diff options
author | rgrimes <rgrimes@FreeBSD.org> | 1994-05-27 05:00:24 +0000 |
---|---|---|
committer | rgrimes <rgrimes@FreeBSD.org> | 1994-05-27 05:00:24 +0000 |
commit | be22b15ae2ff8d7fe06b6e14fddf0c5b444a95da (patch) | |
tree | a18a706dffa5baf86a3b12bbfb4f81caa097f349 /lib/libcompat | |
parent | 2a27bd86e6002c871e3b5561a5334653bb222a77 (diff) | |
download | FreeBSD-src-be22b15ae2ff8d7fe06b6e14fddf0c5b444a95da.zip FreeBSD-src-be22b15ae2ff8d7fe06b6e14fddf0c5b444a95da.tar.gz |
BSD 4.4 Lite Lib Sources
Diffstat (limited to 'lib/libcompat')
-rw-r--r-- | lib/libcompat/4.1/ftime.3 | 84 | ||||
-rw-r--r-- | lib/libcompat/4.1/getpw.3 | 78 | ||||
-rw-r--r-- | lib/libcompat/4.1/stty.3 | 93 | ||||
-rw-r--r-- | lib/libcompat/4.1/vlimit.3 | 123 | ||||
-rw-r--r-- | lib/libcompat/4.1/vtimes.3 | 141 | ||||
-rw-r--r-- | lib/libcompat/4.3/cfree.c | 43 | ||||
-rw-r--r-- | lib/libcompat/4.3/insque.3 | 80 | ||||
-rw-r--r-- | lib/libcompat/4.3/insque.c | 56 | ||||
-rw-r--r-- | lib/libcompat/4.3/lsearch.3 | 102 | ||||
-rw-r--r-- | lib/libcompat/4.3/lsearch.c | 92 | ||||
-rw-r--r-- | lib/libcompat/4.3/re_comp.3 | 123 | ||||
-rw-r--r-- | lib/libcompat/4.3/remque.c | 54 | ||||
-rw-r--r-- | lib/libcompat/4.3/rexec.3 | 122 | ||||
-rw-r--r-- | lib/libcompat/4.3/rexec.c | 146 | ||||
-rw-r--r-- | lib/libcompat/4.4/cuserid.c | 59 | ||||
-rw-r--r-- | lib/libcompat/Makefile | 58 | ||||
-rw-r--r-- | lib/libcompat/regexp/COPYRIGHT | 22 | ||||
-rw-r--r-- | lib/libcompat/regexp/README | 84 | ||||
-rw-r--r-- | lib/libcompat/regexp/regerror.c | 18 | ||||
-rw-r--r-- | lib/libcompat/regexp/regexp.3 | 318 | ||||
-rw-r--r-- | lib/libcompat/regexp/regexp.c | 1320 | ||||
-rw-r--r-- | lib/libcompat/regexp/regexp.h | 21 | ||||
-rw-r--r-- | lib/libcompat/regexp/regmagic.h | 5 | ||||
-rw-r--r-- | lib/libcompat/regexp/regsub.c | 81 |
24 files changed, 3323 insertions, 0 deletions
diff --git a/lib/libcompat/4.1/ftime.3 b/lib/libcompat/4.1/ftime.3 new file mode 100644 index 0000000..a9491af --- /dev/null +++ b/lib/libcompat/4.1/ftime.3 @@ -0,0 +1,84 @@ +.\" Copyright (c) 1980, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)ftime.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt FTIME 3 +.Os BSD 4 +.Sh NAME +.Nm ftime +.Nd get date and time +.Sh SYNOPSIS +.Fd #include <sys/types.h> +.Fd #include <sys/timeb.h> +.Ft struct timeb * +.Fn ftime "struct timeb *tp" +.Sh DESCRIPTION +.Bf -symbolic +This interface is obsoleted by gettimeofday(2). +.Pp +It is available from the compatibility library, libcompat. +.Ef +.Pp +The +.Fn ftime +routine fills in a structure pointed to by its argument, +as defined by +.Aq Pa sys/timeb.h : +.Bd -literal -offset indent +/* + * Structure returned by ftime system call + */ +struct timeb +{ + time_t time; + unsigned short millitm; + short timezone; + short dstflag; +}; +.Ed +.Pp +The structure contains the time since the epoch in seconds, +up to 1000 milliseconds of more-precise interval, +the local time zone (measured in minutes of time westward from Greenwich), +and a flag that, if nonzero, indicates that +Daylight Saving time applies locally during the appropriate part of the year. +.Sh SEE ALSO +.Xr gettimeofday 2 , +.Xr settimeofday 2 , +.Xr time 2 , +.Xr ctime 3 +.Sh HISTORY +The +.Nm +function appeared in +.Bx 4.2 . diff --git a/lib/libcompat/4.1/getpw.3 b/lib/libcompat/4.1/getpw.3 new file mode 100644 index 0000000..1568e74 --- /dev/null +++ b/lib/libcompat/4.1/getpw.3 @@ -0,0 +1,78 @@ +.\" Copyright (c) 1990, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)getpw.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt GETPW 3 +.Os +.Sh NAME +.Nm getpw +.Nd get name from uid +.Sh SYNOPSIS +.Fn getpw uid "char *buf" +.Sh DESCRIPTION +.Bf -symbolic +The getpw function is made obsolete by getpwuid(3). +.br +It is available from the compatibility library, libcompat. +.Ef +.Pp +The +.Fn getpw +function reads the file +.Pa /etc/passwd , +and if it finds +the specified +.Fa uid , +copies the password entry line into the string pointed to by +.Fa buf . +the null terminated entry line from the password database, +and appends the +.Dv NUL +character. +.Sh RETURN VALUES +The +.Fn getpw +function returns the zero if successful, otherwise +a non-zero if the entry does not exist. +.Sh FILES +.Bl -tag -width /etc/passwd - compact +.It Pa /etc/passwd +.El +.Sh SEE ALSO +.Xr getpwent 3 , +.Xr passwd 5 +.Sh HISTORY +A +.Fn getpw +function appeared in +.At v6 . diff --git a/lib/libcompat/4.1/stty.3 b/lib/libcompat/4.1/stty.3 new file mode 100644 index 0000000..eb3a5c8 --- /dev/null +++ b/lib/libcompat/4.1/stty.3 @@ -0,0 +1,93 @@ +.\" Copyright (c) 1983, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)stty.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt STTY 3 +.Os BSD 4.2 +.Sh NAME +.Nm stty , +.Nm gtty +.Nd set and get terminal state (defunct) +.Sh SYNOPSIS +.Fd #include <sgtty.h> +.Fn stty "int fd" "struct sgttyb *buf" +.Fn gtty "int fd" "struct sgttyb *buf" +.Sh DESCRIPTION +.Bf -symbolic +These interfaces are obsoleted by ioctl(2). +They are available from the compatibility library, libcompat. +.Ef +.Pp +The +.Fn stty +function +sets the state of the terminal associated with +.Fa fd . +The +.Fn gtty +function +retrieves the state of the terminal associated +with +.Fa fd . +To set the state of a terminal the call must have +write permission. +.Pp +The +.Fn stty +call is actually +.Ql ioctl(fd, TIOCSETP, buf) , +while +the +.Fn gtty +call is +.Ql ioctl(fd, TIOCGETP, buf) . +See +.Xr ioctl 2 +and +.Xr tty 4 +for an explanation. +.Sh DIAGNOSTICS +If the call is successful 0 is returned, otherwise \-1 is +returned and the global variable +.Va errno +contains the reason for the failure. +.Sh SEE ALSO +.Xr ioctl 2 , +.Xr tty 4 +.Sh HISTORY +The +.Fn stty +and +.Fn gtty +functions appeared in +.Bx 4.2 . diff --git a/lib/libcompat/4.1/vlimit.3 b/lib/libcompat/4.1/vlimit.3 new file mode 100644 index 0000000..062f557 --- /dev/null +++ b/lib/libcompat/4.1/vlimit.3 @@ -0,0 +1,123 @@ +.\" Copyright (c) 1980, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)vlimit.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt VLIMIT 3 +.Os BSD 4 +.Sh NAME +.Nm vlimit +.Nd control maximum system resource consumption +.Sh SYNOPSIS +.Fd #include <sys/vlimit.h> +.Fn vlimit resource value +.Sh DESCRIPTION +.Bf -symbolic +This interface is obsoleted by getrlimit(2). +It is available from the compatibility library, libcompat. +.Ef +.Pp +Limits the consumption by the current process and each process +it creates to not individually exceed +.Fa value +on the specified +.Fa resource . +If +.Fa value +is specified as \-1, then the current limit is returned and the +limit is unchanged. +The resources which are currently controllable are: +.Bl -tag -width LIM_NORAISE +.It Dv LIM_NORAISE +A pseudo-limit; if set non-zero then the limits may not be raised. +Only the super-user may remove the +.Em noraise +restriction. +.It Dv LIM_CPU +the maximum +number of cpu-seconds to be used by each process +.It Dv LIM_FSIZE +the largest single file which can be created +.It Dv LIM_DATA +the maximum growth of the data+stack region via +.Xr sbrk 2 +beyond the end of the program text +.It Dv LIM_STACK +the maximum +size of the automatically-extended stack region +.It Dv LIM_CORE +the size of the largest core dump that will be created. +.It Dv LIM_MAXRSS +a soft limit for the amount of physical memory (in bytes) to be given +to the program. If memory is tight, the system will prefer to take memory +from processes which are exceeding their declared +.Dv LIM_MAXRSS. +.El +.Pp +Because this information is stored in the per-process information +this system call must be executed directly by the shell if it +is to affect all future processes created by the shell; +.Xr limit +is thus a built-in command to +.Xr csh 1 . +.Pp +The system refuses to extend the data or stack space when the limits +would be exceeded in the normal way; a +.Xr break 2 +call fails if the data space limit is reached, or the process is +killed when the stack limit is reached (since the stack cannot be +extended, there is no way to send a signal!). +.Pp +A file +.Tn I/O +operation which would create a file which is too large +will cause a signal +.Dv SIGXFSZ +to be generated, this normally terminates +the process, but may be caught. +When the cpu time limit is exceeded, a signal +.Dv SIGXCPU +is sent to the +offending process; to allow it time to process the signal it is +given 5 seconds grace by raising the +.Tn CPU +time limit. +.Sh SEE ALSO +.Xr csh 1 +.Sh HISTORY +The +.Fn vlimit +function appeared in +.Bx 4.2 . +.Sh BUGS +.Dv LIM_NORAISE +no longer exists. diff --git a/lib/libcompat/4.1/vtimes.3 b/lib/libcompat/4.1/vtimes.3 new file mode 100644 index 0000000..dc4ff4a --- /dev/null +++ b/lib/libcompat/4.1/vtimes.3 @@ -0,0 +1,141 @@ +.\" Copyright (c) 1980, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)vtimes.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt VTIMES 3 +.Os BSD 4 +.Sh NAME +.Nm vtimes +.Nd get information about resource utilization +.Sh SYNOPSIS +.Fd #include <sys/vtimes.h> +.Fn vtimes "struct vtimes *par_vm" "struct vtimes *ch_vm" +.Sh DESCRIPTION +.Bf -symbolic +This interface is obsoleted by getrusage(2). +It is available from the compatibility library, libcompat. +.Ef +.Pp +The +.Fn vtimes +function +returns accounting information for the current process and for +the terminated child processes of the current +process. Either +.Fa par_vm +or +.Fa ch_vm +or both may be 0, in which case only the information for the pointers +which are non-zero is returned. +.Pp +After the call, each buffer contains information as defined by the +contents of the include file +.Pa /usr/include/sys/vtimes.h : +.Bd -literal -offset indent +struct vtimes { + int vm_utime; /* user time (*HZ) */ + int vm_stime; /* system time (*HZ) */ + /* divide next two by utime+stime to get averages */ + unsigned vm_idsrss; /* integral of d+s rss */ + unsigned vm_ixrss; /* integral of text rss */ + int vm_maxrss; /* maximum rss */ + int vm_majflt; /* major page faults */ + int vm_minflt; /* minor page faults */ + int vm_nswap; /* number of swaps */ + int vm_inblk; /* block reads */ + int vm_oublk; /* block writes */ +}; +.Ed +.Pp +The +.Fa vm_utime +and +.Fa vm_stime +fields give the user and system +time respectively in 60ths of a second (or 50ths if that +is the frequency of wall current in your locality.) The +.Fa vm_idrss +and +.Fa vm_ixrss +measure memory usage. They are computed by integrating the number of +memory pages in use each +over +.Tn CPU +time. They are reported as though computed +discretely, adding the current memory usage (in 512 byte +pages) each time the clock ticks. If a process used 5 core +pages over 1 cpu-second for its data and stack, then +.Fa vm_idsrss +would have the value 5*60, where +.Fa vm_utime+vm_stime +would be the 60. +The +.Fa Vm_idsrss +argument +integrates data and stack segment +usage, while +.Fa vm_ixrss +integrates text segment usage. +The +.Fa Vm_maxrss +function +reports the maximum instantaneous sum of the +text+data+stack core-resident page count. +.Pp +The +.Fa vm_majflt +field gives the number of page faults which +resulted in disk activity; the +.Fa vm_minflt +field gives the +number of page faults incurred in simulation of reference +bits; +.Fa vm_nswap +is the number of swaps which occurred. The +number of file system input/output events are reported in +.Fa vm_inblk +and +.Fa vm_oublk +These numbers account only for real +.Tn I/O ; +data supplied by the caching mechanism is charged only +to the first process to read or write the data. +.Sh SEE ALSO +.Xr time 2 , +.Xr wait3 2 , +.Xr getrusage 2 +.Sh HISTORY +The +.Fn vlimit +function appeared in +.Bx 4.2 . diff --git a/lib/libcompat/4.3/cfree.c b/lib/libcompat/4.3/cfree.c new file mode 100644 index 0000000..8bade2e --- /dev/null +++ b/lib/libcompat/4.3/cfree.c @@ -0,0 +1,43 @@ +/*- + * Copyright (c) 1992, 1993 + * The Regents of the University of California. 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. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)cfree.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +void +cfree(p) + void *p; +{ + free(p); +} diff --git a/lib/libcompat/4.3/insque.3 b/lib/libcompat/4.3/insque.3 new file mode 100644 index 0000000..2decaed --- /dev/null +++ b/lib/libcompat/4.3/insque.3 @@ -0,0 +1,80 @@ +.\" Copyright (c) 1983, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)insque.3 8.2 (Berkeley) 12/11/93 +.\" +.Dd December 11, 1993 +.Dt INSQUE 3 +.Os BSD 4.2 +.Sh NAME +.Nm insque , +.Nm remque +.Nd insert/remove element from a queue +.Sh SYNOPSIS +.Bd -literal +struct qelem { + struct qelem *q_forw; + struct qelem *q_back; + char q_data[]; +}; +.Ed + +.Fn insque "(caddr_t) struct qelem *elem" "(caddr_t) struct qelem *pred" +.Fn remque "(caddr_t) struct qelem *elem" +.Sh DESCRIPTION +The +.Fn insque +and +.Fn remque +functions +manipulate queues built from doubly linked lists. Each +element in the queue must be in the form of +.Dq Li struct qelem . +The function +.Fn insque +inserts +.Fa elem +in a queue immediately after +.Fa pred ; +.Fn remque +removes an entry +.Fa elem +from a queue. +.Sh SEE ALSO +.%T "VAX Architecture Handbook" , +pp. 228-235. +.Sh HISTORY +The +.Fn insque +and +.Fn remque +functions appeared in +.Bx 4.2 . diff --git a/lib/libcompat/4.3/insque.c b/lib/libcompat/4.3/insque.c new file mode 100644 index 0000000..55818fd --- /dev/null +++ b/lib/libcompat/4.3/insque.c @@ -0,0 +1,56 @@ +/* + * Copyright (c) 1987, 1993 + * The Regents of the University of California. 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. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)insque.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +/* + * insque -- vax insque instruction + * + * NOTE: this implementation is non-atomic!! + */ + +struct vaxque { /* queue format expected by VAX queue instructions */ + struct vaxque *vq_next; + struct vaxque *vq_prev; +}; + +insque(e, prev) + register struct vaxque *e, *prev; +{ + e->vq_prev = prev; + e->vq_next = prev->vq_next; + prev->vq_next->vq_prev = e; + prev->vq_next = e; +} diff --git a/lib/libcompat/4.3/lsearch.3 b/lib/libcompat/4.3/lsearch.3 new file mode 100644 index 0000000..d6abfca --- /dev/null +++ b/lib/libcompat/4.3/lsearch.3 @@ -0,0 +1,102 @@ +.\" Copyright (c) 1989, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)lsearch.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt LSEARCH 3 +.Os +.Sh NAME +.Nm lsearch , +.Nm lfind, +.Nd linear searching routines +.Sh SYNOPSIS +.Ft char * +.Fn lsearch "const void *key" "const void *base" "size_t *nelp" "size_t width" "int (*compar)(void *, void *)" +.Ft char * +.Fn lfind "const void *key" "const void *base" "size_t *nelp" "size_t width" "int (*compar)(void *, void *)" +.Sh DESCRIPTION +.Bf -symbolic +This interface was obsolete before it was written. +It is available from the compatibility library, libcompat. +.Ef +.Pp +The functions +.Fn lsearch , +and +.Fn lfind +provide basic linear searching functionality. +.Pp +.Fa Base +is the pointer to the beginning of an array. +The argument +.Fa nelp +is the current number of elements in the array, where each element +is +.Fa width +bytes long. +The +.Fa compar +function +is a comparison routine which is used to compare two elements. +It takes two arguments which point to the +.Fa key +object and to an array member, in that order, and must return an integer +less than, equivalent to, or greater than zero if the +.Fa key +object is considered, respectively, to be less than, equal to, or greater +than the array member. +.Pp +The +.Fn lsearch +and +.Fn lfind +functions +return a pointer into the array referenced by +.Fa base +where +.Fa key +is located. +If +.Fa key +does not exist, +.Fn lfind +will return a null pointer and +.Fn lsearch +will add it to the array. +When an element is added to the array by +.Fn lsearch +the location referenced by the argument +.Fa nelp +is incremented by one. +.Sh SEE ALSO +.Xr bsearch 3 , +.Xr db 3 diff --git a/lib/libcompat/4.3/lsearch.c b/lib/libcompat/4.3/lsearch.c new file mode 100644 index 0000000..baf90ed --- /dev/null +++ b/lib/libcompat/4.3/lsearch.c @@ -0,0 +1,92 @@ +/* + * Copyright (c) 1989, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Roger L. Snyder. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)lsearch.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +#include <sys/types.h> +#include <unistd.h> + +static char *linear_base(); + +char * +lsearch(key, base, nelp, width, compar) + char *key, *base; + u_int *nelp, width; + int (*compar)(); +{ + return(linear_base(key, base, nelp, width, compar, 1)); +} + +char * +lfind(key, base, nelp, width, compar) + char *key, *base; + u_int *nelp, width; + int (*compar)(); +{ + return(linear_base(key, base, nelp, width, compar, 0)); +} + +static char * +linear_base(key, base, nelp, width, compar, add_flag) + char *key, *base; + u_int *nelp, width; + int (*compar)(), add_flag; +{ + register char *element, *end; + + end = base + *nelp * width; + for (element = base; element < end; element += width) + if (!compar(element, key)) /* key found */ + return(element); + + if (!add_flag) /* key not found */ + return(NULL); + + /* + * The UNIX System User's Manual, 1986 edition claims that + * a NULL pointer is returned by lsearch with errno set + * appropriately, if there is not enough room in the table + * to add a new item. This can't be done as none of these + * routines have any method of determining the size of the + * table. This comment was isn't in the 1986-87 System V + * manual. + */ + ++*nelp; + bcopy(key, end, (int)width); + return(end); +} diff --git a/lib/libcompat/4.3/re_comp.3 b/lib/libcompat/4.3/re_comp.3 new file mode 100644 index 0000000..498e639 --- /dev/null +++ b/lib/libcompat/4.3/re_comp.3 @@ -0,0 +1,123 @@ +.\" Copyright (c) 1980, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)re_comp.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt RE_COMP 3 +.Os +.Sh NAME +.Nm re_comp , +.Nm re_exec +.Nd regular expression handler +.Sh SYNOPSIS +.Fd #include <unistd.h> +.Ft char * +.Fn re_comp "const char *s" +.Ft int +.Fn re_exec "const char *s" +.Sh DESCRIPTION +This interface is made obsolete by +.Xr regex 3 . +.Pp +The +.Fn re_comp +function +compiles a string into an internal form suitable for pattern matching. +The +.Fn re_exec +function +checks the argument string against the last string passed to +.Fn re_comp . +.Pp +The +.Fn re_comp +function +returns 0 if the string +.Fa s +was compiled successfully; otherwise a string containing an +error message is returned. If +.Fn re_comp +is passed 0 or a null string, it returns without changing the currently +compiled regular expression. +.Pp +The +.Fn re_exec +function +returns 1 if the string +.Fa s +matches the last compiled regular expression, 0 if the string +.Fa s +failed to match the last compiled regular expression, and \-1 if the compiled +regular expression was invalid (indicating an internal error). +.Pp +The strings passed to both +.Fn re_comp +and +.Fn re_exec +may have trailing or embedded newline characters; +they are terminated by +.Dv NUL Ns s. +The regular expressions recognized are described in the manual entry for +.Xr ed 1 , +given the above difference. +.Sh DIAGNOSTICS +The +.Fn re_exec +function +returns \-1 for an internal error. +.Pp +The +.Fn re_comp +function +returns one of the following strings if an error occurs: +.Bd -unfilled -offset indent +No previous regular expression, +Regular expression too long, +unmatched \e(, +missing ], +too many \e(\e) pairs, +unmatched \e). +.Ed +.Sh SEE ALSO +.Xr ed 1 , +.Xr ex 1 , +.Xr egrep 1 , +.Xr fgrep 1 , +.Xr grep 1 , +.Xr regex 3 +.Sh HISTORY +The +.Fn re_comp +and +.Fn re_exec +functions appeared in +.Bx 4.0 . diff --git a/lib/libcompat/4.3/remque.c b/lib/libcompat/4.3/remque.c new file mode 100644 index 0000000..39ebfe0 --- /dev/null +++ b/lib/libcompat/4.3/remque.c @@ -0,0 +1,54 @@ +/* + * Copyright (c) 1987, 1993 + * The Regents of the University of California. 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. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)remque.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +/* + * remque -- vax remque instruction + * + * NOTE: this implementation is non-atomic!! + */ + +struct vaxque { /* queue format expected by VAX queue instructions */ + struct vaxque *vq_next; + struct vaxque *vq_prev; +}; + +remque(e) + register struct vaxque *e; +{ + e->vq_prev->vq_next = e->vq_next; + e->vq_next->vq_prev = e->vq_prev; +} diff --git a/lib/libcompat/4.3/rexec.3 b/lib/libcompat/4.3/rexec.3 new file mode 100644 index 0000000..2bcb5be --- /dev/null +++ b/lib/libcompat/4.3/rexec.3 @@ -0,0 +1,122 @@ +.\" Copyright (c) 1983, 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)rexec.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt REXEC 3 +.Os BSD 4.2 +.Sh NAME +.Nm rexec +.Nd return stream to a remote command +.Sh SYNOPSIS +.Ft int +.Fn rexec ahost "int inport" "char *user" "char *passwd" "char *cmd" "int *fd2p" +.Sh DESCRIPTION +.Bf -symbolic +This interface is obsoleted by krcmd(3). +It is available from the compatibility library, libcompat. +.Ef +.Pp +The +.Fn rexec +function +looks up the host +.Fa *ahost +using +.Xr gethostbyname 3 , +returning \-1 if the host does not exist. +Otherwise +.Fa *ahost +is set to the standard name of the host. +If a username and password are both specified, then these +are used to authenticate to the foreign host; otherwise +the environment and then the user's +.Pa .netrc +file in his +home directory are searched for appropriate information. +If all this fails, the user is prompted for the information. +.Pp +The port +.Fa inport +specifies which well-known +.Tn DARPA +Internet port to use for +the connection; the call +.Ql getservbyname(\\*qexec\\*q, \\*qtcp\\*q) +(see +.Xr getservent 3 ) +will return a pointer to a structure, which contains the +necessary port. +The protocol for connection is described in detail in +.Xr rexecd 8 . +.Pp +If the connection succeeds, +a socket in the Internet domain of type +.Dv SOCK_STREAM +is returned to +the caller, and given to the remote command as +.Em stdin +and +.Em stdout . +If +.Fa fd2p +is non-zero, then an auxiliary channel to a control +process will be setup, and a descriptor for it will be placed +in +.Fa *fd2p . +The control process will return diagnostic +output from the command (unit 2) on this channel, and will also +accept bytes on this channel as being +.Tn UNIX +signal numbers, to be +forwarded to the process group of the command. The diagnostic +information returned does not include remote authorization failure, +as the secondary connection is set up after authorization has been +verified. +If +.Fa fd2p +is 0, then the +.Em stderr +(unit 2 of the remote +command) will be made the same as the +.Em stdout +and no +provision is made for sending arbitrary signals to the remote process, +although you may be able to get its attention by using out-of-band data. +.Sh SEE ALSO +.Xr rcmd 3 , +.Xr rexecd 8 +.Sh HISTORY +The +.Fn rexec +function appeared in +.Bx 4.2 . diff --git a/lib/libcompat/4.3/rexec.c b/lib/libcompat/4.3/rexec.c new file mode 100644 index 0000000..297e444 --- /dev/null +++ b/lib/libcompat/4.3/rexec.c @@ -0,0 +1,146 @@ +/* + * Copyright (c) 1980, 1993 + * The Regents of the University of California. 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. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)rexec.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +#include <sys/types.h> +#include <sys/socket.h> + +#include <netinet/in.h> + +#include <stdio.h> +#include <netdb.h> +#include <errno.h> + +extern errno; +char *index(); +int rexecoptions; +char *getpass(), *getlogin(); + +rexec(ahost, rport, name, pass, cmd, fd2p) + char **ahost; + int rport; + char *name, *pass, *cmd; + int *fd2p; +{ + struct sockaddr_in sin, sin2, from; + struct hostent *hp; + u_short port; + int s, timo = 1, s3; + char c; + + hp = gethostbyname(*ahost); + if (hp == 0) { + herror(*ahost); + return (-1); + } + *ahost = hp->h_name; + ruserpass(hp->h_name, &name, &pass); +retry: + s = socket(AF_INET, SOCK_STREAM, 0); + if (s < 0) { + perror("rexec: socket"); + return (-1); + } + sin.sin_family = hp->h_addrtype; + sin.sin_port = rport; + bcopy(hp->h_addr, (caddr_t)&sin.sin_addr, hp->h_length); + if (connect(s, (struct sockaddr *)&sin, sizeof(sin)) < 0) { + if (errno == ECONNREFUSED && timo <= 16) { + (void) close(s); + sleep(timo); + timo *= 2; + goto retry; + } + perror(hp->h_name); + return (-1); + } + if (fd2p == 0) { + (void) write(s, "", 1); + port = 0; + } else { + char num[8]; + int s2, sin2len; + + s2 = socket(AF_INET, SOCK_STREAM, 0); + if (s2 < 0) { + (void) close(s); + return (-1); + } + listen(s2, 1); + sin2len = sizeof (sin2); + if (getsockname(s2, (struct sockaddr *)&sin2, &sin2len) < 0 || + sin2len != sizeof (sin2)) { + perror("getsockname"); + (void) close(s2); + goto bad; + } + port = ntohs((u_short)sin2.sin_port); + (void) sprintf(num, "%u", port); + (void) write(s, num, strlen(num)+1); + { int len = sizeof (from); + s3 = accept(s2, (struct sockaddr *)&from, &len); + close(s2); + if (s3 < 0) { + perror("accept"); + port = 0; + goto bad; + } + } + *fd2p = s3; + } + (void) write(s, name, strlen(name) + 1); + /* should public key encypt the password here */ + (void) write(s, pass, strlen(pass) + 1); + (void) write(s, cmd, strlen(cmd) + 1); + if (read(s, &c, 1) != 1) { + perror(*ahost); + goto bad; + } + if (c != 0) { + while (read(s, &c, 1) == 1) { + (void) write(2, &c, 1); + if (c == '\n') + break; + } + goto bad; + } + return (s); +bad: + if (port) + (void) close(*fd2p); + (void) close(s); + return (-1); +} diff --git a/lib/libcompat/4.4/cuserid.c b/lib/libcompat/4.4/cuserid.c new file mode 100644 index 0000000..2fc5cc8 --- /dev/null +++ b/lib/libcompat/4.4/cuserid.c @@ -0,0 +1,59 @@ +/*- + * Copyright (c) 1992, 1993 + * The Regents of the University of California. 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. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#if defined(LIBC_SCCS) && !defined(lint) +static char sccsid[] = "@(#)cuserid.c 8.1 (Berkeley) 6/4/93"; +#endif /* LIBC_SCCS and not lint */ + +#include <pwd.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +char * +cuserid(s) + char *s; +{ + register struct passwd *pwd; + + if ((pwd = getpwuid(geteuid())) == NULL) { + if (s) + *s = '\0'; + return (s); + } + if (s) { + (void)strncpy(s, pwd->pw_name, L_cuserid); + return (s); + } + return (pwd->pw_name); +} diff --git a/lib/libcompat/Makefile b/lib/libcompat/Makefile new file mode 100644 index 0000000..bd2aaf9 --- /dev/null +++ b/lib/libcompat/Makefile @@ -0,0 +1,58 @@ +# @(#)Makefile 8.1 (Berkeley) 6/4/93 + +LIB=compat +CFLAGS+=-DLIBC_SCCS -DSYSLIBC_SCCS +AINC= -I${.CURDIR}/../libc/${MACHINE} + +.PATH: ${.CURDIR}/4.1/${MACHINE} ${.CURDIR}/4.1 \ + ${.CURDIR}/4.3/${MACHINE} ${.CURDIR}/4.3 \ + ${.CURDIR}/4.4/${MACHINE} ${.CURDIR}/4.4 \ + ${.CURDIR}/regexp + +# compat 4.1 sources +SRCS= ftime.c getpw.c gtty.c stty.c tell.c vlimit.c vtimes.c + +.if (${MACHINE} == "vax") +SRCS+= reset.s +.endif + +MAN3+= ftime.0 getpw.0 stty.0 vlimit.0 vtimes.0 + +MLINKS+=stty.3 gtty.3 + +# compat 4.3 sources +SRCS+= cfree.c ecvt.c gcvt.c lsearch.c regex.c rexec.c sibuf.c sobuf.c \ + strout.c + +.if (${MACHINE} == "hp300" || ${MACHINE} == "luna68k") +SRCS+= insque.s remque.s +.elif (${MACHINE} == "i386") +SRCS+= insque.c remque.c +.elif (${MACHINE} == "mips") +SRCS+= insque.c remque.c +.elif (${MACHINE} == "sparc") +SRCS+= insque.c remque.c +.elif (${MACHINE} == "tahoe") +SRCS+= nargs.s insque.s remque.s +.elif (${MACHINE} == "vax") +SRCS+= nargs.s insque.s remque.s +.endif + +MAN3+= ecvt.0 insque.0 lsearch.0 re_comp.0 rexec.0 + +MLINKS+=ecvt.3 fcvt.3 ecvt.3 gcvt.3 +MLINKS+=insque.3 remque.3 +MLINKS+=re_comp.3 re_exec.3 + +# compat 4.4 sources +SRCS+= cuserid.c + +# regexp sources +SRCS+= regerror.c regexp.c regsub.c + +MAN3+= regexp.0 + +MLINKS+=regexp.3 regcomp.3 regexp.3 regexec.3 regexp.3 regsub.3 \ + regexp.3 regerror.3 + +.include <bsd.lib.mk> diff --git a/lib/libcompat/regexp/COPYRIGHT b/lib/libcompat/regexp/COPYRIGHT new file mode 100644 index 0000000..48b3f43 --- /dev/null +++ b/lib/libcompat/regexp/COPYRIGHT @@ -0,0 +1,22 @@ +This entire subtree is copyright the University of Toronto. +The following copyright notice applies to all files found here. None of +these files contain AT&T proprietary source code. +_____________________________________________________________________________ + + Copyright (c) 1986 by University of Toronto. + Written by Henry Spencer. Not derived from licensed software. + + Permission is granted to anyone to use this software for any + purpose on any computer system, and to redistribute it freely, + subject to the following restrictions: + + 1. The author is not responsible for the consequences of use of + this software, no matter how awful, even if they arise + from defects in it. + + 2. The origin of this software must not be misrepresented, either + by explicit claim or by omission. + + 3. Altered versions must be plainly marked as such, and must not + be misrepresented as being the original software. + diff --git a/lib/libcompat/regexp/README b/lib/libcompat/regexp/README new file mode 100644 index 0000000..37d6f51 --- /dev/null +++ b/lib/libcompat/regexp/README @@ -0,0 +1,84 @@ +This is a nearly-public-domain reimplementation of the V8 regexp(3) package. +It gives C programs the ability to use egrep-style regular expressions, and +does it in a much cleaner fashion than the analogous routines in SysV. + + Copyright (c) 1986 by University of Toronto. + Written by Henry Spencer. Not derived from licensed software. + + Permission is granted to anyone to use this software for any + purpose on any computer system, and to redistribute it freely, + subject to the following restrictions: + + 1. The author is not responsible for the consequences of use of + this software, no matter how awful, even if they arise + from defects in it. + + 2. The origin of this software must not be misrepresented, either + by explicit claim or by omission. + + 3. Altered versions must be plainly marked as such, and must not + be misrepresented as being the original software. + +Barring a couple of small items in the BUGS list, this implementation is +believed 100% compatible with V8. It should even be binary-compatible, +sort of, since the only fields in a "struct regexp" that other people have +any business touching are declared in exactly the same way at the same +location in the struct (the beginning). + +This implementation is *NOT* AT&T/Bell code, and is not derived from licensed +software. Even though U of T is a V8 licensee. This software is based on +a V8 manual page sent to me by Dennis Ritchie (the manual page enclosed +here is a complete rewrite and hence is not covered by AT&T copyright). +The software was nearly complete at the time of arrival of our V8 tape. +I haven't even looked at V8 yet, although a friend elsewhere at U of T has +been kind enough to run a few test programs using the V8 regexp(3) to resolve +a few fine points. I admit to some familiarity with regular-expression +implementations of the past, but the only one that this code traces any +ancestry to is the one published in Kernighan & Plauger (from which this +one draws ideas but not code). + +Simplistically: put this stuff into a source directory, copy regexp.h into +/usr/include, inspect Makefile for compilation options that need changing +to suit your local environment, and then do "make r". This compiles the +regexp(3) functions, compiles a test program, and runs a large set of +regression tests. If there are no complaints, then put regexp.o, regsub.o, +and regerror.o into your C library, and regexp.3 into your manual-pages +directory. + +Note that if you don't put regexp.h into /usr/include *before* compiling, +you'll have to add "-I." to CFLAGS before compiling. + +The files are: + +Makefile instructions to make everything +regexp.3 manual page +regexp.h header file, for /usr/include +regexp.c source for regcomp() and regexec() +regsub.c source for regsub() +regerror.c source for default regerror() +regmagic.h internal header file +try.c source for test program +timer.c source for timing program +tests test list for try and timer + +This implementation uses nondeterministic automata rather than the +deterministic ones found in some other implementations, which makes it +simpler, smaller, and faster at compiling regular expressions, but slower +at executing them. In theory, anyway. This implementation does employ +some special-case optimizations to make the simpler cases (which do make +up the bulk of regular expressions actually used) run quickly. In general, +if you want blazing speed you're in the wrong place. Replacing the insides +of egrep with this stuff is probably a mistake; if you want your own egrep +you're going to have to do a lot more work. But if you want to use regular +expressions a little bit in something else, you're in luck. Note that many +existing text editors use nondeterministic regular-expression implementations, +so you're in good company. + +This stuff should be pretty portable, given appropriate option settings. +If your chars have less than 8 bits, you're going to have to change the +internal representation of the automaton, although knowledge of the details +of this is fairly localized. There are no "reserved" char values except for +NUL, and no special significance is attached to the top bit of chars. +The string(3) functions are used a fair bit, on the grounds that they are +probably faster than coding the operations in line. Some attempts at code +tuning have been made, but this is invariably a bit machine-specific. diff --git a/lib/libcompat/regexp/regerror.c b/lib/libcompat/regexp/regerror.c new file mode 100644 index 0000000..6d0077d --- /dev/null +++ b/lib/libcompat/regexp/regerror.c @@ -0,0 +1,18 @@ +#include <regexp.h> +#include <stdio.h> + +void +regerror(s) +const char *s; +{ +#ifdef ERRAVAIL + error("regexp: %s", s); +#else +/* + fprintf(stderr, "regexp(3): %s\n", s); + exit(1); +*/ + return; /* let std. egrep handle errors */ +#endif + /* NOTREACHED */ +} diff --git a/lib/libcompat/regexp/regexp.3 b/lib/libcompat/regexp/regexp.3 new file mode 100644 index 0000000..0986d4e --- /dev/null +++ b/lib/libcompat/regexp/regexp.3 @@ -0,0 +1,318 @@ +.\" Copyright (c) 1991, 1993 +.\" The Regents of the University of California. 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. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)regexp.3 8.1 (Berkeley) 6/4/93 +.\" +.Dd June 4, 1993 +.Dt REGEXP 3 +.Os +.Sh NAME +.Nm regcomp , +.Nm regexec , +.Nm regsub , +.Nm regerror +.Nd regular expression handlers +.Sh SYNOPSIS +.Fd #include <regexp.h> +.Ft regexp * +.Fn regcomp "const char *exp" +.Ft int +.Fn regexec "const regexp *prog" "const char *string" +.Ft void +.Fn regsub "const regexp *prog" "const char *source" "char *dest" +.Sh DESCRIPTION +This interface is made obsolete by +.Xr regex 3 . +.Pp +The +.Fn regcomp , +.Fn regexec , +.Fn regsub , +and +.Fn regerror +functions +implement +.Xr egrep 1 Ns -style +regular expressions and supporting facilities. +.Pp +The +.Fn regcomp +function +compiles a regular expression into a structure of type +.Xr regexp , +and returns a pointer to it. +The space has been allocated using +.Xr malloc 3 +and may be released by +.Xr free . +.Pp +The +.Fn regexec +function +matches a +.Dv NUL Ns -terminated +.Fa string +against the compiled regular expression +in +.Fa prog . +It returns 1 for success and 0 for failure, and adjusts the contents of +.Fa prog Ns 's +.Em startp +and +.Em endp +(see below) accordingly. +.Pp +The members of a +.Xr regexp +structure include at least the following (not necessarily in order): +.Bd -literal -offset indent +char *startp[NSUBEXP]; +char *endp[NSUBEXP]; +.Ed +.Pp +where +.Dv NSUBEXP +is defined (as 10) in the header file. +Once a successful +.Fn regexec +has been done using the +.Fn regexp , +each +.Em startp Ns - Em endp +pair describes one substring +within the +.Fa string , +with the +.Em startp +pointing to the first character of the substring and +the +.Em endp +pointing to the first character following the substring. +The 0th substring is the substring of +.Fa string +that matched the whole +regular expression. +The others are those substrings that matched parenthesized expressions +within the regular expression, with parenthesized expressions numbered +in left-to-right order of their opening parentheses. +.Pp +The +.Fn regsub +function +copies +.Fa source +to +.Fa dest , +making substitutions according to the +most recent +.Fn regexec +performed using +.Fa prog . +Each instance of `&' in +.Fa source +is replaced by the substring +indicated by +.Em startp Ns Bq +and +.Em endp Ns Bq . +Each instance of +.Sq \e Ns Em n , +where +.Em n +is a digit, is replaced by +the substring indicated by +.Em startp Ns Bq Em n +and +.Em endp Ns Bq Em n . +To get a literal `&' or +.Sq \e Ns Em n +into +.Fa dest , +prefix it with `\e'; +to get a literal `\e' preceding `&' or +.Sq \e Ns Em n , +prefix it with +another `\e'. +.Pp +The +.Fn regerror +function +is called whenever an error is detected in +.Fn regcomp , +.Fn regexec , +or +.Fn regsub . +The default +.Fn regerror +writes the string +.Fa msg , +with a suitable indicator of origin, +on the standard +error output +and invokes +.Xr exit 2 . +The +.Fn regerror +function +can be replaced by the user if other actions are desirable. +.Sh REGULAR EXPRESSION SYNTAX +A regular expression is zero or more +.Em branches , +separated by `|'. +It matches anything that matches one of the branches. +.Pp +A branch is zero or more +.Em pieces , +concatenated. +It matches a match for the first, followed by a match for the second, etc. +.Pp +A piece is an +.Em atom +possibly followed by `*', `+', or `?'. +An atom followed by `*' matches a sequence of 0 or more matches of the atom. +An atom followed by `+' matches a sequence of 1 or more matches of the atom. +An atom followed by `?' matches a match of the atom, or the null string. +.Pp +An atom is a regular expression in parentheses (matching a match for the +regular expression), a +.Em range +(see below), `.' +(matching any single character), `^' (matching the null string at the +beginning of the input string), `$' (matching the null string at the +end of the input string), a `\e' followed by a single character (matching +that character), or a single character with no other significance +(matching that character). +.Pp +A +.Em range +is a sequence of characters enclosed in `[]'. +It normally matches any single character from the sequence. +If the sequence begins with `^', +it matches any single character +.Em not +from the rest of the sequence. +If two characters in the sequence are separated by `\-', this is shorthand +for the full list of +.Tn ASCII +characters between them +(e.g. `[0-9]' matches any decimal digit). +To include a literal `]' in the sequence, make it the first character +(following a possible `^'). +To include a literal `\-', make it the first or last character. +.Sh AMBIGUITY +If a regular expression could match two different parts of the input string, +it will match the one which begins earliest. +If both begin in the same place but match different lengths, or match +the same length in different ways, life gets messier, as follows. +.Pp +In general, the possibilities in a list of branches are considered in +left-to-right order, the possibilities for `*', `+', and `?' are +considered longest-first, nested constructs are considered from the +outermost in, and concatenated constructs are considered leftmost-first. +The match that will be chosen is the one that uses the earliest +possibility in the first choice that has to be made. +If there is more than one choice, the next will be made in the same manner +(earliest possibility) subject to the decision on the first choice. +And so forth. +.Pp +For example, +.Sq Li (ab|a)b*c +could match +`abc' in one of two ways. +The first choice is between `ab' and `a'; since `ab' is earlier, and does +lead to a successful overall match, it is chosen. +Since the `b' is already spoken for, +the `b*' must match its last possibility\(emthe empty string\(emsince +it must respect the earlier choice. +.Pp +In the particular case where no `|'s are present and there is only one +`*', `+', or `?', the net effect is that the longest possible +match will be chosen. +So +.Sq Li ab* , +presented with `xabbbby', will match `abbbb'. +Note that if +.Sq Li ab* , +is tried against `xabyabbbz', it +will match `ab' just after `x', due to the begins-earliest rule. +(In effect, the decision on where to start the match is the first choice +to be made, hence subsequent choices must respect it even if this leads them +to less-preferred alternatives.) +.Sh RETURN VALUES +The +.Fn regcomp +function +returns +.Dv NULL +for a failure +.Pf ( Fn regerror +permitting), +where failures are syntax errors, exceeding implementation limits, +or applying `+' or `*' to a possibly-null operand. +.Sh SEE ALSO +.Xr ed 1 , +.Xr ex 1 , +.Xr expr 1 , +.Xr egrep 1 , +.Xr fgrep 1 , +.Xr grep 1 , +.Xr regex 3 +.Sh HISTORY +Both code and manual page for +.Fn regcomp , +.Fn regexec , +.Fn regsub , +and +.Fn regerror +were written at the University of Toronto +and appeared in +.Bx 4.3 tahoe . +They are intended to be compatible with the Bell V8 +.Xr regexp 3 , +but are not derived from Bell code. +.Sh BUGS +Empty branches and empty regular expressions are not portable to V8. +.Pp +The restriction against +applying `*' or `+' to a possibly-null operand is an artifact of the +simplistic implementation. +.Pp +Does not support +.Xr egrep Ns 's +newline-separated branches; +neither does the V8 +.Xr regexp 3 , +though. +.Pp +Due to emphasis on +compactness and simplicity, +it's not strikingly fast. +It does give special attention to handling simple cases quickly. diff --git a/lib/libcompat/regexp/regexp.c b/lib/libcompat/regexp/regexp.c new file mode 100644 index 0000000..0084295 --- /dev/null +++ b/lib/libcompat/regexp/regexp.c @@ -0,0 +1,1320 @@ +/* + * regcomp and regexec -- regsub and regerror are elsewhere + * + * Copyright (c) 1986 by University of Toronto. + * Written by Henry Spencer. Not derived from licensed software. + * + * Permission is granted to anyone to use this software for any + * purpose on any computer system, and to redistribute it freely, + * subject to the following restrictions: + * + * 1. The author is not responsible for the consequences of use of + * this software, no matter how awful, even if they arise + * from defects in it. + * + * 2. The origin of this software must not be misrepresented, either + * by explicit claim or by omission. + * + * 3. Altered versions must be plainly marked as such, and must not + * be misrepresented as being the original software. + *** THIS IS AN ALTERED VERSION. It was altered by John Gilmore, + *** hoptoad!gnu, on 27 Dec 1986, to add \n as an alternative to | + *** to assist in implementing egrep. + *** THIS IS AN ALTERED VERSION. It was altered by John Gilmore, + *** hoptoad!gnu, on 27 Dec 1986, to add \< and \> for word-matching + *** as in BSD grep and ex. + *** THIS IS AN ALTERED VERSION. It was altered by John Gilmore, + *** hoptoad!gnu, on 28 Dec 1986, to optimize characters quoted with \. + *** THIS IS AN ALTERED VERSION. It was altered by James A. Woods, + *** ames!jaw, on 19 June 1987, to quash a regcomp() redundancy. + * + * Beware that some of this code is subtly aware of the way operator + * precedence is structured in regular expressions. Serious changes in + * regular-expression syntax might require a total rethink. + */ +#include <regexp.h> +#include <stdio.h> +#include <ctype.h> +#include <stdlib.h> +#include <string.h> +#include "regmagic.h" + +/* + * The "internal use only" fields in regexp.h are present to pass info from + * compile to execute that permits the execute phase to run lots faster on + * simple cases. They are: + * + * regstart char that must begin a match; '\0' if none obvious + * reganch is the match anchored (at beginning-of-line only)? + * regmust string (pointer into program) that match must include, or NULL + * regmlen length of regmust string + * + * Regstart and reganch permit very fast decisions on suitable starting points + * for a match, cutting down the work a lot. Regmust permits fast rejection + * of lines that cannot possibly match. The regmust tests are costly enough + * that regcomp() supplies a regmust only if the r.e. contains something + * potentially expensive (at present, the only such thing detected is * or + + * at the start of the r.e., which can involve a lot of backup). Regmlen is + * supplied because the test in regexec() needs it and regcomp() is computing + * it anyway. + */ + +/* + * Structure for regexp "program". This is essentially a linear encoding + * of a nondeterministic finite-state machine (aka syntax charts or + * "railroad normal form" in parsing technology). Each node is an opcode + * plus a "next" pointer, possibly plus an operand. "Next" pointers of + * all nodes except BRANCH implement concatenation; a "next" pointer with + * a BRANCH on both ends of it is connecting two alternatives. (Here we + * have one of the subtle syntax dependencies: an individual BRANCH (as + * opposed to a collection of them) is never concatenated with anything + * because of operator precedence.) The operand of some types of node is + * a literal string; for others, it is a node leading into a sub-FSM. In + * particular, the operand of a BRANCH node is the first node of the branch. + * (NB this is *not* a tree structure: the tail of the branch connects + * to the thing following the set of BRANCHes.) The opcodes are: + */ + +/* definition number opnd? meaning */ +#define END 0 /* no End of program. */ +#define BOL 1 /* no Match "" at beginning of line. */ +#define EOL 2 /* no Match "" at end of line. */ +#define ANY 3 /* no Match any one character. */ +#define ANYOF 4 /* str Match any character in this string. */ +#define ANYBUT 5 /* str Match any character not in this string. */ +#define BRANCH 6 /* node Match this alternative, or the next... */ +#define BACK 7 /* no Match "", "next" ptr points backward. */ +#define EXACTLY 8 /* str Match this string. */ +#define NOTHING 9 /* no Match empty string. */ +#define STAR 10 /* node Match this (simple) thing 0 or more times. */ +#define PLUS 11 /* node Match this (simple) thing 1 or more times. */ +#define WORDA 12 /* no Match "" at wordchar, where prev is nonword */ +#define WORDZ 13 /* no Match "" at nonwordchar, where prev is word */ +#define OPEN 20 /* no Mark this point in input as start of #n. */ + /* OPEN+1 is number 1, etc. */ +#define CLOSE 30 /* no Analogous to OPEN. */ + +/* + * Opcode notes: + * + * BRANCH The set of branches constituting a single choice are hooked + * together with their "next" pointers, since precedence prevents + * anything being concatenated to any individual branch. The + * "next" pointer of the last BRANCH in a choice points to the + * thing following the whole choice. This is also where the + * final "next" pointer of each individual branch points; each + * branch starts with the operand node of a BRANCH node. + * + * BACK Normal "next" pointers all implicitly point forward; BACK + * exists to make loop structures possible. + * + * STAR,PLUS '?', and complex '*' and '+', are implemented as circular + * BRANCH structures using BACK. Simple cases (one character + * per match) are implemented with STAR and PLUS for speed + * and to minimize recursive plunges. + * + * OPEN,CLOSE ...are numbered at compile time. + */ + +/* + * A node is one char of opcode followed by two chars of "next" pointer. + * "Next" pointers are stored as two 8-bit pieces, high order first. The + * value is a positive offset from the opcode of the node containing it. + * An operand, if any, simply follows the node. (Note that much of the + * code generation knows about this implicit relationship.) + * + * Using two bytes for the "next" pointer is vast overkill for most things, + * but allows patterns to get big without disasters. + */ +#define OP(p) (*(p)) +#define NEXT(p) (((*((p)+1)&0377)<<8) + (*((p)+2)&0377)) +#define OPERAND(p) ((p) + 3) + +/* + * See regmagic.h for one further detail of program structure. + */ + + +/* + * Utility definitions. + */ +#ifndef CHARBITS +#define UCHARAT(p) ((int)*(unsigned char *)(p)) +#else +#define UCHARAT(p) ((int)*(p)&CHARBITS) +#endif + +#define FAIL(m) { regerror(m); return(NULL); } +#define ISMULT(c) ((c) == '*' || (c) == '+' || (c) == '?') + +/* + * Flags to be passed up and down. + */ +#define HASWIDTH 01 /* Known never to match null string. */ +#define SIMPLE 02 /* Simple enough to be STAR/PLUS operand. */ +#define SPSTART 04 /* Starts with * or +. */ +#define WORST 0 /* Worst case. */ + +/* + * Global work variables for regcomp(). + */ +static char *regparse; /* Input-scan pointer. */ +static int regnpar; /* () count. */ +static char regdummy; +static char *regcode; /* Code-emit pointer; ®dummy = don't. */ +static long regsize; /* Code size. */ + +/* + * Forward declarations for regcomp()'s friends. + */ +#ifndef STATIC +#define STATIC static +#endif +STATIC char *reg(); +STATIC char *regbranch(); +STATIC char *regpiece(); +STATIC char *regatom(); +STATIC char *regnode(); +STATIC char *regnext(); +STATIC void regc(); +STATIC void reginsert(); +STATIC void regtail(); +STATIC void regoptail(); +#ifdef STRCSPN +STATIC int strcspn(); +#endif + +/* + - regcomp - compile a regular expression into internal code + * + * We can't allocate space until we know how big the compiled form will be, + * but we can't compile it (and thus know how big it is) until we've got a + * place to put the code. So we cheat: we compile it twice, once with code + * generation turned off and size counting turned on, and once "for real". + * This also means that we don't allocate space until we are sure that the + * thing really will compile successfully, and we never have to move the + * code and thus invalidate pointers into it. (Note that it has to be in + * one piece because free() must be able to free it all.) + * + * Beware that the optimization-preparation code in here knows about some + * of the structure of the compiled regexp. + */ +regexp * +regcomp(exp) +const char *exp; +{ + register regexp *r; + register char *scan; + register char *longest; + register int len; + int flags; + + if (exp == NULL) + FAIL("NULL argument"); + + /* First pass: determine size, legality. */ +#ifdef notdef + if (exp[0] == '.' && exp[1] == '*') exp += 2; /* aid grep */ +#endif + regparse = (char *)exp; + regnpar = 1; + regsize = 0L; + regcode = ®dummy; + regc(MAGIC); + if (reg(0, &flags) == NULL) + return(NULL); + + /* Small enough for pointer-storage convention? */ + if (regsize >= 32767L) /* Probably could be 65535L. */ + FAIL("regexp too big"); + + /* Allocate space. */ + r = (regexp *)malloc(sizeof(regexp) + (unsigned)regsize); + if (r == NULL) + FAIL("out of space"); + + /* Second pass: emit code. */ + regparse = (char *)exp; + regnpar = 1; + regcode = r->program; + regc(MAGIC); + if (reg(0, &flags) == NULL) + return(NULL); + + /* Dig out information for optimizations. */ + r->regstart = '\0'; /* Worst-case defaults. */ + r->reganch = 0; + r->regmust = NULL; + r->regmlen = 0; + scan = r->program+1; /* First BRANCH. */ + if (OP(regnext(scan)) == END) { /* Only one top-level choice. */ + scan = OPERAND(scan); + + /* Starting-point info. */ + if (OP(scan) == EXACTLY) + r->regstart = *OPERAND(scan); + else if (OP(scan) == BOL) + r->reganch++; + + /* + * If there's something expensive in the r.e., find the + * longest literal string that must appear and make it the + * regmust. Resolve ties in favor of later strings, since + * the regstart check works with the beginning of the r.e. + * and avoiding duplication strengthens checking. Not a + * strong reason, but sufficient in the absence of others. + */ + if (flags&SPSTART) { + longest = NULL; + len = 0; + for (; scan != NULL; scan = regnext(scan)) + if (OP(scan) == EXACTLY && strlen(OPERAND(scan)) >= len) { + longest = OPERAND(scan); + len = strlen(OPERAND(scan)); + } + r->regmust = longest; + r->regmlen = len; + } + } + + return(r); +} + +/* + - reg - regular expression, i.e. main body or parenthesized thing + * + * Caller must absorb opening parenthesis. + * + * Combining parenthesis handling with the base level of regular expression + * is a trifle forced, but the need to tie the tails of the branches to what + * follows makes it hard to avoid. + */ +static char * +reg(paren, flagp) +int paren; /* Parenthesized? */ +int *flagp; +{ + register char *ret; + register char *br; + register char *ender; + register int parno; + int flags; + + *flagp = HASWIDTH; /* Tentatively. */ + + /* Make an OPEN node, if parenthesized. */ + if (paren) { + if (regnpar >= NSUBEXP) + FAIL("too many ()"); + parno = regnpar; + regnpar++; + ret = regnode(OPEN+parno); + } else + ret = NULL; + + /* Pick up the branches, linking them together. */ + br = regbranch(&flags); + if (br == NULL) + return(NULL); + if (ret != NULL) + regtail(ret, br); /* OPEN -> first. */ + else + ret = br; + if (!(flags&HASWIDTH)) + *flagp &= ~HASWIDTH; + *flagp |= flags&SPSTART; + while (*regparse == '|' || *regparse == '\n') { + regparse++; + br = regbranch(&flags); + if (br == NULL) + return(NULL); + regtail(ret, br); /* BRANCH -> BRANCH. */ + if (!(flags&HASWIDTH)) + *flagp &= ~HASWIDTH; + *flagp |= flags&SPSTART; + } + + /* Make a closing node, and hook it on the end. */ + ender = regnode((paren) ? CLOSE+parno : END); + regtail(ret, ender); + + /* Hook the tails of the branches to the closing node. */ + for (br = ret; br != NULL; br = regnext(br)) + regoptail(br, ender); + + /* Check for proper termination. */ + if (paren && *regparse++ != ')') { + FAIL("unmatched ()"); + } else if (!paren && *regparse != '\0') { + if (*regparse == ')') { + FAIL("unmatched ()"); + } else + FAIL("junk on end"); /* "Can't happen". */ + /* NOTREACHED */ + } + + return(ret); +} + +/* + - regbranch - one alternative of an | operator + * + * Implements the concatenation operator. + */ +static char * +regbranch(flagp) +int *flagp; +{ + register char *ret; + register char *chain; + register char *latest; + int flags; + + *flagp = WORST; /* Tentatively. */ + + ret = regnode(BRANCH); + chain = NULL; + while (*regparse != '\0' && *regparse != ')' && + *regparse != '\n' && *regparse != '|') { + latest = regpiece(&flags); + if (latest == NULL) + return(NULL); + *flagp |= flags&HASWIDTH; + if (chain == NULL) /* First piece. */ + *flagp |= flags&SPSTART; + else + regtail(chain, latest); + chain = latest; + } + if (chain == NULL) /* Loop ran zero times. */ + (void) regnode(NOTHING); + + return(ret); +} + +/* + - regpiece - something followed by possible [*+?] + * + * Note that the branching code sequences used for ? and the general cases + * of * and + are somewhat optimized: they use the same NOTHING node as + * both the endmarker for their branch list and the body of the last branch. + * It might seem that this node could be dispensed with entirely, but the + * endmarker role is not redundant. + */ +static char * +regpiece(flagp) +int *flagp; +{ + register char *ret; + register char op; + register char *next; + int flags; + + ret = regatom(&flags); + if (ret == NULL) + return(NULL); + + op = *regparse; + if (!ISMULT(op)) { + *flagp = flags; + return(ret); + } + + if (!(flags&HASWIDTH) && op != '?') + FAIL("*+ operand could be empty"); + *flagp = (op != '+') ? (WORST|SPSTART) : (WORST|HASWIDTH); + + if (op == '*' && (flags&SIMPLE)) + reginsert(STAR, ret); + else if (op == '*') { + /* Emit x* as (x&|), where & means "self". */ + reginsert(BRANCH, ret); /* Either x */ + regoptail(ret, regnode(BACK)); /* and loop */ + regoptail(ret, ret); /* back */ + regtail(ret, regnode(BRANCH)); /* or */ + regtail(ret, regnode(NOTHING)); /* null. */ + } else if (op == '+' && (flags&SIMPLE)) + reginsert(PLUS, ret); + else if (op == '+') { + /* Emit x+ as x(&|), where & means "self". */ + next = regnode(BRANCH); /* Either */ + regtail(ret, next); + regtail(regnode(BACK), ret); /* loop back */ + regtail(next, regnode(BRANCH)); /* or */ + regtail(ret, regnode(NOTHING)); /* null. */ + } else if (op == '?') { + /* Emit x? as (x|) */ + reginsert(BRANCH, ret); /* Either x */ + regtail(ret, regnode(BRANCH)); /* or */ + next = regnode(NOTHING); /* null. */ + regtail(ret, next); + regoptail(ret, next); + } + regparse++; + if (ISMULT(*regparse)) + FAIL("nested *?+"); + + return(ret); +} + +/* + - regatom - the lowest level + * + * Optimization: gobbles an entire sequence of ordinary characters so that + * it can turn them into a single node, which is smaller to store and + * faster to run. Backslashed characters are exceptions, each becoming a + * separate node; the code is simpler that way and it's not worth fixing. + */ +static char * +regatom(flagp) +int *flagp; +{ + register char *ret; + int flags; + + *flagp = WORST; /* Tentatively. */ + + switch (*regparse++) { + /* FIXME: these chars only have meaning at beg/end of pat? */ + case '^': + ret = regnode(BOL); + break; + case '$': + ret = regnode(EOL); + break; + case '.': + ret = regnode(ANY); + *flagp |= HASWIDTH|SIMPLE; + break; + case '[': { + register int class; + register int classend; + + if (*regparse == '^') { /* Complement of range. */ + ret = regnode(ANYBUT); + regparse++; + } else + ret = regnode(ANYOF); + if (*regparse == ']' || *regparse == '-') + regc(*regparse++); + while (*regparse != '\0' && *regparse != ']') { + if (*regparse == '-') { + regparse++; + if (*regparse == ']' || *regparse == '\0') + regc('-'); + else { + class = UCHARAT(regparse-2)+1; + classend = UCHARAT(regparse); + if (class > classend+1) + FAIL("invalid [] range"); + for (; class <= classend; class++) + regc(class); + regparse++; + } + } else + regc(*regparse++); + } + regc('\0'); + if (*regparse != ']') + FAIL("unmatched []"); + regparse++; + *flagp |= HASWIDTH|SIMPLE; + } + break; + case '(': + ret = reg(1, &flags); + if (ret == NULL) + return(NULL); + *flagp |= flags&(HASWIDTH|SPSTART); + break; + case '\0': + case '|': + case '\n': + case ')': + FAIL("internal urp"); /* Supposed to be caught earlier. */ + break; + case '?': + case '+': + case '*': + FAIL("?+* follows nothing"); + break; + case '\\': + switch (*regparse++) { + case '\0': + FAIL("trailing \\"); + break; + case '<': + ret = regnode(WORDA); + break; + case '>': + ret = regnode(WORDZ); + break; + /* FIXME: Someday handle \1, \2, ... */ + default: + /* Handle general quoted chars in exact-match routine */ + goto de_fault; + } + break; + de_fault: + default: + /* + * Encode a string of characters to be matched exactly. + * + * This is a bit tricky due to quoted chars and due to + * '*', '+', and '?' taking the SINGLE char previous + * as their operand. + * + * On entry, the char at regparse[-1] is going to go + * into the string, no matter what it is. (It could be + * following a \ if we are entered from the '\' case.) + * + * Basic idea is to pick up a good char in ch and + * examine the next char. If it's *+? then we twiddle. + * If it's \ then we frozzle. If it's other magic char + * we push ch and terminate the string. If none of the + * above, we push ch on the string and go around again. + * + * regprev is used to remember where "the current char" + * starts in the string, if due to a *+? we need to back + * up and put the current char in a separate, 1-char, string. + * When regprev is NULL, ch is the only char in the + * string; this is used in *+? handling, and in setting + * flags |= SIMPLE at the end. + */ + { + char *regprev; + register char ch; + + regparse--; /* Look at cur char */ + ret = regnode(EXACTLY); + for ( regprev = 0 ; ; ) { + ch = *regparse++; /* Get current char */ + switch (*regparse) { /* look at next one */ + + default: + regc(ch); /* Add cur to string */ + break; + + case '.': case '[': case '(': + case ')': case '|': case '\n': + case '$': case '^': + case '\0': + /* FIXME, $ and ^ should not always be magic */ + magic: + regc(ch); /* dump cur char */ + goto done; /* and we are done */ + + case '?': case '+': case '*': + if (!regprev) /* If just ch in str, */ + goto magic; /* use it */ + /* End mult-char string one early */ + regparse = regprev; /* Back up parse */ + goto done; + + case '\\': + regc(ch); /* Cur char OK */ + switch (regparse[1]){ /* Look after \ */ + case '\0': + case '<': + case '>': + /* FIXME: Someday handle \1, \2, ... */ + goto done; /* Not quoted */ + default: + /* Backup point is \, scan * point is after it. */ + regprev = regparse; + regparse++; + continue; /* NOT break; */ + } + } + regprev = regparse; /* Set backup point */ + } + done: + regc('\0'); + *flagp |= HASWIDTH; + if (!regprev) /* One char? */ + *flagp |= SIMPLE; + } + break; + } + + return(ret); +} + +/* + - regnode - emit a node + */ +static char * /* Location. */ +regnode(op) +char op; +{ + register char *ret; + register char *ptr; + + ret = regcode; + if (ret == ®dummy) { + regsize += 3; + return(ret); + } + + ptr = ret; + *ptr++ = op; + *ptr++ = '\0'; /* Null "next" pointer. */ + *ptr++ = '\0'; + regcode = ptr; + + return(ret); +} + +/* + - regc - emit (if appropriate) a byte of code + */ +static void +regc(b) +char b; +{ + if (regcode != ®dummy) + *regcode++ = b; + else + regsize++; +} + +/* + - reginsert - insert an operator in front of already-emitted operand + * + * Means relocating the operand. + */ +static void +reginsert(op, opnd) +char op; +char *opnd; +{ + register char *src; + register char *dst; + register char *place; + + if (regcode == ®dummy) { + regsize += 3; + return; + } + + src = regcode; + regcode += 3; + dst = regcode; + while (src > opnd) + *--dst = *--src; + + place = opnd; /* Op node, where operand used to be. */ + *place++ = op; + *place++ = '\0'; + *place++ = '\0'; +} + +/* + - regtail - set the next-pointer at the end of a node chain + */ +static void +regtail(p, val) +char *p; +char *val; +{ + register char *scan; + register char *temp; + register int offset; + + if (p == ®dummy) + return; + + /* Find last node. */ + scan = p; + for (;;) { + temp = regnext(scan); + if (temp == NULL) + break; + scan = temp; + } + + if (OP(scan) == BACK) + offset = scan - val; + else + offset = val - scan; + *(scan+1) = (offset>>8)&0377; + *(scan+2) = offset&0377; +} + +/* + - regoptail - regtail on operand of first argument; nop if operandless + */ +static void +regoptail(p, val) +char *p; +char *val; +{ + /* "Operandless" and "op != BRANCH" are synonymous in practice. */ + if (p == NULL || p == ®dummy || OP(p) != BRANCH) + return; + regtail(OPERAND(p), val); +} + +/* + * regexec and friends + */ + +/* + * Global work variables for regexec(). + */ +static char *reginput; /* String-input pointer. */ +static char *regbol; /* Beginning of input, for ^ check. */ +static char **regstartp; /* Pointer to startp array. */ +static char **regendp; /* Ditto for endp. */ + +/* + * Forwards. + */ +STATIC int regtry(); +STATIC int regmatch(); +STATIC int regrepeat(); + +#ifdef DEBUG +int regnarrate = 0; +void regdump(); +STATIC char *regprop(); +#endif + +/* + - regexec - match a regexp against a string + */ +int +regexec(prog, string) +register const regexp *prog; +register const char *string; +{ + register char *s; + extern char *strchr(); + + /* Be paranoid... */ + if (prog == NULL || string == NULL) { + regerror("NULL parameter"); + return(0); + } + + /* Check validity of program. */ + if (UCHARAT(prog->program) != MAGIC) { + regerror("corrupted program"); + return(0); + } + + /* If there is a "must appear" string, look for it. */ + if (prog->regmust != NULL) { + s = (char *)string; + while ((s = strchr(s, prog->regmust[0])) != NULL) { + if (strncmp(s, prog->regmust, prog->regmlen) == 0) + break; /* Found it. */ + s++; + } + if (s == NULL) /* Not present. */ + return(0); + } + + /* Mark beginning of line for ^ . */ + regbol = (char *)string; + + /* Simplest case: anchored match need be tried only once. */ + if (prog->reganch) + return(regtry(prog, string)); + + /* Messy cases: unanchored match. */ + s = (char *)string; + if (prog->regstart != '\0') + /* We know what char it must start with. */ + while ((s = strchr(s, prog->regstart)) != NULL) { + if (regtry(prog, s)) + return(1); + s++; + } + else + /* We don't -- general case. */ + do { + if (regtry(prog, s)) + return(1); + } while (*s++ != '\0'); + + /* Failure. */ + return(0); +} + +/* + - regtry - try match at specific point + */ +static int /* 0 failure, 1 success */ +regtry(prog, string) +regexp *prog; +char *string; +{ + register int i; + register char **sp; + register char **ep; + + reginput = string; + regstartp = prog->startp; + regendp = prog->endp; + + sp = prog->startp; + ep = prog->endp; + for (i = NSUBEXP; i > 0; i--) { + *sp++ = NULL; + *ep++ = NULL; + } + if (regmatch(prog->program + 1)) { + prog->startp[0] = string; + prog->endp[0] = reginput; + return(1); + } else + return(0); +} + +/* + - regmatch - main matching routine + * + * Conceptually the strategy is simple: check to see whether the current + * node matches, call self recursively to see whether the rest matches, + * and then act accordingly. In practice we make some effort to avoid + * recursion, in particular by going through "ordinary" nodes (that don't + * need to know whether the rest of the match failed) by a loop instead of + * by recursion. + */ +static int /* 0 failure, 1 success */ +regmatch(prog) +char *prog; +{ + register char *scan; /* Current node. */ + char *next; /* Next node. */ + extern char *strchr(); + + scan = prog; +#ifdef DEBUG + if (scan != NULL && regnarrate) + fprintf(stderr, "%s(\n", regprop(scan)); +#endif + while (scan != NULL) { +#ifdef DEBUG + if (regnarrate) + fprintf(stderr, "%s...\n", regprop(scan)); +#endif + next = regnext(scan); + + switch (OP(scan)) { + case BOL: + if (reginput != regbol) + return(0); + break; + case EOL: + if (*reginput != '\0') + return(0); + break; + case WORDA: + /* Must be looking at a letter, digit, or _ */ + if ((!isalnum(*reginput)) && *reginput != '_') + return(0); + /* Prev must be BOL or nonword */ + if (reginput > regbol && + (isalnum(reginput[-1]) || reginput[-1] == '_')) + return(0); + break; + case WORDZ: + /* Must be looking at non letter, digit, or _ */ + if (isalnum(*reginput) || *reginput == '_') + return(0); + /* We don't care what the previous char was */ + break; + case ANY: + if (*reginput == '\0') + return(0); + reginput++; + break; + case EXACTLY: { + register int len; + register char *opnd; + + opnd = OPERAND(scan); + /* Inline the first character, for speed. */ + if (*opnd != *reginput) + return(0); + len = strlen(opnd); + if (len > 1 && strncmp(opnd, reginput, len) != 0) + return(0); + reginput += len; + } + break; + case ANYOF: + if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) == NULL) + return(0); + reginput++; + break; + case ANYBUT: + if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != NULL) + return(0); + reginput++; + break; + case NOTHING: + break; + case BACK: + break; + case OPEN+1: + case OPEN+2: + case OPEN+3: + case OPEN+4: + case OPEN+5: + case OPEN+6: + case OPEN+7: + case OPEN+8: + case OPEN+9: { + register int no; + register char *save; + + no = OP(scan) - OPEN; + save = reginput; + + if (regmatch(next)) { + /* + * Don't set startp if some later + * invocation of the same parentheses + * already has. + */ + if (regstartp[no] == NULL) + regstartp[no] = save; + return(1); + } else + return(0); + } + break; + case CLOSE+1: + case CLOSE+2: + case CLOSE+3: + case CLOSE+4: + case CLOSE+5: + case CLOSE+6: + case CLOSE+7: + case CLOSE+8: + case CLOSE+9: { + register int no; + register char *save; + + no = OP(scan) - CLOSE; + save = reginput; + + if (regmatch(next)) { + /* + * Don't set endp if some later + * invocation of the same parentheses + * already has. + */ + if (regendp[no] == NULL) + regendp[no] = save; + return(1); + } else + return(0); + } + break; + case BRANCH: { + register char *save; + + if (OP(next) != BRANCH) /* No choice. */ + next = OPERAND(scan); /* Avoid recursion. */ + else { + do { + save = reginput; + if (regmatch(OPERAND(scan))) + return(1); + reginput = save; + scan = regnext(scan); + } while (scan != NULL && OP(scan) == BRANCH); + return(0); + /* NOTREACHED */ + } + } + break; + case STAR: + case PLUS: { + register char nextch; + register int no; + register char *save; + register int min; + + /* + * Lookahead to avoid useless match attempts + * when we know what character comes next. + */ + nextch = '\0'; + if (OP(next) == EXACTLY) + nextch = *OPERAND(next); + min = (OP(scan) == STAR) ? 0 : 1; + save = reginput; + no = regrepeat(OPERAND(scan)); + while (no >= min) { + /* If it could work, try it. */ + if (nextch == '\0' || *reginput == nextch) + if (regmatch(next)) + return(1); + /* Couldn't or didn't -- back up. */ + no--; + reginput = save + no; + } + return(0); + } + break; + case END: + return(1); /* Success! */ + break; + default: + regerror("memory corruption"); + return(0); + break; + } + + scan = next; + } + + /* + * We get here only if there's trouble -- normally "case END" is + * the terminating point. + */ + regerror("corrupted pointers"); + return(0); +} + +/* + - regrepeat - repeatedly match something simple, report how many + */ +static int +regrepeat(p) +char *p; +{ + register int count = 0; + register char *scan; + register char *opnd; + + scan = reginput; + opnd = OPERAND(p); + switch (OP(p)) { + case ANY: + count = strlen(scan); + scan += count; + break; + case EXACTLY: + while (*opnd == *scan) { + count++; + scan++; + } + break; + case ANYOF: + while (*scan != '\0' && strchr(opnd, *scan) != NULL) { + count++; + scan++; + } + break; + case ANYBUT: + while (*scan != '\0' && strchr(opnd, *scan) == NULL) { + count++; + scan++; + } + break; + default: /* Oh dear. Called inappropriately. */ + regerror("internal foulup"); + count = 0; /* Best compromise. */ + break; + } + reginput = scan; + + return(count); +} + +/* + - regnext - dig the "next" pointer out of a node + */ +static char * +regnext(p) +register char *p; +{ + register int offset; + + if (p == ®dummy) + return(NULL); + + offset = NEXT(p); + if (offset == 0) + return(NULL); + + if (OP(p) == BACK) + return(p-offset); + else + return(p+offset); +} + +#ifdef DEBUG + +STATIC char *regprop(); + +/* + - regdump - dump a regexp onto stdout in vaguely comprehensible form + */ +void +regdump(r) +regexp *r; +{ + register char *s; + register char op = EXACTLY; /* Arbitrary non-END op. */ + register char *next; + extern char *strchr(); + + + s = r->program + 1; + while (op != END) { /* While that wasn't END last time... */ + op = OP(s); + printf("%2d%s", s-r->program, regprop(s)); /* Where, what. */ + next = regnext(s); + if (next == NULL) /* Next ptr. */ + printf("(0)"); + else + printf("(%d)", (s-r->program)+(next-s)); + s += 3; + if (op == ANYOF || op == ANYBUT || op == EXACTLY) { + /* Literal string, where present. */ + while (*s != '\0') { + putchar(*s); + s++; + } + s++; + } + putchar('\n'); + } + + /* Header fields of interest. */ + if (r->regstart != '\0') + printf("start `%c' ", r->regstart); + if (r->reganch) + printf("anchored "); + if (r->regmust != NULL) + printf("must have \"%s\"", r->regmust); + printf("\n"); +} + +/* + - regprop - printable representation of opcode + */ +static char * +regprop(op) +char *op; +{ + register char *p; + static char buf[50]; + + (void) strcpy(buf, ":"); + + switch (OP(op)) { + case BOL: + p = "BOL"; + break; + case EOL: + p = "EOL"; + break; + case ANY: + p = "ANY"; + break; + case ANYOF: + p = "ANYOF"; + break; + case ANYBUT: + p = "ANYBUT"; + break; + case BRANCH: + p = "BRANCH"; + break; + case EXACTLY: + p = "EXACTLY"; + break; + case NOTHING: + p = "NOTHING"; + break; + case BACK: + p = "BACK"; + break; + case END: + p = "END"; + break; + case OPEN+1: + case OPEN+2: + case OPEN+3: + case OPEN+4: + case OPEN+5: + case OPEN+6: + case OPEN+7: + case OPEN+8: + case OPEN+9: + sprintf(buf+strlen(buf), "OPEN%d", OP(op)-OPEN); + p = NULL; + break; + case CLOSE+1: + case CLOSE+2: + case CLOSE+3: + case CLOSE+4: + case CLOSE+5: + case CLOSE+6: + case CLOSE+7: + case CLOSE+8: + case CLOSE+9: + sprintf(buf+strlen(buf), "CLOSE%d", OP(op)-CLOSE); + p = NULL; + break; + case STAR: + p = "STAR"; + break; + case PLUS: + p = "PLUS"; + break; + case WORDA: + p = "WORDA"; + break; + case WORDZ: + p = "WORDZ"; + break; + default: + regerror("corrupted opcode"); + break; + } + if (p != NULL) + (void) strcat(buf, p); + return(buf); +} +#endif + +/* + * The following is provided for those people who do not have strcspn() in + * their C libraries. They should get off their butts and do something + * about it; at least one public-domain implementation of those (highly + * useful) string routines has been published on Usenet. + */ +#ifdef STRCSPN +/* + * strcspn - find length of initial segment of s1 consisting entirely + * of characters not from s2 + */ + +static int +strcspn(s1, s2) +char *s1; +char *s2; +{ + register char *scan1; + register char *scan2; + register int count; + + count = 0; + for (scan1 = s1; *scan1 != '\0'; scan1++) { + for (scan2 = s2; *scan2 != '\0';) /* ++ moved down. */ + if (*scan1 == *scan2++) + return(count); + count++; + } + return(count); +} +#endif diff --git a/lib/libcompat/regexp/regexp.h b/lib/libcompat/regexp/regexp.h new file mode 100644 index 0000000..73d6bf4 --- /dev/null +++ b/lib/libcompat/regexp/regexp.h @@ -0,0 +1,21 @@ +/* + * Definitions etc. for regexp(3) routines. + * + * Caveat: this is V8 regexp(3) [actually, a reimplementation thereof], + * not the System V one. + */ +#define NSUBEXP 10 +typedef struct regexp { + char *startp[NSUBEXP]; + char *endp[NSUBEXP]; + char regstart; /* Internal use only. */ + char reganch; /* Internal use only. */ + char *regmust; /* Internal use only. */ + int regmlen; /* Internal use only. */ + char program[1]; /* Unwarranted chumminess with compiler. */ +} regexp; + +extern regexp *regcomp(); +extern int regexec(); +extern void regsub(); +extern void regerror(); diff --git a/lib/libcompat/regexp/regmagic.h b/lib/libcompat/regexp/regmagic.h new file mode 100644 index 0000000..5acf447 --- /dev/null +++ b/lib/libcompat/regexp/regmagic.h @@ -0,0 +1,5 @@ +/* + * The first byte of the regexp internal "program" is actually this magic + * number; the start node begins in the second byte. + */ +#define MAGIC 0234 diff --git a/lib/libcompat/regexp/regsub.c b/lib/libcompat/regexp/regsub.c new file mode 100644 index 0000000..e55b9b6 --- /dev/null +++ b/lib/libcompat/regexp/regsub.c @@ -0,0 +1,81 @@ +/* + * regsub + * + * Copyright (c) 1986 by University of Toronto. + * Written by Henry Spencer. Not derived from licensed software. + * + * Permission is granted to anyone to use this software for any + * purpose on any computer system, and to redistribute it freely, + * subject to the following restrictions: + * + * 1. The author is not responsible for the consequences of use of + * this software, no matter how awful, even if they arise + * from defects in it. + * + * 2. The origin of this software must not be misrepresented, either + * by explicit claim or by omission. + * + * 3. Altered versions must be plainly marked as such, and must not + * be misrepresented as being the original software. + */ +#include <regexp.h> +#include <stdio.h> +#include <string.h> +#include "regmagic.h" + +#ifndef CHARBITS +#define UCHARAT(p) ((int)*(unsigned char *)(p)) +#else +#define UCHARAT(p) ((int)*(p)&CHARBITS) +#endif + +/* + - regsub - perform substitutions after a regexp match + */ +void +regsub(prog, source, dest) +const regexp *prog; +const char *source; +char *dest; +{ + register char *src; + register char *dst; + register char c; + register int no; + register int len; + extern char *strncpy(); + + if (prog == NULL || source == NULL || dest == NULL) { + regerror("NULL parm to regsub"); + return; + } + if (UCHARAT(prog->program) != MAGIC) { + regerror("damaged regexp fed to regsub"); + return; + } + + src = (char *)source; + dst = dest; + while ((c = *src++) != '\0') { + if (c == '&') + no = 0; + else if (c == '\\' && '0' <= *src && *src <= '9') + no = *src++ - '0'; + else + no = -1; + if (no < 0) { /* Ordinary character. */ + if (c == '\\' && (*src == '\\' || *src == '&')) + c = *src++; + *dst++ = c; + } else if (prog->startp[no] != NULL && prog->endp[no] != NULL) { + len = prog->endp[no] - prog->startp[no]; + (void) strncpy(dst, prog->startp[no], len); + dst += len; + if (len != 0 && *(dst-1) == '\0') { /* strncpy hit NUL. */ + regerror("damaged match string"); + return; + } + } + } + *dst++ = '\0'; +} |