2], + ["udp",12,2] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select s, dst_addr as Dst_addr, qtype as questiontype, lower(src_addr) as lower_src, if(1 and s < 1 or s <= 1 or s > 1 or s >= 1, 't', 'f'), trim(trim('foofoo' || rsplit(src_addr, 1) || 'foofoo', 'foo'), 'bar'), count(*), len(src_addr), sum(msg_size + -1 - 2 % 4 << 3 >> 2 | 3 & ~4) + 1, min(msg_size), max(msg_size), truncate(1.1) as integer, 1.1 as float, sum(src_port + 1.0 - 2.0 / 1.5 * -2.5) + 1.0, max(src_port + 1.0), min(src_port + 1.0), avg(src_port), stdev(src_port), name('rcode', 0) from dns where src_addr like '%' and (qr or not qr) group by src_addr, s having s >= 0 order by s, dst_addr, lower_src, integer, float;", + "head": [ + { "name": "s","type": "int" }, + { "name": "Dst_addr","type": "text" }, + { "name": "questiontype","type": "int" }, + { "name": "lower_src","type": "text" }, + { "name": "if((1and((((s<1)or(s<=1))or(s>1))or(s>=1))),t,f)","type": "text" }, + { "name": "trim(trim(((foofoo||rsplit(src_addr,1))||foofoo),foo),bar)","type": "text" }, + { "name": "count(1)","type": "int" }, + { "name": "len(src_addr)","type": "int" }, + { "name": "(sum((msg_size+-((((((1-(2%4))<<3)>>2)|3)&~(4)))))+1)","type": "int" }, + { "name": "min(msg_size)","type": "int" }, + { "name": "max(msg_size)","type": "int" }, + { "name": "integer","type": "int" }, + { "name": "float","type": "float" }, + { "name": "(sum(((src_port+1.0)-((2.0/1.5)*-(2.5))))+1.0)","type": "float" }, + { "name": "max((src_port+1.0))","type": "float" }, + { "name": "min((src_port+1.0))","type": "float" }, + { "name": "avg(src_port)","type": "float" }, + { "name": "stdev(src_port)","type": "float" }, + { "name": "name(rcode,0)","type": "text" } + ], + "data": [ + [1297433016,"172.18.24.52",12,"212.247.204.2","t","204",1,13,125,119,119,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433016,"212.247.204.2",12,"172.18.24.52","t","24",1,12,48,42,42,1,1.1,52271.3,52267,52267,52266,0,"NoError"], + [1297433026,"212.247.204.2",1,"172.18.24.52","t","24",1,12,36,30,30,1,1.1,54066.3,54062,54062,54061,0,"NoError"], + [1297433027,"172.18.24.52",1,"212.247.204.2","t","204",1,13,84,78,78,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433030,"172.18.24.52",1,"212.247.204.2","t","204",1,13,46,40,40,1,1.1,58.3333,54,54,53,0,"NoError"], + [1297433030,"212.247.204.2",1,"172.18.24.52","t","24",1,12,30,24,24,1,1.1,59489.3,59485,59485,59484,0,"NoError"], + [1297433038,"212.247.204.2",12,"172.18.24.52","t","24",1,12,50,44,44,1,1.1,49372.3,49368,49368,49367,0,"NoError"], + [1297433039,"172.18.24.52",12,"212.247.204.2","t","204",1,13,102,96,96,1,1.1,58.3333,54,54,53,0,"NoError"] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select name( 'qtype' , qtype ) as qt, count(*) as count from dns group by qtype order by count, qt desc;", + "head": [ + { "name": "qt","type": "text" }, + { "name": "count","type": "int" } + ], + "data": [ + ["PTR",4], + ["A",4] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select * from icmp;", + "head": [ + { "name": "id","type": "int" }, + { "name": "s","type": "int" }, + { "name": "us","type": "int" }, + { "name": "ether_type","type": "int" }, + { "name": "src_port","type": "int" }, + { "name": "dst_port","type": "int" }, + { "name": "src_addr","type": "text" }, + { "name": "dst_addr","type": "text" }, + { "name": "protocol","type": "int" }, + { "name": "ip_ttl","type": "int" }, + { "name": "ip_version","type": "int" }, + { "name": "fragments","type": "int" }, + { "name": "type","type": "int" }, + { "name": "code","type": "int" }, + { "name": "echo_identifier","type": "int" }, + { "name": "echo_sequence","type": "int" }, + { "name": "du_protocol","type": "int" }, + { "name": "du_src_addr","type": "text" }, + { "name": "du_dst_addr","type": "text" }, + { "name": "desc","type": "text" } + ], + "data": [ + ] + } +] +[ + { + "table_name": "result-0", + "query": "select count(*) from icmp;", + "head": [ + { "name": "count(1)","type": "int" } + ], + "data": [ + ] + } +] diff --git a/src/test/test5.sh b/src/test/test5.sh new file mode 100755 index 0000000..42ce265 --- /dev/null +++ b/src/test/test5.sh @@ -0,0 +1,27 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +rm -f test5.out + +cat "$srcdir/sql.txt" | grep -v '^#' | while read sql; do + ../packetq -s "$sql" "$srcdir/../../pcap/sample.pcap.gz" >> test5.out +done + +diff -uw "$srcdir/test5.gold" test5.out diff --git a/src/test/test6.gold b/src/test/test6.gold new file mode 100644 index 0000000..621f41c --- /dev/null +++ b/src/test/test6.gold @@ -0,0 +1,12 @@ +[ + { + "table_name": "result-0", + "query": "select count(*) from dns", + "head": [ + { "name": "count(1)","type": "int" } + ], + "data": [ + [2] + ] + } +] diff --git a/src/test/test6.sh b/src/test/test6.sh new file mode 100755 index 0000000..9846b36 --- /dev/null +++ b/src/test/test6.sh @@ -0,0 +1,23 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -s "select count(*) from dns" "$srcdir/../../pcap/sample-bigendian.pcap.gz" > test6.out + +diff -uw "$srcdir/test6.gold" test6.out diff --git a/src/test/test7.gold b/src/test/test7.gold new file mode 100644 index 0000000..151c3b5 --- /dev/null +++ b/src/test/test7.gold @@ -0,0 +1,71 @@ +[ + { + "table_name": "result-0", + "query": "select * from icmp", + "head": [ + { "name": "id","type": "int" }, + { "name": "s","type": "int" }, + { "name": "us","type": "int" }, + { "name": "ether_type","type": "int" }, + { "name": "src_port","type": "int" }, + { "name": "dst_port","type": "int" }, + { "name": "src_addr","type": "text" }, + { "name": "dst_addr","type": "text" }, + { "name": "protocol","type": "int" }, + { "name": "ip_ttl","type": "int" }, + { "name": "ip_version","type": "int" }, + { "name": "fragments","type": "int" }, + { "name": "type","type": "int" }, + { "name": "code","type": "int" }, + { "name": "echo_identifier","type": "int" }, + { "name": "echo_sequence","type": "int" }, + { "name": "du_protocol","type": "int" }, + { "name": "du_src_addr","type": "text" }, + { "name": "du_dst_addr","type": "text" }, + { "name": "desc","type": "text" } + ], + "data": [ + [1,1297781718,401023,2048,0,0,"172.18.24.52","172.18.201.234",1,64,4,0,8,0,17563,0,0,"","","Echo Request"], + [2,1297781719,401120,2048,0,0,"172.18.24.52","172.18.201.234",1,64,4,0,8,0,17563,1,0,"","","Echo Request"], + [3,1297781720,401368,2048,0,0,"172.18.24.52","172.18.201.234",1,64,4,0,8,0,17563,2,0,"","","Echo Request"], + [4,1297781729,36800,2048,0,0,"172.18.24.52","172.18.24.1",1,64,4,0,8,0,17819,0,0,"","","Echo Request"], + [5,1297781729,37210,2048,0,0,"172.18.24.1","172.18.24.52",1,64,4,0,0,0,17819,0,0,"","","Echo Reply"], + [6,1297781730,37013,2048,0,0,"172.18.24.52","172.18.24.1",1,64,4,0,8,0,17819,1,0,"","","Echo Request"], + [7,1297781730,37634,2048,0,0,"172.18.24.1","172.18.24.52",1,64,4,0,0,0,17819,1,0,"","","Echo Reply"], + [8,1297781731,37342,2048,0,0,"172.18.24.52","172.18.24.1",1,64,4,0,8,0,17819,2,0,"","","Echo Request"], + [9,1297781731,37864,2048,0,0,"172.18.24.1","172.18.24.52",1,64,4,0,0,0,17819,2,0,"","","Echo Reply"], + [10,1297781733,388527,2048,0,0,"172.18.24.52","172.18.24.12",1,64,4,0,8,0,18075,0,0,"","","Echo Request"], + [11,1297781733,389073,2048,0,0,"172.18.24.12","172.18.24.52",1,128,4,0,0,0,18075,0,0,"","","Echo Reply"], + [12,1297781734,388627,2048,0,0,"172.18.24.52","172.18.24.12",1,64,4,0,8,0,18075,1,0,"","","Echo Request"], + [13,1297781734,388912,2048,0,0,"172.18.24.12","172.18.24.52",1,128,4,0,0,0,18075,1,0,"","","Echo Reply"], + [14,1297781735,388779,2048,0,0,"172.18.24.52","172.18.24.12",1,64,4,0,8,0,18075,2,0,"","","Echo Request"], + [15,1297781735,389060,2048,0,0,"172.18.24.12","172.18.24.52",1,128,4,0,0,0,18075,2,0,"","","Echo Reply"], + [16,1297781739,517764,2048,0,0,"172.18.24.52","172.18.23.12",1,64,4,0,8,0,18331,0,0,"","","Echo Request"], + [17,1297781740,518089,2048,0,0,"172.18.24.52","172.18.23.12",1,64,4,0,8,0,18331,1,0,"","","Echo Request"], + [18,1297781741,518404,2048,0,0,"172.18.24.52","172.18.23.12",1,64,4,0,8,0,18331,2,0,"","","Echo Request"], + [19,1297781745,4951,2048,0,0,"172.18.24.52","173.18.23.12",1,64,4,0,8,0,19355,0,0,"","","Echo Request"], + [20,1297781746,5090,2048,0,0,"172.18.24.52","173.18.23.12",1,64,4,0,8,0,19355,1,0,"","","Echo Request"], + [21,1297781747,5403,2048,0,0,"172.18.24.52","173.18.23.12",1,64,4,0,8,0,19355,2,0,"","","Echo Request"], + [22,1297781749,725341,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,0,0,"","","Echo Request"], + [23,1297781750,725507,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,1,0,"","","Echo Request"], + [24,1297781750,900759,2048,0,0,"75.160.241.10","172.18.24.52",1,234,4,0,3,1,0,0,1,"172.18.24.52","174.18.23.12","Destination host unreachable"], + [25,1297781751,725837,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,2,0,"","","Echo Request"], + [26,1297781752,726162,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,3,0,"","","Echo Request"], + [27,1297781753,726487,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,4,0,"","","Echo Request"], + [28,1297781754,726804,2048,0,0,"172.18.24.52","174.18.23.12",1,64,4,0,8,0,19611,5,0,"","","Echo Request"], + [29,1297781754,903407,2048,0,0,"75.160.241.10","172.18.24.52",1,234,4,0,3,1,0,0,1,"172.18.24.52","174.18.23.12","Destination host unreachable"] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select count(*) from icmp", + "head": [ + { "name": "count(1)","type": "int" } + ], + "data": [ + [29] + ] + } +] diff --git a/src/test/test7.sh b/src/test/test7.sh new file mode 100755 index 0000000..6433aab --- /dev/null +++ b/src/test/test7.sh @@ -0,0 +1,24 @@ +#!/bin/sh -e +# Copyright (c) 2017-2024 OARC, Inc. +# Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +../packetq -s "select * from icmp" "$srcdir/../../pcap/icmp.pcap.gz" > test7.out +../packetq -s "select count(*) from icmp" "$srcdir/../../pcap/icmp.pcap.gz" >> test7.out + +diff -uw "$srcdir/test7.gold" test7.out diff --git a/src/test/test8.gold b/src/test/test8.gold new file mode 100644 index 0000000..02a8b99 --- /dev/null +++ b/src/test/test8.gold @@ -0,0 +1,60 @@ +[ + { + "table_name": "result-0", + "query": "select qname from dns", + "head": [ + { "name": "qname","type": "text" } + ], + "data": [ + ["test."], + ["'."], + ["\"."], + ["$."], + ["\\."], + ["$."], + ["$."], + ["_test.all.54.non-escaped.characters.abcdefghijklmnopqrstuvwxyz.ABCDEFGHIJKLMNOPQRSTUVWXYZ.0123456789.test."], + ["dot.embeded.in.a.label.test."] + ] + } +] +[ + { + "table_name": "result-0", + "query": "select qname from dns", + "head": [ + { "name": "qname","type": "text" } + ], + "data": [ + ["test."], + ["\\039."], + ["\\034."], + ["\\036."], + ["\\092."], + ["\\000."], + ["\\255."], + ["_test.all.54.non-escaped.characters.abcdefghijklmnopqrstuvwxyz.ABCDEFGHIJKLMNOPQRSTUVWXYZ.0123456789.test."], + ["dot\\046embeded.in.a.label.test."] + ] + } +] +"qname" +"test." +"'." +"""." +"$." +"\." +"$." +"$." +"_test.all.54.non-escaped.characters.abcdefghijklmnopqrstuvwxyz.ABCDEFGHIJKLMNOPQRSTUVWXYZ.0123456789.test." +"dot.embeded.in.a.label.test." +"qname" +"test." +"\039." +"\034." +"\036." +"\092." +"\000." +"\255." +"_test.all.54.non-escaped.characters.abcdefghijklmnopqrstuvwxyz.ABCDEFGHIJKLMNOPQRSTUVWXYZ.0123456789.test." +"dot\046embeded.in.a.label.test." diff --git a/src/test/test8.sh b/src/test/test8.sh new file mode 100755 index 0000000..1dde9bf --- /dev/null +++ b/src/test/test8.sh @@ -0,0 +1,26 @@ +#!/bin/sh -e +# Copyright (c) 2021, Internet Systems Consortium, Inc. +# All rights reserved. +# +# This file is part of PacketQ. +# +# PacketQ is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# PacketQ is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + +TESTPCAP="$srcdir/../../pcap/sample-rfc1035escape.pcap.gz" +../packetq -s "select qname from dns" --json "$TESTPCAP" > test8.out +../packetq -s "select qname from dns" --json --rfc1035 "$TESTPCAP" >> test8.out +../packetq -s "select qname from dns" --csv "$TESTPCAP" >> test8.out +../packetq -s "select qname from dns" --csv --rfc1035 "$TESTPCAP" >> test8.out + +diff -uw "$srcdir/test8.gold" test8.out diff --git a/src/variant.h b/src/variant.h new file mode 100644 index 0000000..7c20e04 --- /dev/null +++ b/src/variant.h @@ -0,0 +1,323 @@ +/* + * Copyright (c) 2017-2024 OARC, Inc. + * Copyright (c) 2011-2017, IIS - The Internet Foundation in Sweden + * All rights reserved. + * + * This file is part of PacketQ. + * + * PacketQ is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * PacketQ is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with PacketQ. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __packetq_variant_h +#define __packetq_variant_h + +#include <cstdlib> + +#include "MurmurHash3.h" +#include "refcountstring.h" + +namespace packetq { + +inline std::size_t hash_bytes(const char* bytes, int len) +{ + uint32_t result = 0; + MurmurHash3_x86_32(bytes, len, 0, &result); + return result; +} + +// must be defined in this order - see the "if" statement +#define COLTYPE_MAX 4 +namespace Coltype { + enum Type { + _bool = 0, + _int = 1, + _float = 2, + _text = 3, + }; +}; + +typedef bool bool_column; +static const int bool_size = sizeof(bool_column); +static const int bool_align = ((sizeof(bool_column) / sizeof(void*)) + 1) * sizeof(void*); + +typedef int int_column; +static const int int_size = sizeof(int_column); +static const int int_align = ((sizeof(int_column) / sizeof(void*)) + 1) * sizeof(void*); + +typedef double float_column; +static const int float_size = sizeof(float_column); +static const int float_align = ((sizeof(float_column) / sizeof(void*)) + 1) * sizeof(void*); + +typedef RefCountString* text_column; +static const int text_size = sizeof(text_column); +static const int text_align = ((sizeof(text_column) / sizeof(void*)) + 1) * sizeof(void*); + +inline bool_column convert_column_to_bool(float_column v) { return v; } +inline bool_column convert_column_to_bool(int_column v) { return v; } +inline bool_column convert_column_to_bool(bool_column v) { return v; } +inline bool_column convert_column_to_bool(text_column v) +{ + return std::atoi(v->data); +} + +inline int_column convert_column_to_int(float_column v) { return int(v); } +inline int_column convert_column_to_int(int_column v) { return v; } +inline int_column convert_column_to_int(bool_column v) { return v; } +inline int_column convert_column_to_int(text_column v) +{ + return v->data[0] != '\0'; +} + +inline float_column convert_column_to_float(float_column v) { return v; } +inline float_column convert_column_to_float(int_column v) { return v; } +inline float_column convert_column_to_float(bool_column v) { return v; } +inline float_column convert_column_to_float(text_column v) +{ + return std::atof(v->data); +} + +inline text_column convert_column_to_text(float_column v) +{ + const int bufsize = 50; + RefCountString* str = RefCountString::allocate(bufsize); + snprintf(str->data, bufsize, "%g", v); // lgtm[cpp/badly-bounded-write] + return str; +} +inline text_column convert_column_to_text(int_column v) +{ + const int bufsize = (sizeof(int_column) * 8 + 1) / 3 + 1; + RefCountString* str = RefCountString::allocate(bufsize); + snprintf(str->data, bufsize, "%d", v); // lgtm[cpp/badly-bounded-write] + return str; +} +inline text_column convert_column_to_text(bool_column v) +{ + const int bufsize = 1 + 1; + RefCountString* str = RefCountString::allocate(bufsize); + if (v) + str->data[0] = '1'; + else + str->data[1] = '0'; + str->data[1] = '\0'; + return str; +} +inline text_column convert_column_to_text(text_column v) +{ + // to stay symmetric with above functions that allocate a new string, + // increment reference count + v->inc_refcount(); + return v; +} + +// Variant represents a value that can be either one of the column types, +// plus a type field to figure out which kind it represents +class Variant { +public: + Variant() + { + m_type = Coltype::_int; + m_val.m_int = 0; + } + + Variant(bool_column val) + { + m_type = Coltype::_bool; + m_val.m_bool = val; + } + + Variant(int_column val) + { + m_type = Coltype::_int; + m_val.m_int = val; + } + + Variant(float_column val) + { + m_type = Coltype::_float; + m_val.m_float = val; + } + + Variant(text_column val) + { + m_type = Coltype::_text; + m_val.m_text = val; + m_val.m_text->inc_refcount(); + } + + Variant(const Variant& other) + { + m_type = other.m_type; + m_val = other.m_val; + if (m_type == Coltype::_text) + m_val.m_text->inc_refcount(); + } + + // move constructor + Variant(Variant&& other) + { + // would be cleaner to use default constructor, but alas + // constructor delegation requires GCC >= 4.7 + m_type = Coltype::_int; + m_val.m_int = 0; + + swap(*this, other); + } + + ~Variant() + { + if (m_type == Coltype::_text) + m_val.m_text->dec_refcount(); + } + + Variant& operator=(Variant other) + { + // copy and swap idiom + swap(*this, other); + return *this; + } + + inline friend void swap(Variant& first, Variant& second) + { + using std::swap; + swap(first.m_type, second.m_type); + swap(first.m_val, second.m_val); + } + + bool_column get_bool() const + { + switch (m_type) { + case Coltype::_float: + return convert_column_to_bool(m_val.m_float); + case Coltype::_int: + return convert_column_to_bool(m_val.m_int); + case Coltype::_bool: + return convert_column_to_bool(m_val.m_bool); + case Coltype::_text: + return convert_column_to_bool(m_val.m_text); + } + return false; + } + + int_column get_int() const + { + switch (m_type) { + case Coltype::_float: + return convert_column_to_int(m_val.m_float); + case Coltype::_int: + return convert_column_to_int(m_val.m_int); + case Coltype::_bool: + return convert_column_to_int(m_val.m_bool); + case Coltype::_text: + return convert_column_to_int(m_val.m_text); + } + return 0; + } + + float_column get_float() const + { + switch (m_type) { + case Coltype::_float: + return convert_column_to_float(m_val.m_float); + case Coltype::_int: + return convert_column_to_float(m_val.m_int); + case Coltype::_bool: + return convert_column_to_float(m_val.m_bool); + case Coltype::_text: + return convert_column_to_float(m_val.m_text); + } + return 0.0; + } + + // this returns a RefCountString with the ref-count incremented so + // caller is responsible for decrementing after use + text_column get_text() const + { + switch (m_type) { + case Coltype::_float: + return convert_column_to_text(m_val.m_float); + case Coltype::_int: + return convert_column_to_text(m_val.m_int); + case Coltype::_bool: + return convert_column_to_text(m_val.m_bool); + case Coltype::_text: + return convert_column_to_text(m_val.m_text); + } + return RefCountString::construct(""); + } + + int cmp(const Variant& rhs) const + { + switch (m_type) { + case (Coltype::_bool): + return m_val.m_bool - rhs.get_bool(); + case (Coltype::_int): + return m_val.m_int - rhs.get_int(); + case (Coltype::_float): { + float_column r = rhs.get_float(); + if (m_val.m_float < r) + return -1; + if (m_val.m_float > r) + return 1; + return 0; + } + case (Coltype::_text): { + RefCountString* s = rhs.get_text(); + auto res = strcmp(m_val.m_text->data, s->data); + s->dec_refcount(); + return res; + } + } + return 0; + } + + bool operator<(const Variant& rhs) const + { + return cmp(rhs) < 0; + } + bool operator==(const Variant& rhs) const + { + return cmp(rhs) == 0; + } + + std::size_t hash() const + { + switch (m_type) { + case (Coltype::_bool): + return std::hash<bool>()(m_val.m_bool); + case (Coltype::_int): + return std::hash<int>()(m_val.m_int); + case (Coltype::_float): + return std::hash<float>()(m_val.m_float); + case (Coltype::_text): + return hash_bytes(m_val.m_text->data, strlen(m_val.m_text->data)); + } + return 0; + } + + Coltype::Type m_type; + +private: + union VariantUnion { + bool_column m_bool; + int_column m_int; + float_column m_float; + text_column m_text; + }; + + VariantUnion m_val; +}; + +} // namespace packetq + +#endif // __packetq_variant_h |