mirror/freebsd
1
0
Fork 0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-24 11:29:10 +00:00
Code Issues Releases Activity

This commit was generated by cvs2svn to compensate for changes in r61,

Browse Source 
which included commits to RCS files with non-trunk default branches.
This commit is contained in:
Nate Williams 1993-06-29 06:04:45 +00:00
commit 059e2eccbf
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=62
16 changed files with 7322 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

339
gnu/usr.bin/grep/COPYING Normal file
View File

@ -0,0 +1,339 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
675 Mass Ave, Cambridge, MA 02139, 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
Appendix: 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., 675 Mass Ave, Cambridge, MA 02139, 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.

7
gnu/usr.bin/grep/Makefile Normal file
View File

@ -0,0 +1,7 @@
PROG= grep
SRCS= dfa.c regex.o grep.o
CFLAGS+=-DSTDC_HEADERS=1 -DHAVE_UNISTD_H=1
MLINKS= grep.1 egrep.1
.include <bsd.prog.mk>

70
gnu/usr.bin/grep/README Normal file
View File

@ -0,0 +1,70 @@
This README documents GNU e?grep version 1.6. All bugs reported for
previous versions have been fixed.
See the file INSTALL for compilation and installation instructions.
Send bug reports to bug-gnu-utils@prep.ai.mit.edu.
GNU e?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 e?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
may run more slowly, however.)
GNU e?grep is brought to you by the efforts of several people:
Mike Haertel wrote the deterministic regexp code and the bulk
of the program.
James A. Woods is responsible for the hybridized search strategy
of using Boyer-Moore-Gosper fixed-string search as a filter
before calling the general regexp matcher.
Arthur David Olson contributed code that finds fixed strings for
the aforementioned BMG search for a large class of regexps.
Richard Stallman wrote the backtracking regexp matcher that is
used for \<digit> backreferences, as well as the getopt that
is provided for 4.2BSD sites. The backtracking matcher was
originally written for GNU Emacs.
D. A. Gwyn wrote the C alloca emulation that is provided so
System V machines can run this program. (Alloca is used only
by RMS' backtracking matcher, and then only rarely, so there
is no loss if your machine doesn't have a "real" alloca.)
Scott Anderson and Henry Spencer designed the regression tests
used in the "regress" script.
Paul Placeway wrote the manual page, based on this README.
If you are interested in improving this program, you may wish to try
any of the following:
1. Replace the fast search loop with a faster search loop.
There are several things that could be improved, the most notable
of which would be to calculate a minimal delta2 to use.
2. Make backreferencing \<digit> faster. Right now, backreferencing is
handled by calling the Emacs backtracking matcher to verify the partial
match. This is slow; if the DFA routines could handle backreferencing
themselves a speedup on the order of three to four times might occur
in those cases where the backtracking matcher is called to verify nearly
every line. Also, some portability problems due to the inclusion of the
emacs matcher would be solved because it could then be eliminated.
Note that expressions with backreferencing are not true regular
expressions, and thus are not equivalent to any DFA. So this is hard.
3. Handle POSIX style regexps. I'm not sure if this could be called an
improvement; some of the things on regexps in the POSIX draft I have
seen are pretty sickening. But it would be useful in the interests of
conforming to the standard.
4. Replace the main driver program grep.c with the much cleaner main driver
program used in GNU fgrep.

2276
gnu/usr.bin/grep/dfa.c Normal file
View File

File diff suppressed because it is too large Load Diff

450
gnu/usr.bin/grep/dfa.h Normal file
View File

@ -0,0 +1,450 @@
/* dfa.h - declarations for GNU deterministic regexp compiler
Copyright (C) 1988 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., 675 Mass Ave, Cambridge, MA 02139, USA. */
/* Written June, 1988 by Mike Haertel */
#ifdef STDC_HEADERS
#include <stddef.h>
#include <stdlib.h>
#else /* !STDC_HEADERS */
#define const
#include <sys/types.h> /* For size_t. */
extern char *calloc(), *malloc(), *realloc();
extern void free();
#ifndef NULL
#define NULL 0
#endif
#endif /* ! STDC_HEADERS */
#include <ctype.h>
#ifndef isascii
#define ISALNUM(c) isalnum(c)
#define ISALPHA(c) isalpha(c)
#define ISUPPER(c) isupper(c)
#define ISLOWER(c) islower(c)
#else
#define ISALNUM(c) (isascii(c) && isalnum(c))
#define ISALPHA(c) (isascii(c) && isalpha(c))
#define ISUPPER(c) (isascii(c) && isupper(c))
#define ISLOWER(c) (isascii(c) && islower(c))
#endif
/* 1 means plain parentheses serve as grouping, and backslash
parentheses are needed for literal searching.
0 means backslash-parentheses are grouping, and plain parentheses
are for literal searching. */
#define RE_NO_BK_PARENS 1
/* 1 means plain | serves as the "or"-operator, and \| is a literal.
0 means \| serves as the "or"-operator, and | is a literal. */
#define RE_NO_BK_VBAR 2
/* 0 means plain + or ? serves as an operator, and \+, \? are literals.
1 means \+, \? are operators and plain +, ? are literals. */
#define RE_BK_PLUS_QM 4
/* 1 means | binds tighter than ^ or $.
0 means the contrary. */
#define RE_TIGHT_VBAR 8
/* 1 means treat \n as an _OR operator
0 means treat it as a normal character */
#define RE_NEWLINE_OR 16
/* 0 means that a special characters (such as *, ^, and $) always have
their special meaning regardless of the surrounding context.
1 means that special characters may act as normal characters in some
contexts. Specifically, this applies to:
^ - only special at the beginning, or after ( or |
$ - only special at the end, or before ) or |
*, +, ? - only special when not after the beginning, (, or | */
#define RE_CONTEXT_INDEP_OPS 32
/* Now define combinations of bits for the standard possibilities. */
#define RE_SYNTAX_AWK (RE_NO_BK_PARENS | RE_NO_BK_VBAR | RE_CONTEXT_INDEP_OPS)
#define RE_SYNTAX_EGREP (RE_SYNTAX_AWK | RE_NEWLINE_OR)
#define RE_SYNTAX_GREP (RE_BK_PLUS_QM | RE_NEWLINE_OR)
#define RE_SYNTAX_EMACS 0
/* Number of bits in an unsigned char. */
#define CHARBITS 8
/* First integer value that is greater than any character code. */
#define _NOTCHAR (1 << CHARBITS)
/* INTBITS need not be exact, just a lower bound. */
#define INTBITS (CHARBITS * sizeof (int))
/* Number of ints required to hold a bit for every character. */
#define _CHARSET_INTS ((_NOTCHAR + INTBITS - 1) / INTBITS)
/* Sets of unsigned characters are stored as bit vectors in arrays of ints. */
typedef int _charset[_CHARSET_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. */
#if __STDC__
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. */
_ALLBEGLINE, /* _ALLBEGLINE is a terminal symbol that
matches the empty string if it is at the
beginning of a line; _ALLBEGLINE applies
to the entire regexp and can only occur
as the first token thereof. _ALLBEGLINE
never appears in the parse tree; a _BEGLINE
is prepended with _CAT to the entire
regexp instead. */
_ENDLINE, /* _ENDLINE is a terminal symbol that matches
the empty string if it is at the end of
a line. */
_ALLENDLINE, /* _ALLENDLINE is to _ENDLINE as _ALLBEGLINE
is to _BEGLINE. */
_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. */
_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. */
_LPAREN, /* _LPAREN never appears in the parse tree,
it is only a lexeme. */
_RPAREN, /* _RPAREN never appears in the parse tree. */
_SET /* _SET and (and any value greater) is a
terminal symbol that matches any of a
class of characters. */
} _token;
#else /* ! __STDC__ */
typedef short _token;
#define _END -1
#define _EMPTY _NOTCHAR
#define _BACKREF (_EMPTY + 1)
#define _BEGLINE (_EMPTY + 2)
#define _ALLBEGLINE (_EMPTY + 3)
#define _ENDLINE (_EMPTY + 4)
#define _ALLENDLINE (_EMPTY + 5)
#define _BEGWORD (_EMPTY + 6)
#define _ENDWORD (_EMPTY + 7)
#define _LIMWORD (_EMPTY + 8)
#define _NOTLIMWORD (_EMPTY + 9)
#define _QMARK (_EMPTY + 10)
#define _STAR (_EMPTY + 11)
#define _PLUS (_EMPTY + 12)
#define _CAT (_EMPTY + 13)
#define _OR (_EMPTY + 14)
#define _LPAREN (_EMPTY + 15)
#define _RPAREN (_EMPTY + 16)
#define _SET (_EMPTY + 17)
#endif /* ! __STDC__ */
/* Sets are stored in an array in the compiled regexp; the index of the
array corresponding to a given set token is given by _SET_INDEX(t). */
#define _SET_INDEX(t) ((t) - _SET)
/* 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 regexp 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. */
} _dfa_state;
/* If an r.e. is at most MUST_MAX characters long, we look for a string which
must appear in it; whatever's found is dropped into the struct reg. */
#define MUST_MAX 50
/* A compiled regular expression. */
struct regexp
{
/* Stuff built by the scanner. */
_charset *charsets; /* Array of character sets for _SET tokens. */
int cindex; /* Index for adding new charsets. */
int calloc; /* Number of charsets 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 regparse(). */
/* Stuff owned by the state builder. */
_dfa_state *states; /* States of the regexp. */
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
regexecute and computed in build_state. */
int *newlines; /* Transitions on newlines. The entry for a
newline in any transition table is always
-1 so we can count lines without wasting
too many cycles. The transition for a
newline is stored separately and handled
as a special case. Newline is also used
as a sentinel at the end of the buffer. */
char must[MUST_MAX];
int mustn;
};
/* Some macros for user access to regexp 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, reg) \
_SUCCEEDS_IN_CONTEXT((reg).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, reg) (-(reg).states[state].first_end)
/* Entry points. */
#if __STDC__
/* Regsyntax() takes two arguments; the first sets the syntax bits described
earlier in this file, and the second sets the case-folding flag. */
extern void regsyntax(int, int);
/* Compile the given string of the given length into the given struct regexp.
Final argument is a flag specifying whether to build a searching or an
exact matcher. */
extern void regcompile(const char *, size_t, struct regexp *, int);
/* Execute the given struct regexp on the buffer of characters. The
first char * points to the beginning, and the second points to the
first character after the end of the buffer, which must be a writable
place so a sentinel end-of-buffer marker can be stored there. The
second-to-last argument is a flag telling whether to allow newlines to
be part of a string matching the regexp. The next-to-last argument,
if non-NULL, points to a place to increment every time we see a
newline. The final argument, if non-NULL, 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 NULL if no match is found, or a pointer to the first
character after the first & shortest matching string in the buffer. */
extern char *regexecute(struct regexp *, char *, char *, int, int *, int *);
/* Free the storage held by the components of a struct regexp. */
extern void regfree(struct regexp *);
/* Entry points for people who know what they're doing. */
/* Initialize the components of a struct regexp. */
extern void reginit(struct regexp *);
/* Incrementally parse a string of given length into a struct regexp. */
extern void regparse(const char *, size_t, struct regexp *);
/* Analyze a parsed regexp; second argument tells whether to build a searching
or an exact matcher. */
extern void reganalyze(struct regexp *, int);
/* Compute, for each possible character, the transitions out of a given
state, storing them in an array of integers. */
extern void regstate(int, struct regexp *, int []);
/* Error handling. */
/* Regerror() is called by the regexp routines whenever an error occurs. It
takes a single argument, a NUL-terminated string describing the error.
The default regerror() prints the error message to stderr and exits.
The user can provide a different regfree() if so desired. */
extern void regerror(const char *);
#else /* ! __STDC__ */
extern void regsyntax(), regcompile(), regfree(), reginit(), regparse();
extern void reganalyze(), regstate(), regerror();
extern char *regexecute();
#endif /* ! __STDC__ */

678
gnu/usr.bin/grep/getopt.c Normal file
View File

@ -0,0 +1,678 @@
/* Getopt for GNU.
NOTE: getopt is now part of the C library, so if you don't know what
"Keep this file name-space clean" means, talk to roland@gnu.ai.mit.edu
before changing it!
Copyright (C) 1987, 88, 89, 90, 91, 1992 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., 675 Mass Ave, Cambridge, MA 02139, USA. */
/* AIX requires this to be the first thing in the file. */
#ifdef __GNUC__
#define alloca __builtin_alloca
#else /* not __GNUC__ */
#if defined(sparc) && !defined(USG) && !defined(SVR4) && !defined(__svr4__)
#include <alloca.h>
#else
#ifdef _AIX
#pragma alloca
#else
char *alloca ();
#endif
#endif /* sparc */
#endif /* not __GNUC__ */
#ifdef LIBC
/* For when compiled as part of the GNU C library. */
#include <ansidecl.h>
#endif
#include <stdio.h>
/* This needs to come after some library #include
to get __GNU_LIBRARY__ defined. */
#ifdef __GNU_LIBRARY__
#undef alloca
#include <stdlib.h>
#include <string.h>
#else /* Not GNU C library. */
#define __alloca alloca
#endif /* GNU C library. */
#ifndef __STDC__
#define const
#endif
/* If GETOPT_COMPAT is defined, `+' as well as `--' can introduce a
long-named option. Because this is not POSIX.2 compliant, it is
being phased out. */
#define GETOPT_COMPAT
/* This version of `getopt' appears to the caller like standard Unix `getopt'
but it behaves differently for the user, since it allows the user
to intersperse the options with the other arguments.
As `getopt' works, it permutes the elements of ARGV so that,
when it is done, all the options precede everything else. Thus
all application programs are extended to handle flexible argument order.
Setting the environment variable POSIXLY_CORRECT disables permutation.
Then the behavior is completely standard.
GNU application programs can use a third alternative mode in which
they can distinguish the relative order of options and other arguments. */
#include "getopt.h"
/* For communication from `getopt' to the caller.
When `getopt' finds an option that takes an argument,
the argument value is returned here.
Also, when `ordering' is RETURN_IN_ORDER,
each non-option ARGV-element is returned here. */
char *optarg = 0;
/* Index in ARGV of the next element to be scanned.
This is used for communication to and from the caller
and for communication between successive calls to `getopt'.
On entry to `getopt', zero means this is the first call; initialize.
When `getopt' returns EOF, this is the index of the first of the
non-option elements that the caller should itself scan.
Otherwise, `optind' communicates from one call to the next
how much of ARGV has been scanned so far. */
int optind = 0;
/* The next char to be scanned in the option-element
in which the last option character we returned was found.
This allows us to pick up the scan where we left off.
If this is zero, or a null string, it means resume the scan
by advancing to the next ARGV-element. */
static char *nextchar;
/* Callers store zero here to inhibit the error message
for unrecognized options. */
int opterr = 1;
/* Describe how to deal with options that follow non-option ARGV-elements.
If the caller did not specify anything,
the default is REQUIRE_ORDER if the environment variable
POSIXLY_CORRECT is defined, PERMUTE otherwise.
REQUIRE_ORDER means don't recognize them as options;
stop option processing when the first non-option is seen.
This is what Unix does.
This mode of operation is selected by either setting the environment
variable POSIXLY_CORRECT, or using `+' as the first character
of the list of option characters.
PERMUTE is the default. We permute the contents of ARGV as we scan,
so that eventually all the non-options are at the end. This allows options
to be given in any order, even with programs that were not written to
expect this.
RETURN_IN_ORDER is an option available to programs that were written
to expect options and other ARGV-elements in any order and that care about
the ordering of the two. We describe each non-option ARGV-element
as if it were the argument of an option with character code 1.
Using `-' as the first character of the list of option characters
selects this mode of operation.
The special argument `--' forces an end of option-scanning regardless
of the value of `ordering'. In the case of RETURN_IN_ORDER, only
`--' can cause `getopt' to return EOF with `optind' != ARGC. */
static enum
{
REQUIRE_ORDER, PERMUTE, RETURN_IN_ORDER
} ordering;
#ifdef __GNU_LIBRARY__
#include <string.h>
#define my_index strchr
#define my_bcopy(src, dst, n) memcpy ((dst), (src), (n))
#else
/* Avoid depending on library functions or files
whose names are inconsistent. */
char *getenv ();
static char *
my_index (string, chr)
char *string;
int chr;
{
while (*string)
{
if (*string == chr)
return string;
string++;
}
return 0;
}
static void
my_bcopy (from, to, size)
char *from, *to;
int size;
{
int i;
for (i = 0; i < size; i++)
to[i] = from[i];
}
#endif /* GNU C library. */
/* Handle permutation of arguments. */
/* Describe the part of ARGV that contains non-options that have
been skipped. `first_nonopt' is the index in ARGV of the first of them;
`last_nonopt' is the index after the last of them. */
static int first_nonopt;
static int last_nonopt;
/* Exchange two adjacent subsequences of ARGV.
One subsequence is elements [first_nonopt,last_nonopt)
which contains all the non-options that have been skipped so far.
The other is elements [last_nonopt,optind), which contains all
the options processed since those non-options were skipped.
`first_nonopt' and `last_nonopt' are relocated so that they describe
the new indices of the non-options in ARGV after they are moved. */
static void
exchange (argv)
char **argv;
{
int nonopts_size = (last_nonopt - first_nonopt) * sizeof (char *);
char **temp = (char **) __alloca (nonopts_size);
/* Interchange the two blocks of data in ARGV. */
my_bcopy (&argv[first_nonopt], temp, nonopts_size);
my_bcopy (&argv[last_nonopt], &argv[first_nonopt],
(optind - last_nonopt) * sizeof (char *));
my_bcopy (temp, &argv[first_nonopt + optind - last_nonopt], nonopts_size);
/* Update records for the slots the non-options now occupy. */
first_nonopt += (optind - last_nonopt);
last_nonopt = optind;
}
/* Scan elements of ARGV (whose length is ARGC) for option characters
given in OPTSTRING.
If an element of ARGV starts with '-', and is not exactly "-" or "--",
then it is an option element. The characters of this element
(aside from the initial '-') are option characters. If `getopt'
is called repeatedly, it returns successively each of the option characters
from each of the option elements.
If `getopt' finds another option character, it returns that character,
updating `optind' and `nextchar' so that the next call to `getopt' can
resume the scan with the following option character or ARGV-element.
If there are no more option characters, `getopt' returns `EOF'.
Then `optind' is the index in ARGV of the first ARGV-element
that is not an option. (The ARGV-elements have been permuted
so that those that are not options now come last.)
OPTSTRING is a string containing the legitimate option characters.
If an option character is seen that is not listed in OPTSTRING,
return '?' after printing an error message. If you set `opterr' to
zero, the error message is suppressed but we still return '?'.
If a char in OPTSTRING is followed by a colon, that means it wants an arg,
so the following text in the same ARGV-element, or the text of the following
ARGV-element, is returned in `optarg'. Two colons mean an option that
wants an optional arg; if there is text in the current ARGV-element,
it is returned in `optarg', otherwise `optarg' is set to zero.
If OPTSTRING starts with `-' or `+', it requests different methods of
handling the non-option ARGV-elements.
See the comments about RETURN_IN_ORDER and REQUIRE_ORDER, above.
Long-named options begin with `--' instead of `-'.
Their names may be abbreviated as long as the abbreviation is unique
or is an exact match for some defined option. If they have an
argument, it follows the option name in the same ARGV-element, separated
from the option name by a `=', or else the in next ARGV-element.
When `getopt' finds a long-named option, it returns 0 if that option's
`flag' field is nonzero, the value of the option's `val' field
if the `flag' field is zero.
The elements of ARGV aren't really const, because we permute them.
But we pretend they're const in the prototype to be compatible
with other systems.
LONGOPTS is a vector of `struct option' terminated by an
element containing a name which is zero.
LONGIND returns the index in LONGOPT of the long-named option found.
It is only valid when a long-named option has been found by the most
recent call.
If LONG_ONLY is nonzero, '-' as well as '--' can introduce
long-named options. */
int
_getopt_internal (argc, argv, optstring, longopts, longind, long_only)
int argc;
char *const *argv;
const char *optstring;
const struct option *longopts;
int *longind;
int long_only;
{
int option_index;
optarg = 0;
/* Initialize the internal data when the first call is made.
Start processing options with ARGV-element 1 (since ARGV-element 0
is the program name); the sequence of previously skipped
non-option ARGV-elements is empty. */
if (optind == 0)
{
first_nonopt = last_nonopt = optind = 1;
nextchar = NULL;
/* Determine how to handle the ordering of options and nonoptions. */
if (optstring[0] == '-')
{
ordering = RETURN_IN_ORDER;
++optstring;
}
else if (optstring[0] == '+')
{
ordering = REQUIRE_ORDER;
++optstring;
}
else if (getenv ("POSIXLY_CORRECT") != NULL)
ordering = REQUIRE_ORDER;
else
ordering = PERMUTE;
}
if (nextchar == NULL || *nextchar == '\0')
{
if (ordering == PERMUTE)
{
/* If we have just processed some options following some non-options,
exchange them so that the options come first. */
if (first_nonopt != last_nonopt && last_nonopt != optind)
exchange ((char **) argv);
else if (last_nonopt != optind)
first_nonopt = optind;
/* Now skip any additional non-options
and extend the range of non-options previously skipped. */
while (optind < argc
&& (argv[optind][0] != '-' || argv[optind][1] == '\0')
#ifdef GETOPT_COMPAT
&& (longopts == NULL
|| argv[optind][0] != '+' || argv[optind][1] == '\0')
#endif /* GETOPT_COMPAT */
)
optind++;
last_nonopt = optind;
}
/* Special ARGV-element `--' means premature end of options.
Skip it like a null option,
then exchange with previous non-options as if it were an option,
then skip everything else like a non-option. */
if (optind != argc && !strcmp (argv[optind], "--"))
{
optind++;
if (first_nonopt != last_nonopt && last_nonopt != optind)
exchange ((char **) argv);
else if (first_nonopt == last_nonopt)
first_nonopt = optind;
last_nonopt = argc;
optind = argc;
}
/* If we have done all the ARGV-elements, stop the scan
and back over any non-options that we skipped and permuted. */
if (optind == argc)
{
/* Set the next-arg-index to point at the non-options
that we previously skipped, so the caller will digest them. */
if (first_nonopt != last_nonopt)
optind = first_nonopt;
return EOF;
}
/* If we have come to a non-option and did not permute it,
either stop the scan or describe it to the caller and pass it by. */
if ((argv[optind][0] != '-' || argv[optind][1] == '\0')
#ifdef GETOPT_COMPAT
&& (longopts == NULL
|| argv[optind][0] != '+' || argv[optind][1] == '\0')
#endif /* GETOPT_COMPAT */
)
{
if (ordering == REQUIRE_ORDER)
return EOF;
optarg = argv[optind++];
return 1;
}
/* We have found another option-ARGV-element.
Start decoding its characters. */
nextchar = (argv[optind] + 1
+ (longopts != NULL && argv[optind][1] == '-'));
}
if (longopts != NULL
&& ((argv[optind][0] == '-'
&& (argv[optind][1] == '-' || long_only))
#ifdef GETOPT_COMPAT
|| argv[optind][0] == '+'
#endif /* GETOPT_COMPAT */
))
{
const struct option *p;
char *s = nextchar;
int exact = 0;
int ambig = 0;
const struct option *pfound = NULL;
int indfound;
while (*s && *s != '=')
s++;
/* Test all options for either exact match or abbreviated matches. */
for (p = longopts, option_index = 0; p->name;
p++, option_index++)
if (!strncmp (p->name, nextchar, s - nextchar))
{
if (s - nextchar == strlen (p->name))
{
/* Exact match found. */
pfound = p;
indfound = option_index;
exact = 1;
break;
}
else if (pfound == NULL)
{
/* First nonexact match found. */
pfound = p;
indfound = option_index;
}
else
/* Second nonexact match found. */
ambig = 1;
}
if (ambig && !exact)
{
if (opterr)
fprintf (stderr, "%s: option `%s' is ambiguous\n",
argv[0], argv[optind]);
nextchar += strlen (nextchar);
optind++;
return '?';
}
if (pfound != NULL)
{
option_index = indfound;
optind++;
if (*s)
{
/* Don't test has_arg with >, because some C compilers don't
allow it to be used on enums. */
if (pfound->has_arg)
optarg = s + 1;
else
{
if (opterr)
{
if (argv[optind - 1][1] == '-')
/* --option */
fprintf (stderr,
"%s: option `--%s' doesn't allow an argument\n",
argv[0], pfound->name);
else
/* +option or -option */
fprintf (stderr,
"%s: option `%c%s' doesn't allow an argument\n",
argv[0], argv[optind - 1][0], pfound->name);
}
nextchar += strlen (nextchar);
return '?';
}
}
else if (pfound->has_arg == 1)
{
if (optind < argc)
optarg = argv[optind++];
else
{
if (opterr)
fprintf (stderr, "%s: option `%s' requires an argument\n",
argv[0], argv[optind - 1]);
nextchar += strlen (nextchar);
return '?';
}
}
nextchar += strlen (nextchar);
if (longind != NULL)
*longind = option_index;
if (pfound->flag)
{
*(pfound->flag) = pfound->val;
return 0;
}
return pfound->val;
}
/* Can't find it as a long option. If this is not getopt_long_only,
or the option starts with '--' or is not a valid short
option, then it's an error.
Otherwise interpret it as a short option. */
if (!long_only || argv[optind][1] == '-'
#ifdef GETOPT_COMPAT
|| argv[optind][0] == '+'
#endif /* GETOPT_COMPAT */
|| my_index (optstring, *nextchar) == NULL)
{
if (opterr)
{
if (argv[optind][1] == '-')
/* --option */
fprintf (stderr, "%s: unrecognized option `--%s'\n",
argv[0], nextchar);
else
/* +option or -option */
fprintf (stderr, "%s: unrecognized option `%c%s'\n",
argv[0], argv[optind][0], nextchar);
}
nextchar += strlen (nextchar);
optind++;
return '?';
}
}
/* Look at and handle the next option-character. */
{
char c = *nextchar++;
char *temp = my_index (optstring, c);
/* Increment `optind' when we start to process its last character. */
if (*nextchar == '\0')
optind++;
if (temp == NULL || c == ':')
{
if (opterr)
{
if (c < 040 || c >= 0177)
fprintf (stderr, "%s: unrecognized option, character code 0%o\n",
argv[0], c);
else
fprintf (stderr, "%s: unrecognized option `-%c'\n", argv[0], c);
}
return '?';
}
if (temp[1] == ':')
{
if (temp[2] == ':')
{
/* This is an option that accepts an argument optionally. */
if (*nextchar != '\0')
{
optarg = nextchar;
optind++;
}
else
optarg = 0;
nextchar = NULL;
}
else
{
/* This is an option that requires an argument. */
if (*nextchar != 0)
{
optarg = nextchar;
/* If we end this ARGV-element by taking the rest as an arg,
we must advance to the next element now. */
optind++;
}
else if (optind == argc)
{
if (opterr)
fprintf (stderr, "%s: option `-%c' requires an argument\n",
argv[0], c);
c = '?';
}
else
/* We already incremented `optind' once;
increment it again when taking next ARGV-elt as argument. */
optarg = argv[optind++];
nextchar = NULL;
}
}
return c;
}
}
int
getopt (argc, argv, optstring)
int argc;
char *const *argv;
const char *optstring;
{
return _getopt_internal (argc, argv, optstring,
(const struct option *) 0,
(int *) 0,
0);
}
#ifdef TEST
/* Compile with -DTEST to make an executable for use in testing
the above definition of `getopt'. */
int
main (argc, argv)
int argc;
char **argv;
{
int c;
int digit_optind = 0;
while (1)
{
int this_option_optind = optind ? optind : 1;
c = getopt (argc, argv, "abc:d:0123456789");
if (c == EOF)
break;
switch (c)
{
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
if (digit_optind != 0 && digit_optind != this_option_optind)
printf ("digits occur in two different argv-elements.\n");
digit_optind = this_option_optind;
printf ("option %c\n", c);
break;
case 'a':
printf ("option a\n");
break;
case 'b':
printf ("option b\n");
break;
case 'c':
printf ("option c with value `%s'\n", optarg);
break;
case '?':
break;
default:
printf ("?? getopt returned character code 0%o ??\n", c);
}
}
if (optind < argc)
{
printf ("non-option ARGV-elements: ");
while (optind < argc)
printf ("%s ", argv[optind++]);
printf ("\n");
}
exit (0);
}
#endif /* TEST */

113
gnu/usr.bin/grep/getopt.h Normal file
View File

@ -0,0 +1,113 @@
/* Declarations for getopt.
Copyright (C) 1989, 1990, 1991, 1992 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., 675 Mass Ave, Cambridge, MA 02139, USA. */
#ifndef _GETOPT_H
#define _GETOPT_H 1
/* For communication from `getopt' to the caller.
When `getopt' finds an option that takes an argument,
the argument value is returned here.
Also, when `ordering' is RETURN_IN_ORDER,
each non-option ARGV-element is returned here. */
extern char *optarg;
/* Index in ARGV of the next element to be scanned.
This is used for communication to and from the caller
and for communication between successive calls to `getopt'.
On entry to `getopt', zero means this is the first call; initialize.
When `getopt' returns EOF, this is the index of the first of the
non-option elements that the caller should itself scan.
Otherwise, `optind' communicates from one call to the next
how much of ARGV has been scanned so far. */
extern int optind;
/* Callers store zero here to inhibit the error message `getopt' prints
for unrecognized options. */
extern int opterr;
/* Describe the long-named options requested by the application.
The LONG_OPTIONS argument to getopt_long or getopt_long_only is a vector
of `struct option' terminated by an element containing a name which is
zero.
The field `has_arg' is:
no_argument (or 0) if the option does not take an argument,
required_argument (or 1) if the option requires an argument,
optional_argument (or 2) if the option takes an optional argument.
If the field `flag' is not NULL, it points to a variable that is set
to the value given in the field `val' when the option is found, but
left unchanged if the option is not found.
To have a long-named option do something other than set an `int' to
a compiled-in constant, such as set a value from `optarg', set the
option's `flag' field to zero and its `val' field to a nonzero
value (the equivalent single-letter option character, if there is
one). For long options that have a zero `flag' field, `getopt'
returns the contents of the `val' field. */
struct option
{
#if __STDC__
const char *name;
#else
char *name;
#endif
/* has_arg can't be an enum because some compilers complain about
type mismatches in all the code that assumes it is an int. */
int has_arg;
int *flag;
int val;
};
/* Names for the values of the `has_arg' field of `struct option'. */
enum _argtype
{
no_argument,
required_argument,
optional_argument
};
#if __STDC__
extern int getopt (int argc, char *const *argv, const char *shortopts);
extern int getopt_long (int argc, char *const *argv, const char *shortopts,
const struct option *longopts, int *longind);
extern int getopt_long_only (int argc, char *const *argv,
const char *shortopts,
const struct option *longopts, int *longind);
/* Internal only. Users should not call this directly. */
extern int _getopt_internal (int argc, char *const *argv,
const char *shortopts,
const struct option *longopts, int *longind,
int long_only);
#else /* not __STDC__ */
extern int getopt ();
extern int getopt_long ();
extern int getopt_long_only ();
extern int _getopt_internal ();
#endif /* not __STDC__ */
#endif /* _GETOPT_H */

234
gnu/usr.bin/grep/grep.1 Normal file
View File

@ -0,0 +1,234 @@
.TH GREP 1 "1988 December 13" "GNU Project" \" -*- nroff -*-
.UC 4
.SH NAME
grep, egrep \- print lines matching a regular expression
.SH SYNOPSIS
.B grep
[
.B \-CVbchilnsvwx
] [
.BI \- num
] [
.B \-AB
.I num
] [ [
.B \-e
]
.I expr
|
.B \-f
.I file
] [
.I "files ..."
]
.SH DESCRIPTION
.I Grep
searches the files listed in the arguments (or standard
input if no files are given) for all lines that contain a match for
the given
.IR expr .
If any lines match, they are printed.
.PP
Also, if any matches were found,
.I grep
exits with a status of 0, but if no matches were found it exits
with a status of 1. This is useful for building shell scripts that
use
.I grep
as a condition for, for example, the
.I if
statement.
.PP
When invoked as
.I egrep
the syntax of the
.I expr
is slightly different; See below.
.br
.SH "REGULAR EXPRESSIONS"
.RS 2.5i
.ta 1i 2i
.sp
.ti -2.0i
(grep) (egrep) (explanation)
.sp
.ti -2.0i
\fIc\fP \fIc\fP a single (non-meta) character matches itself.
.sp
.ti -2.0i
\&. . matches any single character except newline.
.sp
.ti -2.0i
\\? ? postfix operator; preceeding item is optional.
.sp
.ti -2.0i
\(** \(** postfix operator; preceeding item 0 or
more times.
.sp
.ti -2.0i
\\+ + postfix operator; preceeding item 1 or
more times.
.sp
.ti -2.0i
\\| | infix operator; matches either
argument.
.sp
.ti -2.0i
^ ^ matches the empty string at the beginning of a line.
.sp
.ti -2.0i
$ $ matches the empty string at the end of a line.
.sp
.ti -2.0i
\\< \\< matches the empty string at the beginning of a word.
.sp
.ti -2.0i
\\> \\> matches the empty string at the end of a word.
.sp
.ti -2.0i
[\fIchars\fP] [\fIchars\fP] match any character in the given class; if the
first character after [ is ^, match any character
not in the given class; a range of characters may
be specified by \fIfirst\-last\fP; for example, \\W
(below) is equivalent to the class [^A\-Za\-z0\-9]
.sp
.ti -2.0i
\\( \\) ( ) parentheses are used to override operator precedence.
.sp
.ti -2.0i
\\\fIdigit\fP \\\fIdigit\fP \\\fIn\fP matches a repeat of the text
matched earlier in the regexp by the subexpression inside the nth
opening parenthesis.
.sp
.ti -2.0i
\\ \\ any special character may be preceded
by a backslash to match it literally.
.sp
.ti -2.0i
(the following are for compatibility with GNU Emacs)
.sp
.ti -2.0i
\\b \\b matches the empty string at the edge of a word.
.sp
.ti -2.0i
\\B \\B matches the empty string if not at the edge of a word.
.sp
.ti -2.0i
\\w \\w matches word-constituent characters (letters & digits).
.sp
.ti -2.0i
\\W \\W matches characters that are not word-constituent.
.RE
.PP
Operator precedence is (highest to lowest) ?, \(**, and +, concatenation,
and finally |. All other constructs are syntactically identical to
normal characters. For the truly interested, the file dfa.c describes
(and implements) the exact grammar understood by the parser.
.SH OPTIONS
.TP
.BI \-A " num"
print <num> lines of context after every matching line
.TP
.BI \-B " num"
print
.I num
lines of context before every matching line
.TP
.B \-C
print 2 lines of context on each side of every match
.TP
.BI \- num
print
.I num
lines of context on each side of every match
.TP
.B \-V
print the version number on the diagnostic output
.TP
.B \-b
print every match preceded by its byte offset
.TP
.B \-c
print a total count of matching lines only
.TP
.BI \-e " expr"
search for
.IR expr ;
useful if
.I expr
begins with \-
.TP
.BI \-f " file"
search for the expression contained in
.I file
.TP
.B \-h
don't display filenames on matches
.TP
.B \-i
ignore case difference when comparing strings
.TP
.B \-l
list files containing matches only
.TP
.B \-n
print each match preceded by its line number
.TP
.B \-s
run silently producing no output except error messages
.TP
.B \-v
print only lines that contain no matches for the <expr>
.TP
.B \-w
print only lines where the match is a complete word
.TP
.B \-x
print only lines where the match is a whole line
.SH "SEE ALSO"
emacs(1), ed(1), sh(1),
.I "GNU Emacs Manual"
.SH INCOMPATIBILITIES
The following incompatibilities with UNIX
.I grep
exist:
.PP
.RS 0.5i
The context-dependent meaning of \(** is not quite the same (grep only).
.PP
.B \-b
prints a byte offset instead of a block offset.
.PP
The {\fIm,n\fP} construct of System V grep is not implemented.
.PP
.SH BUGS
GNU \fIe?grep\fP has been thoroughly debugged and tested over a period
of several years; we think it's a reliable beast or we wouldn't
distribute it. If by some fluke of the universe you discover a bug,
send a detailed description (including options, regular expressions,
and a copy of an input file that can reproduce it) to mike@ai.mit.edu.
.PP
.SH AUTHORS
Mike Haertel wrote the deterministic regexp code and the bulk
of the program.
.PP
James A. Woods is responsible for the hybridized search strategy
of using Boyer-Moore-Gosper fixed-string search as a filter
before calling the general regexp matcher.
.PP
Arthur David Olson contributed code that finds fixed strings for
the aforementioned BMG search for a large class of regexps.
.PP
Richard Stallman wrote the backtracking regexp matcher that is used
for \\\fIdigit\fP backreferences, as well as the GNU getopt. The
backtracking matcher was originally written for GNU Emacs.
.PP
D. A. Gwyn wrote the C alloca emulation that is provided so
System V machines can run this program. (Alloca is used only
by RMS' backtracking matcher, and then only rarely, so there
is no loss if your machine doesn't have a "real" alloca.)
.PP
Scott Anderson and Henry Spencer designed the regression tests
used in the "regress" script.
.PP
Paul Placeway wrote the original version of this manual page.

1007
gnu/usr.bin/grep/grep.c Normal file
View File

File diff suppressed because it is too large Load Diff

1768
gnu/usr.bin/grep/regex.c Normal file
View File

File diff suppressed because it is too large Load Diff

185
gnu/usr.bin/grep/regex.h Normal file
View File

@ -0,0 +1,185 @@
/* Definitions for data structures callers pass the regex library.
Copyright (C) 1985, 1989 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., 675 Mass Ave, Cambridge, MA 02139, USA.
In other words, you are welcome to use, share and improve this program.
You are forbidden to forbid anyone else to use, share and improve
what you give them. Help stamp out software-hoarding! */
/* Define number of parens for which we record the beginnings and ends.
This affects how much space the `struct re_registers' type takes up. */
#ifndef RE_NREGS
#define RE_NREGS 10
#endif
/* These bits are used in the obscure_syntax variable to choose among
alternative regexp syntaxes. */
/* 1 means plain parentheses serve as grouping, and backslash
parentheses are needed for literal searching.
0 means backslash-parentheses are grouping, and plain parentheses
are for literal searching. */
#define RE_NO_BK_PARENS 1
/* 1 means plain | serves as the "or"-operator, and \| is a literal.
0 means \| serves as the "or"-operator, and | is a literal. */
#define RE_NO_BK_VBAR 2
/* 0 means plain + or ? serves as an operator, and \+, \? are literals.
1 means \+, \? are operators and plain +, ? are literals. */
#define RE_BK_PLUS_QM 4
/* 1 means | binds tighter than ^ or $.
0 means the contrary. */
#define RE_TIGHT_VBAR 8
/* 1 means treat \n as an _OR operator
0 means treat it as a normal character */
#define RE_NEWLINE_OR 16
/* 0 means that a special characters (such as *, ^, and $) always have
their special meaning regardless of the surrounding context.
1 means that special characters may act as normal characters in some
contexts. Specifically, this applies to:
^ - only special at the beginning, or after ( or |
$ - only special at the end, or before ) or |
*, +, ? - only special when not after the beginning, (, or | */
#define RE_CONTEXT_INDEP_OPS 32
/* Now define combinations of bits for the standard possibilities. */
#define RE_SYNTAX_AWK (RE_NO_BK_PARENS | RE_NO_BK_VBAR | RE_CONTEXT_INDEP_OPS)
#define RE_SYNTAX_EGREP (RE_SYNTAX_AWK | RE_NEWLINE_OR)
#define RE_SYNTAX_GREP (RE_BK_PLUS_QM | RE_NEWLINE_OR)
#define RE_SYNTAX_EMACS 0
/* This data structure is used to represent a compiled pattern. */
struct re_pattern_buffer
{
char *buffer; /* Space holding the compiled pattern commands. */
int allocated; /* Size of space that buffer points to */
int used; /* Length of portion of buffer actually occupied */
char *fastmap; /* Pointer to fastmap, if any, or zero if none. */
/* re_search uses the fastmap, if there is one,
to skip quickly over totally implausible characters */
char *translate; /* Translate table to apply to all characters before comparing.
Or zero for no translation.
The translation is applied to a pattern when it is compiled
and to data when it is matched. */
char fastmap_accurate;
/* Set to zero when a new pattern is stored,
set to one when the fastmap is updated from it. */
char can_be_null; /* Set to one by compiling fastmap
if this pattern might match the null string.
It does not necessarily match the null string
in that case, but if this is zero, it cannot.
2 as value means can match null string
but at end of range or before a character
listed in the fastmap. */
};
/* Structure to store "register" contents data in.
Pass the address of such a structure as an argument to re_match, etc.,
if you want this information back.
start[i] and end[i] record the string matched by \( ... \) grouping i,
for i from 1 to RE_NREGS - 1.
start[0] and end[0] record the entire string matched. */
struct re_registers
{
int start[RE_NREGS];
int end[RE_NREGS];
};
/* These are the command codes that appear in compiled regular expressions, one per byte.
Some command codes are followed by argument bytes.
A command code can specify any interpretation whatever for its arguments.
Zero-bytes may appear in the compiled regular expression. */
enum regexpcode
{
unused,
exactn, /* followed by one byte giving n, and then by n literal bytes */
begline, /* fails unless at beginning of line */
endline, /* fails unless at end of line */
jump, /* followed by two bytes giving relative address to jump to */
on_failure_jump, /* followed by two bytes giving relative address of place
to resume at in case of failure. */
finalize_jump, /* Throw away latest failure point and then jump to address. */
maybe_finalize_jump, /* Like jump but finalize if safe to do so.
This is used to jump back to the beginning
of a repeat. If the command that follows
this jump is clearly incompatible with the
one at the beginning of the repeat, such that
we can be sure that there is no use backtracking
out of repetitions already completed,
then we finalize. */
dummy_failure_jump, /* jump, and push a dummy failure point.
This failure point will be thrown away
if an attempt is made to use it for a failure.
A + construct makes this before the first repeat. */
anychar, /* matches any one character */
charset, /* matches any one char belonging to specified set.
First following byte is # bitmap bytes.
Then come bytes for a bit-map saying which chars are in.
Bits in each byte are ordered low-bit-first.
A character is in the set if its bit is 1.
A character too large to have a bit in the map
is automatically not in the set */
charset_not, /* similar but match any character that is NOT one of those specified */
start_memory, /* starts remembering the text that is matched
and stores it in a memory register.
followed by one byte containing the register number.
Register numbers must be in the range 0 through NREGS. */
stop_memory, /* stops remembering the text that is matched
and stores it in a memory register.
followed by one byte containing the register number.
Register numbers must be in the range 0 through NREGS. */
duplicate, /* match a duplicate of something remembered.
Followed by one byte containing the index of the memory register. */
before_dot, /* Succeeds if before dot */
at_dot, /* Succeeds if at dot */
after_dot, /* Succeeds if after dot */
begbuf, /* Succeeds if at beginning of buffer */
endbuf, /* Succeeds if at end of buffer */
wordchar, /* Matches any word-constituent character */
notwordchar, /* Matches any char that is not a word-constituent */
wordbeg, /* Succeeds if at word beginning */
wordend, /* Succeeds if at word end */
wordbound, /* Succeeds if at a word boundary */
notwordbound, /* Succeeds if not at a word boundary */
syntaxspec, /* Matches any character whose syntax is specified.
followed by a byte which contains a syntax code, Sword or such like */
notsyntaxspec /* Matches any character whose syntax differs from the specified. */
};
extern char *re_compile_pattern ();
/* Is this really advertised? */
extern void re_compile_fastmap ();
extern int re_search (), re_search_2 ();
extern int re_match (), re_match_2 ();
/* 4.2 bsd compatibility (yuck) */
extern char *re_comp ();
extern int re_exec ();
#ifdef SYNTAX_TABLE
extern char *re_syntax_table;
#endif

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

@ -0,0 +1,32 @@
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 Normal file
View File

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

30
gnu/usr.bin/grep/tests/regress.sh Normal file
View File

@ -0,0 +1,30 @@
#! /bin/sh
# Regression test for GNU e?grep.
# Usage: regress.sh [dir-containing-egrep]
builddir=${1-..}
failures=0
# The Khadafy test is brought to you by Scott Anderson . . .
$builddir/egrep -f khadafy.regexp khadafy.lines > khadafy.out
if cmp khadafy.lines khadafy.out
then
rm khadafy.out
else
echo Khadafy test failed -- output left on khadafy.out
failures=1
fi
# . . . and the following by Henry Spencer.
awk -F: -f scriptgen.awk spencer.tests > tmp.script
if sh tmp.script $builddir
then
rm tmp.script
exit $failures
else
rm tmp.script
exit 1
fi

10
gnu/usr.bin/grep/tests/scriptgen.awk Normal file
View File

@ -0,0 +1,10 @@
BEGIN { print "failures=0"; }
!/^#/ && NF == 3 {
print "echo '" $3 "' | $1/egrep -e '" $2 "' > /dev/null 2>&1";
print "if [ $? != " $1 " ]"
print "then"
printf "\techo Spencer test \\#%d failed\n", ++n
print "\tfailures=1"
print "fi"
}
END { print "exit $failures"; }

122
gnu/usr.bin/grep/tests/spencer.tests Normal file
View File

@ -0,0 +1,122 @@
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:$:abc
0:a.c:abc
0:a.c:axc
0:a.*c:axyzc
1:a.*c:axyzd
1:a[bc]d:abc
0:a[bc]d:abd
1:a[b-d]e:abd
0:a[b-d]e:ace
0:a[b-d]:aac
0:a[-b]:a-
2:a[b-]:a-
1:a[b-a]:-
2:a[]b:-
2:a[:-
0:a]:a]
0:a[]]b:a]b
0:a[^bc]d:aed
1:a[^bc]d:abd
0:a[^-b]c:adc
1:a[^-b]c:a-c
1:a[^]b]c:a]c
0:a[^]b]c:adc
0:ab|cd:abc
0:ab|cd:abcd
0:()ef:def
0:()*:-
1:*a:-
0:^*:-
0:$*:-
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