diff options
author | Eduardo Chappa <echappa@gmx.com> | 2013-02-03 00:59:38 -0700 |
---|---|---|
committer | Eduardo Chappa <echappa@gmx.com> | 2013-02-03 00:59:38 -0700 |
commit | 094ca96844842928810f14844413109fc6cdd890 (patch) | |
tree | e60efbb980f38ba9308ccb4fb2b77b87bbc115f3 /regex | |
download | alpine-094ca96844842928810f14844413109fc6cdd890.tar.xz |
Initial Alpine Version
Diffstat (limited to 'regex')
-rw-r--r-- | regex/Makefile.am | 19 | ||||
-rw-r--r-- | regex/Makefile.in | 530 | ||||
-rw-r--r-- | regex/ReadMe | 39 | ||||
-rw-r--r-- | regex/cclass.h | 70 | ||||
-rw-r--r-- | regex/cname.h | 141 | ||||
-rw-r--r-- | regex/engine.c | 1053 | ||||
-rw-r--r-- | regex/makefile.wnt | 58 | ||||
-rw-r--r-- | regex/re_format.doc | 264 | ||||
-rw-r--r-- | regex/regcomp.c | 1621 | ||||
-rw-r--r-- | regex/regerror.c | 172 | ||||
-rw-r--r-- | regex/regex.doc | 462 | ||||
-rw-r--r-- | regex/regex.h | 117 | ||||
-rw-r--r-- | regex/regex2.h | 173 | ||||
-rw-r--r-- | regex/regexec.c | 176 | ||||
-rw-r--r-- | regex/regfree.c | 79 | ||||
-rw-r--r-- | regex/utils.h | 60 |
16 files changed, 5034 insertions, 0 deletions
diff --git a/regex/Makefile.am b/regex/Makefile.am new file mode 100644 index 00000000..78e7c197 --- /dev/null +++ b/regex/Makefile.am @@ -0,0 +1,19 @@ +## Process this file with automake to produce Makefile.in +## Use aclocal -I m4; automake + +# ======================================================================== +# Copyright 2006-2007 University of Washington +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# ======================================================================== + +noinst_LIBRARIES = libregex.a + +libregex_a_SOURCES = regcomp.c regerror.c regexec.c regfree.c + +AM_CPPFLAGS = -I@top_builddir@/include -I@top_srcdir@/include diff --git a/regex/Makefile.in b/regex/Makefile.in new file mode 100644 index 00000000..632bba20 --- /dev/null +++ b/regex/Makefile.in @@ -0,0 +1,530 @@ +# Makefile.in generated by automake 1.11.1 from Makefile.am. +# @configure_input@ + +# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, +# 2003, 2004, 2005, 2006, 2007, 2008, 2009 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 2006-2007 University of Washington +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# ======================================================================== + +VPATH = @srcdir@ +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 = regex +DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/m4/acx_pthread.m4 \ + $(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/iconv.m4 \ + $(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \ + $(top_srcdir)/m4/lib-prefix.m4 $(top_srcdir)/m4/libtool.m4 \ + $(top_srcdir)/m4/ltoptions.m4 $(top_srcdir)/m4/ltsugar.m4 \ + $(top_srcdir)/m4/ltversion.m4 $(top_srcdir)/m4/lt~obsolete.m4 \ + $(top_srcdir)/m4/nls.m4 $(top_srcdir)/m4/po.m4 \ + $(top_srcdir)/m4/progtest.m4 $(top_srcdir)/VERSION \ + $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs +CONFIG_HEADER = $(top_builddir)/include/config.h +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +LIBRARIES = $(noinst_LIBRARIES) +ARFLAGS = cru +libregex_a_AR = $(AR) $(ARFLAGS) +libregex_a_LIBADD = +am_libregex_a_OBJECTS = regcomp.$(OBJEXT) regerror.$(OBJEXT) \ + regexec.$(OBJEXT) regfree.$(OBJEXT) +libregex_a_OBJECTS = $(am_libregex_a_OBJECTS) +DEFAULT_INCLUDES = +depcomp = $(SHELL) $(top_srcdir)/depcomp +am__depfiles_maybe = depfiles +am__mv = mv -f +COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ + $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +LTCOMPILE = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \ + $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +CCLD = $(CC) +LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ + --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) \ + $(LDFLAGS) -o $@ +SOURCES = $(libregex_a_SOURCES) +DIST_SOURCES = $(libregex_a_SOURCES) +ETAGS = etags +CTAGS = ctags +DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_CFLAGS = @AM_CFLAGS@ +AM_LDFLAGS = @AM_LDFLAGS@ +AR = @AR@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CCDEPMODE = @CCDEPMODE@ +CFLAGS = @CFLAGS@ +CP = @CP@ +CPP = @CPP@ +CPPFLAGS = @CPPFLAGS@ +CYGPATH_W = @CYGPATH_W@ +C_CLIENT_CFLAGS = @C_CLIENT_CFLAGS@ +C_CLIENT_GCCOPTLEVEL = @C_CLIENT_GCCOPTLEVEL@ +C_CLIENT_LDFLAGS = @C_CLIENT_LDFLAGS@ +C_CLIENT_SPECIALS = @C_CLIENT_SPECIALS@ +C_CLIENT_TARGET = @C_CLIENT_TARGET@ +C_CLIENT_WITH_IPV6 = @C_CLIENT_WITH_IPV6@ +DEFS = @DEFS@ +DEPDIR = @DEPDIR@ +DSYMUTIL = @DSYMUTIL@ +DUMPBIN = @DUMPBIN@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EGREP = @EGREP@ +EXEEXT = @EXEEXT@ +FGREP = @FGREP@ +GMSGFMT = @GMSGFMT@ +GMSGFMT_015 = @GMSGFMT_015@ +GREP = @GREP@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +INTLLIBS = @INTLLIBS@ +INTL_MACOSX_LIBS = @INTL_MACOSX_LIBS@ +ISPELLPROG = @ISPELLPROG@ +LD = @LD@ +LDFLAGS = @LDFLAGS@ +LIBICONV = @LIBICONV@ +LIBINTL = @LIBINTL@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LIBTOOL = @LIBTOOL@ +LIPO = @LIPO@ +LN = @LN@ +LN_S = @LN_S@ +LTLIBICONV = @LTLIBICONV@ +LTLIBINTL = @LTLIBINTL@ +LTLIBOBJS = @LTLIBOBJS@ +MAINT = @MAINT@ +MAKE = @MAKE@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +MSGFMT = @MSGFMT@ +MSGFMT_015 = @MSGFMT_015@ +MSGMERGE = @MSGMERGE@ +NM = @NM@ +NMEDIT = @NMEDIT@ +NPA_PROG = @NPA_PROG@ +OBJDUMP = @OBJDUMP@ +OBJEXT = @OBJEXT@ +OTOOL = @OTOOL@ +OTOOL64 = @OTOOL64@ +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@ +POSUB = @POSUB@ +PTHREAD_CC = @PTHREAD_CC@ +PTHREAD_CFLAGS = @PTHREAD_CFLAGS@ +PTHREAD_LIBS = @PTHREAD_LIBS@ +PWPROG = @PWPROG@ +RANLIB = @RANLIB@ +REGEX_BUILD = @REGEX_BUILD@ +RM = @RM@ +SED = @SED@ +SENDMAIL = @SENDMAIL@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +SPELLPROG = @SPELLPROG@ +STRIP = @STRIP@ +USE_NLS = @USE_NLS@ +VERSION = @VERSION@ +WEB_BINDIR = @WEB_BINDIR@ +WEB_BUILD = @WEB_BUILD@ +WEB_PUBCOOKIE_BUILD = @WEB_PUBCOOKIE_BUILD@ +WEB_PUBCOOKIE_LIB = @WEB_PUBCOOKIE_LIB@ +WEB_PUBCOOKIE_LINK = @WEB_PUBCOOKIE_LINK@ +XGETTEXT = @XGETTEXT@ +XGETTEXT_015 = @XGETTEXT_015@ +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_DUMPBIN = @ac_ct_DUMPBIN@ +acx_pthread_config = @acx_pthread_config@ +alpine_interactive_spellcheck = @alpine_interactive_spellcheck@ +alpine_simple_spellcheck = @alpine_simple_spellcheck@ +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@ +localedir = @localedir@ +localstatedir = @localstatedir@ +lt_ECHO = @lt_ECHO@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +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@ +noinst_LIBRARIES = libregex.a +libregex_a_SOURCES = regcomp.c regerror.c regexec.c regfree.c +AM_CPPFLAGS = -I@top_builddir@/include -I@top_srcdir@/include +all: all-am + +.SUFFIXES: +.SUFFIXES: .c .lo .o .obj +$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(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 regex/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --foreign regex/Makefile +.PRECIOUS: 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__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): + +clean-noinstLIBRARIES: + -test -z "$(noinst_LIBRARIES)" || rm -f $(noinst_LIBRARIES) +libregex.a: $(libregex_a_OBJECTS) $(libregex_a_DEPENDENCIES) + -rm -f libregex.a + $(libregex_a_AR) libregex.a $(libregex_a_OBJECTS) $(libregex_a_LIBADD) + $(RANLIB) libregex.a + +mostlyclean-compile: + -rm -f *.$(OBJEXT) + +distclean-compile: + -rm -f *.tab.c + +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regcomp.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regerror.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regexec.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regfree.Po@am__quote@ + +.c.o: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c $< + +.c.obj: +@am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ `$(CYGPATH_W) '$<'` +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(COMPILE) -c `$(CYGPATH_W) '$<'` + +.c.lo: +@am__fastdepCC_TRUE@ $(LTCOMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/$*.Tpo $(DEPDIR)/$*.Plo +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='$<' object='$@' libtool=yes @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(LTCOMPILE) -c -o $@ $< + +mostlyclean-libtool: + -rm -f *.lo + +clean-libtool: + -rm -rf .libs _libs + +ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES) + list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) '{ files[$$0] = 1; nonempty = 1; } \ + END { if (nonempty) { for (i in files) print i; }; }'`; \ + mkid -fID $$unique +tags: TAGS + +TAGS: $(HEADERS) $(SOURCES) $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + set x; \ + here=`pwd`; \ + list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) '{ files[$$0] = 1; nonempty = 1; } \ + END { if (nonempty) { for (i in files) print i; }; }'`; \ + shift; \ + if test -z "$(ETAGS_ARGS)$$*$$unique"; then :; else \ + test -n "$$unique" || unique=$$empty_fix; \ + if test $$# -gt 0; then \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + "$$@" $$unique; \ + else \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + $$unique; \ + fi; \ + fi +ctags: CTAGS +CTAGS: $(HEADERS) $(SOURCES) $(TAGS_DEPENDENCIES) \ + $(TAGS_FILES) $(LISP) + list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | \ + $(AWK) '{ files[$$0] = 1; nonempty = 1; } \ + END { if (nonempty) { for (i in files) print i; }; }'`; \ + 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) "$$here" + +distclean-tags: + -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags + +distdir: $(DISTFILES) + @srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*]/\\\\&/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 +check: check-am +all-am: Makefile $(LIBRARIES) +installdirs: +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + `test -z '$(STRIP)' || \ + echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install +mostlyclean-generic: + +clean-generic: + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." +clean: clean-am + +clean-am: clean-generic clean-libtool clean-noinstLIBRARIES \ + mostlyclean-am + +distclean: distclean-am + -rm -rf ./$(DEPDIR) + -rm -f Makefile +distclean-am: clean-am distclean-compile distclean-generic \ + distclean-tags + +dvi: dvi-am + +dvi-am: + +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 -rf ./$(DEPDIR) + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-compile mostlyclean-generic \ + mostlyclean-libtool + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: + +.MAKE: install-am install-strip + +.PHONY: CTAGS GTAGS all all-am check check-am clean clean-generic \ + clean-libtool clean-noinstLIBRARIES ctags distclean \ + distclean-compile distclean-generic distclean-libtool \ + distclean-tags distdir dvi dvi-am html html-am info info-am \ + install install-am install-data install-data-am install-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-compile mostlyclean-generic mostlyclean-libtool \ + pdf pdf-am ps ps-am tags uninstall uninstall-am + + +# 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/regex/ReadMe b/regex/ReadMe new file mode 100644 index 00000000..992581b8 --- /dev/null +++ b/regex/ReadMe @@ -0,0 +1,39 @@ +The only changes to the source files here are changes to +keep the more picky modern compilers happy. + +The code in this directory is + + Copyright (c) 1992 Henry Spencer. + Copyright (c) 1992, 1993 + The Regents of the University of California. All rights reserved. + + This code is derived from software contributed to Berkeley by + Henry Spencer of the University of Toronto. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + 2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + 3. All advertising materials mentioning features or use of this software + must display the following acknowledgement: + This product includes software developed by the University of + California, Berkeley and its contributors. + 4. Neither the name of the University nor the names of its contributors + may be used to endorse or promote products derived from this software + without specific prior written permission. + + THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + SUCH DAMAGE. diff --git a/regex/cclass.h b/regex/cclass.h new file mode 100644 index 00000000..cabe7faf --- /dev/null +++ b/regex/cclass.h @@ -0,0 +1,70 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)cclass.h 8.3 (Berkeley) 3/20/94 + */ + +/* character-class table */ +static struct cclass { + char *name; + char *chars; + char *multis; +} cclasses[] = { + {"alnum", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\ +0123456789", ""}, + {"alpha", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz", + ""}, + {"blank", " \t", ""}, + {"cntrl", "\007\b\t\n\v\f\r\1\2\3\4\5\6\16\17\20\21\22\23\24\ +\25\26\27\30\31\32\33\34\35\36\37\177", ""}, + {"digit", "0123456789", ""}, + {"graph", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\ +0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~", + ""}, + {"lower", "abcdefghijklmnopqrstuvwxyz", + ""}, + {"print", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\ +0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~ ", + ""}, + {"punct", "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~", + ""}, + {"space", "\t\n\v\f\r ", ""}, + {"upper", "ABCDEFGHIJKLMNOPQRSTUVWXYZ", + ""}, + {"xdigit", "0123456789ABCDEFabcdef", + ""}, + {NULL, 0, ""} +}; diff --git a/regex/cname.h b/regex/cname.h new file mode 100644 index 00000000..c6ba15bd --- /dev/null +++ b/regex/cname.h @@ -0,0 +1,141 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)cname.h 8.3 (Berkeley) 3/20/94 + */ + +/* character-name table */ +static struct cname { + char *name; + char code; +} cnames[] = { + {"NUL", '\0'}, + {"SOH", '\001'}, + {"STX", '\002'}, + {"ETX", '\003'}, + {"EOT", '\004'}, + {"ENQ", '\005'}, + {"ACK", '\006'}, + {"BEL", '\007'}, + {"alert", '\007'}, + {"BS", '\010'}, + {"backspace", '\b'}, + {"HT", '\011'}, + {"tab", '\t'}, + {"LF", '\012'}, + {"newline", '\n'}, + {"VT", '\013'}, + {"vertical-tab", '\v'}, + {"FF", '\014'}, + {"form-feed", '\f'}, + {"CR", '\015'}, + {"carriage-return", '\r'}, + {"SO", '\016'}, + {"SI", '\017'}, + {"DLE", '\020'}, + {"DC1", '\021'}, + {"DC2", '\022'}, + {"DC3", '\023'}, + {"DC4", '\024'}, + {"NAK", '\025'}, + {"SYN", '\026'}, + {"ETB", '\027'}, + {"CAN", '\030'}, + {"EM", '\031'}, + {"SUB", '\032'}, + {"ESC", '\033'}, + {"IS4", '\034'}, + {"FS", '\034'}, + {"IS3", '\035'}, + {"GS", '\035'}, + {"IS2", '\036'}, + {"RS", '\036'}, + {"IS1", '\037'}, + {"US", '\037'}, + {"space", ' '}, + {"exclamation-mark", '!'}, + {"quotation-mark", '"'}, + {"number-sign", '#'}, + {"dollar-sign", '$'}, + {"percent-sign", '%'}, + {"ampersand", '&'}, + {"apostrophe", '\''}, + {"left-parenthesis", '('}, + {"right-parenthesis", ')'}, + {"asterisk", '*'}, + {"plus-sign", '+'}, + {"comma", ','}, + {"hyphen", '-'}, + {"hyphen-minus", '-'}, + {"period", '.'}, + {"full-stop", '.'}, + {"slash", '/'}, + {"solidus", '/'}, + {"zero", '0'}, + {"one", '1'}, + {"two", '2'}, + {"three", '3'}, + {"four", '4'}, + {"five", '5'}, + {"six", '6'}, + {"seven", '7'}, + {"eight", '8'}, + {"nine", '9'}, + {"colon", ':'}, + {"semicolon", ';'}, + {"less-than-sign", '<'}, + {"equals-sign", '='}, + {"greater-than-sign", '>'}, + {"question-mark", '?'}, + {"commercial-at", '@'}, + {"left-square-bracket", '['}, + {"backslash", '\\'}, + {"reverse-solidus", '\\'}, + {"right-square-bracket", ']'}, + {"circumflex", '^'}, + {"circumflex-accent", '^'}, + {"underscore", '_'}, + {"low-line", '_'}, + {"grave-accent", '`'}, + {"left-brace", '{'}, + {"left-curly-bracket", '{'}, + {"vertical-line", '|'}, + {"right-brace", '}'}, + {"right-curly-bracket", '}'}, + {"tilde", '~'}, + {"DEL", '\177'}, + {NULL, 0} +}; diff --git a/regex/engine.c b/regex/engine.c new file mode 100644 index 00000000..e9bb5d4b --- /dev/null +++ b/regex/engine.c @@ -0,0 +1,1053 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)engine.c 8.5 (Berkeley) 3/20/94 + */ + +/* + * The matching engine and friends. This file is #included by regexec.c + * after suitable #defines of a variety of macros used herein, so that + * different state representations can be used without duplicating masses + * of code. + */ + +#ifdef SNAMES +#define matcher smatcher +#define fast sfast +#define slow sslow +#define dissect sdissect +#define backref sbackref +#define step sstep +#define print sprint +#define at sat +#define match smat +#endif +#ifdef LNAMES +#define matcher lmatcher +#define fast lfast +#define slow lslow +#define dissect ldissect +#define backref lbackref +#define step lstep +#define print lprint +#define at lat +#define match lmat +#endif + +/* another structure passed up and down to avoid zillions of parameters */ +struct match { + struct re_guts *g; + int eflags; + regmatch_t *pmatch; /* [nsub+1] (0 element unused) */ + char *offp; /* offsets work from here */ + char *beginp; /* start of string -- virtual NUL precedes */ + char *endp; /* end of string -- virtual NUL here */ + char *coldp; /* can be no match starting before here */ + char **lastpos; /* [nplus+1] */ + STATEVARS; + states st; /* current states */ + states fresh; /* states for a fresh start */ + states tmp; /* temporary */ + states empty; /* empty set of states */ +}; + +/* ========= begin header generated by ./mkh ========= */ +#ifdef __cplusplus +extern "C" { +#endif + +/* === engine.c === */ +static int matcher __P((struct re_guts *g, char *string, size_t nmatch, regmatch_t pmatch[], int eflags)); +static char *dissect __P((struct match *m, char *start, char *stop, sopno startst, sopno stopst)); +static char *backref __P((struct match *m, char *start, char *stop, sopno startst, sopno stopst, sopno lev)); +static char *fast __P((struct match *m, char *start, char *stop, sopno startst, sopno stopst)); +static char *slow __P((struct match *m, char *start, char *stop, sopno startst, sopno stopst)); +static states step __P((struct re_guts *g, sopno start, sopno stop, states bef, int ch, states aft)); +#define BOL (OUT+1) +#define EOL (BOL+1) +#define BOLEOL (BOL+2) +#define NOTHING (BOL+3) +#define BOW (BOL+4) +#define EOW (BOL+5) +#define CODEMAX (BOL+5) /* highest code used */ +#define NONCHAR(c) ((c) > CHAR_MAX) +#define NNONCHAR (CODEMAX-CHAR_MAX) +#ifdef REDEBUG +static void print __P((struct match *m, char *caption, states st, int ch, FILE *d)); +#endif +#ifdef REDEBUG +static void at __P((struct match *m, char *title, char *start, char *stop, sopno startst, sopno stopst)); +#endif +#ifdef REDEBUG +static char *pchar __P((int ch)); +#endif + +#ifdef __cplusplus +} +#endif +/* ========= end header generated by ./mkh ========= */ + +#ifdef REDEBUG +#define SP(t, s, c) print(m, t, s, c, stdout) +#define AT(t, p1, p2, s1, s2) at(m, t, p1, p2, s1, s2) +#define NOTE(str) { if (m->eflags®_TRACE) printf("=%s\n", (str)); } +#else +#define SP(t, s, c) /* nothing */ +#define AT(t, p1, p2, s1, s2) /* nothing */ +#define NOTE(s) /* nothing */ +#endif + +/* + - matcher - the actual matching engine + == static int matcher(register struct re_guts *g, char *string, \ + == size_t nmatch, regmatch_t pmatch[], int eflags); + */ +static int /* 0 success, REG_NOMATCH failure */ +matcher(struct re_guts *g, char *string, size_t nmatch, regmatch_t pmatch[], int eflags) +{ + register char *endp; + register int i; + struct match mv; + register struct match *m = &mv; + register char *dp; + const register sopno gf = g->firststate+1; /* +1 for OEND */ + const register sopno gl = g->laststate; + char *start; + char *stop; + + /* simplify the situation where possible */ + if (g->cflags®_NOSUB) + nmatch = 0; + if (eflags®_STARTEND) { + start = string + pmatch[0].rm_so; + stop = string + pmatch[0].rm_eo; + } else { + start = string; + stop = start + strlen(start); + } + if (stop < start) + return(REG_INVARG); + + /* prescreening; this does wonders for this rather slow code */ + if (g->must != NULL) { + for (dp = start; dp < stop; dp++) + if (*dp == g->must[0] && stop - dp >= g->mlen && + memcmp(dp, g->must, (size_t)g->mlen) == 0) + break; + if (dp == stop) /* we didn't find g->must */ + return(REG_NOMATCH); + } + + /* match struct setup */ + m->g = g; + m->eflags = eflags; + m->pmatch = NULL; + m->lastpos = NULL; + m->offp = string; + m->beginp = start; + m->endp = stop; + STATESETUP(m, 4); + SETUP(m->st); + SETUP(m->fresh); + SETUP(m->tmp); + SETUP(m->empty); + CLEAR(m->empty); + + /* this loop does only one repetition except for backrefs */ + for (;;) { + endp = fast(m, start, stop, gf, gl); + if (endp == NULL) { /* a miss */ + STATETEARDOWN(m); + return(REG_NOMATCH); + } + if (nmatch == 0 && !g->backrefs) + break; /* no further info needed */ + + /* where? */ + assert(m->coldp != NULL); + for (;;) { + NOTE("finding start"); + endp = slow(m, m->coldp, stop, gf, gl); + if (endp != NULL) + break; + assert(m->coldp < m->endp); + m->coldp++; + } + if (nmatch == 1 && !g->backrefs) + break; /* no further info needed */ + + /* oh my, he wants the subexpressions... */ + if (m->pmatch == NULL) + m->pmatch = (regmatch_t *)malloc((m->g->nsub + 1) * + sizeof(regmatch_t)); + if (m->pmatch == NULL) { + STATETEARDOWN(m); + return(REG_ESPACE); + } + for (i = 1; i <= m->g->nsub; i++) + m->pmatch[i].rm_so = m->pmatch[i].rm_eo = -1; + if (!g->backrefs && !(m->eflags®_BACKR)) { + NOTE("dissecting"); + dp = dissect(m, m->coldp, endp, gf, gl); + } else { + if (g->nplus > 0 && m->lastpos == NULL) + m->lastpos = (char **)malloc((g->nplus+1) * + sizeof(char *)); + if (g->nplus > 0 && m->lastpos == NULL) { + free(m->pmatch); + STATETEARDOWN(m); + return(REG_ESPACE); + } + NOTE("backref dissect"); + dp = backref(m, m->coldp, endp, gf, gl, (sopno)0); + } + if (dp != NULL) + break; + + /* uh-oh... we couldn't find a subexpression-level match */ + assert(g->backrefs); /* must be back references doing it */ + assert(g->nplus == 0 || m->lastpos != NULL); + for (;;) { + if (dp != NULL || endp <= m->coldp) + break; /* defeat */ + NOTE("backoff"); + endp = slow(m, m->coldp, endp-1, gf, gl); + if (endp == NULL) + break; /* defeat */ + /* try it on a shorter possibility */ +#ifndef NDEBUG + for (i = 1; i <= m->g->nsub; i++) { + assert(m->pmatch[i].rm_so == -1); + assert(m->pmatch[i].rm_eo == -1); + } +#endif + NOTE("backoff dissect"); + dp = backref(m, m->coldp, endp, gf, gl, (sopno)0); + } + assert(dp == NULL || dp == endp); + if (dp != NULL) /* found a shorter one */ + break; + + /* despite initial appearances, there is no match here */ + NOTE("false alarm"); + start = m->coldp + 1; /* recycle starting later */ + assert(start <= stop); + } + + /* fill in the details if requested */ + if (nmatch > 0) { + pmatch[0].rm_so = m->coldp - m->offp; + pmatch[0].rm_eo = endp - m->offp; + } + if (nmatch > 1) { + assert(m->pmatch != NULL); + for (i = 1; i < nmatch; i++) + if (i <= m->g->nsub) + pmatch[i] = m->pmatch[i]; + else { + pmatch[i].rm_so = -1; + pmatch[i].rm_eo = -1; + } + } + + if (m->pmatch != NULL) + free((char *)m->pmatch); + if (m->lastpos != NULL) + free((char *)m->lastpos); + STATETEARDOWN(m); + return(0); +} + +/* + - dissect - figure out what matched what, no back references + == static char *dissect(register struct match *m, char *start, \ + == char *stop, sopno startst, sopno stopst); + */ +static char * /* == stop (success) always */ +dissect(struct match *m, char *start, char *stop, sopno startst, sopno stopst) +{ + register int i; + register sopno ss; /* start sop of current subRE */ + register sopno es; /* end sop of current subRE */ + register char *sp; /* start of string matched by it */ + register char *stp; /* string matched by it cannot pass here */ + register char *rest; /* start of rest of string */ + register char *tail; /* string unmatched by rest of RE */ + register sopno ssub; /* start sop of subsubRE */ + register sopno esub; /* end sop of subsubRE */ + register char *ssp; /* start of string matched by subsubRE */ + register char *sep; /* end of string matched by subsubRE */ + register char *oldssp; /* previous ssp */ + register char *dp; + + AT("diss", start, stop, startst, stopst); + sp = start; + for (ss = startst; ss < stopst; ss = es) { + /* identify end of subRE */ + es = ss; + switch (OP(m->g->strip[es])) { + case OPLUS_: + case OQUEST_: + es += OPND(m->g->strip[es]); + break; + case OCH_: + while (OP(m->g->strip[es]) != O_CH) + es += OPND(m->g->strip[es]); + break; + } + es++; + + /* figure out what it matched */ + switch (OP(m->g->strip[ss])) { + case OEND: + assert(nope); + break; + case OCHAR: + sp++; + break; + case OBOL: + case OEOL: + case OBOW: + case OEOW: + break; + case OANY: + case OANYOF: + sp++; + break; + case OBACK_: + case O_BACK: + assert(nope); + break; + /* cases where length of match is hard to find */ + case OQUEST_: + stp = stop; + for (;;) { + /* how long could this one be? */ + rest = slow(m, sp, stp, ss, es); + assert(rest != NULL); /* it did match */ + /* could the rest match the rest? */ + tail = slow(m, rest, stop, es, stopst); + if (tail == stop) + break; /* yes! */ + /* no -- try a shorter match for this one */ + stp = rest - 1; + assert(stp >= sp); /* it did work */ + } + ssub = ss + 1; + esub = es - 1; + /* did innards match? */ + if (slow(m, sp, rest, ssub, esub) != NULL) { + dp = dissect(m, sp, rest, ssub, esub); + assert(dp == rest); + } else /* no */ + assert(sp == rest); + sp = rest; + break; + case OPLUS_: + stp = stop; + for (;;) { + /* how long could this one be? */ + rest = slow(m, sp, stp, ss, es); + assert(rest != NULL); /* it did match */ + /* could the rest match the rest? */ + tail = slow(m, rest, stop, es, stopst); + if (tail == stop) + break; /* yes! */ + /* no -- try a shorter match for this one */ + stp = rest - 1; + assert(stp >= sp); /* it did work */ + } + ssub = ss + 1; + esub = es - 1; + ssp = sp; + oldssp = ssp; + for (;;) { /* find last match of innards */ + sep = slow(m, ssp, rest, ssub, esub); + if (sep == NULL || sep == ssp) + break; /* failed or matched null */ + oldssp = ssp; /* on to next try */ + ssp = sep; + } + if (sep == NULL) { + /* last successful match */ + sep = ssp; + ssp = oldssp; + } + assert(sep == rest); /* must exhaust substring */ + assert(slow(m, ssp, sep, ssub, esub) == rest); + dp = dissect(m, ssp, sep, ssub, esub); + assert(dp == sep); + sp = rest; + break; + case OCH_: + stp = stop; + for (;;) { + /* how long could this one be? */ + rest = slow(m, sp, stp, ss, es); + assert(rest != NULL); /* it did match */ + /* could the rest match the rest? */ + tail = slow(m, rest, stop, es, stopst); + if (tail == stop) + break; /* yes! */ + /* no -- try a shorter match for this one */ + stp = rest - 1; + assert(stp >= sp); /* it did work */ + } + ssub = ss + 1; + esub = ss + OPND(m->g->strip[ss]) - 1; + assert(OP(m->g->strip[esub]) == OOR1); + for (;;) { /* find first matching branch */ + if (slow(m, sp, rest, ssub, esub) == rest) + break; /* it matched all of it */ + /* that one missed, try next one */ + assert(OP(m->g->strip[esub]) == OOR1); + esub++; + assert(OP(m->g->strip[esub]) == OOR2); + ssub = esub + 1; + esub += OPND(m->g->strip[esub]); + if (OP(m->g->strip[esub]) == OOR2) + esub--; + else + assert(OP(m->g->strip[esub]) == O_CH); + } + dp = dissect(m, sp, rest, ssub, esub); + assert(dp == rest); + sp = rest; + break; + case O_PLUS: + case O_QUEST: + case OOR1: + case OOR2: + case O_CH: + assert(nope); + break; + case OLPAREN: + i = OPND(m->g->strip[ss]); + assert(0 < i && i <= m->g->nsub); + m->pmatch[i].rm_so = sp - m->offp; + break; + case ORPAREN: + i = OPND(m->g->strip[ss]); + assert(0 < i && i <= m->g->nsub); + m->pmatch[i].rm_eo = sp - m->offp; + break; + default: /* uh oh */ + assert(nope); + break; + } + } + + assert(sp == stop); + return(sp); +} + +/* + - backref - figure out what matched what, figuring in back references + == static char *backref(register struct match *m, char *start, \ + == char *stop, sopno startst, sopno stopst, sopno lev); + */ +static char * /* == stop (success) or NULL (failure) */ +backref(struct match *m, char *start, char *stop, sopno startst, sopno stopst, sopno lev) +{ + register int i; + register sopno ss; /* start sop of current subRE */ + register char *sp; /* start of string matched by it */ + register sopno ssub; /* start sop of subsubRE */ + register sopno esub; /* end sop of subsubRE */ + register char *ssp; /* start of string matched by subsubRE */ + register char *dp; + register size_t len; + register int hard; + register sop s; + register regoff_t offsave; + register cset *cs; + + AT("back", start, stop, startst, stopst); + sp = start; + + /* get as far as we can with easy stuff */ + hard = 0; + for (ss = startst; !hard && ss < stopst; ss++) + switch (OP(s = m->g->strip[ss])) { + case OCHAR: + if (sp == stop || *sp++ != (char)OPND(s)) + return(NULL); + break; + case OANY: + if (sp == stop) + return(NULL); + sp++; + break; + case OANYOF: + cs = &m->g->sets[OPND(s)]; + if (sp == stop || !CHIN(cs, *sp++)) + return(NULL); + break; + case OBOL: + if ( (sp == m->beginp && !(m->eflags®_NOTBOL)) || + (sp < m->endp && *(sp-1) == '\n' && + (m->g->cflags®_NEWLINE)) ) + { /* yes */ } + else + return(NULL); + break; + case OEOL: + if ( (sp == m->endp && !(m->eflags®_NOTEOL)) || + (sp < m->endp && *sp == '\n' && + (m->g->cflags®_NEWLINE)) ) + { /* yes */ } + else + return(NULL); + break; + case OBOW: + if (( (sp == m->beginp && !(m->eflags®_NOTBOL)) || + (sp < m->endp && *(sp-1) == '\n' && + (m->g->cflags®_NEWLINE)) || + (sp > m->beginp && + !ISWORD(*(sp-1))) ) && + (sp < m->endp && ISWORD(*sp)) ) + { /* yes */ } + else + return(NULL); + break; + case OEOW: + if (( (sp == m->endp && !(m->eflags®_NOTEOL)) || + (sp < m->endp && *sp == '\n' && + (m->g->cflags®_NEWLINE)) || + (sp < m->endp && !ISWORD(*sp)) ) && + (sp > m->beginp && ISWORD(*(sp-1))) ) + { /* yes */ } + else + return(NULL); + break; + case O_QUEST: + break; + case OOR1: /* matches null but needs to skip */ + ss++; + s = m->g->strip[ss]; + do { + assert(OP(s) == OOR2); + ss += OPND(s); + } while (OP(s = m->g->strip[ss]) != O_CH); + /* note that the ss++ gets us past the O_CH */ + break; + default: /* have to make a choice */ + hard = 1; + break; + } + if (!hard) { /* that was it! */ + if (sp != stop) + return(NULL); + return(sp); + } + ss--; /* adjust for the for's final increment */ + + /* the hard stuff */ + AT("hard", sp, stop, ss, stopst); + s = m->g->strip[ss]; + switch (OP(s)) { + case OBACK_: /* the vilest depths */ + i = OPND(s); + assert(0 < i && i <= m->g->nsub); + if (m->pmatch[i].rm_eo == -1) + return(NULL); + assert(m->pmatch[i].rm_so != -1); + len = m->pmatch[i].rm_eo - m->pmatch[i].rm_so; + assert(stop - m->beginp >= len); + if (sp > stop - len) + return(NULL); /* not enough left to match */ + ssp = m->offp + m->pmatch[i].rm_so; + if (memcmp(sp, ssp, len) != 0) + return(NULL); + while (m->g->strip[ss] != SOP(O_BACK, i)) + ss++; + return(backref(m, sp+len, stop, ss+1, stopst, lev)); + break; + case OQUEST_: /* to null or not */ + dp = backref(m, sp, stop, ss+1, stopst, lev); + if (dp != NULL) + return(dp); /* not */ + return(backref(m, sp, stop, ss+OPND(s)+1, stopst, lev)); + break; + case OPLUS_: + assert(m->lastpos != NULL); + assert(lev+1 <= m->g->nplus); + m->lastpos[lev+1] = sp; + return(backref(m, sp, stop, ss+1, stopst, lev+1)); + break; + case O_PLUS: + if (sp == m->lastpos[lev]) /* last pass matched null */ + return(backref(m, sp, stop, ss+1, stopst, lev-1)); + /* try another pass */ + m->lastpos[lev] = sp; + dp = backref(m, sp, stop, ss-OPND(s)+1, stopst, lev); + if (dp == NULL) + return(backref(m, sp, stop, ss+1, stopst, lev-1)); + else + return(dp); + break; + case OCH_: /* find the right one, if any */ + ssub = ss + 1; + esub = ss + OPND(s) - 1; + assert(OP(m->g->strip[esub]) == OOR1); + for (;;) { /* find first matching branch */ + dp = backref(m, sp, stop, ssub, esub, lev); + if (dp != NULL) + return(dp); + /* that one missed, try next one */ + if (OP(m->g->strip[esub]) == O_CH) + return(NULL); /* there is none */ + esub++; + assert(OP(m->g->strip[esub]) == OOR2); + ssub = esub + 1; + esub += OPND(m->g->strip[esub]); + if (OP(m->g->strip[esub]) == OOR2) + esub--; + else + assert(OP(m->g->strip[esub]) == O_CH); + } + break; + case OLPAREN: /* must undo assignment if rest fails */ + i = OPND(s); + assert(0 < i && i <= m->g->nsub); + offsave = m->pmatch[i].rm_so; + m->pmatch[i].rm_so = sp - m->offp; + dp = backref(m, sp, stop, ss+1, stopst, lev); + if (dp != NULL) + return(dp); + m->pmatch[i].rm_so = offsave; + return(NULL); + break; + case ORPAREN: /* must undo assignment if rest fails */ + i = OPND(s); + assert(0 < i && i <= m->g->nsub); + offsave = m->pmatch[i].rm_eo; + m->pmatch[i].rm_eo = sp - m->offp; + dp = backref(m, sp, stop, ss+1, stopst, lev); + if (dp != NULL) + return(dp); + m->pmatch[i].rm_eo = offsave; + return(NULL); + break; + default: /* uh oh */ + assert(nope); + break; + } + + /* "can't happen" */ + assert(nope); + /* NOTREACHED */ + return(NULL); +} + +/* + - fast - step through the string at top speed + == static char *fast(register struct match *m, char *start, \ + == char *stop, sopno startst, sopno stopst); + */ +static char * /* where tentative match ended, or NULL */ +fast(struct match *m, char *start, char *stop, sopno startst, sopno stopst) +{ + register states st = m->st; + register states fresh = m->fresh; + register states tmp = m->tmp; + register char *p = start; + register int c = (start == m->beginp) ? OUT : *(start-1); + register int lastc; /* previous c */ + register int flagch; + register int i; + register char *coldp; /* last p after which no match was underway */ + + CLEAR(st); + SET1(st, startst); + st = step(m->g, startst, stopst, st, NOTHING, st); + ASSIGN(fresh, st); + SP("start", st, *p); + coldp = NULL; + for (;;) { + /* next character */ + lastc = c; + c = (p == m->endp) ? OUT : *p; + if (EQ(st, fresh)) + coldp = p; + + /* is there an EOL and/or BOL between lastc and c? */ + flagch = '\0'; + i = 0; + if ( (lastc == '\n' && m->g->cflags®_NEWLINE) || + (lastc == OUT && !(m->eflags®_NOTBOL)) ) { + flagch = BOL; + i = m->g->nbol; + } + if ( (c == '\n' && m->g->cflags®_NEWLINE) || + (c == OUT && !(m->eflags®_NOTEOL)) ) { + flagch = (flagch == BOL) ? BOLEOL : EOL; + i += m->g->neol; + } + if (i != 0) { + for (; i > 0; i--) + st = step(m->g, startst, stopst, st, flagch, st); + SP("boleol", st, c); + } + + /* how about a word boundary? */ + if ( (flagch == BOL || (lastc != OUT && !ISWORD(lastc))) && + (c != OUT && ISWORD(c)) ) { + flagch = BOW; + } + if ( (lastc != OUT && ISWORD(lastc)) && + (flagch == EOL || (c != OUT && !ISWORD(c))) ) { + flagch = EOW; + } + if (flagch == BOW || flagch == EOW) { + st = step(m->g, startst, stopst, st, flagch, st); + SP("boweow", st, c); + } + + /* are we done? */ + if (ISSET(st, stopst) || p == stop) + break; /* NOTE BREAK OUT */ + + /* no, we must deal with this character */ + ASSIGN(tmp, st); + ASSIGN(st, fresh); + assert(c != OUT); + st = step(m->g, startst, stopst, tmp, c, st); + SP("aft", st, c); + assert(EQ(step(m->g, startst, stopst, st, NOTHING, st), st)); + p++; + } + + assert(coldp != NULL); + m->coldp = coldp; + if (ISSET(st, stopst)) + return(p+1); + else + return(NULL); +} + +/* + - slow - step through the string more deliberately + == static char *slow(register struct match *m, char *start, \ + == char *stop, sopno startst, sopno stopst); + */ +static char * /* where it ended */ +slow(struct match *m, char *start, char *stop, sopno startst, sopno stopst) +{ + register states st = m->st; + register states empty = m->empty; + register states tmp = m->tmp; + register char *p = start; + register int c = (start == m->beginp) ? OUT : *(start-1); + register int lastc; /* previous c */ + register int flagch; + register int i; + register char *matchp; /* last p at which a match ended */ + + AT("slow", start, stop, startst, stopst); + CLEAR(st); + SET1(st, startst); + SP("sstart", st, *p); + st = step(m->g, startst, stopst, st, NOTHING, st); + matchp = NULL; + for (;;) { + /* next character */ + lastc = c; + c = (p == m->endp) ? OUT : *p; + + /* is there an EOL and/or BOL between lastc and c? */ + flagch = '\0'; + i = 0; + if ( (lastc == '\n' && m->g->cflags®_NEWLINE) || + (lastc == OUT && !(m->eflags®_NOTBOL)) ) { + flagch = BOL; + i = m->g->nbol; + } + if ( (c == '\n' && m->g->cflags®_NEWLINE) || + (c == OUT && !(m->eflags®_NOTEOL)) ) { + flagch = (flagch == BOL) ? BOLEOL : EOL; + i += m->g->neol; + } + if (i != 0) { + for (; i > 0; i--) + st = step(m->g, startst, stopst, st, flagch, st); + SP("sboleol", st, c); + } + + /* how about a word boundary? */ + if ( (flagch == BOL || (lastc != OUT && !ISWORD(lastc))) && + (c != OUT && ISWORD(c)) ) { + flagch = BOW; + } + if ( (lastc != OUT && ISWORD(lastc)) && + (flagch == EOL || (c != OUT && !ISWORD(c))) ) { + flagch = EOW; + } + if (flagch == BOW || flagch == EOW) { + st = step(m->g, startst, stopst, st, flagch, st); + SP("sboweow", st, c); + } + + /* are we done? */ + if (ISSET(st, stopst)) + matchp = p; + if (EQ(st, empty) || p == stop) + break; /* NOTE BREAK OUT */ + + /* no, we must deal with this character */ + ASSIGN(tmp, st); + ASSIGN(st, empty); + assert(c != OUT); + st = step(m->g, startst, stopst, tmp, c, st); + SP("saft", st, c); + assert(EQ(step(m->g, startst, stopst, st, NOTHING, st), st)); + p++; + } + + return(matchp); +} + + +/* + - step - map set of states reachable before char to set reachable after + == static states step(register struct re_guts *g, sopno start, sopno stop, \ + == register states bef, int ch, register states aft); + == #define BOL (OUT+1) + == #define EOL (BOL+1) + == #define BOLEOL (BOL+2) + == #define NOTHING (BOL+3) + == #define BOW (BOL+4) + == #define EOW (BOL+5) + == #define CODEMAX (BOL+5) // highest code used + == #define NONCHAR(c) ((c) > CHAR_MAX) + == #define NNONCHAR (CODEMAX-CHAR_MAX) + */ +static states +step(struct re_guts *g, + sopno start, /* start state within strip */ + sopno stop, /* state after stop state within strip */ + states bef, /* states reachable before */ + int ch, /* character or NONCHAR code */ + states aft) /* states already known reachable after */ +{ + register cset *cs; + register sop s; + register sopno pc; + register onestate here; /* note, macros know this name */ + register sopno look; + register int i; + + for (pc = start, INIT(here, pc); pc != stop; pc++, INC(here)) { + s = g->strip[pc]; + switch (OP(s)) { + case OEND: + assert(pc == stop-1); + break; + case OCHAR: + /* only characters can match */ + assert(!NONCHAR(ch) || ch != (char)OPND(s)); + if (ch == (char)OPND(s)) + FWD(aft, bef, 1); + break; + case OBOL: + if (ch == BOL || ch == BOLEOL) + FWD(aft, bef, 1); + break; + case OEOL: + if (ch == EOL || ch == BOLEOL) + FWD(aft, bef, 1); + break; + case OBOW: + if (ch == BOW) + FWD(aft, bef, 1); + break; + case OEOW: + if (ch == EOW) + FWD(aft, bef, 1); + break; + case OANY: + if (!NONCHAR(ch)) + FWD(aft, bef, 1); + break; + case OANYOF: + cs = &g->sets[OPND(s)]; + if (!NONCHAR(ch) && CHIN(cs, ch)) + FWD(aft, bef, 1); + break; + case OBACK_: /* ignored here */ + case O_BACK: + FWD(aft, aft, 1); + break; + case OPLUS_: /* forward, this is just an empty */ + FWD(aft, aft, 1); + break; + case O_PLUS: /* both forward and back */ + FWD(aft, aft, 1); + i = ISSETBACK(aft, OPND(s)); + BACK(aft, aft, OPND(s)); + if (!i && ISSETBACK(aft, OPND(s))) { + /* oho, must reconsider loop body */ + pc -= OPND(s) + 1; + INIT(here, pc); + } + break; + case OQUEST_: /* two branches, both forward */ + FWD(aft, aft, 1); + FWD(aft, aft, OPND(s)); + break; + case O_QUEST: /* just an empty */ + FWD(aft, aft, 1); + break; + case OLPAREN: /* not significant here */ + case ORPAREN: + FWD(aft, aft, 1); + break; + case OCH_: /* mark the first two branches */ + FWD(aft, aft, 1); + assert(OP(g->strip[pc+OPND(s)]) == OOR2); + FWD(aft, aft, OPND(s)); + break; + case OOR1: /* done a branch, find the O_CH */ + if (ISSTATEIN(aft, here)) { + for (look = 1; + OP(s = g->strip[pc+look]) != O_CH; + look += OPND(s)) + assert(OP(s) == OOR2); + FWD(aft, aft, look); + } + break; + case OOR2: /* propagate OCH_'s marking */ + FWD(aft, aft, 1); + if (OP(g->strip[pc+OPND(s)]) != O_CH) { + assert(OP(g->strip[pc+OPND(s)]) == OOR2); + FWD(aft, aft, OPND(s)); + } + break; + case O_CH: /* just empty */ + FWD(aft, aft, 1); + break; + default: /* ooooops... */ + assert(nope); + break; + } + } + + return(aft); +} + +#ifdef REDEBUG +/* + - print - print a set of states + == #ifdef REDEBUG + == static void print(struct match *m, char *caption, states st, \ + == int ch, FILE *d); + == #endif + */ +static void +print(struct match *m, char *caption, states st, int ch, FILE *d) +{ + register struct re_guts *g = m->g; + register int i; + register int first = 1; + + if (!(m->eflags®_TRACE)) + return; + + fprintf(d, "%s", caption); + if (ch != '\0') + fprintf(d, " %s", pchar(ch)); + for (i = 0; i < g->nstates; i++) + if (ISSET(st, i)) { + fprintf(d, "%s%d", (first) ? "\t" : ", ", i); + first = 0; + } + fprintf(d, "\n"); +} + +/* + - at - print current situation + == #ifdef REDEBUG + == static void at(struct match *m, char *title, char *start, char *stop, \ + == sopno startst, sopno stopst); + == #endif + */ +static void +at(struct match *m, char *title, char *start, char *stop, sopno startst, sopno stopst) +{ + if (!(m->eflags®_TRACE)) + return; + + printf("%s %s-", title, pchar(*start)); + printf("%s ", pchar(*stop)); + printf("%ld-%ld\n", (long)startst, (long)stopst); +} + +#ifndef PCHARDONE +#define PCHARDONE /* never again */ +/* + - pchar - make a character printable + == #ifdef REDEBUG + == static char *pchar(int ch); + == #endif + * + * Is this identical to regchar() over in debug.c? Well, yes. But a + * duplicate here avoids having a debugging-capable regexec.o tied to + * a matching debug.o, and this is convenient. It all disappears in + * the non-debug compilation anyway, so it doesn't matter much. + */ +static char * /* -> representation */ +pchar(int ch) +{ + static char pbuf[10]; + + if (isprint(ch) || ch == ' ') + sprintf(pbuf, "%c", ch); + else + sprintf(pbuf, "\\%o", ch); + return(pbuf); +} +#endif +#endif + +#undef matcher +#undef fast +#undef slow +#undef dissect +#undef backref +#undef step +#undef print +#undef at +#undef match diff --git a/regex/makefile.wnt b/regex/makefile.wnt new file mode 100644 index 00000000..3d08888c --- /dev/null +++ b/regex/makefile.wnt @@ -0,0 +1,58 @@ +# $Id: makefile.wnt 14098 2005-10-03 18:54:13Z jpf@u.washington.edu $ +# +# ======================================================================== +# Copyright 2006-2007 University of Washington +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# ======================================================================== + +# +# +# Makefile for WIN NT version of libpithrgx.lib +# +# +CC=cl +RM=del +CP=copy +RC=rc + +#includes symbol info for debugging +CDEBUG= #-Zi -Od +LDEBUG= /DEBUG /DEBUGTYPE:CV + +STDCFLAGS= -I..\include -nologo -MT -DWIN32 -DDOS -D_WINDOWS -DJOB_CONTROL -DMSC_MALLOC + +CFLAGS= $(CDEBUG) $(STDCFLAGS) $(NET) $(EXTRACFLAGS) + +LFLAGS= $(LDEBUG) $(EXTRALDFLAGS) + +RCFLAGS = + +# switches for library building +LIBER=lib +LIBARGS=/nologo /verbose + +HFILES= ../include/system.h ../include/general.h \ + cclass.h cname.h regex2.h regex.h utils.h + +OFILES= regcomp.obj regerror.obj regexec.obj regfree.obj + +all: libregex.lib + +.c.obj: + $(CC) -c $(CFLAGS) "$(MAKEDIR)"\$*.c + +$(OFILES): $(HFILES) + +libregex.lib: $(OFILES) + $(RM) libregex.lib || rem + $(LIBER) /out:libregex.lib $(OFILES) + +clean: + $(RM) *.lib + $(RM) *.obj diff --git a/regex/re_format.doc b/regex/re_format.doc new file mode 100644 index 00000000..7a8acd7d --- /dev/null +++ b/regex/re_format.doc @@ -0,0 +1,264 @@ + + + +RE_FORMAT(7) Device and Network Interfaces RE_FORMAT(7) + + + +NAME + re_format - POSIX 1003.2 regular expressions + +DESCRIPTION + Regular expressions (``RE''s), as defined in POSIX 1003.2, + come in two forms: modern REs (roughly those of egrep; + 1003.2 calls these ``extended'' REs) and obsolete REs + (roughly those of ed; 1003.2 ``basic'' REs). Obsolete REs + mostly exist for backward compatibility in some old pro- + grams; they will be discussed at the end. 1003.2 leaves + some aspects of RE syntax and semantics open; ` - ' marks + decisions on these aspects that may not be fully portable to + other 1003.2 implementations. + + A (modern) RE is one- or more non-empty- branches, separated + by `|'. It matches anything that matches one of the + branches. + + A branch is one- or more pieces, concatenated. It matches a + match for the first, followed by a match for the second, + etc. + + A piece is an atom possibly followed by a single- `*', `+', + `?', or bound. An atom followed by `*' matches a sequence + of 0 or more matches of the atom. An atom followed by `+' + matches a sequence of 1 or more matches of the atom. An + atom followed by `?' matches a sequence of 0 or 1 matches of + the atom. + + A bound is `{' followed by an unsigned decimal integer, pos- + sibly followed by `,' possibly followed by another unsigned + decimal integer, always followed by `}'. The integers must + lie between 0 and RE_DUP_MAX (255-) inclusive, and if there + are two of them, the first may not exceed the second. An + atom followed by a bound containing one integer i and no + comma matches a sequence of exactly i matches of the atom. + An atom followed by a bound containing one integer i and a + comma matches a sequence of i or more matches of the atom. + An atom followed by a bound containing two integers i and j + matches a sequence of i through j (inclusive) matches of the + atom. + + An atom is a regular expression enclosed in `()' (matching a + match for the regular expression), an empty set of `()' + (matching the null string) - , a bracket expression (see + below), `.' (matching any single character), `^' (matching + the null string at the beginning of a line), `$' (matching + the null string at the end of a line), a `\' followed by one + of the characters `^.[$()|*+?{\' (matching that character + taken as an ordinary character), a `\' followed by any other + character- (matching that character taken as an ordinary + character, as if the `\' had not been present-), or a single + + + +SunOS 5.5 Last change: March 20, 1994 1 + + + + + + +RE_FORMAT(7) Device and Network Interfaces RE_FORMAT(7) + + + + character with no other significance (matching that charac- + ter). A `{' followed by a character other than a digit is + an ordinary character, not the beginning of a bound-. It is + illegal to end an RE with `\'. + + A bracket expression is a list of characters enclosed in + `[]'. It normally matches any single character from the + list (but see below). If the list begins with `^', it + matches any single character (but see below) not from the + rest of the list. If two characters in the list are + separated by ` -', this is shorthand for the full range of + characters between those two (inclusive) in the collating + sequence, e.g. `[0-9]' in ASCII matches any decimal digit. + It is illegal- for two ranges to share an endpoint, e.g. + `a-c-e'. Ranges are very collating-sequence-dependent, and + portable programs should avoid relying on them. + + To include a literal `]' in the list, make it the first + character (following a possible `^'). To include a literal + `-', make it the first or last character, or the second end- + point of a range. To use a literal `-' as the first end- + point of a range, enclose it in `[.' and `.]' to make it a + collating element (see below). With the exception of these + and some combinations using `[' (see next paragraphs), all + other special characters, including `\', lose their special + significance within a bracket expression. + + Within a bracket expression, a collating element (a charac- + ter, a multi-character sequence that collates as if it were + a single character, or a collating-sequence name for either) + enclosed in `[.' and `.]' stands for the sequence of charac- + ters of that collating element. The sequence is a single + element of the bracket expression's list. A bracket expres- + sion containing a multi-character collating element can thus + match more than one character, e.g. if the collating + sequence includes a `ch' collating element, then the RE + `[[.ch.]]*c' matches the first five characters of `chchcc'. + + Within a bracket expression, a collating element enclosed in + `[=' and `=]' is an equivalence class, standing for the + sequences of characters of all collating elements equivalent + to that one, including itself. (If there are no other + equivalent collating elements, the treatment is as if the + enclosing delimiters were `[.' and `.]'.) For example, if o + and ^ are the members of an equivalence class, then + `[[=o=]]', `[[=^=]]', and `[o^]' are all synonymous. An + equivalence class may not- be an endpoint of a range. + + Within a bracket expression, the name of a character class + enclosed in `[:' and `:]' stands for the list of all charac- + ters belonging to that class. Standard character class + names are: + + + +SunOS 5.5 Last change: March 20, 1994 2 + + + + + + +RE_FORMAT(7) Device and Network Interfaces RE_FORMAT(7) + + + + alnum digit punct + alpha graph space + blank lower upper + cntrl print xdigit + + These stand for the character classes defined in ctype(3). + A locale may provide others. A character class may not be + used as an endpoint of a range. + + There are two special cases- of bracket expressions: the + bracket expressions `[[:<:]]' and `[[:>:]]' match the null + string at the beginning and end of a word respectively. A + word is defined as a sequence of word characters which is + neither preceded nor followed by word characters. A word + character is an alnum character (as defined by ctype(3)) or + an underscore. This is an extension, compatible with but + not specified by POSIX 1003.2, and should be used with cau- + tion in software intended to be portable to other systems. + + In the event that an RE could match more than one substring + of a given string, the RE matches the one starting earliest + in the string. If the RE could match more than one sub- + string starting at that point, it matches the longest. + Subexpressions also match the longest possible substrings, + subject to the constraint that the whole match be as long as + possible, with subexpressions starting earlier in the RE + taking priority over ones starting later. Note that + higher-level subexpressions thus take priority over their + lower-level component subexpressions. + + Match lengths are measured in characters, not collating ele- + ments. A null string is considered longer than no match at + all. For example, `bb*' matches the three middle characters + of `abbbc', `(wee|week)(knights|nights)' matches all ten + characters of `weeknights', when `(.*).*' is matched against + `abc' the parenthesized subexpression matches all three + characters, and when `(a*)*' is matched against `bc' both + the whole RE and the parenthesized subexpression match the + null string. + + If case-independent matching is specified, the effect is + much as if all case distinctions had vanished from the + alphabet. When an alphabetic that exists in multiple cases + appears as an ordinary character outside a bracket expres- + sion, it is effectively transformed into a bracket expres- + sion containing both cases, e.g. `x' becomes `[xX]'. When + it appears inside a bracket expression, all case counter- + parts of it are added to the bracket expression, so that + (e.g.) `[x]' becomes `[xX]' and `[^x]' becomes `[^xX]'. + + No particular limit is imposed on the length of REs-. Pro- + grams intended to be portable should not employ REs longer + + + +SunOS 5.5 Last change: March 20, 1994 3 + + + + + + +RE_FORMAT(7) Device and Network Interfaces RE_FORMAT(7) + + + + than 256 bytes, as an implementation can refuse to accept + such REs and remain POSIX-compliant. + + Obsolete (``basic'') regular expressions differ in several + respects. `|', `+', and `?' are ordinary characters and + there is no equivalent for their functionality. The delim- + iters for bounds are `\{' and `\}', with `{' and `}' by + themselves ordinary characters. The parentheses for nested + subexpressions are `\(' and `\)', with `(' and `)' by them- + selves ordinary characters. `^' is an ordinary character + except at the beginning of the RE or- the beginning of a + parenthesized subexpression, `$' is an ordinary character + except at the end of the RE or- the end of a parenthesized + subexpression, and `*' is an ordinary character if it + appears at the beginning of the RE or the beginning of a + parenthesized subexpression (after a possible leading `^'). + Finally, there is one new type of atom, a back reference: + `\' followed by a non-zero decimal digit d matches the same + sequence of characters matched by the dth parenthesized + subexpression (numbering subexpressions by the positions of + their opening parentheses, left to right), so that (e.g.) + `\([bc]\)\1' matches `bb' or `cc' but not `bc'. + +SEE ALSO + regex(3) + + POSIX 1003.2, section 2.8 (Regular Expression Notation). + +BUGS + Having two kinds of REs is a botch. + + The current 1003.2 spec says that `)' is an ordinary charac- + ter in the absence of an unmatched `('; this was an uninten- + tional result of a wording error, and change is likely. + Avoid relying on it. + + Back references are a dreadful botch, posing major problems + for efficient implementations. They are also somewhat + vaguely defined (does `a\(\(b\)*\2\)*d' match `abbbd'?). + Avoid using them. + + 1003.2's specification of case-independent matching is + vague. The ``one case implies all cases'' definition given + above is current consensus among implementors as to the + right interpretation. + + The syntax for word boundaries is incredibly ugly. + + + + + + + + +SunOS 5.5 Last change: March 20, 1994 4 + + + diff --git a/regex/regcomp.c b/regex/regcomp.c new file mode 100644 index 00000000..0747190a --- /dev/null +++ b/regex/regcomp.c @@ -0,0 +1,1621 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)regcomp.c 8.5 (Berkeley) 3/20/94 + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)regcomp.c 8.5 (Berkeley) 3/20/94"; +#endif /* LIBC_SCCS and not lint */ + +#include <sys/types.h> +#include <stdio.h> +#include <string.h> +#include <ctype.h> +#include <limits.h> +#include <stdlib.h> +#include "regex.h" + +#include "utils.h" +#include "regex2.h" + +#include "cclass.h" +#include "cname.h" + +/* + * parse structure, passed up and down to avoid global variables and + * other clumsinesses + */ +struct parse { + char *next; /* next character in RE */ + char *end; /* end of string (-> NUL normally) */ + int error; /* has an error been seen? */ + sop *strip; /* malloced strip */ + sopno ssize; /* malloced strip size (allocated) */ + sopno slen; /* malloced strip length (used) */ + int ncsalloc; /* number of csets allocated */ + struct re_guts *g; +# define NPAREN 10 /* we need to remember () 1-9 for back refs */ + sopno pbegin[NPAREN]; /* -> ( ([0] unused) */ + sopno pend[NPAREN]; /* -> ) ([0] unused) */ +}; + +/* ========= begin header generated by ./mkh ========= */ +#ifdef __cplusplus +extern "C" { +#endif + +/* === regcomp.c === */ +static void p_ere __P((struct parse *p, int stop)); +static void p_ere_exp __P((struct parse *p)); +static void p_str __P((struct parse *p)); +static void p_bre __P((struct parse *p, int end1, int end2)); +static int p_simp_re __P((struct parse *p, int starordinary)); +static int p_count __P((struct parse *p)); +static void p_bracket __P((struct parse *p)); +static void p_b_term __P((struct parse *p, cset *cs)); +static void p_b_cclass __P((struct parse *p, cset *cs)); +static void p_b_eclass __P((struct parse *p, cset *cs)); +static char p_b_symbol __P((struct parse *p)); +static char p_b_coll_elem __P((struct parse *p, int endc)); +static char othercase __P((int ch)); +static void bothcases __P((struct parse *p, int ch)); +static void ordinary __P((struct parse *p, int ch)); +static void nonnewline __P((struct parse *p)); +static void repeat __P((struct parse *p, sopno start, int from, int to)); +static int seterr __P((struct parse *p, int e)); +static cset *allocset __P((struct parse *p)); +static void freeset __P((struct parse *p, cset *cs)); +static int freezeset __P((struct parse *p, cset *cs)); +static int firstch __P((struct parse *p, cset *cs)); +static int nch __P((struct parse *p, cset *cs)); +static void mcadd __P((struct parse *p, cset *cs, char *cp)); +static void mcsub __P((cset *cs, char *cp)); +static int mcin __P((cset *cs, char *cp)); +static char *mcfind __P((cset *cs, char *cp)); +static void mcinvert __P((struct parse *p, cset *cs)); +static void mccase __P((struct parse *p, cset *cs)); +static int isinsets __P((struct re_guts *g, int c)); +static int samesets __P((struct re_guts *g, int c1, int c2)); +static void categorize __P((struct parse *p, struct re_guts *g)); +static sopno dupl __P((struct parse *p, sopno start, sopno finish)); +static void doemit __P((struct parse *p, sop op, size_t opnd)); +static void doinsert __P((struct parse *p, sop op, size_t opnd, sopno pos)); +static void dofwd __P((struct parse *p, sopno pos, sop value)); +static void enlarge __P((struct parse *p, sopno size)); +static void stripsnug __P((struct parse *p, struct re_guts *g)); +static void findmust __P((struct parse *p, struct re_guts *g)); +static sopno pluscount __P((struct parse *p, struct re_guts *g)); + +#ifdef __cplusplus +} +#endif +/* ========= end header generated by ./mkh ========= */ + +static char nuls[10]; /* place to point scanner in event of error */ + +/* + * macros for use with parse structure + * BEWARE: these know that the parse structure is named `p' !!! + */ +#define PEEK() (*p->next) +#define PEEK2() (*(p->next+1)) +#define MORE() (p->next < p->end) +#define MORE2() (p->next+1 < p->end) +#define SEE(c) (MORE() && PEEK() == (c)) +#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b)) +#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0) +#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0) +#define NEXT() (p->next++) +#define NEXT2() (p->next += 2) +#define NEXTn(n) (p->next += (n)) +#define GETNEXT() (*p->next++) +#define SETERROR(e) seterr(p, (e)) +#define REQUIRE(co, e) ((void) ((co) || SETERROR(e))) +#define MUSTSEE(c, e) (REQUIRE(MORE() && PEEK() == (c), e)) +#define MUSTEAT(c, e) (REQUIRE(MORE() && GETNEXT() == (c), e)) +#define MUSTNOTSEE(c, e) (REQUIRE(!MORE() || PEEK() != (c), e)) +#define EMIT(op, sopnd) doemit(p, (sop)(op), (size_t)(sopnd)) +#define INSERT(op, pos) doinsert(p, (sop)(op), HERE()-(pos)+1, pos) +#define AHEAD(pos) dofwd(p, pos, HERE()-(pos)) +#define ASTERN(sop, pos) EMIT(sop, HERE()-pos) +#define HERE() (p->slen) +#define THERE() (p->slen - 1) +#define THERETHERE() (p->slen - 2) +#define DROP(n) (p->slen -= (n)) + +#ifndef NDEBUG +static int never = 0; /* for use in asserts; shuts lint up */ +#else +#define never 0 /* some <assert.h>s have bugs too */ +#endif + +/* + - regcomp - interface for parser and compilation + = extern int regcomp(regex_t *, const char *, int); + = #define REG_BASIC 0000 + = #define REG_EXTENDED 0001 + = #define REG_ICASE 0002 + = #define REG_NOSUB 0004 + = #define REG_NEWLINE 0010 + = #define REG_NOSPEC 0020 + = #define REG_PEND 0040 + = #define REG_DUMP 0200 + */ +int __stdcall /* 0 success, otherwise REG_something */ +regcomp(regex_t *preg, const char *pattern, int cflags) +{ + struct parse pa; + register struct re_guts *g; + register struct parse *p = &pa; + register int i; + register size_t len; +#ifdef REDEBUG +# define GOODFLAGS(f) (f) +#else +# define GOODFLAGS(f) ((f)&~REG_DUMP) +#endif + + cflags = GOODFLAGS(cflags); + if ((cflags®_EXTENDED) && (cflags®_NOSPEC)) + return(REG_INVARG); + + if (cflags®_PEND) { + if (preg->re_endp < pattern) + return(REG_INVARG); + len = preg->re_endp - pattern; + } else + len = strlen((char *)pattern); + + /* do the mallocs early so failure handling is easy */ + g = (struct re_guts *)malloc(sizeof(struct re_guts) + + (NC-1)*sizeof(cat_t)); + if (g == NULL) + return(REG_ESPACE); + p->ssize = len/(size_t)2*(size_t)3 + (size_t)1; /* ugh */ + p->strip = (sop *)malloc(p->ssize * sizeof(sop)); + p->slen = 0; + if (p->strip == NULL) { + free((char *)g); + return(REG_ESPACE); + } + + /* set things up */ + p->g = g; + p->next = (char *)pattern; /* convenience; we do not modify it */ + p->end = p->next + len; + p->error = 0; + p->ncsalloc = 0; + for (i = 0; i < NPAREN; i++) { + p->pbegin[i] = 0; + p->pend[i] = 0; + } + g->csetsize = NC; + g->sets = NULL; + g->setbits = NULL; + g->ncsets = 0; + g->cflags = cflags; + g->iflags = 0; + g->nbol = 0; + g->neol = 0; + g->must = NULL; + g->mlen = 0; + g->nsub = 0; + g->ncategories = 1; /* category 0 is "everything else" */ + g->categories = &g->catspace[-(CHAR_MIN)]; + (void) memset((char *)g->catspace, 0, NC*sizeof(cat_t)); + g->backrefs = 0; + + /* do it */ + EMIT(OEND, 0); + g->firststate = THERE(); + if (cflags®_EXTENDED) + p_ere(p, OUT); + else if (cflags®_NOSPEC) + p_str(p); + else + p_bre(p, OUT, OUT); + EMIT(OEND, 0); + g->laststate = THERE(); + + /* tidy up loose ends and fill things in */ + categorize(p, g); + stripsnug(p, g); + findmust(p, g); + g->nplus = pluscount(p, g); + g->magic = MAGIC2; + preg->re_nsub = g->nsub; + preg->re_g = g; + preg->re_magic = MAGIC1; +#ifndef REDEBUG + /* not debugging, so can't rely on the assert() in regexec() */ + if (g->iflags&BAD) + SETERROR(REG_ASSERT); +#endif + + /* win or lose, we're done */ + if (p->error != 0) /* lose */ + regfree(preg); + return(p->error); +} + +/* + - p_ere - ERE parser top level, concatenation and alternation + == static void p_ere(register struct parse *p, int stop); + */ +static void +p_ere(struct parse *p, + int stop) /* character this ERE should end at */ +{ + register char c; + register sopno prevback; + register sopno prevfwd; + register sopno conc; + register int first = 1; /* is this the first alternative? */ + + for (;;) { + /* do a bunch of concatenated expressions */ + conc = HERE(); + while (MORE() && (c = PEEK()) != '|' && c != stop) + p_ere_exp(p); + REQUIRE(HERE() != conc, REG_EMPTY); /* require nonempty */ + + if (!EAT('|')) + break; /* NOTE BREAK OUT */ + + if (first) { + INSERT(OCH_, conc); /* offset is wrong */ + prevfwd = conc; + prevback = conc; + first = 0; + } + ASTERN(OOR1, prevback); + prevback = THERE(); + AHEAD(prevfwd); /* fix previous offset */ + prevfwd = HERE(); + EMIT(OOR2, 0); /* offset is very wrong */ + } + + if (!first) { /* tail-end fixups */ + AHEAD(prevfwd); + ASTERN(O_CH, prevback); + } + + assert(!MORE() || SEE(stop)); +} + +/* + - p_ere_exp - parse one subERE, an atom possibly followed by a repetition op + == static void p_ere_exp(register struct parse *p); + */ +static void +p_ere_exp(struct parse *p) +{ + register char c; + register sopno pos; + register int count; + register int count2; + register sopno subno; + int wascaret = 0; + + assert(MORE()); /* caller should have ensured this */ + c = GETNEXT(); + + pos = HERE(); + switch (c) { + case '(': + REQUIRE(MORE(), REG_EPAREN); + p->g->nsub++; + subno = p->g->nsub; + if (subno < NPAREN) + p->pbegin[subno] = HERE(); + EMIT(OLPAREN, subno); + if (!SEE(')')) + p_ere(p, ')'); + if (subno < NPAREN) { + p->pend[subno] = HERE(); + assert(p->pend[subno] != 0); + } + EMIT(ORPAREN, subno); + MUSTEAT(')', REG_EPAREN); + break; +#ifndef POSIX_MISTAKE + case ')': /* happens only if no current unmatched ( */ + /* + * You may ask, why the ifndef? Because I didn't notice + * this until slightly too late for 1003.2, and none of the + * other 1003.2 regular-expression reviewers noticed it at + * all. So an unmatched ) is legal POSIX, at least until + * we can get it fixed. + */ + SETERROR(REG_EPAREN); + break; +#endif + case '^': + EMIT(OBOL, 0); + p->g->iflags |= USEBOL; + p->g->nbol++; + wascaret = 1; + break; + case '$': + EMIT(OEOL, 0); + p->g->iflags |= USEEOL; + p->g->neol++; + break; + case '|': + SETERROR(REG_EMPTY); + break; + case '*': + case '+': + case '?': + SETERROR(REG_BADRPT); + break; + case '.': + if (p->g->cflags®_NEWLINE) + nonnewline(p); + else + EMIT(OANY, 0); + break; + case '[': + p_bracket(p); + break; + case '\\': + REQUIRE(MORE(), REG_EESCAPE); + c = GETNEXT(); + ordinary(p, c); + break; + case '{': /* okay as ordinary except if digit follows */ + REQUIRE(!MORE() || !isdigit(PEEK()), REG_BADRPT); + /* FALLTHROUGH */ + default: + ordinary(p, c); + break; + } + + if (!MORE()) + return; + c = PEEK(); + /* we call { a repetition if followed by a digit */ + if (!( c == '*' || c == '+' || c == '?' || + (c == '{' && MORE2() && isdigit(PEEK2())) )) + return; /* no repetition, we're done */ + NEXT(); + + REQUIRE(!wascaret, REG_BADRPT); + switch (c) { + case '*': /* implemented as +? */ + /* this case does not require the (y|) trick, noKLUDGE */ + INSERT(OPLUS_, pos); + ASTERN(O_PLUS, pos); + INSERT(OQUEST_, pos); + ASTERN(O_QUEST, pos); + break; + case '+': + INSERT(OPLUS_, pos); + ASTERN(O_PLUS, pos); + break; + case '?': + /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */ + INSERT(OCH_, pos); /* offset slightly wrong */ + ASTERN(OOR1, pos); /* this one's right */ + AHEAD(pos); /* fix the OCH_ */ + EMIT(OOR2, 0); /* offset very wrong... */ + AHEAD(THERE()); /* ...so fix it */ + ASTERN(O_CH, THERETHERE()); + break; + case '{': + count = p_count(p); + if (EAT(',')) { + if (isdigit(PEEK())) { + count2 = p_count(p); + REQUIRE(count <= count2, REG_BADBR); + } else /* single number with comma */ + count2 = INFINITY; + } else /* just a single number */ + count2 = count; + repeat(p, pos, count, count2); + if (!EAT('}')) { /* error heuristics */ + while (MORE() && PEEK() != '}') + NEXT(); + REQUIRE(MORE(), REG_EBRACE); + SETERROR(REG_BADBR); + } + break; + } + + if (!MORE()) + return; + c = PEEK(); + if (!( c == '*' || c == '+' || c == '?' || + (c == '{' && MORE2() && isdigit(PEEK2())) ) ) + return; + SETERROR(REG_BADRPT); +} + +/* + - p_str - string (no metacharacters) "parser" + == static void p_str(register struct parse *p); + */ +static void +p_str(struct parse *p) +{ + REQUIRE(MORE(), REG_EMPTY); + while (MORE()) + ordinary(p, GETNEXT()); +} + +/* + - p_bre - BRE parser top level, anchoring and concatenation + == static void p_bre(register struct parse *p, register int end1, \ + == register int end2); + * Giving end1 as OUT essentially eliminates the end1/end2 check. + * + * This implementation is a bit of a kludge, in that a trailing $ is first + * taken as an ordinary character and then revised to be an anchor. The + * only undesirable side effect is that '$' gets included as a character + * category in such cases. This is fairly harmless; not worth fixing. + * The amount of lookahead needed to avoid this kludge is excessive. + */ +static void +p_bre(struct parse *p, + int end1, /* first terminating character */ + int end2) /* second terminating character */ +{ + register sopno start = HERE(); + register int first = 1; /* first subexpression? */ + register int wasdollar = 0; + + if (EAT('^')) { + EMIT(OBOL, 0); + p->g->iflags |= USEBOL; + p->g->nbol++; + } + while (MORE() && !SEETWO(end1, end2)) { + wasdollar = p_simp_re(p, first); + first = 0; + } + if (wasdollar) { /* oops, that was a trailing anchor */ + DROP(1); + EMIT(OEOL, 0); + p->g->iflags |= USEEOL; + p->g->neol++; + } + + REQUIRE(HERE() != start, REG_EMPTY); /* require nonempty */ +} + +/* + - p_simp_re - parse a simple RE, an atom possibly followed by a repetition + == static int p_simp_re(register struct parse *p, int starordinary); + */ +static int /* was the simple RE an unbackslashed $? */ +p_simp_re(struct parse *p, + int starordinary) /* is a leading * an ordinary character? */ +{ + register int c; + register int count; + register int count2; + register sopno pos; + register int i; + register sopno subno; +# define BACKSL (1<<CHAR_BIT) + + pos = HERE(); /* repetion op, if any, covers from here */ + + assert(MORE()); /* caller should have ensured this */ + c = GETNEXT(); + if (c == '\\') { + REQUIRE(MORE(), REG_EESCAPE); + c = BACKSL | (unsigned char)GETNEXT(); + } + switch (c) { + case '.': + if (p->g->cflags®_NEWLINE) + nonnewline(p); + else + EMIT(OANY, 0); + break; + case '[': + p_bracket(p); + break; + case BACKSL|'{': + SETERROR(REG_BADRPT); + break; + case BACKSL|'(': + p->g->nsub++; + subno = p->g->nsub; + if (subno < NPAREN) + p->pbegin[subno] = HERE(); + EMIT(OLPAREN, subno); + /* the MORE here is an error heuristic */ + if (MORE() && !SEETWO('\\', ')')) + p_bre(p, '\\', ')'); + if (subno < NPAREN) { + p->pend[subno] = HERE(); + assert(p->pend[subno] != 0); + } + EMIT(ORPAREN, subno); + REQUIRE(EATTWO('\\', ')'), REG_EPAREN); + break; + case BACKSL|')': /* should not get here -- must be user */ + case BACKSL|'}': + SETERROR(REG_EPAREN); + break; + case BACKSL|'1': + case BACKSL|'2': + case BACKSL|'3': + case BACKSL|'4': + case BACKSL|'5': + case BACKSL|'6': + case BACKSL|'7': + case BACKSL|'8': + case BACKSL|'9': + i = (c&~BACKSL) - '0'; + assert(i < NPAREN); + if (p->pend[i] != 0) { + assert(i <= p->g->nsub); + EMIT(OBACK_, i); + assert(p->pbegin[i] != 0); + assert(OP(p->strip[p->pbegin[i]]) == OLPAREN); + assert(OP(p->strip[p->pend[i]]) == ORPAREN); + (void) dupl(p, p->pbegin[i]+1, p->pend[i]); + EMIT(O_BACK, i); + } else + SETERROR(REG_ESUBREG); + p->g->backrefs = 1; + break; + case '*': + REQUIRE(starordinary, REG_BADRPT); + /* FALLTHROUGH */ + default: + ordinary(p, c &~ BACKSL); + break; + } + + if (EAT('*')) { /* implemented as +? */ + /* this case does not require the (y|) trick, noKLUDGE */ + INSERT(OPLUS_, pos); + ASTERN(O_PLUS, pos); + INSERT(OQUEST_, pos); + ASTERN(O_QUEST, pos); + } else if (EATTWO('\\', '{')) { + count = p_count(p); + if (EAT(',')) { + if (MORE() && isdigit(PEEK())) { + count2 = p_count(p); + REQUIRE(count <= count2, REG_BADBR); + } else /* single number with comma */ + count2 = INFINITY; + } else /* just a single number */ + count2 = count; + repeat(p, pos, count, count2); + if (!EATTWO('\\', '}')) { /* error heuristics */ + while (MORE() && !SEETWO('\\', '}')) + NEXT(); + REQUIRE(MORE(), REG_EBRACE); + SETERROR(REG_BADBR); + } + } else if (c == (unsigned char)'$') /* $ (but not \$) ends it */ + return(1); + + return(0); +} + +/* + - p_count - parse a repetition count + == static int p_count(register struct parse *p); + */ +static int /* the value */ +p_count(struct parse *p) +{ + register int count = 0; + register int ndigits = 0; + + while (MORE() && isdigit(PEEK()) && count <= DUPMAX) { + count = count*10 + (GETNEXT() - '0'); + ndigits++; + } + + REQUIRE(ndigits > 0 && count <= DUPMAX, REG_BADBR); + return(count); +} + +/* + - p_bracket - parse a bracketed character list + == static void p_bracket(register struct parse *p); + * + * Note a significant property of this code: if the allocset() did SETERROR, + * no set operations are done. + */ +static void +p_bracket(struct parse *p) +{ + register cset *cs = allocset(p); + register int invert = 0; + + /* Dept of Truly Sickening Special-Case Kludges */ + if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) { + EMIT(OBOW, 0); + NEXTn(6); + return; + } + if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) { + EMIT(OEOW, 0); + NEXTn(6); + return; + } + + if (EAT('^')) + invert++; /* make note to invert set at end */ + if (EAT(']')) + CHadd(cs, ']'); + else if (EAT('-')) + CHadd(cs, '-'); + while (MORE() && PEEK() != ']' && !SEETWO('-', ']')) + p_b_term(p, cs); + if (EAT('-')) + CHadd(cs, '-'); + MUSTEAT(']', REG_EBRACK); + + if (p->error != 0) /* don't mess things up further */ + return; + + if (p->g->cflags®_ICASE) { + register int i; + register int ci; + + for (i = p->g->csetsize - 1; i >= 0; i--) + if (CHIN(cs, i) && isalpha(i)) { + ci = othercase(i); + if (ci != i) + CHadd(cs, ci); + } + if (cs->multis != NULL) + mccase(p, cs); + } + if (invert) { + register int i; + + for (i = p->g->csetsize - 1; i >= 0; i--) + if (CHIN(cs, i)) + CHsub(cs, i); + else + CHadd(cs, i); + if (p->g->cflags®_NEWLINE) + CHsub(cs, '\n'); + if (cs->multis != NULL) + mcinvert(p, cs); + } + + assert(cs->multis == NULL); /* xxx */ + + if (nch(p, cs) == 1) { /* optimize singleton sets */ + ordinary(p, firstch(p, cs)); + freeset(p, cs); + } else + EMIT(OANYOF, freezeset(p, cs)); +} + +/* + - p_b_term - parse one term of a bracketed character list + == static void p_b_term(register struct parse *p, register cset *cs); + */ +static void +p_b_term(struct parse *p, cset *cs) +{ + register char c; + register char start, finish; + register int i; + + /* classify what we've got */ + switch ((MORE()) ? PEEK() : '\0') { + case '[': + c = (MORE2()) ? PEEK2() : '\0'; + break; + case '-': + SETERROR(REG_ERANGE); + return; /* NOTE RETURN */ + break; + default: + c = '\0'; + break; + } + + switch (c) { + case ':': /* character class */ + NEXT2(); + REQUIRE(MORE(), REG_EBRACK); + c = PEEK(); + REQUIRE(c != '-' && c != ']', REG_ECTYPE); + p_b_cclass(p, cs); + REQUIRE(MORE(), REG_EBRACK); + REQUIRE(EATTWO(':', ']'), REG_ECTYPE); + break; + case '=': /* equivalence class */ + NEXT2(); + REQUIRE(MORE(), REG_EBRACK); + c = PEEK(); + REQUIRE(c != '-' && c != ']', REG_ECOLLATE); + p_b_eclass(p, cs); + REQUIRE(MORE(), REG_EBRACK); + REQUIRE(EATTWO('=', ']'), REG_ECOLLATE); + break; + default: /* symbol, ordinary character, or range */ +/* xxx revision needed for multichar stuff */ + start = p_b_symbol(p); + if (SEE('-') && MORE2() && PEEK2() != ']') { + /* range */ + NEXT(); + if (EAT('-')) + finish = '-'; + else + finish = p_b_symbol(p); + } else + finish = start; +/* xxx what about signed chars here... */ + REQUIRE(start <= finish, REG_ERANGE); + for (i = start; i <= finish; i++) + CHadd(cs, i); + break; + } +} + +/* + - p_b_cclass - parse a character-class name and deal with it + == static void p_b_cclass(register struct parse *p, register cset *cs); + */ +static void +p_b_cclass(struct parse *p, cset *cs) +{ + register char *sp = p->next; + register struct cclass *cp; + register size_t len; + register char *u; + register char c; + + while (MORE() && isalpha(PEEK())) + NEXT(); + len = p->next - sp; + for (cp = cclasses; cp->name != NULL; cp++) + if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0') + break; + if (cp->name == NULL) { + /* oops, didn't find it */ + SETERROR(REG_ECTYPE); + return; + } + + u = cp->chars; + while ((c = *u++) != '\0') + CHadd(cs, c); + for (u = cp->multis; *u != '\0'; u += strlen(u) + 1) + MCadd(p, cs, u); +} + +/* + - p_b_eclass - parse an equivalence-class name and deal with it + == static void p_b_eclass(register struct parse *p, register cset *cs); + * + * This implementation is incomplete. xxx + */ +static void +p_b_eclass(struct parse *p, cset *cs) +{ + register char c; + + c = p_b_coll_elem(p, '='); + CHadd(cs, c); +} + +/* + - p_b_symbol - parse a character or [..]ed multicharacter collating symbol + == static char p_b_symbol(register struct parse *p); + */ +static char /* value of symbol */ +p_b_symbol(struct parse *p) +{ + register char value; + + REQUIRE(MORE(), REG_EBRACK); + if (!EATTWO('[', '.')) + return(GETNEXT()); + + /* collating symbol */ + value = p_b_coll_elem(p, '.'); + REQUIRE(EATTWO('.', ']'), REG_ECOLLATE); + return(value); +} + +/* + - p_b_coll_elem - parse a collating-element name and look it up + == static char p_b_coll_elem(register struct parse *p, int endc); + */ +static char /* value of collating element */ +p_b_coll_elem(struct parse *p, + int endc) /* name ended by endc,']' */ +{ + register char *sp = p->next; + register struct cname *cp; + register int len; + + while (MORE() && !SEETWO(endc, ']')) + NEXT(); + if (!MORE()) { + SETERROR(REG_EBRACK); + return(0); + } + len = p->next - sp; + for (cp = cnames; cp->name != NULL; cp++) + if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0') + return(cp->code); /* known name */ + if (len == 1) + return(*sp); /* single character */ + SETERROR(REG_ECOLLATE); /* neither */ + return(0); +} + +/* + - othercase - return the case counterpart of an alphabetic + == static char othercase(int ch); + */ +static char /* if no counterpart, return ch */ +othercase(int ch) +{ + assert(isalpha(ch)); + if (isupper(ch)) + return(tolower(ch)); + else if (islower(ch)) + return(toupper(ch)); + else /* peculiar, but could happen */ + return(ch); +} + +/* + - bothcases - emit a dualcase version of a two-case character + == static void bothcases(register struct parse *p, int ch); + * + * Boy, is this implementation ever a kludge... + */ +static void +bothcases(struct parse *p, int ch) +{ + register char *oldnext = p->next; + register char *oldend = p->end; + char bracket[3]; + + assert(othercase(ch) != ch); /* p_bracket() would recurse */ + p->next = bracket; + p->end = bracket+2; + bracket[0] = ch; + bracket[1] = ']'; + bracket[2] = '\0'; + p_bracket(p); + assert(p->next == bracket+2); + p->next = oldnext; + p->end = oldend; +} + +/* + - ordinary - emit an ordinary character + == static void ordinary(register struct parse *p, register int ch); + */ +static void +ordinary(struct parse *p, int ch) +{ + register cat_t *cap = p->g->categories; + + if ((p->g->cflags®_ICASE) && isalpha(ch) && othercase(ch) != ch) + bothcases(p, ch); + else { + EMIT(OCHAR, (unsigned char)ch); + if (cap[ch] == 0) + cap[ch] = p->g->ncategories++; + } +} + +/* + - nonnewline - emit REG_NEWLINE version of OANY + == static void nonnewline(register struct parse *p); + * + * Boy, is this implementation ever a kludge... + */ +static void +nonnewline(struct parse *p) +{ + register char *oldnext = p->next; + register char *oldend = p->end; + char bracket[4]; + + p->next = bracket; + p->end = bracket+3; + bracket[0] = '^'; + bracket[1] = '\n'; + bracket[2] = ']'; + bracket[3] = '\0'; + p_bracket(p); + assert(p->next == bracket+3); + p->next = oldnext; + p->end = oldend; +} + +/* + - repeat - generate code for a bounded repetition, recursively if needed + == static void repeat(register struct parse *p, sopno start, int from, int to); + */ +static void +repeat(struct parse *p, + sopno start, /* operand from here to end of strip */ + int from, /* repeated from this number */ + int to) /* to this number of times (maybe INFINITY) */ +{ + register sopno finish = HERE(); +# define N 2 +# define INF 3 +# define REP(f, t) ((f)*8 + (t)) +# define MAP(n) (((n) <= 1) ? (n) : ((n) == INFINITY) ? INF : N) + register sopno copy; + + if (p->error != 0) /* head off possible runaway recursion */ + return; + + assert(from <= to); + + switch (REP(MAP(from), MAP(to))) { + case REP(0, 0): /* must be user doing this */ + DROP(finish-start); /* drop the operand */ + break; + case REP(0, 1): /* as x{1,1}? */ + case REP(0, N): /* as x{1,n}? */ + case REP(0, INF): /* as x{1,}? */ + /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */ + INSERT(OCH_, start); /* offset is wrong... */ + repeat(p, start+1, 1, to); + ASTERN(OOR1, start); + AHEAD(start); /* ... fix it */ + EMIT(OOR2, 0); + AHEAD(THERE()); + ASTERN(O_CH, THERETHERE()); + break; + case REP(1, 1): /* trivial case */ + /* done */ + break; + case REP(1, N): /* as x?x{1,n-1} */ + /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */ + INSERT(OCH_, start); + ASTERN(OOR1, start); + AHEAD(start); + EMIT(OOR2, 0); /* offset very wrong... */ + AHEAD(THERE()); /* ...so fix it */ + ASTERN(O_CH, THERETHERE()); + copy = dupl(p, start+1, finish+1); + assert(copy == finish+4); + repeat(p, copy, 1, to-1); + break; + case REP(1, INF): /* as x+ */ + INSERT(OPLUS_, start); + ASTERN(O_PLUS, start); + break; + case REP(N, N): /* as xx{m-1,n-1} */ + copy = dupl(p, start, finish); + repeat(p, copy, from-1, to-1); + break; + case REP(N, INF): /* as xx{n-1,INF} */ + copy = dupl(p, start, finish); + repeat(p, copy, from-1, to); + break; + default: /* "can't happen" */ + SETERROR(REG_ASSERT); /* just in case */ + break; + } +} + +/* + - seterr - set an error condition + == static int seterr(register struct parse *p, int e); + */ +static int /* useless but makes type checking happy */ +seterr(struct parse *p, int e) +{ + if (p->error == 0) /* keep earliest error condition */ + p->error = e; + p->next = nuls; /* try to bring things to a halt */ + p->end = nuls; + return(0); /* make the return value well-defined */ +} + +/* + - allocset - allocate a set of characters for [] + == static cset *allocset(register struct parse *p); + */ +static cset * +allocset(struct parse *p) +{ + register int no = p->g->ncsets++; + register size_t nc; + register size_t nbytes; + register cset *cs; + register size_t css = (size_t)p->g->csetsize; + register int i; + + if (no >= p->ncsalloc) { /* need another column of space */ + p->ncsalloc += CHAR_BIT; + nc = p->ncsalloc; + assert(nc % CHAR_BIT == 0); + nbytes = nc / CHAR_BIT * css; + if (p->g->sets == NULL) + p->g->sets = (cset *)malloc(nc * sizeof(cset)); + else + p->g->sets = (cset *)realloc((char *)p->g->sets, + nc * sizeof(cset)); + if (p->g->setbits == NULL) + p->g->setbits = (uch *)malloc(nbytes); + else { + p->g->setbits = (uch *)realloc((char *)p->g->setbits, + nbytes); + /* xxx this isn't right if setbits is now NULL */ + for (i = 0; i < no; i++) + p->g->sets[i].ptr = p->g->setbits + css*(i/CHAR_BIT); + } + if (p->g->sets != NULL && p->g->setbits != NULL) + (void) memset((char *)p->g->setbits + (nbytes - css), + 0, css); + else { + no = 0; + SETERROR(REG_ESPACE); + /* caller's responsibility not to do set ops */ + } + } + + assert(p->g->sets != NULL); /* xxx */ + cs = &p->g->sets[no]; + cs->ptr = p->g->setbits + css*((no)/CHAR_BIT); + cs->mask = 1 << ((no) % CHAR_BIT); + cs->hash = 0; + cs->smultis = 0; + cs->multis = NULL; + + return(cs); +} + +/* + - freeset - free a now-unused set + == static void freeset(register struct parse *p, register cset *cs); + */ +static void +freeset(struct parse *p, cset *cs) +{ + register int i; + register cset *top = &p->g->sets[p->g->ncsets]; + register size_t css = (size_t)p->g->csetsize; + + for (i = 0; i < css; i++) + CHsub(cs, i); + if (cs == top-1) /* recover only the easy case */ + p->g->ncsets--; +} + +/* + - freezeset - final processing on a set of characters + == static int freezeset(register struct parse *p, register cset *cs); + * + * The main task here is merging identical sets. This is usually a waste + * of time (although the hash code minimizes the overhead), but can win + * big if REG_ICASE is being used. REG_ICASE, by the way, is why the hash + * is done using addition rather than xor -- all ASCII [aA] sets xor to + * the same value! + */ +static int /* set number */ +freezeset(struct parse *p, cset *cs) +{ + register uch h = cs->hash; + register int i; + register cset *top = &p->g->sets[p->g->ncsets]; + register cset *cs2; + register size_t css = (size_t)p->g->csetsize; + + /* look for an earlier one which is the same */ + for (cs2 = &p->g->sets[0]; cs2 < top; cs2++) + if (cs2->hash == h && cs2 != cs) { + /* maybe */ + for (i = 0; i < css; i++) + if (!!CHIN(cs2, i) != !!CHIN(cs, i)) + break; /* no */ + if (i == css) + break; /* yes */ + } + + if (cs2 < top) { /* found one */ + freeset(p, cs); + cs = cs2; + } + + return((int)(cs - p->g->sets)); +} + +/* + - firstch - return first character in a set (which must have at least one) + == static int firstch(register struct parse *p, register cset *cs); + */ +static int /* character; there is no "none" value */ +firstch(struct parse *p, cset *cs) +{ + register int i; + register size_t css = (size_t)p->g->csetsize; + + for (i = 0; i < css; i++) + if (CHIN(cs, i)) + return((char)i); + assert(never); + return(0); /* arbitrary */ +} + +/* + - nch - number of characters in a set + == static int nch(register struct parse *p, register cset *cs); + */ +static int +nch(struct parse *p, cset *cs) +{ + register int i; + register size_t css = (size_t)p->g->csetsize; + register int n = 0; + + for (i = 0; i < css; i++) + if (CHIN(cs, i)) + n++; + return(n); +} + +/* + - mcadd - add a collating element to a cset + == static void mcadd(register struct parse *p, register cset *cs, \ + == register char *cp); + */ +static void +mcadd(struct parse *p, cset *cs, char *cp) +{ + register size_t oldend = cs->smultis; + + cs->smultis += strlen(cp) + 1; + if (cs->multis == NULL) + cs->multis = malloc(cs->smultis); + else + cs->multis = realloc(cs->multis, cs->smultis); + if (cs->multis == NULL) { + SETERROR(REG_ESPACE); + return; + } + + (void) strcpy(cs->multis + oldend - 1, cp); + cs->multis[cs->smultis - 1] = '\0'; +} + +/* + - mcsub - subtract a collating element from a cset + == static void mcsub(register cset *cs, register char *cp); + */ +static void +mcsub(cset *cs, char *cp) +{ + register char *fp = mcfind(cs, cp); + register size_t len = strlen(fp); + + assert(fp != NULL); + (void) memmove(fp, fp + len + 1, + cs->smultis - (fp + len + 1 - cs->multis)); + cs->smultis -= len; + + if (cs->smultis == 0) { + free(cs->multis); + cs->multis = NULL; + return; + } + + cs->multis = realloc(cs->multis, cs->smultis); + assert(cs->multis != NULL); +} + +/* + - mcin - is a collating element in a cset? + == static int mcin(register cset *cs, register char *cp); + */ +static int +mcin(cset *cs, char *cp) +{ + return(mcfind(cs, cp) != NULL); +} + +/* + - mcfind - find a collating element in a cset + == static char *mcfind(register cset *cs, register char *cp); + */ +static char * +mcfind(cset *cs, char *cp) +{ + register char *p; + + if (cs->multis == NULL) + return(NULL); + for (p = cs->multis; *p != '\0'; p += strlen(p) + 1) + if (strcmp(cp, p) == 0) + return(p); + return(NULL); +} + +/* + - mcinvert - invert the list of collating elements in a cset + == static void mcinvert(register struct parse *p, register cset *cs); + * + * This would have to know the set of possibilities. Implementation + * is deferred. + */ +static void +mcinvert(struct parse *p, cset *cs) +{ + assert(cs->multis == NULL); /* xxx */ +} + +/* + - mccase - add case counterparts of the list of collating elements in a cset + == static void mccase(register struct parse *p, register cset *cs); + * + * This would have to know the set of possibilities. Implementation + * is deferred. + */ +static void +mccase(struct parse *p, cset *cs) +{ + assert(cs->multis == NULL); /* xxx */ +} + +/* + - isinsets - is this character in any sets? + == static int isinsets(register struct re_guts *g, int c); + */ +static int /* predicate */ +isinsets(struct re_guts *g, int c) +{ + register uch *col; + register int i; + register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT; + register unsigned uc = (unsigned char)c; + + for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize) + if (col[uc] != 0) + return(1); + return(0); +} + +/* + - samesets - are these two characters in exactly the same sets? + == static int samesets(register struct re_guts *g, int c1, int c2); + */ +static int /* predicate */ +samesets(struct re_guts *g, int c1, int c2) +{ + register uch *col; + register int i; + register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT; + register unsigned uc1 = (unsigned char)c1; + register unsigned uc2 = (unsigned char)c2; + + for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize) + if (col[uc1] != col[uc2]) + return(0); + return(1); +} + +/* + - categorize - sort out character categories + == static void categorize(struct parse *p, register struct re_guts *g); + */ +static void +categorize(struct parse *p, struct re_guts *g) +{ + register cat_t *cats = g->categories; + register int c; + register int c2; + register cat_t cat; + + /* avoid making error situations worse */ + if (p->error != 0) + return; + + for (c = CHAR_MIN; c <= CHAR_MAX; c++) + if (cats[c] == 0 && isinsets(g, c)) { + cat = g->ncategories++; + cats[c] = cat; + for (c2 = c+1; c2 <= CHAR_MAX; c2++) + if (cats[c2] == 0 && samesets(g, c, c2)) + cats[c2] = cat; + } +} + +/* + - dupl - emit a duplicate of a bunch of sops + == static sopno dupl(register struct parse *p, sopno start, sopno finish); + */ +static sopno /* start of duplicate */ +dupl(struct parse *p, + sopno start, /* from here */ + sopno finish) /* to this less one */ +{ + register sopno ret = HERE(); + register sopno len = finish - start; + + assert(finish >= start); + if (len == 0) + return(ret); + enlarge(p, p->ssize + len); /* this many unexpected additions */ + assert(p->ssize >= p->slen + len); + (void) memcpy((char *)(p->strip + p->slen), + (char *)(p->strip + start), (size_t)len*sizeof(sop)); + p->slen += len; + return(ret); +} + +/* + - doemit - emit a strip operator + == static void doemit(register struct parse *p, sop op, size_t opnd); + * + * It might seem better to implement this as a macro with a function as + * hard-case backup, but it's just too big and messy unless there are + * some changes to the data structures. Maybe later. + */ +static void +doemit(struct parse *p, sop op, size_t opnd) +{ + /* avoid making error situations worse */ + if (p->error != 0) + return; + + /* deal with oversize operands ("can't happen", more or less) */ + assert(opnd < 1<<OPSHIFT); + + /* deal with undersized strip */ + if (p->slen >= p->ssize) + enlarge(p, (p->ssize+1) / 2 * 3); /* +50% */ + assert(p->slen < p->ssize); + + /* finally, it's all reduced to the easy case */ + p->strip[p->slen++] = SOP(op, opnd); +} + +/* + - doinsert - insert a sop into the strip + == static void doinsert(register struct parse *p, sop op, size_t opnd, sopno pos); + */ +static void +doinsert(struct parse *p, sop op, size_t opnd, sopno pos) +{ + register sopno sn; + register sop s; + register int i; + + /* avoid making error situations worse */ + if (p->error != 0) + return; + + sn = HERE(); + EMIT(op, opnd); /* do checks, ensure space */ + assert(HERE() == sn+1); + s = p->strip[sn]; + + /* adjust paren pointers */ + assert(pos > 0); + for (i = 1; i < NPAREN; i++) { + if (p->pbegin[i] >= pos) { + p->pbegin[i]++; + } + if (p->pend[i] >= pos) { + p->pend[i]++; + } + } + + memmove((char *)&p->strip[pos+1], (char *)&p->strip[pos], + (HERE()-pos-1)*sizeof(sop)); + p->strip[pos] = s; +} + +/* + - dofwd - complete a forward reference + == static void dofwd(register struct parse *p, sopno pos, sop value); + */ +static void +dofwd(struct parse *p, sopno pos, sop value) +{ + /* avoid making error situations worse */ + if (p->error != 0) + return; + + assert(value < 1<<OPSHIFT); + p->strip[pos] = OP(p->strip[pos]) | value; +} + +/* + - enlarge - enlarge the strip + == static void enlarge(register struct parse *p, sopno size); + */ +static void +enlarge(struct parse *p, sopno size) +{ + register sop *sp; + + if (p->ssize >= size) + return; + + sp = (sop *)realloc(p->strip, size*sizeof(sop)); + if (sp == NULL) { + SETERROR(REG_ESPACE); + return; + } + p->strip = sp; + p->ssize = size; +} + +/* + - stripsnug - compact the strip + == static void stripsnug(register struct parse *p, register struct re_guts *g); + */ +static void +stripsnug(struct parse *p, struct re_guts *g) +{ + g->nstates = p->slen; + g->strip = (sop *)realloc((char *)p->strip, p->slen * sizeof(sop)); + if (g->strip == NULL) { + SETERROR(REG_ESPACE); + g->strip = p->strip; + } +} + +/* + - findmust - fill in must and mlen with longest mandatory literal string + == static void findmust(register struct parse *p, register struct re_guts *g); + * + * This algorithm could do fancy things like analyzing the operands of | + * for common subsequences. Someday. This code is simple and finds most + * of the interesting cases. + * + * Note that must and mlen got initialized during setup. + */ +static void +findmust(struct parse *p, struct re_guts *g) +{ + register sop *scan; + sop *start; + register sop *newstart; + register sopno newlen; + register sop s; + register char *cp; + register sopno i; + + /* avoid making error situations worse */ + if (p->error != 0) + return; + + /* find the longest OCHAR sequence in strip */ + newlen = 0; + scan = g->strip + 1; + do { + s = *scan++; + switch (OP(s)) { + case OCHAR: /* sequence member */ + if (newlen == 0) /* new sequence */ + newstart = scan - 1; + newlen++; + break; + case OPLUS_: /* things that don't break one */ + case OLPAREN: + case ORPAREN: + break; + case OQUEST_: /* things that must be skipped */ + case OCH_: + scan--; + do { + scan += OPND(s); + s = *scan; + /* assert() interferes w debug printouts */ + if (OP(s) != O_QUEST && OP(s) != O_CH && + OP(s) != OOR2) { + g->iflags |= BAD; + return; + } + } while (OP(s) != O_QUEST && OP(s) != O_CH); + /* fallthrough */ + default: /* things that break a sequence */ + if (newlen > g->mlen) { /* ends one */ + start = newstart; + g->mlen = newlen; + } + newlen = 0; + break; + } + } while (OP(s) != OEND); + + if (g->mlen == 0) /* there isn't one */ + return; + + /* turn it into a character string */ + g->must = malloc((size_t)g->mlen + 1); + if (g->must == NULL) { /* argh; just forget it */ + g->mlen = 0; + return; + } + cp = g->must; + scan = start; + for (i = g->mlen; i > 0; i--) { + while (OP(s = *scan++) != OCHAR) + continue; + assert(cp < g->must + g->mlen); + *cp++ = (char)OPND(s); + } + assert(cp == g->must + g->mlen); + *cp++ = '\0'; /* just on general principles */ +} + +/* + - pluscount - count + nesting + == static sopno pluscount(register struct parse *p, register struct re_guts *g); + */ +static sopno /* nesting depth */ +pluscount(struct parse *p, struct re_guts *g) +{ + register sop *scan; + register sop s; + register sopno plusnest = 0; + register sopno maxnest = 0; + + if (p->error != 0) + return(0); /* there may not be an OEND */ + + scan = g->strip + 1; + do { + s = *scan++; + switch (OP(s)) { + case OPLUS_: + plusnest++; + break; + case O_PLUS: + if (plusnest > maxnest) + maxnest = plusnest; + plusnest--; + break; + } + } while (OP(s) != OEND); + if (plusnest != 0) + g->iflags |= BAD; + return(maxnest); +} diff --git a/regex/regerror.c b/regex/regerror.c new file mode 100644 index 00000000..7b1cecf4 --- /dev/null +++ b/regex/regerror.c @@ -0,0 +1,172 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)regerror.c 8.4 (Berkeley) 3/20/94 + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)regerror.c 8.4 (Berkeley) 3/20/94"; +#endif /* LIBC_SCCS and not lint */ + +#include <sys/types.h> +#include <stdio.h> +#include <string.h> +#include <ctype.h> +#include <limits.h> +#include <stdlib.h> +#include "regex.h" + +#include "utils.h" + +/* ========= begin header generated by ./mkh ========= */ +#ifdef __cplusplus +extern "C" { +#endif + +/* === regerror.c === */ +static char *regatoi __P((const regex_t *preg, char *localbuf)); + +#ifdef __cplusplus +} +#endif +/* ========= end header generated by ./mkh ========= */ +/* + = #define REG_NOMATCH 1 + = #define REG_BADPAT 2 + = #define REG_ECOLLATE 3 + = #define REG_ECTYPE 4 + = #define REG_EESCAPE 5 + = #define REG_ESUBREG 6 + = #define REG_EBRACK 7 + = #define REG_EPAREN 8 + = #define REG_EBRACE 9 + = #define REG_BADBR 10 + = #define REG_ERANGE 11 + = #define REG_ESPACE 12 + = #define REG_BADRPT 13 + = #define REG_EMPTY 14 + = #define REG_ASSERT 15 + = #define REG_INVARG 16 + = #define REG_ATOI 255 // convert name to number (!) + = #define REG_ITOA 0400 // convert number to name (!) + */ +static struct rerr { + int code; + char *name; + char *explain; +} rerrs[] = { + {REG_NOMATCH, "REG_NOMATCH", "regexec() failed to match"}, + {REG_BADPAT, "REG_BADPAT", "invalid regular expression"}, + {REG_ECOLLATE, "REG_ECOLLATE", "invalid collating element"}, + {REG_ECTYPE, "REG_ECTYPE", "invalid character class"}, + {REG_EESCAPE, "REG_EESCAPE", "trailing backslash (\\)"}, + {REG_ESUBREG, "REG_ESUBREG", "invalid backreference number"}, + {REG_EBRACK, "REG_EBRACK", "brackets ([ ]) not balanced"}, + {REG_EPAREN, "REG_EPAREN", "parentheses not balanced"}, + {REG_EBRACE, "REG_EBRACE", "braces not balanced"}, + {REG_BADBR, "REG_BADBR", "invalid repetition count(s)"}, + {REG_ERANGE, "REG_ERANGE", "invalid character range"}, + {REG_ESPACE, "REG_ESPACE", "out of memory"}, + {REG_BADRPT, "REG_BADRPT", "repetition-operator operand invalid"}, + {REG_EMPTY, "REG_EMPTY", "empty (sub)expression"}, + {REG_ASSERT, "REG_ASSERT", "\"can't happen\" -- you found a bug"}, + {REG_INVARG, "REG_INVARG", "invalid argument to regex routine"}, + {0, "", "*** unknown regexp error code ***"} +}; + +/* + - regerror - the interface to error numbers + = extern size_t regerror(int, const regex_t *, char *, size_t); + */ +/* ARGSUSED */ +size_t __stdcall +regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) +{ + register struct rerr *r; + register size_t len; + register int target = errcode &~ REG_ITOA; + register char *s; + char convbuf[50]; + + if (errcode == REG_ATOI) + s = regatoi(preg, convbuf); + else { + for (r = rerrs; r->code != 0; r++) + if (r->code == target) + break; + + if (errcode®_ITOA) { + if (r->code != 0) + (void) strcpy(convbuf, r->name); + else + sprintf(convbuf, "REG_0x%x", target); + assert(strlen(convbuf) < sizeof(convbuf)); + s = convbuf; + } else + s = r->explain; + } + + len = strlen(s) + 1; + if (errbuf_size > 0) { + if (errbuf_size > len) + (void) strcpy(errbuf, s); + else { + (void) strncpy(errbuf, s, errbuf_size-1); + errbuf[errbuf_size-1] = '\0'; + } + } + + return(len); +} + +/* + - regatoi - internal routine to implement REG_ATOI + == static char *regatoi(const regex_t *preg, char *localbuf); + */ +static char * +regatoi(const regex_t *preg, char *localbuf) +{ + register struct rerr *r; + + for (r = rerrs; r->code != 0; r++) + if (strcmp(r->name, preg->re_endp) == 0) + break; + if (r->code == 0) + return("0"); + + sprintf(localbuf, "%d", r->code); + return(localbuf); +} diff --git a/regex/regex.doc b/regex/regex.doc new file mode 100644 index 00000000..100be4fb --- /dev/null +++ b/regex/regex.doc @@ -0,0 +1,462 @@ + + + +REGEX(3) C Library Functions REGEX(3) + + + +NAME + regcomp, regexec, regerror, regfree - regular-expression + library + +SYNOPSIS + #include <sys/types.h> + #include <regex.h> + + int regcomp(regex_t *preg, const char *pattern, int cflags); + + int regexec(const regex_t *preg, const char *string, + size_t nmatch, regmatch_t pmatch[], int eflags); + + size_t regerror(int errcode, const regex_t *preg, + char *errbuf, size_t errbuf_size); + + void regfree(regex_t *preg); + +DESCRIPTION + These routines implement POSIX 1003.2 regular expressions + (``RE''s); see re_format(7). Regcomp compiles an RE written + as a string into an internal form, regexec matches that + internal form against a string and reports results, regerror + transforms error codes from either into human-readable mes- + sages, and regfree frees any dynamically-allocated storage + used by the internal form of an RE. + + The header <regex.h> declares two structure types, regex_t + and regmatch_t, the former for compiled internal forms and + the latter for match reporting. It also declares the four + functions, a type regoff_t, and a number of constants with + names starting with ``REG_''. + + Regcomp compiles the regular expression contained in the + pattern string, subject to the flags in cflags, and places + the results in the regex_t structure pointed to by preg. + Cflags is the bitwise OR of zero or more of the following + flags: + + REG_EXTENDED Compile modern (``extended'') REs, rather than + the obsolete (``basic'') REs that are the + default. + + REG_BASIC This is a synonym for 0, provided as a coun- + terpart to REG_EXTENDED to improve readabil- + ity. + + REG_NOSPEC Compile with recognition of all special char- + acters turned off. All characters are thus + considered ordinary, so the ``RE'' is a + literal string. This is an extension, compa- + tible with but not specified by POSIX 1003.2, + + + +SunOS 5.5 Last change: March 20, 1994 1 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + and should be used with caution in software + intended to be portable to other systems. + REG_EXTENDED and REG_NOSPEC may not be used in + the same call to regcomp. + + REG_ICASE Compile for matching that ignores upper/lower + case distinctions. See re_format(7). + + REG_NOSUB Compile for matching that need only report + success or failure, not what was matched. + + REG_NEWLINE Compile for newline-sensitive matching. By + default, newline is a completely ordinary + character with no special meaning in either + REs or strings. With this flag, `[^' bracket + expressions and `.' never match newline, a `^' + anchor matches the null string after any new- + line in the string in addition to its normal + function, and the `$' anchor matches the null + string before any newline in the string in + addition to its normal function. + + REG_PEND The regular expression ends, not at the first + NUL, but just before the character pointed to + by the re_endp member of the structure pointed + to by preg. The re_endp member is of type + const char *. This flag permits inclusion of + NULs in the RE; they are considered ordinary + characters. This is an extension, compatible + with but not specified by POSIX 1003.2, and + should be used with caution in software + intended to be portable to other systems. + + When successful, regcomp returns 0 and fills in the struc- + ture pointed to by preg. One member of that structure + (other than re_endp) is publicized: re_nsub, of type + size_t, contains the number of parenthesized subexpressions + within the RE (except that the value of this member is unde- + fined if the REG_NOSUB flag was used). If regcomp fails, it + returns a non-zero error code; see DIAGNOSTICS. + + Regexec matches the compiled RE pointed to by preg against + the string, subject to the flags in eflags, and reports + results using nmatch, pmatch, and the returned value. The + RE must have been compiled by a previous invocation of + regcomp. The compiled form is not altered during execution + of regexec, so a single compiled RE can be used simultane- + ously by multiple threads. + + By default, the NUL-terminated string pointed to by string + is considered to be the text of an entire line, minus any + terminating newline. The eflags argument is the bitwise OR + + + +SunOS 5.5 Last change: March 20, 1994 2 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + of zero or more of the following flags: + + REG_NOTBOL The first character of the string is not the + beginning of a line, so the `^' anchor should + not match before it. This does not affect the + behavior of newlines under REG_NEWLINE. + + REG_NOTEOL The NUL terminating the string does not end a + line, so the `$' anchor should not match + before it. This does not affect the behavior + of newlines under REG_NEWLINE. + + REG_STARTEND The string is considered to start at string + + pmatch[0].rm_so and to have a terminating NUL + located at string + pmatch[0].rm_eo (there + need not actually be a NUL at that location), + regardless of the value of nmatch. See below + for the definition of pmatch and nmatch. This + is an extension, compatible with but not + specified by POSIX 1003.2, and should be used + with caution in software intended to be port- + able to other systems. Note that a non-zero + rm_so does not imply REG_NOTBOL; REG_STARTEND + affects only the location of the string, not + how it is matched. + + See re_format(7) for a discussion of what is matched in + situations where an RE or a portion thereof could match any + of several substrings of string. + + Normally, regexec returns 0 for success and the non-zero + code REG_NOMATCH for failure. Other non-zero error codes + may be returned in exceptional situations; see DIAGNOSTICS. + + If REG_NOSUB was specified in the compilation of the RE, or + if nmatch is 0, regexec ignores the pmatch argument (but see + below for the case where REG_STARTEND is specified). Other- + wise, pmatch points to an array of nmatch structures of type + regmatch_t. Such a structure has at least the members rm_so + and rm_eo, both of type regoff_t (a signed arithmetic type + at least as large as an off_t and a ssize_t), containing + respectively the offset of the first character of a sub- + string and the offset of the first character after the end + of the substring. Offsets are measured from the beginning + of the string argument given to regexec. An empty substring + is denoted by equal offsets, both indicating the character + following the empty substring. + + The 0th member of the pmatch array is filled in to indicate + what substring of string was matched by the entire RE. + Remaining members report what substring was matched by + parenthesized subexpressions within the RE; member i reports + + + +SunOS 5.5 Last change: March 20, 1994 3 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + subexpression i, with subexpressions counted (starting at 1) + by the order of their opening parentheses in the RE, left to + right. Unused entries in the array-corresponding either to + subexpressions that did not participate in the match at all, + or to subexpressions that do not exist in the RE (that is, + i > preg->re_nsub)-have both rm_so and rm_eo set to -1. If + a subexpression participated in the match several times, the + reported substring is the last one it matched. (Note, as an + example in particular, that when the RE `(b*)+' matches + `bbb', the parenthesized subexpression matches each of the + three `b's and then an infinite number of empty strings fol- + lowing the last `b', so the reported substring is one of the + empties.) + + If REG_STARTEND is specified, pmatch must point to at least + one regmatch_t (even if nmatch is 0 or REG_NOSUB was speci- + fied), to hold the input offsets for REG_STARTEND. Use for + output is still entirely controlled by nmatch; if nmatch is + 0 or REG_NOSUB was specified, the value of pmatch[0] will + not be changed by a successful regexec. + + Regerror maps a non-zero errcode from either regcomp or + regexec to a human-readable, printable message. If preg is + non-NULL, the error code should have arisen from use of the + regex_t pointed to by preg, and if the error code came from + regcomp, it should have been the result from the most recent + regcomp using that regex_t. (Regerror may be able to supply + a more detailed message using information from the regex_t.) + Regerror places the NUL-terminated message into the buffer + pointed to by errbuf, limiting the length (including the + NUL) to at most errbuf_size bytes. If the whole message + won't fit, as much of it as will fit before the terminating + NUL is supplied. In any case, the returned value is the + size of buffer needed to hold the whole message (including + terminating NUL). If errbuf_size is 0, errbuf is ignored + but the return value is still correct. + + If the errcode given to regerror is first ORed with + REG_ITOA, the ``message'' that results is the printable name + of the error code, e.g. ``REG_NOMATCH'', rather than an + explanation thereof. If errcode is REG_ATOI, then preg + shall be non-NULL and the re_endp member of the structure it + points to must point to the printable name of an error code; + in this case, the result in errbuf is the decimal digits of + the numeric value of the error code (0 if the name is not + recognized). REG_ITOA and REG_ATOI are intended primarily + as debugging facilities; they are extensions, compatible + with but not specified by POSIX 1003.2, and should be used + with caution in software intended to be portable to other + systems. Be warned also that they are considered experimen- + tal and changes are possible. + + + + +SunOS 5.5 Last change: March 20, 1994 4 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + Regfree frees any dynamically-allocated storage associated + with the compiled RE pointed to by preg. The remaining + regex_t is no longer a valid compiled RE and the effect of + supplying it to regexec or regerror is undefined. + + None of these functions references global variables except + for tables of constants; all are safe for use from multiple + threads if the arguments are safe. + +IMPLEMENTATION CHOICES + There are a number of decisions that 1003.2 leaves up to the + implementor, either by explicitly saying ``undefined'' or by + virtue of them being forbidden by the RE grammar. This + implementation treats them as follows. + + See re_format(7) for a discussion of the definition of + case-independent matching. + + There is no particular limit on the length of REs, except + insofar as memory is limited. Memory usage is approximately + linear in RE size, and largely insensitive to RE complexity, + except for bounded repetitions. See BUGS for one short RE + using them that will run almost any system out of memory. + + A backslashed character other than one specifically given a + magic meaning by 1003.2 (such magic meanings occur only in + obsolete [``basic''] REs) is taken as an ordinary character. + + Any unmatched [ is a REG_EBRACK error. + + Equivalence classes cannot begin or end bracket-expression + ranges. The endpoint of one range cannot begin another. + + RE_DUP_MAX, the limit on repetition counts in bounded + repetitions, is 255. + + A repetition operator (?, *, +, or bounds) cannot follow + another repetition operator. A repetition operator cannot + begin an expression or subexpression or follow `^' or `|'. + + `|' cannot appear first or last in a (sub)expression or + after another `|', i.e. an operand of `|' cannot be an empty + subexpression. An empty parenthesized subexpression, `()', + is legal and matches an empty (sub)string. An empty string + is not a legal RE. + + A `{' followed by a digit is considered the beginning of + bounds for a bounded repetition, which must then follow the + syntax for bounds. A `{' not followed by a digit is con- + sidered an ordinary character. + + + + + +SunOS 5.5 Last change: March 20, 1994 5 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + `^' and `$' beginning and ending subexpressions in obsolete + (``basic'') REs are anchors, not ordinary characters. + +SEE ALSO + grep(1), re_format(7) + + POSIX 1003.2, sections 2.8 (Regular Expression Notation) and + B.5 (C Binding for Regular Expression Matching). + +DIAGNOSTICS + Non-zero error codes from regcomp and regexec include the + following: + + REG_NOMATCH regexec() failed to match + REG_BADPAT invalid regular expression + REG_ECOLLATE invalid collating element + REG_ECTYPE invalid character class + REG_EESCAPE \ applied to unescapable character + REG_ESUBREG invalid backreference number + REG_EBRACK brackets [ ] not balanced + REG_EPAREN parentheses ( ) not balanced + REG_EBRACE braces { } not balanced + REG_BADBR invalid repetition count(s) in { } + REG_ERANGE invalid character range in [ ] + REG_ESPACE ran out of memory + REG_BADRPT ?, *, or + operand invalid + REG_EMPTY empty (sub)expression + REG_ASSERT ``can't happen''-you found a bug + REG_INVARG invalid argument, e.g. negative-length string + +HISTORY + Originally written by Henry Spencer. Altered for inclusion + in the 4.4BSD distribution. + +BUGS + This is an alpha release with known defects. Please report + problems. + + There is one known functionality bug. The implementation of + internationalization is incomplete: the locale is always + assumed to be the default one of 1003.2, and only the col- + lating elements etc. of that locale are available. + + The back-reference code is subtle and doubts linger about + its correctness in complex cases. + + Regexec performance is poor. This will improve with later + releases. Nmatch exceeding 0 is expensive; nmatch exceeding + 1 is worse. Regexec is largely insensitive to RE complexity + except that back references are massively expensive. RE + length does matter; in particular, there is a strong speed + bonus for keeping RE length under about 30 characters, with + + + +SunOS 5.5 Last change: March 20, 1994 6 + + + + + + +REGEX(3) C Library Functions REGEX(3) + + + + most special characters counting roughly double. + + Regcomp implements bounded repetitions by macro expansion, + which is costly in time and space if counts are large or + bounded repetitions are nested. An RE like, say, + `((((a{1,100}){1,100}){1,100}){1,100}){1,100}' will (eventu- + ally) run almost any existing machine out of swap space. + + There are suspected problems with response to obscure error + conditions. Notably, certain kinds of internal overflow, + produced only by truly enormous REs or by multiply nested + bounded repetitions, are probably not handled well. + + Due to a mistake in 1003.2, things like `a)b' are legal REs + because `)' is a special character only in the presence of a + previous unmatched `('. This can't be fixed until the spec + is fixed. + + The standard's definition of back references is vague. For + example, does `a\(\(b\)*\2\)*d' match `abbbd'? Until the + standard is clarified, behavior in such cases should not be + relied on. + + The implementation of word-boundary matching is a bit of a + kludge, and bugs may lurk in combinations of word-boundary + matching and anchoring. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +SunOS 5.5 Last change: March 20, 1994 7 + + + diff --git a/regex/regex.h b/regex/regex.h new file mode 100644 index 00000000..8d11536e --- /dev/null +++ b/regex/regex.h @@ -0,0 +1,117 @@ +
+
+/*-
+ * Copyright (c) 1992 Henry Spencer.
+ * Copyright (c) 1992, 1993
+ * The Regents of the University of California. All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Henry Spencer of the University of Toronto.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ * must display the following acknowledgement:
+ * This product includes software developed by the University of
+ * California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * @(#)regex.h 8.2 (Berkeley) 1/3/94
+ */
+
+#ifndef _REGEX_H_
+#define _REGEX_H_
+
+#ifdef WIN32
+#include <sys/types.h>
+#define __const
+#define __BEGIN_DECLS
+#define __END_DECLS
+#define __P(_X) _X
+#else
+#include <sys/cdefs.h>
+#define __stdcall
+#endif
+
+/* types */
+typedef off_t regoff_t;
+
+typedef struct {
+ int re_magic;
+ size_t re_nsub; /* number of parenthesized subexpressions */
+ __const char *re_endp; /* end pointer for REG_PEND */
+ struct re_guts *re_g; /* none of your business :-) */
+} regex_t;
+
+typedef struct {
+ regoff_t rm_so; /* start of match */
+ regoff_t rm_eo; /* end of match */
+} regmatch_t;
+
+/* regcomp() flags */
+#define REG_BASIC 0000
+#define REG_EXTENDED 0001
+#define REG_ICASE 0002
+#define REG_NOSUB 0004
+#define REG_NEWLINE 0010
+#define REG_NOSPEC 0020
+#define REG_PEND 0040
+#define REG_DUMP 0200
+
+/* regerror() flags */
+#define REG_NOMATCH 1
+#define REG_BADPAT 2
+#define REG_ECOLLATE 3
+#define REG_ECTYPE 4
+#define REG_EESCAPE 5
+#define REG_ESUBREG 6
+#define REG_EBRACK 7
+#define REG_EPAREN 8
+#define REG_EBRACE 9
+#define REG_BADBR 10
+#define REG_ERANGE 11
+#define REG_ESPACE 12
+#define REG_BADRPT 13
+#define REG_EMPTY 14
+#define REG_ASSERT 15
+#define REG_INVARG 16
+#define REG_ATOI 255 /* convert name to number (!) */
+#define REG_ITOA 0400 /* convert number to name (!) */
+
+/* regexec() flags */
+#define REG_NOTBOL 00001
+#define REG_NOTEOL 00002
+#define REG_STARTEND 00004
+#define REG_TRACE 00400 /* tracing of execution */
+#define REG_LARGE 01000 /* force large representation */
+#define REG_BACKR 02000 /* force use of backref code */
+
+__BEGIN_DECLS
+int __stdcall regcomp __P((regex_t *, const char *, int));
+size_t __stdcall regerror __P((int, const regex_t *, char *, size_t));
+int __stdcall regexec __P((const regex_t *,
+ const char *, size_t, regmatch_t [], int));
+void __stdcall regfree __P((regex_t *));
+__END_DECLS
+
+#endif /* !_REGEX_H_ */
diff --git a/regex/regex2.h b/regex/regex2.h new file mode 100644 index 00000000..64b62121 --- /dev/null +++ b/regex/regex2.h @@ -0,0 +1,173 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)regex2.h 8.4 (Berkeley) 3/20/94 + */ + +/* + * First, the stuff that ends up in the outside-world include file + = typedef off_t regoff_t; + = typedef struct { + = int re_magic; + = size_t re_nsub; // number of parenthesized subexpressions + = const char *re_endp; // end pointer for REG_PEND + = struct re_guts *re_g; // none of your business :-) + = } regex_t; + = typedef struct { + = regoff_t rm_so; // start of match + = regoff_t rm_eo; // end of match + = } regmatch_t; + */ +/* + * internals of regex_t + */ +#define MAGIC1 ((('r'^0200)<<8) | 'e') + +/* + * The internal representation is a *strip*, a sequence of + * operators ending with an endmarker. (Some terminology etc. is a + * historical relic of earlier versions which used multiple strips.) + * Certain oddities in the representation are there to permit running + * the machinery backwards; in particular, any deviation from sequential + * flow must be marked at both its source and its destination. Some + * fine points: + * + * - OPLUS_ and O_PLUS are *inside* the loop they create. + * - OQUEST_ and O_QUEST are *outside* the bypass they create. + * - OCH_ and O_CH are *outside* the multi-way branch they create, while + * OOR1 and OOR2 are respectively the end and the beginning of one of + * the branches. Note that there is an implicit OOR2 following OCH_ + * and an implicit OOR1 preceding O_CH. + * + * In state representations, an operator's bit is on to signify a state + * immediately *preceding* "execution" of that operator. + */ +typedef unsigned long sop; /* strip operator */ +typedef long sopno; +#define OPRMASK 0xf8000000 +#define OPDMASK 0x07ffffff +#define OPSHIFT ((unsigned)27) +#define OP(n) ((n)&OPRMASK) +#define OPND(n) ((n)&OPDMASK) +#define SOP(op, opnd) ((op)|(opnd)) +/* operators meaning operand */ +/* (back, fwd are offsets) */ +#define OEND (1<<OPSHIFT) /* endmarker - */ +#define OCHAR (2<<OPSHIFT) /* character unsigned char */ +#define OBOL (3<<OPSHIFT) /* left anchor - */ +#define OEOL (4<<OPSHIFT) /* right anchor - */ +#define OANY (5<<OPSHIFT) /* . - */ +#define OANYOF (6<<OPSHIFT) /* [...] set number */ +#define OBACK_ (7<<OPSHIFT) /* begin \d paren number */ +#define O_BACK (8<<OPSHIFT) /* end \d paren number */ +#define OPLUS_ (9<<OPSHIFT) /* + prefix fwd to suffix */ +#define O_PLUS (10<<OPSHIFT) /* + suffix back to prefix */ +#define OQUEST_ (11<<OPSHIFT) /* ? prefix fwd to suffix */ +#define O_QUEST (12<<OPSHIFT) /* ? suffix back to prefix */ +#define OLPAREN (13<<OPSHIFT) /* ( fwd to ) */ +#define ORPAREN (14<<OPSHIFT) /* ) back to ( */ +#define OCH_ (15<<OPSHIFT) /* begin choice fwd to OOR2 */ +#define OOR1 (16<<OPSHIFT) /* | pt. 1 back to OOR1 or OCH_ */ +#define OOR2 (17<<OPSHIFT) /* | pt. 2 fwd to OOR2 or O_CH */ +#define O_CH (18<<OPSHIFT) /* end choice back to OOR1 */ +#define OBOW (19<<OPSHIFT) /* begin word - */ +#define OEOW (20<<OPSHIFT) /* end word - */ + +/* + * Structure for [] character-set representation. Character sets are + * done as bit vectors, grouped 8 to a byte vector for compactness. + * The individual set therefore has both a pointer to the byte vector + * and a mask to pick out the relevant bit of each byte. A hash code + * simplifies testing whether two sets could be identical. + * + * This will get trickier for multicharacter collating elements. As + * preliminary hooks for dealing with such things, we also carry along + * a string of multi-character elements, and decide the size of the + * vectors at run time. + */ +typedef struct { + uch *ptr; /* -> uch [csetsize] */ + uch mask; /* bit within array */ + uch hash; /* hash code */ + size_t smultis; + char *multis; /* -> char[smulti] ab\0cd\0ef\0\0 */ +} cset; +/* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */ +#define CHadd(cs, c) ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c)) +#define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c)) +#define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask) +#define MCadd(p, cs, cp) mcadd(p, cs, cp) /* regcomp() internal fns */ +#define MCsub(p, cs, cp) mcsub(p, cs, cp) +#define MCin(p, cs, cp) mcin(p, cs, cp) + +/* stuff for character categories */ +typedef unsigned char cat_t; + +/* + * main compiled-expression structure + */ +struct re_guts { + int magic; +# define MAGIC2 ((('R'^0200)<<8)|'E') + sop *strip; /* malloced area for strip */ + int csetsize; /* number of bits in a cset vector */ + int ncsets; /* number of csets in use */ + cset *sets; /* -> cset [ncsets] */ + uch *setbits; /* -> uch[csetsize][ncsets/CHAR_BIT] */ + int cflags; /* copy of regcomp() cflags argument */ + sopno nstates; /* = number of sops */ + sopno firststate; /* the initial OEND (normally 0) */ + sopno laststate; /* the final OEND */ + int iflags; /* internal flags */ +# define USEBOL 01 /* used ^ */ +# define USEEOL 02 /* used $ */ +# define BAD 04 /* something wrong */ + int nbol; /* number of ^ used */ + int neol; /* number of $ used */ + int ncategories; /* how many character categories */ + cat_t *categories; /* ->catspace[-CHAR_MIN] */ + char *must; /* match must contain this string */ + int mlen; /* length of must */ + size_t nsub; /* copy of re_nsub */ + int backrefs; /* does it use back references? */ + sopno nplus; /* how deep does it nest +s? */ + /* catspace must be last */ + cat_t catspace[1]; /* actually [NC] */ +}; + +/* misc utilities */ +#define OUT (CHAR_MAX+1) /* a non-character value */ +#define ISWORD(c) (isalnum(c) || (c) == '_') diff --git a/regex/regexec.c b/regex/regexec.c new file mode 100644 index 00000000..0c112e53 --- /dev/null +++ b/regex/regexec.c @@ -0,0 +1,176 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)regexec.c 8.3 (Berkeley) 3/20/94 + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)regexec.c 8.3 (Berkeley) 3/20/94"; +#endif /* LIBC_SCCS and not lint */ + +/* + * the outer shell of regexec() + * + * This file includes engine.c *twice*, after muchos fiddling with the + * macros that code uses. This lets the same code operate on two different + * representations for state sets. + */ +#include <sys/types.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <limits.h> +#include <ctype.h> +#include "regex.h" + +#include "utils.h" +#include "regex2.h" + +static int nope = 0; /* for use in asserts; shuts lint up */ + +/* macros for manipulating states, small version */ +#define states long +#define states1 states /* for later use in regexec() decision */ +#define CLEAR(v) ((v) = 0) +#define SET0(v, n) ((v) &= ~(1 << (n))) +#define SET1(v, n) ((v) |= 1 << (n)) +#define ISSET(v, n) ((v) & (1 << (n))) +#define ASSIGN(d, s) ((d) = (s)) +#define EQ(a, b) ((a) == (b)) +#define STATEVARS int dummy /* dummy version */ +#define STATESETUP(m, n) /* nothing */ +#define STATETEARDOWN(m) /* nothing */ +#define SETUP(v) ((v) = 0) +#define onestate int +#define INIT(o, n) ((o) = (unsigned)1 << (n)) +#define INC(o) ((o) <<= 1) +#define ISSTATEIN(v, o) ((v) & (o)) +/* some abbreviations; note that some of these know variable names! */ +/* do "if I'm here, I can also be there" etc without branches */ +#define FWD(dst, src, n) ((dst) |= ((unsigned)(src)&(here)) << (n)) +#define BACK(dst, src, n) ((dst) |= ((unsigned)(src)&(here)) >> (n)) +#define ISSETBACK(v, n) ((v) & ((unsigned)here >> (n))) +/* function names */ +#define SNAMES /* engine.c looks after details */ + +#include "engine.c" + +/* now undo things */ +#undef states +#undef CLEAR +#undef SET0 +#undef SET1 +#undef ISSET +#undef ASSIGN +#undef EQ +#undef STATEVARS +#undef STATESETUP +#undef STATETEARDOWN +#undef SETUP +#undef onestate +#undef INIT +#undef INC +#undef ISSTATEIN +#undef FWD +#undef BACK +#undef ISSETBACK +#undef SNAMES + +/* macros for manipulating states, large version */ +#define states char * +#define CLEAR(v) memset(v, 0, m->g->nstates) +#define SET0(v, n) ((v)[n] = 0) +#define SET1(v, n) ((v)[n] = 1) +#define ISSET(v, n) ((v)[n]) +#define ASSIGN(d, s) memcpy(d, s, m->g->nstates) +#define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0) +#define STATEVARS int vn; char *space +#define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \ + if ((m)->space == NULL) return(REG_ESPACE); \ + (m)->vn = 0; } +#define STATETEARDOWN(m) { free((m)->space); } +#define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates]) +#define onestate int +#define INIT(o, n) ((o) = (n)) +#define INC(o) ((o)++) +#define ISSTATEIN(v, o) ((v)[o]) +/* some abbreviations; note that some of these know variable names! */ +/* do "if I'm here, I can also be there" etc without branches */ +#define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here]) +#define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here]) +#define ISSETBACK(v, n) ((v)[here - (n)]) +/* function names */ +#define LNAMES /* flag */ + +#include "engine.c" + +/* + - regexec - interface for matching + = extern int regexec(const regex_t *, const char *, size_t, \ + = regmatch_t [], int); + = #define REG_NOTBOL 00001 + = #define REG_NOTEOL 00002 + = #define REG_STARTEND 00004 + = #define REG_TRACE 00400 // tracing of execution + = #define REG_LARGE 01000 // force large representation + = #define REG_BACKR 02000 // force use of backref code + * + * We put this here so we can exploit knowledge of the state representation + * when choosing which matcher to call. Also, by this point the matchers + * have been prototyped. + */ +int __stdcall /* 0 success, REG_NOMATCH failure */ +regexec(const regex_t *preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags) +{ + register struct re_guts *g = preg->re_g; +#ifdef REDEBUG +# define GOODFLAGS(f) (f) +#else +# define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND)) +#endif + + if (preg->re_magic != MAGIC1 || g->magic != MAGIC2) + return(REG_BADPAT); + assert(!(g->iflags&BAD)); + if (g->iflags&BAD) /* backstop for no-debug case */ + return(REG_BADPAT); + eflags = GOODFLAGS(eflags); + + if (g->nstates <= CHAR_BIT*sizeof(states1) && !(eflags®_LARGE)) + return(smatcher(g, (char *)string, nmatch, pmatch, eflags)); + else + return(lmatcher(g, (char *)string, nmatch, pmatch, eflags)); +} diff --git a/regex/regfree.c b/regex/regfree.c new file mode 100644 index 00000000..a53341fc --- /dev/null +++ b/regex/regfree.c @@ -0,0 +1,79 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)regfree.c 8.3 (Berkeley) 3/20/94 + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)regfree.c 8.3 (Berkeley) 3/20/94"; +#endif /* LIBC_SCCS and not lint */ + +#include <sys/types.h> +#include <stdio.h> +#include <stdlib.h> +#include "regex.h" + +#include "utils.h" +#include "regex2.h" + +/* + - regfree - free everything + = extern void regfree(regex_t *); + */ +void __stdcall +regfree(regex_t *preg) +{ + register struct re_guts *g; + + if (preg->re_magic != MAGIC1) /* oops */ + return; /* nice to complain, but hard */ + + g = preg->re_g; + if (g == NULL || g->magic != MAGIC2) /* oops again */ + return; + preg->re_magic = 0; /* mark it invalid */ + g->magic = 0; /* mark it invalid */ + + if (g->strip != NULL) + free((char *)g->strip); + if (g->sets != NULL) + free((char *)g->sets); + if (g->setbits != NULL) + free((char *)g->setbits); + if (g->must != NULL) + free(g->must); + free((char *)g); +} diff --git a/regex/utils.h b/regex/utils.h new file mode 100644 index 00000000..efe9836c --- /dev/null +++ b/regex/utils.h @@ -0,0 +1,60 @@ +/*- + * Copyright (c) 1992, 1993, 1994 Henry Spencer. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Henry Spencer. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)utils.h 8.3 (Berkeley) 3/20/94 + */ + +/* utility definitions */
+#ifndef _POSIX2_RE_DUP_MAX
+#define _POSIX2_RE_DUP_MAX 255
+#endif +#define DUPMAX _POSIX2_RE_DUP_MAX /* xxx is this right? */ +#define INFINITY (DUPMAX + 1) +#define NC (CHAR_MAX - CHAR_MIN + 1) +typedef unsigned char uch; + +/* switch off assertions (if not already off) if no REDEBUG */ +#ifndef REDEBUG +#ifndef NDEBUG +#define NDEBUG /* no assertions please */ +#endif +#endif +#include <assert.h> + +/* for old systems with bcopy() but no memmove() */ +#ifdef USEBCOPY +#define memmove(d, s, c) bcopy(s, d, c) +#endif |