system/freebsd-src
system/freebsd-src
1
0
Fork 0
mirror of https://github.com/freebsd/freebsd-src synced 2024-07-21 02:06:37 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

gnu: remove gnugrep and libgnuregex

Browse source 
Differential Revision:	https://reviews.freebsd.org/D27732
This commit is contained in:
Kyle Evans 2020-12-22 15:38:09 -06:00
parent d1c965f143
commit 47d1ad2413
69 changed files with 0 additions and 18129 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
gnu/lib/libregex/Makefile
View file

@ -1,32 +0,0 @@
# $FreeBSD$
LIB= gnuregex
SHLIB_MAJOR= 5
REGEXDIR= ${SRCTOP}/contrib/libgnuregex
.PATH: ${REGEXDIR}
WARNS?= 1
SRCS= gnuregex.c
INCSGROUPS= INCS WRINCS PXINCS
INCS= regex.h.patched
INCSNAME= regex.h
INCSDIR= ${INCLUDEDIR}/gnu
WRINCS= gnuregex.h
PXINCS= ${REGEXDIR}/regex.h
PXINCSDIR= ${INCSDIR}/posix
CFLAGS+= -D__attribute_warn_unused_result__=""
CFLAGS+= -DHAVE_CONFIG_H -I${.CURDIR} -I${REGEXDIR}
CLEANFILES= regex.h.patched gnuregex.c
regex.h.patched: regex.h
sed 's=<posix/regex\.h>=<gnu/posix/regex.h>=g' \
< ${.ALLSRC} > ${.TARGET}
gnuregex.c: regex.c
sed 's=<regex\.h>=<gnu/regex.h>=g' \
< ${.ALLSRC} > ${.TARGET}
.include <bsd.lib.mk>

16
gnu/lib/libregex/Makefile.depend
View file

@ -1,16 +0,0 @@
# $FreeBSD$
# Autogenerated - do NOT edit!
DIRDEPS = \
include \
include/xlocale \
lib/${CSU_DIR} \
lib/libc \
lib/libcompiler_rt \
.include <dirdeps.mk>
.if ${DEP_RELDIR} == ${_DEP_RELDIR}
# local dependencies - needed for -jN in clean tree
.endif

15
gnu/lib/libregex/config.h
View file

@ -1,15 +0,0 @@
/* $FreeBSD$ */
#define _REGEX_RE_COMP 1
#define HAVE_LANGINFO_H 1
#define HAVE_LANGINFO_CODESET 1
#define HAVE_LOCALE_H 1
#define HAVE_WCHAR_H 1
#define HAVE_WCTYPE_H 1
#define HAVE_ISBLANK 1
#define HAVE_WCRTOMB 1
#define HAVE_MBRTOWC 1
#define HAVE_WCSCOLL 1
#define HAVE_ALLOCA 1
#define HAVE_STDBOOL_H 1
#define HAVE_STDINT_H 1

33
gnu/lib/libregex/gnuregex.h
View file

@ -1,33 +0,0 @@
/*-
* Copyright (c) 2004 David E. O'Brien
* Copyright (c) 2004 Andrey A. Chernov
* All rights reserved.
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
*
* $FreeBSD$
*/
#ifdef __GNUC__
#warning "Use -I/usr/include/gnu and <regex.h> instead of <gnuregex.h>"
#endif
#include <gnu/regex.h>

54
gnu/lib/libregex/regex.h
View file

@ -1,54 +0,0 @@
/* $FreeBSD$ */
#ifndef _REGEX_H
#ifndef __USE_GNU
#define __USE_GNU
#endif
#include <posix/regex.h>
/* Document internal interfaces. */
extern reg_syntax_t __re_set_syntax (reg_syntax_t __syntax);
extern const char *__re_compile_pattern (const char *__pattern, size_t __length,
struct re_pattern_buffer *__buffer);
extern int __re_compile_fastmap (struct re_pattern_buffer *__buffer);
extern int __re_search (struct re_pattern_buffer *__buffer, const char *__string,
int __length, int __start, int __range,
struct re_registers *__regs);
extern int __re_search_2 (struct re_pattern_buffer *__buffer,
const char *__string1, int __length1,
const char *__string2, int __length2, int __start,
int __range, struct re_registers *__regs, int __stop);
extern int __re_match (struct re_pattern_buffer *__buffer, const char *__string,
int __length, int __start, struct re_registers *__regs);
extern int __re_match_2 (struct re_pattern_buffer *__buffer,
const char *__string1, int __length1,
const char *__string2, int __length2, int __start,
struct re_registers *__regs, int __stop);
extern void __re_set_registers (struct re_pattern_buffer *__buffer,
struct re_registers *__regs,
unsigned int __num_regs,
regoff_t *__starts, regoff_t *__ends);
extern int __regcomp (regex_t *__restrict __preg,
const char *__restrict __pattern,
int __cflags);
extern int __regexec (const regex_t *__restrict __preg,
const char *__restrict __string, size_t __nmatch,
regmatch_t __pmatch[__restrict_arr],
int __eflags);
extern size_t __regerror (int __errcode, const regex_t *__restrict __preg,
char *__restrict __errbuf, size_t __errbuf_size);
extern void __regfree (regex_t *__preg);
#endif /* _REGEX_H */

44
gnu/usr.bin/grep/AUTHORS
View file

@ -1,44 +0,0 @@
Mike Haertel wrote the main program and the dfa and kwset matchers.
Arthur David Olson contributed the heuristics for finding fixed substrings
at the end of dfa.c.
Richard Stallman and Karl Berry wrote the regex backtracking matcher.
Henry Spencer wrote the original test suite from which grep's was derived.
Scott Anderson invented the Khadafy test.
David MacKenzie wrote the automatic configuration software use to
produce the configure script.
Authors of the replacements for standard library routines are identified
in the corresponding source files.
The idea of using Boyer-Moore type algorithms to quickly filter out
non-matching text before calling the regexp matcher was originally due
to James Woods. He also contributed some code to early versions of
GNU grep.
Mike Haertel would like to thank Andrew Hume for many fascinating discussions
of string searching issues over the years. Hume & Sunday's excellent
paper on fast string searching (AT&T Bell Laboratories CSTR #156)
describes some of the history of the subject, as well as providing
exhaustive performance analysis of various implementation alternatives.
The inner loop of GNU grep is similar to Hume & Sunday's recommended
"Tuned Boyer Moore" inner loop.
More work was done on regex.[ch] by Ulrich Drepper and Arnold
Robbins. Regex is now part of GNU C library, see this package
for complete details and credits.
Arnold Robbins contributed to improve dfa.[ch]. In fact
it came straight from gawk-3.0.3 with small editing and fixes.
Many folks contributed see THANKS, if I omited someone please
send me email.
Alain Magloire maintained GNU grep until version 2.5e.
Bernhard "Bero" Rosenkränzer <bero@redhat.com> is the current maintainer.

340
gnu/usr.bin/grep/COPYING
View file

@ -1,340 +0,0 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Library General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) 19yy <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) 19yy name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Library General
Public License instead of this License.

2477
gnu/usr.bin/grep/ChangeLog
View file

File diff suppressed because it is too large Load diff

37
gnu/usr.bin/grep/FREEBSD-upgrade
View file

@ -1,37 +0,0 @@
$FreeBSD$
GNU grep
Original source distribution can be found at:
http://ftp.gnu.org/pub/gnu/grep/
Due to an unfortunate number of bugs and performance problems in
GNU grep 2.5.1, various patches from The Fedora Project have been applied.
These patches can be extracted from the SRPM package available at:
http://download.fedora.redhat.com/pub/fedora/linux/core/test/
3.92/SRPMS/grep-2.5.1-48.src.rpm
The following patches have been applied:
grep-2.5-i18n.patch
grep-2.5.1-bracket.patch
grep-2.5.1-color.patch
grep-2.5.1-dfa-optional.patch
grep-2.5.1-egf-speedup.patch
grep-2.5.1-fgrep.patch
grep-2.5.1-icolor.patch
grep-2.5.1-oi.patch
grep-2.5.1-w.patch
In addition to these, some FreeBSD-specific changes have been made
to add bzip2 support, etc.
Due to the large number of patches applied, conflicts are likely with
future releases. However, most of the patches are either (a) small bug
fixes that have been fed upstream, or (b) performance improvements that
could be reverted without loss of functionality.
It is suggested that those planning to import a newer release of GNU grep
should revert all local changes since the 2.5.1 import before proceeding
with the newer import.

58
gnu/usr.bin/grep/Makefile
View file

@ -1,58 +0,0 @@
# $FreeBSD$
.include <src.opts.mk>
GREP_LIBZ=YES
.if ${MK_BSD_GREP} != "yes"
PROG= grep
.else
PROG= gnugrep
.endif
SRCS= closeout.c dfa.c error.c exclude.c grep.c grepmat.c hard-locale.c \
isdir.c kwset.c obstack.c quotearg.c savedir.c search.c xmalloc.c \
xstrtoumax.c
CLEANFILES+= gnugrep.1
WARNS?= 0
CFLAGS+=-I${.CURDIR} -I${SYSROOT:U${DESTDIR}}/usr/include/gnu -DHAVE_CONFIG_H
.if ${MK_BSD_GREP} != "yes"
LINKS+= ${BINDIR}/grep ${BINDIR}/egrep \
${BINDIR}/grep ${BINDIR}/fgrep
MLINKS= grep.1 egrep.1 grep.1 fgrep.1
.endif
LIBADD= gnuregex bz2
.if defined(GREP_LIBZ) && !empty(GREP_LIBZ)
LIBADD+= z
CFLAGS+=-DHAVE_LIBZ=1
.endif
gnugrep.1: grep.1
${CP} ${.ALLSRC} ${.TARGET}
check: all
@failed=0; total=0; \
for tst in ${TESTS}; do \
total=$$(($$total+1)); \
if GREP=${.OBJDIR}/${PROG} srcdir=${.CURDIR}/tests \
${.CURDIR}/tests/$$tst; then \
echo "PASS: $$tst"; \
else \
failed=$$(($$failed+1)); \
echo "FAIL: $$tst"; \
fi; \
done; \
if [ "$$failed" -eq 0 ]; then \
echo "All $$total tests passed"; \
else \
echo "$$failed of $$total tests failed"; \
fi
TESTS= warning.sh khadafy.sh spencer1.sh bre.sh ere.sh status.sh empty.sh \
options.sh backref.sh file.sh
.include <bsd.prog.mk>

20
gnu/usr.bin/grep/Makefile.depend
View file

@ -1,20 +0,0 @@
# $FreeBSD$
# Autogenerated - do NOT edit!
DIRDEPS = \
gnu/lib/csu \
gnu/lib/libregex \
include \
include/xlocale \
lib/${CSU_DIR} \
lib/libbz2 \
lib/libc \
lib/libcompiler_rt \
lib/libz \
.include <dirdeps.mk>
.if ${DEP_RELDIR} == ${_DEP_RELDIR}
# local dependencies - needed for -jN in clean tree
.endif

238
gnu/usr.bin/grep/NEWS
View file

@ -1,238 +0,0 @@
Version 2.5.1
- This is a bugfix release. No new features.
Version 2.5
- The new option --label allows to specify a different name for input
from stdin. See the man or info pages for details.
- The internal lib/getopt* files are no longer used on systems providing
getopt functionality in their libc (e.g. glibc 2.2.x).
If you need the old getopt files, use --with-included-getopt.
- The new option --only-matching (-o) will print only the part of matching
lines that matches the pattern. This is useful, for example, to extract
IP addresses from log files.
- i18n bug fixed ([A-Z0-9] wouldn't match A in locales other than C on
systems using recent glibc builds
- GNU grep can now be built with autoconf 2.52.
- The new option --devices controls how grep handles device files. Its usage
is analogous to --directories.
- The new option --line-buffered fflush on everyline. There is a noticeable
slow down when forcing line buffering.
- Back references are now local to the regex.
grep -e '\(a\)\1' -e '\(b\)\1'
The last backref \1 in the second expression refer to \(b\)
- The new option --include=PATTERN will only search matching files
when recursing in directories
- The new option --exclude=PATTERN will skip matching files when
recursing in directories.
- The new option --color will use the environment variable GREP_COLOR
(default is red) to highlight the matching string.
--color takes an optional argument specifying when to colorize a line:
--color=always, --color=tty, --color=never
- The following changes are for POSIX.2 conformance:
. The -q or --quiet or --silent option now causes grep to exit
with zero status when a input line is selected, even if an error
also occurs.
. The -s or --no-messages option no longer affects the exit status.
. Bracket regular expressions like [a-z] are now locale-dependent.
For example, many locales sort characters in dictionary order,
and in these locales the regular expression [a-d] is not
equivalent to [abcd]; it might be equivalent to [aBbCcDd], for
example. To obtain the traditional interpretation of bracket
expressions, you can use the C locale by setting the LC_ALL
environment variable to the value "C".
- The -C or --context option now requires an argument, partly for
consistency, and partly because POSIX.2 recommends against
optional arguments.
- The new -P or --perl-regexp option tells grep to interpert the pattern as
a Perl regular expression.
- The new option --max-count=num makes grep stop reading a file after num
matching lines.
New option -m; equivalent to --max-count.
- Translations for bg, ca, da, nb and tr have been added.
Version 2.4.2
- Added more check in configure to default the grep-${version}/src/regex.c
instead of the one in GNU Lib C.
Version 2.4.1
- If the final byte of an input file is not a newline, grep now silently
supplies one.
- The new option --binary-files=TYPE makes grep assume that a binary input
file is of type TYPE.
--binary-files='binary' (the default) outputs a 1-line summary of matches.
--binary-files='without-match' assumes binary files do not match.
--binary-files='text' treats binary files as text
(equivalent to the -a or --text option).
- New option -I; equivalent to --binary-files='without-match'.
Version 2.4:
- egrep is now equivalent to `grep -E' as required by POSIX,
removing a longstanding source of confusion and incompatibility.
`grep' is now more forgiving about stray `{'s, for backward
compatibility with traditional egrep.
- The lower bound of an interval is not optional.
You must use an explicit zero, e.g. `x{0,10}' instead of `x{,10}'.
(The old documentation incorrectly claimed that it was optional.)
- The --revert-match option has been renamed to --invert-match.
- The --fixed-regexp option has been renamed to --fixed-string.
- New option -H or --with-filename.
- New option --mmap. By default, GNU grep now uses read instead of mmap.
This is faster on some hosts, and is safer on all.
- The new option -z or --null-data causes `grep' to treat a zero byte
(the ASCII NUL character) as a line terminator in input data, and
to treat newlines as ordinary data.
- The new option -Z or --null causes `grep' to output a zero byte
instead of the normal separator after a file name.
- These two options can be used with commands like `find -print0',
`perl -0', `sort -z', and `xargs -0' to process arbitrary file names,
even those that contain newlines.
- The environment variable GREP_OPTIONS specifies default options;
e.g. GREP_OPTIONS='--directories=skip' reestablishes grep 2.1's
behavior of silently skipping directories.
- You can specify a matcher multiple times without error, e.g.
`grep -E -E' or `fgrep -F'. It is still an error to specify
conflicting matchers.
- -u and -U are now allowed on non-DOS hosts, and have no effect.
- Modifications of the tests scripts to go around the "Broken Pipe"
errors from bash. See Bash FAQ.
- New option -r or --recursive or --directories=recurse.
(This option was also in grep 2.3, but wasn't announced here.)
- --without-included-regex disable, was causing bogus reports .i.e
doing more harm then good.
Version 2.3:
- When searching a binary file FOO, grep now just reports
`Binary file FOO matches' instead of outputting binary data.
This is typically more useful than the old behavior,
and it is also more consistent with other utilities like `diff'.
A file is considered to be binary if it contains a NUL (i.e. zero) byte.
The new -a or --text option causes `grep' to assume that all
input is text. (This option has the same meaning as with `diff'.)
Use it if you want binary data in your output.
- `grep' now searches directories just like ordinary files; it no longer
silently skips directories. This is the traditional behavior of
Unix text utilities (in particular, of traditional `grep').
Hence `grep PATTERN DIRECTORY' should report
`grep: DIRECTORY: Is a directory' on hosts where the operating system
does not permit programs to read directories directly, and
`grep: DIRECTORY: Binary file matches' (or nothing) otherwise.
The new -d ACTION or --directories=ACTION option affects directory handling.
`-d skip' causes `grep' to silently skip directories, as in grep 2.1;
`-d read' (the default) causes `grep' to read directories if possible,
as in earlier versions of grep.
- The MS-DOS and Microsoft Windows ports now behave identically to the
GNU and Unix ports with respect to binary files and directories.
Version 2.2:
Bug fix release.
- Status error number fix.
- Skipping directories removed.
- Many typos fix.
- -f /dev/null fix(not to consider as an empty pattern).
- Checks for wctype/wchar.
- -E was using the wrong matcher fix.
- bug in regex char class fix
- Fixes for DJGPP
Version 2.1:
This is a bug fix release(see Changelog) i.e. no new features.
- More compliance to GNU standard.
- Long options.
- Internationalisation.
- Use automake/autoconf.
- Directory hierarchy change.
- Sigvec with -e on Linux corrected.
- Sigvec with -f on Linux corrected.
- Sigvec with the mmap() corrected.
- Bug in kwset corrected.
- -q, -L and -l stop on first match.
- New and improve regex.[ch] from Ulrich Drepper.
- New and improve dfa.[ch] from Arnold Robbins.
- Prototypes for over zealous C compiler.
- Not scanning a file, if it's a directory
(cause problems on Sun).
- Ported to MS-DOS/MS-Windows with DJGPP tools.
See Changelog for the full story and proper credits.
Version 2.0:
The most important user visible change is that egrep and fgrep have
disappeared as separate programs into the single grep program mandated
by POSIX 1003.2. New options -G, -E, and -F have been added,
selecting grep, egrep, and fgrep behavior respectively. For
compatibility with historical practice, hard links named egrep and
fgrep are also provided. See the manual page for details.
In addition, the regular expression facilities described in Posix
draft 11.2 are now supported, except for internationalization features
related to locale-dependent collating sequence information.
There is a new option, -L, which is like -l except it lists
files which don't contain matches. The reason this option was
added is because '-l -v' doesn't do what you expect.
Performance has been improved; the amount of improvement is platform
dependent, but (for example) grep 2.0 typically runs at least 30% faster
than grep 1.6 on a DECstation using the MIPS compiler. Where possible,
grep now uses mmap() for file input; on a Sun 4 running SunOS 4.1 this
may cut system time by as much as half, for a total reduction in running
time by nearly 50%. On machines that don't use mmap(), the buffering
code has been rewritten to choose more favorable alignments and buffer
sizes for read().
Portability has been substantially cleaned up, and an automatic
configure script is now provided.
The internals have changed in ways too numerous to mention.
People brave enough to reuse the DFA matcher in other programs
will now have their bravery amply "rewarded", for the interface
to that file has been completely changed. Some changes were
necessary to track the evolution of the regex package, and since
I was changing it anyway I decided to do a general cleanup.

26
gnu/usr.bin/grep/README
View file

@ -1,26 +0,0 @@
This is GNU grep, the "fastest grep in the west" (we hope). All
bugs reported in previous releases have been fixed. Many exciting new
bugs have probably been introduced in this revision.
GNU grep is provided "as is" with no warranty. The exact terms
under which you may use and (re)distribute this program are detailed
in the GNU General Public License, in the file COPYING.
GNU grep is based on a fast lazy-state deterministic matcher (about
twice as fast as stock Unix egrep) hybridized with a Boyer-Moore-Gosper
search for a fixed string that eliminates impossible text from being
considered by the full regexp matcher without necessarily having to
look at every character. The result is typically many times faster
than Unix grep or egrep. (Regular expressions containing backreferencing
will run more slowly, however.)
See the files AUTHORS and THANKS for a list of authors and other contributors.
See the file INSTALL for compilation and installation instructions.
See the file NEWS for a description of major changes in this release.
See the file TODO for ideas on how you could help us improve grep.
Send bug reports to bug-gnu-utils@gnu.org. Be sure to
include the word "grep" in your Subject: header field.

72
gnu/usr.bin/grep/THANKS
View file

@ -1,72 +0,0 @@
Aharon Robbins <arnold@gnu.org>
Akim Demaille <akim@epita.fr>
Alain Magloire <alainm@gnu.org>
Andreas Schwab <schwab@suse.de>
Andreas Ley <andy@rz.uni-karlsruhe.de>
Bastiaan "Darquan" Stougie <darquan@zonnet.nl>
Ben Elliston <bje@cygnus.com>
Bernd Strieder <strieder@student.uni-kl.de>
Bernhard Rosenkraenzer <bero@redhat.com>
Bob Proulx <rwp@hprwp.fc.hp.com>
Brian Youmans <3diff@gnu.org>
Bruno Haible <haible@ilog.fr>
Christian Groessler <cpg@aladdin.de>
David Clissold <cliss@austin.ibm.com>
David J MacKenzie <djm@catapult.va.pubnix.com>
David O'Brien <obrien@freebsd.org>
Eli Zaretskii <eliz@is.elta.co.il>
Florian La Roche <laroche@redhat.com>
Franc,ois Pinard <pinard@IRO.UMontreal.CA>
Gerald Stoller <gerald_stoller@hotmail.com>
Grant McDorman <grant@isgtec.com>
Greg Louis <glouis@dynamicro.on.ca>
Guglielmo 'bond' Bondioni <g.bondioni@libero.it>
H. Merijn Brand <h.m.brand@hccnet.nl>
Harald Hanche-Olsen <hanche@math.ntnu.no>
Hans-Bernhard Broeker <broeker@physik.rwth-aachen.de>
Heikki Korpela <heko@iki.fi>
Isamu Hasegawa <isamu@yamato.ibm.com>
Jeff Bailey <jbailey@nisa.net>
Jim Hand <jhand@austx.tandem.com>
Jim Meyering <meyering@asic.sc.ti.com>
Jochen Hein <jochen.hein@delphi.central.de>
Joel N. Weber II <devnull@gnu.org>
John Hughes <john@nitelite.calvacom.fr>
Jorge Stolfi <stolfi@dcc.unicamp.br>
Juan Manuel Guerrero <ST001906@HRZ1.HRZ.TU-Darmstadt.De>
Karl Berry <karl@cs.umb.edu>
Karl Heuer <kwzh@gnu.org>
Kaveh R. Ghazi <ghazi@caip.rutgers.edu>
Kazuro Furukawa <furukawa@apricot.kek.jp>
Keith Bostic <bostic@bsdi.com>
Krishna Sethuraman <krishna@sgihub.corp.sgi.com>
Kurt D Schwehr <kdschweh@insci14.ucsd.edu>
Mark Waite <markw@mddmew.fc.hp.com>
Martin P.J. Zinser <zinser@decus.de>
Martin Rex <martin.rex@sap-ag.de>
Michael Aichlmayr <mikla@nx.com>
Miles Bader <miles@ccs.mt.nec.co.jp>
Olaf Kirch <okir@ns.lst.de>
Paul Eggert <eggert@twinsun.com>
Paul Kimoto <kimoto@spacenet.tn.cornell.edu>
Phillip C. Brisco <phillip.craig.brisco@ccmail.census.gov>
Philippe Defert <Philippe.Defert@cern.ch>
Philippe De Muyter <phdm@info.ucl.ac.be>
Philip Hazel <ph10@cus.cam.ac.uk>
Roland Roberts <rroberts@muller.com>
Ruslan Ermilov <ru@freebsd.org>
Santiago Vila <sanvila@unex.es>
Shannon Hill <hill@synnet.com>
Sotiris Vassilopoulos <Sotiris.Vassilopoulos@betatech.gr>
Stewart Levin <stew@sep.stanford.edu>
Sydoruk Stepan <step@unitex.kiev.ua>
Tapani Tarvainen <tt@mit.jyu.fi>
Tom 'moof' Spindler <dogcow@ccs.neu.edu>
Tom Tromey <tromey@creche.cygnus.com>
Ulrich Drepper <drepper@cygnus.com>
UEBAYASHI Masao <masao@nf.enveng.titech.ac.jp>
Uwe H. Steinfeld <usteinfeld@gmx.net>
Volker Borchert <bt@teknon.de>
Wichert Akkerman <wichert@cistron.nl>
William Bader <william@nscs.fast.net>
Wolfgang Schludi <schludi@syscomp.de>

121
gnu/usr.bin/grep/closeout.c
View file

@ -1,121 +0,0 @@
/* closeout.c - close standard output
Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#if ENABLE_NLS
# include <libintl.h>
# define _(Text) gettext (Text)
#else
# define _(Text) Text
#endif
#if HAVE_STDLIB_H
# include <stdlib.h>
#endif
#ifndef EXIT_FAILURE
# define EXIT_FAILURE 1
#endif
#include <stdio.h>
#include <errno.h>
#ifndef errno
extern int errno;
#endif
#include "closeout.h"
#include "error.h"
#include "quotearg.h"
#if 0
#include "__fpending.h"
#endif
static int default_exit_status = EXIT_FAILURE;
static const char *file_name;
/* Set the value to be used for the exit status when close_stdout is called.
This is useful when it is not convenient to call close_stdout_status,
e.g., when close_stdout is called via atexit. */
void
close_stdout_set_status (int status)
{
default_exit_status = status;
}
/* Set the file name to be reported in the event an error is detected
by close_stdout_status. */
void
close_stdout_set_file_name (const char *file)
{
file_name = file;
}
/* Close standard output, exiting with status STATUS on failure.
If a program writes *anything* to stdout, that program should `fflush'
stdout and make sure that it succeeds before exiting. Otherwise,
suppose that you go to the extreme of checking the return status
of every function that does an explicit write to stdout. The last
printf can succeed in writing to the internal stream buffer, and yet
the fclose(stdout) could still fail (due e.g., to a disk full error)
when it tries to write out that buffered data. Thus, you would be
left with an incomplete output file and the offending program would
exit successfully.
FIXME: note the fflush suggested above is implicit in the fclose
we actually do below. Consider doing only the fflush and/or using
setvbuf to inhibit buffering.
Besides, it's wasteful to check the return value from every call
that writes to stdout -- just let the internal stream state record
the failure. That's what the ferror test is checking below.
It's important to detect such failures and exit nonzero because many
tools (most notably `make' and other build-management systems) depend
on being able to detect failure in other tools via their exit status. */
void
close_stdout_status (int status)
{
int e = ferror (stdout) ? 0 : -1;
#if 0
if (__fpending (stdout) == 0)
return;
#endif
if (fclose (stdout) != 0)
e = errno;
if (0 < e)
{
char const *write_error = _("write error");
if (file_name)
error (status, e, "%s: %s", quotearg_colon (file_name), write_error);
else
error (status, e, "%s", write_error);
}
}
/* Close standard output, exiting with status EXIT_FAILURE on failure. */
void
close_stdout (void)
{
close_stdout_status (default_exit_status);
}

17
gnu/usr.bin/grep/closeout.h
View file

@ -1,17 +0,0 @@
#ifndef CLOSEOUT_H
# define CLOSEOUT_H 1
# ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
# endif
void close_stdout_set_status PARAMS ((int status));
void close_stdout_set_file_name PARAMS ((const char *file));
void close_stdout PARAMS ((void));
void close_stdout_status PARAMS ((int status));
#endif

342
gnu/usr.bin/grep/config.h
View file

@ -1,342 +0,0 @@
/* $FreeBSD$ */
/* config.h. Generated by configure. */
/* config.hin. Generated from configure.in by autoheader. */
/* Define to 1 if the `closedir' function returns void instead of `int'. */
/* #undef CLOSEDIR_VOID */
/* Define to one of `_getb67', `GETB67', `getb67' for Cray-2 and Cray-YMP
systems. This function is required for `alloca.c' support on those systems.
*/
/* #undef CRAY_STACKSEG_END */
/* Define to 1 if using `alloca.c'. */
/* #undef C_ALLOCA */
/* Define to 1 if translation of program messages to the user's native
language is requested. */
/* #undef ENABLE_NLS */
/* We are building grep */
#define GREP 1
/* Define to 1 if you have `alloca', as a function or macro. */
#define HAVE_ALLOCA 1
/* Define to 1 if you have <alloca.h> and it should be used (not on Ultrix).
*/
/* #undef HAVE_ALLOCA_H */
/* Define to 1 if you have the <argz.h> header file. */
/* #undef HAVE_ARGZ_H */
/* Define to 1 if you have the `atexit' function. */
#define HAVE_ATEXIT 1
/* Define to 1 if you have the `btowc' function. */
#define HAVE_BTOWC 1
/* Define to 1 if you have the `dcgettext' function. */
/* #undef HAVE_DCGETTEXT */
/* Define to 1 if strerror_r is declared. */
#define HAVE_DECL_STRERROR_R 1
/* Define if <stdlib.h> declares strtoul. */
#define HAVE_DECL_STRTOUL 1
/* Define if <stdlib.h> declares strtoull. */
#define HAVE_DECL_STRTOULL 1
/* Define to 1 if you have the <dirent.h> header file, and it defines `DIR'.
*/
#define HAVE_DIRENT_H 1
/* Define if the malloc check has been performed. */
#define HAVE_DONE_WORKING_MALLOC_CHECK 1
/* Define if the realloc check has been performed. */
#define HAVE_DONE_WORKING_REALLOC_CHECK 1
/* Define to 1 if you have the `doprnt' function. */
/* #undef HAVE_DOPRNT */
/* Define if text file lines end in CRLF. */
/* #undef HAVE_DOS_FILE_CONTENTS */
/* Define if your OS uses backslashes as directory separators */
/* #undef HAVE_DOS_FILE_NAMES */
/* Define to 1 if you have the `feof_unlocked' function. */
#define HAVE_FEOF_UNLOCKED 1
/* Define to 1 if you have the `fgets_unlocked' function. */
/* #undef HAVE_FGETS_UNLOCKED */
/* Define to 1 if you have the `fnmatch' function. */
#define HAVE_FNMATCH 1
/* Define to 1 if you have the `getcwd' function. */
#define HAVE_GETCWD 1
/* Define to 1 if you have the `getegid' function. */
#define HAVE_GETEGID 1
/* Define to 1 if you have the `geteuid' function. */
#define HAVE_GETEUID 1
/* Define to 1 if you have the `getgid' function. */
#define HAVE_GETGID 1
/* Define to 1 if you have the `getpagesize' function. */
#define HAVE_GETPAGESIZE 1
/* Define if the GNU gettext() function is already present or preinstalled. */
/* #undef HAVE_GETTEXT */
/* Define to 1 if you have the `getuid' function. */
#define HAVE_GETUID 1
/* Define if you have the iconv() function. */
#define HAVE_ICONV 1
/* Define if <inttypes.h> exists, doesn't clash with <sys/types.h>, and
declares uintmax_t. */
#define HAVE_INTTYPES_H 1
/* Define to 1 if you have the `isascii' function. */
#define HAVE_ISASCII 1
/* Define if you have <langinfo.h> and nl_langinfo(CODESET). */
#define HAVE_LANGINFO_CODESET 1
/* Define if your <locale.h> file defines LC_MESSAGES. */
#define HAVE_LC_MESSAGES 1
/* Define to 1 if you have the <libintl.h> header file. */
/* #undef HAVE_LIBINTL_H */
/* Define to 1 if you have the `pcre' library (-lpcre). */
/* #undef HAVE_LIBPCRE */
/* Define to 1 if you have the <limits.h> header file. */
#define HAVE_LIMITS_H 1
/* Define to 1 if you have the <locale.h> header file. */
#define HAVE_LOCALE_H 1
/* Define to 1 if you have the <malloc.h> header file. */
/* #undef HAVE_MALLOC_H */
/* Define to 1 if you have the `mbrtowc' function. */
#define HAVE_MBRTOWC 1
/* Define to 1 if you have the `memchr' function. */
#define HAVE_MEMCHR 1
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE 1
/* Define to 1 if you have the <memory.h> header file. */
#define HAVE_MEMORY_H 1
/* Define to 1 if you have the `mempcpy' function. */
/* #undef HAVE_MEMPCPY */
/* Define to 1 if you have a working `mmap' system call. */
#define HAVE_MMAP 1
/* Define to 1 if you have the `munmap' function. */
#define HAVE_MUNMAP 1
/* Define to 1 if you have the <ndir.h> header file, and it defines `DIR'. */
/* #undef HAVE_NDIR_H */
/* Define to 1 if you have the <nl_types.h> header file. */
#define HAVE_NL_TYPES_H 1
/* Define to 1 if you have the `putenv' function. */
#define HAVE_PUTENV 1
/* Define to 1 if you have the `setenv' function. */
#define HAVE_SETENV 1
/* Define to 1 if you have the `setlocale' function. */
#define HAVE_SETLOCALE 1
/* Define to 1 if you have the `setmode' function. */
#define HAVE_SETMODE 1
/* Define to 1 if you have the <stddef.h> header file. */
#define HAVE_STDDEF_H 1
/* Define to 1 if you have the <stdint.h> header file. */
#define HAVE_STDINT_H 1
/* Define to 1 if you have the <stdlib.h> header file. */
#define HAVE_STDLIB_H 1
/* Define to 1 if you have the `stpcpy' function. */
#define HAVE_STPCPY 1
/* Define to 1 if you have the `strcasecmp' function. */
#define HAVE_STRCASECMP 1
/* Define to 1 if you have the `strchr' function. */
#define HAVE_STRCHR 1
/* Define to 1 if you have the `strdup' function. */
#define HAVE_STRDUP 1
/* Define to 1 if you have the `strerror' function. */
#define HAVE_STRERROR 1
/* Define to 1 if you have the `strerror_r' function. */
#define HAVE_STRERROR_R 1
/* Define to 1 if you have the <strings.h> header file. */
#define HAVE_STRINGS_H 1
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
/* Define to 1 if you have the `strtoul' function. */
#define HAVE_STRTOUL 1
/* Define to 1 if you have the `strtoull' function. */
/* #undef HAVE_STRTOULL */
/* Define to 1 if you have the `strtoumax' function. */
#define HAVE_STRTOUMAX 1
/* Define to 1 if you have the <sys/dir.h> header file, and it defines `DIR'.
*/
/* #undef HAVE_SYS_DIR_H */
/* Define to 1 if you have the <sys/ndir.h> header file, and it defines `DIR'.
*/
/* #undef HAVE_SYS_NDIR_H */
/* Define to 1 if you have the <sys/param.h> header file. */
#define HAVE_SYS_PARAM_H 1
/* Define to 1 if you have the <sys/stat.h> header file. */
#define HAVE_SYS_STAT_H 1
/* Define to 1 if you have the <sys/types.h> header file. */
#define HAVE_SYS_TYPES_H 1
/* Define to 1 if you have the `tsearch' function. */
#define HAVE_TSEARCH 1
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* Define if you have the unsigned long long type. */
#define HAVE_UNSIGNED_LONG_LONG 1
/* Define to 1 if you have the `vprintf' function. */
#define HAVE_VPRINTF 1
/* Define to 1 if you have the <wchar.h> header file. */
#define HAVE_WCHAR_H 1
/* Define to 1 if you have the `wctype' function. */
#define HAVE_WCTYPE 1
/* Define to 1 if you have the <wctype.h> header file. */
#define HAVE_WCTYPE_H 1
/* Define to 1 if strerror_r returns a string. */
/* #undef HAVE_WORKING_STRERROR_R */
/* Define to 1 if you have the `__argz_count' function. */
/* #undef HAVE___ARGZ_COUNT */
/* Define to 1 if you have the `__argz_next' function. */
/* #undef HAVE___ARGZ_NEXT */
/* Define to 1 if you have the `__argz_stringify' function. */
/* #undef HAVE___ARGZ_STRINGIFY */
/* Define as const if the declaration of iconv() needs const. */
#define ICONV_CONST
/* Name of package */
#define PACKAGE "grep"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT ""
/* Define to the full name of this package. */
#define PACKAGE_NAME ""
/* Define to the full name and version of this package. */
#define PACKAGE_STRING ""
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME ""
/* Define to the version of this package. */
#define PACKAGE_VERSION ""
/* Define if compiler has function prototypes */
#define PROTOTYPES 1
/* If using the C implementation of alloca, define if you know the
direction of stack growth for your system; otherwise it will be
automatically deduced at run-time.
STACK_DIRECTION > 0 => grows toward higher addresses
STACK_DIRECTION < 0 => grows toward lower addresses
STACK_DIRECTION = 0 => direction of growth unknown */
/* #undef STACK_DIRECTION */
/* Define to 1 if the `S_IS*' macros in <sys/stat.h> do not work properly. */
/* #undef STAT_MACROS_BROKEN */
/* Define to 1 if you have the ANSI C header files. */
#define STDC_HEADERS 1
/* Version number of package */
#define VERSION "2.5.1-FreeBSD"
/* Number of bits in a file offset, on hosts where this is settable. */
/* #undef _FILE_OFFSET_BITS */
/* Define to make fseeko etc. visible, on some hosts. */
/* #undef _LARGEFILE_SOURCE */
/* Define for large files, on AIX-style hosts. */
/* #undef _LARGE_FILES */
/* Define if your compiler is broken */
/* #undef alloca */
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
/* Define as `__inline' if that's what the C compiler calls it, or to nothing
if it is not supported. */
/* #undef inline */
/* Define to rpl_malloc if the replacement function should be used. */
/* #undef malloc */
/* Define to a type if <wchar.h> does not define. */
/* #undef mbstate_t */
/* Define to `long' if <sys/types.h> does not define. */
/* #undef off_t */
/* Define to rpl_realloc if the replacement function should be used. */
/* #undef realloc */
/* Define to `unsigned' if <sys/types.h> does not define. */
/* #undef size_t */
/* Define to `int' if <sys/types.h> does not define. */
/* #undef ssize_t */
/* Define to unsigned long or unsigned long long if <inttypes.h> doesn't
define. */
/* #undef uintmax_t */

3586
gnu/usr.bin/grep/dfa.c
View file

File diff suppressed because it is too large Load diff

434
gnu/usr.bin/grep/dfa.h
View file

@ -1,434 +0,0 @@
/* dfa.h - declarations for GNU deterministic regexp compiler
Copyright (C) 1988, 1998 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA */
/* Written June, 1988 by Mike Haertel */
/* $FreeBSD$ */
/* FIXME:
2. We should not export so much of the DFA internals.
In addition to clobbering modularity, we eat up valuable
name space. */
#ifdef __STDC__
# ifndef _PTR_T
# define _PTR_T
typedef void * ptr_t;
# endif
#else
# ifndef _PTR_T
# define _PTR_T
typedef char * ptr_t;
# endif
#endif
#ifdef PARAMS
# undef PARAMS
#endif
#if PROTOTYPES
# define PARAMS(x) x
#else
# define PARAMS(x) ()
#endif
/* Number of bits in an unsigned char. */
#ifndef CHARBITS
#define CHARBITS 8
#endif
/* First integer value that is greater than any character code. */
#define NOTCHAR (1 << CHARBITS)
/* INTBITS need not be exact, just a lower bound. */
#ifndef INTBITS
#define INTBITS (CHARBITS * sizeof (int))
#endif
/* Number of ints required to hold a bit for every character. */
#define CHARCLASS_INTS ((NOTCHAR + INTBITS - 1) / INTBITS)
/* Sets of unsigned characters are stored as bit vectors in arrays of ints. */
typedef int charclass[CHARCLASS_INTS];
/* The regexp is parsed into an array of tokens in postfix form. Some tokens
are operators and others are terminal symbols. Most (but not all) of these
codes are returned by the lexical analyzer. */
typedef enum
{
END = -1, /* END is a terminal symbol that matches the
end of input; any value of END or less in
the parse tree is such a symbol. Accepting
states of the DFA are those that would have
a transition on END. */
/* Ordinary character values are terminal symbols that match themselves. */
EMPTY = NOTCHAR, /* EMPTY is a terminal symbol that matches
the empty string. */
BACKREF, /* BACKREF is generated by \<digit>; it
it not completely handled. If the scanner
detects a transition on backref, it returns
a kind of "semi-success" indicating that
the match will have to be verified with
a backtracking matcher. */
BEGLINE, /* BEGLINE is a terminal symbol that matches
the empty string if it is at the beginning
of a line. */
ENDLINE, /* ENDLINE is a terminal symbol that matches
the empty string if it is at the end of
a line. */
BEGWORD, /* BEGWORD is a terminal symbol that matches
the empty string if it is at the beginning
of a word. */
ENDWORD, /* ENDWORD is a terminal symbol that matches
the empty string if it is at the end of
a word. */
LIMWORD, /* LIMWORD is a terminal symbol that matches
the empty string if it is at the beginning
or the end of a word. */
NOTLIMWORD, /* NOTLIMWORD is a terminal symbol that
matches the empty string if it is not at
the beginning or end of a word. */
QMARK, /* QMARK is an operator of one argument that
matches zero or one occurences of its
argument. */
STAR, /* STAR is an operator of one argument that
matches the Kleene closure (zero or more
occurrences) of its argument. */
PLUS, /* PLUS is an operator of one argument that
matches the positive closure (one or more
occurrences) of its argument. */
REPMN, /* REPMN is a lexical token corresponding
to the {m,n} construct. REPMN never
appears in the compiled token vector. */
CAT, /* CAT is an operator of two arguments that
matches the concatenation of its
arguments. CAT is never returned by the
lexical analyzer. */
OR, /* OR is an operator of two arguments that
matches either of its arguments. */
ORTOP, /* OR at the toplevel in the parse tree.
This is used for a boyer-moore heuristic. */
LPAREN, /* LPAREN never appears in the parse tree,
it is only a lexeme. */
RPAREN, /* RPAREN never appears in the parse tree. */
CRANGE, /* CRANGE never appears in the parse tree.
It stands for a character range that can
match a string of one or more characters.
For example, [a-z] can match "ch" in
a Spanish locale. */
#ifdef MBS_SUPPORT
ANYCHAR, /* ANYCHAR is a terminal symbol that matches
any multibyte(or singlebyte) characters.
It is used only if MB_CUR_MAX > 1. */
MBCSET, /* MBCSET is similar to CSET, but for
multibyte characters. */
#endif /* MBS_SUPPORT */
CSET /* CSET and (and any value greater) is a
terminal symbol that matches any of a
class of characters. */
} token;
/* Sets are stored in an array in the compiled dfa; the index of the
array corresponding to a given set token is given by SET_INDEX(t). */
#define SET_INDEX(t) ((t) - CSET)
/* Sometimes characters can only be matched depending on the surrounding
context. Such context decisions depend on what the previous character
was, and the value of the current (lookahead) character. Context
dependent constraints are encoded as 8 bit integers. Each bit that
is set indicates that the constraint succeeds in the corresponding
context.
bit 7 - previous and current are newlines
bit 6 - previous was newline, current isn't
bit 5 - previous wasn't newline, current is
bit 4 - neither previous nor current is a newline
bit 3 - previous and current are word-constituents
bit 2 - previous was word-constituent, current isn't
bit 1 - previous wasn't word-constituent, current is
bit 0 - neither previous nor current is word-constituent
Word-constituent characters are those that satisfy isalnum().
The macro SUCCEEDS_IN_CONTEXT determines whether a a given constraint
succeeds in a particular context. Prevn is true if the previous character
was a newline, currn is true if the lookahead character is a newline.
Prevl and currl similarly depend upon whether the previous and current
characters are word-constituent letters. */
#define MATCHES_NEWLINE_CONTEXT(constraint, prevn, currn) \
((constraint) & 1 << (((prevn) ? 2 : 0) + ((currn) ? 1 : 0) + 4))
#define MATCHES_LETTER_CONTEXT(constraint, prevl, currl) \
((constraint) & 1 << (((prevl) ? 2 : 0) + ((currl) ? 1 : 0)))
#define SUCCEEDS_IN_CONTEXT(constraint, prevn, currn, prevl, currl) \
(MATCHES_NEWLINE_CONTEXT(constraint, prevn, currn) \
&& MATCHES_LETTER_CONTEXT(constraint, prevl, currl))
/* The following macros give information about what a constraint depends on. */
#define PREV_NEWLINE_DEPENDENT(constraint) \
(((constraint) & 0xc0) >> 2 != ((constraint) & 0x30))
#define PREV_LETTER_DEPENDENT(constraint) \
(((constraint) & 0x0c) >> 2 != ((constraint) & 0x03))
/* Tokens that match the empty string subject to some constraint actually
work by applying that constraint to determine what may follow them,
taking into account what has gone before. The following values are
the constraints corresponding to the special tokens previously defined. */
#define NO_CONSTRAINT 0xff
#define BEGLINE_CONSTRAINT 0xcf
#define ENDLINE_CONSTRAINT 0xaf
#define BEGWORD_CONSTRAINT 0xf2
#define ENDWORD_CONSTRAINT 0xf4
#define LIMWORD_CONSTRAINT 0xf6
#define NOTLIMWORD_CONSTRAINT 0xf9
/* States of the recognizer correspond to sets of positions in the parse
tree, together with the constraints under which they may be matched.
So a position is encoded as an index into the parse tree together with
a constraint. */
typedef struct
{
unsigned index; /* Index into the parse array. */
unsigned constraint; /* Constraint for matching this position. */
} position;
/* Sets of positions are stored as arrays. */
typedef struct
{
position *elems; /* Elements of this position set. */
int nelem; /* Number of elements in this set. */
} position_set;
/* A state of the dfa consists of a set of positions, some flags,
and the token value of the lowest-numbered position of the state that
contains an END token. */
typedef struct
{
int hash; /* Hash of the positions of this state. */
position_set elems; /* Positions this state could match. */
char newline; /* True if previous state matched newline. */
char letter; /* True if previous state matched a letter. */
char backref; /* True if this state matches a \<digit>. */
unsigned char constraint; /* Constraint for this state to accept. */
int first_end; /* Token value of the first END in elems. */
#ifdef MBS_SUPPORT
position_set mbps; /* Positions which can match multibyte
characters. e.g. period.
These staff are used only if
MB_CUR_MAX > 1. */
#endif
} dfa_state;
/* Element of a list of strings, at least one of which is known to
appear in any R.E. matching the DFA. */
struct dfamust
{
int exact;
char *must;
struct dfamust *next;
};
#ifdef MBS_SUPPORT
/* A bracket operator.
e.g. [a-c], [[:alpha:]], etc. */
struct mb_char_classes
{
int invert;
wchar_t *chars; /* Normal characters. */
int nchars;
wctype_t *ch_classes; /* Character classes. */
int nch_classes;
wchar_t *range_sts; /* Range characters (start of the range). */
wchar_t *range_ends; /* Range characters (end of the range). */
int nranges;
char **equivs; /* Equivalent classes. */
int nequivs;
char **coll_elems;
int ncoll_elems; /* Collating elements. */
};
#endif
/* A compiled regular expression. */
struct dfa
{
/* Stuff built by the scanner. */
charclass *charclasses; /* Array of character sets for CSET tokens. */
int cindex; /* Index for adding new charclasses. */
int calloc; /* Number of charclasses currently allocated. */
/* Stuff built by the parser. */
token *tokens; /* Postfix parse array. */
int tindex; /* Index for adding new tokens. */
int talloc; /* Number of tokens currently allocated. */
int depth; /* Depth required of an evaluation stack
used for depth-first traversal of the
parse tree. */
int nleaves; /* Number of leaves on the parse tree. */
int nregexps; /* Count of parallel regexps being built
with dfaparse(). */
#ifdef MBS_SUPPORT
/* These stuff are used only if MB_CUR_MAX > 1 or multibyte environments. */
int nmultibyte_prop;
int *multibyte_prop;
/* The value of multibyte_prop[i] is defined by following rule.
if tokens[i] < NOTCHAR
bit 1 : tokens[i] is a singlebyte character, or the last-byte of
a multibyte character.
bit 0 : tokens[i] is a singlebyte character, or the 1st-byte of
a multibyte character.
if tokens[i] = MBCSET
("the index of mbcsets correspnd to this operator" << 2) + 3
e.g.
tokens
= 'single_byte_a', 'multi_byte_A', single_byte_b'
= 'sb_a', 'mb_A(1st byte)', 'mb_A(2nd byte)', 'mb_A(3rd byte)', 'sb_b'
multibyte_prop
= 3 , 1 , 0 , 2 , 3
*/
/* Array of the bracket expressoin in the DFA. */
struct mb_char_classes *mbcsets;
int nmbcsets;
int mbcsets_alloc;
#endif
/* Stuff owned by the state builder. */
dfa_state *states; /* States of the dfa. */
int sindex; /* Index for adding new states. */
int salloc; /* Number of states currently allocated. */
/* Stuff built by the structure analyzer. */
position_set *follows; /* Array of follow sets, indexed by position
index. The follow of a position is the set
of positions containing characters that
could conceivably follow a character
matching the given position in a string
matching the regexp. Allocated to the
maximum possible position index. */
int searchflag; /* True if we are supposed to build a searching
as opposed to an exact matcher. A searching
matcher finds the first and shortest string
matching a regexp anywhere in the buffer,
whereas an exact matcher finds the longest
string matching, but anchored to the
beginning of the buffer. */
/* Stuff owned by the executor. */
int tralloc; /* Number of transition tables that have
slots so far. */
int trcount; /* Number of transition tables that have
actually been built. */
int **trans; /* Transition tables for states that can
never accept. If the transitions for a
state have not yet been computed, or the
state could possibly accept, its entry in
this table is NULL. */
int **realtrans; /* Trans always points to realtrans + 1; this
is so trans[-1] can contain NULL. */
int **fails; /* Transition tables after failing to accept
on a state that potentially could do so. */
int *success; /* Table of acceptance conditions used in
dfaexec and computed in build_state. */
struct dfamust *musts; /* List of strings, at least one of which
is known to appear in any r.e. matching
the dfa. */
};
/* Some macros for user access to dfa internals. */
/* ACCEPTING returns true if s could possibly be an accepting state of r. */
#define ACCEPTING(s, r) ((r).states[s].constraint)
/* ACCEPTS_IN_CONTEXT returns true if the given state accepts in the
specified context. */
#define ACCEPTS_IN_CONTEXT(prevn, currn, prevl, currl, state, dfa) \
SUCCEEDS_IN_CONTEXT((dfa).states[state].constraint, \
prevn, currn, prevl, currl)
/* FIRST_MATCHING_REGEXP returns the index number of the first of parallel
regexps that a given state could accept. Parallel regexps are numbered
starting at 1. */
#define FIRST_MATCHING_REGEXP(state, dfa) (-(dfa).states[state].first_end)
/* Entry points. */
/* dfasyntax() takes three arguments; the first sets the syntax bits described
earlier in this file, the second sets the case-folding flag, and the
third specifies the line terminator. */
extern void dfasyntax PARAMS ((reg_syntax_t, int, unsigned char));
/* Compile the given string of the given length into the given struct dfa.
Final argument is a flag specifying whether to build a searching or an
exact matcher. */
extern void dfacomp PARAMS ((char const *, size_t, struct dfa *, int));
/* Execute the given struct dfa on the buffer of characters. The
last byte of the buffer must equal the end-of-line byte.
The final argument points to a flag that will
be set if further examination by a backtracking matcher is needed in
order to verify backreferencing; otherwise the flag will be cleared.
Returns (size_t) -1 if no match is found, or the offset of the first
character after the first & shortest matching string in the buffer. */
extern size_t dfaexec PARAMS ((struct dfa *, char const *, size_t, int *));
/* Free the storage held by the components of a struct dfa. */
extern void dfafree PARAMS ((struct dfa *));
/* Entry points for people who know what they're doing. */
/* Initialize the components of a struct dfa. */
extern void dfainit PARAMS ((struct dfa *));
/* Incrementally parse a string of given length into a struct dfa. */
extern void dfaparse PARAMS ((char const *, size_t, struct dfa *));
/* Analyze a parsed regexp; second argument tells whether to build a searching
or an exact matcher. */
extern void dfaanalyze PARAMS ((struct dfa *, int));
/* Compute, for each possible character, the transitions out of a given
state, storing them in an array of integers. */
extern void dfastate PARAMS ((int, struct dfa *, int []));
/* Error handling. */
/* dfaerror() is called by the regexp routines whenever an error occurs. It
takes a single argument, a NUL-terminated string describing the error.
The user must supply a dfaerror. */
extern void dfaerror PARAMS ((const char *));

276
gnu/usr.bin/grep/error.c
View file

@ -1,276 +0,0 @@
/* Error handler for noninteractive utilities
Copyright (C) 1990-1998, 2000 Free Software Foundation, Inc.
This file is part of the GNU C Library. Its master source is NOT part of
the C library, however. The master source lives in /gd/gnu/lib.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU C Library; see the file COPYING.LIB. If not,
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
/* Written by David MacKenzie <djm@gnu.ai.mit.edu>. */
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <stdio.h>
#if HAVE_LIBINTL_H
# include <libintl.h>
#endif
#if HAVE_VPRINTF || HAVE_DOPRNT || _LIBC
# if __STDC__
# include <stdarg.h>
# define VA_START(args, lastarg) va_start(args, lastarg)
# else
# include <varargs.h>
# define VA_START(args, lastarg) va_start(args)
# endif
#else
# define va_alist a1, a2, a3, a4, a5, a6, a7, a8
# define va_dcl char *a1, *a2, *a3, *a4, *a5, *a6, *a7, *a8;
#endif
#if STDC_HEADERS || _LIBC
# include <stdlib.h>
# include <string.h>
#else
void exit ();
#endif
#include "error.h"
#ifndef HAVE_DECL_STRERROR_R
"this configure-time declaration test was not run"
#endif
#if !HAVE_DECL_STRERROR_R
char *strerror_r ();
#endif
#ifndef _
# define _(String) String
#endif
/* If NULL, error will flush stdout, then print on stderr the program
name, a colon and a space. Otherwise, error will call this
function without parameters instead. */
void (*error_print_progname) (
#if __STDC__ - 0
void
#endif
);
/* This variable is incremented each time `error' is called. */
unsigned int error_message_count;
#ifdef _LIBC
/* In the GNU C library, there is a predefined variable for this. */
# define program_name program_invocation_name
# include <errno.h>
/* In GNU libc we want do not want to use the common name `error' directly.
Instead make it a weak alias. */
# define error __error
# define error_at_line __error_at_line
# ifdef USE_IN_LIBIO
# include <libio/iolibio.h>
# define fflush(s) _IO_fflush (s)
# endif
#else /* not _LIBC */
/* The calling program should define program_name and set it to the
name of the executing program. */
extern char *program_name;
# ifdef HAVE_STRERROR_R
# define __strerror_r strerror_r
# else
# if HAVE_STRERROR
# ifndef strerror /* On some systems, strerror is a macro */
char *strerror ();
# endif
# else
static char *
private_strerror (errnum)
int errnum;
{
extern char *sys_errlist[];
extern int sys_nerr;
if (errnum > 0 && errnum <= sys_nerr)
return _(sys_errlist[errnum]);
return _("Unknown system error");
}
# define strerror private_strerror
# endif /* HAVE_STRERROR */
# endif /* HAVE_STRERROR_R */
#endif /* not _LIBC */
/* Print the program name and error message MESSAGE, which is a printf-style
format string with optional args.
If ERRNUM is nonzero, print its corresponding system error message.
Exit with status STATUS if it is nonzero. */
/* VARARGS */
void
#if defined VA_START && __STDC__
error (int status, int errnum, const char *message, ...)
#else
error (status, errnum, message, va_alist)
int status;
int errnum;
char *message;
va_dcl
#endif
{
#ifdef VA_START
va_list args;
#endif
if (error_print_progname)
(*error_print_progname) ();
else
{
fflush (stdout);
fprintf (stderr, "%s: ", program_name);
}
#ifdef VA_START
VA_START (args, message);
# if HAVE_VPRINTF || _LIBC
vfprintf (stderr, message, args);
# else
_doprnt (message, args, stderr);
# endif
va_end (args);
#else
fprintf (stderr, message, a1, a2, a3, a4, a5, a6, a7, a8);
#endif
++error_message_count;
if (errnum)
{
#if defined HAVE_STRERROR_R || _LIBC
char errbuf[1024];
# if HAVE_WORKING_STRERROR_R || _LIBC
fprintf (stderr, ": %s", __strerror_r (errnum, errbuf, sizeof errbuf));
# else
/* Don't use __strerror_r's return value because on some systems
(at least DEC UNIX 4.0[A-D]) strerror_r returns `int'. */
__strerror_r (errnum, errbuf, sizeof errbuf);
fprintf (stderr, ": %s", errbuf);
# endif
#else
fprintf (stderr, ": %s", strerror (errnum));
#endif
}
putc ('\n', stderr);
fflush (stderr);
if (status)
exit (status);
}
/* Sometimes we want to have at most one error per line. This
variable controls whether this mode is selected or not. */
int error_one_per_line;
void
#if defined VA_START && __STDC__
error_at_line (int status, int errnum, const char *file_name,
unsigned int line_number, const char *message, ...)
#else
error_at_line (status, errnum, file_name, line_number, message, va_alist)
int status;
int errnum;
const char *file_name;
unsigned int line_number;
char *message;
va_dcl
#endif
{
#ifdef VA_START
va_list args;
#endif
if (error_one_per_line)
{
static const char *old_file_name;
static unsigned int old_line_number;
if (old_line_number == line_number &&
(file_name == old_file_name || !strcmp (old_file_name, file_name)))
/* Simply return and print nothing. */
return;
old_file_name = file_name;
old_line_number = line_number;
}
if (error_print_progname)
(*error_print_progname) ();
else
{
fflush (stdout);
fprintf (stderr, "%s:", program_name);
}
if (file_name != NULL)
fprintf (stderr, "%s:%d: ", file_name, line_number);
#ifdef VA_START
VA_START (args, message);
# if HAVE_VPRINTF || _LIBC
vfprintf (stderr, message, args);
# else
_doprnt (message, args, stderr);
# endif
va_end (args);
#else
fprintf (stderr, message, a1, a2, a3, a4, a5, a6, a7, a8);
#endif
++error_message_count;
if (errnum)
{
#if defined HAVE_STRERROR_R || _LIBC
char errbuf[1024];
# if HAVE_WORKING_STRERROR_R || _LIBC
fprintf (stderr, ": %s", __strerror_r (errnum, errbuf, sizeof errbuf));
# else
/* Don't use __strerror_r's return value because on some systems
(at least DEC UNIX 4.0[A-D]) strerror_r returns `int'. */
__strerror_r (errnum, errbuf, sizeof errbuf);
fprintf (stderr, ": %s", errbuf);
# endif
#else
fprintf (stderr, ": %s", strerror (errnum));
#endif
}
putc ('\n', stderr);
fflush (stderr);
if (status)
exit (status);
}
#ifdef _LIBC
/* Make the weak alias. */
# undef error
# undef error_at_line
weak_alias (__error, error)
weak_alias (__error_at_line, error_at_line)
#endif

78
gnu/usr.bin/grep/error.h
View file

@ -1,78 +0,0 @@
/* Declaration for error-reporting function
Copyright (C) 1995, 1996, 1997 Free Software Foundation, Inc.
NOTE: The canonical source of this file is maintained with the GNU C Library.
Bugs can be reported to bug-glibc@prep.ai.mit.edu.
This program is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
USA. */
#ifndef _ERROR_H
#define _ERROR_H 1
#ifndef __attribute__
/* This feature is available in gcc versions 2.5 and later. */
# if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 5) || __STRICT_ANSI__
# define __attribute__(Spec) /* empty */
# endif
/* The __-protected variants of `format' and `printf' attributes
are accepted by gcc versions 2.6.4 (effectively 2.7) and later. */
# if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 7)
# define __format__ format
# define __printf__ printf
# endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
#if defined (__STDC__) && __STDC__
/* Print a message with `fprintf (stderr, FORMAT, ...)';
if ERRNUM is nonzero, follow it with ": " and strerror (ERRNUM).
If STATUS is nonzero, terminate the program with `exit (STATUS)'. */
extern void error (int status, int errnum, const char *format, ...)
__attribute__ ((__format__ (__printf__, 3, 4)));
extern void error_at_line (int status, int errnum, const char *fname,
unsigned int lineno, const char *format, ...)
__attribute__ ((__format__ (__printf__, 5, 6)));
/* If NULL, error will flush stdout, then print on stderr the program
name, a colon and a space. Otherwise, error will call this
function without parameters instead. */
extern void (*error_print_progname) (void);
#else
void error ();
void error_at_line ();
extern void (*error_print_progname) ();
#endif
/* This variable is incremented each time `error' is called. */
extern unsigned int error_message_count;
/* Sometimes we want to have at most one error per line. This
variable controls whether this mode is selected or not. */
extern int error_one_per_line;
#ifdef __cplusplus
}
#endif
#endif /* error.h */

128
gnu/usr.bin/grep/exclude.c
View file

@ -1,128 +0,0 @@
/* exclude.c -- exclude file names
Copyright 1992, 1993, 1994, 1997, 1999, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING.
If not, write to the Free Software Foundation,
59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Paul Eggert <eggert@twinsun.com> */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#include <errno.h>
#ifndef errno
extern int errno;
#endif
#include <exclude.h>
#include <fnmatch.h>
#include <stdio.h>
#include <sys/types.h>
void *xmalloc PARAMS ((size_t));
void *xrealloc PARAMS ((void *, size_t));
/* Keep track of excluded file name patterns. */
struct exclude
{
char const **exclude;
int exclude_alloc;
int exclude_count;
};
struct exclude *
new_exclude (void)
{
struct exclude *ex = (struct exclude *) xmalloc (sizeof (struct exclude));
ex->exclude_count = 0;
ex->exclude_alloc = 64;
ex->exclude = (char const **) xmalloc (ex->exclude_alloc * sizeof (char *));
return ex;
}
int
excluded_filename (struct exclude const *ex, char const *f, int options)
{
char const * const *exclude = ex->exclude;
int exclude_count = ex->exclude_count;
int i;
for (i = 0; i < exclude_count; i++)
if (fnmatch (exclude[i], f, options) == 0)
return 1;
return 0;
}
void
add_exclude (struct exclude *ex, char const *pattern)
{
if (ex->exclude_alloc <= ex->exclude_count)
ex->exclude = (char const **) xrealloc (ex->exclude,
((ex->exclude_alloc *= 2)
* sizeof (char *)));
ex->exclude[ex->exclude_count++] = pattern;
}
int
add_exclude_file (void (*add_func) PARAMS ((struct exclude *, char const *)),
struct exclude *ex, char const *filename, char line_end)
{
int use_stdin = filename[0] == '-' && !filename[1];
FILE *in;
char *buf;
char *p;
char const *pattern;
char const *lim;
size_t buf_alloc = 1024;
size_t buf_count = 0;
int c;
int e = 0;
if (use_stdin)
in = stdin;
else if (! (in = fopen (filename, "r")))
return -1;
buf = xmalloc (buf_alloc);
while ((c = getc (in)) != EOF)
{
buf[buf_count++] = c;
if (buf_count == buf_alloc)
buf = xrealloc (buf, buf_alloc *= 2);
}
buf = xrealloc (buf, buf_count + 1);
if (ferror (in))
e = errno;
if (!use_stdin && fclose (in) != 0)
e = errno;
for (pattern = p = buf, lim = buf + buf_count; p <= lim; p++)
if (p < lim ? *p == line_end : buf < p && p[-1])
{
*p = '\0';
(*add_func) (ex, pattern);
pattern = p + 1;
}
errno = e;
return e ? -1 : 0;
}

35
gnu/usr.bin/grep/exclude.h
View file

@ -1,35 +0,0 @@
/* exclude.h -- declarations for excluding file names
Copyright 1992, 1993, 1994, 1997, 1999 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING.
If not, write to the Free Software Foundation,
59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Paul Eggert <eggert@twinsun.com> */
#ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
#endif
struct exclude;
struct exclude *new_exclude PARAMS ((void));
void add_exclude PARAMS ((struct exclude *, char const *));
int add_exclude_file PARAMS ((void (*) (struct exclude *, char const *),
struct exclude *, char const *, char));
int excluded_filename PARAMS ((struct exclude const *, char const *, int));

48
gnu/usr.bin/grep/getpagesize.h
View file

@ -1,48 +0,0 @@
/* Emulate getpagesize on systems that lack it. */
/* $FreeBSD$ */
#ifndef HAVE_GETPAGESIZE
#if !defined getpagesize && defined __BEOS__
# include <OS.h>
# define getpagesize() B_PAGE_SIZE
#endif
#ifdef HAVE_UNISTD_H
# include <unistd.h>
#endif
#if !defined getpagesize && defined _SC_PAGESIZE
# if !(defined VMS && __VMS_VER < 70000000)
# define getpagesize() sysconf (_SC_PAGESIZE)
# endif
#endif
#if !defined getpagesize && defined VMS
# ifdef __ALPHA
# define getpagesize() 8192
# else
# define getpagesize() 512
# endif
#endif
#ifndef getpagesize
# include <sys/param.h>
# ifdef EXEC_PAGESIZE
# define getpagesize() EXEC_PAGESIZE
# else
# ifdef NBPG
# ifndef CLSIZE
# define CLSIZE 1
# endif
# define getpagesize() (NBPG * CLSIZE)
# else
# ifdef NBPC
# define getpagesize() NBPC
# endif
# endif
# endif
#endif
#endif /* not HAVE_GETPAGESIZE */

780
gnu/usr.bin/grep/grep.1
View file

@ -1,780 +0,0 @@
.\" grep man page
.\" $FreeBSD$
.if !\n(.g \{\
. if !\w|\*(lq| \{\
. ds lq ``
. if \w'\(lq' .ds lq "\(lq
. \}
. if !\w|\*(rq| \{\
. ds rq ''
. if \w'\(rq' .ds rq "\(rq
. \}
.\}
.de Id
.ds Dt \\$4
..
.Id $Id: grep.1,v 1.23 2002/01/22 13:20:04 bero Exp $
.TH GREP 1 \*(Dt "GNU Project"
.SH NAME
grep, egrep, fgrep, zgrep, zegrep, zfgrep,
bzgrep, bzegrep, bzfgrep \- print lines matching a pattern
.SH SYNOPSIS
.B grep
.RI [ options ]
.I PATTERN
.RI [ FILE .\|.\|.]
.br
.B grep
.RI [ options ]
.RB [ \-e
.I PATTERN
|
.B \-f
.IR FILE ]
.RI [ FILE .\|.\|.]
.SH DESCRIPTION
.B grep
searches the named input
.IR FILE s
(or standard input if no files are named, or
the file name
.B \-
is given)
for lines containing a match to the given
.IR PATTERN .
By default,
.B grep
prints the matching lines.
.PP
In addition, two variant programs
.B egrep
and
.B fgrep
are available.
.B egrep
is the same as
.BR "grep\ \-E" .
.B fgrep
is the same as
.BR "grep\ \-F" .
.B zgrep
is the same as
.BR "grep\ \-Z" .
.B zegrep
is the same as
.BR "grep\ \-EZ" .
.B zfgrep
is the same as
.BR "grep\ \-FZ" .
.SH OPTIONS
.TP
.BI \-A " NUM" "\fR,\fP \-\^\-after-context=" NUM
Print
.I NUM
lines of trailing context after matching lines.
Places a line containing
.B \-\^\-
between contiguous groups of matches.
.TP
.BR \-a ", " \-\^\-text
Process a binary file as if it were text; this is equivalent to the
.B \-\^\-binary-files=text
option.
.TP
.BI \-B " NUM" "\fR,\fP \-\^\-before-context=" NUM
Print
.I NUM
lines of leading context before matching lines.
Places a line containing
.B \-\^\-
between contiguous groups of matches.
.TP
.BI \-C " NUM" "\fR,\fP \-\^\-context=" NUM
Print
.I NUM
lines of output context.
Places a line containing
.B \-\^\-
between contiguous groups of matches.
.TP
.BR \-b ", " \-\^\-byte-offset
Print the byte offset within the input file before
each line of output.
.TP
.BI \-\^\-binary-files= TYPE
If the first few bytes of a file indicate that the file contains binary
data, assume that the file is of type
.IR TYPE .
By default,
.I TYPE
is
.BR binary ,
and
.B grep
normally outputs either
a one-line message saying that a binary file matches, or no message if
there is no match.
If
.I TYPE
is
.BR without-match ,
.B grep
assumes that a binary file does not match; this is equivalent to the
.B \-I
option.
If
.I TYPE
is
.BR text ,
.B grep
processes a binary file as if it were text; this is equivalent to the
.B \-a
option.
.I Warning:
.B "grep \-\^\-binary-files=text"
might output binary garbage,
which can have nasty side effects if the output is a terminal and if the
terminal driver interprets some of it as commands.
.TP
.BI \-\^\-colour[=\fIWHEN\fR] ", " \-\^\-color[=\fIWHEN\fR]
Surround the matching string with the marker find in
.B GREP_COLOR
environment variable. WHEN may be `never', `always', or `auto'
.TP
.BR \-c ", " \-\^\-count
Suppress normal output; instead print a count of
matching lines for each input file.
With the
.BR \-v ", " \-\^\-invert-match
option (see below), count non-matching lines.
.TP
.BI \-D " ACTION" "\fR,\fP \-\^\-devices=" ACTION
If an input file is a device, FIFO or socket, use
.I ACTION
to process it. By default,
.I ACTION
is
.BR read ,
which means that devices are read just as if they were ordinary files.
If
.I ACTION
is
.BR skip ,
devices are silently skipped.
.TP
.BI \-d " ACTION" "\fR,\fP \-\^\-directories=" ACTION
If an input file is a directory, use
.I ACTION
to process it. By default,
.I ACTION
is
.BR read ,
which means that directories are read just as if they were ordinary files.
If
.I ACTION
is
.BR skip ,
directories are silently skipped.
If
.I ACTION
is
.BR recurse ,
.B grep
reads all files under each directory, recursively;
this is equivalent to the
.B \-r
option.
.TP
.BR \-E ", " \-\^\-extended-regexp
Interpret
.I PATTERN
as an extended regular expression (see below).
.TP
.BI \-e " PATTERN" "\fR,\fP \-\^\-regexp=" PATTERN
Use
.I PATTERN
as the pattern; useful to protect patterns beginning with
.BR \- .
.TP
.BR \-F ", " \-\^\-fixed-strings
Interpret
.I PATTERN
as a list of fixed strings, separated by newlines,
any of which is to be matched.
.TP
.BR \-P ", " \-\^\-perl-regexp
Interpret
.I PATTERN
as a Perl regular expression.
This option is not supported in FreeBSD.
.TP
.BI \-f " FILE" "\fR,\fP \-\^\-file=" FILE
Obtain patterns from
.IR FILE ,
one per line.
The empty file contains zero patterns, and therefore matches nothing.
.TP
.BR \-G ", " \-\^\-basic-regexp
Interpret
.I PATTERN
as a basic regular expression (see below). This is the default.
.TP
.BR \-H ", " \-\^\-with-filename
Print the filename for each match.
.TP
.BR \-h ", " \-\^\-no-filename
Suppress the prefixing of filenames on output
when multiple files are searched.
.TP
.B \-\^\-help
Output a brief help message.
.TP
.BR \-I
Process a binary file as if it did not contain matching data; this is
equivalent to the
.B \-\^\-binary-files=without-match
option.
.TP
.BR \-i ", " \-\^\-ignore-case
Ignore case distinctions in both the
.I PATTERN
and the input files.
.TP
.BR \-L ", " \-\^\-files-without-match
Suppress normal output; instead print the name
of each input file from which no output would
normally have been printed. The scanning will stop
on the first match.
.TP
.BR \-l ", " \-\^\-files-with-matches
Suppress normal output; instead print
the name of each input file from which output
would normally have been printed. The scanning will
stop on the first match.
.TP
.BI \-m " NUM" "\fR,\fP \-\^\-max-count=" NUM
Stop reading a file after
.I NUM
matching lines. If the input is standard input from a regular file,
and
.I NUM
matching lines are output,
.B grep
ensures that the standard input is positioned to just after the last
matching line before exiting, regardless of the presence of trailing
context lines. This enables a calling process to resume a search.
When
.B grep
stops after
.I NUM
matching lines, it outputs any trailing context lines. When the
.B \-c
or
.B \-\^\-count
option is also used,
.B grep
does not output a count greater than
.IR NUM .
When the
.B \-v
or
.B \-\^\-invert-match
option is also used,
.B grep
stops after outputting
.I NUM
non-matching lines.
.TP
.B \-\^\-mmap
If possible, use the
.BR mmap (2)
system call to read input, instead of
the default
.BR read (2)
system call. In some situations,
.B \-\^\-mmap
yields better performance. However,
.B \-\^\-mmap
can cause undefined behavior (including core dumps)
if an input file shrinks while
.B grep
is operating, or if an I/O error occurs.
.TP
.BR \-n ", " \-\^\-line-number
Prefix each line of output with the line number
within its input file.
.TP
.BR \-o ", " \-\^\-only-matching
Show only the part of a matching line that matches
.I PATTERN.
.TP
.BI \-\^\-label= LABEL
Displays input actually coming from standard input as input coming from file
.I LABEL.
This is especially useful for tools like zgrep, e.g.
.B "gzip -cd foo.gz |grep --label=foo something"
.TP
.BR \-\^\-line-buffered
Flush output on every line.
Note that this incurs a performance penalty.
.TP
.BR \-q ", " \-\^\-quiet ", " \-\^\-silent
Quiet; do not write anything to standard output.
Exit immediately with zero status if any match is found,
even if an error was detected.
Also see the
.B \-s
or
.B \-\^\-no-messages
option.
.TP
.BR \-R ", " \-r ", " \-\^\-recursive
Read all files under each directory, recursively;
this is equivalent to the
.B "\-d recurse"
option.
.TP
.BR "\fR \fP \-\^\-include=" PATTERN
Recurse in directories only searching file matching
.I PATTERN.
.TP
.BR "\fR \fP \-\^\-exclude=" PATTERN
Recurse in directories skip file matching
.I PATTERN.
.TP
.BR \-s ", " \-\^\-no-messages
Suppress error messages about nonexistent or unreadable files.
Portability note: unlike \s-1GNU\s0
.BR grep ,
traditional
.B grep
did not conform to \s-1POSIX.2\s0, because traditional
.B grep
lacked a
.B \-q
option and its
.B \-s
option behaved like \s-1GNU\s0
.BR grep 's
.B \-q
option.
Shell scripts intended to be portable to traditional
.B grep
should avoid both
.B \-q
and
.B \-s
and should redirect output to /dev/null instead.
.TP
.BR \-U ", " \-\^\-binary
Treat the file(s) as binary. By default, under MS-DOS and MS-Windows,
.BR grep
guesses the file type by looking at the contents of the first 32KB
read from the file. If
.BR grep
decides the file is a text file, it strips the CR characters from the
original file contents (to make regular expressions with
.B ^
and
.B $
work correctly). Specifying
.B \-U
overrules this guesswork, causing all files to be read and passed to the
matching mechanism verbatim; if the file is a text file with CR/LF
pairs at the end of each line, this will cause some regular
expressions to fail.
This option has no effect on platforms other than MS-DOS and
MS-Windows.
.TP
.BR \-u ", " \-\^\-unix-byte-offsets
Report Unix-style byte offsets. This switch causes
.B grep
to report byte offsets as if the file were Unix-style text file, i.e. with
CR characters stripped off. This will produce results identical to running
.B grep
on a Unix machine. This option has no effect unless
.B \-b
option is also used;
it has no effect on platforms other than MS-DOS and MS-Windows.
.TP
.BR \-V ", " \-\^\-version
Print the version number of
.B grep
to standard error. This version number should
be included in all bug reports (see below).
.TP
.BR \-v ", " \-\^\-invert-match
Invert the sense of matching, to select non-matching lines.
.TP
.BR \-w ", " \-\^\-word-regexp
Select only those lines containing matches that form whole words.
The test is that the matching substring must either be at the
beginning of the line, or preceded by a non-word constituent
character. Similarly, it must be either at the end of the line
or followed by a non-word constituent character. Word-constituent
characters are letters, digits, and the underscore.
.TP
.BR \-x ", " \-\^\-line-regexp
Select only those matches that exactly match the whole line.
.TP
.B \-y
Obsolete synonym for
.BR \-i .
.TP
.B \-\^\-null
Output a zero byte (the \s-1ASCII\s0
.B NUL
character) instead of the character that normally follows a file name.
For example,
.B "grep \-l \-\^\-null"
outputs a zero byte after each file name instead of the usual newline.
This option makes the output unambiguous, even in the presence of file
names containing unusual characters like newlines. This option can be
used with commands like
.BR "find \-print0" ,
.BR "perl \-0" ,
.BR "sort \-z" ,
and
.B "xargs \-0"
to process arbitrary file names,
even those that contain newline characters.
.TP
.BR \-Z ", " \-\^\-decompress
Decompress the input data before searching.
This option is only available if compiled with
.BR zlib (3)
library.
.TP
.BR \-J ", " \-\^\-bz2decompress
Decompress the
.BR bzip2 (1)
compressed input data before searching.
.SH "REGULAR EXPRESSIONS"
A regular expression is a pattern that describes a set of strings.
Regular expressions are constructed analogously to arithmetic
expressions, by using various operators to combine smaller expressions.
.PP
.B grep
understands two different versions of regular expression syntax:
\*(lqbasic\*(rq and \*(lqextended.\*(rq In
.RB "\s-1GNU\s0\ " grep ,
there is no difference in available functionality using either syntax.
In other implementations, basic regular expressions are less powerful.
The following description applies to extended regular expressions;
differences for basic regular expressions are summarized afterwards.
.PP
The fundamental building blocks are the regular expressions that match
a single character. Most characters, including all letters and digits,
are regular expressions that match themselves. Any metacharacter with
special meaning may be quoted by preceding it with a backslash.
.PP
A
.I "bracket expression"
is a list of characters enclosed by
.B [
and
.BR ] .
It matches any single
character in that list; if the first character of the list
is the caret
.B ^
then it matches any character
.I not
in the list.
For example, the regular expression
.B [0123456789]
matches any single digit.
.PP
Within a bracket expression, a
.I "range expression"
consists of two characters separated by a hyphen.
It matches any single character that sorts between the two characters,
inclusive, using the locale's collating sequence and character set.
For example, in the default C locale,
.B [a\-d]
is equivalent to
.BR [abcd] .
Many locales sort characters in dictionary order, and in these locales
.B [a\-d]
is typically not equivalent to
.BR [abcd] ;
it might be equivalent to
.BR [aBbCcDd] ,
for example.
To obtain the traditional interpretation of bracket expressions,
you can use the C locale by setting the
.B LC_ALL
environment variable to the value
.BR C .
.PP
Finally, certain named classes of characters are predefined within
bracket expressions, as follows.
Their names are self explanatory, and they are
.BR [:alnum:] ,
.BR [:alpha:] ,
.BR [:blank:] ,
.BR [:cntrl:] ,
.BR [:digit:] ,
.BR [:graph:] ,
.BR [:lower:] ,
.BR [:print:] ,
.BR [:punct:] ,
.BR [:space:] ,
.BR [:upper:] ,
and
.BR [:xdigit:].
For example,
.B [[:alnum:]]
means
.BR [0\-9A\-Za\-z] ,
except the latter form depends upon the C locale and the
\s-1ASCII\s0 character encoding, whereas the former is independent
of locale and character set.
(Note that the brackets in these class names are part of the symbolic
names, and must be included in addition to the brackets delimiting
the bracket list.) Most metacharacters lose their special meaning
inside lists. To include a literal
.B ]
place it first in the list. Similarly, to include a literal
.B ^
place it anywhere but first. Finally, to include a literal
.B \-
place it last.
.PP
The period
.B .
matches any single character.
The symbol
.B \ew
is a synonym for
.B [[:alnum:]]
and
.B \eW
is a synonym for
.BR [^[:alnum:]] .
.PP
The caret
.B ^
and the dollar sign
.B $
are metacharacters that respectively match the empty string at the
beginning and end of a line.
The symbols
.B \e<
and
.B \e>
respectively match the empty string at the beginning and end of a word.
The symbol
.B \eb
matches the empty string at the edge of a word,
and
.B \eB
matches the empty string provided it's
.I not
at the edge of a word.
.PP
A regular expression may be followed by one of several repetition operators:
.PD 0
.TP
.B ?
The preceding item is optional and matched at most once.
.TP
.B *
The preceding item will be matched zero or more times.
.TP
.B +
The preceding item will be matched one or more times.
.TP
.BI { n }
The preceding item is matched exactly
.I n
times.
.TP
.BI { n ,}
The preceding item is matched
.I n
or more times.
.TP
.BI { n , m }
The preceding item is matched at least
.I n
times, but not more than
.I m
times.
.PD
.PP
Two regular expressions may be concatenated; the resulting
regular expression matches any string formed by concatenating
two substrings that respectively match the concatenated
subexpressions.
.PP
Two regular expressions may be joined by the infix operator
.BR | ;
the resulting regular expression matches any string matching
either subexpression.
.PP
Repetition takes precedence over concatenation, which in turn
takes precedence over alternation. A whole subexpression may be
enclosed in parentheses to override these precedence rules.
.PP
The backreference
.BI \e n\c
\&, where
.I n
is a single digit, matches the substring
previously matched by the
.IR n th
parenthesized subexpression of the regular expression.
.PP
In basic regular expressions the metacharacters
.BR ? ,
.BR + ,
.BR { ,
.BR | ,
.BR ( ,
and
.BR )
lose their special meaning; instead use the backslashed
versions
.BR \e? ,
.BR \e+ ,
.BR \e{ ,
.BR \e| ,
.BR \e( ,
and
.BR \e) .
.PP
Traditional
.B egrep
did not support the
.B {
metacharacter, and some
.B egrep
implementations support
.B \e{
instead, so portable scripts should avoid
.B {
in
.B egrep
patterns and should use
.B [{]
to match a literal
.BR { .
.PP
\s-1GNU\s0
.B egrep
attempts to support traditional usage by assuming that
.B {
is not special if it would be the start of an invalid interval
specification. For example, the shell command
.B "egrep '{1'"
searches for the two-character string
.B {1
instead of reporting a syntax error in the regular expression.
\s-1POSIX.2\s0 allows this behavior as an extension, but portable scripts
should avoid it.
.SH "ENVIRONMENT VARIABLES"
Grep's behavior is affected by the following environment variables.
.PP
A locale
.BI LC_ foo
is specified by examining the three environment variables
.BR LC_ALL ,
.BR LC_\fIfoo\fP ,
.BR LANG ,
in that order.
The first of these variables that is set specifies the locale.
For example, if
.B LC_ALL
is not set, but
.B LC_MESSAGES
is set to
.BR pt_BR ,
then Brazilian Portuguese is used for the
.B LC_MESSAGES
locale.
The C locale is used if none of these environment variables are set,
or if the locale catalog is not installed, or if
.B grep
was not compiled with national language support (\s-1NLS\s0).
.TP
.B GREP_OPTIONS
This variable specifies default options to be placed in front of any
explicit options. For example, if
.B GREP_OPTIONS
is
.BR "'\-\^\-binary-files=without-match \-\^\-directories=skip'" ,
.B grep
behaves as if the two options
.B \-\^\-binary-files=without-match
and
.B \-\^\-directories=skip
had been specified before any explicit options.
Option specifications are separated by whitespace.
A backslash escapes the next character,
so it can be used to specify an option containing whitespace or a backslash.
.TP
.B GREP_COLOR
Specifies the marker for highlighting.
.TP
\fBLC_ALL\fP, \fBLC_COLLATE\fP, \fBLANG\fP
These variables specify the
.B LC_COLLATE
locale, which determines the collating sequence used to interpret
range expressions like
.BR [a\-z] .
.TP
\fBLC_ALL\fP, \fBLC_CTYPE\fP, \fBLANG\fP
These variables specify the
.B LC_CTYPE
locale, which determines the type of characters, e.g., which
characters are whitespace.
.TP
\fBLC_ALL\fP, \fBLC_MESSAGES\fP, \fBLANG\fP
These variables specify the
.B LC_MESSAGES
locale, which determines the language that
.B grep
uses for messages.
The default C locale uses American English messages.
.TP
.B POSIXLY_CORRECT
If set,
.B grep
behaves as \s-1POSIX.2\s0 requires; otherwise,
.B grep
behaves more like other \s-1GNU\s0 programs.
\s-1POSIX.2\s0 requires that options that follow file names must be
treated as file names; by default, such options are permuted to the
front of the operand list and are treated as options.
Also, \s-1POSIX.2\s0 requires that unrecognized options be diagnosed as
\*(lqillegal\*(rq, but since they are not really against the law the default
is to diagnose them as \*(lqinvalid\*(rq.
.SH DIAGNOSTICS
.PP
Normally, exit status is 0 if selected lines are found and 1 otherwise.
But the exit status is 2 if an error occurred, unless the
.B \-q
or
.B \-\^\-quiet
or
.B \-\^\-silent
option is used and a selected line is found.
.SH BUGS
Email bug reports to
.BR bug-gnu-utils@gnu.org .
Be sure to include the word \*(lqgrep\*(rq somewhere in the
\*(lqSubject:\*(rq field.
.PP
Large repetition counts in the
.BI { n , m }
construct may cause grep to use lots of memory.
In addition,
certain other obscure regular expressions require exponential time
and space, and may cause
.B grep
to run out of memory.
.PP
Backreferences are very slow, and may require exponential time.
.\" Work around problems with some troff -man implementations.
.br

1867
gnu/usr.bin/grep/grep.c
View file

File diff suppressed because it is too large Load diff

44
gnu/usr.bin/grep/grep.h
View file

@ -1,44 +0,0 @@
/* grep.h - interface to grep driver for searching subroutines.
Copyright (C) 1992, 1998, 2001 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
02111-1307, USA. */
/* $FreeBSD$ */
#if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 6) || __STRICT_ANSI__
# define __attribute__(x)
#endif
/* Grep.c expects the matchers vector to be terminated
by an entry with a NULL compile, and to contain at least
an entry named "default". */
extern struct matcher
{
char name[8];
void (*compile) PARAMS ((char const *, size_t));
size_t (*execute) PARAMS ((char const *, size_t, size_t *, int));
} const matchers[];
/* Exported from fgrepmat.c, egrepmat.c, grepmat.c. */
extern char const *matcher;
/* The following flags are exported from grep for the matchers
to look at. */
extern int match_icase; /* -i */
extern int match_words; /* -w */
extern int match_lines; /* -x */
extern unsigned char eolbyte; /* -z */

6
gnu/usr.bin/grep/grepmat.c
View file

@ -1,6 +0,0 @@
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include "system.h"
#include "grep.h"
char const *matcher;

87
gnu/usr.bin/grep/hard-locale.c
View file

@ -1,87 +0,0 @@
/* hard-locale.c -- Determine whether a locale is hard.
Copyright 1997, 1998, 1999 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* $FreeBSD$ */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#ifndef __GNUC__
# ifdef HAVE_ALLOCA_H
# include <alloca.h>
# else
# ifdef _AIX
# pragma alloca
# else
# ifdef _WIN32
# include <malloc.h>
# include <io.h>
# else
# ifndef alloca
char *alloca ();
# endif
# endif
# endif
# endif
#endif
#if HAVE_LOCALE_H
# include <locale.h>
#endif
#if HAVE_STRING_H
# include <string.h>
#endif
/* Return nonzero if the current CATEGORY locale is hard, i.e. if you
can't get away with assuming traditional C or POSIX behavior. */
int
hard_locale (int category)
{
#if ! HAVE_SETLOCALE
return 0;
#else
int hard = 1;
char const *p = setlocale (category, 0);
if (p)
{
# if defined(__FreeBSD__) || (defined __GLIBC__ && __GLIBC__ >= 2)
if (strcmp (p, "C") == 0 || strcmp (p, "POSIX") == 0)
hard = 0;
# else
char *locale = alloca (strlen (p) + 1);
strcpy (locale, p);
/* Temporarily set the locale to the "C" and "POSIX" locales to
find their names, so that we can determine whether one or the
other is the caller's locale. */
if (((p = setlocale (category, "C")) && strcmp (p, locale) == 0)
|| ((p = setlocale (category, "POSIX")) && strcmp (p, locale) == 0))
hard = 0;
/* Restore the caller's locale. */
setlocale (category, locale);
# endif
}
return hard;
#endif
}

18
gnu/usr.bin/grep/hard-locale.h
View file

@ -1,18 +0,0 @@
#ifndef HARD_LOCALE_H_
# define HARD_LOCALE_H_ 1
# if HAVE_CONFIG_H
# include <config.h>
# endif
# ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
# endif
int hard_locale PARAMS ((int));
#endif /* HARD_LOCALE_H_ */

42
gnu/usr.bin/grep/isdir.c
View file

@ -1,42 +0,0 @@
/* isdir.c -- determine whether a directory exists
Copyright (C) 1990, 1998 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#include <sys/stat.h>
#if STAT_MACROS_BROKEN
# undef S_ISDIR
#endif
#if !defined S_ISDIR && defined S_IFDIR
# define S_ISDIR(Mode) (((Mode) & S_IFMT) == S_IFDIR)
#endif
/* If PATH is an existing directory or symbolic link to a directory,
return nonzero, else 0. */
int
isdir (const char *path)
{
struct stat stats;
return stat (path, &stats) == 0 && S_ISDIR (stats.st_mode);
}

773
gnu/usr.bin/grep/kwset.c
View file

@ -1,773 +0,0 @@
/* kwset.c - search for any of a set of keywords.
Copyright 1989, 1998, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
02111-1307, USA. */
/* $FreeBSD$ */
/* Written August 1989 by Mike Haertel.
The author may be reached (Email) at the address mike@ai.mit.edu,
or (US mail) as Mike Haertel c/o Free Software Foundation. */
/* The algorithm implemented by these routines bears a startling resemblence
to one discovered by Beate Commentz-Walter, although it is not identical.
See "A String Matching Algorithm Fast on the Average," Technical Report,
IBM-Germany, Scientific Center Heidelberg, Tiergartenstrasse 15, D-6900
Heidelberg, Germany. See also Aho, A.V., and M. Corasick, "Efficient
String Matching: An Aid to Bibliographic Search," CACM June 1975,
Vol. 18, No. 6, which describes the failure function used below. */
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#include "system.h"
#include "kwset.h"
#include "obstack.h"
#ifdef GREP
extern char *xmalloc();
# undef malloc
# define malloc xmalloc
#endif
#define NCHAR (UCHAR_MAX + 1)
#define obstack_chunk_alloc malloc
#define obstack_chunk_free free
/* Balanced tree of edges and labels leaving a given trie node. */
struct tree
{
struct tree *llink; /* Left link; MUST be first field. */
struct tree *rlink; /* Right link (to larger labels). */
struct trie *trie; /* Trie node pointed to by this edge. */
unsigned char label; /* Label on this edge. */
char balance; /* Difference in depths of subtrees. */
};
/* Node of a trie representing a set of reversed keywords. */
struct trie
{
unsigned int accepting; /* Word index of accepted word, or zero. */
struct tree *links; /* Tree of edges leaving this node. */
struct trie *parent; /* Parent of this node. */
struct trie *next; /* List of all trie nodes in level order. */
struct trie *fail; /* Aho-Corasick failure function. */
int depth; /* Depth of this node from the root. */
int shift; /* Shift function for search failures. */
int maxshift; /* Max shift of self and descendents. */
};
/* Structure returned opaquely to the caller, containing everything. */
struct kwset
{
struct obstack obstack; /* Obstack for node allocation. */
int words; /* Number of words in the trie. */
struct trie *trie; /* The trie itself. */
int mind; /* Minimum depth of an accepting node. */
int maxd; /* Maximum depth of any node. */
unsigned char delta[NCHAR]; /* Delta table for rapid search. */
struct trie *next[NCHAR]; /* Table of children of the root. */
char *target; /* Target string if there's only one. */
int mind2; /* Used in Boyer-Moore search for one string. */
char const *trans; /* Character translation table. */
};
/* Allocate and initialize a keyword set object, returning an opaque
pointer to it. Return NULL if memory is not available. */
kwset_t
kwsalloc (char const *trans)
{
struct kwset *kwset;
kwset = (struct kwset *) malloc(sizeof (struct kwset));
if (!kwset)
return 0;
obstack_init(&kwset->obstack);
kwset->words = 0;
kwset->trie
= (struct trie *) obstack_alloc(&kwset->obstack, sizeof (struct trie));
if (!kwset->trie)
{
kwsfree((kwset_t) kwset);
return 0;
}
kwset->trie->accepting = 0;
kwset->trie->links = 0;
kwset->trie->parent = 0;
kwset->trie->next = 0;
kwset->trie->fail = 0;
kwset->trie->depth = 0;
kwset->trie->shift = 0;
kwset->mind = INT_MAX;
kwset->maxd = -1;
kwset->target = 0;
kwset->trans = trans;
return (kwset_t) kwset;
}
/* Add the given string to the contents of the keyword set. Return NULL
for success, an error message otherwise. */
char *
kwsincr (kwset_t kws, char const *text, size_t len)
{
struct kwset *kwset;
register struct trie *trie;
register unsigned char label;
register struct tree *link;
register int depth;
struct tree *links[12];
enum { L, R } dirs[12];
struct tree *t, *r, *l, *rl, *lr;
kwset = (struct kwset *) kws;
trie = kwset->trie;
text += len;
/* Descend the trie (built of reversed keywords) character-by-character,
installing new nodes when necessary. */
while (len--)
{
label = kwset->trans ? kwset->trans[(unsigned char) *--text] : *--text;
/* Descend the tree of outgoing links for this trie node,
looking for the current character and keeping track
of the path followed. */
link = trie->links;
links[0] = (struct tree *) &trie->links;
dirs[0] = L;
depth = 1;
while (link && label != link->label)
{
links[depth] = link;
if (label < link->label)
dirs[depth++] = L, link = link->llink;
else
dirs[depth++] = R, link = link->rlink;
}
/* The current character doesn't have an outgoing link at
this trie node, so build a new trie node and install
a link in the current trie node's tree. */
if (!link)
{
link = (struct tree *) obstack_alloc(&kwset->obstack,
sizeof (struct tree));
if (!link)
return _("memory exhausted");
link->llink = 0;
link->rlink = 0;
link->trie = (struct trie *) obstack_alloc(&kwset->obstack,
sizeof (struct trie));
if (!link->trie)
return _("memory exhausted");
link->trie->accepting = 0;
link->trie->links = 0;
link->trie->parent = trie;
link->trie->next = 0;
link->trie->fail = 0;
link->trie->depth = trie->depth + 1;
link->trie->shift = 0;
link->label = label;
link->balance = 0;
/* Install the new tree node in its parent. */
if (dirs[--depth] == L)
links[depth]->llink = link;
else
links[depth]->rlink = link;
/* Back up the tree fixing the balance flags. */
while (depth && !links[depth]->balance)
{
if (dirs[depth] == L)
--links[depth]->balance;
else
++links[depth]->balance;
--depth;
}
/* Rebalance the tree by pointer rotations if necessary. */
if (depth && ((dirs[depth] == L && --links[depth]->balance)
|| (dirs[depth] == R && ++links[depth]->balance)))
{
switch (links[depth]->balance)
{
case (char) -2:
switch (dirs[depth + 1])
{
case L:
r = links[depth], t = r->llink, rl = t->rlink;
t->rlink = r, r->llink = rl;
t->balance = r->balance = 0;
break;
case R:
r = links[depth], l = r->llink, t = l->rlink;
rl = t->rlink, lr = t->llink;
t->llink = l, l->rlink = lr, t->rlink = r, r->llink = rl;
l->balance = t->balance != 1 ? 0 : -1;
r->balance = t->balance != (char) -1 ? 0 : 1;
t->balance = 0;
break;
default:
abort ();
}
break;
case 2:
switch (dirs[depth + 1])
{
case R:
l = links[depth], t = l->rlink, lr = t->llink;
t->llink = l, l->rlink = lr;
t->balance = l->balance = 0;
break;
case L:
l = links[depth], r = l->rlink, t = r->llink;
lr = t->llink, rl = t->rlink;
t->llink = l, l->rlink = lr, t->rlink = r, r->llink = rl;
l->balance = t->balance != 1 ? 0 : -1;
r->balance = t->balance != (char) -1 ? 0 : 1;
t->balance = 0;
break;
default:
abort ();
}
break;
default:
abort ();
}
if (dirs[depth - 1] == L)
links[depth - 1]->llink = t;
else
links[depth - 1]->rlink = t;
}
}
trie = link->trie;
}
/* Mark the node we finally reached as accepting, encoding the
index number of this word in the keyword set so far. */
if (!trie->accepting)
trie->accepting = 1 + 2 * kwset->words;
++kwset->words;
/* Keep track of the longest and shortest string of the keyword set. */
if (trie->depth < kwset->mind)
kwset->mind = trie->depth;
if (trie->depth > kwset->maxd)
kwset->maxd = trie->depth;
return 0;
}
/* Enqueue the trie nodes referenced from the given tree in the
given queue. */
static void
enqueue (struct tree *tree, struct trie **last)
{
if (!tree)
return;
enqueue(tree->llink, last);
enqueue(tree->rlink, last);
(*last) = (*last)->next = tree->trie;
}
/* Compute the Aho-Corasick failure function for the trie nodes referenced
from the given tree, given the failure function for their parent as
well as a last resort failure node. */
static void
treefails (register struct tree const *tree, struct trie const *fail,
struct trie *recourse)
{
register struct tree *link;
if (!tree)
return;
treefails(tree->llink, fail, recourse);
treefails(tree->rlink, fail, recourse);
/* Find, in the chain of fails going back to the root, the first
node that has a descendent on the current label. */
while (fail)
{
link = fail->links;
while (link && tree->label != link->label)
if (tree->label < link->label)
link = link->llink;
else
link = link->rlink;
if (link)
{
tree->trie->fail = link->trie;
return;
}
fail = fail->fail;
}
tree->trie->fail = recourse;
}
/* Set delta entries for the links of the given tree such that
the preexisting delta value is larger than the current depth. */
static void
treedelta (register struct tree const *tree,
register unsigned int depth,
unsigned char delta[])
{
if (!tree)
return;
treedelta(tree->llink, depth, delta);
treedelta(tree->rlink, depth, delta);
if (depth < delta[tree->label])
delta[tree->label] = depth;
}
/* Return true if A has every label in B. */
static int
hasevery (register struct tree const *a, register struct tree const *b)
{
if (!b)
return 1;
if (!hasevery(a, b->llink))
return 0;
if (!hasevery(a, b->rlink))
return 0;
while (a && b->label != a->label)
if (b->label < a->label)
a = a->llink;
else
a = a->rlink;
return !!a;
}
/* Compute a vector, indexed by character code, of the trie nodes
referenced from the given tree. */
static void
treenext (struct tree const *tree, struct trie *next[])
{
if (!tree)
return;
treenext(tree->llink, next);
treenext(tree->rlink, next);
next[tree->label] = tree->trie;
}
/* Compute the shift for each trie node, as well as the delta
table and next cache for the given keyword set. */
char *
kwsprep (kwset_t kws)
{
register struct kwset *kwset;
register int i;
register struct trie *curr, *fail;
register char const *trans;
unsigned char delta[NCHAR];
struct trie *last, *next[NCHAR];
kwset = (struct kwset *) kws;
/* Initial values for the delta table; will be changed later. The
delta entry for a given character is the smallest depth of any
node at which an outgoing edge is labeled by that character. */
if (kwset->mind < 256)
for (i = 0; i < NCHAR; ++i)
delta[i] = kwset->mind;
else
for (i = 0; i < NCHAR; ++i)
delta[i] = 255;
/* Check if we can use the simple boyer-moore algorithm, instead
of the hairy commentz-walter algorithm. */
if (kwset->words == 1 && kwset->trans == 0)
{
/* Looking for just one string. Extract it from the trie. */
kwset->target = obstack_alloc(&kwset->obstack, kwset->mind);
for (i = kwset->mind - 1, curr = kwset->trie; i >= 0; --i)
{
kwset->target[i] = curr->links->label;
curr = curr->links->trie;
}
/* Build the Boyer Moore delta. Boy that's easy compared to CW. */
for (i = 0; i < kwset->mind; ++i)
delta[(unsigned char) kwset->target[i]] = kwset->mind - (i + 1);
kwset->mind2 = kwset->mind;
/* Find the minimal delta2 shift that we might make after
a backwards match has failed. */
for (i = 0; i < kwset->mind - 1; ++i)
if (kwset->target[i] == kwset->target[kwset->mind - 1])
kwset->mind2 = kwset->mind - (i + 1);
}
else
{
/* Traverse the nodes of the trie in level order, simultaneously
computing the delta table, failure function, and shift function. */
for (curr = last = kwset->trie; curr; curr = curr->next)
{
/* Enqueue the immediate descendents in the level order queue. */
enqueue(curr->links, &last);
curr->shift = kwset->mind;
curr->maxshift = kwset->mind;
/* Update the delta table for the descendents of this node. */
treedelta(curr->links, curr->depth, delta);
/* Compute the failure function for the decendents of this node. */
treefails(curr->links, curr->fail, kwset->trie);
/* Update the shifts at each node in the current node's chain
of fails back to the root. */
for (fail = curr->fail; fail; fail = fail->fail)
{
/* If the current node has some outgoing edge that the fail
doesn't, then the shift at the fail should be no larger
than the difference of their depths. */
if (!hasevery(fail->links, curr->links))
if (curr->depth - fail->depth < fail->shift)
fail->shift = curr->depth - fail->depth;
/* If the current node is accepting then the shift at the
fail and its descendents should be no larger than the
difference of their depths. */
if (curr->accepting && fail->maxshift > curr->depth - fail->depth)
fail->maxshift = curr->depth - fail->depth;
}
}
/* Traverse the trie in level order again, fixing up all nodes whose
shift exceeds their inherited maxshift. */
for (curr = kwset->trie->next; curr; curr = curr->next)
{
if (curr->maxshift > curr->parent->maxshift)
curr->maxshift = curr->parent->maxshift;
if (curr->shift > curr->maxshift)
curr->shift = curr->maxshift;
}
/* Create a vector, indexed by character code, of the outgoing links
from the root node. */
for (i = 0; i < NCHAR; ++i)
next[i] = 0;
treenext(kwset->trie->links, next);
if ((trans = kwset->trans) != 0)
for (i = 0; i < NCHAR; ++i)
kwset->next[i] = next[(unsigned char) trans[i]];
else
for (i = 0; i < NCHAR; ++i)
kwset->next[i] = next[i];
}
/* Fix things up for any translation table. */
if ((trans = kwset->trans) != 0)
for (i = 0; i < NCHAR; ++i)
kwset->delta[i] = delta[(unsigned char) trans[i]];
else
for (i = 0; i < NCHAR; ++i)
kwset->delta[i] = delta[i];
return 0;
}
#define U(C) ((unsigned char) (C))
/* Fast boyer-moore search. */
static size_t
bmexec (kwset_t kws, char const *text, size_t size)
{
struct kwset const *kwset;
register unsigned char const *d1;
register char const *ep, *sp, *tp;
register int d, gc, i, len, md2;
kwset = (struct kwset const *) kws;
len = kwset->mind;
if (len == 0)
return 0;
if (len > size)
return -1;
if (len == 1)
{
tp = memchr (text, kwset->target[0], size);
return tp ? tp - text : -1;
}
d1 = kwset->delta;
sp = kwset->target + len;
gc = U(sp[-2]);
md2 = kwset->mind2;
tp = text + len;
/* Significance of 12: 1 (initial offset) + 10 (skip loop) + 1 (md2). */
if (size > 12 * len)
/* 11 is not a bug, the initial offset happens only once. */
for (ep = text + size - 11 * len;;)
{
while (tp <= ep)
{
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
if (d == 0)
goto found;
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
if (d == 0)
goto found;
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
if (d == 0)
goto found;
d = d1[U(tp[-1])], tp += d;
d = d1[U(tp[-1])], tp += d;
}
break;
found:
if (U(tp[-2]) == gc)
{
for (i = 3; i <= len && U(tp[-i]) == U(sp[-i]); ++i)
;
if (i > len)
return tp - len - text;
}
tp += md2;
}
/* Now we have only a few characters left to search. We
carefully avoid ever producing an out-of-bounds pointer. */
ep = text + size;
d = d1[U(tp[-1])];
while (d <= ep - tp)
{
d = d1[U((tp += d)[-1])];
if (d != 0)
continue;
if (U(tp[-2]) == gc)
{
for (i = 3; i <= len && U(tp[-i]) == U(sp[-i]); ++i)
;
if (i > len)
return tp - len - text;
}
d = md2;
}
return -1;
}
/* Hairy multiple string search. */
static size_t
cwexec (kwset_t kws, char const *text, size_t len, struct kwsmatch *kwsmatch)
{
struct kwset const *kwset;
struct trie * const *next;
struct trie const *trie;
struct trie const *accept;
char const *beg, *lim, *mch, *lmch;
register unsigned char c;
register unsigned char const *delta;
register int d;
register char const *end, *qlim;
register struct tree const *tree;
register char const *trans;
#ifdef lint
accept = NULL;
#endif
/* Initialize register copies and look for easy ways out. */
kwset = (struct kwset *) kws;
if (len < kwset->mind)
return -1;
next = kwset->next;
delta = kwset->delta;
trans = kwset->trans;
lim = text + len;
end = text;
if ((d = kwset->mind) != 0)
mch = 0;
else
{
mch = text, accept = kwset->trie;
goto match;
}
if (len >= 4 * kwset->mind)
qlim = lim - 4 * kwset->mind;
else
qlim = 0;
while (lim - end >= d)
{
if (qlim && end <= qlim)
{
end += d - 1;
while ((d = delta[c = *end]) && end < qlim)
{
end += d;
end += delta[(unsigned char) *end];
end += delta[(unsigned char) *end];
}
++end;
}
else
d = delta[c = (end += d)[-1]];
if (d)
continue;
beg = end - 1;
trie = next[c];
if (trie->accepting)
{
mch = beg;
accept = trie;
}
d = trie->shift;
while (beg > text)
{
c = trans ? trans[(unsigned char) *--beg] : *--beg;
tree = trie->links;
while (tree && c != tree->label)
if (c < tree->label)
tree = tree->llink;
else
tree = tree->rlink;
if (tree)
{
trie = tree->trie;
if (trie->accepting)
{
mch = beg;
accept = trie;
}
}
else
break;
d = trie->shift;
}
if (mch)
goto match;
}
return -1;
match:
/* Given a known match, find the longest possible match anchored
at or before its starting point. This is nearly a verbatim
copy of the preceding main search loops. */
if (lim - mch > kwset->maxd)
lim = mch + kwset->maxd;
lmch = 0;
d = 1;
while (lim - end >= d)
{
if ((d = delta[c = (end += d)[-1]]) != 0)
continue;
beg = end - 1;
if (!(trie = next[c]))
{
d = 1;
continue;
}
if (trie->accepting && beg <= mch)
{
lmch = beg;
accept = trie;
}
d = trie->shift;
while (beg > text)
{
c = trans ? trans[(unsigned char) *--beg] : *--beg;
tree = trie->links;
while (tree && c != tree->label)
if (c < tree->label)
tree = tree->llink;
else
tree = tree->rlink;
if (tree)
{
trie = tree->trie;
if (trie->accepting && beg <= mch)
{
lmch = beg;
accept = trie;
}
}
else
break;
d = trie->shift;
}
if (lmch)
{
mch = lmch;
goto match;
}
if (!d)
d = 1;
}
if (kwsmatch)
{
kwsmatch->index = accept->accepting / 2;
kwsmatch->offset[0] = mch - text;
kwsmatch->size[0] = accept->depth;
}
return mch - text;
}
/* Search through the given text for a match of any member of the
given keyword set. Return a pointer to the first character of
the matching substring, or NULL if no match is found. If FOUNDLEN
is non-NULL store in the referenced location the length of the
matching substring. Similarly, if FOUNDIDX is non-NULL, store
in the referenced location the index number of the particular
keyword matched. */
size_t
kwsexec (kwset_t kws, char const *text, size_t size,
struct kwsmatch *kwsmatch)
{
struct kwset const *kwset = (struct kwset *) kws;
if (kwset->words == 1 && kwset->trans == 0)
{
size_t ret = bmexec (kws, text, size);
if (kwsmatch != 0 && ret != (size_t) -1)
{
kwsmatch->index = 0;
kwsmatch->offset[0] = ret;
kwsmatch->size[0] = kwset->mind;
}
return ret;
}
else
return cwexec(kws, text, size, kwsmatch);
}
/* Free the components of the given keyword set. */
void
kwsfree (kwset_t kws)
{
struct kwset *kwset;
kwset = (struct kwset *) kws;
obstack_free(&kwset->obstack, 0);
free(kws);
}

59
gnu/usr.bin/grep/kwset.h
View file

@ -1,59 +0,0 @@
/* kwset.h - header declaring the keyword set library.
Copyright (C) 1989, 1998 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
02111-1307, USA. */
/* Written August 1989 by Mike Haertel.
The author may be reached (Email) at the address mike@ai.mit.edu,
or (US mail) as Mike Haertel c/o Free Software Foundation. */
/* $FreeBSD$ */
struct kwsmatch
{
int index; /* Index number of matching keyword. */
size_t offset[1]; /* Offset of each submatch. */
size_t size[1]; /* Length of each submatch. */
};
typedef ptr_t kwset_t;
/* Return an opaque pointer to a newly allocated keyword set, or NULL
if enough memory cannot be obtained. The argument if non-NULL
specifies a table of character translations to be applied to all
pattern and search text. */
extern kwset_t kwsalloc PARAMS((char const *));
/* Incrementally extend the keyword set to include the given string.
Return NULL for success, or an error message. Remember an index
number for each keyword included in the set. */
extern char *kwsincr PARAMS((kwset_t, char const *, size_t));
/* When the keyword set has been completely built, prepare it for
use. Return NULL for success, or an error message. */
extern char *kwsprep PARAMS((kwset_t));
/* Search through the given buffer for a member of the keyword set.
Return a pointer to the leftmost longest match found, or NULL if
no match is found. If foundlen is non-NULL, store the length of
the matching substring in the integer it points to. Similarly,
if foundindex is non-NULL, store the index of the particular
keyword found therein. */
extern size_t kwsexec PARAMS((kwset_t, char const *, size_t, struct kwsmatch *));
/* Deallocate the given keyword set and all its associated storage. */
extern void kwsfree PARAMS((kwset_t));

598
gnu/usr.bin/grep/obstack.c
View file

@ -1,598 +0,0 @@
/* obstack.c - subroutines used implicitly by object stack macros
Copyright (C) 1988-1994,96,97,98,99 Free Software Foundation, Inc.
This file is part of the GNU C Library. Its master source is NOT part of
the C library, however. The master source lives in /gd/gnu/lib.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU C Library; see the file COPYING.LIB. If not,
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
#ifdef HAVE_CONFIG_H
#include <config.h>
#endif
#include "obstack.h"
/* NOTE BEFORE MODIFYING THIS FILE: This version number must be
incremented whenever callers compiled using an old obstack.h can no
longer properly call the functions in this obstack.c. */
#define OBSTACK_INTERFACE_VERSION 1
/* Comment out all this code if we are using the GNU C Library, and are not
actually compiling the library itself, and the installed library
supports the same library interface we do. This code is part of the GNU
C Library, but also included in many other GNU distributions. Compiling
and linking in this code is a waste when using the GNU C library
(especially if it is a shared library). Rather than having every GNU
program understand `configure --with-gnu-libc' and omit the object
files, it is simpler to just do this in the source for each such file. */
#include <stdio.h> /* Random thing to get __GNU_LIBRARY__. */
#if !defined (_LIBC) && defined (__GNU_LIBRARY__) && __GNU_LIBRARY__ > 1
#include <gnu-versions.h>
#if _GNU_OBSTACK_INTERFACE_VERSION == OBSTACK_INTERFACE_VERSION
#define ELIDE_CODE
#endif
#endif
#ifndef ELIDE_CODE
#if defined (__STDC__) && __STDC__
#define POINTER void *
#else
#define POINTER char *
#endif
/* Determine default alignment. */
struct fooalign {char x; double d;};
#define DEFAULT_ALIGNMENT \
((PTR_INT_TYPE) ((char *) &((struct fooalign *) 0)->d - (char *) 0))
/* If malloc were really smart, it would round addresses to DEFAULT_ALIGNMENT.
But in fact it might be less smart and round addresses to as much as
DEFAULT_ROUNDING. So we prepare for it to do that. */
union fooround {long x; double d;};
#define DEFAULT_ROUNDING (sizeof (union fooround))
/* When we copy a long block of data, this is the unit to do it with.
On some machines, copying successive ints does not work;
in such a case, redefine COPYING_UNIT to `long' (if that works)
or `char' as a last resort. */
#ifndef COPYING_UNIT
#define COPYING_UNIT int
#endif
/* The functions allocating more room by calling `obstack_chunk_alloc'
jump to the handler pointed to by `obstack_alloc_failed_handler'.
This can be set to a user defined function which should either
abort gracefully or use longjump - but shouldn't return. This
variable by default points to the internal function
`print_and_abort'. */
#if defined (__STDC__) && __STDC__
static void print_and_abort (void);
void (*obstack_alloc_failed_handler) (void) = print_and_abort;
#else
static void print_and_abort ();
void (*obstack_alloc_failed_handler) () = print_and_abort;
#endif
/* Exit value used when `print_and_abort' is used. */
#if defined __GNU_LIBRARY__ || defined HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifndef EXIT_FAILURE
#define EXIT_FAILURE 1
#endif
int obstack_exit_failure = EXIT_FAILURE;
/* The non-GNU-C macros copy the obstack into this global variable
to avoid multiple evaluation. */
struct obstack *_obstack;
/* Define a macro that either calls functions with the traditional malloc/free
calling interface, or calls functions with the mmalloc/mfree interface
(that adds an extra first argument), based on the state of use_extra_arg.
For free, do not use ?:, since some compilers, like the MIPS compilers,
do not allow (expr) ? void : void. */
#if defined (__STDC__) && __STDC__
#define CALL_CHUNKFUN(h, size) \
(((h) -> use_extra_arg) \
? (*(h)->chunkfun) ((h)->extra_arg, (size)) \
: (*(struct _obstack_chunk *(*) (long)) (h)->chunkfun) ((size)))
#define CALL_FREEFUN(h, old_chunk) \
do { \
if ((h) -> use_extra_arg) \
(*(h)->freefun) ((h)->extra_arg, (old_chunk)); \
else \
(*(void (*) (void *)) (h)->freefun) ((old_chunk)); \
} while (0)
#else
#define CALL_CHUNKFUN(h, size) \
(((h) -> use_extra_arg) \
? (*(h)->chunkfun) ((h)->extra_arg, (size)) \
: (*(struct _obstack_chunk *(*) ()) (h)->chunkfun) ((size)))
#define CALL_FREEFUN(h, old_chunk) \
do { \
if ((h) -> use_extra_arg) \
(*(h)->freefun) ((h)->extra_arg, (old_chunk)); \
else \
(*(void (*) ()) (h)->freefun) ((old_chunk)); \
} while (0)
#endif
/* Initialize an obstack H for use. Specify chunk size SIZE (0 means default).
Objects start on multiples of ALIGNMENT (0 means use default).
CHUNKFUN is the function to use to allocate chunks,
and FREEFUN the function to free them.
Return nonzero if successful, calls obstack_alloc_failed_handler if
allocation fails. */
int
_obstack_begin (h, size, alignment, chunkfun, freefun)
struct obstack *h;
int size;
int alignment;
#if defined (__STDC__) && __STDC__
POINTER (*chunkfun) (long);
void (*freefun) (void *);
#else
POINTER (*chunkfun) ();
void (*freefun) ();
#endif
{
register struct _obstack_chunk *chunk; /* points to new chunk */
if (alignment == 0)
alignment = (int) DEFAULT_ALIGNMENT;
if (size == 0)
/* Default size is what GNU malloc can fit in a 4096-byte block. */
{
/* 12 is sizeof (mhead) and 4 is EXTRA from GNU malloc.
Use the values for range checking, because if range checking is off,
the extra bytes won't be missed terribly, but if range checking is on
and we used a larger request, a whole extra 4096 bytes would be
allocated.
These number are irrelevant to the new GNU malloc. I suspect it is
less sensitive to the size of the request. */
int extra = ((((12 + DEFAULT_ROUNDING - 1) & ~(DEFAULT_ROUNDING - 1))
+ 4 + DEFAULT_ROUNDING - 1)
& ~(DEFAULT_ROUNDING - 1));
size = 4096 - extra;
}
#if defined (__STDC__) && __STDC__
h->chunkfun = (struct _obstack_chunk * (*)(void *, long)) chunkfun;
h->freefun = (void (*) (void *, struct _obstack_chunk *)) freefun;
#else
h->chunkfun = (struct _obstack_chunk * (*)()) chunkfun;
h->freefun = freefun;
#endif
h->chunk_size = size;
h->alignment_mask = alignment - 1;
h->use_extra_arg = 0;
chunk = h->chunk = CALL_CHUNKFUN (h, h -> chunk_size);
if (!chunk)
(*obstack_alloc_failed_handler) ();
h->next_free = h->object_base = chunk->contents;
h->chunk_limit = chunk->limit
= (char *) chunk + h->chunk_size;
chunk->prev = 0;
/* The initial chunk now contains no empty object. */
h->maybe_empty_object = 0;
h->alloc_failed = 0;
return 1;
}
int
_obstack_begin_1 (h, size, alignment, chunkfun, freefun, arg)
struct obstack *h;
int size;
int alignment;
#if defined (__STDC__) && __STDC__
POINTER (*chunkfun) (POINTER, long);
void (*freefun) (POINTER, POINTER);
#else
POINTER (*chunkfun) ();
void (*freefun) ();
#endif
POINTER arg;
{
register struct _obstack_chunk *chunk; /* points to new chunk */
if (alignment == 0)
alignment = (int) DEFAULT_ALIGNMENT;
if (size == 0)
/* Default size is what GNU malloc can fit in a 4096-byte block. */
{
/* 12 is sizeof (mhead) and 4 is EXTRA from GNU malloc.
Use the values for range checking, because if range checking is off,
the extra bytes won't be missed terribly, but if range checking is on
and we used a larger request, a whole extra 4096 bytes would be
allocated.
These number are irrelevant to the new GNU malloc. I suspect it is
less sensitive to the size of the request. */
int extra = ((((12 + DEFAULT_ROUNDING - 1) & ~(DEFAULT_ROUNDING - 1))
+ 4 + DEFAULT_ROUNDING - 1)
& ~(DEFAULT_ROUNDING - 1));
size = 4096 - extra;
}
#if defined(__STDC__) && __STDC__
h->chunkfun = (struct _obstack_chunk * (*)(void *,long)) chunkfun;
h->freefun = (void (*) (void *, struct _obstack_chunk *)) freefun;
#else
h->chunkfun = (struct _obstack_chunk * (*)()) chunkfun;
h->freefun = freefun;
#endif
h->chunk_size = size;
h->alignment_mask = alignment - 1;
h->extra_arg = arg;
h->use_extra_arg = 1;
chunk = h->chunk = CALL_CHUNKFUN (h, h -> chunk_size);
if (!chunk)
(*obstack_alloc_failed_handler) ();
h->next_free = h->object_base = chunk->contents;
h->chunk_limit = chunk->limit
= (char *) chunk + h->chunk_size;
chunk->prev = 0;
/* The initial chunk now contains no empty object. */
h->maybe_empty_object = 0;
h->alloc_failed = 0;
return 1;
}
/* Allocate a new current chunk for the obstack *H
on the assumption that LENGTH bytes need to be added
to the current object, or a new object of length LENGTH allocated.
Copies any partial object from the end of the old chunk
to the beginning of the new one. */
void
_obstack_newchunk (h, length)
struct obstack *h;
int length;
{
register struct _obstack_chunk *old_chunk = h->chunk;
register struct _obstack_chunk *new_chunk;
register long new_size;
register long obj_size = h->next_free - h->object_base;
register long i;
long already;
/* Compute size for new chunk. */
new_size = (obj_size + length) + (obj_size >> 3) + 100;
if (new_size < h->chunk_size)
new_size = h->chunk_size;
/* Allocate and initialize the new chunk. */
new_chunk = CALL_CHUNKFUN (h, new_size);
if (!new_chunk)
(*obstack_alloc_failed_handler) ();
h->chunk = new_chunk;
new_chunk->prev = old_chunk;
new_chunk->limit = h->chunk_limit = (char *) new_chunk + new_size;
/* Move the existing object to the new chunk.
Word at a time is fast and is safe if the object
is sufficiently aligned. */
if (h->alignment_mask + 1 >= DEFAULT_ALIGNMENT)
{
for (i = obj_size / sizeof (COPYING_UNIT) - 1;
i >= 0; i--)
((COPYING_UNIT *)new_chunk->contents)[i]
= ((COPYING_UNIT *)h->object_base)[i];
/* We used to copy the odd few remaining bytes as one extra COPYING_UNIT,
but that can cross a page boundary on a machine
which does not do strict alignment for COPYING_UNITS. */
already = obj_size / sizeof (COPYING_UNIT) * sizeof (COPYING_UNIT);
}
else
already = 0;
/* Copy remaining bytes one by one. */
for (i = already; i < obj_size; i++)
new_chunk->contents[i] = h->object_base[i];
/* If the object just copied was the only data in OLD_CHUNK,
free that chunk and remove it from the chain.
But not if that chunk might contain an empty object. */
if (h->object_base == old_chunk->contents && ! h->maybe_empty_object)
{
new_chunk->prev = old_chunk->prev;
CALL_FREEFUN (h, old_chunk);
}
h->object_base = new_chunk->contents;
h->next_free = h->object_base + obj_size;
/* The new chunk certainly contains no empty object yet. */
h->maybe_empty_object = 0;
}
/* Return nonzero if object OBJ has been allocated from obstack H.
This is here for debugging.
If you use it in a program, you are probably losing. */
#if defined (__STDC__) && __STDC__
/* Suppress -Wmissing-prototypes warning. We don't want to declare this in
obstack.h because it is just for debugging. */
int _obstack_allocated_p (struct obstack *h, POINTER obj);
#endif
int
_obstack_allocated_p (h, obj)
struct obstack *h;
POINTER obj;
{
register struct _obstack_chunk *lp; /* below addr of any objects in this chunk */
register struct _obstack_chunk *plp; /* point to previous chunk if any */
lp = (h)->chunk;
/* We use >= rather than > since the object cannot be exactly at
the beginning of the chunk but might be an empty object exactly
at the end of an adjacent chunk. */
while (lp != 0 && ((POINTER) lp >= obj || (POINTER) (lp)->limit < obj))
{
plp = lp->prev;
lp = plp;
}
return lp != 0;
}
/* Free objects in obstack H, including OBJ and everything allocate
more recently than OBJ. If OBJ is zero, free everything in H. */
#undef obstack_free
/* This function has two names with identical definitions.
This is the first one, called from non-ANSI code. */
void
_obstack_free (h, obj)
struct obstack *h;
POINTER obj;
{
register struct _obstack_chunk *lp; /* below addr of any objects in this chunk */
register struct _obstack_chunk *plp; /* point to previous chunk if any */
lp = h->chunk;
/* We use >= because there cannot be an object at the beginning of a chunk.
But there can be an empty object at that address
at the end of another chunk. */
while (lp != 0 && ((POINTER) lp >= obj || (POINTER) (lp)->limit < obj))
{
plp = lp->prev;
CALL_FREEFUN (h, lp);
lp = plp;
/* If we switch chunks, we can't tell whether the new current
chunk contains an empty object, so assume that it may. */
h->maybe_empty_object = 1;
}
if (lp)
{
h->object_base = h->next_free = (char *) (obj);
h->chunk_limit = lp->limit;
h->chunk = lp;
}
else if (obj != 0)
/* obj is not in any of the chunks! */
abort ();
}
/* This function is used from ANSI code. */
void
obstack_free (h, obj)
struct obstack *h;
POINTER obj;
{
register struct _obstack_chunk *lp; /* below addr of any objects in this chunk */
register struct _obstack_chunk *plp; /* point to previous chunk if any */
lp = h->chunk;
/* We use >= because there cannot be an object at the beginning of a chunk.
But there can be an empty object at that address
at the end of another chunk. */
while (lp != 0 && ((POINTER) lp >= obj || (POINTER) (lp)->limit < obj))
{
plp = lp->prev;
CALL_FREEFUN (h, lp);
lp = plp;
/* If we switch chunks, we can't tell whether the new current
chunk contains an empty object, so assume that it may. */
h->maybe_empty_object = 1;
}
if (lp)
{
h->object_base = h->next_free = (char *) (obj);
h->chunk_limit = lp->limit;
h->chunk = lp;
}
else if (obj != 0)
/* obj is not in any of the chunks! */
abort ();
}
int
_obstack_memory_used (h)
struct obstack *h;
{
register struct _obstack_chunk* lp;
register int nbytes = 0;
for (lp = h->chunk; lp != 0; lp = lp->prev)
{
nbytes += lp->limit - (char *) lp;
}
return nbytes;
}
/* Define the error handler. */
#ifndef _
# ifdef HAVE_LIBINTL_H
# include <libintl.h>
# ifndef _
# define _(Str) gettext (Str)
# endif
# else
# define _(Str) (Str)
# endif
#endif
#if defined _LIBC && defined USE_IN_LIBIO
# include <libio/iolibio.h>
# define fputs(s, f) _IO_fputs (s, f)
#endif
static void
print_and_abort ()
{
fputs (_("memory exhausted"), stderr);
fputc ('\n', stderr);
exit (obstack_exit_failure);
}
#if 0
/* These are now turned off because the applications do not use it
and it uses bcopy via obstack_grow, which causes trouble on sysV. */
/* Now define the functional versions of the obstack macros.
Define them to simply use the corresponding macros to do the job. */
#if defined (__STDC__) && __STDC__
/* These function definitions do not work with non-ANSI preprocessors;
they won't pass through the macro names in parentheses. */
/* The function names appear in parentheses in order to prevent
the macro-definitions of the names from being expanded there. */
POINTER (obstack_base) (obstack)
struct obstack *obstack;
{
return obstack_base (obstack);
}
POINTER (obstack_next_free) (obstack)
struct obstack *obstack;
{
return obstack_next_free (obstack);
}
int (obstack_object_size) (obstack)
struct obstack *obstack;
{
return obstack_object_size (obstack);
}
int (obstack_room) (obstack)
struct obstack *obstack;
{
return obstack_room (obstack);
}
int (obstack_make_room) (obstack, length)
struct obstack *obstack;
int length;
{
return obstack_make_room (obstack, length);
}
void (obstack_grow) (obstack, pointer, length)
struct obstack *obstack;
POINTER pointer;
int length;
{
obstack_grow (obstack, pointer, length);
}
void (obstack_grow0) (obstack, pointer, length)
struct obstack *obstack;
POINTER pointer;
int length;
{
obstack_grow0 (obstack, pointer, length);
}
void (obstack_1grow) (obstack, character)
struct obstack *obstack;
int character;
{
obstack_1grow (obstack, character);
}
void (obstack_blank) (obstack, length)
struct obstack *obstack;
int length;
{
obstack_blank (obstack, length);
}
void (obstack_1grow_fast) (obstack, character)
struct obstack *obstack;
int character;
{
obstack_1grow_fast (obstack, character);
}
void (obstack_blank_fast) (obstack, length)
struct obstack *obstack;
int length;
{
obstack_blank_fast (obstack, length);
}
POINTER (obstack_finish) (obstack)
struct obstack *obstack;
{
return obstack_finish (obstack);
}
POINTER (obstack_alloc) (obstack, length)
struct obstack *obstack;
int length;
{
return obstack_alloc (obstack, length);
}
POINTER (obstack_copy) (obstack, pointer, length)
struct obstack *obstack;
POINTER pointer;
int length;
{
return obstack_copy (obstack, pointer, length);
}
POINTER (obstack_copy0) (obstack, pointer, length)
struct obstack *obstack;
POINTER pointer;
int length;
{
return obstack_copy0 (obstack, pointer, length);
}
#endif /* __STDC__ */
#endif /* 0 */
#endif /* !ELIDE_CODE */

593
gnu/usr.bin/grep/obstack.h
View file

@ -1,593 +0,0 @@
/* obstack.h - object stack macros
Copyright (C) 1988,89,90,91,92,93,94,96,97,98,99 Free Software Foundation, Inc.
This file is part of the GNU C Library. Its master source is NOT part of
the C library, however. The master source lives in /gd/gnu/lib.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU C Library; see the file COPYING.LIB. If not,
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
/* Summary:
All the apparent functions defined here are macros. The idea
is that you would use these pre-tested macros to solve a
very specific set of problems, and they would run fast.
Caution: no side-effects in arguments please!! They may be
evaluated MANY times!!
These macros operate a stack of objects. Each object starts life
small, and may grow to maturity. (Consider building a word syllable
by syllable.) An object can move while it is growing. Once it has
been "finished" it never changes address again. So the "top of the
stack" is typically an immature growing object, while the rest of the
stack is of mature, fixed size and fixed address objects.
These routines grab large chunks of memory, using a function you
supply, called `obstack_chunk_alloc'. On occasion, they free chunks,
by calling `obstack_chunk_free'. You must define them and declare
them before using any obstack macros.
Each independent stack is represented by a `struct obstack'.
Each of the obstack macros expects a pointer to such a structure
as the first argument.
One motivation for this package is the problem of growing char strings
in symbol tables. Unless you are "fascist pig with a read-only mind"
--Gosper's immortal quote from HAKMEM item 154, out of context--you
would not like to put any arbitrary upper limit on the length of your
symbols.
In practice this often means you will build many short symbols and a
few long symbols. At the time you are reading a symbol you don't know
how long it is. One traditional method is to read a symbol into a
buffer, realloc()ating the buffer every time you try to read a symbol
that is longer than the buffer. This is beaut, but you still will
want to copy the symbol from the buffer to a more permanent
symbol-table entry say about half the time.
With obstacks, you can work differently. Use one obstack for all symbol
names. As you read a symbol, grow the name in the obstack gradually.
When the name is complete, finalize it. Then, if the symbol exists already,
free the newly read name.
The way we do this is to take a large chunk, allocating memory from
low addresses. When you want to build a symbol in the chunk you just
add chars above the current "high water mark" in the chunk. When you
have finished adding chars, because you got to the end of the symbol,
you know how long the chars are, and you can create a new object.
Mostly the chars will not burst over the highest address of the chunk,
because you would typically expect a chunk to be (say) 100 times as
long as an average object.
In case that isn't clear, when we have enough chars to make up
the object, THEY ARE ALREADY CONTIGUOUS IN THE CHUNK (guaranteed)
so we just point to it where it lies. No moving of chars is
needed and this is the second win: potentially long strings need
never be explicitly shuffled. Once an object is formed, it does not
change its address during its lifetime.
When the chars burst over a chunk boundary, we allocate a larger
chunk, and then copy the partly formed object from the end of the old
chunk to the beginning of the new larger chunk. We then carry on
accreting characters to the end of the object as we normally would.
A special macro is provided to add a single char at a time to a
growing object. This allows the use of register variables, which
break the ordinary 'growth' macro.
Summary:
We allocate large chunks.
We carve out one object at a time from the current chunk.
Once carved, an object never moves.
We are free to append data of any size to the currently
growing object.
Exactly one object is growing in an obstack at any one time.
You can run one obstack per control block.
You may have as many control blocks as you dare.
Because of the way we do it, you can `unwind' an obstack
back to a previous state. (You may remove objects much
as you would with a stack.)
*/
/* Don't do the contents of this file more than once. */
#ifndef _OBSTACK_H
#define _OBSTACK_H 1
#ifdef __cplusplus
extern "C" {
#endif
/* We use subtraction of (char *) 0 instead of casting to int
because on word-addressable machines a simple cast to int
may ignore the byte-within-word field of the pointer. */
#ifndef __PTR_TO_INT
# define __PTR_TO_INT(P) ((P) - (char *) 0)
#endif
#ifndef __INT_TO_PTR
# define __INT_TO_PTR(P) ((P) + (char *) 0)
#endif
/* We need the type of the resulting object. If __PTRDIFF_TYPE__ is
defined, as with GNU C, use that; that way we don't pollute the
namespace with <stddef.h>'s symbols. Otherwise, if <stddef.h> is
available, include it and use ptrdiff_t. In traditional C, long is
the best that we can do. */
#ifdef __PTRDIFF_TYPE__
# define PTR_INT_TYPE __PTRDIFF_TYPE__
#else
# ifdef HAVE_STDDEF_H
# include <stddef.h>
# define PTR_INT_TYPE ptrdiff_t
# else
# define PTR_INT_TYPE long
# endif
#endif
#if defined _LIBC || defined HAVE_STRING_H
# include <string.h>
# define _obstack_memcpy(To, From, N) memcpy ((To), (From), (N))
#else
# ifdef memcpy
# define _obstack_memcpy(To, From, N) memcpy ((To), (From), (N))
# else
# define _obstack_memcpy(To, From, N) bcopy ((From), (To), (N))
# endif
#endif
struct _obstack_chunk /* Lives at front of each chunk. */
{
char *limit; /* 1 past end of this chunk */
struct _obstack_chunk *prev; /* address of prior chunk or NULL */
char contents[4]; /* objects begin here */
};
struct obstack /* control current object in current chunk */
{
long chunk_size; /* preferred size to allocate chunks in */
struct _obstack_chunk *chunk; /* address of current struct obstack_chunk */
char *object_base; /* address of object we are building */
char *next_free; /* where to add next char to current object */
char *chunk_limit; /* address of char after current chunk */
PTR_INT_TYPE temp; /* Temporary for some macros. */
int alignment_mask; /* Mask of alignment for each object. */
#if defined __STDC__ && __STDC__
/* These prototypes vary based on `use_extra_arg', and we use
casts to the prototypeless function type in all assignments,
but having prototypes here quiets -Wstrict-prototypes. */
struct _obstack_chunk *(*chunkfun) (void *, long);
void (*freefun) (void *, struct _obstack_chunk *);
void *extra_arg; /* first arg for chunk alloc/dealloc funcs */
#else
struct _obstack_chunk *(*chunkfun) (); /* User's fcn to allocate a chunk. */
void (*freefun) (); /* User's function to free a chunk. */
char *extra_arg; /* first arg for chunk alloc/dealloc funcs */
#endif
unsigned use_extra_arg:1; /* chunk alloc/dealloc funcs take extra arg */
unsigned maybe_empty_object:1;/* There is a possibility that the current
chunk contains a zero-length object. This
prevents freeing the chunk if we allocate
a bigger chunk to replace it. */
unsigned alloc_failed:1; /* No longer used, as we now call the failed
handler on error, but retained for binary
compatibility. */
};
/* Declare the external functions we use; they are in obstack.c. */
#if defined __STDC__ && __STDC__
extern void _obstack_newchunk (struct obstack *, int);
extern void _obstack_free (struct obstack *, void *);
extern int _obstack_begin (struct obstack *, int, int,
void *(*) (long), void (*) (void *));
extern int _obstack_begin_1 (struct obstack *, int, int,
void *(*) (void *, long),
void (*) (void *, void *), void *);
extern int _obstack_memory_used (struct obstack *);
#else
extern void _obstack_newchunk ();
extern void _obstack_free ();
extern int _obstack_begin ();
extern int _obstack_begin_1 ();
extern int _obstack_memory_used ();
#endif
#if defined __STDC__ && __STDC__
/* Do the function-declarations after the structs
but before defining the macros. */
void obstack_init (struct obstack *obstack);
void * obstack_alloc (struct obstack *obstack, int size);
void * obstack_copy (struct obstack *obstack, void *address, int size);
void * obstack_copy0 (struct obstack *obstack, void *address, int size);
void obstack_free (struct obstack *obstack, void *block);
void obstack_blank (struct obstack *obstack, int size);
void obstack_grow (struct obstack *obstack, void *data, int size);
void obstack_grow0 (struct obstack *obstack, void *data, int size);
void obstack_1grow (struct obstack *obstack, int data_char);
void obstack_ptr_grow (struct obstack *obstack, void *data);
void obstack_int_grow (struct obstack *obstack, int data);
void * obstack_finish (struct obstack *obstack);
int obstack_object_size (struct obstack *obstack);
int obstack_room (struct obstack *obstack);
void obstack_make_room (struct obstack *obstack, int size);
void obstack_1grow_fast (struct obstack *obstack, int data_char);
void obstack_ptr_grow_fast (struct obstack *obstack, void *data);
void obstack_int_grow_fast (struct obstack *obstack, int data);
void obstack_blank_fast (struct obstack *obstack, int size);
void * obstack_base (struct obstack *obstack);
void * obstack_next_free (struct obstack *obstack);
int obstack_alignment_mask (struct obstack *obstack);
int obstack_chunk_size (struct obstack *obstack);
int obstack_memory_used (struct obstack *obstack);
#endif /* __STDC__ */
/* Non-ANSI C cannot really support alternative functions for these macros,
so we do not declare them. */
/* Error handler called when `obstack_chunk_alloc' failed to allocate
more memory. This can be set to a user defined function which
should either abort gracefully or use longjump - but shouldn't
return. The default action is to print a message and abort. */
#if defined __STDC__ && __STDC__
extern void (*obstack_alloc_failed_handler) (void);
#else
extern void (*obstack_alloc_failed_handler) ();
#endif
/* Exit value used when `print_and_abort' is used. */
extern int obstack_exit_failure;
/* Pointer to beginning of object being allocated or to be allocated next.
Note that this might not be the final address of the object
because a new chunk might be needed to hold the final size. */
#define obstack_base(h) ((h)->object_base)
/* Size for allocating ordinary chunks. */
#define obstack_chunk_size(h) ((h)->chunk_size)
/* Pointer to next byte not yet allocated in current chunk. */
#define obstack_next_free(h) ((h)->next_free)
/* Mask specifying low bits that should be clear in address of an object. */
#define obstack_alignment_mask(h) ((h)->alignment_mask)
/* To prevent prototype warnings provide complete argument list in
standard C version. */
#if defined __STDC__ && __STDC__
# define obstack_init(h) \
_obstack_begin ((h), 0, 0, \
(void *(*) (long)) obstack_chunk_alloc, (void (*) (void *)) obstack_chunk_free)
# define obstack_begin(h, size) \
_obstack_begin ((h), (size), 0, \
(void *(*) (long)) obstack_chunk_alloc, (void (*) (void *)) obstack_chunk_free)
# define obstack_specify_allocation(h, size, alignment, chunkfun, freefun) \
_obstack_begin ((h), (size), (alignment), \
(void *(*) (long)) (chunkfun), (void (*) (void *)) (freefun))
# define obstack_specify_allocation_with_arg(h, size, alignment, chunkfun, freefun, arg) \
_obstack_begin_1 ((h), (size), (alignment), \
(void *(*) (void *, long)) (chunkfun), \
(void (*) (void *, void *)) (freefun), (arg))
# define obstack_chunkfun(h, newchunkfun) \
((h) -> chunkfun = (struct _obstack_chunk *(*)(void *, long)) (newchunkfun))
# define obstack_freefun(h, newfreefun) \
((h) -> freefun = (void (*)(void *, struct _obstack_chunk *)) (newfreefun))
#else
# define obstack_init(h) \
_obstack_begin ((h), 0, 0, \
(void *(*) ()) obstack_chunk_alloc, (void (*) ()) obstack_chunk_free)
# define obstack_begin(h, size) \
_obstack_begin ((h), (size), 0, \
(void *(*) ()) obstack_chunk_alloc, (void (*) ()) obstack_chunk_free)
# define obstack_specify_allocation(h, size, alignment, chunkfun, freefun) \
_obstack_begin ((h), (size), (alignment), \
(void *(*) ()) (chunkfun), (void (*) ()) (freefun))
# define obstack_specify_allocation_with_arg(h, size, alignment, chunkfun, freefun, arg) \
_obstack_begin_1 ((h), (size), (alignment), \
(void *(*) ()) (chunkfun), (void (*) ()) (freefun), (arg))
# define obstack_chunkfun(h, newchunkfun) \
((h) -> chunkfun = (struct _obstack_chunk *(*)()) (newchunkfun))
# define obstack_freefun(h, newfreefun) \
((h) -> freefun = (void (*)()) (newfreefun))
#endif
#define obstack_1grow_fast(h,achar) (*((h)->next_free)++ = achar)
#define obstack_blank_fast(h,n) ((h)->next_free += (n))
#define obstack_memory_used(h) _obstack_memory_used (h)
#if defined __GNUC__ && defined __STDC__ && __STDC__
/* NextStep 2.0 cc is really gcc 1.93 but it defines __GNUC__ = 2 and
does not implement __extension__. But that compiler doesn't define
__GNUC_MINOR__. */
# if __GNUC__ < 2 || (__NeXT__ && !__GNUC_MINOR__)
# define __extension__
# endif
/* For GNU C, if not -traditional,
we can define these macros to compute all args only once
without using a global variable.
Also, we can avoid using the `temp' slot, to make faster code. */
# define obstack_object_size(OBSTACK) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
(unsigned) (__o->next_free - __o->object_base); })
# define obstack_room(OBSTACK) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
(unsigned) (__o->chunk_limit - __o->next_free); })
# define obstack_make_room(OBSTACK,length) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
int __len = (length); \
if (__o->chunk_limit - __o->next_free < __len) \
_obstack_newchunk (__o, __len); \
(void) 0; })
# define obstack_empty_p(OBSTACK) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
(__o->chunk->prev == 0 && __o->next_free - __o->chunk->contents == 0); })
# define obstack_grow(OBSTACK,where,length) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
int __len = (length); \
if (__o->next_free + __len > __o->chunk_limit) \
_obstack_newchunk (__o, __len); \
_obstack_memcpy (__o->next_free, (char *) (where), __len); \
__o->next_free += __len; \
(void) 0; })
# define obstack_grow0(OBSTACK,where,length) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
int __len = (length); \
if (__o->next_free + __len + 1 > __o->chunk_limit) \
_obstack_newchunk (__o, __len + 1); \
_obstack_memcpy (__o->next_free, (char *) (where), __len); \
__o->next_free += __len; \
*(__o->next_free)++ = 0; \
(void) 0; })
# define obstack_1grow(OBSTACK,datum) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
if (__o->next_free + 1 > __o->chunk_limit) \
_obstack_newchunk (__o, 1); \
*(__o->next_free)++ = (datum); \
(void) 0; })
/* These assume that the obstack alignment is good enough for pointers or ints,
and that the data added so far to the current object
shares that much alignment. */
# define obstack_ptr_grow(OBSTACK,datum) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
if (__o->next_free + sizeof (void *) > __o->chunk_limit) \
_obstack_newchunk (__o, sizeof (void *)); \
*((void **)__o->next_free)++ = ((void *)datum); \
(void) 0; })
# define obstack_int_grow(OBSTACK,datum) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
if (__o->next_free + sizeof (int) > __o->chunk_limit) \
_obstack_newchunk (__o, sizeof (int)); \
*((int *)__o->next_free)++ = ((int)datum); \
(void) 0; })
# define obstack_ptr_grow_fast(h,aptr) (*((void **) (h)->next_free)++ = (void *)aptr)
# define obstack_int_grow_fast(h,aint) (*((int *) (h)->next_free)++ = (int) aint)
# define obstack_blank(OBSTACK,length) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
int __len = (length); \
if (__o->chunk_limit - __o->next_free < __len) \
_obstack_newchunk (__o, __len); \
__o->next_free += __len; \
(void) 0; })
# define obstack_alloc(OBSTACK,length) \
__extension__ \
({ struct obstack *__h = (OBSTACK); \
obstack_blank (__h, (length)); \
obstack_finish (__h); })
# define obstack_copy(OBSTACK,where,length) \
__extension__ \
({ struct obstack *__h = (OBSTACK); \
obstack_grow (__h, (where), (length)); \
obstack_finish (__h); })
# define obstack_copy0(OBSTACK,where,length) \
__extension__ \
({ struct obstack *__h = (OBSTACK); \
obstack_grow0 (__h, (where), (length)); \
obstack_finish (__h); })
/* The local variable is named __o1 to avoid a name conflict
when obstack_blank is called. */
# define obstack_finish(OBSTACK) \
__extension__ \
({ struct obstack *__o1 = (OBSTACK); \
void *value; \
value = (void *) __o1->object_base; \
if (__o1->next_free == value) \
__o1->maybe_empty_object = 1; \
__o1->next_free \
= __INT_TO_PTR ((__PTR_TO_INT (__o1->next_free)+__o1->alignment_mask)\
& ~ (__o1->alignment_mask)); \
if (__o1->next_free - (char *)__o1->chunk \
> __o1->chunk_limit - (char *)__o1->chunk) \
__o1->next_free = __o1->chunk_limit; \
__o1->object_base = __o1->next_free; \
value; })
# define obstack_free(OBSTACK, OBJ) \
__extension__ \
({ struct obstack *__o = (OBSTACK); \
void *__obj = (OBJ); \
if (__obj > (void *)__o->chunk && __obj < (void *)__o->chunk_limit) \
__o->next_free = __o->object_base = (char *)__obj; \
else (obstack_free) (__o, __obj); })
#else /* not __GNUC__ or not __STDC__ */
# define obstack_object_size(h) \
(unsigned) ((h)->next_free - (h)->object_base)
# define obstack_room(h) \
(unsigned) ((h)->chunk_limit - (h)->next_free)
# define obstack_empty_p(h) \
((h)->chunk->prev == 0 && (h)->next_free - (h)->chunk->contents == 0)
/* Note that the call to _obstack_newchunk is enclosed in (..., 0)
so that we can avoid having void expressions
in the arms of the conditional expression.
Casting the third operand to void was tried before,
but some compilers won't accept it. */
# define obstack_make_room(h,length) \
( (h)->temp = (length), \
(((h)->next_free + (h)->temp > (h)->chunk_limit) \
? (_obstack_newchunk ((h), (h)->temp), 0) : 0))
# define obstack_grow(h,where,length) \
( (h)->temp = (length), \
(((h)->next_free + (h)->temp > (h)->chunk_limit) \
? (_obstack_newchunk ((h), (h)->temp), 0) : 0), \
_obstack_memcpy ((h)->next_free, (char *) (where), (h)->temp), \
(h)->next_free += (h)->temp)
# define obstack_grow0(h,where,length) \
( (h)->temp = (length), \
(((h)->next_free + (h)->temp + 1 > (h)->chunk_limit) \
? (_obstack_newchunk ((h), (h)->temp + 1), 0) : 0), \
_obstack_memcpy ((h)->next_free, (char *) (where), (h)->temp), \
(h)->next_free += (h)->temp, \
*((h)->next_free)++ = 0)
# define obstack_1grow(h,datum) \
( (((h)->next_free + 1 > (h)->chunk_limit) \
? (_obstack_newchunk ((h), 1), 0) : 0), \
(*((h)->next_free)++ = (datum)))
# define obstack_ptr_grow(h,datum) \
( (((h)->next_free + sizeof (char *) > (h)->chunk_limit) \
? (_obstack_newchunk ((h), sizeof (char *)), 0) : 0), \
(*((char **) (((h)->next_free+=sizeof(char *))-sizeof(char *))) = ((char *) datum)))
# define obstack_int_grow(h,datum) \
( (((h)->next_free + sizeof (int) > (h)->chunk_limit) \
? (_obstack_newchunk ((h), sizeof (int)), 0) : 0), \
(*((int *) (((h)->next_free+=sizeof(int))-sizeof(int))) = ((int) datum)))
# define obstack_ptr_grow_fast(h,aptr) (*((char **) (h)->next_free)++ = (char *) aptr)
# define obstack_int_grow_fast(h,aint) (*((int *) (h)->next_free)++ = (int) aint)
# define obstack_blank(h,length) \
( (h)->temp = (length), \
(((h)->chunk_limit - (h)->next_free < (h)->temp) \
? (_obstack_newchunk ((h), (h)->temp), 0) : 0), \
((h)->next_free += (h)->temp))
# define obstack_alloc(h,length) \
(obstack_blank ((h), (length)), obstack_finish ((h)))
# define obstack_copy(h,where,length) \
(obstack_grow ((h), (where), (length)), obstack_finish ((h)))
# define obstack_copy0(h,where,length) \
(obstack_grow0 ((h), (where), (length)), obstack_finish ((h)))
# define obstack_finish(h) \
( ((h)->next_free == (h)->object_base \
? (((h)->maybe_empty_object = 1), 0) \
: 0), \
(h)->temp = __PTR_TO_INT ((h)->object_base), \
(h)->next_free \
= __INT_TO_PTR ((__PTR_TO_INT ((h)->next_free)+(h)->alignment_mask) \
& ~ ((h)->alignment_mask)), \
(((h)->next_free - (char *) (h)->chunk \
> (h)->chunk_limit - (char *) (h)->chunk) \
? ((h)->next_free = (h)->chunk_limit) : 0), \
(h)->object_base = (h)->next_free, \
__INT_TO_PTR ((h)->temp))
# if defined __STDC__ && __STDC__
# define obstack_free(h,obj) \
( (h)->temp = (char *) (obj) - (char *) (h)->chunk, \
(((h)->temp > 0 && (h)->temp < (h)->chunk_limit - (char *) (h)->chunk)\
? (int) ((h)->next_free = (h)->object_base \
= (h)->temp + (char *) (h)->chunk) \
: (((obstack_free) ((h), (h)->temp + (char *) (h)->chunk), 0), 0)))
# else
# define obstack_free(h,obj) \
( (h)->temp = (char *) (obj) - (char *) (h)->chunk, \
(((h)->temp > 0 && (h)->temp < (h)->chunk_limit - (char *) (h)->chunk)\
? (int) ((h)->next_free = (h)->object_base \
= (h)->temp + (char *) (h)->chunk) \
: (_obstack_free ((h), (h)->temp + (char *) (h)->chunk), 0)))
# endif
#endif /* not __GNUC__ or not __STDC__ */
#ifdef __cplusplus
} /* C++ */
#endif
#endif /* obstack.h */

613
gnu/usr.bin/grep/quotearg.c
View file

@ -1,613 +0,0 @@
/* quotearg.c - quote arguments for output
Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Paul Eggert <eggert@twinsun.com> */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#if HAVE_STDDEF_H
# include <stddef.h> /* For the definition of size_t on windows w/MSVC. */
#endif
#include <sys/types.h>
#include <quotearg.h>
#include <xalloc.h>
#include <ctype.h>
#if ENABLE_NLS
# include <libintl.h>
# define _(text) gettext (text)
#else
# define _(text) text
#endif
#define N_(text) text
#if HAVE_LIMITS_H
# include <limits.h>
#endif
#ifndef CHAR_BIT
# define CHAR_BIT 8
#endif
#ifndef UCHAR_MAX
# define UCHAR_MAX ((unsigned char) -1)
#endif
#if HAVE_C_BACKSLASH_A
# define ALERT_CHAR '\a'
#else
# define ALERT_CHAR '\7'
#endif
#if HAVE_STDLIB_H
# include <stdlib.h>
#endif
#if HAVE_STRING_H
# include <string.h>
#endif
#if HAVE_WCHAR_H
# include <wchar.h>
#endif
#if !HAVE_MBRTOWC
/* Disable multibyte processing entirely. Since MB_CUR_MAX is 1, the
other macros are defined only for documentation and to satisfy C
syntax. */
# undef MB_CUR_MAX
# define MB_CUR_MAX 1
# define mbrtowc(pwc, s, n, ps) ((*(pwc) = *(s)) != 0)
# define mbsinit(ps) 1
# define iswprint(wc) ISPRINT ((unsigned char) (wc))
#endif
#ifndef iswprint
# if HAVE_WCTYPE_H
# include <wctype.h>
# endif
# if !defined iswprint && !HAVE_ISWPRINT
# define iswprint(wc) 1
# endif
#endif
#define INT_BITS (sizeof (int) * CHAR_BIT)
#if defined (STDC_HEADERS) || (!defined (isascii) && !defined (HAVE_ISASCII))
# define IN_CTYPE_DOMAIN(c) 1
#else
# define IN_CTYPE_DOMAIN(c) isascii(c)
#endif
/* Undefine to protect against the definition in wctype.h of solaris2.6. */
#undef ISPRINT
#define ISPRINT(c) (IN_CTYPE_DOMAIN (c) && isprint (c))
struct quoting_options
{
/* Basic quoting style. */
enum quoting_style style;
/* Quote the characters indicated by this bit vector even if the
quoting style would not normally require them to be quoted. */
int quote_these_too[(UCHAR_MAX / INT_BITS) + 1];
};
/* Names of quoting styles. */
char const *const quoting_style_args[] =
{
"literal",
"shell",
"shell-always",
"c",
"escape",
"locale",
"clocale",
0
};
/* Correspondences to quoting style names. */
enum quoting_style const quoting_style_vals[] =
{
literal_quoting_style,
shell_quoting_style,
shell_always_quoting_style,
c_quoting_style,
escape_quoting_style,
locale_quoting_style,
clocale_quoting_style
};
/* The default quoting options. */
static struct quoting_options default_quoting_options;
/* Allocate a new set of quoting options, with contents initially identical
to O if O is not null, or to the default if O is null.
It is the caller's responsibility to free the result. */
struct quoting_options *
clone_quoting_options (struct quoting_options *o)
{
struct quoting_options *p
= (struct quoting_options *) xmalloc (sizeof (struct quoting_options));
*p = *(o ? o : &default_quoting_options);
return p;
}
/* Get the value of O's quoting style. If O is null, use the default. */
enum quoting_style
get_quoting_style (struct quoting_options *o)
{
return (o ? o : &default_quoting_options)->style;
}
/* In O (or in the default if O is null),
set the value of the quoting style to S. */
void
set_quoting_style (struct quoting_options *o, enum quoting_style s)
{
(o ? o : &default_quoting_options)->style = s;
}
/* In O (or in the default if O is null),
set the value of the quoting options for character C to I.
Return the old value. Currently, the only values defined for I are
0 (the default) and 1 (which means to quote the character even if
it would not otherwise be quoted). */
int
set_char_quoting (struct quoting_options *o, char c, int i)
{
unsigned char uc = c;
int *p = (o ? o : &default_quoting_options)->quote_these_too + uc / INT_BITS;
int shift = uc % INT_BITS;
int r = (*p >> shift) & 1;
*p ^= ((i & 1) ^ r) << shift;
return r;
}
/* MSGID approximates a quotation mark. Return its translation if it
has one; otherwise, return either it or "\"", depending on S. */
static char const *
gettext_quote (char const *msgid, enum quoting_style s)
{
char const *translation = _(msgid);
if (translation == msgid && s == clocale_quoting_style)
translation = "\"";
return translation;
}
/* Place into buffer BUFFER (of size BUFFERSIZE) a quoted version of
argument ARG (of size ARGSIZE), using QUOTING_STYLE and the
non-quoting-style part of O to control quoting.
Terminate the output with a null character, and return the written
size of the output, not counting the terminating null.
If BUFFERSIZE is too small to store the output string, return the
value that would have been returned had BUFFERSIZE been large enough.
If ARGSIZE is -1, use the string length of the argument for ARGSIZE.
This function acts like quotearg_buffer (BUFFER, BUFFERSIZE, ARG,
ARGSIZE, O), except it uses QUOTING_STYLE instead of the quoting
style specified by O, and O may not be null. */
static size_t
quotearg_buffer_restyled (char *buffer, size_t buffersize,
char const *arg, size_t argsize,
enum quoting_style quoting_style,
struct quoting_options const *o)
{
size_t i;
size_t len = 0;
char const *quote_string = 0;
size_t quote_string_len = 0;
int backslash_escapes = 0;
int unibyte_locale = MB_CUR_MAX == 1;
#define STORE(c) \
do \
{ \
if (len < buffersize) \
buffer[len] = (c); \
len++; \
} \
while (0)
switch (quoting_style)
{
case c_quoting_style:
STORE ('"');
backslash_escapes = 1;
quote_string = "\"";
quote_string_len = 1;
break;
case escape_quoting_style:
backslash_escapes = 1;
break;
case locale_quoting_style:
case clocale_quoting_style:
{
/* Get translations for open and closing quotation marks.
The message catalog should translate "`" to a left
quotation mark suitable for the locale, and similarly for
"'". If the catalog has no translation,
locale_quoting_style quotes `like this', and
clocale_quoting_style quotes "like this".
For example, an American English Unicode locale should
translate "`" to U+201C (LEFT DOUBLE QUOTATION MARK), and
should translate "'" to U+201D (RIGHT DOUBLE QUOTATION
MARK). A British English Unicode locale should instead
translate these to U+2018 (LEFT SINGLE QUOTATION MARK) and
U+2019 (RIGHT SINGLE QUOTATION MARK), respectively. */
char const *left = gettext_quote (N_("`"), quoting_style);
char const *right = gettext_quote (N_("'"), quoting_style);
for (quote_string = left; *quote_string; quote_string++)
STORE (*quote_string);
backslash_escapes = 1;
quote_string = right;
quote_string_len = strlen (quote_string);
}
break;
case shell_always_quoting_style:
STORE ('\'');
quote_string = "'";
quote_string_len = 1;
break;
default:
break;
}
for (i = 0; ! (argsize == (size_t) -1 ? arg[i] == '\0' : i == argsize); i++)
{
unsigned char c;
unsigned char esc;
if (backslash_escapes
&& quote_string_len
&& i + quote_string_len <= argsize
&& memcmp (arg + i, quote_string, quote_string_len) == 0)
STORE ('\\');
c = arg[i];
switch (c)
{
case '?':
switch (quoting_style)
{
case shell_quoting_style:
goto use_shell_always_quoting_style;
case c_quoting_style:
if (i + 2 < argsize && arg[i + 1] == '?')
switch (arg[i + 2])
{
case '!': case '\'':
case '(': case ')': case '-': case '/':
case '<': case '=': case '>':
/* Escape the second '?' in what would otherwise be
a trigraph. */
i += 2;
c = arg[i + 2];
STORE ('?');
STORE ('\\');
STORE ('?');
break;
}
break;
default:
break;
}
break;
case ALERT_CHAR: esc = 'a'; goto c_escape;
case '\b': esc = 'b'; goto c_escape;
case '\f': esc = 'f'; goto c_escape;
case '\n': esc = 'n'; goto c_and_shell_escape;
case '\r': esc = 'r'; goto c_and_shell_escape;
case '\t': esc = 't'; goto c_and_shell_escape;
case '\v': esc = 'v'; goto c_escape;
case '\\': esc = c; goto c_and_shell_escape;
c_and_shell_escape:
if (quoting_style == shell_quoting_style)
goto use_shell_always_quoting_style;
c_escape:
if (backslash_escapes)
{
c = esc;
goto store_escape;
}
break;
case '#': case '~':
if (i != 0)
break;
/* Fall through. */
case ' ':
case '!': /* special in bash */
case '"': case '$': case '&':
case '(': case ')': case '*': case ';':
case '<': case '>': case '[':
case '^': /* special in old /bin/sh, e.g. SunOS 4.1.4 */
case '`': case '|':
/* A shell special character. In theory, '$' and '`' could
be the first bytes of multibyte characters, which means
we should check them with mbrtowc, but in practice this
doesn't happen so it's not worth worrying about. */
if (quoting_style == shell_quoting_style)
goto use_shell_always_quoting_style;
break;
case '\'':
switch (quoting_style)
{
case shell_quoting_style:
goto use_shell_always_quoting_style;
case shell_always_quoting_style:
STORE ('\'');
STORE ('\\');
STORE ('\'');
break;
default:
break;
}
break;
case '%': case '+': case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9': case ':': case '=':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z': case ']': case '_': case 'a': case 'b':
case 'c': case 'd': case 'e': case 'f': case 'g': case 'h':
case 'i': case 'j': case 'k': case 'l': case 'm': case 'n':
case 'o': case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y': case 'z':
case '{': case '}':
/* These characters don't cause problems, no matter what the
quoting style is. They cannot start multibyte sequences. */
break;
default:
/* If we have a multibyte sequence, copy it until we reach
its end, find an error, or come back to the initial shift
state. For C-like styles, if the sequence has
unprintable characters, escape the whole sequence, since
we can't easily escape single characters within it. */
{
/* Length of multibyte sequence found so far. */
size_t m;
int printable;
if (unibyte_locale)
{
m = 1;
printable = ISPRINT (c);
}
else
{
mbstate_t mbstate;
memset (&mbstate, 0, sizeof mbstate);
m = 0;
printable = 1;
if (argsize == (size_t) -1)
argsize = strlen (arg);
do
{
wchar_t w;
size_t bytes = mbrtowc (&w, &arg[i + m],
argsize - (i + m), &mbstate);
if (bytes == 0)
break;
else if (bytes == (size_t) -1)
{
printable = 0;
break;
}
else if (bytes == (size_t) -2)
{
printable = 0;
while (i + m < argsize && arg[i + m])
m++;
break;
}
else
{
if (! iswprint (w))
printable = 0;
m += bytes;
}
}
while (! mbsinit (&mbstate));
}
if (1 < m || (backslash_escapes && ! printable))
{
/* Output a multibyte sequence, or an escaped
unprintable unibyte character. */
size_t ilim = i + m;
for (;;)
{
if (backslash_escapes && ! printable)
{
STORE ('\\');
STORE ('0' + (c >> 6));
STORE ('0' + ((c >> 3) & 7));
c = '0' + (c & 7);
}
if (ilim <= i + 1)
break;
STORE (c);
c = arg[++i];
}
goto store_c;
}
}
}
if (! (backslash_escapes
&& o->quote_these_too[c / INT_BITS] & (1 << (c % INT_BITS))))
goto store_c;
store_escape:
STORE ('\\');
store_c:
STORE (c);
}
if (quote_string)
for (; *quote_string; quote_string++)
STORE (*quote_string);
if (len < buffersize)
buffer[len] = '\0';
return len;
use_shell_always_quoting_style:
return quotearg_buffer_restyled (buffer, buffersize, arg, argsize,
shell_always_quoting_style, o);
}
/* Place into buffer BUFFER (of size BUFFERSIZE) a quoted version of
argument ARG (of size ARGSIZE), using O to control quoting.
If O is null, use the default.
Terminate the output with a null character, and return the written
size of the output, not counting the terminating null.
If BUFFERSIZE is too small to store the output string, return the
value that would have been returned had BUFFERSIZE been large enough.
If ARGSIZE is -1, use the string length of the argument for ARGSIZE. */
size_t
quotearg_buffer (char *buffer, size_t buffersize,
char const *arg, size_t argsize,
struct quoting_options const *o)
{
struct quoting_options const *p = o ? o : &default_quoting_options;
return quotearg_buffer_restyled (buffer, buffersize, arg, argsize,
p->style, p);
}
/* Use storage slot N to return a quoted version of the string ARG.
OPTIONS specifies the quoting options.
The returned value points to static storage that can be
reused by the next call to this function with the same value of N.
N must be nonnegative. N is deliberately declared with type "int"
to allow for future extensions (using negative values). */
static char *
quotearg_n_options (int n, char const *arg,
struct quoting_options const *options)
{
/* Preallocate a slot 0 buffer, so that the caller can always quote
one small component of a "memory exhausted" message in slot 0. */
static char slot0[256];
static unsigned int nslots = 1;
struct slotvec
{
size_t size;
char *val;
};
static struct slotvec slotvec0 = {sizeof slot0, slot0};
static struct slotvec *slotvec = &slotvec0;
if (nslots <= n)
{
int n1 = n + 1;
size_t s = n1 * sizeof (struct slotvec);
if (! (0 < n1 && n1 == s / sizeof (struct slotvec)))
abort ();
if (slotvec == &slotvec0)
{
slotvec = (struct slotvec *) xmalloc (sizeof (struct slotvec));
*slotvec = slotvec0;
}
slotvec = (struct slotvec *) xrealloc (slotvec, s);
memset (slotvec + nslots, 0, (n1 - nslots) * sizeof (struct slotvec));
nslots = n;
}
{
size_t size = slotvec[n].size;
char *val = slotvec[n].val;
size_t qsize = quotearg_buffer (val, size, arg, (size_t) -1, options);
if (size <= qsize)
{
slotvec[n].size = size = qsize + 1;
slotvec[n].val = val = xrealloc (val == slot0 ? 0 : val, size);
quotearg_buffer (val, size, arg, (size_t) -1, options);
}
return val;
}
}
char *
quotearg_n (unsigned int n, char const *arg)
{
return quotearg_n_options (n, arg, &default_quoting_options);
}
char *
quotearg (char const *arg)
{
return quotearg_n (0, arg);
}
char *
quotearg_n_style (unsigned int n, enum quoting_style s, char const *arg)
{
struct quoting_options o;
o.style = s;
memset (o.quote_these_too, 0, sizeof o.quote_these_too);
return quotearg_n_options (n, arg, &o);
}
char *
quotearg_style (enum quoting_style s, char const *arg)
{
return quotearg_n_style (0, s, arg);
}
char *
quotearg_char (char const *arg, char ch)
{
struct quoting_options options;
options = default_quoting_options;
set_char_quoting (&options, ch, 1);
return quotearg_n_options (0, arg, &options);
}
char *
quotearg_colon (char const *arg)
{
return quotearg_char (arg, ':');
}

110
gnu/usr.bin/grep/quotearg.h
View file

@ -1,110 +0,0 @@
/* quotearg.h - quote arguments for output
Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Paul Eggert <eggert@twinsun.com> */
/* Basic quoting styles. */
enum quoting_style
{
literal_quoting_style, /* --quoting-style=literal */
shell_quoting_style, /* --quoting-style=shell */
shell_always_quoting_style, /* --quoting-style=shell-always */
c_quoting_style, /* --quoting-style=c */
escape_quoting_style, /* --quoting-style=escape */
locale_quoting_style, /* --quoting-style=locale */
clocale_quoting_style /* --quoting-style=clocale */
};
/* For now, --quoting-style=literal is the default, but this may change. */
#ifndef DEFAULT_QUOTING_STYLE
# define DEFAULT_QUOTING_STYLE literal_quoting_style
#endif
/* Names of quoting styles and their corresponding values. */
extern char const *const quoting_style_args[];
extern enum quoting_style const quoting_style_vals[];
struct quoting_options;
#ifndef PARAMS
# if defined PROTOTYPES || defined __STDC__
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
#endif
/* The functions listed below set and use a hidden variable
that contains the default quoting style options. */
/* Allocate a new set of quoting options, with contents initially identical
to O if O is not null, or to the default if O is null.
It is the caller's responsibility to free the result. */
struct quoting_options *clone_quoting_options
PARAMS ((struct quoting_options *o));
/* Get the value of O's quoting style. If O is null, use the default. */
enum quoting_style get_quoting_style PARAMS ((struct quoting_options *o));
/* In O (or in the default if O is null),
set the value of the quoting style to S. */
void set_quoting_style PARAMS ((struct quoting_options *o,
enum quoting_style s));
/* In O (or in the default if O is null),
set the value of the quoting options for character C to I.
Return the old value. Currently, the only values defined for I are
0 (the default) and 1 (which means to quote the character even if
it would not otherwise be quoted). */
int set_char_quoting PARAMS ((struct quoting_options *o, char c, int i));
/* Place into buffer BUFFER (of size BUFFERSIZE) a quoted version of
argument ARG (of size ARGSIZE), using O to control quoting.
If O is null, use the default.
Terminate the output with a null character, and return the written
size of the output, not counting the terminating null.
If BUFFERSIZE is too small to store the output string, return the
value that would have been returned had BUFFERSIZE been large enough.
If ARGSIZE is -1, use the string length of the argument for ARGSIZE. */
size_t quotearg_buffer PARAMS ((char *buffer, size_t buffersize,
char const *arg, size_t argsize,
struct quoting_options const *o));
/* Use storage slot N to return a quoted version of the string ARG.
Use the default quoting options.
The returned value points to static storage that can be
reused by the next call to this function with the same value of N.
N must be nonnegative. */
char *quotearg_n PARAMS ((unsigned int n, char const *arg));
/* Equivalent to quotearg_n (0, ARG). */
char *quotearg PARAMS ((char const *arg));
/* Use style S and storage slot N to return a quoted version of the string ARG.
This is like quotearg_n (N, ARG), except that it uses S with no other
options to specify the quoting method. */
char *quotearg_n_style PARAMS ((unsigned int n, enum quoting_style s,
char const *arg));
/* Equivalent to quotearg_n_style (0, S, ARG). */
char *quotearg_style PARAMS ((enum quoting_style s, char const *arg));
/* Like quotearg (ARG), except also quote any instances of CH. */
char *quotearg_char PARAMS ((char const *arg, char ch));
/* Equivalent to quotearg_char (ARG, ':'). */
char *quotearg_colon PARAMS ((char const *arg));

183
gnu/usr.bin/grep/savedir.c
View file

@ -1,183 +0,0 @@
/* savedir.c -- save the list of files in a directory in a string
Copyright (C) 1990, 1997, 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by David MacKenzie <djm@gnu.ai.mit.edu>. */
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#if HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#if HAVE_UNISTD_H
# include <unistd.h>
#endif
#if HAVE_DIRENT_H
# include <dirent.h>
# define NAMLEN(dirent) strlen((dirent)->d_name)
#else
# define dirent direct
# define NAMLEN(dirent) (dirent)->d_namlen
# if HAVE_SYS_NDIR_H
# include <sys/ndir.h>
# endif
# if HAVE_SYS_DIR_H
# include <sys/dir.h>
# endif
# if HAVE_NDIR_H
# include <ndir.h>
# endif
#endif
#ifdef CLOSEDIR_VOID
/* Fake a return value. */
# define CLOSEDIR(d) (closedir (d), 0)
#else
# define CLOSEDIR(d) closedir (d)
#endif
#ifdef STDC_HEADERS
# include <stdlib.h>
# include <string.h>
#else
char *malloc ();
char *realloc ();
#endif
#ifndef NULL
# define NULL 0
#endif
#ifndef stpcpy
char *stpcpy ();
#endif
#include <fnmatch.h>
#include "savedir.h"
#include "system.h"
char *path;
size_t pathlen;
static int
isdir1 (const char *dir, const char *file)
{
int status;
int slash;
size_t dirlen = strlen (dir);
size_t filelen = strlen (file);
if ((dirlen + filelen + 2) > pathlen)
{
path = calloc (dirlen + 1 + filelen + 1, sizeof (*path));
pathlen = dirlen + filelen + 2;
}
strcpy (path, dir);
slash = (path[dirlen] != '/');
path[dirlen] = '/';
strcpy (path + dirlen + slash , file);
status = isdir (path);
return status;
}
/* Return a freshly allocated string containing the filenames
in directory DIR, separated by '\0' characters;
the end is marked by two '\0' characters in a row.
NAME_SIZE is the number of bytes to initially allocate
for the string; it will be enlarged as needed.
Return NULL if DIR cannot be opened or if out of memory. */
char *
savedir (const char *dir, off_t name_size, struct exclude *included_patterns,
struct exclude *excluded_patterns)
{
DIR *dirp;
struct dirent *dp;
char *name_space;
char *namep;
dirp = opendir (dir);
if (dirp == NULL)
return NULL;
/* Be sure name_size is at least `1' so there's room for
the final NUL byte. */
if (name_size <= 0)
name_size = 1;
name_space = (char *) malloc (name_size);
if (name_space == NULL)
{
closedir (dirp);
return NULL;
}
namep = name_space;
while ((dp = readdir (dirp)) != NULL)
{
/* Skip "." and ".." (some NFS filesystems' directories lack them). */
if (dp->d_name[0] != '.'
|| (dp->d_name[1] != '\0'
&& (dp->d_name[1] != '.' || dp->d_name[2] != '\0')))
{
off_t size_needed = (namep - name_space) + NAMLEN (dp) + 2;
if ((included_patterns || excluded_patterns)
&& !isdir1 (dir, dp->d_name))
{
if (included_patterns
&& !excluded_filename (included_patterns, path, 0))
continue;
if (excluded_patterns
&& excluded_filename (excluded_patterns, path, 0))
continue;
}
if (size_needed > name_size)
{
char *new_name_space;
while (size_needed > name_size)
name_size += 1024;
new_name_space = realloc (name_space, name_size);
if (new_name_space == NULL)
{
closedir (dirp);
return NULL;
}
namep += new_name_space - name_space;
name_space = new_name_space;
}
namep = stpcpy (namep, dp->d_name) + 1;
}
}
*namep = '\0';
if (CLOSEDIR (dirp))
{
free (name_space);
return NULL;
}
if (path)
{
free (path);
path = NULL;
pathlen = 0;
}
return name_space;
}

18
gnu/usr.bin/grep/savedir.h
View file

@ -1,18 +0,0 @@
#if !defined SAVEDIR_H_
# define SAVEDIR_H_
#include "exclude.h"
# ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
# endif
extern char *
savedir PARAMS ((const char *dir, off_t name_size,
struct exclude *, struct exclude *));
#endif

1303
gnu/usr.bin/grep/search.c
View file

File diff suppressed because it is too large Load diff

206
gnu/usr.bin/grep/system.h
View file

@ -1,206 +0,0 @@
/* Portability cruft. Include after config.h and sys/types.h.
Copyright 1996, 1998, 1999, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
02111-1307, USA. */
#undef PARAMS
#if defined (__STDC__) && __STDC__
# ifndef _PTR_T
# define _PTR_T
typedef void * ptr_t;
# endif
# define PARAMS(x) x
#else
# ifndef _PTR_T
# define _PTR_T
typedef char * ptr_t;
# endif
# define PARAMS(x) ()
#endif
#ifdef HAVE_UNISTD_H
# include <fcntl.h>
# include <unistd.h>
#else
# define O_RDONLY 0
# define SEEK_SET 0
# define SEEK_CUR 1
int open(), read(), close();
#endif
#include <errno.h>
#ifndef errno
extern int errno;
#endif
#ifndef HAVE_STRERROR
extern int sys_nerr;
extern char *sys_errlist[];
# define strerror(E) (0 <= (E) && (E) < sys_nerr ? _(sys_errlist[E]) : _("Unknown system error"))
#endif
/* Some operating systems treat text and binary files differently. */
#ifdef __BEOS__
# undef O_BINARY /* BeOS 5 has O_BINARY and O_TEXT, but they have no effect. */
#endif
#ifdef HAVE_DOS_FILE_CONTENTS
# include <io.h>
# ifdef HAVE_SETMODE
# define SET_BINARY(fd) setmode (fd, O_BINARY)
# else
# define SET_BINARY(fd) _setmode (fd, O_BINARY)
# endif
#endif
#ifdef HAVE_DOS_FILE_NAMES
# define IS_SLASH(c) ((c) == '/' || (c) == '\\')
# define FILESYSTEM_PREFIX_LEN(f) ((f)[0] && (f)[1] == ':' ? 2 : 0)
#endif
#ifndef IS_SLASH
# define IS_SLASH(c) ((c) == '/')
#endif
#ifndef FILESYSTEM_PREFIX_LEN
# define FILESYSTEM_PREFIX_LEN(f) 0
#endif
int isdir PARAMS ((char const *));
#ifdef HAVE_DIR_EACCES_BUG
# ifdef EISDIR
# define is_EISDIR(e, f) \
((e) == EISDIR \
|| ((e) == EACCES && isdir (f) && ((e) = EISDIR, 1)))
# else
# define is_EISDIR(e, f) ((e) == EACCES && isdir (f))
# endif
#endif
#ifndef is_EISDIR
# ifdef EISDIR
# define is_EISDIR(e, f) ((e) == EISDIR)
# else
# define is_EISDIR(e, f) 0
# endif
#endif
#if STAT_MACROS_BROKEN
# undef S_ISDIR
# undef S_ISREG
#endif
#if !defined(S_ISDIR) && defined(S_IFDIR)
# define S_ISDIR(Mode) (((Mode) & S_IFMT) == S_IFDIR)
#endif
#if !defined(S_ISREG) && defined(S_IFREG)
# define S_ISREG(Mode) (((Mode) & S_IFMT) == S_IFREG)
#endif
#ifdef STDC_HEADERS
# include <stdlib.h>
#else
char *getenv ();
ptr_t malloc(), realloc(), calloc();
void free();
#endif
#if __STDC__
# include <stddef.h>
#endif
#ifdef STDC_HEADERS
# include <limits.h>
#endif
#ifndef CHAR_BIT
# define CHAR_BIT 8
#endif
/* The extra casts work around common compiler bugs. */
#define TYPE_SIGNED(t) (! ((t) 0 < (t) -1))
#define TYPE_MINIMUM(t) ((t) (TYPE_SIGNED (t) \
? ~ (t) 0 << (sizeof (t) * CHAR_BIT - 1) \
: (t) 0))
#define TYPE_MAXIMUM(t) ((t) (~ (t) 0 - TYPE_MINIMUM (t)))
#ifndef CHAR_MAX
# define CHAR_MAX TYPE_MAXIMUM (char)
#endif
#ifndef INT_MAX
# define INT_MAX TYPE_MAXIMUM (int)
#endif
#ifndef UCHAR_MAX
# define UCHAR_MAX TYPE_MAXIMUM (unsigned char)
#endif
#if !defined(STDC_HEADERS) && defined(HAVE_STRING_H) && defined(HAVE_MEMORY_H)
# include <memory.h>
#endif
#if defined(STDC_HEADERS) || defined(HAVE_STRING_H)
# include <string.h>
#else
# include <strings.h>
# undef strchr
# define strchr index
# undef strrchr
# define strrchr rindex
# undef memcpy
# define memcpy(d, s, n) bcopy (s, d, n)
#endif
#ifndef HAVE_MEMCHR
ptr_t memchr();
#endif
#if ! defined HAVE_MEMMOVE && ! defined memmove
# define memmove(d, s, n) bcopy (s, d, n)
#endif
#include <ctype.h>
#ifndef isgraph
# define isgraph(C) (isprint(C) && !isspace(C))
#endif
#if defined (STDC_HEADERS) || (!defined (isascii) && !defined (HAVE_ISASCII))
# define IN_CTYPE_DOMAIN(c) 1
#else
# define IN_CTYPE_DOMAIN(c) isascii(c)
#endif
#define ISALPHA(C) (IN_CTYPE_DOMAIN (C) && isalpha (C))
#define ISUPPER(C) (IN_CTYPE_DOMAIN (C) && isupper (C))
#define ISLOWER(C) (IN_CTYPE_DOMAIN (C) && islower (C))
#define ISDIGIT(C) (IN_CTYPE_DOMAIN (C) && isdigit (C))
#define ISXDIGIT(C) (IN_CTYPE_DOMAIN (C) && isxdigit (C))
#define ISSPACE(C) (IN_CTYPE_DOMAIN (C) && isspace (C))
#define ISPUNCT(C) (IN_CTYPE_DOMAIN (C) && ispunct (C))
#define ISALNUM(C) (IN_CTYPE_DOMAIN (C) && isalnum (C))
#define ISPRINT(C) (IN_CTYPE_DOMAIN (C) && isprint (C))
#define ISGRAPH(C) (IN_CTYPE_DOMAIN (C) && isgraph (C))
#define ISCNTRL(C) (IN_CTYPE_DOMAIN (C) && iscntrl (C))
#define TOLOWER(C) (ISUPPER(C) ? tolower(C) : (C))
#if ENABLE_NLS
# include <libintl.h>
# define _(String) gettext (String)
#else
# define _(String) String
#endif
#define N_(String) String
#if HAVE_SETLOCALE
# include <locale.h>
#endif
#ifndef initialize_main
#define initialize_main(argcp, argvp)
#endif

38
gnu/usr.bin/grep/tests/backref.sh
View file

@ -1,38 +0,0 @@
#!/bin/sh
# Test that backrefs are local to regex.
#
#
: ${srcdir=.}
failures=0
# checking for a palindrome
echo "radar" | ${GREP} -e '\(.\)\(.\).\2\1' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "backref: palindrome, test \#1 failed"
failures=1
fi
# hit hard with the `Bond' tests
echo "civic" | ${GREP} -E -e '^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?).?\9\8\7\6\5\4\3\2\1$' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Options: Bond, test \#2 failed"
failures=1
fi
# backref are local should be error
echo "123" | ${GREP} -e 'a\(.\)' -e 'b\1' > /dev/null 2>&1
if test $? -ne 2 ; then
echo "Options: Backref not local, test \#3 failed"
failures=1
fi
# Pattern should faile
echo "123" | ${GREP} -e '[' -e ']' > /dev/null 2>&1
if test $? -ne 2 ; then
echo "Options: Compiled not local, test \#3 failed"
failures=1
fi
exit $failures

27
gnu/usr.bin/grep/tests/bre.awk
View file

@ -1,27 +0,0 @@
BEGIN {
FS="@";
n = 0;
printf ("# Generated Spencer BRE Test\n");
printf ("failures=0\n");
}
$0 ~ /^#/ { next; }
NF == 3 {
# printf ("status=`echo '%s' | { ${GREP} -e '%s' > /dev/null 2>&1; echo $?; cat >/dev/null; }`\n",$3, $2);
printf ("status=`echo '%s' | { ${GREP} -e '%s' > /dev/null 2>&1; echo $? ; }`\n",$3, $2);
printf ("if test $status -ne %s ; then\n", $1);
printf ("\techo Spencer bre test \\#%d failed\n", ++n);
printf ("\tfailures=1\n");
printf ("fi\n");
}
NF == 4 {
#don't alarm users
# printf ("echo '%s' | ${GREP} -e '%s' > /dev/null 2>&1\n",$3, $2);
# printf ("if test $? -ne %s ; then\n", $1);
# printf ("\techo Expected non conformance \\#%d ... continuing\n", ++n);
# printf ("fi\n");
}
END { printf ("exit $failures\n"); }

13
gnu/usr.bin/grep/tests/bre.sh
View file

@ -1,13 +0,0 @@
#!/bin/sh
# Regression test for GNU grep.
: ${srcdir=.}
failures=0
# . . . and the following by Henry Spencer.
${AWK-awk} -f $srcdir/bre.awk $srcdir/bre.tests > bre.script
sh bre.script && exit $failures
exit 1

62
gnu/usr.bin/grep/tests/bre.tests
View file

@ -1,62 +0,0 @@
0@a\(b\)c@abc
0@a(@a(
2@a\(@EPAREN
2@a\(b@EPAREN
0@a(b@a(b
0@a)@a)
2@a\)@EPAREN
2@\)@EPAREN
0@a\(\)b@ab
0@a^b@a^b@TO CORRECT
0@a$b@a$b
0@\($\)\(^\)@@
0@a*\(^b$\)c*@b
0@|@|
0@*@*
0@\(\)@abc
2@\(\{1\}a\)@BADRPT@TO CORRECT
0@^*@*
2@^\{1\}@BADRPT@TO CORRECT
0@{@{
1@a\(b*\)c\1d@abbcbd
1@a\(b*\)c\1d@abbcbbbd
1@^\(.\)\1@abc
0@a\(\([bc]\)\2\)*d@abbccd
1@a\(\([bc]\)\2\)*d@abbcbd
0@a\(\(b\)*\2\)*d@abbbd
0@\(a\)\1bcd@aabcd
0@\(a\)\1bc*d@aabcd
0@\(a\)\1bc*d@aabd
0@\(a\)\1bc*d@aabcccd
0@\(a\)\1bc*[ce]d@aabcccd@TO CORRECT
0@^\(a\)\1b\(c\)*cd$@aabcccd
0@a\(*\)b@a*b
0@a\(**\)b@ab
2@a\(***\)b@BADRPT@TO CORRECT
0@*a@*a
0@**a@a
2@***a@BADRPT@TO CORRECT
0@a\{1\}b@ab
0@a\{1,\}b@ab
0@a\{1,2\}b@aab
2@a\{1@EBRACE
2@a\{1a@EBRACE
2@a\{1a\}@BADBR
2@a\{,2\}@BADBR
2@a\{,\}@BADBR
2@a\{1,x\}@BADBR
2@a\{1,x@EBRACE
2@a\{32768\}@BADBR
2@a\{1,0\}@BADBR
0@ab\{0,0\}c@abcac
0@ab\{0,1\}c@abcac
0@ab\{0,3\}c@abbcac
0@ab\{1,1\}c@acabc
0@ab\{1,3\}c@acabc
0@ab\{2,2\}c@abcabbc
0@ab\{2,4\}c@abcabbc
2@a\{1\}\{1\}@BADRPT@TO CORRECT
2@a*\{1\}@BADRPT@TO CORRECT
2@a\{1\}*@BADRPT@TO CORRECT
1@a\(b\)?c\1d@acd
0@-\{0,1\}[0-9]*$@-5

33
gnu/usr.bin/grep/tests/empty.sh
View file

@ -1,33 +0,0 @@
#!/bin/sh
# test that the empty file means no pattern
# and an empty pattern means match all.
: ${srcdir=.}
failures=0
for options in '-E' '-E -w' '-F -x' '-G -w -x'; do
# should return 0 found a match
echo "" | ${GREP} $options -e '' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Status: Wrong status code, test \#1 failed ($options)"
failures=1
fi
# should return 1 found no match
echo "abcd" | ${GREP} $options -f /dev/null > /dev/null 2>&1
if test $? -ne 1 ; then
echo "Status: Wrong status code, test \#2 failed ($options)"
failures=1
fi
# should return 0 found a match
echo "abcd" | ${GREP} $options -f /dev/null -e "abcd" > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Status: Wrong status code, test \#3 failed ($options)"
failures=1
fi
done
exit $failures

32
gnu/usr.bin/grep/tests/ere.awk
View file

@ -1,32 +0,0 @@
BEGIN {
FS="@";
n = 0;
printf ("# Generated Spencer ERE Test\n");
printf ("failures=0\n");
}
$0 ~ /^#/ { next; }
NF == 3 {
# printf ("status=`echo '%s' | { ${GREP} -E -e '%s' > /dev/null 2>&1; echo $?; cat >/dev/null; }`\n",$3, $2);
printf ("status=`echo '%s' | { ${GREP} -E -e '%s' > /dev/null 2>&1; echo $?; }`\n",$3, $2);
printf ("if test $status -ne %s ; then\n", $1);
printf ("\techo Spencer ere test \\#%d failed\n", ++n);
printf ("\tfailures=1\n");
printf ("fi\n");
}
NF == 4 {
# don't alarm the user for now
# printf ("echo '%s'|${GREP} -E -e '%s' > /dev/null 2>&1\n",$3, $2);
# printf ("if test $? -ne %s ; then\n", $1);
# printf ("\techo Expected non conformance \\#%d ... continuing\n", ++n);
# printf ("fi\n");
}
NF == 5 {
# don't alarm the user for now
next;
}
END { printf ("exit $failures\n"); }

13
gnu/usr.bin/grep/tests/ere.sh
View file

@ -1,13 +0,0 @@
#!/bin/sh
# Regression test for GNU grep.
: ${srcdir=.}
failures=0
# . . . and the following by Henry Spencer.
${AWK-awk} -f $srcdir/ere.awk $srcdir/ere.tests > ere.script
sh ere.script && exit $failures
exit 1

215
gnu/usr.bin/grep/tests/ere.tests
View file

@ -1,215 +0,0 @@
0@a@a
0@abc@abc
0@abc|de@abc
0@a|b|c@abc
0@a(b)c@abc
2@a(@EPAREN
0@a\(@a(
2@a(b@EPAREN
0@a)@a)@POSIX BOTCH
0@)@)@POSIX BOTCH
0@a()b@ab
0@^abc$@abc
1@a^b@a^b
1@a$b@a$b
0@^@abc
0@$@abc
0@^$@@
0@$^@@
0@^^@@
0@$$@@
0@a*(^b$)c*@b
2@|@EMPTY@NO ALTERNATION
2@*@BADRPT@TO CORRECT
2@+@BADRPT@TO CORRECT
2@?@BADRPT@TO CORRECT
1@&C@PASS
0@()@abc
2@a||b@EMPTY@NO ALTERNATION
2@|ab@EMPTY@NO ALTERNATION
2@ab|@EMPTY@NO ALTERNATION
2@(|a)b@EMPTY@NO ALTERNATION
2@(a|)b@EMPTY@NO ALTERNATION
2@(*a)@BADRPT@TO CORRECT
2@(+a)@BADRPT@TO CORRECT
2@(?a)@BADRPT@TO CORRECT
2@({1}a)@BADRPT@TO CORRECT
2@(a|*b)@BADRPT@NO ALTERNATION
2@(a|+b)@BADRPT@NO ALTERNATION
2@(a|?b)@BADRPT@NO ALTERNATION
2@(a|{1}b)@BADRPT@NO ALTERNATION
2@^*@BADRPT@TO CORRECT
2@^+@BADRPT@TO CORRECT
2@^?@BADRPT@TO CORRECT
2@^{1}@BADRPT@TO CORRECT
0@a.c@abc
0@a[bc]d@abd
0@a\*c@a*c
0@a\\b@a\b@TO CORRECT
0@a\\\*b@a\*b@SHELL TROUBLE
0@a\bc@abc@TO CORRECT
2@a\@EESCAPE@SHELL TROUBLE
0@a\\bc@a\bc@TO CORRECT
0@a\[b@a[b
2@a[b@EBRACK
0@a$@a
1@a$@a$
1@a\$@a@SHELL TROUBLE
0@a\$@a$@SHELL TROUBLE
1@a\\$@a
1@a\\$@a$@SHELL TROUBLE
1@a\\$@a\$@SHELL TROUBLE
0@a\\$@a\@SHEL TROUBLE
0@ab*c@abc
0@ab+c@abc
0@ab?c@abc
0@{@{@TO CORRECT
0@{abc@{abc@TO CORRECT
0@{1@{1
2@{1}@BADRPT@TO CORRECT
0@a{b@a{b@TO CORRECT
0@a{1}b@ab
0@a{1,}b@ab
0@a{1,2}b@aab
0@a{1@a{1
1@a{1a@aa
0@a{1a}@a{1a}
0@a{,2}@a{,2}
0@a{,}@a{,}
0@a{1,*}@a{1,,,}
2@a{1,x@EBRACE@TO CORRECT
2@a{300}@BADBR@TO CORRECT
2@a{1,0}@BADBR@TO CORRECT
0@ab{0,0}c@abcac
0@ab{0,1}c@abcac
0@ab{0,3}c@abbcac
0@ab{1,1}c@acabc
0@ab{1,3}c@acabc
0@ab{2,2}c@abcabbc
0@ab{2,4}c@abcabbc
2@a**@BADRPT@TO CORRECT
2@a++@BADRPT@TO CORRECT
2@a??@BADRPT@TO CORRECT
2@a*+@BADRPT@TO CORRECT
2@a*?@BADRPT@TO CORRECT
2@a+*@BADRPT@TO CORRECT
2@a+?@BADRPT@TO CORRECT
2@a?*@BADRPT@TO CORRECT
2@a?+@BADRPT@TO CORRECT
2@a{1}{1}@BADRPT@TO CORRECT
2@a*{1}@BADRPT@TO CORRECT
2@a+{1}@BADRPT@TO CORRECT
2@a?{1}@BADRPT@TO CORRECT
2@a{1}*@BADRPT@TO CORRECT
2@a{1}+@BADRPT@TO CORRECT
2@a{1}?@BADRPT@TO CORRECT
0@a*{b}@a{b}@TO CORRECT
0@a[b]c@abc
0@a[ab]c@abc
0@a[^ab]c@adc
0@a[]b]c@a]c
0@a[[b]c@a[c
0@a[-b]c@a-c
0@a[^]b]c@adc
0@a[^-b]c@adc
0@a[b-]c@a-c
2@a[b@EBRACK
2@a[]@EBRACK
0@a[1-3]c@a2c
2@a[3-1]c@ERANGE@TO CORRECT
2@a[1-3-5]c@ERANGE@TO CORRECT
0@a[[.-.]--]c@a-c@TO CORRECT
2@a[1-@ERANGE
2@a[[.@EBRACK
2@a[[.x@EBRACK
2@a[[.x.@EBRACK
2@a[[.x.]@EBRACK@TO CORRECT
0@a[[.x.]]@ax@TO CORRECT
2@a[[.x,.]]@ECOLLATE@TO CORRECT
0@a[[.one.]]b@a1b@TO CORRECT
2@a[[.notdef.]]b@ECOLLATE@TO CORRECT
0@a[[.].]]b@a]b@TO CORRECT
0@a[[:alpha:]]c@abc
2@a[[:notdef:]]c@ECTYPE
2@a[[:@EBRACK
2@a[[:alpha@EBRACK
2@a[[:alpha:]@EBRACK
2@a[[:alpha,:]@ECTYPE
2@a[[:]:]]b@ECTYPE
2@a[[:-:]]b@ECTYPE
2@a[[:alph:]]@ECTYPE
2@a[[:alphabet:]]@ECTYPE
0@[[:digit:]]+@a019b
0@[[:lower:]]+@AabC
0@[[:upper:]]+@aBCd
0@[[:xdigit:]]+@p0f3Cq
0@a[[=b=]]c@abc@TO CORRECT
2@a[[=@EBRACK
2@a[[=b@EBRACK
2@a[[=b=@EBRACK
2@a[[=b=]@EBRACK@TO CORRECT
2@a[[=b,=]]@ECOLLATE@TO CORRECT
0@a[[=one=]]b@a1b@TO CORRECT
0@a(((b)))c@abc
0@a(b|(c))d@abd
0@a(b*|c)d@abbd
0@a[ab]{20}@aaaaabaaaabaaaabaaaab
0@a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab]@aaaaabaaaabaaaabaaaab
0@a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab](wee|week)(knights|night)@aaaaabaaaabaaaabaaaabweeknights
0@12345678901234567890123456789@a12345678901234567890123456789b
0@123456789012345678901234567890@a123456789012345678901234567890b
0@1234567890123456789012345678901@a1234567890123456789012345678901b
0@12345678901234567890123456789012@a12345678901234567890123456789012b
0@123456789012345678901234567890123@a123456789012345678901234567890123b
0@1234567890123456789012345678901234567890123456789012345678901234567890@a1234567890123456789012345678901234567890123456789012345678901234567890b
0@[ab][cd][ef][gh][ij][kl][mn]@xacegikmoq
0@[ab][cd][ef][gh][ij][kl][mn][op]@xacegikmoq
0@[ab][cd][ef][gh][ij][kl][mn][op][qr]@xacegikmoqy
0@[ab][cd][ef][gh][ij][kl][mn][op][q]@xacegikmoqy
0@abc@xabcy
0@aBc@Abc@TO CORRECT
0@a[Bc]*d@abBCcd@TO CORRECT
0@0[[:upper:]]1@0a1@TO CORRECT
0@0[[:lower:]]1@0A1@TO CORRECT
1@a[^b]c@abc
1@a[^b]c@aBc@TO CORRECT
0@a[^b]c@adc
0@[a]b[c]@abc
0@[a]b[a]@aba
0@[abc]b[abc]@abc
0@[abc]b[abd]@abd
0@a(b?c)+d@accd
0@(wee|week)(knights|night)@weeknights
0@(we|wee|week|frob)(knights|night|day)@weeknights
0@a[bc]d@xyzaaabcaababdacd
0@a[ab]c@aaabc
0@a*@b
0@/\*.*\*/@/*x*/
0@/\*.*\*/@/*x*/y/*z*/
0@/\*([^*]|\*[^/])*\*/@/*x*/
0@/\*([^*]|\*[^/])*\*/@/*x*/y/*z*/
0@/\*([^*]|\*[^/])*\*/@/*x**/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x*/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x**/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x****/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x**x*/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x***x/y/*z*/
0@aZb@a@TO CORRECT
0@[[:<:]]a@a@TO CORRECT
1@[[:<:]]a@ba@TO CORRECT
0@[[:<:]]a@-a@TO CORRECT
0@a[[:>:]]@a@TO CORRECT
1@a[[:>:]]@ab@TO CORRECT
0@a[[:>:]]@a-@TO CORRECT
0@[[:<:]]a.c[[:>:]]@axcd-dayc-dazce-abc@TO CORRECT
0@[[:<:]]a.c[[:>:]]@axcd-dayc-dazce-abc-q@TO CORRECT
0@[[:<:]]a.c[[:>:]]@axc-dayc-dazce-abc@TO CORRECT
0@[[:<:]]b.c[[:>:]]@a_bxc-byc_d-bzc-q@TO CORRECT
0@[[:<:]].x..[[:>:]]@y_xa_-_xb_y-_xc_-axdc@TO CORRECT
1@[[:<:]]a_b[[:>:]]@x_a_b@TO CORRECT
0@(A[1])|(A[2])|(A[3])|(A[4])|(A[5])|(A[6])|(A[7])|(A[8])|(A[9])|(A[A])@A1
0@abcdefghijklmnop@abcdefghijklmnop
0@abcdefghijklmnopqrstuv@abcdefghijklmnopqrstuv
0@CC[13]1|a{21}[23][EO][123][Es][12]a{15}aa[34][EW]aaaaaaa[X]a@CC11
0@a?b@ab

59
gnu/usr.bin/grep/tests/file.sh
View file

@ -1,59 +0,0 @@
#!/bin/sh
# Test for POSIX.2 options for grep
#
# grep -E -f pattern_file file
# grep -F -f pattern_file file
# grep -G -f pattern_file file
#
: ${srcdir=.}
failures=0
cat <<EOF >patfile
radar
MILES
GNU
EOF
# match
echo "miles" | ${GREP} -i -E -f patfile > /dev/null 2>&1
if test $? -ne 0 ; then
echo "File_pattern: Wrong status code, test \#1 failed"
failures=1
fi
# match
echo "GNU" | ${GREP} -G -f patfile > /dev/null 2>&1
if test $? -ne 0 ; then
echo "File_pattern: Wrong status code, test \#2 failed"
failures=1
fi
# checking for no match
echo "ridar" | ${GREP} -F -f patfile > /dev/null 2>&1
if test $? -ne 1 ; then
echo "File_pattern: Wrong status code, test \#3 failed"
failures=1
fi
cat <<EOF >patfile
EOF
# empty pattern : every match
echo "abbcd" | ${GREP} -F -f patfile > /dev/null 2>&1
if test $? -ne 0 ; then
echo "File_pattern: Wrong status code, test \#4 failed"
failures=1
fi
cp /dev/null patfile
# null pattern : no match
echo "abbcd" | ${GREP} -F -f patfile > /dev/null 2>&1
if test $? -ne 1 ; then
echo "File_pattern: Wrong status code, test \#5 failed"
failures=1
fi
exit $failures

55
gnu/usr.bin/grep/tests/formatbre.awk
View file

@ -1,55 +0,0 @@
#
# Basic Regular Expression
# kip comments
$0 ~ /^#/ { next; }
# skip those option specific to regexec/regcomp
$2 ~ /[msnr$#p^]/ { next; }
# skip empty lines
$0 ~ /^$/ { next; }
# debug
#{ printf ("<%s> <%s> <%s> <%s>\n", $1, $2, $3, $4); }
# subreg expresion
NF >= 5 { next; }
# errors
NF == 3 {
# gsub (/@/, ",");
# it means empty lines
gsub (/\"\"/, "");
# escapes
gsub (/\\\'/, "\\\'\'");
# error in regex
if (index ($2, "C") != 0)
{
if (index ($2, "b") != 0)
printf ("2@%s@%s\n", $1, $3);
}
# erro no match
else
{
if (index ($2, "b") != 0)
printf ("1@%s@%s\n", $1, $3);
}
next;
}
# ok
NF == 4 {
# skip those magic cookies can't rely on echo to gnerate them
if (match($3, /[NSTZ]/))
next;
# gsub (/@/, ",");
# it means empty lines
gsub (/\"\"/, "");
# escape escapes
gsub (/\\\'/, "\\\'\'");
if (index ($2, "b") != 0)
printf ("0@%s@%s\n", $1, $3);
}

60
gnu/usr.bin/grep/tests/formatere.awk
View file

@ -1,60 +0,0 @@
#
# Extended Regular Expression
# skip comments
$0 ~ /^#/ { next; }
# skip specifics to regcomp/regexec
$2 ~ /[msnr$#p^]/ { next; }
# jump empty lines
$0 ~ /^$/ { next; }
# subreg skip
NF >= 5 { next; }
# debug
#{ printf ("<%s> <%s> <%s> <%s>\n", $1, $2, $3, $4); }
# errors
NF == 3 {
# nuke any remaining '@'
# gsub (/@/, ",");
# it means empty lines
gsub (/\"\"/, "");
# escapes
gsub (/\\\'/, "\\\'\'");
# error in regex
if (index ($2, "C") != 0)
{
if (index ($2, "b") == 0)
printf ("2@%s@%s\n", $1, $3);
}
# error not matching
else
{
if (index ($2, "b") == 0)
printf ("1@%s@%s\n", $1, $3);
}
next;
}
# ok
NF == 4 {
# skip those magic cookies can't rely on echo to gnerate them
if (match($3, /[NSTZ]/))
next;
# nuke any remaining '@'
# gsub (/@/, ",");
# it means empty lines
gsub (/\"\"/, "");
# escape escapes
gsub (/\\\'/, "\\\'\'");
if (index ($2, "b") == 0)
{
printf ("0@%s@%s\n", $1, $3);
}
next;
}

32
gnu/usr.bin/grep/tests/khadafy.lines
View file

@ -1,32 +0,0 @@
1) Muammar Qaddafi
2) Mo'ammar Gadhafi
3) Muammar Kaddafi
4) Muammar Qadhafi
5) Moammar El Kadhafi
6) Muammar Gadafi
7) Mu'ammar al-Qadafi
8) Moamer El Kazzafi
9) Moamar al-Gaddafi
10) Mu'ammar Al Qathafi
11) Muammar Al Qathafi
12) Mo'ammar el-Gadhafi
13) Moamar El Kadhafi
14) Muammar al-Qadhafi
15) Mu'ammar al-Qadhdhafi
16) Mu'ammar Qadafi
17) Moamar Gaddafi
18) Mu'ammar Qadhdhafi
19) Muammar Khaddafi
20) Muammar al-Khaddafi
21) Mu'amar al-Kadafi
22) Muammar Ghaddafy
23) Muammar Ghadafi
24) Muammar Ghaddafi
25) Muamar Kaddafi
26) Muammar Quathafi
27) Muammar Gheddafi
28) Muamar Al-Kaddafi
29) Moammar Khadafy
30) Moammar Qudhafi
31) Mu'ammar al-Qaddafi
32) Mulazim Awwal Mu'ammar Muhammad Abu Minyar al-Qadhafi

1
gnu/usr.bin/grep/tests/khadafy.regexp
View file

@ -1 +0,0 @@
M[ou]'?am+[ae]r .*([AEae]l[- ])?[GKQ]h?[aeu]+([dtz][dhz]?)+af[iy]

20
gnu/usr.bin/grep/tests/khadafy.sh
View file

@ -1,20 +0,0 @@
#!/bin/sh
# Regression test for GNU grep.
: ${srcdir=.}
: ${GREP=../src/grep}
failures=0
# The Khadafy test is brought to you by Scott Anderson . . .
${GREP} -E -f $srcdir/khadafy.regexp $srcdir/khadafy.lines > khadafy.out
if cmp $srcdir/khadafy.lines khadafy.out
then
:
else
echo Khadafy test failed -- output left on khadafy.out
failures=1
fi
exit $failures

36
gnu/usr.bin/grep/tests/options.sh
View file

@ -1,36 +0,0 @@
#!/bin/sh
# Test for POSIX.2 options for grep
#
# grep [ -E| -F][ -c| -l| -q ][-insvx] -e pattern_list
# [-f pattern_file] ... [file. ..]
# grep [ -E| -F][ -c| -l| -q ][-insvx][-e pattern_list]
# -f pattern_file ... [file ...]
# grep [ -E| -F][ -c| -l| -q ][-insvx] pattern_list [file...]
#
: ${srcdir=.}
failures=0
# checking for -E extended regex
echo "abababccccccd" | ${GREP} -E -e 'c{3}' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Options: Wrong status code, test \#1 failed"
failures=1
fi
# checking for basic regex
echo "abababccccccd" | ${GREP} -G -e 'c\{3\}' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Options: Wrong status code, test \#2 failed"
failures=1
fi
# checking for fixed string
echo "abababccccccd" | ${GREP} -F -e 'c\{3\}' > /dev/null 2>&1
if test $? -ne 1 ; then
echo "Options: Wrong status code, test \#3 failed"
failures=1
fi
exit $failures

15
gnu/usr.bin/grep/tests/spencer1.awk
View file

@ -1,15 +0,0 @@
BEGIN {
FS = "@";
printf ("failures=0\n");
}
$0 !~ /^#/ && NF = 3 {
# printf ("status=`echo '%s'| { ${GREP} -E -e '%s' > /dev/null 2>&1; echo $?; cat >/dev/null; }`\n",$3, $2);
printf ("status=`echo '%s'| { ${GREP} -E -e '%s' >/dev/null 2>&1 ; echo $?; }`\n",$3, $2);
printf ("if test $status -ne %s ; then\n", $1);
printf ("\techo Spencer test \\#%d failed\n", ++n);
printf ("\tfailures=1\n");
printf ("fi\n");
}
END { printf ("exit $failures\n"); }

13
gnu/usr.bin/grep/tests/spencer1.sh
View file

@ -1,13 +0,0 @@
#!/bin/sh
# Regression test for GNU grep.
: ${srcdir=.}
failures=0
# . . . and the following by Henry Spencer.
${AWK-awk} -f $srcdir/spencer1.awk $srcdir/spencer1.tests > spencer1.script
sh spencer1.script && exit $failures
exit 1

122
gnu/usr.bin/grep/tests/spencer1.tests
View file

@ -1,122 +0,0 @@
0@abc@abc
1@abc@xbc
1@abc@axc
1@abc@abx
0@abc@xabcy
0@abc@ababc
0@ab*c@abc
0@ab*bc@abc
0@ab*bc@abbc
0@ab*bc@abbbbc
0@ab+bc@abbc
1@ab+bc@abc
1@ab+bc@abq
0@ab+bc@abbbbc
0@ab?bc@abbc
0@ab?bc@abc
1@ab?bc@abbbbc
0@ab?c@abc
0@^abc$@abc
1@^abc$@abcc
0@^abc@abcc
1@^abc$@aabc
0@abc$@aabc
0@^@abc
0@$@abc
0@a.c@abc
0@a.c@axc
0@a.*c@axyzc
1@a.*c@axyzd
1@a[bc]d@abc
0@a[bc]d@abd
1@a[b-d]e@abd
0@a[b-d]e@ace
0@a[b-d]@aac
0@a[-b]@a-
0@a[b-]@a-
1@a[b-a]@-
2@a[]b@-
2@a[@-
0@a]@a]
0@a[]]b@a]b
0@a[^bc]d@aed
1@a[^bc]d@abd
0@a[^-b]c@adc
1@a[^-b]c@a-c
1@a[^]b]c@a]c
0@a[^]b]c@adc
0@ab|cd@abc
0@ab|cd@abcd
0@()ef@def
0@()*@-
1@*a@-
0@^*@-
0@$*@-
1@(*)b@-
1@$b@b
2@a\@-
0@a\(b@a(b
0@a\(*b@ab
0@a\(*b@a((b
1@a\x@a\x
2@abc)@-
2@(abc@-
0@((a))@abc
0@(a)b(c)@abc
0@a+b+c@aabbabc
0@a**@-
0@a*?@-
0@(a*)*@-
0@(a*)+@-
0@(a|)*@-
0@(a*|b)*@-
0@(a+|b)*@ab
0@(a+|b)+@ab
0@(a+|b)?@ab
0@[^ab]*@cde
0@(^)*@-
0@(ab|)*@-
2@)(@-
1@abc@
1@abc@
0@a*@
0@([abc])*d@abbbcd
0@([abc])*bcd@abcd
0@a|b|c|d|e@e
0@(a|b|c|d|e)f@ef
0@((a*|b))*@-
0@abcd*efg@abcdefg
0@ab*@xabyabbbz
0@ab*@xayabbbz
0@(ab|cd)e@abcde
0@[abhgefdc]ij@hij
1@^(ab|cd)e@abcde
0@(abc|)ef@abcdef
0@(a|b)c*d@abcd
0@(ab|ab*)bc@abc
0@a([bc]*)c*@abc
0@a([bc]*)(c*d)@abcd
0@a([bc]+)(c*d)@abcd
0@a([bc]*)(c+d)@abcd
0@a[bcd]*dcdcde@adcdcde
1@a[bcd]+dcdcde@adcdcde
0@(ab|a)b*c@abc
0@((a)(b)c)(d)@abcd
0@[A-Za-z_][A-Za-z0-9_]*@alpha
0@^a(bc+|b[eh])g|.h$@abh
0@(bc+d$|ef*g.|h?i(j|k))@effgz
0@(bc+d$|ef*g.|h?i(j|k))@ij
1@(bc+d$|ef*g.|h?i(j|k))@effg
1@(bc+d$|ef*g.|h?i(j|k))@bcdd
0@(bc+d$|ef*g.|h?i(j|k))@reffgz
1@((((((((((a))))))))))@-
0@(((((((((a)))))))))@a
1@multiple words of text@uh-uh
0@multiple words@multiple words, yeah
0@(.*)c(.*)@abcde
1@\((.*),@(.*)\)
1@[k]@ab
0@abcd@abcd
0@a(bc)d@abcd
0@a[-]?c@ac
0@(....).*\1@beriberi

13
gnu/usr.bin/grep/tests/spencer2.sh
View file

@ -1,13 +0,0 @@
#!/bin/sh
# Regression test for GNU grep.
: ${srcdir=.}
failures=0
# . . . and the following by Henry Spencer.
${AWK-awk} -f $srcdir/scriptgen.awk $srcdir/spencer2.tests > tmp2.script
sh tmp2.script && exit $failures
exit 1

317
gnu/usr.bin/grep/tests/spencer2.tests
View file

@ -1,317 +0,0 @@
0@a@a
0@abc@abc
0@abc|de@abc
0@a|b|c@abc
0@a(b)c@abc
1@a\(b\)c@abc
2@a(@EPAREN
2@a(@a(
0@a\(@a(
1@a\(@EPAREN
1@a\(b@EPAREN
2@a(b@EPAREN
2@a(b@a(b
2@a)@a)
2@)@)
2@a)@a)
1@a\)@EPAREN
1@\)@EPAREN
0@a()b@ab
1@a\(\)b@ab
0@^abc$@abc
1@a^b@a^b
1@a^b@a^b
1@a$b@a$b
1@a$b@a$b
0@^@abc
0@$@abc
1@^$@""
1@$^@""
1@\($\)\(^\)@""
0@^^@""
0@$$@""
1@b$@abNc
1@b$@abNc
1@^b$@aNbNc
1@^b$@aNbNc
1@^$@aNNb
1@^$@abc
1@^$@abcN
1@$^@aNNb
1@\($\)\(^\)@aNNb
0@^^@aNNb
0@$$@aNNb
0@^a@a
0@a$@a
0@^a@aNb
1@^b@aNb
0@a$@bNa
1@b$@bNa
0@a*(^b$)c*@b
1@a*\(^b$\)c*@b
0@|@EMPTY
0@|@|
0@*@BADRPT
0@*@*
0@+@BADRPT
0@?@BADRPT
1@""@EMPTY
0@()@abc
1@\(\)@abc
0@a||b@EMPTY
0@|ab@EMPTY
0@ab|@EMPTY
1@(|a)b@EMPTY
1@(a|)b@EMPTY
1@(*a)@BADRPT
1@(+a)@BADRPT
1@(?a)@BADRPT
1@({1}a)@BADRPT
1@\(\{1\}a\)@BADRPT
1@(a|*b)@BADRPT
1@(a|+b)@BADRPT
1@(a|?b)@BADRPT
1@(a|{1}b)@BADRPT
0@^*@BADRPT
0@^*@*
0@^+@BADRPT
0@^?@BADRPT
0@^{1}@BADRPT
1@^\{1\}@BADRPT
0@a.c@abc
0@a[bc]d@abd
0@a\*c@a*c
1@ac@abc
1@a\bc@ac
1@\{@BADRPT
0@a\[b@a[b
2@a[b@EBRACK
0@a$@a
1@a$@a$
1@a\$@a
0@a\$@a$
1@a\$@a
1@a\$@a\$
2@a\(b\)\2c@ESUBREG
2@a\(b\1\)c@ESUBREG
2@a\(b*\)c\1d@abbcbd
2@a\(b*\)c\1d@abbcbbbd
2@^\(.\)\1@abc
2@a\(\([bc]\)\2\)*d@abbccd
2@a\(\([bc]\)\2\)*d@abbcbd
2@a\(\(b\)*\2\)*d@abbbd
2@\(a\)\1bcd@aabcd
2@\(a\)\1bc*d@aabcd
2@\(a\)\1bc*d@aabd
2@\(a\)\1bc*d@aabcccd
2@\(a\)\1bc*[ce]d@aabcccd
2@^\(a\)\1b\(c\)*cd$@aabcccd
0@ab*c@abc
0@ab+c@abc
0@ab?c@abc
1@a\(*\)b@a*b
1@a\(**\)b@ab
1@a\(***\)b@BADRPT
0@*a@*a
0@**a@a
1@***a@BADRPT
2@{@{
2@{abc@{abc
2@{1@BADRPT
0@{1}@BADRPT
2@a{b@a{b
0@a{1}b@ab
1@a\{1\}b@ab
0@a{1,}b@ab
1@a\{1,\}b@ab
0@a{1,2}b@aab
1@a\{1,2\}b@aab
2@a{1@EBRACE
1@a\{1@EBRACE
2@a{1a@EBRACE
1@a\{1a@EBRACE
2@a{1a}@BADBR
1@a\{1a\}@BADBR
0@a{,2}@a{,2}
1@a\{,2\}@BADBR
0@a{,}@a{,}
1@a\{,\}@BADBR
2@a{1,x}@BADBR
1@a\{1,x\}@BADBR
2@a{1,x@EBRACE
1@a\{1,x@EBRACE
1@a{300}@BADBR
1@a\{300\}@BADBR
1@a{1,0}@BADBR
1@a\{1,0\}@BADBR
0@ab{0,0}c@abcac
1@ab\{0,0\}c@abcac
0@ab{0,1}c@abcac
1@ab\{0,1\}c@abcac
0@ab{0,3}c@abbcac
1@ab\{0,3\}c@abbcac
0@ab{1,1}c@acabc
1@ab\{1,1\}c@acabc
0@ab{1,3}c@acabc
1@ab\{1,3\}c@acabc
0@ab{2,2}c@abcabbc
1@ab\{2,2\}c@abcabbc
0@ab{2,4}c@abcabbc
1@ab\{2,4\}c@abcabbc
0@a**@BADRPT
1@a++@BADRPT
0@a??@BADRPT
0@a*+@BADRPT
0@a*?@BADRPT
0@a+*@BADRPT
0@a+?@BADRPT
0@a?*@BADRPT
0@a?+@BADRPT
1@a{1}{1}@BADRPT
0@a*{1}@BADRPT
1@a+{1}@BADRPT
0@a?{1}@BADRPT
0@a{1}*@BADRPT
1@a{1}+@BADRPT
0@a{1}?@BADRPT
2@a*{b}@a{b}
1@a\{1\}\{1\}@BADRPT
1@a*\{1\}@BADRPT
1@a\{1\}*@BADRPT
0@a[b]c@abc
0@a[ab]c@abc
0@a[^ab]c@adc
0@a[]b]c@a]c
0@a[[b]c@a[c
0@a[-b]c@a-c
0@a[^]b]c@adc
0@a[^-b]c@adc
0@a[b-]c@a-c
2@a[b@EBRACK
2@a[]@EBRACK
0@a[1-3]c@a2c
1@a[3-1]c@ERANGE
1@a[1-3-5]c@ERANGE
1@a[[.-.]--]c@a-c
2@a[1-@ERANGE
2@a[[.@EBRACK
2@a[[.x@EBRACK
2@a[[.x.@EBRACK
1@a[[.x.]@EBRACK
1@a[[.x.]]@ax
1@a[[.x,.]]@ECOLLATE
1@a[[.one.]]b@a1b
1@a[[.notdef.]]b@ECOLLATE
1@a[[.].]]b@a]b
0@a[[:alpha:]]c@abc
2@a[[:notdef:]]c@ECTYPE
2@a[[:@EBRACK
2@a[[:alpha@EBRACK
2@a[[:alpha:]@EBRACK
2@a[[:alpha,:]@ECTYPE
2@a[[:]:]]b@ECTYPE
2@a[[:-:]]b@ECTYPE
2@a[[:alph:]]@ECTYPE
2@a[[:alphabet:]]@ECTYPE
1@[[:blank:]]+@aSSTb
1@[[:cntrl:]]+@aNTb
0@[[:digit:]]+@a019b
0@[[:graph:]]+@Sa%bS
0@[[:lower:]]+@AabC
0@[[:print:]]+@NaSbN
0@[[:punct:]]+@S%-&T
1@[[:space:]]+@aSNTb
0@[[:upper:]]+@aBCd
0@[[:xdigit:]]+@p0f3Cq
1@a[[=b=]]c@abc
2@a[[=@EBRACK
2@a[[=b@EBRACK
2@a[[=b=@EBRACK
1@a[[=b=]@EBRACK
1@a[[=b,=]]@ECOLLATE
1@a[[=one=]]b@a1b
0@a(((b)))c@abc
0@a(b|(c))d@abd
0@a(b*|c)d@abbd
0@a[ab]{20}@aaaaabaaaabaaaabaaaab
0@a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab]@aaaaabaaaabaaaabaaaab
0@a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab](wee|week)(knights|night)@aaaaabaaaabaaaabaaaabweeknights
0@12345678901234567890123456789@a12345678901234567890123456789b
0@123456789012345678901234567890@a123456789012345678901234567890b
0@1234567890123456789012345678901@a1234567890123456789012345678901b
0@12345678901234567890123456789012@a12345678901234567890123456789012b
0@123456789012345678901234567890123@a123456789012345678901234567890123b
0@1234567890123456789012345678901234567890123456789012345678901234567890@a1234567890123456789012345678901234567890123456789012345678901234567890b
0@[ab][cd][ef][gh][ij][kl][mn]@xacegikmoq
0@[ab][cd][ef][gh][ij][kl][mn][op]@xacegikmoq
0@[ab][cd][ef][gh][ij][kl][mn][op][qr]@xacegikmoqy
0@[ab][cd][ef][gh][ij][kl][mn][op][q]@xacegikmoqy
0@abc@xabcy
2@a\(b\)?c\1d@acd
1@aBc@Abc
1@a[Bc]*d@abBCcd
1@0[[:upper:]]1@0a1
1@0[[:lower:]]1@0A1
1@a[^b]c@abc
0@a[^b]c@aBc
0@a[^b]c@adc
0@[a]b[c]@abc
0@[a]b[a]@aba
0@[abc]b[abc]@abc
0@[abc]b[abd]@abd
0@a(b?c)+d@accd
0@(wee|week)(knights|night)@weeknights
0@(we|wee|week|frob)(knights|night|day)@weeknights
0@a[bc]d@xyzaaabcaababdacd
0@a[ab]c@aaabc
0@abc@abc
0@a*@b
0@/\*.*\*/@/*x*/
0@/\*.*\*/@/*x*/y/*z*/
0@/\*([^*]|\*[^/])*\*/@/*x*/
0@/\*([^*]|\*[^/])*\*/@/*x*/y/*z*/
0@/\*([^*]|\*[^/])*\*/@/*x**/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x*/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x**/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x****/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x**x*/y/*z*/
0@/\*([^*]|\*+[^*/])*\*+/@/*x***x/y/*z*/
0@[abc]@a(b)c
0@[abc]@a(d)c
0@[abc]@a(bc)d
0@[abc]@a(dc)d
0@.@a()c
0@b.*c@b(bc)c
0@b.*@b(bc)c
0@.*c@b(bc)c
0@abc@abc
0@abc@xabcy
1@abc@xyz
0@a*b@aba*b
0@a*b@ab
1@""@EMPTY
1@aZb@a
1@aZb@a
0@aZb@(aZb)
0@aZ*b@(ab)
0@a.b@(aZb)
0@a.*@(aZb)c
2@[[:<:]]a@a
2@[[:<:]]a@ba
2@[[:<:]]a@-a
2@a[[:>:]]@a
2@a[[:>:]]@ab
2@a[[:>:]]@a-
2@[[:<:]]a.c[[:>:]]@axcd-dayc-dazce-abc
2@[[:<:]]a.c[[:>:]]@axcd-dayc-dazce-abc-q
2@[[:<:]]a.c[[:>:]]@axc-dayc-dazce-abc
2@[[:<:]]b.c[[:>:]]@a_bxc-byc_d-bzc-q
2@[[:<:]].x..[[:>:]]@y_xa_-_xb_y-_xc_-axdc
2@[[:<:]]a_b[[:>:]]@x_a_b
0@(A[1])|(A[2])|(A[3])|(A[4])|(A[5])|(A[6])|(A[7])|(A[8])|(A[9])|(A[A])@A1
0@abcdefghijklmnop@abcdefghijklmnop
0@abcdefghijklmnopqrstuv@abcdefghijklmnopqrstuv
0@CC[13]1|a{21}[23][EO][123][Es][12]a{15}aa[34][EW]aaaaaaa[X]a@CC11
0@a?b@ab
1@-\{0,1\}[0-9]*$@-5

52
gnu/usr.bin/grep/tests/status.sh
View file

@ -1,52 +0,0 @@
#!/bin/sh
# Test for status code for GNU grep.
# status code
# 0 match found
# 1 no match
# 2 file not found
: ${srcdir=.}
failures=0
# should return 0 found a match
echo "abcd" | ${GREP} -E -e 'abc' > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Status: Wrong status code, test \#1 failed"
failures=1
fi
# should return 1 found no match
echo "abcd" | ${GREP} -E -e 'zbc' > /dev/null 2>&1
if test $? -ne 1 ; then
echo "Status: Wrong status code, test \#2 failed"
failures=1
fi
# the filename MMMMMMMM.MMM should not exist hopefully
if test -r MMMMMMMM.MMM; then
echo "Please remove MMMMMMMM.MMM to run check"
else
# should return 2 file not found
${GREP} -E -e 'abc' MMMMMMMM.MMM > /dev/null 2>&1
if test $? -ne 2 ; then
echo "Status: Wrong status code, test \#3 failed"
failures=1
fi
# should return 2 file not found
${GREP} -E -s -e 'abc' MMMMMMMM.MMM > /dev/null 2>&1
if test $? -ne 2 ; then
echo "Status: Wrong status code, test \#4 failed"
failures=1
fi
# should return 0 found a match
echo "abcd" | ${GREP} -E -q -s 'abc' MMMMMMMM.MMM - > /dev/null 2>&1
if test $? -ne 0 ; then
echo "Status: Wrong status code, test \#5 failed"
failures=1
fi
fi
exit $failures

475
gnu/usr.bin/grep/tests/tests
View file

@ -1,475 +0,0 @@
# regular expression test set
# Lines are at least three fields, separated by one or more tabs. "" stands
# for an empty field. First field is an RE. Second field is flags. If
# C flag given, regcomp() is expected to fail, and the third field is the
# error name (minus the leading REG_).
#
# Otherwise it is expected to succeed, and the third field is the string to
# try matching it against. If there is no fourth field, the match is
# expected to fail. If there is a fourth field, it is the substring that
# the RE is expected to match. If there is a fifth field, it is a comma-
# separated list of what the subexpressions should match, with - indicating
# no match for that one. In both the fourth and fifth fields, a (sub)field
# starting with @ indicates that the (sub)expression is expected to match
# a null string followed by the stuff after the @; this provides a way to
# test where null strings match. The character `N' in REs and strings
# is newline, `S' is space, `T' is tab, `Z' is NUL.
#
# The full list of flags:
# - placeholder, does nothing
# b RE is a BRE, not an ERE
# & try it as both an ERE and a BRE
# C regcomp() error expected, third field is error name
# i REG_ICASE
# m ("mundane") REG_NOSPEC
# s REG_NOSUB (not really testable)
# n REG_NEWLINE
# ^ REG_NOTBOL
# $ REG_NOTEOL
# # REG_STARTEND (see below)
# p REG_PEND
#
# For REG_STARTEND, the start/end offsets are those of the substring
# enclosed in ().
# basics
a & a a
abc & abc abc
abc|de - abc abc
a|b|c - abc a
# parentheses and perversions thereof
a(b)c - abc abc
a\(b\)c b abc abc
a( C EPAREN
a( b a( a(
a\( - a( a(
a\( bC EPAREN
a\(b bC EPAREN
a(b C EPAREN
a(b b a(b a(b
# gag me with a right parenthesis -- 1003.2 goofed here (my fault, partly)
a) - a) a)
) - ) )
# end gagging (in a just world, those *should* give EPAREN)
a) b a) a)
a\) bC EPAREN
\) bC EPAREN
a()b - ab ab
a\(\)b b ab ab
# anchoring and REG_NEWLINE
^abc$ & abc abc
a^b - a^b
a^b b a^b a^b
a$b - a$b
a$b b a$b a$b
^ & abc @abc
$ & abc @
^$ & "" @
$^ - "" @
\($\)\(^\) b "" @
# stop retching, those are legitimate (although disgusting)
^^ - "" @
$$ - "" @
##b$ & abNc
##b$ &n abNc b
##^b$ & aNbNc
##^b$ &n aNbNc b
##^$ &n aNNb @Nb
^$ n abc
##^$ n abcN @
##$^ n aNNb @Nb
##\($\)\(^\) bn aNNb @Nb
##^^ n^ aNNb @Nb
##$$ n aNNb @NN
^a ^ a
a$ $ a
##^a ^n aNb
##^b ^n aNb b
##a$ $n bNa
##b$ $n bNa b
a*(^b$)c* - b b
a*\(^b$\)c* b b b
# certain syntax errors and non-errors
| C EMPTY
| b | |
* C BADRPT
* b * *
+ C BADRPT
? C BADRPT
"" &C EMPTY
() - abc @abc
\(\) b abc @abc
a||b C EMPTY
|ab C EMPTY
ab| C EMPTY
(|a)b C EMPTY
(a|)b C EMPTY
(*a) C BADRPT
(+a) C BADRPT
(?a) C BADRPT
({1}a) C BADRPT
\(\{1\}a\) bC BADRPT
(a|*b) C BADRPT
(a|+b) C BADRPT
(a|?b) C BADRPT
(a|{1}b) C BADRPT
^* C BADRPT
^* b * *
^+ C BADRPT
^? C BADRPT
^{1} C BADRPT
^\{1\} bC BADRPT
# metacharacters, backslashes
a.c & abc abc
a[bc]d & abd abd
a\*c & a*c a*c
a\\b & a\b a\b
a\\\*b & a\*b a\*b
a\bc & abc abc
a\ &C EESCAPE
a\\bc & a\bc a\bc
\{ bC BADRPT
a\[b & a[b a[b
a[b &C EBRACK
# trailing $ is a peculiar special case for the BRE code
a$ & a a
a$ & a$
a\$ & a
a\$ & a$ a$
a\\$ & a
a\\$ & a$
a\\$ & a\$
a\\$ & a\ a\
# back references, ugh
##a\(b\)\2c bC ESUBREG
##a\(b\1\)c bC ESUBREG
a\(b*\)c\1d b abbcbbd abbcbbd bb
a\(b*\)c\1d b abbcbd
a\(b*\)c\1d b abbcbbbd
^\(.\)\1 b abc
a\([bc]\)\1d b abcdabbd abbd b
a\(\([bc]\)\2\)*d b abbccd abbccd
a\(\([bc]\)\2\)*d b abbcbd
# actually, this next one probably ought to fail, but the spec is unclear
a\(\(b\)*\2\)*d b abbbd abbbd
# here is a case that no NFA implementation does right
\(ab*\)[ab]*\1 b ababaaa ababaaa a
# check out normal matching in the presence of back refs
\(a\)\1bcd b aabcd aabcd
\(a\)\1bc*d b aabcd aabcd
\(a\)\1bc*d b aabd aabd
\(a\)\1bc*d b aabcccd aabcccd
\(a\)\1bc*[ce]d b aabcccd aabcccd
^\(a\)\1b\(c\)*cd$ b aabcccd aabcccd
# ordinary repetitions
ab*c & abc abc
ab+c - abc abc
ab?c - abc abc
a\(*\)b b a*b a*b
a\(**\)b b ab ab
a\(***\)b bC BADRPT
*a b *a *a
**a b a a
***a bC BADRPT
# the dreaded bounded repetitions
{ & { {
{abc & {abc {abc
{1 C BADRPT
{1} C BADRPT
a{b & a{b a{b
a{1}b - ab ab
a\{1\}b b ab ab
a{1,}b - ab ab
a\{1,\}b b ab ab
a{1,2}b - aab aab
a\{1,2\}b b aab aab
a{1 C EBRACE
a\{1 bC EBRACE
a{1a C EBRACE
a\{1a bC EBRACE
a{1a} C BADBR
a\{1a\} bC BADBR
a{,2} - a{,2} a{,2}
a\{,2\} bC BADBR
a{,} - a{,} a{,}
a\{,\} bC BADBR
a{1,x} C BADBR
a\{1,x\} bC BADBR
a{1,x C EBRACE
a\{1,x bC EBRACE
a{300} C BADBR
a\{300\} bC BADBR
a{1,0} C BADBR
a\{1,0\} bC BADBR
ab{0,0}c - abcac ac
ab\{0,0\}c b abcac ac
ab{0,1}c - abcac abc
ab\{0,1\}c b abcac abc
ab{0,3}c - abbcac abbc
ab\{0,3\}c b abbcac abbc
ab{1,1}c - acabc abc
ab\{1,1\}c b acabc abc
ab{1,3}c - acabc abc
ab\{1,3\}c b acabc abc
ab{2,2}c - abcabbc abbc
ab\{2,2\}c b abcabbc abbc
ab{2,4}c - abcabbc abbc
ab\{2,4\}c b abcabbc abbc
((a{1,10}){1,10}){1,10} - a a a,a
# multiple repetitions
a** &C BADRPT
a++ C BADRPT
a?? C BADRPT
a*+ C BADRPT
a*? C BADRPT
a+* C BADRPT
a+? C BADRPT
a?* C BADRPT
a?+ C BADRPT
a{1}{1} C BADRPT
a*{1} C BADRPT
a+{1} C BADRPT
a?{1} C BADRPT
a{1}* C BADRPT
a{1}+ C BADRPT
a{1}? C BADRPT
a*{b} - a{b} a{b}
a\{1\}\{1\} bC BADRPT
a*\{1\} bC BADRPT
a\{1\}* bC BADRPT
# brackets, and numerous perversions thereof
a[b]c & abc abc
a[ab]c & abc abc
a[^ab]c & adc adc
a[]b]c & a]c a]c
a[[b]c & a[c a[c
a[-b]c & a-c a-c
a[^]b]c & adc adc
a[^-b]c & adc adc
a[b-]c & a-c a-c
a[b &C EBRACK
a[] &C EBRACK
a[1-3]c & a2c a2c
a[3-1]c &C ERANGE
a[1-3-5]c &C ERANGE
a[[.-.]--]c & a-c a-c
a[1- &C ERANGE
a[[. &C EBRACK
a[[.x &C EBRACK
a[[.x. &C EBRACK
a[[.x.] &C EBRACK
a[[.x.]] & ax ax
a[[.x,.]] &C ECOLLATE
a[[.one.]]b & a1b a1b
a[[.notdef.]]b &C ECOLLATE
a[[.].]]b & a]b a]b
a[[:alpha:]]c & abc abc
a[[:notdef:]]c &C ECTYPE
a[[: &C EBRACK
a[[:alpha &C EBRACK
a[[:alpha:] &C EBRACK
a[[:alpha,:] &C ECTYPE
a[[:]:]]b &C ECTYPE
a[[:-:]]b &C ECTYPE
a[[:alph:]] &C ECTYPE
a[[:alphabet:]] &C ECTYPE
##[[:alnum:]]+ - -%@a0X- a0X
##[[:alpha:]]+ - -%@aX0- aX
[[:blank:]]+ - aSSTb SST
##[[:cntrl:]]+ - aNTb NT
[[:digit:]]+ - a019b 019
##[[:graph:]]+ - Sa%bS a%b
[[:lower:]]+ - AabC ab
##[[:print:]]+ - NaSbN aSb
##[[:punct:]]+ - S%-&T %-&
[[:space:]]+ - aSNTb SNT
[[:upper:]]+ - aBCd BC
[[:xdigit:]]+ - p0f3Cq 0f3C
a[[=b=]]c & abc abc
a[[= &C EBRACK
a[[=b &C EBRACK
a[[=b= &C EBRACK
a[[=b=] &C EBRACK
a[[=b,=]] &C ECOLLATE
a[[=one=]]b & a1b a1b
# complexities
a(((b)))c - abc abc
a(b|(c))d - abd abd
a(b*|c)d - abbd abbd
# just gotta have one DFA-buster, of course
a[ab]{20} - aaaaabaaaabaaaabaaaab aaaaabaaaabaaaabaaaab
# and an inline expansion in case somebody gets tricky
a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab] - aaaaabaaaabaaaabaaaab aaaaabaaaabaaaabaaaab
# and in case somebody just slips in an NFA...
a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab](wee|week)(knights|night) - aaaaabaaaabaaaabaaaabweeknights aaaaabaaaabaaaabaaaabweeknights
# fish for anomalies as the number of states passes 32
12345678901234567890123456789 - a12345678901234567890123456789b 12345678901234567890123456789
123456789012345678901234567890 - a123456789012345678901234567890b 123456789012345678901234567890
1234567890123456789012345678901 - a1234567890123456789012345678901b 1234567890123456789012345678901
12345678901234567890123456789012 - a12345678901234567890123456789012b 12345678901234567890123456789012
123456789012345678901234567890123 - a123456789012345678901234567890123b 123456789012345678901234567890123
# and one really big one, beyond any plausible word width
1234567890123456789012345678901234567890123456789012345678901234567890 - a1234567890123456789012345678901234567890123456789012345678901234567890b 1234567890123456789012345678901234567890123456789012345678901234567890
# fish for problems as brackets go past 8
[ab][cd][ef][gh][ij][kl][mn] - xacegikmoq acegikm
[ab][cd][ef][gh][ij][kl][mn][op] - xacegikmoq acegikmo
[ab][cd][ef][gh][ij][kl][mn][op][qr] - xacegikmoqy acegikmoq
[ab][cd][ef][gh][ij][kl][mn][op][q] - xacegikmoqy acegikmoq
# subtleties of matching
abc & xabcy abc
a\(b\)?c\1d b acd
aBc i Abc Abc
a[Bc]*d i abBCcd abBCcd
0[[:upper:]]1 &i 0a1 0a1
0[[:lower:]]1 &i 0A1 0A1
a[^b]c &i abc
a[^b]c &i aBc
a[^b]c &i adc adc
[a]b[c] - abc abc
[a]b[a] - aba aba
[abc]b[abc] - abc abc
[abc]b[abd] - abd abd
a(b?c)+d - accd accd
(wee|week)(knights|night) - weeknights weeknights
(we|wee|week|frob)(knights|night|day) - weeknights weeknights
a[bc]d - xyzaaabcaababdacd abd
a[ab]c - aaabc abc
abc s abc abc
a* & b @b
# Let's have some fun -- try to match a C comment.
# first the obvious, which looks okay at first glance...
/\*.*\*/ - /*x*/ /*x*/
# but...
/\*.*\*/ - /*x*/y/*z*/ /*x*/y/*z*/
# okay, we must not match */ inside; try to do that...
/\*([^*]|\*[^/])*\*/ - /*x*/ /*x*/
/\*([^*]|\*[^/])*\*/ - /*x*/y/*z*/ /*x*/
# but...
/\*([^*]|\*[^/])*\*/ - /*x**/y/*z*/ /*x**/y/*z*/
# and a still fancier version, which does it right (I think)...
/\*([^*]|\*+[^*/])*\*+/ - /*x*/ /*x*/
/\*([^*]|\*+[^*/])*\*+/ - /*x*/y/*z*/ /*x*/
/\*([^*]|\*+[^*/])*\*+/ - /*x**/y/*z*/ /*x**/
/\*([^*]|\*+[^*/])*\*+/ - /*x****/y/*z*/ /*x****/
/\*([^*]|\*+[^*/])*\*+/ - /*x**x*/y/*z*/ /*x**x*/
/\*([^*]|\*+[^*/])*\*+/ - /*x***x/y/*z*/ /*x***x/y/*z*/
# subexpressions
a(b)(c)d - abcd abcd b,c
a(((b)))c - abc abc b,b,b
a(b|(c))d - abd abd b,-
a(b*|c|e)d - abbd abbd bb
a(b*|c|e)d - acd acd c
a(b*|c|e)d - ad ad @d
a(b?)c - abc abc b
a(b?)c - ac ac @c
a(b+)c - abc abc b
a(b+)c - abbbc abbbc bbb
a(b*)c - ac ac @c
(a|ab)(bc([de]+)f|cde) - abcdef abcdef a,bcdef,de
# the regression tester only asks for 9 subexpressions
a(b)(c)(d)(e)(f)(g)(h)(i)(j)k - abcdefghijk abcdefghijk b,c,d,e,f,g,h,i,j
a(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)l - abcdefghijkl abcdefghijkl b,c,d,e,f,g,h,i,j,k
a([bc]?)c - abc abc b
a([bc]?)c - ac ac @c
a([bc]+)c - abc abc b
a([bc]+)c - abcc abcc bc
a([bc]+)bc - abcbc abcbc bc
a(bb+|b)b - abb abb b
a(bbb+|bb+|b)b - abb abb b
a(bbb+|bb+|b)b - abbb abbb bb
a(bbb+|bb+|b)bb - abbb abbb b
(.*).* - abcdef abcdef abcdef
##(a*)* - bc @b @b
# do we get the right subexpression when it is used more than once?
a(b|c)*d - ad ad -
a(b|c)*d - abcd abcd c
a(b|c)+d - abd abd b
a(b|c)+d - abcd abcd c
a(b|c?)+d - ad ad @d
a(b|c?)+d - abcd abcd @d
a(b|c){0,0}d - ad ad -
a(b|c){0,1}d - ad ad -
a(b|c){0,1}d - abd abd b
a(b|c){0,2}d - ad ad -
a(b|c){0,2}d - abcd abcd c
a(b|c){0,}d - ad ad -
a(b|c){0,}d - abcd abcd c
a(b|c){1,1}d - abd abd b
a(b|c){1,1}d - acd acd c
a(b|c){1,2}d - abd abd b
a(b|c){1,2}d - abcd abcd c
a(b|c){1,}d - abd abd b
a(b|c){1,}d - abcd abcd c
a(b|c){2,2}d - acbd acbd b
a(b|c){2,2}d - abcd abcd c
a(b|c){2,4}d - abcd abcd c
a(b|c){2,4}d - abcbd abcbd b
a(b|c){2,4}d - abcbcd abcbcd c
a(b|c){2,}d - abcd abcd c
a(b|c){2,}d - abcbd abcbd b
##a(b+|((c)*))+d - abd abd @d,@d,-
##a(b+|((c)*))+d - abcd abcd @d,@d,-
# check out the STARTEND option
[abc] &# a(b)c b
[abc] &# a(d)c
[abc] &# a(bc)d b
[abc] &# a(dc)d c
. &# a()c
b.*c &# b(bc)c bc
b.* &# b(bc)c bc
.*c &# b(bc)c bc
# plain strings, with the NOSPEC flag
abc m abc abc
abc m xabcy abc
abc m xyz
a*b m aba*b a*b
a*b m ab
"" mC EMPTY
# cases involving NULs
aZb & a a
aZb &p a
#aZb &p# (aZb) aZb
aZ*b &p# (ab) ab
#a.b &# (aZb) aZb
#a.* &# (aZb)c aZb
# word boundaries (ick)
[[:<:]]a & a a
[[:<:]]a & ba
[[:<:]]a & -a a
a[[:>:]] & a a
a[[:>:]] & ab
a[[:>:]] & a- a
[[:<:]]a.c[[:>:]] & axcd-dayc-dazce-abc abc
[[:<:]]a.c[[:>:]] & axcd-dayc-dazce-abc-q abc
[[:<:]]a.c[[:>:]] & axc-dayc-dazce-abc axc
[[:<:]]b.c[[:>:]] & a_bxc-byc_d-bzc-q bzc
[[:<:]].x..[[:>:]] & y_xa_-_xb_y-_xc_-axdc _xc_
[[:<:]]a_b[[:>:]] & x_a_b
# past problems, and suspected problems
(A[1])|(A[2])|(A[3])|(A[4])|(A[5])|(A[6])|(A[7])|(A[8])|(A[9])|(A[A]) - A1 A1
abcdefghijklmnop i abcdefghijklmnop abcdefghijklmnop
abcdefghijklmnopqrstuv i abcdefghijklmnopqrstuv abcdefghijklmnopqrstuv
(ALAK)|(ALT[AB])|(CC[123]1)|(CM[123]1)|(GAMC)|(LC[23][EO ])|(SEM[1234])|(SL[ES][12])|(SLWW)|(SLF )|(SLDT)|(VWH[12])|(WH[34][EW])|(WP1[ESN]) - CC11 CC11
CC[13]1|a{21}[23][EO][123][Es][12]a{15}aa[34][EW]aaaaaaa[X]a - CC11 CC11
Char \([a-z0-9_]*\)\[.* b Char xyz[k Char xyz[k xyz
a?b - ab ab
-\{0,1\}[0-9]*$ b -5 -5

19
gnu/usr.bin/grep/tests/warning.sh
View file

@ -1,19 +0,0 @@
#!/bin/sh
#
# Tell them not to be alarmed.
: ${srcdir=.}
failures=0
#
cat <<\EOF
Please, do not be alarmed if some of the tests failed.
Report them to <bug-gnu-utils@gnu.org>,
with the line number, the name of the file,
and grep version number 'grep --version'.
Make sure you have the word grep in the subject.
Thank You.
EOF

87
gnu/usr.bin/grep/xalloc.h
View file

@ -1,87 +0,0 @@
/* xalloc.h -- malloc with out-of-memory checking
Copyright (C) 1990-1998, 1999, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
#ifndef XALLOC_H_
# define XALLOC_H_
# ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
# endif
# ifndef __attribute__
# if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 8) || __STRICT_ANSI__
# define __attribute__(x)
# endif
# endif
# ifndef ATTRIBUTE_NORETURN
# define ATTRIBUTE_NORETURN __attribute__ ((__noreturn__))
# endif
/* Exit value when the requested amount of memory is not available.
It is initialized to EXIT_FAILURE, but the caller may set it to
some other value. */
extern int xalloc_exit_failure;
/* If this pointer is non-zero, run the specified function upon each
allocation failure. It is initialized to zero. */
extern void (*xalloc_fail_func) PARAMS ((void));
/* If XALLOC_FAIL_FUNC is undefined or a function that returns, this
message is output. It is translated via gettext.
Its value is "memory exhausted". */
extern char const xalloc_msg_memory_exhausted[];
/* This function is always triggered when memory is exhausted. It is
in charge of honoring the three previous items. This is the
function to call when one wants the program to die because of a
memory allocation failure. */
extern void xalloc_die PARAMS ((void)) ATTRIBUTE_NORETURN;
void *xmalloc PARAMS ((size_t n));
void *xcalloc PARAMS ((size_t n, size_t s));
void *xrealloc PARAMS ((void *p, size_t n));
char *xstrdup PARAMS ((const char *str));
# define XMALLOC(Type, N_items) ((Type *) xmalloc (sizeof (Type) * (N_items)))
# define XCALLOC(Type, N_items) ((Type *) xcalloc (sizeof (Type), (N_items)))
# define XREALLOC(Ptr, Type, N_items) \
((Type *) xrealloc ((void *) (Ptr), sizeof (Type) * (N_items)))
/* Declare and alloc memory for VAR of type TYPE. */
# define NEW(Type, Var) Type *(Var) = XMALLOC (Type, 1)
/* Free VAR only if non NULL. */
# define XFREE(Var) \
do { \
if (Var) \
free (Var); \
} while (0)
/* Return a pointer to a malloc'ed copy of the array SRC of NUM elements. */
# define CCLONE(Src, Num) \
(memcpy (xmalloc (sizeof (*Src) * (Num)), (Src), sizeof (*Src) * (Num)))
/* Return a malloc'ed copy of SRC. */
# define CLONE(Src) CCLONE (Src, 1)
#endif /* !XALLOC_H_ */

116
gnu/usr.bin/grep/xmalloc.c
View file

@ -1,116 +0,0 @@
/* xmalloc.c -- malloc with out of memory checking
Copyright (C) 1990-1999, 2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#if STDC_HEADERS
# include <stdlib.h>
#else
void *calloc ();
void *malloc ();
void *realloc ();
void free ();
#endif
#if ENABLE_NLS
# include <libintl.h>
# define _(Text) gettext (Text)
#else
# define textdomain(Domain)
# define _(Text) Text
#endif
#define N_(Text) Text
#include "error.h"
#include "xalloc.h"
#ifndef EXIT_FAILURE
# define EXIT_FAILURE 1
#endif
#ifndef HAVE_DONE_WORKING_MALLOC_CHECK
"you must run the autoconf test for a properly working malloc -- see malloc.m4"
#endif
#ifndef HAVE_DONE_WORKING_REALLOC_CHECK
"you must run the autoconf test for a properly working realloc --see realloc.m4"
#endif
/* Exit value when the requested amount of memory is not available.
The caller may set it to some other value. */
int xalloc_exit_failure = EXIT_FAILURE;
/* If non NULL, call this function when memory is exhausted. */
void (*xalloc_fail_func) PARAMS ((void)) = 0;
/* If XALLOC_FAIL_FUNC is NULL, or does return, display this message
before exiting when memory is exhausted. Goes through gettext. */
char const xalloc_msg_memory_exhausted[] = N_("memory exhausted");
void
xalloc_die (void)
{
if (xalloc_fail_func)
(*xalloc_fail_func) ();
error (xalloc_exit_failure, 0, "%s", _(xalloc_msg_memory_exhausted));
/* The `noreturn' cannot be given to error, since it may return if
its first argument is 0. To help compilers understand the
xalloc_die does terminate, call exit. */
exit (EXIT_FAILURE);
}
/* Allocate N bytes of memory dynamically, with error checking. */
void *
xmalloc (size_t n)
{
void *p;
p = malloc (n);
if (p == 0)
xalloc_die ();
return p;
}
/* Change the size of an allocated block of memory P to N bytes,
with error checking. */
void *
xrealloc (void *p, size_t n)
{
p = realloc (p, n);
if (p == 0)
xalloc_die ();
return p;
}
/* Allocate memory for N elements of S bytes, with error checking. */
void *
xcalloc (size_t n, size_t s)
{
void *p;
p = calloc (n, s);
if (p == 0)
xalloc_die ();
return p;
}

282
gnu/usr.bin/grep/xstrtol.c
View file

@ -1,282 +0,0 @@
/* A more useful interface to strtol.
Copyright (C) 1995, 1996, 1998-2000 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Jim Meyering. */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#ifndef __strtol
# define __strtol strtol
# define __strtol_t long int
# define __xstrtol xstrtol
#endif
/* Some pre-ANSI implementations (e.g. SunOS 4)
need stderr defined if assertion checking is enabled. */
#include <stdio.h>
#if STDC_HEADERS
# include <stdlib.h>
#endif
#if HAVE_STRING_H
# include <string.h>
#else
# include <strings.h>
# ifndef strchr
# define strchr index
# endif
#endif
#include <assert.h>
#include <ctype.h>
#include <errno.h>
#ifndef errno
extern int errno;
#endif
#if HAVE_LIMITS_H
# include <limits.h>
#endif
#ifndef CHAR_BIT
# define CHAR_BIT 8
#endif
/* The extra casts work around common compiler bugs. */
#define TYPE_SIGNED(t) (! ((t) 0 < (t) -1))
/* The outer cast is needed to work around a bug in Cray C 5.0.3.0.
It is necessary at least when t == time_t. */
#define TYPE_MINIMUM(t) ((t) (TYPE_SIGNED (t) \
? ~ (t) 0 << (sizeof (t) * CHAR_BIT - 1) : (t) 0))
#define TYPE_MAXIMUM(t) (~ (t) 0 - TYPE_MINIMUM (t))
#if defined (STDC_HEADERS) || (!defined (isascii) && !defined (HAVE_ISASCII))
# define IN_CTYPE_DOMAIN(c) 1
#else
# define IN_CTYPE_DOMAIN(c) isascii(c)
#endif
#define ISSPACE(c) (IN_CTYPE_DOMAIN (c) && isspace (c))
#include "xstrtol.h"
#ifndef strtol
long int strtol ();
#endif
#ifndef strtoul
unsigned long int strtoul ();
#endif
#ifndef strtoumax
uintmax_t strtoumax ();
#endif
static int
bkm_scale (__strtol_t *x, int scale_factor)
{
__strtol_t product = *x * scale_factor;
if (*x != product / scale_factor)
return 1;
*x = product;
return 0;
}
static int
bkm_scale_by_power (__strtol_t *x, int base, int power)
{
while (power--)
if (bkm_scale (x, base))
return 1;
return 0;
}
/* FIXME: comment. */
strtol_error
__xstrtol (const char *s, char **ptr, int strtol_base,
__strtol_t *val, const char *valid_suffixes)
{
char *t_ptr;
char **p;
__strtol_t tmp;
assert (0 <= strtol_base && strtol_base <= 36);
p = (ptr ? ptr : &t_ptr);
if (! TYPE_SIGNED (__strtol_t))
{
const char *q = s;
while (ISSPACE ((unsigned char) *q))
++q;
if (*q == '-')
return LONGINT_INVALID;
}
errno = 0;
tmp = __strtol (s, p, strtol_base);
if (errno != 0)
return LONGINT_OVERFLOW;
if (*p == s)
return LONGINT_INVALID;
/* Let valid_suffixes == NULL mean `allow any suffix'. */
/* FIXME: update all callers except the ones that allow suffixes
after the number, changing last parameter NULL to `""'. */
if (!valid_suffixes)
{
*val = tmp;
return LONGINT_OK;
}
if (**p != '\0')
{
int base = 1024;
int suffixes = 1;
int overflow;
if (!strchr (valid_suffixes, **p))
{
*val = tmp;
return LONGINT_INVALID_SUFFIX_CHAR;
}
if (strchr (valid_suffixes, '0'))
{
/* The ``valid suffix'' '0' is a special flag meaning that
an optional second suffix is allowed, which can change
the base, e.g. "100MD" for 100 megabytes decimal. */
switch (p[0][1])
{
case 'B':
suffixes++;
break;
case 'D':
base = 1000;
suffixes++;
break;
}
}
switch (**p)
{
case 'b':
overflow = bkm_scale (&tmp, 512);
break;
case 'B':
overflow = bkm_scale (&tmp, 1024);
break;
case 'c':
overflow = 0;
break;
case 'E': /* Exa */
overflow = bkm_scale_by_power (&tmp, base, 6);
break;
case 'G': /* Giga */
overflow = bkm_scale_by_power (&tmp, base, 3);
break;
case 'k': /* kilo */
overflow = bkm_scale_by_power (&tmp, base, 1);
break;
case 'M': /* Mega */
case 'm': /* 'm' is undocumented; for backward compatibility only */
overflow = bkm_scale_by_power (&tmp, base, 2);
break;
case 'P': /* Peta */
overflow = bkm_scale_by_power (&tmp, base, 5);
break;
case 'T': /* Tera */
overflow = bkm_scale_by_power (&tmp, base, 4);
break;
case 'w':
overflow = bkm_scale (&tmp, 2);
break;
case 'Y': /* Yotta */
overflow = bkm_scale_by_power (&tmp, base, 8);
break;
case 'Z': /* Zetta */
overflow = bkm_scale_by_power (&tmp, base, 7);
break;
default:
*val = tmp;
return LONGINT_INVALID_SUFFIX_CHAR;
break;
}
if (overflow)
return LONGINT_OVERFLOW;
(*p) += suffixes;
}
*val = tmp;
return LONGINT_OK;
}
#ifdef TESTING_XSTRTO
# include <stdio.h>
# include "error.h"
char *program_name;
int
main (int argc, char** argv)
{
strtol_error s_err;
int i;
program_name = argv[0];
for (i=1; i<argc; i++)
{
char *p;
__strtol_t val;
s_err = __xstrtol (argv[i], &p, 0, &val, "bckmw");
if (s_err == LONGINT_OK)
{
printf ("%s->%lu (%s)\n", argv[i], val, p);
}
else
{
STRTOL_FATAL_ERROR (argv[i], "arg", s_err);
}
}
exit (0);
}
#endif /* TESTING_XSTRTO */

64
gnu/usr.bin/grep/xstrtol.h
View file

@ -1,64 +0,0 @@
#ifndef XSTRTOL_H_
# define XSTRTOL_H_ 1
# if HAVE_INTTYPES_H
# include <inttypes.h> /* for uintmax_t */
# endif
# ifndef PARAMS
# if defined PROTOTYPES || (defined __STDC__ && __STDC__)
# define PARAMS(Args) Args
# else
# define PARAMS(Args) ()
# endif
# endif
# ifndef _STRTOL_ERROR
enum strtol_error
{
LONGINT_OK, LONGINT_INVALID, LONGINT_INVALID_SUFFIX_CHAR, LONGINT_OVERFLOW
};
typedef enum strtol_error strtol_error;
# endif
# define _DECLARE_XSTRTOL(name, type) \
strtol_error \
name PARAMS ((const char *s, char **ptr, int base, \
type *val, const char *valid_suffixes));
_DECLARE_XSTRTOL (xstrtol, long int)
_DECLARE_XSTRTOL (xstrtoul, unsigned long int)
_DECLARE_XSTRTOL (xstrtoumax, uintmax_t)
# define _STRTOL_ERROR(Exit_code, Str, Argument_type_string, Err) \
do \
{ \
switch ((Err)) \
{ \
case LONGINT_OK: \
abort (); \
\
case LONGINT_INVALID: \
error ((Exit_code), 0, "invalid %s `%s'", \
(Argument_type_string), (Str)); \
break; \
\
case LONGINT_INVALID_SUFFIX_CHAR: \
error ((Exit_code), 0, "invalid character following %s `%s'", \
(Argument_type_string), (Str)); \
break; \
\
case LONGINT_OVERFLOW: \
error ((Exit_code), 0, "%s `%s' too large", \
(Argument_type_string), (Str)); \
break; \
} \
} \
while (0)
# define STRTOL_FATAL_ERROR(Str, Argument_type_string, Err) \
_STRTOL_ERROR (2, Str, Argument_type_string, Err)
# define STRTOL_FAIL_WARN(Str, Argument_type_string, Err) \
_STRTOL_ERROR (0, Str, Argument_type_string, Err)
#endif /* not XSTRTOL_H_ */

31
gnu/usr.bin/grep/xstrtoumax.c
View file

@ -1,31 +0,0 @@
/* xstrtoumax.c -- A more useful interface to strtoumax.
Copyright 1999 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Written by Paul Eggert. */
#if HAVE_CONFIG_H
# include <config.h>
#endif
#if HAVE_INTTYPES_H
# include <inttypes.h>
#endif
#define __strtol strtoumax
#define __strtol_t uintmax_t
#define __xstrtol xstrtoumax
#include "xstrtol.c"