a2p
accept
access
acct
addftinfo
addr2line
adjtime
afmtodit
after
aio_cancel
aio_error
aio_read
aio_return
aio_suspend
aio_waitcomplete
aio_write
alias
aliases
alloc
anvil
append
apply
apropos
ar
array
as
asa
asn1parse
at
atq
atrm
attemptckalloc
attemptckrealloc
authlib
authtest
autopoint
awk
b64decode
b64encode
basename
batch
bc
bdes
bell
bg
bgerror
biff
big5
binary
bind
bindkey
bindtags
bindtextdomain
bio
bitmap
blowfish
bn
bootparams
bootptab
bounce
brandelf
break
breaksw
brk
bsdiff
bsdtar
bsnmpd
bspatch
bthost
btsockstat
buffer
builtin
builtins
bunzip2
button
byacc
bzcat
bzegrep
bzfgrep
bzgrep
bzip2
c2ph
c89
c99
ca
cal
calendar
canvas
cap_mkdb
case
cat
catch
catman
cc
cd
cdcontrol
chdir
checkbutton
checknr
chflags
chfn
chgrp
chio
chkey
chmod
chown
chpass
chroot
chsh
ci
ciphers
ckalloc
ckdist
ckfree
ckrealloc
cksum
cleanup
clear
clipboard
clock
clock_getres
clock_gettime
clock_settime
close
cmp
co
col
colcrt
colldef
colors
colrm
column
comm
command
compile_et
complete
compress
concat
config
connect
console
continue
core
courierlogger
couriertcpd
cp
cpan
cpio
cpp
creat
crl
crontab
crunchgen
crunchide
crypt
crypto
csh
csplit
ctags
ctm
ctm_dequeue
ctm_rmail
ctm_smail
cu
cursor
cursors
cut
cvs
date
dbiprof
dbiproxy
dc
dcgettext
dcngettext
dd
dde
default
defer
deliverquota
des
destroy
devfs
df
dgettext
dgst
dh
dhparam
dialog
diff
diff3
dig
dir
dirent
dirname
dirs
discard
disktab
dngettext
do
domainname
done
dprofpp
dsa
dsaparam
dtmfdecode
du
dup
dup2
eaccess
ec
ecdsa
echo
echotc
ecparam
ed
edit
editrc
ee
egrep
elf
elfdump
elif
else
enc
enc2xs
encoding
end
endif
endsw
engine
enigma
entry
env
envsubst
eof
eqn
err
errno
error
errstr
esac
ethers
euc
eui64
eval
event
evp
ex
exec
execve
exit
expand
export
exports
expr
extattr
extattr_delete_fd
extattr_delete_file
extattr_get_fd
extattr_get_file
extattr_set_fd
extattr_set_file
f77
false
famm
famx
fblocked
fbtab
fc
fchdir
fchflags
fchmod
fchown
fcntl
fconfigure
fcopy
fdescfs
fdformat
fdread
fdwrite
fetch
fg
fgrep
fhopen
fhstat
fhstatfs
fi
file
file2c
fileevent
filename
filetest
find
find2perl
finger
flex
flock
flush
fmt
focus
fold
font
fontedit
for
foreach
fork
format
forward
fpathconf
frame
from
fs
fstab
fstat
fstatfs
fsync
ftp
ftpchroot
ftpusers
ftruncate
futimes
g711conv
gb2312
gb18030
gbk
gcc
gcore
gcov
gdb
gencat
gendsa
genrsa
gensnmptree
getconf
getdents
getdirentries
getdtablesize
getegid
geteuid
getfacl
getfh
getfsstat
getgid
getgroups
getitimer
getlogin
getopt
getopts
getpeername
getpgid
getpgrp
getpid
getppid
getpriority
getresgid
getresuid
getrlimit
getrusage
gets
getsid
getsockname
getsockopt
gettext
gettextize
gettimeofday
gettytab
getuid
glob
global
gmake
goto
gperf
gprof
grab
grep
grid
grn
grodvi
groff
groff_font
groff_out
groff_tmac
grog
grolbp
grolj4
grops
grotty
group
groups
gunzip
gzcat
gzexe
gzip
h2ph
h2xs
hash
hashstat
hd
head
help2man
hesinfo
hexdump
history
host
hostname
hosts
hosts_access
hosts_options
hpftodit
http
hup
i386_get_ioperm
i386_get_ldt
i386_set_ioperm
i386_set_ldt
i386_vm86
iconv
id
ident
idprio
if
ifnames253
ifnames259
image
imapd
incr
indent
indxbib
info
infokey
inode
install
instmodsh
interp
intro
introduction
ioctl
ipcrm
ipcs
ipf
ipftest
ipnat
ippool
ipresend
issetugid
jail
jail_attach
jobid
jobs
join
jot
kbdcontrol
kbdmap
kcon
kdestroy
kdump
kenv
kevent
keycap
keylogin
keylogout
keymap
keysyms
kgdb
kill
killall
killpg
kinit
kldfind
kldfirstmod
kldload
kldnext
kldstat
kldsym
kldunload
klist
kpasswd
kqueue
kse
kse_create
kse_exit
kse_release
kse_switchin
kse_thr_interrupt
kse_wakeup
ktrace
label
labelframe
lam
lappend
last
lastcomm
lastlog
lchflags
lchmod
lchown
ld
ldap
ldapadd
ldapcompare
ldapdelete
ldapmodify
ldapmodrdn
ldappasswd
ldapsearch
ldapwhoami
ldd
leave
less
lesskey
lex
lgetfh
lhash
libnetcfg
library
limit
limits
lindex
link
linprocfs
linsert
lint
lio_listio
list
listbox
listen
lj4_font
lkbib
llength
lmtp
ln
load
loadfont
local
locale
locate
lock
lockf
log
logger
login
logins
logname
logout
look
lookbib
lorder
lower
lp
lpq
lpr
lprm
lptest
lrange
lreplace
ls
lsearch
lseek
lset
lsort
lstat
lsvfs
lutimes
lynx
m4
madvise
magic
mail
maildiracl
maildirkw
maildirmake
mailq
mailx
make
makeinfo
makewhatis
man
manpath
master
mc
mcedit
mcview
md2
md4
md5
mdc2
memory
menu
menubar
menubutton
merge
mesg
message
mincore
minherit
minigzip
mkdep
mkdir
mkfifo
mkimapdcert
mklocale
mknod
mkpop3dcert
mkstr
mktemp
mlock
mlockall
mmap
mmroff
modfind
modfnext
modnext
modstat
moduli
more
motd
mount
mprotect
mptable
msdos
msdosfs
msgattrib
msgcat
msgcmp
msgcomm
msgconv
msgen
msgexec
msgfilter
msgfmt
msggrep
msginit
msgmerge
msgs
msgunfmt
msguniq
mskanji
msql2mysql
msync
mt
munlock
munlockall
munmap
mv
myisamchk
myisamlog
myisampack
mysql
mysqlaccess
mysqladmin
mysqlbinlog
mysqlcheck
mysqld
mysqldump
mysqld_multi
mysqld_safe
mysqlhotcopy
mysqlimport
mysqlshow
mysql_config
mysql_fix_privilege_tables
mysql_zap
namespace
nanosleep
nawk
nc
ncal
ncplist
ncplogin
ncplogout
neqn
netconfig
netgroup
netid
netstat
networks
newaliases
newgrp
nex
nfsstat
nfssvc
ngettext
nice
nl
nm
nmount
nohup
nologin
notify
nroff
nseq
nslookup
ntp_adjtime
ntp_gettime
nvi
nview
objcopy
objdump
objformat
ocsp
od
onintr
open
openssl
opieaccess
opieinfo
opiekey
opiekeys
opiepasswd
option
options
oqmgr
pack
package
packagens
pagesize
palette
pam_auth
panedwindow
parray
passwd
paste
patch
pathchk
pathconf
pawd
pax
pbm
pcre
pcreapi
pcrebuild
pcrecallout
pcrecompat
pcrecpp
pcregrep
pcrematching
pcrepartial
pcrepattern
pcreperform
pcreposix
pcreprecompile
pcresample
pcretest
perl
perl56delta
perl58delta
perl561delta
perl570delta
perl571delta
perl572delta
perl573delta
perl581delta
perl582delta
perl583delta
perl584delta
perl585delta
perl586delta
perl587delta
perl588delta
perl5004delta
perl5005delta
perlaix
perlamiga
perlapi
perlapio
perlapollo
perlartistic
perlbeos
perlbook
perlboot
perlbot
perlbs2000
perlbug
perlcall
perlcc
perlce
perlcheat
perlclib
perlcn
perlcompile
perlcygwin
perldata
perldbmfilter
perldebguts
perldebtut
perldebug
perldelta
perldgux
perldiag
perldoc
perldos
perldsc
perlebcdic
perlembed
perlepoc
perlfaq
perlfaq1
perlfaq2
perlfaq3
perlfaq4
perlfaq5
perlfaq6
perlfaq7
perlfaq8
perlfaq9
perlfilter
perlfork
perlform
perlfreebsd
perlfunc
perlglossary
perlgpl
perlguts
perlhack
perlhist
perlhpux
perlhurd
perlintern
perlintro
perliol
perlipc
perlirix
perlivp
perljp
perlko
perllexwarn
perllinux
perllocale
perllol
perlmachten
perlmacos
perlmacosx
perlmint
perlmod
perlmodinstall
perlmodlib
perlmodstyle
perlmpeix
perlnetware
perlnewmod
perlnumber
perlobj
perlop
perlopenbsd
perlopentut
perlos2
perlos390
perlos400
perlothrtut
perlpacktut
perlplan9
perlpod
perlpodspec
perlport
perlqnx
perlre
perlref
perlreftut
perlrequick
perlreref
perlretut
perlrun
perlsec
perlsolaris
perlstyle
perlsub
perlsyn
perlthrtut
perltie
perltoc
perltodo
perltooc
perltoot
perltrap
perltru64
perltw
perlunicode
perluniintro
perlutil
perluts
perlvar
perlvmesa
perlvms
perlvos
perlwin32
perlxs
perlxstut
perror
pfbtops
pftp
pgrep
phones
photo
pic
pickup
piconv
pid
pipe
pkcs7
pkcs8
pkcs12
pkg_add
pkg_check
pkg_create
pkg_delete
pkg_info
pkg_sign
pkg_version
pkill
pl2pm
place
pod2html
pod2latex
pod2man
pod2text
pod2usage
podchecker
podselect
poll
popd
popup
posix_madvise
postalias
postcat
postconf
postdrop
postfix
postkick
postlock
postlog
postmap
postqueue
postsuper
pr
pread
preadv
printcap
printenv
printf
proc
procfs
profil
protocols
prove
proxymap
ps
psed
psroff
pstruct
ptrace
publickey
pushd
puts
pwd
pwrite
pwritev
qmgr
qmqpd
quota
quotactl
radiobutton
raise
rand
ranlib
rcp
rcs
rcsclean
rcsdiff
rcsfile
rcsfreeze
rcsintro
rcsmerge
read
readelf
readlink
readonly
readv
realpath
reboot
recv
recvfrom
recvmsg
red
ree
refer
regexp
registry
regsub
rehash
remote
rename
repeat
replace
req
reset
resolver
resource
return
rev
revoke
rfcomm_sppd
rfork
rhosts
ripemd
ripemd160
rlog
rlogin
rm
rmd160
rmdir
rpc
rpcgen
rs
rsa
rsautl
rsh
rtld
rtprio
rup
ruptime
rusers
rwall
rwho
s2p
safe
sasl
sasldblistusers2
saslpasswd2
sbrk
scache
scale
scan
sched
sched_getparam
sched_getscheduler
sched_get_priority_max
sched_get_priority_min
sched_rr_get_interval
sched_setparam
sched_setscheduler
sched_yield
scon
scp
script
scrollbar
sdiff
sed
seek
select
selection
semctl
semget
semop
send
sendbug
sendfile
sendmail
sendmsg
sendto
services
sess_id
set
setegid
setenv
seteuid
setfacl
setgid
setgroups
setitimer
setlogin
setpgid
setpgrp
setpriority
setregid
setresgid
setresuid
setreuid
setrlimit
setsid
setsockopt
settc
settimeofday
setty
setuid
setvar
sftp
sh
sha
sha1
sha256
shar
shells
shift
shmat
shmctl
shmdt
shmget
showq
shutdown
sigaction
sigaltstack
sigblock
sigmask
sigpause
sigpending
sigprocmask
sigreturn
sigsetmask
sigstack
sigsuspend
sigvec
sigwait
size
slapadd
slapcat
slapd
slapdn
slapindex
slappasswd
slaptest
sleep
slogin
slurpd
smbutil
smime
smtp
smtpd
socket
socketpair
sockstat
soelim
sort
source
spawn
speed
spinbox
spkac
splain
split
squid
squid_ldap_auth
squid_ldap_group
squid_unix_group
sscop
ssh
sshd_config
ssh_config
stab
startslip
stat
statfs
stop
string
strings
strip
stty
su
subst
sum
suspend
swapoff
swapon
switch
symlink
sync
sysarch
syscall
sysconftool
sysconftoolcheck
systat
s_client
s_server
s_time
tabs
tail
talk
tar
tbl
tclsh
tcltest
tclvars
tcopy
tcpdump
tcpslice
tcsh
tee
tell
telltc
telnet
term
termcap
terminfo
test
texindex
texinfo
text
textdomain
tfmtodit
tftp
then
threads
time
tip
tk
tkerror
tkvars
tkwait
tlsmgr
tmac
top
toplevel
touch
tput
tr
trace
trafshow
trap
troff
true
truncate
truss
tset
tsort
tty
ttys
type
tzfile
ui
ul
ulimit
umask
unalias
uname
uncomplete
uncompress
undelete
unexpand
unhash
unifdef
unifdefall
uniq
units
unknown
unlimit
unlink
unmount
unset
unsetenv
until
unvis
update
uplevel
uptime
upvar
usbhidaction
usbhidctl
users
utf8
utimes
utmp
utrace
uudecode
uuencode
uuidgen
vacation
variable
verify
version
vfork
vgrind
vgrindefs
vi
vidcontrol
vidfont
view
virtual
vis
vt220keys
vwait
w
wait
wait3
wait4
waitpid
wall
wc
wget
what
whatis
where
whereis
which
while
who
whoami
whois
window
winfo
wish
wm
write
writev
wtmp
x509
xargs
xgettext
xmlwf
xstr
xsubpp
yacc
yes
ypcat
ypchfn
ypchpass
ypchsh
ypmatch
yppasswd
ypwhich
yyfix
zcat
zcmp
zdiff
zegrep
zfgrep
zforce
zgrep
zmore
znew
_exit
__syscall
 
FreeBSD/Linux/UNIX General Commands Manual
Hypertext Man Pages
pcreapi
 
PCREAPI(3)							    PCREAPI(3)



NAME
       PCRE - Perl-compatible regular expressions

PCRE NATIVE API

       #include 

       pcre *pcre_compile(const char *pattern, int options,
	    const char **errptr, int *erroffset,
	    const unsigned char *tableptr);

       pcre *pcre_compile2(const char *pattern, int options,
	    int *errorcodeptr,
	    const char **errptr, int *erroffset,
	    const unsigned char *tableptr);

       pcre_extra *pcre_study(const pcre *code, int options,
	    const char **errptr);

       int pcre_exec(const pcre *code, const pcre_extra *extra,
	    const char *subject, int length, int startoffset,
	    int options, int *ovector, int ovecsize);

       int pcre_dfa_exec(const pcre *code, const pcre_extra *extra,
	    const char *subject, int length, int startoffset,
	    int options, int *ovector, int ovecsize,
	    int *workspace, int wscount);

       int pcre_copy_named_substring(const pcre *code,
	    const char *subject, int *ovector,
	    int stringcount, const char *stringname,
	    char *buffer, int buffersize);

       int pcre_copy_substring(const char *subject, int *ovector,
	    int stringcount, int stringnumber, char *buffer,
	    int buffersize);

       int pcre_get_named_substring(const pcre *code,
	    const char *subject, int *ovector,
	    int stringcount, const char *stringname,
	    const char **stringptr);

       int pcre_get_stringnumber(const pcre *code,
	    const char *name);

       int pcre_get_substring(const char *subject, int *ovector,
	    int stringcount, int stringnumber,
	    const char **stringptr);

       int pcre_get_substring_list(const char *subject,
	    int *ovector, int stringcount, const char ***listptr);

       void pcre_free_substring(const char *stringptr);

       void pcre_free_substring_list(const char **stringptr);

       const unsigned char *pcre_maketables(void);

       int pcre_fullinfo(const pcre *code, const pcre_extra *extra,
	    int what, void *where);

       int pcre_info(const pcre *code, int *optptr, int *firstcharptr);

       int pcre_refcount(pcre *code, int adjust);

       int pcre_config(int what, void *where);

       char *pcre_version(void);

       void *(*pcre_malloc)(size_t);

       void (*pcre_free)(void *);

       void *(*pcre_stack_malloc)(size_t);

       void (*pcre_stack_free)(void *);

       int (*pcre_callout)(pcre_callout_block *);

PCRE API OVERVIEW

       PCRE has its own native API, which is described in this document. There
       is also a set of wrapper functions that correspond to the POSIX regular
       expression  API.  These	are  described in the pcreposix documentation.
       Both of these APIs define a set of C function calls. A C++  wrapper  is
       distributed with PCRE. It is documented in the pcrecpp page.

       The  native  API  C  function prototypes are defined in the header file
       pcre.h, and on Unix systems the library itself is called  libpcre.   It
       can normally be accessed by adding -lpcre to the command for linking an
       application  that  uses	PCRE.  The  header  file  defines  the	macros
       PCRE_MAJOR  and	PCRE_MINOR to contain the major and minor release num-
       bers for the library.  Applications can use these  to  include  support
       for different releases of PCRE.

       The   functions	 pcre_compile(),  pcre_compile2(),  pcre_study(),  and
       pcre_exec() are used for compiling and matching regular expressions  in
       a  Perl-compatible  manner. A sample program that demonstrates the sim-
       plest way of using them is provided in the file	called	pcredemo.c  in
       the  source distribution. The pcresample documentation describes how to
       run it.

       A second matching function, pcre_dfa_exec(), which is not Perl-compati-
       ble,  is  also provided. This uses a different algorithm for the match-
       ing. This allows it to find all possible matches (at a given  point  in
       the  subject),  not  just  one. However, this algorithm does not return
       captured substrings. A description of the two matching  algorithms  and
       their  advantages  and disadvantages is given in the pcrematching docu-
       mentation.

       In addition to the main compiling and  matching	functions,  there  are
       convenience functions for extracting captured substrings from a subject
       string that is matched by pcre_exec(). They are:

	 pcre_copy_substring()
	 pcre_copy_named_substring()
	 pcre_get_substring()
	 pcre_get_named_substring()
	 pcre_get_substring_list()
	 pcre_get_stringnumber()

       pcre_free_substring() and pcre_free_substring_list() are also provided,
       to free the memory used for extracted strings.

       The  function  pcre_maketables()  is  used  to build a set of character
       tables  in  the	current  locale   for	passing   to   pcre_compile(),
       pcre_exec(),  or  pcre_dfa_exec(). This is an optional facility that is
       provided for specialist use.  Most  commonly,  no  special  tables  are
       passed,	in  which case internal tables that are generated when PCRE is
       built are used.

       The function pcre_fullinfo() is used to find out  information  about  a
       compiled  pattern; pcre_info() is an obsolete version that returns only
       some of the available information, but is retained for  backwards  com-
       patibility.   The function pcre_version() returns a pointer to a string
       containing the version of PCRE and its date of release.

       The function pcre_refcount() maintains a  reference  count  in  a  data
       block  containing  a compiled pattern. This is provided for the benefit
       of object-oriented applications.

       The global variables pcre_malloc and pcre_free  initially  contain  the
       entry  points  of  the  standard malloc() and free() functions, respec-
       tively. PCRE calls the memory management functions via these variables,
       so  a  calling  program	can replace them if it wishes to intercept the
       calls. This should be done before calling any PCRE functions.

       The global variables pcre_stack_malloc  and  pcre_stack_free  are  also
       indirections  to  memory  management functions. These special functions
       are used only when PCRE is compiled to use  the	heap  for  remembering
       data, instead of recursive function calls, when running the pcre_exec()
       function. This is a non-standard way of building PCRE, for use in envi-
       ronments that have limited stacks. Because of the greater use of memory
       management, it runs more slowly.  Separate functions  are  provided  so
       that  special-purpose  external	code  can  be used for this case. When
       used, these functions are always called in a  stack-like  manner  (last
       obtained,  first freed), and always for memory blocks of the same size.

       The global variable pcre_callout initially contains NULL. It can be set
       by  the	caller	to  a "callout" function, which PCRE will then call at
       specified points during a matching operation. Details are given in  the
       pcrecallout documentation.

MULTITHREADING

       The  PCRE  functions  can be used in multi-threading applications, with
       the  proviso  that  the	memory	management  functions  pointed	to  by
       pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the
       callout function pointed to by pcre_callout, are shared by all threads.

       The  compiled form of a regular expression is not altered during match-
       ing, so the same compiled pattern can safely be used by several threads
       at once.

SAVING PRECOMPILED PATTERNS FOR LATER USE

       The compiled form of a regular expression can be saved and re-used at a
       later time, possibly by a different program, and even on a  host  other
       than  the  one  on  which  it  was  compiled.  Details are given in the
       pcreprecompile documentation.

CHECKING BUILD-TIME OPTIONS

       int pcre_config(int what, void *where);

       The function pcre_config() makes it possible for a PCRE client to  dis-
       cover which optional features have been compiled into the PCRE library.
       The pcrebuild documentation has more details about these optional  fea-
       tures.

       The  first  argument  for pcre_config() is an integer, specifying which
       information is required; the second argument is a pointer to a variable
       into  which  the  information  is  placed. The following information is
       available:

	 PCRE_CONFIG_UTF8

       The output is an integer that is set to one if UTF-8 support is	avail-
       able; otherwise it is set to zero.

	 PCRE_CONFIG_UNICODE_PROPERTIES

       The  output  is	an  integer  that is set to one if support for Unicode
       character properties is available; otherwise it is set to zero.

	 PCRE_CONFIG_NEWLINE

       The output is an integer that is set to the value of the code  that  is
       used  for the newline character. It is either linefeed (10) or carriage
       return (13), and should normally be the	standard  character  for  your
       operating system.

	 PCRE_CONFIG_LINK_SIZE

       The  output  is	an  integer that contains the number of bytes used for
       internal linkage in compiled regular expressions. The value is 2, 3, or
       4.  Larger  values  allow larger regular expressions to be compiled, at
       the expense of slower matching. The default value of  2	is  sufficient
       for  all  but  the  most massive patterns, since it allows the compiled
       pattern to be up to 64K in size.

	 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD

       The output is an integer that contains the threshold  above  which  the
       POSIX  interface  uses malloc() for output vectors. Further details are
       given in the pcreposix documentation.

	 PCRE_CONFIG_MATCH_LIMIT

       The output is an integer that gives the default limit for the number of
       internal  matching  function  calls in a pcre_exec() execution. Further
       details are given with pcre_exec() below.

	 PCRE_CONFIG_MATCH_LIMIT_RECURSION

       The output is an integer that gives the default limit for the depth  of
       recursion  when calling the internal matching function in a pcre_exec()
       execution. Further details are given with pcre_exec() below.

	 PCRE_CONFIG_STACKRECURSE

       The output is an integer that is set to one if internal recursion  when
       running pcre_exec() is implemented by recursive function calls that use
       the stack to remember their state. This is the usual way that  PCRE  is
       compiled. The output is zero if PCRE was compiled to use blocks of data
       on the  heap  instead  of  recursive  function  calls.  In  this  case,
       pcre_stack_malloc  and  pcre_stack_free	are  called  to  manage memory
       blocks on the heap, thus avoiding the use of the stack.

COMPILING A PATTERN

       pcre *pcre_compile(const char *pattern, int options,
	    const char **errptr, int *erroffset,
	    const unsigned char *tableptr);

       pcre *pcre_compile2(const char *pattern, int options,
	    int *errorcodeptr,
	    const char **errptr, int *erroffset,
	    const unsigned char *tableptr);

       Either of the functions pcre_compile() or pcre_compile2() can be called
       to compile a pattern into an internal form. The only difference between
       the two interfaces is that pcre_compile2() has an additional  argument,
       errorcodeptr, via which a numerical error code can be returned.

       The pattern is a C string terminated by a binary zero, and is passed in
       the pattern argument. A pointer to a single block  of  memory  that  is
       obtained  via  pcre_malloc is returned. This contains the compiled code
       and related data. The pcre type is defined for the returned block; this
       is a typedef for a structure whose contents are not externally defined.
       It is up to the caller  to  free  the  memory  when  it	is  no	longer
       required.

       Although  the compiled code of a PCRE regex is relocatable, that is, it
       does not depend on memory location, the complete pcre data block is not
       fully  relocatable, because it may contain a copy of the tableptr argu-
       ment, which is an address (see below).

       The options argument contains independent bits that affect the compila-
       tion.  It  should  be  zero  if	no options are required. The available
       options are described below. Some of them, in  particular,  those  that
       are  compatible	with  Perl,  can also be set and unset from within the
       pattern (see the detailed description  in  the  pcrepattern  documenta-
       tion).  For  these options, the contents of the options argument speci-
       fies their initial settings at the start of compilation and  execution.
       The  PCRE_ANCHORED option can be set at the time of matching as well as
       at compile time.

       If errptr is NULL, pcre_compile() returns NULL immediately.  Otherwise,
       if  compilation	of  a  pattern fails, pcre_compile() returns NULL, and
       sets the variable pointed to by errptr to point to a textual error mes-
       sage. This is a static string that is part of the library. You must not
       try to free it. The offset from the start of the pattern to the charac-
       ter where the error was discovered is placed in the variable pointed to
       by erroffset, which must not be NULL. If it is, an immediate  error  is
       given.

       If  pcre_compile2()  is	used instead of pcre_compile(), and the error-
       codeptr argument is not NULL, a non-zero error code number is  returned
       via  this argument in the event of an error. This is in addition to the
       textual error message. Error codes and messages are listed below.

       If the final argument, tableptr, is NULL, PCRE uses a  default  set  of
       character  tables  that	are  built  when  PCRE	is compiled, using the
       default C locale. Otherwise, tableptr must be an address  that  is  the
       result  of  a  call to pcre_maketables(). This value is stored with the
       compiled pattern, and used again by pcre_exec(), unless	another  table
       pointer is passed to it. For more discussion, see the section on locale
       support below.

       This code fragment shows a typical straightforward  call  to  pcre_com-
       pile():

	 pcre *re;
	 const char *error;
	 int erroffset;
	 re = pcre_compile(
	   "^A.*Z",	     /* the pattern */
	   0,		     /* default options */
	   &error,	     /* for error message */
	   &erroffset,	     /* for error offset */
	   NULL);	     /* use default character tables */

       The  following  names  for option bits are defined in the pcre.h header
       file:

	 PCRE_ANCHORED

       If this bit is set, the pattern is forced to be "anchored", that is, it
       is  constrained to match only at the first matching point in the string
       that is being searched (the "subject string"). This effect can also  be
       achieved  by appropriate constructs in the pattern itself, which is the
       only way to do it in Perl.

	 PCRE_AUTO_CALLOUT

       If this bit is set, pcre_compile() automatically inserts callout items,
       all  with  number  255, before each pattern item. For discussion of the
       callout facility, see the pcrecallout documentation.

	 PCRE_CASELESS

       If this bit is set, letters in the pattern match both upper  and  lower
       case  letters.  It  is  equivalent  to  Perl's /i option, and it can be
       changed within a pattern by a (?i) option setting. In UTF-8 mode,  PCRE
       always  understands the concept of case for characters whose values are
       less than 128, so caseless matching is always possible. For  characters
       with  higher  values,  the concept of case is supported if PCRE is com-
       piled with Unicode property support, but not otherwise. If you want  to
       use  caseless  matching	for  characters 128 and above, you must ensure
       that PCRE is compiled with Unicode property support  as	well  as  with
       UTF-8 support.

	 PCRE_DOLLAR_ENDONLY

       If  this bit is set, a dollar metacharacter in the pattern matches only
       at the end of the subject string. Without this option,  a  dollar  also
       matches	immediately before the final character if it is a newline (but
       not before any  other  newlines).  The  PCRE_DOLLAR_ENDONLY  option  is
       ignored if PCRE_MULTILINE is set. There is no equivalent to this option
       in Perl, and no way to set it within a pattern.

	 PCRE_DOTALL

       If this bit is set, a dot metacharater in the pattern matches all char-
       acters,	including  newlines.  Without  it, newlines are excluded. This
       option is equivalent to Perl's /s option, and it can be changed	within
       a  pattern  by  a  (?s)	option	setting. A negative class such as [^a]
       always matches a newline character, independent of the setting of  this
       option.

	 PCRE_EXTENDED

       If  this  bit  is  set,	whitespace  data characters in the pattern are
       totally ignored except when escaped or inside a character class. White-
       space does not include the VT character (code 11). In addition, charac-
       ters between an unescaped # outside a character class and the next new-
       line  character,  inclusive,  are  also	ignored. This is equivalent to
       Perl's /x option, and it can be changed within  a  pattern  by  a  (?x)
       option setting.

       This  option  makes  it possible to include comments inside complicated
       patterns.  Note, however, that this applies only  to  data  characters.
       Whitespace   characters	may  never  appear  within  special  character
       sequences in a pattern, for  example  within  the  sequence  (?(  which
       introduces a conditional subpattern.

	 PCRE_EXTRA

       This  option  was invented in order to turn on additional functionality
       of PCRE that is incompatible with Perl, but it  is  currently  of  very
       little  use. When set, any backslash in a pattern that is followed by a
       letter that has no special meaning  causes  an  error,  thus  reserving
       these  combinations  for  future  expansion.  By default, as in Perl, a
       backslash followed by a letter with no special meaning is treated as  a
       literal.  There	are  at  present  no other features controlled by this
       option. It can also be set by a (?X) option setting within a pattern.

	 PCRE_FIRSTLINE

       If this option is set, an  unanchored  pattern  is  required  to  match
       before  or at the first newline character in the subject string, though
       the matched text may continue over the newline.

	 PCRE_MULTILINE

       By default, PCRE treats the subject string as consisting  of  a	single
       line  of characters (even if it actually contains newlines). The "start
       of line" metacharacter (^) matches only at the  start  of  the  string,
       while  the  "end  of line" metacharacter ($) matches only at the end of
       the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY
       is set). This is the same as Perl.

       When  PCRE_MULTILINE  it  is set, the "start of line" and "end of line"
       constructs match immediately following or immediately before  any  new-
       line  in the subject string, respectively, as well as at the very start
       and end. This is equivalent to Perl's /m option, and it can be  changed
       within a pattern by a (?m) option setting. If there are no "\n" charac-
       ters in a subject string, or no occurrences of ^ or  $  in  a  pattern,
       setting PCRE_MULTILINE has no effect.

	 PCRE_NO_AUTO_CAPTURE

       If this option is set, it disables the use of numbered capturing paren-
       theses in the pattern. Any opening parenthesis that is not followed  by
       ?  behaves as if it were followed by ?: but named parentheses can still
       be used for capturing (and they acquire	numbers  in  the  usual  way).
       There is no equivalent of this option in Perl.

	 PCRE_UNGREEDY

       This  option  inverts  the "greediness" of the quantifiers so that they
       are not greedy by default, but become greedy if followed by "?". It  is
       not  compatible	with Perl. It can also be set by a (?U) option setting
       within the pattern.

	 PCRE_UTF8

       This option causes PCRE to regard both the pattern and the  subject  as
       strings	of  UTF-8 characters instead of single-byte character strings.
       However, it is available only when PCRE is built to include UTF-8  sup-
       port.  If not, the use of this option provokes an error. Details of how
       this option changes the behaviour of PCRE are given in the  section  on
       UTF-8 support in the main pcre page.

	 PCRE_NO_UTF8_CHECK

       When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
       automatically checked. If an invalid UTF-8 sequence of bytes is	found,
       pcre_compile()  returns an error. If you already know that your pattern
       is valid, and you want to skip this check for performance reasons,  you
       can  set  the  PCRE_NO_UTF8_CHECK option. When it is set, the effect of
       passing an invalid UTF-8 string as a pattern is undefined. It may cause
       your  program  to  crash.   Note that this option can also be passed to
       pcre_exec() and pcre_dfa_exec(), to suppress the UTF-8 validity	check-
       ing of subject strings.

COMPILATION ERROR CODES

       The  following  table  lists  the  error  codes than may be returned by
       pcre_compile2(), along with the error messages that may be returned  by
       both compiling functions.

	  0  no error
	  1  \ at end of pattern
	  2  \c at end of pattern
	  3  unrecognized character follows \
	  4  numbers out of order in {} quantifier
	  5  number too big in {} quantifier
	  6  missing terminating ] for character class
	  7  invalid escape sequence in character class
	  8  range out of order in character class
	  9  nothing to repeat
	 10  operand of unlimited repeat could match the empty string
	 11  internal error: unexpected repeat
	 12  unrecognized character after (?
	 13  POSIX named classes are supported only within a class
	 14  missing )
	 15  reference to non-existent subpattern
	 16  erroffset passed as NULL
	 17  unknown option bit(s) set
	 18  missing ) after comment
	 19  parentheses nested too deeply
	 20  regular expression too large
	 21  failed to get memory
	 22  unmatched parentheses
	 23  internal error: code overflow
	 24  unrecognized character after (?<
	 25  lookbehind assertion is not fixed length
	 26  malformed number after (?(
	 27  conditional group contains more than two branches
	 28  assertion expected after (?(
	 29  (?R or (?digits must be followed by )
	 30  unknown POSIX class name
	 31  POSIX collating elements are not supported
	 32  this version of PCRE is not compiled with PCRE_UTF8 support
	 33  spare error
	 34  character value in \x{...} sequence is too large
	 35  invalid condition (?(0)
	 36  \C not allowed in lookbehind assertion
	 37  PCRE does not support \L, \l, \N, \U, or \u
	 38  number after (?C is > 255
	 39  closing ) for (?C expected
	 40  recursive call could loop indefinitely
	 41  unrecognized character after (?P
	 42  syntax error after (?P
	 43  two named groups have the same name
	 44  invalid UTF-8 string
	 45  support for \P, \p, and \X has not been compiled
	 46  malformed \P or \p sequence
	 47  unknown property name after \P or \p

STUDYING A PATTERN

       pcre_extra *pcre_study(const pcre *code, int options
	    const char **errptr);

       If  a  compiled	pattern is going to be used several times, it is worth
       spending more time analyzing it in order to speed up the time taken for
       matching.  The function pcre_study() takes a pointer to a compiled pat-
       tern as its first argument. If studying the pattern produces additional
       information  that  will	help speed up matching, pcre_study() returns a
       pointer to a pcre_extra block, in which the study_data field points  to
       the results of the study.

       The  returned  value  from  pcre_study()  can  be  passed  directly  to
       pcre_exec(). However, a pcre_extra block  also  contains  other	fields
       that  can  be  set  by the caller before the block is passed; these are
       described below in the section on matching a pattern.

       If studying the pattern does not  produce  any  additional  information
       pcre_study() returns NULL. In that circumstance, if the calling program
       wants to pass any of the other fields to pcre_exec(), it  must  set  up
       its own pcre_extra block.

       The  second  argument of pcre_study() contains option bits. At present,
       no options are defined, and this argument should always be zero.

       The third argument for pcre_study() is a pointer for an error  message.
       If  studying  succeeds  (even  if no data is returned), the variable it
       points to is set to NULL. Otherwise it is set to  point	to  a  textual
       error message. This is a static string that is part of the library. You
       must not try to free it. You should test the  error  pointer  for  NULL
       after calling pcre_study(), to be sure that it has run successfully.

       This is a typical call to pcre_study():

	 pcre_extra *pe;
	 pe = pcre_study(
	   re,		   /* result of pcre_compile() */
	   0,		   /* no options exist */
	   &error);	   /* set to NULL or points to a message */

       At present, studying a pattern is useful only for non-anchored patterns
       that do not have a single fixed starting character. A bitmap of	possi-
       ble starting bytes is created.

LOCALE SUPPORT

       PCRE  handles  caseless matching, and determines whether characters are
       letters digits, or whatever, by reference to a set of  tables,  indexed
       by  character  value.  When running in UTF-8 mode, this applies only to
       characters with codes less than 128. Higher-valued  codes  never  match
       escapes	such  as  \w or \d, but can be tested with \p if PCRE is built
       with Unicode character property support. The use of locales  with  Uni-
       code is discouraged.

       An  internal set of tables is created in the default C locale when PCRE
       is built. This is used when the final  argument	of  pcre_compile()  is
       NULL,  and  is  sufficient for many applications. An alternative set of
       tables can, however, be supplied. These may be created in  a  different
       locale  from the default. As more and more applications change to using
       Unicode, the need for this locale support is expected to die away.

       External tables are built by calling  the  pcre_maketables()  function,
       which  has no arguments, in the relevant locale. The result can then be
       passed to pcre_compile() or pcre_exec()	as  often  as  necessary.  For
       example,  to  build  and use tables that are appropriate for the French
       locale (where accented characters with  values  greater	than  128  are
       treated as letters), the following code could be used:

	 setlocale(LC_CTYPE, "fr_FR");
	 tables = pcre_maketables();
	 re = pcre_compile(..., tables);

       When  pcre_maketables()	runs,  the  tables are built in memory that is
       obtained via pcre_malloc. It is the caller's responsibility  to	ensure
       that  the memory containing the tables remains available for as long as
       it is needed.

       The pointer that is passed to pcre_compile() is saved with the compiled
       pattern,  and the same tables are used via this pointer by pcre_study()
       and normally also by pcre_exec(). Thus, by default, for any single pat-
       tern, compilation, studying and matching all happen in the same locale,
       but different patterns can be compiled in different locales.

       It is possible to pass a table pointer or NULL (indicating the  use  of
       the  internal  tables)  to  pcre_exec(). Although not intended for this
       purpose, this facility could be used to match a pattern in a  different
       locale from the one in which it was compiled. Passing table pointers at
       run time is discussed below in the section on matching a pattern.

INFORMATION ABOUT A PATTERN

       int pcre_fullinfo(const pcre *code, const pcre_extra *extra,
	    int what, void *where);

       The pcre_fullinfo() function returns information about a compiled  pat-
       tern. It replaces the obsolete pcre_info() function, which is neverthe-
       less retained for backwards compability (and is documented below).

       The first argument for pcre_fullinfo() is a  pointer  to  the  compiled
       pattern.  The second argument is the result of pcre_study(), or NULL if
       the pattern was not studied. The third argument specifies  which  piece
       of  information	is required, and the fourth argument is a pointer to a
       variable to receive the data. The yield of the  function  is  zero  for
       success, or one of the following negative numbers:

	 PCRE_ERROR_NULL       the argument code was NULL
			       the argument where was NULL
	 PCRE_ERROR_BADMAGIC   the "magic number" was not found
	 PCRE_ERROR_BADOPTION  the value of what was invalid

       The  "magic  number" is placed at the start of each compiled pattern as
       an simple check against passing an arbitrary memory pointer. Here is  a
       typical	call  of pcre_fullinfo(), to obtain the length of the compiled
       pattern:

	 int rc;
	 unsigned long int length;
	 rc = pcre_fullinfo(
	   re,		     /* result of pcre_compile() */
	   pe,		     /* result of pcre_study(), or NULL */
	   PCRE_INFO_SIZE,   /* what is required */
	   &length);	     /* where to put the data */

       The possible values for the third argument are defined in  pcre.h,  and
       are as follows:

	 PCRE_INFO_BACKREFMAX

       Return  the  number  of	the highest back reference in the pattern. The
       fourth argument should point to an int variable. Zero  is  returned  if
       there are no back references.

	 PCRE_INFO_CAPTURECOUNT

       Return  the  number of capturing subpatterns in the pattern. The fourth
       argument should point to an int variable.

	 PCRE_INFO_DEFAULT_TABLES

       Return a pointer to the internal default character tables within  PCRE.
       The  fourth  argument should point to an unsigned char * variable. This
       information call is provided for internal use by the pcre_study() func-
       tion.  External	callers  can  cause PCRE to use its internal tables by
       passing a NULL table pointer.

	 PCRE_INFO_FIRSTBYTE

       Return information about the first byte of any matched  string,	for  a
       non-anchored    pattern.    (This    option    used    to   be	called
       PCRE_INFO_FIRSTCHAR; the old name is  still  recognized	for  backwards
       compatibility.)

       If  there  is  a  fixed first byte, for example, from a pattern such as
       (cat|cow|coyote), it is returned in the integer pointed	to  by	where.
       Otherwise, if either

       (a)  the pattern was compiled with the PCRE_MULTILINE option, and every
       branch starts with "^", or

       (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not
       set (if it were set, the pattern would be anchored),

       -1  is  returned, indicating that the pattern matches only at the start
       of a subject string or after any newline within the  string.  Otherwise
       -2 is returned. For anchored patterns, -2 is returned.

	 PCRE_INFO_FIRSTTABLE

       If  the pattern was studied, and this resulted in the construction of a
       256-bit table indicating a fixed set of bytes for the first byte in any
       matching  string, a pointer to the table is returned. Otherwise NULL is
       returned. The fourth argument should point to an unsigned char *  vari-
       able.

	 PCRE_INFO_LASTLITERAL

       Return  the  value of the rightmost literal byte that must exist in any
       matched string, other than at its  start,  if  such  a  byte  has  been
       recorded. The fourth argument should point to an int variable. If there
       is no such byte, -1 is returned. For anchored patterns, a last  literal
       byte  is  recorded only if it follows something of variable length. For
       example, for the pattern /^a\d+z\d+/ the returned value is "z", but for
       /^a\dz\d/ the returned value is -1.

	 PCRE_INFO_NAMECOUNT
	 PCRE_INFO_NAMEENTRYSIZE
	 PCRE_INFO_NAMETABLE

       PCRE  supports the use of named as well as numbered capturing parenthe-
       ses. The names are just an additional way of identifying the  parenthe-
       ses,  which  still  acquire  numbers.  A  convenience  function	called
       pcre_get_named_substring() is provided  for  extracting	an  individual
       captured  substring  by	name.  It is also possible to extract the data
       directly, by first converting the name to a number in order  to	access
       the  correct  pointers in the output vector (described with pcre_exec()
       below). To do the conversion, you need to use the  name-to-number  map,
       which is described by these three values.

       The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT
       gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size
       of  each  entry;  both  of  these  return  an int value. The entry size
       depends on the length of the longest name. PCRE_INFO_NAMETABLE  returns
       a  pointer  to  the  first  entry of the table (a pointer to char). The
       first two bytes of each entry are the number of the capturing parenthe-
       sis,  most  significant byte first. The rest of the entry is the corre-
       sponding name, zero terminated. The names are  in  alphabetical	order.
       For  example,  consider	the following pattern (assume PCRE_EXTENDED is
       set, so white space - including newlines - is ignored):

	 (?P (?P(\d\d)?\d\d) -
	 (?P\d\d) - (?P\d\d) )

       There are four named subpatterns, so the table has  four  entries,  and
       each  entry  in the table is eight bytes long. The table is as follows,
       with non-printing bytes shows in hexadecimal, and undefined bytes shown
       as ??:

	 00 01 d  a  t	e  00 ??
	 00 05 d  a  y	00 ?? ??
	 00 04 m  o  n	t  h  00
	 00 02 y  e  a	r  00 ??

       When  writing  code  to	extract  data from named subpatterns using the
       name-to-number map, remember that the length of each entry is likely to
       be different for each compiled pattern.

	 PCRE_INFO_OPTIONS

       Return  a  copy of the options with which the pattern was compiled. The
       fourth argument should point to an unsigned long  int  variable.  These
       option bits are those specified in the call to pcre_compile(), modified
       by any top-level option settings within the pattern itself.

       A pattern is automatically anchored by PCRE if  all  of	its  top-level
       alternatives begin with one of the following:

	 ^     unless PCRE_MULTILINE is set
	 \A    always
	 \G    always
	 .*    if PCRE_DOTALL is set and there are no back
		 references to the subpattern in which .* appears

       For such patterns, the PCRE_ANCHORED bit is set in the options returned
       by pcre_fullinfo().

	 PCRE_INFO_SIZE

       Return the size of the compiled pattern, that is, the  value  that  was
       passed as the argument to pcre_malloc() when PCRE was getting memory in
       which to place the compiled data. The fourth argument should point to a
       size_t variable.

	 PCRE_INFO_STUDYSIZE

       Return the size of the data block pointed to by the study_data field in
       a pcre_extra block. That is,  it  is  the  value  that  was  passed  to
       pcre_malloc() when PCRE was getting memory into which to place the data
       created by pcre_study(). The fourth argument should point to  a	size_t
       variable.

OBSOLETE INFO FUNCTION

       int pcre_info(const pcre *code, int *optptr, int *firstcharptr);

       The  pcre_info()  function is now obsolete because its interface is too
       restrictive to return all the available data about a compiled  pattern.
       New   programs	should	use  pcre_fullinfo()  instead.	The  yield  of
       pcre_info() is the number of capturing subpatterns, or one of the  fol-
       lowing negative numbers:

	 PCRE_ERROR_NULL       the argument code was NULL
	 PCRE_ERROR_BADMAGIC   the "magic number" was not found

       If  the	optptr	argument is not NULL, a copy of the options with which
       the pattern was compiled is placed in the integer  it  points  to  (see
       PCRE_INFO_OPTIONS above).

       If  the	pattern  is  not anchored and the firstcharptr argument is not
       NULL, it is used to pass back information about the first character  of
       any matched string (see PCRE_INFO_FIRSTBYTE above).

REFERENCE COUNTS

       int pcre_refcount(pcre *code, int adjust);

       The  pcre_refcount()  function is used to maintain a reference count in
       the data block that contains a compiled pattern. It is provided for the
       benefit	of  applications  that	operate  in an object-oriented manner,
       where different parts of the application may be using the same compiled
       pattern, but you want to free the block when they are all done.

       When a pattern is compiled, the reference count field is initialized to
       zero.  It is changed only by calling this function, whose action is  to
       add  the  adjust  value	(which may be positive or negative) to it. The
       yield of the function is the new value. However, the value of the count
       is  constrained to lie between 0 and 65535, inclusive. If the new value
       is outside these limits, it is forced to the appropriate limit value.

       Except when it is zero, the reference count is not correctly  preserved
       if  a  pattern  is  compiled on one host and then transferred to a host
       whose byte-order is different. (This seems a highly unlikely scenario.)

MATCHING A PATTERN: THE TRADITIONAL FUNCTION

       int pcre_exec(const pcre *code, const pcre_extra *extra,
	    const char *subject, int length, int startoffset,
	    int options, int *ovector, int ovecsize);

       The  function pcre_exec() is called to match a subject string against a
       compiled pattern, which is passed in the code argument. If the  pattern
       has been studied, the result of the study should be passed in the extra
       argument. This function is the main matching facility of  the  library,
       and it operates in a Perl-like manner. For specialist use there is also
       an alternative matching function, which is described below in the  sec-
       tion about the pcre_dfa_exec() function.

       In  most applications, the pattern will have been compiled (and option-
       ally studied) in the same process that calls pcre_exec().  However,  it
       is possible to save compiled patterns and study data, and then use them
       later in different processes, possibly even on different hosts.	For  a
       discussion about this, see the pcreprecompile documentation.

       Here is an example of a simple call to pcre_exec():

	 int rc;
	 int ovector[30];
	 rc = pcre_exec(
	   re,		   /* result of pcre_compile() */
	   NULL,	   /* we didn't study the pattern */
	   "some string",  /* the subject string */
	   11,		   /* the length of the subject string */
	   0,		   /* start at offset 0 in the subject */
	   0,		   /* default options */
	   ovector,	   /* vector of integers for substring information */
	   30); 	   /* number of elements (NOT size in bytes) */

   Extra data for pcre_exec()

       If  the	extra argument is not NULL, it must point to a pcre_extra data
       block. The pcre_study() function returns such a block (when it  doesn't
       return  NULL), but you can also create one for yourself, and pass addi-
       tional information in it. The pcre_extra block contains	the  following
       fields (not necessarily in this order):

	 unsigned long int flags;
	 void *study_data;
	 unsigned long int match_limit;
	 unsigned long int match_limit_recursion;
	 void *callout_data;
	 const unsigned char *tables;

       The  flags  field  is a bitmap that specifies which of the other fields
       are set. The flag bits are:

	 PCRE_EXTRA_STUDY_DATA
	 PCRE_EXTRA_MATCH_LIMIT
	 PCRE_EXTRA_MATCH_LIMIT_RECURSION
	 PCRE_EXTRA_CALLOUT_DATA
	 PCRE_EXTRA_TABLES

       Other flag bits should be set to zero. The study_data field is  set  in
       the  pcre_extra	block  that is returned by pcre_study(), together with
       the appropriate flag bit. You should not set this yourself, but you may
       add  to	the  block by setting the other fields and their corresponding
       flag bits.

       The match_limit field provides a means of preventing PCRE from using up
       a  vast amount of resources when running patterns that are not going to
       match, but which have a very large number  of  possibilities  in  their
       search  trees.  The  classic  example  is  the  use of nested unlimited
       repeats.

       Internally, PCRE uses a function called match() which it calls  repeat-
       edly  (sometimes  recursively). The limit set by match_limit is imposed
       on the number of times this function is called during  a  match,  which
       has  the  effect  of  limiting the amount of backtracking that can take
       place. For patterns that are not anchored, the count restarts from zero
       for each position in the subject string.

       The  default  value  for  the  limit can be set when PCRE is built; the
       default default is 10 million, which handles all but the  most  extreme
       cases.  You  can  override  the	default by suppling pcre_exec() with a
       pcre_extra    block    in    which    match_limit    is	  set,	   and
       PCRE_EXTRA_MATCH_LIMIT  is  set	in  the  flags	field. If the limit is
       exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT.

       The match_limit_recursion field is similar to match_limit, but  instead
       of limiting the total number of times that match() is called, it limits
       the depth of recursion. The recursion depth is a  smaller  number  than
       the  total number of calls, because not all calls to match() are recur-
       sive.  This limit is of use only if it is set smaller than match_limit.

       Limiting  the  recursion  depth	limits the amount of stack that can be
       used, or, when PCRE has been compiled to use memory on the heap instead
       of the stack, the amount of heap memory that can be used.

       The  default  value  for  match_limit_recursion can be set when PCRE is
       built; the default default  is  the  same  value  as  the  default  for
       match_limit.  You can override the default by suppling pcre_exec() with
       a  pcre_extra  block  in  which	match_limit_recursion  is   set,   and
       PCRE_EXTRA_MATCH_LIMIT_RECURSION  is  set  in  the  flags field. If the
       limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT.

       The pcre_callout field is used in conjunction with the  "callout"  fea-
       ture, which is described in the pcrecallout documentation.

       The  tables  field  is  used  to  pass  a  character  tables pointer to
       pcre_exec(); this overrides the value that is stored with the  compiled
       pattern.  A  non-NULL value is stored with the compiled pattern only if
       custom tables were supplied to pcre_compile() via  its  tableptr  argu-
       ment.  If NULL is passed to pcre_exec() using this mechanism, it forces
       PCRE's internal tables to be used. This facility is  helpful  when  re-
       using  patterns	that  have been saved after compiling with an external
       set of tables, because the external tables  might  be  at  a  different
       address	when  pcre_exec() is called. See the pcreprecompile documenta-
       tion for a discussion of saving compiled patterns for later use.

   Option bits for pcre_exec()

       The unused bits of the options argument for pcre_exec() must  be  zero.
       The   only  bits  that  may  be	set  are  PCRE_ANCHORED,  PCRE_NOTBOL,
       PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.

	 PCRE_ANCHORED

       The PCRE_ANCHORED option limits pcre_exec() to matching	at  the  first
       matching  position.  If	a  pattern was compiled with PCRE_ANCHORED, or
       turned out to be anchored by virtue of its contents, it cannot be  made
       unachored at matching time.

	 PCRE_NOTBOL

       This option specifies that first character of the subject string is not
       the beginning of a line, so the	circumflex  metacharacter  should  not
       match  before it. Setting this without PCRE_MULTILINE (at compile time)
       causes circumflex never to match. This option affects only  the	behav-
       iour of the circumflex metacharacter. It does not affect \A.

	 PCRE_NOTEOL

       This option specifies that the end of the subject string is not the end
       of a line, so the dollar metacharacter should not match it nor  (except
       in  multiline mode) a newline immediately before it. Setting this with-
       out PCRE_MULTILINE (at compile time) causes dollar never to match. This
       option  affects only the behaviour of the dollar metacharacter. It does
       not affect \Z or \z.

	 PCRE_NOTEMPTY

       An empty string is not considered to be a valid match if this option is
       set.  If  there are alternatives in the pattern, they are tried. If all
       the alternatives match the empty string, the entire  match  fails.  For
       example, if the pattern

	 a?b?

       is  applied  to	a string not beginning with "a" or "b", it matches the
       empty string at the start of the subject. With PCRE_NOTEMPTY set,  this
       match is not valid, so PCRE searches further into the string for occur-
       rences of "a" or "b".

       Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe-
       cial  case  of  a  pattern match of the empty string within its split()
       function, and when using the /g modifier. It  is  possible  to  emulate
       Perl's behaviour after matching a null string by first trying the match
       again at the same offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then
       if  that  fails by advancing the starting offset (see below) and trying
       an ordinary match again. There is some code that demonstrates how to do
       this in the pcredemo.c sample program.

	 PCRE_NO_UTF8_CHECK

       When PCRE_UTF8 is set at compile time, the validity of the subject as a
       UTF-8 string is automatically checked when pcre_exec() is  subsequently
       called.	 The  value  of  startoffset is also checked to ensure that it
       points to the start of a UTF-8 character. If an invalid UTF-8  sequence
       of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8. If
       startoffset contains an	invalid  value,  PCRE_ERROR_BADUTF8_OFFSET  is
       returned.

       If  you	already  know that your subject is valid, and you want to skip
       these   checks	for   performance   reasons,   you   can    set    the
       PCRE_NO_UTF8_CHECK  option  when calling pcre_exec(). You might want to
       do this for the second and subsequent calls to pcre_exec() if  you  are
       making  repeated  calls	to  find  all  the matches in a single subject
       string. However, you should be  sure  that  the	value  of  startoffset
       points  to  the	start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is
       set, the effect of passing an invalid UTF-8 string as a subject,  or  a
       value  of startoffset that does not point to the start of a UTF-8 char-
       acter, is undefined. Your program may crash.

	 PCRE_PARTIAL

       This option turns on the  partial  matching  feature.  If  the  subject
       string  fails to match the pattern, but at some point during the match-
       ing process the end of the subject was reached (that  is,  the  subject
       partially  matches  the	pattern and the failure to match occurred only
       because there were not enough subject characters), pcre_exec()  returns
       PCRE_ERROR_PARTIAL  instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is
       used, there are restrictions on what may appear in the  pattern.  These
       are discussed in the pcrepartial documentation.

   The string to be matched by pcre_exec()

       The  subject string is passed to pcre_exec() as a pointer in subject, a
       length in length, and a starting byte offset in startoffset.  In  UTF-8
       mode,  the  byte  offset  must point to the start of a UTF-8 character.
       Unlike the pattern string, the subject may contain binary  zero	bytes.
       When  the starting offset is zero, the search for a match starts at the
       beginning of the subject, and this is by far the most common case.

       A non-zero starting offset is useful when searching for	another  match
       in  the same subject by calling pcre_exec() again after a previous suc-
       cess.  Setting startoffset differs from just passing over  a  shortened
       string  and  setting  PCRE_NOTBOL  in the case of a pattern that begins
       with any kind of lookbehind. For example, consider the pattern

	 \Biss\B

       which finds occurrences of "iss" in the middle of  words.  (\B  matches
       only  if  the  current position in the subject is not a word boundary.)
       When applied to the string "Mississipi" the first call  to  pcre_exec()
       finds  the  first  occurrence. If pcre_exec() is called again with just
       the remainder of the subject,  namely  "issipi",  it  does  not	match,
       because \B is always false at the start of the subject, which is deemed
       to be a word boundary. However, if pcre_exec()  is  passed  the	entire
       string again, but with startoffset set to 4, it finds the second occur-
       rence of "iss" because it is able to look behind the starting point  to
       discover that it is preceded by a letter.

       If  a  non-zero starting offset is passed when the pattern is anchored,
       one attempt to match at the given offset is made. This can only succeed
       if  the	pattern  does  not require the match to be at the start of the
       subject.

   How pcre_exec() returns captured substrings

       In general, a pattern matches a certain portion of the subject, and  in
       addition,  further  substrings  from  the  subject may be picked out by
       parts of the pattern. Following the usage  in  Jeffrey  Friedl's  book,
       this  is  called "capturing" in what follows, and the phrase "capturing
       subpattern" is used for a fragment of a pattern that picks out  a  sub-
       string.	PCRE  supports several other kinds of parenthesized subpattern
       that do not cause substrings to be captured.

       Captured substrings are returned to the caller via a vector of  integer
       offsets	whose  address is passed in ovector. The number of elements in
       the vector is passed in ovecsize, which must be a non-negative  number.
       Note: this argument is NOT the size of ovector in bytes.

       The  first  two-thirds of the vector is used to pass back captured sub-
       strings, each substring using a pair of integers. The  remaining  third
       of  the	vector is used as workspace by pcre_exec() while matching cap-
       turing subpatterns, and is not available for passing back  information.
       The  length passed in ovecsize should always be a multiple of three. If
       it is not, it is rounded down.

       When a match is successful, information about  captured	substrings  is
       returned  in  pairs  of integers, starting at the beginning of ovector,
       and continuing up to two-thirds of its length at the  most.  The  first
       element of a pair is set to the offset of the first character in a sub-
       string, and the second is set to the  offset  of  the  first  character
       after  the  end	of  a  substring. The first pair, ovector[0] and ovec-
       tor[1], identify the portion of	the  subject  string  matched  by  the
       entire  pattern.  The next pair is used for the first capturing subpat-
       tern, and so on. The value returned by pcre_exec()  is  the  number  of
       pairs  that  have  been set. If there are no capturing subpatterns, the
       return value from a successful match is 1,  indicating  that  just  the
       first pair of offsets has been set.

       Some  convenience  functions  are  provided for extracting the captured
       substrings as separate strings. These are described  in	the  following
       section.

       It  is  possible  for  an capturing subpattern number n+1 to match some
       part of the subject when subpattern n has not been  used  at  all.  For
       example, if the string "abc" is matched against the pattern (a|(z))(bc)
       subpatterns 1 and 3 are matched, but 2 is not. When this happens,  both
       offset values corresponding to the unused subpattern are set to -1.

       If a capturing subpattern is matched repeatedly, it is the last portion
       of the string that it matched that is returned.

       If the vector is too small to hold all the captured substring  offsets,
       it is used as far as possible (up to two-thirds of its length), and the
       function returns a value of zero. In particular, if the substring  off-
       sets are not of interest, pcre_exec() may be called with ovector passed
       as NULL and ovecsize as zero. However, if  the  pattern	contains  back
       references  and	the  ovector is not big enough to remember the related
       substrings, PCRE has to get additional memory for use during  matching.
       Thus it is usually advisable to supply an ovector.

       Note  that  pcre_info() can be used to find out how many capturing sub-
       patterns there are in a compiled pattern. The smallest size for ovector
       that  will  allow for n captured substrings, in addition to the offsets
       of the substring matched by the whole pattern, is (n+1)*3.

   Return values from pcre_exec()

       If pcre_exec() fails, it returns a negative number. The	following  are
       defined in the header file:

	 PCRE_ERROR_NOMATCH	   (-1)

       The subject string did not match the pattern.

	 PCRE_ERROR_NULL	   (-2)

       Either  code  or  subject  was  passed as NULL, or ovector was NULL and
       ovecsize was not zero.

	 PCRE_ERROR_BADOPTION	   (-3)

       An unrecognized bit was set in the options argument.

	 PCRE_ERROR_BADMAGIC	   (-4)

       PCRE stores a 4-byte "magic number" at the start of the compiled  code,
       to catch the case when it is passed a junk pointer and to detect when a
       pattern that was compiled in an environment of one endianness is run in
       an  environment	with the other endianness. This is the error that PCRE
       gives when the magic number is not present.

	 PCRE_ERROR_UNKNOWN_NODE   (-5)

       While running the pattern match, an unknown item was encountered in the
       compiled  pattern.  This  error	could be caused by a bug in PCRE or by
       overwriting of the compiled pattern.

	 PCRE_ERROR_NOMEMORY	   (-6)

       If a pattern contains back references, but the ovector that  is	passed
       to pcre_exec() is not big enough to remember the referenced substrings,
       PCRE gets a block of memory at the start of matching to	use  for  this
       purpose.  If the call via pcre_malloc() fails, this error is given. The
       memory is automatically freed at the end of matching.

	 PCRE_ERROR_NOSUBSTRING    (-7)

       This error is used by the pcre_copy_substring(),  pcre_get_substring(),
       and  pcre_get_substring_list()  functions  (see	below).  It  is  never
       returned by pcre_exec().

	 PCRE_ERROR_MATCHLIMIT	   (-8)

       The backtracking limit, as specified by	the  match_limit  field  in  a
       pcre_extra  structure  (or  defaulted) was reached. See the description
       above.

	 PCRE_ERROR_RECURSIONLIMIT (-21)

       The internal recursion limit, as specified by the match_limit_recursion
       field  in  a  pcre_extra  structure (or defaulted) was reached. See the
       description above.

	 PCRE_ERROR_CALLOUT	   (-9)

       This error is never generated by pcre_exec() itself. It is provided for
       use  by	callout functions that want to yield a distinctive error code.
       See the pcrecallout documentation for details.

	 PCRE_ERROR_BADUTF8	   (-10)

       A string that contains an invalid UTF-8 byte sequence was passed  as  a
       subject.

	 PCRE_ERROR_BADUTF8_OFFSET (-11)

       The UTF-8 byte sequence that was passed as a subject was valid, but the
       value of startoffset did not point to the beginning of a UTF-8  charac-
       ter.

	 PCRE_ERROR_PARTIAL	   (-12)

       The  subject  string did not match, but it did match partially. See the
       pcrepartial documentation for details of partial matching.

	 PCRE_ERROR_BADPARTIAL	   (-13)

       The PCRE_PARTIAL option was used with  a  compiled  pattern  containing
       items  that are not supported for partial matching. See the pcrepartial
       documentation for details of partial matching.

	 PCRE_ERROR_INTERNAL	   (-14)

       An unexpected internal error has occurred. This error could  be	caused
       by a bug in PCRE or by overwriting of the compiled pattern.

	 PCRE_ERROR_BADCOUNT	   (-15)

       This  error is given if the value of the ovecsize argument is negative.

EXTRACTING CAPTURED SUBSTRINGS BY NUMBER

       int pcre_copy_substring(const char *subject, int *ovector,
	    int stringcount, int stringnumber, char *buffer,
	    int buffersize);

       int pcre_get_substring(const char *subject, int *ovector,
	    int stringcount, int stringnumber,
	    const char **stringptr);

       int pcre_get_substring_list(const char *subject,
	    int *ovector, int stringcount, const char ***listptr);

       Captured substrings can be  accessed  directly  by  using  the  offsets
       returned  by  pcre_exec()  in  ovector.	For convenience, the functions
       pcre_copy_substring(),	 pcre_get_substring(),	  and	 pcre_get_sub-
       string_list()  are  provided for extracting captured substrings as new,
       separate, zero-terminated strings. These functions identify  substrings
       by  number.  The  next section describes functions for extracting named
       substrings. A substring	that  contains	a  binary  zero  is  correctly
       extracted  and  has  a further zero added on the end, but the result is
       not, of course, a C string.

       The first three arguments are the same for all  three  of  these  func-
       tions:  subject	is  the subject string that has just been successfully
       matched, ovector is a pointer to the vector of integer offsets that was
       passed to pcre_exec(), and stringcount is the number of substrings that
       were captured by the match, including the substring  that  matched  the
       entire regular expression. This is the value returned by pcre_exec() if
       it is greater than zero. If pcre_exec() returned zero, indicating  that
       it  ran out of space in ovector, the value passed as stringcount should
       be the number of elements in the vector divided by three.

       The functions pcre_copy_substring() and pcre_get_substring() extract  a
       single  substring,  whose  number  is given as stringnumber. A value of
       zero extracts the substring that matched the  entire  pattern,  whereas
       higher  values  extract	the  captured  substrings.  For pcre_copy_sub-
       string(), the string is placed in buffer,  whose  length  is  given  by
       buffersize,  while  for	pcre_get_substring()  a new block of memory is
       obtained via pcre_malloc, and its address is  returned  via  stringptr.
       The  yield  of  the function is the length of the string, not including
       the terminating zero, or one of

	 PCRE_ERROR_NOMEMORY	   (-6)

       The buffer was too small for pcre_copy_substring(), or the  attempt  to
       get memory failed for pcre_get_substring().

	 PCRE_ERROR_NOSUBSTRING    (-7)

       There is no substring whose number is stringnumber.

       The  pcre_get_substring_list()  function  extracts  all	available sub-
       strings and builds a list of pointers to them. All this is  done  in  a
       single block of memory that is obtained via pcre_malloc. The address of
       the memory block is returned via listptr, which is also	the  start  of
       the  list  of  string pointers. The end of the list is marked by a NULL
       pointer. The yield of the function is zero if all went well, or

	 PCRE_ERROR_NOMEMORY	   (-6)

       if the attempt to get the memory block failed.

       When any of these functions encounter a substring that is unset,  which
       can  happen  when  capturing subpattern number n+1 matches some part of
       the subject, but subpattern n has not been used at all, they return  an
       empty string. This can be distinguished from a genuine zero-length sub-
       string by inspecting the appropriate offset in ovector, which is  nega-
       tive for unset substrings.

       The  two convenience functions pcre_free_substring() and pcre_free_sub-
       string_list() can be used to free the memory  returned  by  a  previous
       call  of  pcre_get_substring()  or  pcre_get_substring_list(),  respec-
       tively. They do nothing more than  call	the  function  pointed	to  by
       pcre_free,  which  of course could be called directly from a C program.
       However, PCRE is used in some situations where it is linked via a  spe-
       cial  interface	to  another  programming  language  which  cannot  use
       pcre_free directly; it is for these cases that the functions  are  pro-
       vided.

EXTRACTING CAPTURED SUBSTRINGS BY NAME

       int pcre_get_stringnumber(const pcre *code,
	    const char *name);

       int pcre_copy_named_substring(const pcre *code,
	    const char *subject, int *ovector,
	    int stringcount, const char *stringname,
	    char *buffer, int buffersize);

       int pcre_get_named_substring(const pcre *code,
	    const char *subject, int *ovector,
	    int stringcount, const char *stringname,
	    const char **stringptr);

       To  extract a substring by name, you first have to find associated num-
       ber.  For example, for this pattern

	 (a+)b(?P\d+)...

       the number of the subpattern called "xxx" is 2. You can find the number
       from the name by calling pcre_get_stringnumber(). The first argument is
       the compiled pattern, and the second is the  name.  The	yield  of  the
       function  is  the  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if
       there is no subpattern of that name.

       Given the number, you can extract the substring directly, or use one of
       the functions described in the previous section. For convenience, there
       are also two functions that do the whole job.

       Most   of   the	 arguments    of    pcre_copy_named_substring()    and
       pcre_get_named_substring()  are	the  same  as  those for the similarly
       named functions that extract by number. As these are described  in  the
       previous  section,  they  are not re-described here. There are just two
       differences:

       First, instead of a substring number, a substring name is  given.  Sec-
       ond, there is an extra argument, given at the start, which is a pointer
       to the compiled pattern. This is needed in order to gain access to  the
       name-to-number translation table.

       These  functions call pcre_get_stringnumber(), and if it succeeds, they
       then call pcre_copy_substring() or pcre_get_substring(),  as  appropri-
       ate.

FINDING ALL POSSIBLE MATCHES

       The  traditional  matching  function  uses a similar algorithm to Perl,
       which stops when it finds the first match, starting at a given point in
       the  subject.  If you want to find all possible matches, or the longest
       possible match, consider using the alternative matching	function  (see
       below)  instead.  If you cannot use the alternative function, but still
       need to find all possible matches, you can kludge it up by  making  use
       of the callout facility, which is described in the pcrecallout documen-
       tation.

       What you have to do is to insert a callout right at the end of the pat-
       tern.   When your callout function is called, extract and save the cur-
       rent matched substring. Then return  1,	which  forces  pcre_exec()  to
       backtrack  and  try other alternatives. Ultimately, when it runs out of
       matches, pcre_exec() will yield PCRE_ERROR_NOMATCH.

MATCHING A PATTERN: THE ALTERNATIVE FUNCTION

       int pcre_dfa_exec(const pcre *code, const pcre_extra *extra,
	    const char *subject, int length, int startoffset,
	    int options, int *ovector, int ovecsize,
	    int *workspace, int wscount);

       The function pcre_dfa_exec()  is  called  to  match  a  subject	string
       against	a compiled pattern, using a "DFA" matching algorithm. This has
       different characteristics to the normal algorithm, and is not  compati-
       ble with Perl. Some of the features of PCRE patterns are not supported.
       Nevertheless, there are times when this kind of matching can be useful.
       For  a  discussion of the two matching algorithms, see the pcrematching
       documentation.

       The arguments for the pcre_dfa_exec() function  are  the  same  as  for
       pcre_exec(), plus two extras. The ovector argument is used in a differ-
       ent way, and this is described below. The other	common	arguments  are
       used  in  the  same way as for pcre_exec(), so their description is not
       repeated here.

       The two additional arguments provide workspace for  the	function.  The
       workspace  vector  should  contain at least 20 elements. It is used for
       keeping	track  of  multiple  paths  through  the  pattern  tree.  More
       workspace  will	be  needed for patterns and subjects where there are a
       lot of possible matches.

       Here is an example of a simple call to pcre_dfa_exec():

	 int rc;
	 int ovector[10];
	 int wspace[20];
	 rc = pcre_dfa_exec(
	   re,		   /* result of pcre_compile() */
	   NULL,	   /* we didn't study the pattern */
	   "some string",  /* the subject string */
	   11,		   /* the length of the subject string */
	   0,		   /* start at offset 0 in the subject */
	   0,		   /* default options */
	   ovector,	   /* vector of integers for substring information */
	   10,		   /* number of elements (NOT size in bytes) */
	   wspace,	   /* working space vector */
	   20); 	   /* number of elements (NOT size in bytes) */

   Option bits for pcre_dfa_exec()

       The unused bits of the options argument	for  pcre_dfa_exec()  must  be
       zero.  The  only  bits  that may be set are PCRE_ANCHORED, PCRE_NOTBOL,
       PCRE_NOTEOL,    PCRE_NOTEMPTY,	 PCRE_NO_UTF8_CHECK,	 PCRE_PARTIAL,
       PCRE_DFA_SHORTEST,  and	PCRE_DFA_RESTART.  All	but  the last three of
       these are the same as for pcre_exec(),  so  their  description  is  not
       repeated here.

	 PCRE_PARTIAL

       This  has  the  same general effect as it does for pcre_exec(), but the
       details	are  slightly  different.  When  PCRE_PARTIAL	is   set   for
       pcre_dfa_exec(),  the  return code PCRE_ERROR_NOMATCH is converted into
       PCRE_ERROR_PARTIAL if the end of the subject  is  reached,  there  have
       been no complete matches, but there is still at least one matching pos-
       sibility. The portion of the string that provided the partial match  is
       set as the first matching string.

	 PCRE_DFA_SHORTEST

       Setting	the  PCRE_DFA_SHORTEST option causes the matching algorithm to
       stop as soon as it has found one match. Because	of  the  way  the  DFA
       algorithm works, this is necessarily the shortest possible match at the
       first possible matching point in the subject string.

	 PCRE_DFA_RESTART

       When pcre_dfa_exec()  is  called  with  the  PCRE_PARTIAL  option,  and
       returns	a  partial  match, it is possible to call it again, with addi-
       tional subject characters, and have it continue with  the  same	match.
       The  PCRE_DFA_RESTART  option requests this action; when it is set, the
       workspace and wscount options must reference the same vector as	before
       because	data  about  the  match so far is left in them after a partial
       match. There is more discussion of this	facility  in  the  pcrepartial
       documentation.

   Successful returns from pcre_dfa_exec()

       When  pcre_dfa_exec()  succeeds, it may have matched more than one sub-
       string in the subject. Note, however, that all the matches from one run
       of  the	function  start  at the same point in the subject. The shorter
       matches are all initial substrings of the longer matches. For  example,
       if the pattern

	 <.*>

       is matched against the string

	 This is    no more

       the three matched strings are

	 
	  
	   

       On  success,  the  yield of the function is a number greater than zero,
       which is the number of matched substrings.  The	substrings  themselves
       are  returned  in  ovector. Each string uses two elements; the first is
       the offset to the start, and the second is the offset to the  end.  All
       the strings have the same start offset. (Space could have been saved by
       giving this only once, but it was decided to retain some  compatibility
       with  the  way pcre_exec() returns data, even though the meaning of the
       strings is different.)

       The strings are returned in reverse order of length; that is, the long-
       est  matching  string is given first. If there were too many matches to
       fit into ovector, the yield of the function is zero, and the vector  is
       filled with the longest matches.

   Error returns from pcre_dfa_exec()

       The  pcre_dfa_exec()  function returns a negative number when it fails.
       Many of the errors are the same	as  for  pcre_exec(),  and  these  are
       described  above.   There are in addition the following errors that are
       specific to pcre_dfa_exec():

	 PCRE_ERROR_DFA_UITEM	   (-16)

       This return is given if pcre_dfa_exec() encounters an item in the  pat-
       tern  that  it  does not support, for instance, the use of \C or a back
       reference.

	 PCRE_ERROR_DFA_UCOND	   (-17)

       This return is given if pcre_dfa_exec() encounters a condition item  in
       a  pattern  that  uses  a back reference for the condition. This is not
       supported.

	 PCRE_ERROR_DFA_UMLIMIT    (-18)

       This return is given if pcre_dfa_exec() is called with an  extra  block
       that contains a setting of the match_limit field. This is not supported
       (it is meaningless).

	 PCRE_ERROR_DFA_WSSIZE	   (-19)

       This return is given if	pcre_dfa_exec()  runs  out  of	space  in  the
       workspace vector.

	 PCRE_ERROR_DFA_RECURSE    (-20)

       When  a	recursive subpattern is processed, the matching function calls
       itself recursively, using private vectors for  ovector  and  workspace.
       This  error  is	given  if  the output vector is not large enough. This
       should be extremely rare, as a vector of size 1000 is used.

Last updated: 18 January 2006
Copyright (c) 1997-2006 University of Cambridge.



								    PCREAPI(3)
=11688
+149
(75)